From a62e90308f7b6965310cf4ec61393aef6861f50d Mon Sep 17 00:00:00 2001 From: wanzongshun Date: Thu, 31 Dec 2009 15:06:05 +0100 Subject: ARM: 5859/1: Add nuc93x platform support The previous nuc932 support patches have been discarded by me and because it belongs to another SoCs series named nuc93x,at present, which included nuc931 and nuc932, I think it is better to create a new mach-nuc93x,So I made the patch,and request your advice.Thanks! Signed-off-by: Wan ZongShun Signed-off-by: Russell King --- arch/arm/Kconfig | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'arch/arm/Kconfig') diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 233a222752c0..79251a9cfb6f 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -548,6 +548,15 @@ config ARCH_W90X900 +config ARCH_NUC93X + bool "Nuvoton NUC93X CPU" + select CPU_ARM926T + select HAVE_CLK + select COMMON_CLKDEV + help + Support for Nuvoton (Winbond logic dept.) NUC93X MCU,The NUC93X is a + low-power and high performance MPEG-4/JPEG multimedia controller chip. + config ARCH_PNX4008 bool "Philips Nexperia PNX4008 Mobile" select CPU_ARM926T @@ -828,6 +837,8 @@ source "arch/arm/mach-u300/Kconfig" source "arch/arm/mach-w90x900/Kconfig" +source "arch/arm/mach-nuc93x/Kconfig" + source "arch/arm/mach-bcmring/Kconfig" source "arch/arm/mach-ux500/Kconfig" -- cgit v1.2.3 From d91a8910d9585950706536a643ece51b67c695ec Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 4 Feb 2010 18:13:17 +0000 Subject: ARM: Fix badly placed nuc932 Kconfig entry Signed-off-by: Russell King --- arch/arm/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/arm/Kconfig') diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 79251a9cfb6f..8e6672acb9c9 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -766,6 +766,8 @@ source "arch/arm/plat-pxa/Kconfig" source "arch/arm/mach-mmp/Kconfig" +source "arch/arm/mach-nuc93x/Kconfig" + source "arch/arm/mach-sa1100/Kconfig" source "arch/arm/plat-omap/Kconfig" @@ -837,8 +839,6 @@ source "arch/arm/mach-u300/Kconfig" source "arch/arm/mach-w90x900/Kconfig" -source "arch/arm/mach-nuc93x/Kconfig" - source "arch/arm/mach-bcmring/Kconfig" source "arch/arm/mach-ux500/Kconfig" -- cgit v1.2.3 From 0f4f0672ac950c96cffaf84a666d35e817d7c3ca Mon Sep 17 00:00:00 2001 From: Jamie Iles Date: Tue, 2 Feb 2010 20:23:15 +0100 Subject: ARM: 5899/2: arm: provide a mechanism to reserve performance counters To add support for perf events and to allow the hardware counters to be shared with oprofile, we need a way to reserve access to the pmu (performance monitor unit). Platforms with PMU interrupts should register the interrupts in arch/arm/kernel/pmu.c Signed-off-by: Jamie Iles Signed-off-by: Russell King --- arch/arm/Kconfig | 5 +++ arch/arm/include/asm/pmu.h | 75 +++++++++++++++++++++++++++++++++ arch/arm/kernel/Makefile | 1 + arch/arm/kernel/pmu.c | 103 +++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 184 insertions(+) create mode 100644 arch/arm/include/asm/pmu.h create mode 100644 arch/arm/kernel/pmu.c (limited to 'arch/arm/Kconfig') diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 233a222752c0..9e08891062bf 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -863,6 +863,11 @@ config XSCALE_PMU depends on CPU_XSCALE && !XSCALE_PMU_TIMER default y +config CPU_HAS_PMU + depends on CPU_V6 || CPU_V7 || XSCALE_PMU + default y + bool + if !MMU source "arch/arm/Kconfig-nommu" endif diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h new file mode 100644 index 000000000000..2829b9f981a1 --- /dev/null +++ b/arch/arm/include/asm/pmu.h @@ -0,0 +1,75 @@ +/* + * linux/arch/arm/include/asm/pmu.h + * + * Copyright (C) 2009 picoChip Designs Ltd, Jamie Iles + * + * 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. + * + */ + +#ifndef __ARM_PMU_H__ +#define __ARM_PMU_H__ + +#ifdef CONFIG_CPU_HAS_PMU + +struct pmu_irqs { + const int *irqs; + int num_irqs; +}; + +/** + * reserve_pmu() - reserve the hardware performance counters + * + * Reserve the hardware performance counters in the system for exclusive use. + * The 'struct pmu_irqs' for the system is returned on success, ERR_PTR() + * encoded error on failure. + */ +extern const struct pmu_irqs * +reserve_pmu(void); + +/** + * release_pmu() - Relinquish control of the performance counters + * + * Release the performance counters and allow someone else to use them. + * Callers must have disabled the counters and released IRQs before calling + * this. The 'struct pmu_irqs' returned from reserve_pmu() must be passed as + * a cookie. + */ +extern int +release_pmu(const struct pmu_irqs *irqs); + +/** + * init_pmu() - Initialise the PMU. + * + * Initialise the system ready for PMU enabling. This should typically set the + * IRQ affinity and nothing else. The users (oprofile/perf events etc) will do + * the actual hardware initialisation. + */ +extern int +init_pmu(void); + +#else /* CONFIG_CPU_HAS_PMU */ + +static inline const struct pmu_irqs * +reserve_pmu(void) +{ + return ERR_PTR(-ENODEV); +} + +static inline int +release_pmu(const struct pmu_irqs *irqs) +{ + return -ENODEV; +} + +static inline int +init_pmu(void) +{ + return -ENODEV; +} + +#endif /* CONFIG_CPU_HAS_PMU */ + +#endif /* __ARM_PMU_H__ */ diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index dd00f747e2ad..216890d804c2 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -46,6 +46,7 @@ obj-$(CONFIG_CPU_XSCALE) += xscale-cp0.o obj-$(CONFIG_CPU_XSC3) += xscale-cp0.o obj-$(CONFIG_CPU_MOHAWK) += xscale-cp0.o obj-$(CONFIG_IWMMXT) += iwmmxt.o +obj-$(CONFIG_CPU_HAS_PMU) += pmu.o AFLAGS_iwmmxt.o := -Wa,-mcpu=iwmmxt ifneq ($(CONFIG_ARCH_EBSA110),y) diff --git a/arch/arm/kernel/pmu.c b/arch/arm/kernel/pmu.c new file mode 100644 index 000000000000..a124312e343f --- /dev/null +++ b/arch/arm/kernel/pmu.c @@ -0,0 +1,103 @@ +/* + * linux/arch/arm/kernel/pmu.c + * + * Copyright (C) 2009 picoChip Designs Ltd, Jamie Iles + * + * 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 + +/* + * Define the IRQs for the system. We could use something like a platform + * device but that seems fairly heavyweight for this. Also, the performance + * counters can't be removed or hotplugged. + * + * Ordering is important: init_pmu() will use the ordering to set the affinity + * to the corresponding core. e.g. the first interrupt will go to cpu 0, the + * second goes to cpu 1 etc. + */ +static const int irqs[] = { +#if defined(CONFIG_ARCH_OMAP2) + 3, +#elif defined(CONFIG_ARCH_BCMRING) + IRQ_PMUIRQ, +#elif defined(CONFIG_MACH_REALVIEW_EB) + IRQ_EB11MP_PMU_CPU0, + IRQ_EB11MP_PMU_CPU1, + IRQ_EB11MP_PMU_CPU2, + IRQ_EB11MP_PMU_CPU3, +#elif defined(CONFIG_ARCH_OMAP3) + INT_34XX_BENCH_MPU_EMUL, +#elif defined(CONFIG_ARCH_IOP32X) + IRQ_IOP32X_CORE_PMU, +#elif defined(CONFIG_ARCH_IOP33X) + IRQ_IOP33X_CORE_PMU, +#elif defined(CONFIG_ARCH_PXA) + IRQ_PMU, +#endif +}; + +static const struct pmu_irqs pmu_irqs = { + .irqs = irqs, + .num_irqs = ARRAY_SIZE(irqs), +}; + +static volatile long pmu_lock; + +const struct pmu_irqs * +reserve_pmu(void) +{ + return test_and_set_bit_lock(0, &pmu_lock) ? ERR_PTR(-EBUSY) : + &pmu_irqs; +} +EXPORT_SYMBOL_GPL(reserve_pmu); + +int +release_pmu(const struct pmu_irqs *irqs) +{ + if (WARN_ON(irqs != &pmu_irqs)) + return -EINVAL; + clear_bit_unlock(0, &pmu_lock); + return 0; +} +EXPORT_SYMBOL_GPL(release_pmu); + +static int +set_irq_affinity(int irq, + unsigned int cpu) +{ +#ifdef CONFIG_SMP + int err = irq_set_affinity(irq, cpumask_of(cpu)); + if (err) + pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n", + irq, cpu); + return err; +#else + return 0; +#endif +} + +int +init_pmu(void) +{ + int i, err = 0; + + for (i = 0; i < pmu_irqs.num_irqs; ++i) { + err = set_irq_affinity(pmu_irqs.irqs[i], i); + if (err) + break; + } + + return err; +} +EXPORT_SYMBOL_GPL(init_pmu); -- cgit v1.2.3 From 7ada189f5c8627662c23f49b3e68463f86fc511e Mon Sep 17 00:00:00 2001 From: Jamie Iles Date: Tue, 2 Feb 2010 20:24:58 +0100 Subject: ARM: 5900/2: arm: enable support for software perf events The perf events subsystem allows counting of both hardware and software events. This patch implements the bare minimum for software performance events. Cc: Peter Zijlstra Cc: Ingo Molnar Signed-off-by: Jamie Iles Signed-off-by: Russell King --- arch/arm/Kconfig | 2 ++ arch/arm/include/asm/perf_event.h | 31 +++++++++++++++++++++++++++++++ arch/arm/mm/fault.c | 7 +++++++ 3 files changed, 40 insertions(+) create mode 100644 arch/arm/include/asm/perf_event.h (limited to 'arch/arm/Kconfig') diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 9e08891062bf..74d1e767f0b7 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -18,6 +18,8 @@ config ARM select HAVE_KRETPROBES if (HAVE_KPROBES) select HAVE_FUNCTION_TRACER if (!XIP_KERNEL) select HAVE_GENERIC_DMA_COHERENT + select HAVE_PERF_EVENTS + select PERF_USE_VMALLOC help The ARM series is a line of low-power-consumption RISC chip designs licensed by ARM Ltd and targeted at embedded applications and diff --git a/arch/arm/include/asm/perf_event.h b/arch/arm/include/asm/perf_event.h new file mode 100644 index 000000000000..49e3049aba32 --- /dev/null +++ b/arch/arm/include/asm/perf_event.h @@ -0,0 +1,31 @@ +/* + * linux/arch/arm/include/asm/perf_event.h + * + * Copyright (C) 2009 picoChip Designs Ltd, Jamie Iles + * + * 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. + * + */ + +#ifndef __ARM_PERF_EVENT_H__ +#define __ARM_PERF_EVENT_H__ + +/* + * NOP: on *most* (read: all supported) ARM platforms, the performance + * counter interrupts are regular interrupts and not an NMI. This + * means that when we receive the interrupt we can call + * perf_event_do_pending() that handles all of the work with + * interrupts enabled. + */ +static inline void +set_perf_event_pending(void) +{ +} + +/* ARM performance counters start from 1 (in the cp15 accesses) so use the + * same indexes here for consistency. */ +#define PERF_EVENT_INDEX_OFFSET 1 + +#endif /* __ARM_PERF_EVENT_H__ */ diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 10e06801afb3..9d40c341e07e 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -302,6 +303,12 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) fault = __do_page_fault(mm, addr, fsr, tsk); up_read(&mm->mmap_sem); + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, addr); + if (fault & VM_FAULT_MAJOR) + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0, regs, addr); + else if (fault & VM_FAULT_MINOR) + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0, regs, addr); + /* * Handle the "normal" case first - VM_FAULT_MAJOR / VM_FAULT_MINOR */ -- cgit v1.2.3 From 1b8873a0c6ec511870c106c80b94658f857c47f2 Mon Sep 17 00:00:00 2001 From: Jamie Iles Date: Tue, 2 Feb 2010 20:25:44 +0100 Subject: ARM: 5902/4: arm/perfevents: implement perf event support for ARMv6 This patch implements support for ARMv6 performance counters in the Linux performance events subsystem. ARMv6 architectures that have the performance counters should enable HW_PERF_EVENTS to get hardware performance events support in addition to the software events. Note: only ARM Ltd ARM cores are supported. This implementation also provides an ARM PMU abstraction layer to allow ARMv7 and others to be supported in the future by adding new a 'struct arm_pmu'. Cc: Jean Pihet Cc: Will Deacon Signed-off-by: Jamie Iles Signed-off-by: Russell King --- arch/arm/Kconfig | 8 + arch/arm/kernel/Makefile | 1 + arch/arm/kernel/perf_event.c | 1348 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 1357 insertions(+) create mode 100644 arch/arm/kernel/perf_event.c (limited to 'arch/arm/Kconfig') diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 74d1e767f0b7..9fb91ce106bc 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1174,6 +1174,14 @@ config HIGHPTE depends on HIGHMEM depends on !OUTER_CACHE +config HW_PERF_EVENTS + bool "Enable hardware performance counter support for perf events" + depends on PERF_EVENTS && CPU_HAS_PMU && CPU_V6 + default y + help + Enable hardware performance counter support for perf events. If + disabled, perf events will use software events only. + source "mm/Kconfig" config LEDS diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index 216890d804c2..c76e6d2679b8 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -47,6 +47,7 @@ obj-$(CONFIG_CPU_XSC3) += xscale-cp0.o obj-$(CONFIG_CPU_MOHAWK) += xscale-cp0.o obj-$(CONFIG_IWMMXT) += iwmmxt.o obj-$(CONFIG_CPU_HAS_PMU) += pmu.o +obj-$(CONFIG_HW_PERF_EVENTS) += perf_event.o AFLAGS_iwmmxt.o := -Wa,-mcpu=iwmmxt ifneq ($(CONFIG_ARCH_EBSA110),y) diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c new file mode 100644 index 000000000000..7b1022b9aa52 --- /dev/null +++ b/arch/arm/kernel/perf_event.c @@ -0,0 +1,1348 @@ +#undef DEBUG + +/* + * ARM performance counter support. + * + * Copyright (C) 2009 picoChip Designs, Ltd., Jamie Iles + * + * This code is based on the sparc64 perf event code, which is in turn based + * on the x86 code. Callchain code is based on the ARM OProfile backtrace + * code. + */ +#define pr_fmt(fmt) "hw perfevents: " fmt + +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +static const struct pmu_irqs *pmu_irqs; + +/* + * Hardware lock to serialize accesses to PMU registers. Needed for the + * read/modify/write sequences. + */ +DEFINE_SPINLOCK(pmu_lock); + +/* + * ARMv6 supports a maximum of 3 events, starting from index 1. If we add + * another platform that supports more, we need to increase this to be the + * largest of all platforms. + */ +#define ARMPMU_MAX_HWEVENTS 4 + +/* The events for a given CPU. */ +struct cpu_hw_events { + /* + * The events that are active on the CPU for the given index. Index 0 + * is reserved. + */ + struct perf_event *events[ARMPMU_MAX_HWEVENTS]; + + /* + * A 1 bit for an index indicates that the counter is being used for + * an event. A 0 means that the counter can be used. + */ + unsigned long used_mask[BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)]; + + /* + * A 1 bit for an index indicates that the counter is actively being + * used. + */ + unsigned long active_mask[BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)]; +}; +DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events); + +struct arm_pmu { + const char *name; + irqreturn_t (*handle_irq)(int irq_num, void *dev); + void (*enable)(struct hw_perf_event *evt, int idx); + void (*disable)(struct hw_perf_event *evt, int idx); + int (*event_map)(int evt); + u64 (*raw_event)(u64); + int (*get_event_idx)(struct cpu_hw_events *cpuc, + struct hw_perf_event *hwc); + u32 (*read_counter)(int idx); + void (*write_counter)(int idx, u32 val); + void (*start)(void); + void (*stop)(void); + int num_events; + u64 max_period; +}; + +/* Set at runtime when we know what CPU type we are. */ +static const struct arm_pmu *armpmu; + +#define HW_OP_UNSUPPORTED 0xFFFF + +#define C(_x) \ + PERF_COUNT_HW_CACHE_##_x + +#define CACHE_OP_UNSUPPORTED 0xFFFF + +static unsigned armpmu_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX]; + +static int +armpmu_map_cache_event(u64 config) +{ + unsigned int cache_type, cache_op, cache_result, ret; + + cache_type = (config >> 0) & 0xff; + if (cache_type >= PERF_COUNT_HW_CACHE_MAX) + return -EINVAL; + + cache_op = (config >> 8) & 0xff; + if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX) + return -EINVAL; + + cache_result = (config >> 16) & 0xff; + if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX) + return -EINVAL; + + ret = (int)armpmu_perf_cache_map[cache_type][cache_op][cache_result]; + + if (ret == CACHE_OP_UNSUPPORTED) + return -ENOENT; + + return ret; +} + +static int +armpmu_event_set_period(struct perf_event *event, + struct hw_perf_event *hwc, + int idx) +{ + s64 left = atomic64_read(&hwc->period_left); + s64 period = hwc->sample_period; + int ret = 0; + + if (unlikely(left <= -period)) { + left = period; + atomic64_set(&hwc->period_left, left); + hwc->last_period = period; + ret = 1; + } + + if (unlikely(left <= 0)) { + left += period; + atomic64_set(&hwc->period_left, left); + hwc->last_period = period; + ret = 1; + } + + if (left > (s64)armpmu->max_period) + left = armpmu->max_period; + + atomic64_set(&hwc->prev_count, (u64)-left); + + armpmu->write_counter(idx, (u64)(-left) & 0xffffffff); + + perf_event_update_userpage(event); + + return ret; +} + +static u64 +armpmu_event_update(struct perf_event *event, + struct hw_perf_event *hwc, + int idx) +{ + int shift = 64 - 32; + s64 prev_raw_count, new_raw_count; + s64 delta; + +again: + prev_raw_count = atomic64_read(&hwc->prev_count); + new_raw_count = armpmu->read_counter(idx); + + if (atomic64_cmpxchg(&hwc->prev_count, prev_raw_count, + new_raw_count) != prev_raw_count) + goto again; + + delta = (new_raw_count << shift) - (prev_raw_count << shift); + delta >>= shift; + + atomic64_add(delta, &event->count); + atomic64_sub(delta, &hwc->period_left); + + return new_raw_count; +} + +static void +armpmu_disable(struct perf_event *event) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + + WARN_ON(idx < 0); + + clear_bit(idx, cpuc->active_mask); + armpmu->disable(hwc, idx); + + barrier(); + + armpmu_event_update(event, hwc, idx); + cpuc->events[idx] = NULL; + clear_bit(idx, cpuc->used_mask); + + perf_event_update_userpage(event); +} + +static void +armpmu_read(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + /* Don't read disabled counters! */ + if (hwc->idx < 0) + return; + + armpmu_event_update(event, hwc, hwc->idx); +} + +static void +armpmu_unthrottle(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + /* + * Set the period again. Some counters can't be stopped, so when we + * were throttled we simply disabled the IRQ source and the counter + * may have been left counting. If we don't do this step then we may + * get an interrupt too soon or *way* too late if the overflow has + * happened since disabling. + */ + armpmu_event_set_period(event, hwc, hwc->idx); + armpmu->enable(hwc, hwc->idx); +} + +static int +armpmu_enable(struct perf_event *event) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct hw_perf_event *hwc = &event->hw; + int idx; + int err = 0; + + /* If we don't have a space for the counter then finish early. */ + idx = armpmu->get_event_idx(cpuc, hwc); + if (idx < 0) { + err = idx; + goto out; + } + + /* + * If there is an event in the counter we are going to use then make + * sure it is disabled. + */ + event->hw.idx = idx; + armpmu->disable(hwc, idx); + cpuc->events[idx] = event; + set_bit(idx, cpuc->active_mask); + + /* Set the period for the event. */ + armpmu_event_set_period(event, hwc, idx); + + /* Enable the event. */ + armpmu->enable(hwc, idx); + + /* Propagate our changes to the userspace mapping. */ + perf_event_update_userpage(event); + +out: + return err; +} + +static struct pmu pmu = { + .enable = armpmu_enable, + .disable = armpmu_disable, + .unthrottle = armpmu_unthrottle, + .read = armpmu_read, +}; + +static int +validate_event(struct cpu_hw_events *cpuc, + struct perf_event *event) +{ + struct hw_perf_event fake_event = event->hw; + + if (event->pmu && event->pmu != &pmu) + return 0; + + return armpmu->get_event_idx(cpuc, &fake_event) >= 0; +} + +static int +validate_group(struct perf_event *event) +{ + struct perf_event *sibling, *leader = event->group_leader; + struct cpu_hw_events fake_pmu; + + memset(&fake_pmu, 0, sizeof(fake_pmu)); + + if (!validate_event(&fake_pmu, leader)) + return -ENOSPC; + + list_for_each_entry(sibling, &leader->sibling_list, group_entry) { + if (!validate_event(&fake_pmu, sibling)) + return -ENOSPC; + } + + if (!validate_event(&fake_pmu, event)) + return -ENOSPC; + + return 0; +} + +static int +armpmu_reserve_hardware(void) +{ + int i; + int err; + + pmu_irqs = reserve_pmu(); + if (IS_ERR(pmu_irqs)) { + pr_warning("unable to reserve pmu\n"); + return PTR_ERR(pmu_irqs); + } + + init_pmu(); + + if (pmu_irqs->num_irqs < 1) { + pr_err("no irqs for PMUs defined\n"); + return -ENODEV; + } + + for (i = 0; i < pmu_irqs->num_irqs; ++i) { + err = request_irq(pmu_irqs->irqs[i], armpmu->handle_irq, + IRQF_DISABLED, "armpmu", NULL); + if (err) { + pr_warning("unable to request IRQ%d for ARM " + "perf counters\n", pmu_irqs->irqs[i]); + break; + } + } + + if (err) { + for (i = i - 1; i >= 0; --i) + free_irq(pmu_irqs->irqs[i], NULL); + release_pmu(pmu_irqs); + pmu_irqs = NULL; + } + + return err; +} + +static void +armpmu_release_hardware(void) +{ + int i; + + for (i = pmu_irqs->num_irqs - 1; i >= 0; --i) + free_irq(pmu_irqs->irqs[i], NULL); + armpmu->stop(); + + release_pmu(pmu_irqs); + pmu_irqs = NULL; +} + +static atomic_t active_events = ATOMIC_INIT(0); +static DEFINE_MUTEX(pmu_reserve_mutex); + +static void +hw_perf_event_destroy(struct perf_event *event) +{ + if (atomic_dec_and_mutex_lock(&active_events, &pmu_reserve_mutex)) { + armpmu_release_hardware(); + mutex_unlock(&pmu_reserve_mutex); + } +} + +static int +__hw_perf_event_init(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + int mapping, err; + + /* Decode the generic type into an ARM event identifier. */ + if (PERF_TYPE_HARDWARE == event->attr.type) { + mapping = armpmu->event_map(event->attr.config); + } else if (PERF_TYPE_HW_CACHE == event->attr.type) { + mapping = armpmu_map_cache_event(event->attr.config); + } else if (PERF_TYPE_RAW == event->attr.type) { + mapping = armpmu->raw_event(event->attr.config); + } else { + pr_debug("event type %x not supported\n", event->attr.type); + return -EOPNOTSUPP; + } + + if (mapping < 0) { + pr_debug("event %x:%llx not supported\n", event->attr.type, + event->attr.config); + return mapping; + } + + /* + * Check whether we need to exclude the counter from certain modes. + * The ARM performance counters are on all of the time so if someone + * has asked us for some excludes then we have to fail. + */ + if (event->attr.exclude_kernel || event->attr.exclude_user || + event->attr.exclude_hv || event->attr.exclude_idle) { + pr_debug("ARM performance counters do not support " + "mode exclusion\n"); + return -EPERM; + } + + /* + * We don't assign an index until we actually place the event onto + * hardware. Use -1 to signify that we haven't decided where to put it + * yet. For SMP systems, each core has it's own PMU so we can't do any + * clever allocation or constraints checking at this point. + */ + hwc->idx = -1; + + /* + * Store the event encoding into the config_base field. config and + * event_base are unused as the only 2 things we need to know are + * the event mapping and the counter to use. The counter to use is + * also the indx and the config_base is the event type. + */ + hwc->config_base = (unsigned long)mapping; + hwc->config = 0; + hwc->event_base = 0; + + if (!hwc->sample_period) { + hwc->sample_period = armpmu->max_period; + hwc->last_period = hwc->sample_period; + atomic64_set(&hwc->period_left, hwc->sample_period); + } + + err = 0; + if (event->group_leader != event) { + err = validate_group(event); + if (err) + return -EINVAL; + } + + return err; +} + +const struct pmu * +hw_perf_event_init(struct perf_event *event) +{ + int err = 0; + + if (!armpmu) + return ERR_PTR(-ENODEV); + + event->destroy = hw_perf_event_destroy; + + if (!atomic_inc_not_zero(&active_events)) { + if (atomic_read(&active_events) > perf_max_events) { + atomic_dec(&active_events); + return ERR_PTR(-ENOSPC); + } + + mutex_lock(&pmu_reserve_mutex); + if (atomic_read(&active_events) == 0) { + err = armpmu_reserve_hardware(); + } + + if (!err) + atomic_inc(&active_events); + mutex_unlock(&pmu_reserve_mutex); + } + + if (err) + return ERR_PTR(err); + + err = __hw_perf_event_init(event); + if (err) + hw_perf_event_destroy(event); + + return err ? ERR_PTR(err) : &pmu; +} + +void +hw_perf_enable(void) +{ + /* Enable all of the perf events on hardware. */ + int idx; + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + if (!armpmu) + return; + + for (idx = 0; idx <= armpmu->num_events; ++idx) { + struct perf_event *event = cpuc->events[idx]; + + if (!event) + continue; + + armpmu->enable(&event->hw, idx); + } + + armpmu->start(); +} + +void +hw_perf_disable(void) +{ + if (armpmu) + armpmu->stop(); +} + +/* + * ARMv6 Performance counter handling code. + * + * ARMv6 has 2 configurable performance counters and a single cycle counter. + * They all share a single reset bit but can be written to zero so we can use + * that for a reset. + * + * The counters can't be individually enabled or disabled so when we remove + * one event and replace it with another we could get spurious counts from the + * wrong event. However, we can take advantage of the fact that the + * performance counters can export events to the event bus, and the event bus + * itself can be monitored. This requires that we *don't* export the events to + * the event bus. The procedure for disabling a configurable counter is: + * - change the counter to count the ETMEXTOUT[0] signal (0x20). This + * effectively stops the counter from counting. + * - disable the counter's interrupt generation (each counter has it's + * own interrupt enable bit). + * Once stopped, the counter value can be written as 0 to reset. + * + * To enable a counter: + * - enable the counter's interrupt generation. + * - set the new event type. + * + * Note: the dedicated cycle counter only counts cycles and can't be + * enabled/disabled independently of the others. When we want to disable the + * cycle counter, we have to just disable the interrupt reporting and start + * ignoring that counter. When re-enabling, we have to reset the value and + * enable the interrupt. + */ + +enum armv6_perf_types { + ARMV6_PERFCTR_ICACHE_MISS = 0x0, + ARMV6_PERFCTR_IBUF_STALL = 0x1, + ARMV6_PERFCTR_DDEP_STALL = 0x2, + ARMV6_PERFCTR_ITLB_MISS = 0x3, + ARMV6_PERFCTR_DTLB_MISS = 0x4, + ARMV6_PERFCTR_BR_EXEC = 0x5, + ARMV6_PERFCTR_BR_MISPREDICT = 0x6, + ARMV6_PERFCTR_INSTR_EXEC = 0x7, + ARMV6_PERFCTR_DCACHE_HIT = 0x9, + ARMV6_PERFCTR_DCACHE_ACCESS = 0xA, + ARMV6_PERFCTR_DCACHE_MISS = 0xB, + ARMV6_PERFCTR_DCACHE_WBACK = 0xC, + ARMV6_PERFCTR_SW_PC_CHANGE = 0xD, + ARMV6_PERFCTR_MAIN_TLB_MISS = 0xF, + ARMV6_PERFCTR_EXPL_D_ACCESS = 0x10, + ARMV6_PERFCTR_LSU_FULL_STALL = 0x11, + ARMV6_PERFCTR_WBUF_DRAINED = 0x12, + ARMV6_PERFCTR_CPU_CYCLES = 0xFF, + ARMV6_PERFCTR_NOP = 0x20, +}; + +enum armv6_counters { + ARMV6_CYCLE_COUNTER = 1, + ARMV6_COUNTER0, + ARMV6_COUNTER1, +}; + +/* + * The hardware events that we support. We do support cache operations but + * we have harvard caches and no way to combine instruction and data + * accesses/misses in hardware. + */ +static const unsigned armv6_perf_map[PERF_COUNT_HW_MAX] = { + [PERF_COUNT_HW_CPU_CYCLES] = ARMV6_PERFCTR_CPU_CYCLES, + [PERF_COUNT_HW_INSTRUCTIONS] = ARMV6_PERFCTR_INSTR_EXEC, + [PERF_COUNT_HW_CACHE_REFERENCES] = HW_OP_UNSUPPORTED, + [PERF_COUNT_HW_CACHE_MISSES] = HW_OP_UNSUPPORTED, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV6_PERFCTR_BR_EXEC, + [PERF_COUNT_HW_BRANCH_MISSES] = ARMV6_PERFCTR_BR_MISPREDICT, + [PERF_COUNT_HW_BUS_CYCLES] = HW_OP_UNSUPPORTED, +}; + +static const unsigned armv6_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + [C(L1D)] = { + /* + * The performance counters don't differentiate between read + * and write accesses/misses so this isn't strictly correct, + * but it's the best we can do. Writes and reads get + * combined. + */ + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = ARMV6_PERFCTR_DCACHE_ACCESS, + [C(RESULT_MISS)] = ARMV6_PERFCTR_DCACHE_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = ARMV6_PERFCTR_DCACHE_ACCESS, + [C(RESULT_MISS)] = ARMV6_PERFCTR_DCACHE_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(L1I)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV6_PERFCTR_ICACHE_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV6_PERFCTR_ICACHE_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(DTLB)] = { + /* + * The ARM performance counters can count micro DTLB misses, + * micro ITLB misses and main TLB misses. There isn't an event + * for TLB misses, so use the micro misses here and if users + * want the main TLB misses they can use a raw counter. + */ + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV6_PERFCTR_DTLB_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV6_PERFCTR_DTLB_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(ITLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV6_PERFCTR_ITLB_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV6_PERFCTR_ITLB_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(BPU)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, +}; + +enum armv6mpcore_perf_types { + ARMV6MPCORE_PERFCTR_ICACHE_MISS = 0x0, + ARMV6MPCORE_PERFCTR_IBUF_STALL = 0x1, + ARMV6MPCORE_PERFCTR_DDEP_STALL = 0x2, + ARMV6MPCORE_PERFCTR_ITLB_MISS = 0x3, + ARMV6MPCORE_PERFCTR_DTLB_MISS = 0x4, + ARMV6MPCORE_PERFCTR_BR_EXEC = 0x5, + ARMV6MPCORE_PERFCTR_BR_NOTPREDICT = 0x6, + ARMV6MPCORE_PERFCTR_BR_MISPREDICT = 0x7, + ARMV6MPCORE_PERFCTR_INSTR_EXEC = 0x8, + ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS = 0xA, + ARMV6MPCORE_PERFCTR_DCACHE_RDMISS = 0xB, + ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS = 0xC, + ARMV6MPCORE_PERFCTR_DCACHE_WRMISS = 0xD, + ARMV6MPCORE_PERFCTR_DCACHE_EVICTION = 0xE, + ARMV6MPCORE_PERFCTR_SW_PC_CHANGE = 0xF, + ARMV6MPCORE_PERFCTR_MAIN_TLB_MISS = 0x10, + ARMV6MPCORE_PERFCTR_EXPL_MEM_ACCESS = 0x11, + ARMV6MPCORE_PERFCTR_LSU_FULL_STALL = 0x12, + ARMV6MPCORE_PERFCTR_WBUF_DRAINED = 0x13, + ARMV6MPCORE_PERFCTR_CPU_CYCLES = 0xFF, +}; + +/* + * The hardware events that we support. We do support cache operations but + * we have harvard caches and no way to combine instruction and data + * accesses/misses in hardware. + */ +static const unsigned armv6mpcore_perf_map[PERF_COUNT_HW_MAX] = { + [PERF_COUNT_HW_CPU_CYCLES] = ARMV6MPCORE_PERFCTR_CPU_CYCLES, + [PERF_COUNT_HW_INSTRUCTIONS] = ARMV6MPCORE_PERFCTR_INSTR_EXEC, + [PERF_COUNT_HW_CACHE_REFERENCES] = HW_OP_UNSUPPORTED, + [PERF_COUNT_HW_CACHE_MISSES] = HW_OP_UNSUPPORTED, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV6MPCORE_PERFCTR_BR_EXEC, + [PERF_COUNT_HW_BRANCH_MISSES] = ARMV6MPCORE_PERFCTR_BR_MISPREDICT, + [PERF_COUNT_HW_BUS_CYCLES] = HW_OP_UNSUPPORTED, +}; + +static const unsigned armv6mpcore_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + [C(L1D)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = + ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS, + [C(RESULT_MISS)] = + ARMV6MPCORE_PERFCTR_DCACHE_RDMISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = + ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS, + [C(RESULT_MISS)] = + ARMV6MPCORE_PERFCTR_DCACHE_WRMISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(L1I)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ICACHE_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ICACHE_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(DTLB)] = { + /* + * The ARM performance counters can count micro DTLB misses, + * micro ITLB misses and main TLB misses. There isn't an event + * for TLB misses, so use the micro misses here and if users + * want the main TLB misses they can use a raw counter. + */ + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DTLB_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DTLB_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(ITLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ITLB_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ITLB_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(BPU)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, +}; + +static inline unsigned long +armv6_pmcr_read(void) +{ + u32 val; + asm volatile("mrc p15, 0, %0, c15, c12, 0" : "=r"(val)); + return val; +} + +static inline void +armv6_pmcr_write(unsigned long val) +{ + asm volatile("mcr p15, 0, %0, c15, c12, 0" : : "r"(val)); +} + +#define ARMV6_PMCR_ENABLE (1 << 0) +#define ARMV6_PMCR_CTR01_RESET (1 << 1) +#define ARMV6_PMCR_CCOUNT_RESET (1 << 2) +#define ARMV6_PMCR_CCOUNT_DIV (1 << 3) +#define ARMV6_PMCR_COUNT0_IEN (1 << 4) +#define ARMV6_PMCR_COUNT1_IEN (1 << 5) +#define ARMV6_PMCR_CCOUNT_IEN (1 << 6) +#define ARMV6_PMCR_COUNT0_OVERFLOW (1 << 8) +#define ARMV6_PMCR_COUNT1_OVERFLOW (1 << 9) +#define ARMV6_PMCR_CCOUNT_OVERFLOW (1 << 10) +#define ARMV6_PMCR_EVT_COUNT0_SHIFT 20 +#define ARMV6_PMCR_EVT_COUNT0_MASK (0xFF << ARMV6_PMCR_EVT_COUNT0_SHIFT) +#define ARMV6_PMCR_EVT_COUNT1_SHIFT 12 +#define ARMV6_PMCR_EVT_COUNT1_MASK (0xFF << ARMV6_PMCR_EVT_COUNT1_SHIFT) + +#define ARMV6_PMCR_OVERFLOWED_MASK \ + (ARMV6_PMCR_COUNT0_OVERFLOW | ARMV6_PMCR_COUNT1_OVERFLOW | \ + ARMV6_PMCR_CCOUNT_OVERFLOW) + +static inline int +armv6_pmcr_has_overflowed(unsigned long pmcr) +{ + return (pmcr & ARMV6_PMCR_OVERFLOWED_MASK); +} + +static inline int +armv6_pmcr_counter_has_overflowed(unsigned long pmcr, + enum armv6_counters counter) +{ + int ret = 0; + + if (ARMV6_CYCLE_COUNTER == counter) + ret = pmcr & ARMV6_PMCR_CCOUNT_OVERFLOW; + else if (ARMV6_COUNTER0 == counter) + ret = pmcr & ARMV6_PMCR_COUNT0_OVERFLOW; + else if (ARMV6_COUNTER1 == counter) + ret = pmcr & ARMV6_PMCR_COUNT1_OVERFLOW; + else + WARN_ONCE(1, "invalid counter number (%d)\n", counter); + + return ret; +} + +static inline u32 +armv6pmu_read_counter(int counter) +{ + unsigned long value = 0; + + if (ARMV6_CYCLE_COUNTER == counter) + asm volatile("mrc p15, 0, %0, c15, c12, 1" : "=r"(value)); + else if (ARMV6_COUNTER0 == counter) + asm volatile("mrc p15, 0, %0, c15, c12, 2" : "=r"(value)); + else if (ARMV6_COUNTER1 == counter) + asm volatile("mrc p15, 0, %0, c15, c12, 3" : "=r"(value)); + else + WARN_ONCE(1, "invalid counter number (%d)\n", counter); + + return value; +} + +static inline void +armv6pmu_write_counter(int counter, + u32 value) +{ + if (ARMV6_CYCLE_COUNTER == counter) + asm volatile("mcr p15, 0, %0, c15, c12, 1" : : "r"(value)); + else if (ARMV6_COUNTER0 == counter) + asm volatile("mcr p15, 0, %0, c15, c12, 2" : : "r"(value)); + else if (ARMV6_COUNTER1 == counter) + asm volatile("mcr p15, 0, %0, c15, c12, 3" : : "r"(value)); + else + WARN_ONCE(1, "invalid counter number (%d)\n", counter); +} + +void +armv6pmu_enable_event(struct hw_perf_event *hwc, + int idx) +{ + unsigned long val, mask, evt, flags; + + if (ARMV6_CYCLE_COUNTER == idx) { + mask = 0; + evt = ARMV6_PMCR_CCOUNT_IEN; + } else if (ARMV6_COUNTER0 == idx) { + mask = ARMV6_PMCR_EVT_COUNT0_MASK; + evt = (hwc->config_base << ARMV6_PMCR_EVT_COUNT0_SHIFT) | + ARMV6_PMCR_COUNT0_IEN; + } else if (ARMV6_COUNTER1 == idx) { + mask = ARMV6_PMCR_EVT_COUNT1_MASK; + evt = (hwc->config_base << ARMV6_PMCR_EVT_COUNT1_SHIFT) | + ARMV6_PMCR_COUNT1_IEN; + } else { + WARN_ONCE(1, "invalid counter number (%d)\n", idx); + return; + } + + /* + * Mask out the current event and set the counter to count the event + * that we're interested in. + */ + spin_lock_irqsave(&pmu_lock, flags); + val = armv6_pmcr_read(); + val &= ~mask; + val |= evt; + armv6_pmcr_write(val); + spin_unlock_irqrestore(&pmu_lock, flags); +} + +static irqreturn_t +armv6pmu_handle_irq(int irq_num, + void *dev) +{ + unsigned long pmcr = armv6_pmcr_read(); + struct perf_sample_data data; + struct cpu_hw_events *cpuc; + struct pt_regs *regs; + int idx; + + if (!armv6_pmcr_has_overflowed(pmcr)) + return IRQ_NONE; + + regs = get_irq_regs(); + + /* + * The interrupts are cleared by writing the overflow flags back to + * the control register. All of the other bits don't have any effect + * if they are rewritten, so write the whole value back. + */ + armv6_pmcr_write(pmcr); + + data.addr = 0; + + cpuc = &__get_cpu_var(cpu_hw_events); + for (idx = 0; idx <= armpmu->num_events; ++idx) { + struct perf_event *event = cpuc->events[idx]; + struct hw_perf_event *hwc; + + if (!test_bit(idx, cpuc->active_mask)) + continue; + + /* + * We have a single interrupt for all counters. Check that + * each counter has overflowed before we process it. + */ + if (!armv6_pmcr_counter_has_overflowed(pmcr, idx)) + continue; + + hwc = &event->hw; + armpmu_event_update(event, hwc, idx); + data.period = event->hw.last_period; + if (!armpmu_event_set_period(event, hwc, idx)) + continue; + + if (perf_event_overflow(event, 0, &data, regs)) + armpmu->disable(hwc, idx); + } + + /* + * Handle the pending perf events. + * + * Note: this call *must* be run with interrupts enabled. For + * platforms that can have the PMU interrupts raised as a PMI, this + * will not work. + */ + perf_event_do_pending(); + + return IRQ_HANDLED; +} + +static void +armv6pmu_start(void) +{ + unsigned long flags, val; + + spin_lock_irqsave(&pmu_lock, flags); + val = armv6_pmcr_read(); + val |= ARMV6_PMCR_ENABLE; + armv6_pmcr_write(val); + spin_unlock_irqrestore(&pmu_lock, flags); +} + +void +armv6pmu_stop(void) +{ + unsigned long flags, val; + + spin_lock_irqsave(&pmu_lock, flags); + val = armv6_pmcr_read(); + val &= ~ARMV6_PMCR_ENABLE; + armv6_pmcr_write(val); + spin_unlock_irqrestore(&pmu_lock, flags); +} + +static inline int +armv6pmu_event_map(int config) +{ + int mapping = armv6_perf_map[config]; + if (HW_OP_UNSUPPORTED == mapping) + mapping = -EOPNOTSUPP; + return mapping; +} + +static inline int +armv6mpcore_pmu_event_map(int config) +{ + int mapping = armv6mpcore_perf_map[config]; + if (HW_OP_UNSUPPORTED == mapping) + mapping = -EOPNOTSUPP; + return mapping; +} + +static u64 +armv6pmu_raw_event(u64 config) +{ + return config & 0xff; +} + +static int +armv6pmu_get_event_idx(struct cpu_hw_events *cpuc, + struct hw_perf_event *event) +{ + /* Always place a cycle counter into the cycle counter. */ + if (ARMV6_PERFCTR_CPU_CYCLES == event->config_base) { + if (test_and_set_bit(ARMV6_CYCLE_COUNTER, cpuc->used_mask)) + return -EAGAIN; + + return ARMV6_CYCLE_COUNTER; + } else { + /* + * For anything other than a cycle counter, try and use + * counter0 and counter1. + */ + if (!test_and_set_bit(ARMV6_COUNTER1, cpuc->used_mask)) { + return ARMV6_COUNTER1; + } + + if (!test_and_set_bit(ARMV6_COUNTER0, cpuc->used_mask)) { + return ARMV6_COUNTER0; + } + + /* The counters are all in use. */ + return -EAGAIN; + } +} + +static void +armv6pmu_disable_event(struct hw_perf_event *hwc, + int idx) +{ + unsigned long val, mask, evt, flags; + + if (ARMV6_CYCLE_COUNTER == idx) { + mask = ARMV6_PMCR_CCOUNT_IEN; + evt = 0; + } else if (ARMV6_COUNTER0 == idx) { + mask = ARMV6_PMCR_COUNT0_IEN | ARMV6_PMCR_EVT_COUNT0_MASK; + evt = ARMV6_PERFCTR_NOP << ARMV6_PMCR_EVT_COUNT0_SHIFT; + } else if (ARMV6_COUNTER1 == idx) { + mask = ARMV6_PMCR_COUNT1_IEN | ARMV6_PMCR_EVT_COUNT1_MASK; + evt = ARMV6_PERFCTR_NOP << ARMV6_PMCR_EVT_COUNT1_SHIFT; + } else { + WARN_ONCE(1, "invalid counter number (%d)\n", idx); + return; + } + + /* + * Mask out the current event and set the counter to count the number + * of ETM bus signal assertion cycles. The external reporting should + * be disabled and so this should never increment. + */ + spin_lock_irqsave(&pmu_lock, flags); + val = armv6_pmcr_read(); + val &= ~mask; + val |= evt; + armv6_pmcr_write(val); + spin_unlock_irqrestore(&pmu_lock, flags); +} + +static void +armv6mpcore_pmu_disable_event(struct hw_perf_event *hwc, + int idx) +{ + unsigned long val, mask, flags, evt = 0; + + if (ARMV6_CYCLE_COUNTER == idx) { + mask = ARMV6_PMCR_CCOUNT_IEN; + } else if (ARMV6_COUNTER0 == idx) { + mask = ARMV6_PMCR_COUNT0_IEN; + } else if (ARMV6_COUNTER1 == idx) { + mask = ARMV6_PMCR_COUNT1_IEN; + } else { + WARN_ONCE(1, "invalid counter number (%d)\n", idx); + return; + } + + /* + * Unlike UP ARMv6, we don't have a way of stopping the counters. We + * simply disable the interrupt reporting. + */ + spin_lock_irqsave(&pmu_lock, flags); + val = armv6_pmcr_read(); + val &= ~mask; + val |= evt; + armv6_pmcr_write(val); + spin_unlock_irqrestore(&pmu_lock, flags); +} + +static const struct arm_pmu armv6pmu = { + .name = "v6", + .handle_irq = armv6pmu_handle_irq, + .enable = armv6pmu_enable_event, + .disable = armv6pmu_disable_event, + .event_map = armv6pmu_event_map, + .raw_event = armv6pmu_raw_event, + .read_counter = armv6pmu_read_counter, + .write_counter = armv6pmu_write_counter, + .get_event_idx = armv6pmu_get_event_idx, + .start = armv6pmu_start, + .stop = armv6pmu_stop, + .num_events = 3, + .max_period = (1LLU << 32) - 1, +}; + +/* + * ARMv6mpcore is almost identical to single core ARMv6 with the exception + * that some of the events have different enumerations and that there is no + * *hack* to stop the programmable counters. To stop the counters we simply + * disable the interrupt reporting and update the event. When unthrottling we + * reset the period and enable the interrupt reporting. + */ +static const struct arm_pmu armv6mpcore_pmu = { + .name = "v6mpcore", + .handle_irq = armv6pmu_handle_irq, + .enable = armv6pmu_enable_event, + .disable = armv6mpcore_pmu_disable_event, + .event_map = armv6mpcore_pmu_event_map, + .raw_event = armv6pmu_raw_event, + .read_counter = armv6pmu_read_counter, + .write_counter = armv6pmu_write_counter, + .get_event_idx = armv6pmu_get_event_idx, + .start = armv6pmu_start, + .stop = armv6pmu_stop, + .num_events = 3, + .max_period = (1LLU << 32) - 1, +}; + +static int __init +init_hw_perf_events(void) +{ + unsigned long cpuid = read_cpuid_id(); + unsigned long implementor = (cpuid & 0xFF000000) >> 24; + unsigned long part_number = (cpuid & 0xFFF0); + + /* We only support ARM CPUs implemented by ARM at the moment. */ + if (0x41 == implementor) { + switch (part_number) { + case 0xB360: /* ARM1136 */ + case 0xB560: /* ARM1156 */ + case 0xB760: /* ARM1176 */ + armpmu = &armv6pmu; + memcpy(armpmu_perf_cache_map, armv6_perf_cache_map, + sizeof(armv6_perf_cache_map)); + perf_max_events = armv6pmu.num_events; + break; + case 0xB020: /* ARM11mpcore */ + armpmu = &armv6mpcore_pmu; + memcpy(armpmu_perf_cache_map, + armv6mpcore_perf_cache_map, + sizeof(armv6mpcore_perf_cache_map)); + perf_max_events = armv6mpcore_pmu.num_events; + break; + default: + pr_info("no hardware support available\n"); + perf_max_events = -1; + } + } + + if (armpmu) + pr_info("enabled with %s PMU driver\n", + armpmu->name); + + return 0; +} +arch_initcall(init_hw_perf_events); + +/* + * Callchain handling code. + */ +static inline void +callchain_store(struct perf_callchain_entry *entry, + u64 ip) +{ + if (entry->nr < PERF_MAX_STACK_DEPTH) + entry->ip[entry->nr++] = ip; +} + +/* + * The registers we're interested in are at the end of the variable + * length saved register structure. The fp points at the end of this + * structure so the address of this struct is: + * (struct frame_tail *)(xxx->fp)-1 + * + * This code has been adapted from the ARM OProfile support. + */ +struct frame_tail { + struct frame_tail *fp; + unsigned long sp; + unsigned long lr; +} __attribute__((packed)); + +/* + * Get the return address for a single stackframe and return a pointer to the + * next frame tail. + */ +static struct frame_tail * +user_backtrace(struct frame_tail *tail, + struct perf_callchain_entry *entry) +{ + struct frame_tail buftail; + + /* Also check accessibility of one struct frame_tail beyond */ + if (!access_ok(VERIFY_READ, tail, sizeof(buftail))) + return NULL; + if (__copy_from_user_inatomic(&buftail, tail, sizeof(buftail))) + return NULL; + + callchain_store(entry, buftail.lr); + + /* + * Frame pointers should strictly progress back up the stack + * (towards higher addresses). + */ + if (tail >= buftail.fp) + return NULL; + + return buftail.fp - 1; +} + +static void +perf_callchain_user(struct pt_regs *regs, + struct perf_callchain_entry *entry) +{ + struct frame_tail *tail; + + callchain_store(entry, PERF_CONTEXT_USER); + + if (!user_mode(regs)) + regs = task_pt_regs(current); + + tail = (struct frame_tail *)regs->ARM_fp - 1; + + while (tail && !((unsigned long)tail & 0x3)) + tail = user_backtrace(tail, entry); +} + +/* + * Gets called by walk_stackframe() for every stackframe. This will be called + * whist unwinding the stackframe and is like a subroutine return so we use + * the PC. + */ +static int +callchain_trace(struct stackframe *fr, + void *data) +{ + struct perf_callchain_entry *entry = data; + callchain_store(entry, fr->pc); + return 0; +} + +static void +perf_callchain_kernel(struct pt_regs *regs, + struct perf_callchain_entry *entry) +{ + struct stackframe fr; + + callchain_store(entry, PERF_CONTEXT_KERNEL); + fr.fp = regs->ARM_fp; + fr.sp = regs->ARM_sp; + fr.lr = regs->ARM_lr; + fr.pc = regs->ARM_pc; + walk_stackframe(&fr, callchain_trace, entry); +} + +static void +perf_do_callchain(struct pt_regs *regs, + struct perf_callchain_entry *entry) +{ + int is_user; + + if (!regs) + return; + + is_user = user_mode(regs); + + if (!current || !current->pid) + return; + + if (is_user && current->state != TASK_RUNNING) + return; + + if (!is_user) + perf_callchain_kernel(regs, entry); + + if (current->mm) + perf_callchain_user(regs, entry); +} + +static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry); + +struct perf_callchain_entry * +perf_callchain(struct pt_regs *regs) +{ + struct perf_callchain_entry *entry = &__get_cpu_var(pmc_irq_entry); + + entry->nr = 0; + perf_do_callchain(regs, entry); + return entry; +} -- cgit v1.2.3 From 796d12959ad374cae8eb77faaf4243455a305433 Mon Sep 17 00:00:00 2001 From: Jean PIHET Date: Tue, 26 Jan 2010 18:51:05 +0100 Subject: ARM: 5903/1: arm/perfevents: add support for ARMv7 Adds the Performance Events support for ARMv7 processor, using the PMNC unit in HW. Supports the following: - Cortex-A8 and Cortex-A9 processors, - dynamic detection of the number of available counters, based on the PMCR value, - runtime detection of the CPU arch (v6 or v7) and model (Cortex-A8 or Cortex-A9) Tested on OMAP3 (Cortex-A8) only. Signed-off-by: Jean Pihet Signed-off-by: Russell King --- arch/arm/Kconfig | 2 +- arch/arm/kernel/perf_event.c | 936 ++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 933 insertions(+), 5 deletions(-) (limited to 'arch/arm/Kconfig') diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 9fb91ce106bc..1d10b9064567 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1176,7 +1176,7 @@ config HIGHPTE config HW_PERF_EVENTS bool "Enable hardware performance counter support for perf events" - depends on PERF_EVENTS && CPU_HAS_PMU && CPU_V6 + depends on PERF_EVENTS && CPU_HAS_PMU && (CPU_V6 || CPU_V7) default y help Enable hardware performance counter support for perf events. If diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 7b1022b9aa52..c54ceb3d1f97 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -5,6 +5,9 @@ * * Copyright (C) 2009 picoChip Designs, Ltd., Jamie Iles * + * ARMv7 support: Jean Pihet + * 2010 (c) MontaVista Software, LLC. + * * This code is based on the sparc64 perf event code, which is in turn based * on the x86 code. Callchain code is based on the ARM OProfile backtrace * code. @@ -35,8 +38,12 @@ DEFINE_SPINLOCK(pmu_lock); * ARMv6 supports a maximum of 3 events, starting from index 1. If we add * another platform that supports more, we need to increase this to be the * largest of all platforms. + * + * ARMv7 supports up to 32 events: + * cycle counter CCNT + 31 events counters CNT0..30. + * Cortex-A8 has 1+4 counters, Cortex-A9 has 1+6 counters. */ -#define ARMPMU_MAX_HWEVENTS 4 +#define ARMPMU_MAX_HWEVENTS 33 /* The events for a given CPU. */ struct cpu_hw_events { @@ -61,7 +68,7 @@ struct cpu_hw_events { DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events); struct arm_pmu { - const char *name; + char *name; irqreturn_t (*handle_irq)(int irq_num, void *dev); void (*enable)(struct hw_perf_event *evt, int idx); void (*disable)(struct hw_perf_event *evt, int idx); @@ -1174,6 +1181,903 @@ static const struct arm_pmu armv6mpcore_pmu = { .max_period = (1LLU << 32) - 1, }; +/* + * ARMv7 Cortex-A8 and Cortex-A9 Performance Events handling code. + * + * Copied from ARMv6 code, with the low level code inspired + * by the ARMv7 Oprofile code. + * + * Cortex-A8 has up to 4 configurable performance counters and + * a single cycle counter. + * Cortex-A9 has up to 31 configurable performance counters and + * a single cycle counter. + * + * All counters can be enabled/disabled and IRQ masked separately. The cycle + * counter and all 4 performance counters together can be reset separately. + */ + +#define ARMV7_PMU_CORTEX_A8_NAME "ARMv7 Cortex-A8" + +#define ARMV7_PMU_CORTEX_A9_NAME "ARMv7 Cortex-A9" + +/* Common ARMv7 event types */ +enum armv7_perf_types { + ARMV7_PERFCTR_PMNC_SW_INCR = 0x00, + ARMV7_PERFCTR_IFETCH_MISS = 0x01, + ARMV7_PERFCTR_ITLB_MISS = 0x02, + ARMV7_PERFCTR_DCACHE_REFILL = 0x03, + ARMV7_PERFCTR_DCACHE_ACCESS = 0x04, + ARMV7_PERFCTR_DTLB_REFILL = 0x05, + ARMV7_PERFCTR_DREAD = 0x06, + ARMV7_PERFCTR_DWRITE = 0x07, + + ARMV7_PERFCTR_EXC_TAKEN = 0x09, + ARMV7_PERFCTR_EXC_EXECUTED = 0x0A, + ARMV7_PERFCTR_CID_WRITE = 0x0B, + /* ARMV7_PERFCTR_PC_WRITE is equivalent to HW_BRANCH_INSTRUCTIONS. + * It counts: + * - all branch instructions, + * - instructions that explicitly write the PC, + * - exception generating instructions. + */ + ARMV7_PERFCTR_PC_WRITE = 0x0C, + ARMV7_PERFCTR_PC_IMM_BRANCH = 0x0D, + ARMV7_PERFCTR_UNALIGNED_ACCESS = 0x0F, + ARMV7_PERFCTR_PC_BRANCH_MIS_PRED = 0x10, + ARMV7_PERFCTR_CLOCK_CYCLES = 0x11, + + ARMV7_PERFCTR_PC_BRANCH_MIS_USED = 0x12, + + ARMV7_PERFCTR_CPU_CYCLES = 0xFF +}; + +/* ARMv7 Cortex-A8 specific event types */ +enum armv7_a8_perf_types { + ARMV7_PERFCTR_INSTR_EXECUTED = 0x08, + + ARMV7_PERFCTR_PC_PROC_RETURN = 0x0E, + + ARMV7_PERFCTR_WRITE_BUFFER_FULL = 0x40, + ARMV7_PERFCTR_L2_STORE_MERGED = 0x41, + ARMV7_PERFCTR_L2_STORE_BUFF = 0x42, + ARMV7_PERFCTR_L2_ACCESS = 0x43, + ARMV7_PERFCTR_L2_CACH_MISS = 0x44, + ARMV7_PERFCTR_AXI_READ_CYCLES = 0x45, + ARMV7_PERFCTR_AXI_WRITE_CYCLES = 0x46, + ARMV7_PERFCTR_MEMORY_REPLAY = 0x47, + ARMV7_PERFCTR_UNALIGNED_ACCESS_REPLAY = 0x48, + ARMV7_PERFCTR_L1_DATA_MISS = 0x49, + ARMV7_PERFCTR_L1_INST_MISS = 0x4A, + ARMV7_PERFCTR_L1_DATA_COLORING = 0x4B, + ARMV7_PERFCTR_L1_NEON_DATA = 0x4C, + ARMV7_PERFCTR_L1_NEON_CACH_DATA = 0x4D, + ARMV7_PERFCTR_L2_NEON = 0x4E, + ARMV7_PERFCTR_L2_NEON_HIT = 0x4F, + ARMV7_PERFCTR_L1_INST = 0x50, + ARMV7_PERFCTR_PC_RETURN_MIS_PRED = 0x51, + ARMV7_PERFCTR_PC_BRANCH_FAILED = 0x52, + ARMV7_PERFCTR_PC_BRANCH_TAKEN = 0x53, + ARMV7_PERFCTR_PC_BRANCH_EXECUTED = 0x54, + ARMV7_PERFCTR_OP_EXECUTED = 0x55, + ARMV7_PERFCTR_CYCLES_INST_STALL = 0x56, + ARMV7_PERFCTR_CYCLES_INST = 0x57, + ARMV7_PERFCTR_CYCLES_NEON_DATA_STALL = 0x58, + ARMV7_PERFCTR_CYCLES_NEON_INST_STALL = 0x59, + ARMV7_PERFCTR_NEON_CYCLES = 0x5A, + + ARMV7_PERFCTR_PMU0_EVENTS = 0x70, + ARMV7_PERFCTR_PMU1_EVENTS = 0x71, + ARMV7_PERFCTR_PMU_EVENTS = 0x72, +}; + +/* ARMv7 Cortex-A9 specific event types */ +enum armv7_a9_perf_types { + ARMV7_PERFCTR_JAVA_HW_BYTECODE_EXEC = 0x40, + ARMV7_PERFCTR_JAVA_SW_BYTECODE_EXEC = 0x41, + ARMV7_PERFCTR_JAZELLE_BRANCH_EXEC = 0x42, + + ARMV7_PERFCTR_COHERENT_LINE_MISS = 0x50, + ARMV7_PERFCTR_COHERENT_LINE_HIT = 0x51, + + ARMV7_PERFCTR_ICACHE_DEP_STALL_CYCLES = 0x60, + ARMV7_PERFCTR_DCACHE_DEP_STALL_CYCLES = 0x61, + ARMV7_PERFCTR_TLB_MISS_DEP_STALL_CYCLES = 0x62, + ARMV7_PERFCTR_STREX_EXECUTED_PASSED = 0x63, + ARMV7_PERFCTR_STREX_EXECUTED_FAILED = 0x64, + ARMV7_PERFCTR_DATA_EVICTION = 0x65, + ARMV7_PERFCTR_ISSUE_STAGE_NO_INST = 0x66, + ARMV7_PERFCTR_ISSUE_STAGE_EMPTY = 0x67, + ARMV7_PERFCTR_INST_OUT_OF_RENAME_STAGE = 0x68, + + ARMV7_PERFCTR_PREDICTABLE_FUNCT_RETURNS = 0x6E, + + ARMV7_PERFCTR_MAIN_UNIT_EXECUTED_INST = 0x70, + ARMV7_PERFCTR_SECOND_UNIT_EXECUTED_INST = 0x71, + ARMV7_PERFCTR_LD_ST_UNIT_EXECUTED_INST = 0x72, + ARMV7_PERFCTR_FP_EXECUTED_INST = 0x73, + ARMV7_PERFCTR_NEON_EXECUTED_INST = 0x74, + + ARMV7_PERFCTR_PLD_FULL_DEP_STALL_CYCLES = 0x80, + ARMV7_PERFCTR_DATA_WR_DEP_STALL_CYCLES = 0x81, + ARMV7_PERFCTR_ITLB_MISS_DEP_STALL_CYCLES = 0x82, + ARMV7_PERFCTR_DTLB_MISS_DEP_STALL_CYCLES = 0x83, + ARMV7_PERFCTR_MICRO_ITLB_MISS_DEP_STALL_CYCLES = 0x84, + ARMV7_PERFCTR_MICRO_DTLB_MISS_DEP_STALL_CYCLES = 0x85, + ARMV7_PERFCTR_DMB_DEP_STALL_CYCLES = 0x86, + + ARMV7_PERFCTR_INTGR_CLK_ENABLED_CYCLES = 0x8A, + ARMV7_PERFCTR_DATA_ENGINE_CLK_EN_CYCLES = 0x8B, + + ARMV7_PERFCTR_ISB_INST = 0x90, + ARMV7_PERFCTR_DSB_INST = 0x91, + ARMV7_PERFCTR_DMB_INST = 0x92, + ARMV7_PERFCTR_EXT_INTERRUPTS = 0x93, + + ARMV7_PERFCTR_PLE_CACHE_LINE_RQST_COMPLETED = 0xA0, + ARMV7_PERFCTR_PLE_CACHE_LINE_RQST_SKIPPED = 0xA1, + ARMV7_PERFCTR_PLE_FIFO_FLUSH = 0xA2, + ARMV7_PERFCTR_PLE_RQST_COMPLETED = 0xA3, + ARMV7_PERFCTR_PLE_FIFO_OVERFLOW = 0xA4, + ARMV7_PERFCTR_PLE_RQST_PROG = 0xA5 +}; + +/* + * Cortex-A8 HW events mapping + * + * The hardware events that we support. We do support cache operations but + * we have harvard caches and no way to combine instruction and data + * accesses/misses in hardware. + */ +static const unsigned armv7_a8_perf_map[PERF_COUNT_HW_MAX] = { + [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES, + [PERF_COUNT_HW_INSTRUCTIONS] = ARMV7_PERFCTR_INSTR_EXECUTED, + [PERF_COUNT_HW_CACHE_REFERENCES] = HW_OP_UNSUPPORTED, + [PERF_COUNT_HW_CACHE_MISSES] = HW_OP_UNSUPPORTED, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE, + [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [PERF_COUNT_HW_BUS_CYCLES] = ARMV7_PERFCTR_CLOCK_CYCLES, +}; + +static const unsigned armv7_a8_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + [C(L1D)] = { + /* + * The performance counters don't differentiate between read + * and write accesses/misses so this isn't strictly correct, + * but it's the best we can do. Writes and reads get + * combined. + */ + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_DCACHE_ACCESS, + [C(RESULT_MISS)] = ARMV7_PERFCTR_DCACHE_REFILL, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_DCACHE_ACCESS, + [C(RESULT_MISS)] = ARMV7_PERFCTR_DCACHE_REFILL, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(L1I)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_INST, + [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_INST_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_INST, + [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_INST_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L2_ACCESS, + [C(RESULT_MISS)] = ARMV7_PERFCTR_L2_CACH_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L2_ACCESS, + [C(RESULT_MISS)] = ARMV7_PERFCTR_L2_CACH_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(DTLB)] = { + /* + * Only ITLB misses and DTLB refills are supported. + * If users want the DTLB refills misses a raw counter + * must be used. + */ + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(ITLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(BPU)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_WRITE, + [C(RESULT_MISS)] + = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_WRITE, + [C(RESULT_MISS)] + = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, +}; + +/* + * Cortex-A9 HW events mapping + */ +static const unsigned armv7_a9_perf_map[PERF_COUNT_HW_MAX] = { + [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES, + [PERF_COUNT_HW_INSTRUCTIONS] = + ARMV7_PERFCTR_INST_OUT_OF_RENAME_STAGE, + [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV7_PERFCTR_COHERENT_LINE_HIT, + [PERF_COUNT_HW_CACHE_MISSES] = ARMV7_PERFCTR_COHERENT_LINE_MISS, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE, + [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [PERF_COUNT_HW_BUS_CYCLES] = ARMV7_PERFCTR_CLOCK_CYCLES, +}; + +static const unsigned armv7_a9_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + [C(L1D)] = { + /* + * The performance counters don't differentiate between read + * and write accesses/misses so this isn't strictly correct, + * but it's the best we can do. Writes and reads get + * combined. + */ + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_DCACHE_ACCESS, + [C(RESULT_MISS)] = ARMV7_PERFCTR_DCACHE_REFILL, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_DCACHE_ACCESS, + [C(RESULT_MISS)] = ARMV7_PERFCTR_DCACHE_REFILL, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(L1I)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV7_PERFCTR_IFETCH_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV7_PERFCTR_IFETCH_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(DTLB)] = { + /* + * Only ITLB misses and DTLB refills are supported. + * If users want the DTLB refills misses a raw counter + * must be used. + */ + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(ITLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(BPU)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_WRITE, + [C(RESULT_MISS)] + = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_WRITE, + [C(RESULT_MISS)] + = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, +}; + +/* + * Perf Events counters + */ +enum armv7_counters { + ARMV7_CYCLE_COUNTER = 1, /* Cycle counter */ + ARMV7_COUNTER0 = 2, /* First event counter */ +}; + +/* + * The cycle counter is ARMV7_CYCLE_COUNTER. + * The first event counter is ARMV7_COUNTER0. + * The last event counter is (ARMV7_COUNTER0 + armpmu->num_events - 1). + */ +#define ARMV7_COUNTER_LAST (ARMV7_COUNTER0 + armpmu->num_events - 1) + +/* + * ARMv7 low level PMNC access + */ + +/* + * Per-CPU PMNC: config reg + */ +#define ARMV7_PMNC_E (1 << 0) /* Enable all counters */ +#define ARMV7_PMNC_P (1 << 1) /* Reset all counters */ +#define ARMV7_PMNC_C (1 << 2) /* Cycle counter reset */ +#define ARMV7_PMNC_D (1 << 3) /* CCNT counts every 64th cpu cycle */ +#define ARMV7_PMNC_X (1 << 4) /* Export to ETM */ +#define ARMV7_PMNC_DP (1 << 5) /* Disable CCNT if non-invasive debug*/ +#define ARMV7_PMNC_N_SHIFT 11 /* Number of counters supported */ +#define ARMV7_PMNC_N_MASK 0x1f +#define ARMV7_PMNC_MASK 0x3f /* Mask for writable bits */ + +/* + * Available counters + */ +#define ARMV7_CNT0 0 /* First event counter */ +#define ARMV7_CCNT 31 /* Cycle counter */ + +/* Perf Event to low level counters mapping */ +#define ARMV7_EVENT_CNT_TO_CNTx (ARMV7_COUNTER0 - ARMV7_CNT0) + +/* + * CNTENS: counters enable reg + */ +#define ARMV7_CNTENS_P(idx) (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx)) +#define ARMV7_CNTENS_C (1 << ARMV7_CCNT) + +/* + * CNTENC: counters disable reg + */ +#define ARMV7_CNTENC_P(idx) (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx)) +#define ARMV7_CNTENC_C (1 << ARMV7_CCNT) + +/* + * INTENS: counters overflow interrupt enable reg + */ +#define ARMV7_INTENS_P(idx) (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx)) +#define ARMV7_INTENS_C (1 << ARMV7_CCNT) + +/* + * INTENC: counters overflow interrupt disable reg + */ +#define ARMV7_INTENC_P(idx) (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx)) +#define ARMV7_INTENC_C (1 << ARMV7_CCNT) + +/* + * EVTSEL: Event selection reg + */ +#define ARMV7_EVTSEL_MASK 0x7f /* Mask for writable bits */ + +/* + * SELECT: Counter selection reg + */ +#define ARMV7_SELECT_MASK 0x1f /* Mask for writable bits */ + +/* + * FLAG: counters overflow flag status reg + */ +#define ARMV7_FLAG_P(idx) (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx)) +#define ARMV7_FLAG_C (1 << ARMV7_CCNT) +#define ARMV7_FLAG_MASK 0xffffffff /* Mask for writable bits */ +#define ARMV7_OVERFLOWED_MASK ARMV7_FLAG_MASK + +static inline unsigned long armv7_pmnc_read(void) +{ + u32 val; + asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r"(val)); + return val; +} + +static inline void armv7_pmnc_write(unsigned long val) +{ + val &= ARMV7_PMNC_MASK; + asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r"(val)); +} + +static inline int armv7_pmnc_has_overflowed(unsigned long pmnc) +{ + return pmnc & ARMV7_OVERFLOWED_MASK; +} + +static inline int armv7_pmnc_counter_has_overflowed(unsigned long pmnc, + enum armv7_counters counter) +{ + int ret; + + if (counter == ARMV7_CYCLE_COUNTER) + ret = pmnc & ARMV7_FLAG_C; + else if ((counter >= ARMV7_COUNTER0) && (counter <= ARMV7_COUNTER_LAST)) + ret = pmnc & ARMV7_FLAG_P(counter); + else + pr_err("CPU%u checking wrong counter %d overflow status\n", + smp_processor_id(), counter); + + return ret; +} + +static inline int armv7_pmnc_select_counter(unsigned int idx) +{ + u32 val; + + if ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST)) { + pr_err("CPU%u selecting wrong PMNC counter" + " %d\n", smp_processor_id(), idx); + return -1; + } + + val = (idx - ARMV7_EVENT_CNT_TO_CNTx) & ARMV7_SELECT_MASK; + asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (val)); + + return idx; +} + +static inline u32 armv7pmu_read_counter(int idx) +{ + unsigned long value = 0; + + if (idx == ARMV7_CYCLE_COUNTER) + asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (value)); + else if ((idx >= ARMV7_COUNTER0) && (idx <= ARMV7_COUNTER_LAST)) { + if (armv7_pmnc_select_counter(idx) == idx) + asm volatile("mrc p15, 0, %0, c9, c13, 2" + : "=r" (value)); + } else + pr_err("CPU%u reading wrong counter %d\n", + smp_processor_id(), idx); + + return value; +} + +static inline void armv7pmu_write_counter(int idx, u32 value) +{ + if (idx == ARMV7_CYCLE_COUNTER) + asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (value)); + else if ((idx >= ARMV7_COUNTER0) && (idx <= ARMV7_COUNTER_LAST)) { + if (armv7_pmnc_select_counter(idx) == idx) + asm volatile("mcr p15, 0, %0, c9, c13, 2" + : : "r" (value)); + } else + pr_err("CPU%u writing wrong counter %d\n", + smp_processor_id(), idx); +} + +static inline void armv7_pmnc_write_evtsel(unsigned int idx, u32 val) +{ + if (armv7_pmnc_select_counter(idx) == idx) { + val &= ARMV7_EVTSEL_MASK; + asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (val)); + } +} + +static inline u32 armv7_pmnc_enable_counter(unsigned int idx) +{ + u32 val; + + if ((idx != ARMV7_CYCLE_COUNTER) && + ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) { + pr_err("CPU%u enabling wrong PMNC counter" + " %d\n", smp_processor_id(), idx); + return -1; + } + + if (idx == ARMV7_CYCLE_COUNTER) + val = ARMV7_CNTENS_C; + else + val = ARMV7_CNTENS_P(idx); + + asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (val)); + + return idx; +} + +static inline u32 armv7_pmnc_disable_counter(unsigned int idx) +{ + u32 val; + + + if ((idx != ARMV7_CYCLE_COUNTER) && + ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) { + pr_err("CPU%u disabling wrong PMNC counter" + " %d\n", smp_processor_id(), idx); + return -1; + } + + if (idx == ARMV7_CYCLE_COUNTER) + val = ARMV7_CNTENC_C; + else + val = ARMV7_CNTENC_P(idx); + + asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (val)); + + return idx; +} + +static inline u32 armv7_pmnc_enable_intens(unsigned int idx) +{ + u32 val; + + if ((idx != ARMV7_CYCLE_COUNTER) && + ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) { + pr_err("CPU%u enabling wrong PMNC counter" + " interrupt enable %d\n", smp_processor_id(), idx); + return -1; + } + + if (idx == ARMV7_CYCLE_COUNTER) + val = ARMV7_INTENS_C; + else + val = ARMV7_INTENS_P(idx); + + asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (val)); + + return idx; +} + +static inline u32 armv7_pmnc_disable_intens(unsigned int idx) +{ + u32 val; + + if ((idx != ARMV7_CYCLE_COUNTER) && + ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) { + pr_err("CPU%u disabling wrong PMNC counter" + " interrupt enable %d\n", smp_processor_id(), idx); + return -1; + } + + if (idx == ARMV7_CYCLE_COUNTER) + val = ARMV7_INTENC_C; + else + val = ARMV7_INTENC_P(idx); + + asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (val)); + + return idx; +} + +static inline u32 armv7_pmnc_getreset_flags(void) +{ + u32 val; + + /* Read */ + asm volatile("mrc p15, 0, %0, c9, c12, 3" : "=r" (val)); + + /* Write to clear flags */ + val &= ARMV7_FLAG_MASK; + asm volatile("mcr p15, 0, %0, c9, c12, 3" : : "r" (val)); + + return val; +} + +#ifdef DEBUG +static void armv7_pmnc_dump_regs(void) +{ + u32 val; + unsigned int cnt; + + printk(KERN_INFO "PMNC registers dump:\n"); + + asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (val)); + printk(KERN_INFO "PMNC =0x%08x\n", val); + + asm volatile("mrc p15, 0, %0, c9, c12, 1" : "=r" (val)); + printk(KERN_INFO "CNTENS=0x%08x\n", val); + + asm volatile("mrc p15, 0, %0, c9, c14, 1" : "=r" (val)); + printk(KERN_INFO "INTENS=0x%08x\n", val); + + asm volatile("mrc p15, 0, %0, c9, c12, 3" : "=r" (val)); + printk(KERN_INFO "FLAGS =0x%08x\n", val); + + asm volatile("mrc p15, 0, %0, c9, c12, 5" : "=r" (val)); + printk(KERN_INFO "SELECT=0x%08x\n", val); + + asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val)); + printk(KERN_INFO "CCNT =0x%08x\n", val); + + for (cnt = ARMV7_COUNTER0; cnt < ARMV7_COUNTER_LAST; cnt++) { + armv7_pmnc_select_counter(cnt); + asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (val)); + printk(KERN_INFO "CNT[%d] count =0x%08x\n", + cnt-ARMV7_EVENT_CNT_TO_CNTx, val); + asm volatile("mrc p15, 0, %0, c9, c13, 1" : "=r" (val)); + printk(KERN_INFO "CNT[%d] evtsel=0x%08x\n", + cnt-ARMV7_EVENT_CNT_TO_CNTx, val); + } +} +#endif + +void armv7pmu_enable_event(struct hw_perf_event *hwc, int idx) +{ + unsigned long flags; + + /* + * Enable counter and interrupt, and set the counter to count + * the event that we're interested in. + */ + spin_lock_irqsave(&pmu_lock, flags); + + /* + * Disable counter + */ + armv7_pmnc_disable_counter(idx); + + /* + * Set event (if destined for PMNx counters) + * We don't need to set the event if it's a cycle count + */ + if (idx != ARMV7_CYCLE_COUNTER) + armv7_pmnc_write_evtsel(idx, hwc->config_base); + + /* + * Enable interrupt for this counter + */ + armv7_pmnc_enable_intens(idx); + + /* + * Enable counter + */ + armv7_pmnc_enable_counter(idx); + + spin_unlock_irqrestore(&pmu_lock, flags); +} + +static void armv7pmu_disable_event(struct hw_perf_event *hwc, int idx) +{ + unsigned long flags; + + /* + * Disable counter and interrupt + */ + spin_lock_irqsave(&pmu_lock, flags); + + /* + * Disable counter + */ + armv7_pmnc_disable_counter(idx); + + /* + * Disable interrupt for this counter + */ + armv7_pmnc_disable_intens(idx); + + spin_unlock_irqrestore(&pmu_lock, flags); +} + +static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev) +{ + unsigned long pmnc; + struct perf_sample_data data; + struct cpu_hw_events *cpuc; + struct pt_regs *regs; + int idx; + + /* + * Get and reset the IRQ flags + */ + pmnc = armv7_pmnc_getreset_flags(); + + /* + * Did an overflow occur? + */ + if (!armv7_pmnc_has_overflowed(pmnc)) + return IRQ_NONE; + + /* + * Handle the counter(s) overflow(s) + */ + regs = get_irq_regs(); + + data.addr = 0; + + cpuc = &__get_cpu_var(cpu_hw_events); + for (idx = 0; idx <= armpmu->num_events; ++idx) { + struct perf_event *event = cpuc->events[idx]; + struct hw_perf_event *hwc; + + if (!test_bit(idx, cpuc->active_mask)) + continue; + + /* + * We have a single interrupt for all counters. Check that + * each counter has overflowed before we process it. + */ + if (!armv7_pmnc_counter_has_overflowed(pmnc, idx)) + continue; + + hwc = &event->hw; + armpmu_event_update(event, hwc, idx); + data.period = event->hw.last_period; + if (!armpmu_event_set_period(event, hwc, idx)) + continue; + + if (perf_event_overflow(event, 0, &data, regs)) + armpmu->disable(hwc, idx); + } + + /* + * Handle the pending perf events. + * + * Note: this call *must* be run with interrupts enabled. For + * platforms that can have the PMU interrupts raised as a PMI, this + * will not work. + */ + perf_event_do_pending(); + + return IRQ_HANDLED; +} + +static void armv7pmu_start(void) +{ + unsigned long flags; + + spin_lock_irqsave(&pmu_lock, flags); + /* Enable all counters */ + armv7_pmnc_write(armv7_pmnc_read() | ARMV7_PMNC_E); + spin_unlock_irqrestore(&pmu_lock, flags); +} + +static void armv7pmu_stop(void) +{ + unsigned long flags; + + spin_lock_irqsave(&pmu_lock, flags); + /* Disable all counters */ + armv7_pmnc_write(armv7_pmnc_read() & ~ARMV7_PMNC_E); + spin_unlock_irqrestore(&pmu_lock, flags); +} + +static inline int armv7_a8_pmu_event_map(int config) +{ + int mapping = armv7_a8_perf_map[config]; + if (HW_OP_UNSUPPORTED == mapping) + mapping = -EOPNOTSUPP; + return mapping; +} + +static inline int armv7_a9_pmu_event_map(int config) +{ + int mapping = armv7_a9_perf_map[config]; + if (HW_OP_UNSUPPORTED == mapping) + mapping = -EOPNOTSUPP; + return mapping; +} + +static u64 armv7pmu_raw_event(u64 config) +{ + return config & 0xff; +} + +static int armv7pmu_get_event_idx(struct cpu_hw_events *cpuc, + struct hw_perf_event *event) +{ + int idx; + + /* Always place a cycle counter into the cycle counter. */ + if (event->config_base == ARMV7_PERFCTR_CPU_CYCLES) { + if (test_and_set_bit(ARMV7_CYCLE_COUNTER, cpuc->used_mask)) + return -EAGAIN; + + return ARMV7_CYCLE_COUNTER; + } else { + /* + * For anything other than a cycle counter, try and use + * the events counters + */ + for (idx = ARMV7_COUNTER0; idx <= armpmu->num_events; ++idx) { + if (!test_and_set_bit(idx, cpuc->used_mask)) + return idx; + } + + /* The counters are all in use. */ + return -EAGAIN; + } +} + +static struct arm_pmu armv7pmu = { + .handle_irq = armv7pmu_handle_irq, + .enable = armv7pmu_enable_event, + .disable = armv7pmu_disable_event, + .raw_event = armv7pmu_raw_event, + .read_counter = armv7pmu_read_counter, + .write_counter = armv7pmu_write_counter, + .get_event_idx = armv7pmu_get_event_idx, + .start = armv7pmu_start, + .stop = armv7pmu_stop, + .max_period = (1LLU << 32) - 1, +}; + +static u32 __init armv7_reset_read_pmnc(void) +{ + u32 nb_cnt; + + /* Initialize & Reset PMNC: C and P bits */ + armv7_pmnc_write(ARMV7_PMNC_P | ARMV7_PMNC_C); + + /* Read the nb of CNTx counters supported from PMNC */ + nb_cnt = (armv7_pmnc_read() >> ARMV7_PMNC_N_SHIFT) & ARMV7_PMNC_N_MASK; + + /* Add the CPU cycles counter and return */ + return nb_cnt + 1; +} + static int __init init_hw_perf_events(void) { @@ -1199,6 +2103,30 @@ init_hw_perf_events(void) sizeof(armv6mpcore_perf_cache_map)); perf_max_events = armv6mpcore_pmu.num_events; break; + case 0xC080: /* Cortex-A8 */ + armv7pmu.name = ARMV7_PMU_CORTEX_A8_NAME; + memcpy(armpmu_perf_cache_map, armv7_a8_perf_cache_map, + sizeof(armv7_a8_perf_cache_map)); + armv7pmu.event_map = armv7_a8_pmu_event_map; + armpmu = &armv7pmu; + + /* Reset PMNC and read the nb of CNTx counters + supported */ + armv7pmu.num_events = armv7_reset_read_pmnc(); + perf_max_events = armv7pmu.num_events; + break; + case 0xC090: /* Cortex-A9 */ + armv7pmu.name = ARMV7_PMU_CORTEX_A9_NAME; + memcpy(armpmu_perf_cache_map, armv7_a9_perf_cache_map, + sizeof(armv7_a9_perf_cache_map)); + armv7pmu.event_map = armv7_a9_pmu_event_map; + armpmu = &armv7pmu; + + /* Reset PMNC and read the nb of CNTx counters + supported */ + armv7pmu.num_events = armv7_reset_read_pmnc(); + perf_max_events = armv7pmu.num_events; + break; default: pr_info("no hardware support available\n"); perf_max_events = -1; @@ -1206,8 +2134,8 @@ init_hw_perf_events(void) } if (armpmu) - pr_info("enabled with %s PMU driver\n", - armpmu->name); + pr_info("enabled with %s PMU driver, %d counters available\n", + armpmu->name, armpmu->num_events); return 0; } -- cgit v1.2.3 From 6985a5ad0d719d8c8d584a69f6e5d7138a2e19ab Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 20 Nov 2009 10:32:41 +0000 Subject: ARM: PNX4008: convert to clkdev Acked-by: Vitaly Wool Signed-off-by: Russell King --- arch/arm/Kconfig | 1 + arch/arm/mach-pnx4008/clock.c | 66 +++++++++++++++-------------- arch/arm/mach-pnx4008/clock.h | 2 - arch/arm/mach-pnx4008/include/mach/clkdev.h | 7 +++ 4 files changed, 43 insertions(+), 33 deletions(-) create mode 100644 arch/arm/mach-pnx4008/include/mach/clkdev.h (limited to 'arch/arm/Kconfig') diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 4c33ca82f9b1..fb2a51b0ec15 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -554,6 +554,7 @@ config ARCH_PNX4008 bool "Philips Nexperia PNX4008 Mobile" select CPU_ARM926T select HAVE_CLK + select COMMON_CLKDEV help This enables support for Philips PNX4008 mobile platform. diff --git a/arch/arm/mach-pnx4008/clock.c b/arch/arm/mach-pnx4008/clock.c index 898c0e88acbc..6f5d2e502654 100644 --- a/arch/arm/mach-pnx4008/clock.c +++ b/arch/arm/mach-pnx4008/clock.c @@ -22,8 +22,9 @@ #include #include -#include +#include +#include #include #include "clock.h" @@ -747,7 +748,7 @@ static struct clk wdt_ck = { /* These clocks are visible outside this module * and can be initialized */ -static struct clk *onchip_clks[] = { +static struct clk *onchip_clks[] __initdata = { &ck_13MHz, &ck_pll1, &ck_pll4, @@ -777,6 +778,36 @@ static struct clk *onchip_clks[] = { &wdt_ck, }; +static struct clk_lookup onchip_clkreg[] = { + { .clk = &ck_13MHz, .con_id = "ck_13MHz" }, + { .clk = &ck_pll1, .con_id = "ck_pll1" }, + { .clk = &ck_pll4, .con_id = "ck_pll4" }, + { .clk = &ck_pll5, .con_id = "ck_pll5" }, + { .clk = &ck_pll3, .con_id = "ck_pll3" }, + { .clk = &vfp9_ck, .con_id = "vfp9_ck" }, + { .clk = &m2hclk_ck, .con_id = "m2hclk_ck" }, + { .clk = &hclk_ck, .con_id = "hclk_ck" }, + { .clk = &dma_ck, .con_id = "dma_ck" }, + { .clk = &flash_ck, .con_id = "flash_ck" }, + { .clk = &dum_ck, .con_id = "dum_ck" }, + { .clk = &keyscan_ck, .con_id = "keyscan_ck" }, + { .clk = &pwm1_ck, .con_id = "pwm1_ck" }, + { .clk = &pwm2_ck, .con_id = "pwm2_ck" }, + { .clk = &jpeg_ck, .con_id = "jpeg_ck" }, + { .clk = &ms_ck, .con_id = "ms_ck" }, + { .clk = &touch_ck, .con_id = "touch_ck" }, + { .clk = &i2c0_ck, .con_id = "i2c0_ck" }, + { .clk = &i2c1_ck, .con_id = "i2c1_ck" }, + { .clk = &i2c2_ck, .con_id = "i2c2_ck" }, + { .clk = &spi0_ck, .con_id = "spi0_ck" }, + { .clk = &spi1_ck, .con_id = "spi1_ck" }, + { .clk = &uart3_ck, .con_id = "uart3_ck" }, + { .clk = &uart4_ck, .con_id = "uart4_ck" }, + { .clk = &uart5_ck, .con_id = "uart5_ck" }, + { .clk = &uart6_ck, .con_id = "uart6_ck" }, + { .clk = &wdt_ck, .con_id = "wdt_ck" }, +}; + static int local_clk_enable(struct clk *clk) { int ret = 0; @@ -866,35 +897,6 @@ out: EXPORT_SYMBOL(clk_set_rate); -struct clk *clk_get(struct device *dev, const char *id) -{ - struct clk *clk = ERR_PTR(-ENOENT); - struct clk **clkp; - - clock_lock(); - for (clkp = onchip_clks; clkp < onchip_clks + ARRAY_SIZE(onchip_clks); - clkp++) { - if (strcmp(id, (*clkp)->name) == 0 - && try_module_get((*clkp)->owner)) { - clk = (*clkp); - break; - } - } - clock_unlock(); - - return clk; -} -EXPORT_SYMBOL(clk_get); - -void clk_put(struct clk *clk) -{ - clock_lock(); - if (clk && !IS_ERR(clk)) - module_put(clk->owner); - clock_unlock(); -} -EXPORT_SYMBOL(clk_put); - unsigned long clk_get_rate(struct clk *clk) { unsigned long ret; @@ -987,6 +989,8 @@ static int __init clk_init(void) /* Disable autoclocking */ __raw_writeb(0xff, AUTOCLK_CTRL); + clkdev_add_table(onchip_clkreg, ARRAY_SIZE(onchip_clkreg)); + return 0; } diff --git a/arch/arm/mach-pnx4008/clock.h b/arch/arm/mach-pnx4008/clock.h index cd58f372cfd0..933e18133b96 100644 --- a/arch/arm/mach-pnx4008/clock.h +++ b/arch/arm/mach-pnx4008/clock.h @@ -14,8 +14,6 @@ #define __ARCH_ARM_PNX4008_CLOCK_H__ struct clk { - struct list_head node; - struct module *owner; const char *name; struct clk *parent; struct clk *propagate_next; diff --git a/arch/arm/mach-pnx4008/include/mach/clkdev.h b/arch/arm/mach-pnx4008/include/mach/clkdev.h new file mode 100644 index 000000000000..04b37a89801c --- /dev/null +++ b/arch/arm/mach-pnx4008/include/mach/clkdev.h @@ -0,0 +1,7 @@ +#ifndef __ASM_MACH_CLKDEV_H +#define __ASM_MACH_CLKDEV_H + +#define __clk_get(clk) ({ 1; }) +#define __clk_put(clk) do { } while (0) + +#endif -- cgit v1.2.3 From e119bfff1f102f8d1505910cd6c09df55c776b43 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 10 Jan 2010 17:23:29 +0000 Subject: ARM: Move creation of /proc/cpu out of alignment.c Always creating this directory avoids other users having to jump through silly hoops when they want to share this directory. Signed-off-by: Russell King --- arch/arm/Kconfig | 4 ++++ arch/arm/kernel/setup.c | 15 ++++++++++++++- arch/arm/mm/alignment.c | 6 +----- 3 files changed, 19 insertions(+), 6 deletions(-) (limited to 'arch/arm/Kconfig') diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index c2238cd474c7..b224216c11db 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -52,6 +52,9 @@ config HAVE_TCM bool select GENERIC_ALLOCATOR +config HAVE_PROC_CPU + bool + config NO_IOPORT bool @@ -1229,6 +1232,7 @@ config ALIGNMENT_TRAP bool depends on CPU_CP15_MMU default y if !ARCH_EBSA110 + select HAVE_PROC_CPU if PROC_FS help ARM processors cannot fetch/store information which is not naturally aligned on the bus, i.e., a 4 byte fetch must start at an diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index c6c57b640b6b..5357e48f2c39 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include @@ -782,9 +783,21 @@ static int __init topology_init(void) return 0; } - subsys_initcall(topology_init); +#ifdef CONFIG_HAVE_PROC_CPU +static int __init proc_cpu_init(void) +{ + struct proc_dir_entry *res; + + res = proc_mkdir("cpu", NULL); + if (!res) + return -ENOMEM; + return 0; +} +fs_initcall(proc_cpu_init); +#endif + static const char *hwcap_str[] = { "swp", "half", diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index b270d6228fe2..0c5eb6983cef 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -898,11 +898,7 @@ static int __init alignment_init(void) #ifdef CONFIG_PROC_FS struct proc_dir_entry *res; - res = proc_mkdir("cpu", NULL); - if (!res) - return -ENOMEM; - - res = create_proc_entry("alignment", S_IWUSR | S_IRUGO, res); + res = create_proc_entry("cpu/alignment", S_IWUSR | S_IRUGO, NULL); if (!res) return -ENOMEM; -- cgit v1.2.3 From 24b44a66fa240f6fc63343623ca730d39754047e Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 20 Jan 2010 19:05:07 +0100 Subject: ARM: 5889/1: Add atomic64 routines for ARMv6k and above. In preparation for perf-events support, ARM needs to support atomic64_t operations. v6k and above support the ldrexd and strexd instructions to do just that. This patch adds atomic64 support to the ARM architecture. v6k and above make use of new instructions whilst older cores fall back on the generic solution using spinlocks. If and when v7-M cores are supported by Linux, they will need to fall back on the spinlock implementation too. Signed-off-by: Will Deacon Acked-by: Catalin Marinas Signed-off-by: Russell King --- arch/arm/Kconfig | 1 + arch/arm/include/asm/atomic.h | 228 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 229 insertions(+) (limited to 'arch/arm/Kconfig') diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index b224216c11db..762ae536f909 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -12,6 +12,7 @@ config ARM select HAVE_IDE select RTC_LIB select SYS_SUPPORTS_APM_EMULATION + select GENERIC_ATOMIC64 if (!CPU_32v6K) select HAVE_OPROFILE select HAVE_ARCH_KGDB select HAVE_KPROBES if (!XIP_KERNEL) diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h index d0daeab2234e..e8ddec2cb158 100644 --- a/arch/arm/include/asm/atomic.h +++ b/arch/arm/include/asm/atomic.h @@ -235,6 +235,234 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u) #define smp_mb__before_atomic_inc() smp_mb() #define smp_mb__after_atomic_inc() smp_mb() +#ifndef CONFIG_GENERIC_ATOMIC64 +typedef struct { + u64 __aligned(8) counter; +} atomic64_t; + +#define ATOMIC64_INIT(i) { (i) } + +static inline u64 atomic64_read(atomic64_t *v) +{ + u64 result; + + __asm__ __volatile__("@ atomic64_read\n" +" ldrexd %0, %H0, [%1]" + : "=&r" (result) + : "r" (&v->counter) + ); + + return result; +} + +static inline void atomic64_set(atomic64_t *v, u64 i) +{ + u64 tmp; + + __asm__ __volatile__("@ atomic64_set\n" +"1: ldrexd %0, %H0, [%1]\n" +" strexd %0, %2, %H2, [%1]\n" +" teq %0, #0\n" +" bne 1b" + : "=&r" (tmp) + : "r" (&v->counter), "r" (i) + : "cc"); +} + +static inline void atomic64_add(u64 i, atomic64_t *v) +{ + u64 result; + unsigned long tmp; + + __asm__ __volatile__("@ atomic64_add\n" +"1: ldrexd %0, %H0, [%2]\n" +" adds %0, %0, %3\n" +" adc %H0, %H0, %H3\n" +" strexd %1, %0, %H0, [%2]\n" +" teq %1, #0\n" +" bne 1b" + : "=&r" (result), "=&r" (tmp) + : "r" (&v->counter), "r" (i) + : "cc"); +} + +static inline u64 atomic64_add_return(u64 i, atomic64_t *v) +{ + u64 result; + unsigned long tmp; + + smp_mb(); + + __asm__ __volatile__("@ atomic64_add_return\n" +"1: ldrexd %0, %H0, [%2]\n" +" adds %0, %0, %3\n" +" adc %H0, %H0, %H3\n" +" strexd %1, %0, %H0, [%2]\n" +" teq %1, #0\n" +" bne 1b" + : "=&r" (result), "=&r" (tmp) + : "r" (&v->counter), "r" (i) + : "cc"); + + smp_mb(); + + return result; +} + +static inline void atomic64_sub(u64 i, atomic64_t *v) +{ + u64 result; + unsigned long tmp; + + __asm__ __volatile__("@ atomic64_sub\n" +"1: ldrexd %0, %H0, [%2]\n" +" subs %0, %0, %3\n" +" sbc %H0, %H0, %H3\n" +" strexd %1, %0, %H0, [%2]\n" +" teq %1, #0\n" +" bne 1b" + : "=&r" (result), "=&r" (tmp) + : "r" (&v->counter), "r" (i) + : "cc"); +} + +static inline u64 atomic64_sub_return(u64 i, atomic64_t *v) +{ + u64 result; + unsigned long tmp; + + smp_mb(); + + __asm__ __volatile__("@ atomic64_sub_return\n" +"1: ldrexd %0, %H0, [%2]\n" +" subs %0, %0, %3\n" +" sbc %H0, %H0, %H3\n" +" strexd %1, %0, %H0, [%2]\n" +" teq %1, #0\n" +" bne 1b" + : "=&r" (result), "=&r" (tmp) + : "r" (&v->counter), "r" (i) + : "cc"); + + smp_mb(); + + return result; +} + +static inline u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old, u64 new) +{ + u64 oldval; + unsigned long res; + + smp_mb(); + + do { + __asm__ __volatile__("@ atomic64_cmpxchg\n" + "ldrexd %1, %H1, [%2]\n" + "mov %0, #0\n" + "teq %1, %3\n" + "teqeq %H1, %H3\n" + "strexdeq %0, %4, %H4, [%2]" + : "=&r" (res), "=&r" (oldval) + : "r" (&ptr->counter), "r" (old), "r" (new) + : "cc"); + } while (res); + + smp_mb(); + + return oldval; +} + +static inline u64 atomic64_xchg(atomic64_t *ptr, u64 new) +{ + u64 result; + unsigned long tmp; + + smp_mb(); + + __asm__ __volatile__("@ atomic64_xchg\n" +"1: ldrexd %0, %H0, [%2]\n" +" strexd %1, %3, %H3, [%2]\n" +" teq %1, #0\n" +" bne 1b" + : "=&r" (result), "=&r" (tmp) + : "r" (&ptr->counter), "r" (new) + : "cc"); + + smp_mb(); + + return result; +} + +static inline u64 atomic64_dec_if_positive(atomic64_t *v) +{ + u64 result; + unsigned long tmp; + + smp_mb(); + + __asm__ __volatile__("@ atomic64_dec_if_positive\n" +"1: ldrexd %0, %H0, [%2]\n" +" subs %0, %0, #1\n" +" sbc %H0, %H0, #0\n" +" teq %H0, #0\n" +" bmi 2f\n" +" strexd %1, %0, %H0, [%2]\n" +" teq %1, #0\n" +" bne 1b\n" +"2:" + : "=&r" (result), "=&r" (tmp) + : "r" (&v->counter) + : "cc"); + + smp_mb(); + + return result; +} + +static inline int atomic64_add_unless(atomic64_t *v, u64 a, u64 u) +{ + u64 val; + unsigned long tmp; + int ret = 1; + + smp_mb(); + + __asm__ __volatile__("@ atomic64_add_unless\n" +"1: ldrexd %0, %H0, [%3]\n" +" teq %0, %4\n" +" teqeq %H0, %H4\n" +" moveq %1, #0\n" +" beq 2f\n" +" adds %0, %0, %5\n" +" adc %H0, %H0, %H5\n" +" strexd %2, %0, %H0, [%3]\n" +" teq %2, #0\n" +" bne 1b\n" +"2:" + : "=&r" (val), "=&r" (ret), "=&r" (tmp) + : "r" (&v->counter), "r" (u), "r" (a) + : "cc"); + + if (ret) + smp_mb(); + + return ret; +} + +#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) +#define atomic64_inc(v) atomic64_add(1LL, (v)) +#define atomic64_inc_return(v) atomic64_add_return(1LL, (v)) +#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) +#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0) +#define atomic64_dec(v) atomic64_sub(1LL, (v)) +#define atomic64_dec_return(v) atomic64_sub_return(1LL, (v)) +#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0) +#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1LL, 0LL) + +#else /* !CONFIG_GENERIC_ATOMIC64 */ +#include +#endif #include #endif #endif -- cgit v1.2.3 From 9e65582a8e8715f883a34eea66e0643778ce878d Mon Sep 17 00:00:00 2001 From: Santosh Shilimkar Date: Thu, 4 Feb 2010 19:42:42 +0100 Subject: ARM: 5919/1: ARM: L2 : Errata 588369: Clean & Invalidate do not invalidate clean lines This patch implements the work-around for the errata 588369.The secure API is used to alter L2 debug register because of trust-zone. This version updated with comments from Russell and Catalin and generated against 2.6.33-rc6 mainline kernel. Detail comments can be found: http://www.spinics.net/lists/linux-omap/msg23431.html Signed-off-by: Woodruff Richard Signed-off-by: Santosh Shilimkar Acked-by: Catalin Marinas Acked-by: Tony Lindgren Signed-off-by: Russell King --- arch/arm/Kconfig | 13 +++++++++++++ arch/arm/mm/cache-l2x0.c | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 49 insertions(+) (limited to 'arch/arm/Kconfig') diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 762ae536f909..0f1ad743ccdd 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -924,6 +924,19 @@ config ARM_ERRATA_460075 ACTLR register. Note that setting specific bits in the ACTLR register may not be available in non-secure mode. +config PL310_ERRATA_588369 + bool "Clean & Invalidate maintenance operations do not invalidate clean lines" + depends on CACHE_L2X0 && ARCH_OMAP4 + help + The PL310 L2 cache controller implements three types of Clean & + Invalidate maintenance operations: by Physical Address + (offset 0x7F0), by Index/Way (0x7F8) and by Way (0x7FC). + They are architecturally defined to behave as the execution of a + clean operation followed immediately by an invalidate operation, + both performing to the same memory location. This functionality + is not correctly implemented in PL310 as clean lines are not + invalidated as a result of these operations. Note that this errata + uses Texas Instrument's secure monitor api. endmenu source "arch/arm/common/Kconfig" diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index 1a14d18e5713..07334632d3e2 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -56,12 +56,42 @@ static inline void l2x0_inv_line(unsigned long addr) writel(addr, base + L2X0_INV_LINE_PA); } +#ifdef CONFIG_PL310_ERRATA_588369 +static void debug_writel(unsigned long val) +{ + extern void omap_smc1(u32 fn, u32 arg); + + /* + * Texas Instrument secure monitor api to modify the + * PL310 Debug Control Register. + */ + omap_smc1(0x100, val); +} + +static inline void l2x0_flush_line(unsigned long addr) +{ + void __iomem *base = l2x0_base; + + /* Clean by PA followed by Invalidate by PA */ + cache_wait(base + L2X0_CLEAN_LINE_PA, 1); + writel(addr, base + L2X0_CLEAN_LINE_PA); + cache_wait(base + L2X0_INV_LINE_PA, 1); + writel(addr, base + L2X0_INV_LINE_PA); +} +#else + +/* Optimised out for non-errata case */ +static inline void debug_writel(unsigned long val) +{ +} + static inline void l2x0_flush_line(unsigned long addr) { void __iomem *base = l2x0_base; cache_wait(base + L2X0_CLEAN_INV_LINE_PA, 1); writel(addr, base + L2X0_CLEAN_INV_LINE_PA); } +#endif static inline void l2x0_inv_all(void) { @@ -83,13 +113,17 @@ static void l2x0_inv_range(unsigned long start, unsigned long end) spin_lock_irqsave(&l2x0_lock, flags); if (start & (CACHE_LINE_SIZE - 1)) { start &= ~(CACHE_LINE_SIZE - 1); + debug_writel(0x03); l2x0_flush_line(start); + debug_writel(0x00); start += CACHE_LINE_SIZE; } if (end & (CACHE_LINE_SIZE - 1)) { end &= ~(CACHE_LINE_SIZE - 1); + debug_writel(0x03); l2x0_flush_line(end); + debug_writel(0x00); } while (start < end) { @@ -145,10 +179,12 @@ static void l2x0_flush_range(unsigned long start, unsigned long end) while (start < end) { unsigned long blk_end = start + min(end - start, 4096UL); + debug_writel(0x03); while (start < blk_end) { l2x0_flush_line(start); start += CACHE_LINE_SIZE; } + debug_writel(0x00); if (blk_end < end) { spin_unlock_irqrestore(&l2x0_lock, flags); -- cgit v1.2.3 From d6d502fa4be1acd01971476fc732c95a4da16d90 Mon Sep 17 00:00:00 2001 From: Kukjin Kim Date: Mon, 22 Feb 2010 00:02:59 +0100 Subject: ARM: 5952/1: ARM: MM: Add ARM_L1_CACHE_SHIFT_6 for handle inside each ARCH Kconfig Add ARM_L1_CACHE_SHIFT_6 to arch/arm/Kconfig to allow CPUs with L1 cache lines which are 64bytes to indicate this without having to alter the arch/arm/mm/Kconfig entry each time. Update the mm Kconfig so that ARM_L1_CACHE_SHIFT default value uses this and change OMAP3 and S5PC1XX to select ARM_L1_CACHE_SHIFT_6. Acked-by: Ben Dooks Acked-by: Tony Lindgren Signed-off-by: Kukjin Kim Signed-off-by: Russell King --- arch/arm/Kconfig | 6 ++++++ arch/arm/mm/Kconfig | 2 +- arch/arm/plat-omap/Kconfig | 1 + 3 files changed, 8 insertions(+), 1 deletion(-) (limited to 'arch/arm/Kconfig') diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 0f1ad743ccdd..04247ba31d69 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -165,6 +165,11 @@ config ARCH_MTD_XIP config GENERIC_HARDIRQS_NO__DO_IRQ def_bool y +config ARM_L1_CACHE_SHIFT_6 + bool + help + Setting ARM L1 cache line size to 64 Bytes. + if OPROFILE config OPROFILE_ARMV6 @@ -642,6 +647,7 @@ config ARCH_S5PC1XX select GENERIC_GPIO select HAVE_CLK select CPU_V7 + select ARM_L1_CACHE_SHIFT_6 help Samsung S5PC1XX series based systems diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index e859743024a0..c4ed9f93f646 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -779,5 +779,5 @@ config CACHE_XSC3L2 config ARM_L1_CACHE_SHIFT int - default 6 if ARCH_OMAP3 || ARCH_S5PC1XX + default 6 if ARM_L1_CACHE_SHIFT_6 default 5 diff --git a/arch/arm/plat-omap/Kconfig b/arch/arm/plat-omap/Kconfig index e2ea04a4c8a1..2e3eec660864 100644 --- a/arch/arm/plat-omap/Kconfig +++ b/arch/arm/plat-omap/Kconfig @@ -22,6 +22,7 @@ config ARCH_OMAP3 bool "TI OMAP3" select CPU_V7 select COMMON_CLKDEV + select ARM_L1_CACHE_SHIFT_6 config ARCH_OMAP4 bool "TI OMAP4" -- cgit v1.2.3