From 5cfc8ee0bb5134e1204e1ec5843e164f24315021 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 24 Mar 2010 00:22:36 +0000 Subject: ARM: convert arm to arch_gettimeoffset() Convert arm to use GENERIC_TIME via the arch_getoffset() infrastructure, reducing the amount of arch specific code we need to maintain. The arm architecture is the last arch that need to be converted. Signed-off-by: John Stultz Signed-off-by: Russell King Cc: Andrew Morton --- arch/arm/kernel/time.c | 70 +++++--------------------------------------------- 1 file changed, 6 insertions(+), 64 deletions(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c index 28753805d2d..38c261f9951 100644 --- a/arch/arm/kernel/time.c +++ b/arch/arm/kernel/time.c @@ -72,12 +72,15 @@ unsigned long profile_pc(struct pt_regs *regs) EXPORT_SYMBOL(profile_pc); #endif -#ifndef CONFIG_GENERIC_TIME -static unsigned long dummy_gettimeoffset(void) +#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET +u32 arch_gettimeoffset(void) { + if (system_timer->offset != NULL) + return system_timer->offset() * 1000; + return 0; } -#endif +#endif /* CONFIG_ARCH_USES_GETTIMEOFFSET */ #ifdef CONFIG_LEDS_TIMER static inline void do_leds(void) @@ -93,63 +96,6 @@ static inline void do_leds(void) #define do_leds() #endif -#ifndef CONFIG_GENERIC_TIME -void do_gettimeofday(struct timeval *tv) -{ - unsigned long flags; - unsigned long seq; - unsigned long usec, sec; - - do { - seq = read_seqbegin_irqsave(&xtime_lock, flags); - usec = system_timer->offset(); - sec = xtime.tv_sec; - usec += xtime.tv_nsec / 1000; - } while (read_seqretry_irqrestore(&xtime_lock, seq, flags)); - - /* usec may have gone up a lot: be safe */ - while (usec >= 1000000) { - usec -= 1000000; - sec++; - } - - tv->tv_sec = sec; - tv->tv_usec = usec; -} - -EXPORT_SYMBOL(do_gettimeofday); - -int do_settimeofday(struct timespec *tv) -{ - time_t wtm_sec, sec = tv->tv_sec; - long wtm_nsec, nsec = tv->tv_nsec; - - if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC) - return -EINVAL; - - write_seqlock_irq(&xtime_lock); - /* - * This is revolting. We need to set "xtime" correctly. However, the - * value in this location is the value at the most recent update of - * wall time. Discover what correction gettimeofday() would have - * done, and then undo it! - */ - nsec -= system_timer->offset() * NSEC_PER_USEC; - - wtm_sec = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec); - wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec); - - set_normalized_timespec(&xtime, sec, nsec); - set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); - - ntp_clear(); - write_sequnlock_irq(&xtime_lock); - clock_was_set(); - return 0; -} - -EXPORT_SYMBOL(do_settimeofday); -#endif /* !CONFIG_GENERIC_TIME */ #ifndef CONFIG_GENERIC_CLOCKEVENTS /* @@ -214,10 +160,6 @@ device_initcall(timer_init_sysfs); void __init time_init(void) { -#ifndef CONFIG_GENERIC_TIME - if (system_timer->offset == NULL) - system_timer->offset = dummy_gettimeoffset; -#endif system_timer->init(); } -- cgit v1.2.3-70-g09d2 From e193ba290f0228453341b41ab2bbdd963259f97e Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 24 Dec 2009 18:32:13 +0000 Subject: ARM: dma: add /proc/dma support to arch/arm/kernel/dma.c We have our own private implementation for ISA-like DMA which has been missing exposure via the /proc/dma interface. Add support for this. Signed-off-by: Russell King --- arch/arm/kernel/dma.c | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'arch/arm/kernel') diff --git a/arch/arm/kernel/dma.c b/arch/arm/kernel/dma.c index 7d5b9fb01e7..2c4a185f92c 100644 --- a/arch/arm/kernel/dma.c +++ b/arch/arm/kernel/dma.c @@ -16,6 +16,8 @@ #include #include #include +#include +#include #include @@ -264,3 +266,37 @@ int get_dma_residue(unsigned int chan) return ret; } EXPORT_SYMBOL(get_dma_residue); + +#ifdef CONFIG_PROC_FS +static int proc_dma_show(struct seq_file *m, void *v) +{ + int i; + + for (i = 0 ; i < MAX_DMA_CHANNELS ; i++) { + dma_t *dma = dma_channel(i); + if (dma && dma->lock) + seq_printf(m, "%2d: %s\n", i, dma->device_id); + } + return 0; +} + +static int proc_dma_open(struct inode *inode, struct file *file) +{ + return single_open(file, proc_dma_show, NULL); +} + +static const struct file_operations proc_dma_operations = { + .open = proc_dma_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init proc_dma_init(void) +{ + proc_create("dma", 0, NULL, &proc_dma_operations); + return 0; +} + +__initcall(proc_dma_init); +#endif -- cgit v1.2.3-70-g09d2 From 52882173cfed4fabcc1496755000bf022d681e52 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Mon, 19 Apr 2010 13:20:49 +0100 Subject: ARM: 6058/1: Add support for PCI domains This patch adds support for PCI domains on ARM platforms. Also, protect asm/mach/pci.h from multiple inclustions, otherwise build fails because of pci_domain_nr() and pci_proc_domain() redefinitions. Signed-off-by: Anton Vorontsov Signed-off-by: Russell King --- arch/arm/Kconfig | 4 ++++ arch/arm/include/asm/mach/pci.h | 11 +++++++++++ arch/arm/include/asm/pci.h | 15 +++++++++++++++ arch/arm/kernel/bios32.c | 3 +++ 4 files changed, 33 insertions(+) (limited to 'arch/arm/kernel') diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 5c8128c7699..88f9334110c 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1074,6 +1074,10 @@ config PCI your box. Other bus systems are ISA, EISA, MicroChannel (MCA) or VESA. If you have PCI, say Y, otherwise N. +config PCI_DOMAINS + bool + depends on PCI + config PCI_SYSCALL def_bool PCI diff --git a/arch/arm/include/asm/mach/pci.h b/arch/arm/include/asm/mach/pci.h index a38bdc7afa3..52f0da1e97d 100644 --- a/arch/arm/include/asm/mach/pci.h +++ b/arch/arm/include/asm/mach/pci.h @@ -8,10 +8,16 @@ * published by the Free Software Foundation. */ +#ifndef __ASM_MACH_PCI_H +#define __ASM_MACH_PCI_H + struct pci_sys_data; struct pci_bus; struct hw_pci { +#ifdef CONFIG_PCI_DOMAINS + int domain; +#endif struct list_head buses; int nr_controllers; int (*setup)(int nr, struct pci_sys_data *); @@ -26,6 +32,9 @@ struct hw_pci { * Per-controller structure */ struct pci_sys_data { +#ifdef CONFIG_PCI_DOMAINS + int domain; +#endif struct list_head node; int busnr; /* primary bus number */ u64 mem_offset; /* bus->cpu memory mapping offset */ @@ -70,3 +79,5 @@ extern int pci_v3_setup(int nr, struct pci_sys_data *); extern struct pci_bus *pci_v3_scan_bus(int nr, struct pci_sys_data *); extern void pci_v3_preinit(void); extern void pci_v3_postinit(void); + +#endif /* __ASM_MACH_PCI_H */ diff --git a/arch/arm/include/asm/pci.h b/arch/arm/include/asm/pci.h index 47980118d0a..92e2a833693 100644 --- a/arch/arm/include/asm/pci.h +++ b/arch/arm/include/asm/pci.h @@ -4,8 +4,23 @@ #ifdef __KERNEL__ #include +#include /* for pci_sys_data */ #include /* for PCIBIOS_MIN_* */ +#ifdef CONFIG_PCI_DOMAINS +static inline int pci_domain_nr(struct pci_bus *bus) +{ + struct pci_sys_data *root = bus->sysdata; + + return root->domain; +} + +static inline int pci_proc_domain(struct pci_bus *bus) +{ + return pci_domain_nr(bus); +} +#endif /* CONFIG_PCI_DOMAINS */ + #ifdef CONFIG_PCI_HOST_ITE8152 /* ITE bridge requires setting latency timer to avoid early bus access termination by PIC bus mater devices diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c index bd397e0b663..c6273a3bfc2 100644 --- a/arch/arm/kernel/bios32.c +++ b/arch/arm/kernel/bios32.c @@ -527,6 +527,9 @@ static void __init pcibios_init_hw(struct hw_pci *hw) if (!sys) panic("PCI: unable to allocate sys data!"); +#ifdef CONFIG_PCI_DOMAINS + sys->domain = hw->domain; +#endif sys->hw = hw; sys->busnr = busnr; sys->swizzle = hw->swizzle; -- cgit v1.2.3-70-g09d2 From ee3c454b8da04815c1884ed85fe89d2d131c0e51 Mon Sep 17 00:00:00 2001 From: Daniel Walker Date: Fri, 1 Jan 2010 14:52:30 -0800 Subject: arm: msm: add oprofile pmu support add oprofile pmu support for msm. Signed-off-by: Daniel Walker --- arch/arm/kernel/pmu.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/arm/kernel') diff --git a/arch/arm/kernel/pmu.c b/arch/arm/kernel/pmu.c index a124312e343..4f0eb4c2a72 100644 --- a/arch/arm/kernel/pmu.c +++ b/arch/arm/kernel/pmu.c @@ -44,6 +44,8 @@ static const int irqs[] = { IRQ_IOP33X_CORE_PMU, #elif defined(CONFIG_ARCH_PXA) IRQ_PMU, +#elif defined(CONFIG_ARCH_MSM_ARM11) + INT_ARM11_PMU, #endif }; -- cgit v1.2.3-70-g09d2 From 1252fa3154fae1f9624ea40cbbf0ea5e21319013 Mon Sep 17 00:00:00 2001 From: Daniel Walker Date: Fri, 7 May 2010 12:09:52 -0700 Subject: Revert "arm: msm: add oprofile pmu support" This reverts commit ee3c454b8da04815c1884ed85fe89d2d131c0e51. As request by Russell King. Signed-off-by: Daniel Walker --- arch/arm/kernel/pmu.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/kernel/pmu.c b/arch/arm/kernel/pmu.c index 4f0eb4c2a72..a124312e343 100644 --- a/arch/arm/kernel/pmu.c +++ b/arch/arm/kernel/pmu.c @@ -44,8 +44,6 @@ static const int irqs[] = { IRQ_IOP33X_CORE_PMU, #elif defined(CONFIG_ARCH_PXA) IRQ_PMU, -#elif defined(CONFIG_ARCH_MSM_ARM11) - INT_ARM11_PMU, #endif }; -- cgit v1.2.3-70-g09d2 From f4a27aed48584b9e4699e9ee76288618a8574d77 Mon Sep 17 00:00:00 2001 From: Srinidhi Kasagar Date: Wed, 12 May 2010 05:52:18 +0100 Subject: ARM: 6125/1: ARM TWD: move TWD registers to common header This moves the TWD register set of MPcore to a common existing file so that watchdog driver can access it Signed-off-by: srinidhi kasagar Acked-by: Linus Walleij Signed-off-by: Russell King --- arch/arm/include/asm/smp_twd.h | 17 +++++++++++++++++ arch/arm/kernel/smp_twd.c | 17 ----------------- 2 files changed, 17 insertions(+), 17 deletions(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/include/asm/smp_twd.h b/arch/arm/include/asm/smp_twd.h index 7be0978b262..634f357be6b 100644 --- a/arch/arm/include/asm/smp_twd.h +++ b/arch/arm/include/asm/smp_twd.h @@ -1,6 +1,23 @@ #ifndef __ASMARM_SMP_TWD_H #define __ASMARM_SMP_TWD_H +#define TWD_TIMER_LOAD 0x00 +#define TWD_TIMER_COUNTER 0x04 +#define TWD_TIMER_CONTROL 0x08 +#define TWD_TIMER_INTSTAT 0x0C + +#define TWD_WDOG_LOAD 0x20 +#define TWD_WDOG_COUNTER 0x24 +#define TWD_WDOG_CONTROL 0x28 +#define TWD_WDOG_INTSTAT 0x2C +#define TWD_WDOG_RESETSTAT 0x30 +#define TWD_WDOG_DISABLE 0x34 + +#define TWD_TIMER_CONTROL_ENABLE (1 << 0) +#define TWD_TIMER_CONTROL_ONESHOT (0 << 1) +#define TWD_TIMER_CONTROL_PERIODIC (1 << 1) +#define TWD_TIMER_CONTROL_IT_ENABLE (1 << 2) + struct clock_event_device; extern void __iomem *twd_base; diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c index ea02a7b1c24..7c5f0c024db 100644 --- a/arch/arm/kernel/smp_twd.c +++ b/arch/arm/kernel/smp_twd.c @@ -21,23 +21,6 @@ #include #include -#define TWD_TIMER_LOAD 0x00 -#define TWD_TIMER_COUNTER 0x04 -#define TWD_TIMER_CONTROL 0x08 -#define TWD_TIMER_INTSTAT 0x0C - -#define TWD_WDOG_LOAD 0x20 -#define TWD_WDOG_COUNTER 0x24 -#define TWD_WDOG_CONTROL 0x28 -#define TWD_WDOG_INTSTAT 0x2C -#define TWD_WDOG_RESETSTAT 0x30 -#define TWD_WDOG_DISABLE 0x34 - -#define TWD_TIMER_CONTROL_ENABLE (1 << 0) -#define TWD_TIMER_CONTROL_ONESHOT (0 << 1) -#define TWD_TIMER_CONTROL_PERIODIC (1 << 1) -#define TWD_TIMER_CONTROL_IT_ENABLE (1 << 2) - /* set up by the platform code */ void __iomem *twd_base; -- cgit v1.2.3-70-g09d2 From 8e2a43f5f5e1255879064924917fb1a6e5be7cb3 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 15 May 2010 10:18:05 +0100 Subject: ARM: rename mach_cpu_disable() to platform_cpu_disable() Consistently name all SMP platform related functions. Signed-off-by: Russell King --- arch/arm/include/asm/smp.h | 2 +- arch/arm/kernel/smp.c | 2 +- arch/arm/mach-realview/hotplug.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h index e0d763be184..3d05190797c 100644 --- a/arch/arm/include/asm/smp.h +++ b/arch/arm/include/asm/smp.h @@ -82,7 +82,7 @@ struct secondary_data { extern struct secondary_data secondary_data; extern int __cpu_disable(void); -extern int mach_cpu_disable(unsigned int cpu); +extern int platform_cpu_disable(unsigned int cpu); extern void __cpu_die(unsigned int cpu); extern void cpu_die(void); diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 577543f3857..7a3cc026693 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -162,7 +162,7 @@ int __cpu_disable(void) struct task_struct *p; int ret; - ret = mach_cpu_disable(cpu); + ret = platform_cpu_disable(cpu); if (ret) return ret; diff --git a/arch/arm/mach-realview/hotplug.c b/arch/arm/mach-realview/hotplug.c index be048e3e879..f95521a5e5c 100644 --- a/arch/arm/mach-realview/hotplug.c +++ b/arch/arm/mach-realview/hotplug.c @@ -131,7 +131,7 @@ void platform_cpu_die(unsigned int cpu) cpu_leave_lowpower(); } -int mach_cpu_disable(unsigned int cpu) +int platform_cpu_disable(unsigned int cpu) { /* * we don't allow CPU 0 to be shutdown (it is still too special -- cgit v1.2.3-70-g09d2 From 49c006b93769a86bec2b32b9234abf016ac0d50e Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 29 Apr 2010 17:13:24 +0100 Subject: ARM: 6064/1: pmu: register IRQs at runtime The current PMU infrastructure for ARM requires that the IRQs for the PMU device are fixed at compile time and are selected based on the ARCH_ or MACH_ flags. This has the disadvantage of tying the Kernel down to a particular board as far as profiling is concerned. This patch replaces the compile-time IRQ registration with a runtime mechanism which allows the IRQs to be registered with the framework as a platform_device. A further advantage of this change is that there is scope for registering different types of performance counters in the future by changing the id of the platform_device and attaching different resources to it. Acked-by: Jamie Iles Signed-off-by: Will Deacon Signed-off-by: Russell King --- arch/arm/include/asm/pmu.h | 27 ++++----- arch/arm/kernel/perf_event.c | 52 +++++++++++------- arch/arm/kernel/pmu.c | 127 ++++++++++++++++++++++++++++--------------- 3 files changed, 126 insertions(+), 80 deletions(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h index 44bec1f02cb..8ccea012722 100644 --- a/arch/arm/include/asm/pmu.h +++ b/arch/arm/include/asm/pmu.h @@ -19,31 +19,26 @@ enum arm_pmu_type { #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() + * The platform_device for the system is returned on success, ERR_PTR() * encoded error on failure. */ -extern const struct pmu_irqs * -reserve_pmu(void); +extern struct platform_device * +reserve_pmu(enum arm_pmu_type device); /** * 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 + * this. The platform_device returned from reserve_pmu() must be passed as * a cookie. */ extern int -release_pmu(const struct pmu_irqs *irqs); +release_pmu(struct platform_device *pdev); /** * init_pmu() - Initialise the PMU. @@ -53,24 +48,26 @@ release_pmu(const struct pmu_irqs *irqs); * the actual hardware initialisation. */ extern int -init_pmu(void); +init_pmu(enum arm_pmu_type device); #else /* CONFIG_CPU_HAS_PMU */ -static inline const struct pmu_irqs * -reserve_pmu(void) +#include + +static inline struct platform_device * +reserve_pmu(enum arm_pmu_type device) { return ERR_PTR(-ENODEV); } static inline int -release_pmu(const struct pmu_irqs *irqs) +release_pmu(struct platform_device *pdev) { return -ENODEV; } static inline int -init_pmu(void) +init_pmu(enum arm_pmu_type device) { return -ENODEV; } diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 9e70f2053f9..89a77fcb13e 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -26,7 +27,7 @@ #include #include -static const struct pmu_irqs *pmu_irqs; +static struct platform_device *pmu_device; /* * Hardware lock to serialize accesses to PMU registers. Needed for the @@ -314,38 +315,44 @@ validate_group(struct perf_event *event) static int armpmu_reserve_hardware(void) { - int i; - int err; + int i, err = -ENODEV, irq; - pmu_irqs = reserve_pmu(); - if (IS_ERR(pmu_irqs)) { + pmu_device = reserve_pmu(ARM_PMU_DEVICE_CPU); + if (IS_ERR(pmu_device)) { pr_warning("unable to reserve pmu\n"); - return PTR_ERR(pmu_irqs); + return PTR_ERR(pmu_device); } - init_pmu(); + init_pmu(ARM_PMU_DEVICE_CPU); - if (pmu_irqs->num_irqs < 1) { + if (pmu_device->num_resources < 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, + for (i = 0; i < pmu_device->num_resources; ++i) { + irq = platform_get_irq(pmu_device, i); + if (irq < 0) + continue; + + err = request_irq(irq, armpmu->handle_irq, IRQF_DISABLED | IRQF_NOBALANCING, "armpmu", NULL); if (err) { - pr_warning("unable to request IRQ%d for ARM " - "perf counters\n", pmu_irqs->irqs[i]); + pr_warning("unable to request IRQ%d for ARM perf " + "counters\n", irq); break; } } if (err) { - for (i = i - 1; i >= 0; --i) - free_irq(pmu_irqs->irqs[i], NULL); - release_pmu(pmu_irqs); - pmu_irqs = NULL; + for (i = i - 1; i >= 0; --i) { + irq = platform_get_irq(pmu_device, i); + if (irq >= 0) + free_irq(irq, NULL); + } + release_pmu(pmu_device); + pmu_device = NULL; } return err; @@ -354,14 +361,17 @@ armpmu_reserve_hardware(void) static void armpmu_release_hardware(void) { - int i; + int i, irq; - for (i = pmu_irqs->num_irqs - 1; i >= 0; --i) - free_irq(pmu_irqs->irqs[i], NULL); + for (i = pmu_device->num_resources - 1; i >= 0; --i) { + irq = platform_get_irq(pmu_device, i); + if (irq >= 0) + free_irq(irq, NULL); + } armpmu->stop(); - release_pmu(pmu_irqs); - pmu_irqs = NULL; + release_pmu(pmu_device); + pmu_device = NULL; } static atomic_t active_events = ATOMIC_INIT(0); diff --git a/arch/arm/kernel/pmu.c b/arch/arm/kernel/pmu.c index a124312e343..b8af96ea62e 100644 --- a/arch/arm/kernel/pmu.c +++ b/arch/arm/kernel/pmu.c @@ -2,6 +2,7 @@ * linux/arch/arm/kernel/pmu.c * * Copyright (C) 2009 picoChip Designs Ltd, Jamie Iles + * Copyright (C) 2010 ARM Ltd, Will Deacon * * 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 @@ -9,65 +10,78 @@ * */ +#define pr_fmt(fmt) "PMU: " fmt + #include #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 volatile long pmu_lock; + +static struct platform_device *pmu_devices[ARM_NUM_PMU_DEVICES]; + +static int __devinit pmu_device_probe(struct platform_device *pdev) +{ + + if (pdev->id < 0 || pdev->id >= ARM_NUM_PMU_DEVICES) { + pr_warning("received registration request for unknown " + "device %d\n", pdev->id); + return -EINVAL; + } + + if (pmu_devices[pdev->id]) + pr_warning("registering new PMU device type %d overwrites " + "previous registration!\n", pdev->id); + else + pr_info("registered new PMU device of type %d\n", + pdev->id); -static const struct pmu_irqs pmu_irqs = { - .irqs = irqs, - .num_irqs = ARRAY_SIZE(irqs), + pmu_devices[pdev->id] = pdev; + return 0; +} + +static struct platform_driver pmu_driver = { + .driver = { + .name = "arm-pmu", + }, + .probe = pmu_device_probe, }; -static volatile long pmu_lock; +static int __init register_pmu_driver(void) +{ + return platform_driver_register(&pmu_driver); +} +device_initcall(register_pmu_driver); -const struct pmu_irqs * -reserve_pmu(void) +struct platform_device * +reserve_pmu(enum arm_pmu_type device) { - return test_and_set_bit_lock(0, &pmu_lock) ? ERR_PTR(-EBUSY) : - &pmu_irqs; + struct platform_device *pdev; + + if (test_and_set_bit_lock(device, &pmu_lock)) { + pdev = ERR_PTR(-EBUSY); + } else if (pmu_devices[device] == NULL) { + clear_bit_unlock(device, &pmu_lock); + pdev = ERR_PTR(-ENODEV); + } else { + pdev = pmu_devices[device]; + } + + return pdev; } EXPORT_SYMBOL_GPL(reserve_pmu); int -release_pmu(const struct pmu_irqs *irqs) +release_pmu(struct platform_device *pdev) { - if (WARN_ON(irqs != &pmu_irqs)) + if (WARN_ON(pdev != pmu_devices[pdev->id])) return -EINVAL; - clear_bit_unlock(0, &pmu_lock); + clear_bit_unlock(pdev->id, &pmu_lock); return 0; } EXPORT_SYMBOL_GPL(release_pmu); @@ -87,17 +101,42 @@ set_irq_affinity(int irq, #endif } -int -init_pmu(void) +static int +init_cpu_pmu(void) { int i, err = 0; + struct platform_device *pdev = pmu_devices[ARM_PMU_DEVICE_CPU]; + + if (!pdev) { + err = -ENODEV; + goto out; + } - for (i = 0; i < pmu_irqs.num_irqs; ++i) { - err = set_irq_affinity(pmu_irqs.irqs[i], i); + for (i = 0; i < pdev->num_resources; ++i) { + err = set_irq_affinity(platform_get_irq(pdev, i), i); if (err) break; } +out: + return err; +} + +int +init_pmu(enum arm_pmu_type device) +{ + int err = 0; + + switch (device) { + case ARM_PMU_DEVICE_CPU: + err = init_cpu_pmu(); + break; + default: + pr_warning("attempt to initialise unknown device %d\n", + device); + err = -EINVAL; + } + return err; } EXPORT_SYMBOL_GPL(init_pmu); -- cgit v1.2.3-70-g09d2 From 181193f398e7d8da6b1196138f0e219709621743 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 30 Apr 2010 11:32:44 +0100 Subject: ARM: 6069/1: perf-events: use numeric ID to identify PMU The ARM perf-events framework provides support for a number of different PMUs using struct arm_pmu. The char *name field of this struct can be used to identify the PMU, but this is cumbersome if used outside of perf. This patch replaces the name string for a PMU with an enum, which holds a unique ID for the PMU being represented. This ID can be used to index an array of names within perf, so no functionality is lost. The presence of the ID field, allows other kernel subsystems [currently oprofile] to use their own mappings for the PMU name. Cc: Jean Pihet Acked-by: Jamie Iles Signed-off-by: Will Deacon Signed-off-by: Russell King --- arch/arm/include/asm/perf_event.h | 14 ++++++++++++++ arch/arm/kernel/perf_event.c | 39 +++++++++++++++++++++++++++++---------- 2 files changed, 43 insertions(+), 10 deletions(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/include/asm/perf_event.h b/arch/arm/include/asm/perf_event.h index 49e3049aba3..fa4b32625d3 100644 --- a/arch/arm/include/asm/perf_event.h +++ b/arch/arm/include/asm/perf_event.h @@ -28,4 +28,18 @@ set_perf_event_pending(void) * same indexes here for consistency. */ #define PERF_EVENT_INDEX_OFFSET 1 +/* ARM perf PMU IDs for use by internal perf clients. */ +enum arm_perf_pmu_ids { + ARM_PERF_PMU_ID_XSCALE1 = 0, + ARM_PERF_PMU_ID_XSCALE2, + ARM_PERF_PMU_ID_V6, + ARM_PERF_PMU_ID_V6MP, + ARM_PERF_PMU_ID_CA8, + ARM_PERF_PMU_ID_CA9, + ARM_NUM_PMU_IDS, +}; + +extern enum arm_perf_pmu_ids +armpmu_get_pmu_id(void); + #endif /* __ARM_PERF_EVENT_H__ */ diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 89a77fcb13e..10a0bcdf215 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -16,6 +16,7 @@ #include #include +#include #include #include #include @@ -68,8 +69,18 @@ struct cpu_hw_events { }; DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events); +/* PMU names. */ +static const char *arm_pmu_names[] = { + [ARM_PERF_PMU_ID_XSCALE1] = "xscale1", + [ARM_PERF_PMU_ID_XSCALE2] = "xscale2", + [ARM_PERF_PMU_ID_V6] = "v6", + [ARM_PERF_PMU_ID_V6MP] = "v6mpcore", + [ARM_PERF_PMU_ID_CA8] = "ARMv7 Cortex-A8", + [ARM_PERF_PMU_ID_CA9] = "ARMv7 Cortex-A9", +}; + struct arm_pmu { - char *name; + enum arm_perf_pmu_ids id; 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); @@ -88,6 +99,18 @@ struct arm_pmu { /* Set at runtime when we know what CPU type we are. */ static const struct arm_pmu *armpmu; +enum arm_perf_pmu_ids +armpmu_get_pmu_id(void) +{ + int id = -ENODEV; + + if (armpmu != NULL) + id = armpmu->id; + + return id; +} +EXPORT_SYMBOL_GPL(armpmu_get_pmu_id); + #define HW_OP_UNSUPPORTED 0xFFFF #define C(_x) \ @@ -1154,7 +1177,7 @@ armv6mpcore_pmu_disable_event(struct hw_perf_event *hwc, } static const struct arm_pmu armv6pmu = { - .name = "v6", + .id = ARM_PERF_PMU_ID_V6, .handle_irq = armv6pmu_handle_irq, .enable = armv6pmu_enable_event, .disable = armv6pmu_disable_event, @@ -1177,7 +1200,7 @@ static const struct arm_pmu armv6pmu = { * reset the period and enable the interrupt reporting. */ static const struct arm_pmu armv6mpcore_pmu = { - .name = "v6mpcore", + .id = ARM_PERF_PMU_ID_V6MP, .handle_irq = armv6pmu_handle_irq, .enable = armv6pmu_enable_event, .disable = armv6mpcore_pmu_disable_event, @@ -1207,10 +1230,6 @@ static const struct arm_pmu armv6mpcore_pmu = { * 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, @@ -2115,7 +2134,7 @@ init_hw_perf_events(void) perf_max_events = armv6mpcore_pmu.num_events; break; case 0xC080: /* Cortex-A8 */ - armv7pmu.name = ARMV7_PMU_CORTEX_A8_NAME; + armv7pmu.id = ARM_PERF_PMU_ID_CA8; memcpy(armpmu_perf_cache_map, armv7_a8_perf_cache_map, sizeof(armv7_a8_perf_cache_map)); armv7pmu.event_map = armv7_a8_pmu_event_map; @@ -2127,7 +2146,7 @@ init_hw_perf_events(void) perf_max_events = armv7pmu.num_events; break; case 0xC090: /* Cortex-A9 */ - armv7pmu.name = ARMV7_PMU_CORTEX_A9_NAME; + armv7pmu.id = ARM_PERF_PMU_ID_CA9; memcpy(armpmu_perf_cache_map, armv7_a9_perf_cache_map, sizeof(armv7_a9_perf_cache_map)); armv7pmu.event_map = armv7_a9_pmu_event_map; @@ -2146,7 +2165,7 @@ init_hw_perf_events(void) if (armpmu) pr_info("enabled with %s PMU driver, %d counters available\n", - armpmu->name, armpmu->num_events); + arm_pmu_names[armpmu->id], armpmu->num_events); return 0; } -- cgit v1.2.3-70-g09d2 From 49e6a32f2f0876b6267584d9c7e0e213bca6e2b8 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 30 Apr 2010 11:33:33 +0100 Subject: ARM: 6070/1: perf-events: add support for xscale PMUs The perf-events framework for ARM only supports v6 and v7 cores. This patch adds support for xscale v1 and v2 PMUs to perf, based on the OProfile drivers in arch/arm/oprofile/op_model_xscale.c Signed-off-by: Will Deacon Signed-off-by: Russell King --- arch/arm/kernel/perf_event.c | 827 ++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 821 insertions(+), 6 deletions(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 10a0bcdf215..381f1211233 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -2108,6 +2108,803 @@ static u32 __init armv7_reset_read_pmnc(void) return nb_cnt + 1; } +/* + * ARMv5 [xscale] Performance counter handling code. + * + * Based on xscale OProfile code. + * + * There are two variants of the xscale PMU that we support: + * - xscale1pmu: 2 event counters and a cycle counter + * - xscale2pmu: 4 event counters and a cycle counter + * The two variants share event definitions, but have different + * PMU structures. + */ + +enum xscale_perf_types { + XSCALE_PERFCTR_ICACHE_MISS = 0x00, + XSCALE_PERFCTR_ICACHE_NO_DELIVER = 0x01, + XSCALE_PERFCTR_DATA_STALL = 0x02, + XSCALE_PERFCTR_ITLB_MISS = 0x03, + XSCALE_PERFCTR_DTLB_MISS = 0x04, + XSCALE_PERFCTR_BRANCH = 0x05, + XSCALE_PERFCTR_BRANCH_MISS = 0x06, + XSCALE_PERFCTR_INSTRUCTION = 0x07, + XSCALE_PERFCTR_DCACHE_FULL_STALL = 0x08, + XSCALE_PERFCTR_DCACHE_FULL_STALL_CONTIG = 0x09, + XSCALE_PERFCTR_DCACHE_ACCESS = 0x0A, + XSCALE_PERFCTR_DCACHE_MISS = 0x0B, + XSCALE_PERFCTR_DCACHE_WRITE_BACK = 0x0C, + XSCALE_PERFCTR_PC_CHANGED = 0x0D, + XSCALE_PERFCTR_BCU_REQUEST = 0x10, + XSCALE_PERFCTR_BCU_FULL = 0x11, + XSCALE_PERFCTR_BCU_DRAIN = 0x12, + XSCALE_PERFCTR_BCU_ECC_NO_ELOG = 0x14, + XSCALE_PERFCTR_BCU_1_BIT_ERR = 0x15, + XSCALE_PERFCTR_RMW = 0x16, + /* XSCALE_PERFCTR_CCNT is not hardware defined */ + XSCALE_PERFCTR_CCNT = 0xFE, + XSCALE_PERFCTR_UNUSED = 0xFF, +}; + +enum xscale_counters { + XSCALE_CYCLE_COUNTER = 1, + XSCALE_COUNTER0, + XSCALE_COUNTER1, + XSCALE_COUNTER2, + XSCALE_COUNTER3, +}; + +static const unsigned xscale_perf_map[PERF_COUNT_HW_MAX] = { + [PERF_COUNT_HW_CPU_CYCLES] = XSCALE_PERFCTR_CCNT, + [PERF_COUNT_HW_INSTRUCTIONS] = XSCALE_PERFCTR_INSTRUCTION, + [PERF_COUNT_HW_CACHE_REFERENCES] = HW_OP_UNSUPPORTED, + [PERF_COUNT_HW_CACHE_MISSES] = HW_OP_UNSUPPORTED, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = XSCALE_PERFCTR_BRANCH, + [PERF_COUNT_HW_BRANCH_MISSES] = XSCALE_PERFCTR_BRANCH_MISS, + [PERF_COUNT_HW_BUS_CYCLES] = HW_OP_UNSUPPORTED, +}; + +static const unsigned xscale_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)] = XSCALE_PERFCTR_DCACHE_ACCESS, + [C(RESULT_MISS)] = XSCALE_PERFCTR_DCACHE_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = XSCALE_PERFCTR_DCACHE_ACCESS, + [C(RESULT_MISS)] = XSCALE_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)] = XSCALE_PERFCTR_ICACHE_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = XSCALE_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)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = XSCALE_PERFCTR_DTLB_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = XSCALE_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)] = XSCALE_PERFCTR_ITLB_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = XSCALE_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, + }, + }, +}; + +#define XSCALE_PMU_ENABLE 0x001 +#define XSCALE_PMN_RESET 0x002 +#define XSCALE_CCNT_RESET 0x004 +#define XSCALE_PMU_RESET (CCNT_RESET | PMN_RESET) +#define XSCALE_PMU_CNT64 0x008 + +static inline int +xscalepmu_event_map(int config) +{ + int mapping = xscale_perf_map[config]; + if (HW_OP_UNSUPPORTED == mapping) + mapping = -EOPNOTSUPP; + return mapping; +} + +static u64 +xscalepmu_raw_event(u64 config) +{ + return config & 0xff; +} + +#define XSCALE1_OVERFLOWED_MASK 0x700 +#define XSCALE1_CCOUNT_OVERFLOW 0x400 +#define XSCALE1_COUNT0_OVERFLOW 0x100 +#define XSCALE1_COUNT1_OVERFLOW 0x200 +#define XSCALE1_CCOUNT_INT_EN 0x040 +#define XSCALE1_COUNT0_INT_EN 0x010 +#define XSCALE1_COUNT1_INT_EN 0x020 +#define XSCALE1_COUNT0_EVT_SHFT 12 +#define XSCALE1_COUNT0_EVT_MASK (0xff << XSCALE1_COUNT0_EVT_SHFT) +#define XSCALE1_COUNT1_EVT_SHFT 20 +#define XSCALE1_COUNT1_EVT_MASK (0xff << XSCALE1_COUNT1_EVT_SHFT) + +static inline u32 +xscale1pmu_read_pmnc(void) +{ + u32 val; + asm volatile("mrc p14, 0, %0, c0, c0, 0" : "=r" (val)); + return val; +} + +static inline void +xscale1pmu_write_pmnc(u32 val) +{ + /* upper 4bits and 7, 11 are write-as-0 */ + val &= 0xffff77f; + asm volatile("mcr p14, 0, %0, c0, c0, 0" : : "r" (val)); +} + +static inline int +xscale1_pmnc_counter_has_overflowed(unsigned long pmnc, + enum xscale_counters counter) +{ + int ret = 0; + + switch (counter) { + case XSCALE_CYCLE_COUNTER: + ret = pmnc & XSCALE1_CCOUNT_OVERFLOW; + break; + case XSCALE_COUNTER0: + ret = pmnc & XSCALE1_COUNT0_OVERFLOW; + break; + case XSCALE_COUNTER1: + ret = pmnc & XSCALE1_COUNT1_OVERFLOW; + break; + default: + WARN_ONCE(1, "invalid counter number (%d)\n", counter); + } + + return ret; +} + +static irqreturn_t +xscale1pmu_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; + + /* + * NOTE: there's an A stepping erratum that states if an overflow + * bit already exists and another occurs, the previous + * Overflow bit gets cleared. There's no workaround. + * Fixed in B stepping or later. + */ + pmnc = xscale1pmu_read_pmnc(); + + /* + * Write the value back to clear the overflow flags. Overflow + * flags remain in pmnc for use below. We also disable the PMU + * while we process the interrupt. + */ + xscale1pmu_write_pmnc(pmnc & ~XSCALE_PMU_ENABLE); + + if (!(pmnc & XSCALE1_OVERFLOWED_MASK)) + return IRQ_NONE; + + regs = get_irq_regs(); + + perf_sample_data_init(&data, 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; + + if (!xscale1_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); + } + + perf_event_do_pending(); + + /* + * Re-enable the PMU. + */ + pmnc = xscale1pmu_read_pmnc() | XSCALE_PMU_ENABLE; + xscale1pmu_write_pmnc(pmnc); + + return IRQ_HANDLED; +} + +static void +xscale1pmu_enable_event(struct hw_perf_event *hwc, int idx) +{ + unsigned long val, mask, evt, flags; + + switch (idx) { + case XSCALE_CYCLE_COUNTER: + mask = 0; + evt = XSCALE1_CCOUNT_INT_EN; + break; + case XSCALE_COUNTER0: + mask = XSCALE1_COUNT0_EVT_MASK; + evt = (hwc->config_base << XSCALE1_COUNT0_EVT_SHFT) | + XSCALE1_COUNT0_INT_EN; + break; + case XSCALE_COUNTER1: + mask = XSCALE1_COUNT1_EVT_MASK; + evt = (hwc->config_base << XSCALE1_COUNT1_EVT_SHFT) | + XSCALE1_COUNT1_INT_EN; + break; + default: + WARN_ONCE(1, "invalid counter number (%d)\n", idx); + return; + } + + spin_lock_irqsave(&pmu_lock, flags); + val = xscale1pmu_read_pmnc(); + val &= ~mask; + val |= evt; + xscale1pmu_write_pmnc(val); + spin_unlock_irqrestore(&pmu_lock, flags); +} + +static void +xscale1pmu_disable_event(struct hw_perf_event *hwc, int idx) +{ + unsigned long val, mask, evt, flags; + + switch (idx) { + case XSCALE_CYCLE_COUNTER: + mask = XSCALE1_CCOUNT_INT_EN; + evt = 0; + break; + case XSCALE_COUNTER0: + mask = XSCALE1_COUNT0_INT_EN | XSCALE1_COUNT0_EVT_MASK; + evt = XSCALE_PERFCTR_UNUSED << XSCALE1_COUNT0_EVT_SHFT; + break; + case XSCALE_COUNTER1: + mask = XSCALE1_COUNT1_INT_EN | XSCALE1_COUNT1_EVT_MASK; + evt = XSCALE_PERFCTR_UNUSED << XSCALE1_COUNT1_EVT_SHFT; + break; + default: + WARN_ONCE(1, "invalid counter number (%d)\n", idx); + return; + } + + spin_lock_irqsave(&pmu_lock, flags); + val = xscale1pmu_read_pmnc(); + val &= ~mask; + val |= evt; + xscale1pmu_write_pmnc(val); + spin_unlock_irqrestore(&pmu_lock, flags); +} + +static int +xscale1pmu_get_event_idx(struct cpu_hw_events *cpuc, + struct hw_perf_event *event) +{ + if (XSCALE_PERFCTR_CCNT == event->config_base) { + if (test_and_set_bit(XSCALE_CYCLE_COUNTER, cpuc->used_mask)) + return -EAGAIN; + + return XSCALE_CYCLE_COUNTER; + } else { + if (!test_and_set_bit(XSCALE_COUNTER1, cpuc->used_mask)) { + return XSCALE_COUNTER1; + } + + if (!test_and_set_bit(XSCALE_COUNTER0, cpuc->used_mask)) { + return XSCALE_COUNTER0; + } + + return -EAGAIN; + } +} + +static void +xscale1pmu_start(void) +{ + unsigned long flags, val; + + spin_lock_irqsave(&pmu_lock, flags); + val = xscale1pmu_read_pmnc(); + val |= XSCALE_PMU_ENABLE; + xscale1pmu_write_pmnc(val); + spin_unlock_irqrestore(&pmu_lock, flags); +} + +static void +xscale1pmu_stop(void) +{ + unsigned long flags, val; + + spin_lock_irqsave(&pmu_lock, flags); + val = xscale1pmu_read_pmnc(); + val &= ~XSCALE_PMU_ENABLE; + xscale1pmu_write_pmnc(val); + spin_unlock_irqrestore(&pmu_lock, flags); +} + +static inline u32 +xscale1pmu_read_counter(int counter) +{ + u32 val = 0; + + switch (counter) { + case XSCALE_CYCLE_COUNTER: + asm volatile("mrc p14, 0, %0, c1, c0, 0" : "=r" (val)); + break; + case XSCALE_COUNTER0: + asm volatile("mrc p14, 0, %0, c2, c0, 0" : "=r" (val)); + break; + case XSCALE_COUNTER1: + asm volatile("mrc p14, 0, %0, c3, c0, 0" : "=r" (val)); + break; + } + + return val; +} + +static inline void +xscale1pmu_write_counter(int counter, u32 val) +{ + switch (counter) { + case XSCALE_CYCLE_COUNTER: + asm volatile("mcr p14, 0, %0, c1, c0, 0" : : "r" (val)); + break; + case XSCALE_COUNTER0: + asm volatile("mcr p14, 0, %0, c2, c0, 0" : : "r" (val)); + break; + case XSCALE_COUNTER1: + asm volatile("mcr p14, 0, %0, c3, c0, 0" : : "r" (val)); + break; + } +} + +static const struct arm_pmu xscale1pmu = { + .id = ARM_PERF_PMU_ID_XSCALE1, + .handle_irq = xscale1pmu_handle_irq, + .enable = xscale1pmu_enable_event, + .disable = xscale1pmu_disable_event, + .event_map = xscalepmu_event_map, + .raw_event = xscalepmu_raw_event, + .read_counter = xscale1pmu_read_counter, + .write_counter = xscale1pmu_write_counter, + .get_event_idx = xscale1pmu_get_event_idx, + .start = xscale1pmu_start, + .stop = xscale1pmu_stop, + .num_events = 3, + .max_period = (1LLU << 32) - 1, +}; + +#define XSCALE2_OVERFLOWED_MASK 0x01f +#define XSCALE2_CCOUNT_OVERFLOW 0x001 +#define XSCALE2_COUNT0_OVERFLOW 0x002 +#define XSCALE2_COUNT1_OVERFLOW 0x004 +#define XSCALE2_COUNT2_OVERFLOW 0x008 +#define XSCALE2_COUNT3_OVERFLOW 0x010 +#define XSCALE2_CCOUNT_INT_EN 0x001 +#define XSCALE2_COUNT0_INT_EN 0x002 +#define XSCALE2_COUNT1_INT_EN 0x004 +#define XSCALE2_COUNT2_INT_EN 0x008 +#define XSCALE2_COUNT3_INT_EN 0x010 +#define XSCALE2_COUNT0_EVT_SHFT 0 +#define XSCALE2_COUNT0_EVT_MASK (0xff << XSCALE2_COUNT0_EVT_SHFT) +#define XSCALE2_COUNT1_EVT_SHFT 8 +#define XSCALE2_COUNT1_EVT_MASK (0xff << XSCALE2_COUNT1_EVT_SHFT) +#define XSCALE2_COUNT2_EVT_SHFT 16 +#define XSCALE2_COUNT2_EVT_MASK (0xff << XSCALE2_COUNT2_EVT_SHFT) +#define XSCALE2_COUNT3_EVT_SHFT 24 +#define XSCALE2_COUNT3_EVT_MASK (0xff << XSCALE2_COUNT3_EVT_SHFT) + +static inline u32 +xscale2pmu_read_pmnc(void) +{ + u32 val; + asm volatile("mrc p14, 0, %0, c0, c1, 0" : "=r" (val)); + /* bits 1-2 and 4-23 are read-unpredictable */ + return val & 0xff000009; +} + +static inline void +xscale2pmu_write_pmnc(u32 val) +{ + /* bits 4-23 are write-as-0, 24-31 are write ignored */ + val &= 0xf; + asm volatile("mcr p14, 0, %0, c0, c1, 0" : : "r" (val)); +} + +static inline u32 +xscale2pmu_read_overflow_flags(void) +{ + u32 val; + asm volatile("mrc p14, 0, %0, c5, c1, 0" : "=r" (val)); + return val; +} + +static inline void +xscale2pmu_write_overflow_flags(u32 val) +{ + asm volatile("mcr p14, 0, %0, c5, c1, 0" : : "r" (val)); +} + +static inline u32 +xscale2pmu_read_event_select(void) +{ + u32 val; + asm volatile("mrc p14, 0, %0, c8, c1, 0" : "=r" (val)); + return val; +} + +static inline void +xscale2pmu_write_event_select(u32 val) +{ + asm volatile("mcr p14, 0, %0, c8, c1, 0" : : "r"(val)); +} + +static inline u32 +xscale2pmu_read_int_enable(void) +{ + u32 val; + asm volatile("mrc p14, 0, %0, c4, c1, 0" : "=r" (val)); + return val; +} + +static void +xscale2pmu_write_int_enable(u32 val) +{ + asm volatile("mcr p14, 0, %0, c4, c1, 0" : : "r" (val)); +} + +static inline int +xscale2_pmnc_counter_has_overflowed(unsigned long of_flags, + enum xscale_counters counter) +{ + int ret = 0; + + switch (counter) { + case XSCALE_CYCLE_COUNTER: + ret = of_flags & XSCALE2_CCOUNT_OVERFLOW; + break; + case XSCALE_COUNTER0: + ret = of_flags & XSCALE2_COUNT0_OVERFLOW; + break; + case XSCALE_COUNTER1: + ret = of_flags & XSCALE2_COUNT1_OVERFLOW; + break; + case XSCALE_COUNTER2: + ret = of_flags & XSCALE2_COUNT2_OVERFLOW; + break; + case XSCALE_COUNTER3: + ret = of_flags & XSCALE2_COUNT3_OVERFLOW; + break; + default: + WARN_ONCE(1, "invalid counter number (%d)\n", counter); + } + + return ret; +} + +static irqreturn_t +xscale2pmu_handle_irq(int irq_num, void *dev) +{ + unsigned long pmnc, of_flags; + struct perf_sample_data data; + struct cpu_hw_events *cpuc; + struct pt_regs *regs; + int idx; + + /* Disable the PMU. */ + pmnc = xscale2pmu_read_pmnc(); + xscale2pmu_write_pmnc(pmnc & ~XSCALE_PMU_ENABLE); + + /* Check the overflow flag register. */ + of_flags = xscale2pmu_read_overflow_flags(); + if (!(of_flags & XSCALE2_OVERFLOWED_MASK)) + return IRQ_NONE; + + /* Clear the overflow bits. */ + xscale2pmu_write_overflow_flags(of_flags); + + regs = get_irq_regs(); + + perf_sample_data_init(&data, 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; + + if (!xscale2_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); + } + + perf_event_do_pending(); + + /* + * Re-enable the PMU. + */ + pmnc = xscale2pmu_read_pmnc() | XSCALE_PMU_ENABLE; + xscale2pmu_write_pmnc(pmnc); + + return IRQ_HANDLED; +} + +static void +xscale2pmu_enable_event(struct hw_perf_event *hwc, int idx) +{ + unsigned long flags, ien, evtsel; + + ien = xscale2pmu_read_int_enable(); + evtsel = xscale2pmu_read_event_select(); + + switch (idx) { + case XSCALE_CYCLE_COUNTER: + ien |= XSCALE2_CCOUNT_INT_EN; + break; + case XSCALE_COUNTER0: + ien |= XSCALE2_COUNT0_INT_EN; + evtsel &= ~XSCALE2_COUNT0_EVT_MASK; + evtsel |= hwc->config_base << XSCALE2_COUNT0_EVT_SHFT; + break; + case XSCALE_COUNTER1: + ien |= XSCALE2_COUNT1_INT_EN; + evtsel &= ~XSCALE2_COUNT1_EVT_MASK; + evtsel |= hwc->config_base << XSCALE2_COUNT1_EVT_SHFT; + break; + case XSCALE_COUNTER2: + ien |= XSCALE2_COUNT2_INT_EN; + evtsel &= ~XSCALE2_COUNT2_EVT_MASK; + evtsel |= hwc->config_base << XSCALE2_COUNT2_EVT_SHFT; + break; + case XSCALE_COUNTER3: + ien |= XSCALE2_COUNT3_INT_EN; + evtsel &= ~XSCALE2_COUNT3_EVT_MASK; + evtsel |= hwc->config_base << XSCALE2_COUNT3_EVT_SHFT; + break; + default: + WARN_ONCE(1, "invalid counter number (%d)\n", idx); + return; + } + + spin_lock_irqsave(&pmu_lock, flags); + xscale2pmu_write_event_select(evtsel); + xscale2pmu_write_int_enable(ien); + spin_unlock_irqrestore(&pmu_lock, flags); +} + +static void +xscale2pmu_disable_event(struct hw_perf_event *hwc, int idx) +{ + unsigned long flags, ien, evtsel; + + ien = xscale2pmu_read_int_enable(); + evtsel = xscale2pmu_read_event_select(); + + switch (idx) { + case XSCALE_CYCLE_COUNTER: + ien &= ~XSCALE2_CCOUNT_INT_EN; + break; + case XSCALE_COUNTER0: + ien &= ~XSCALE2_COUNT0_INT_EN; + evtsel &= ~XSCALE2_COUNT0_EVT_MASK; + evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT0_EVT_SHFT; + break; + case XSCALE_COUNTER1: + ien &= ~XSCALE2_COUNT1_INT_EN; + evtsel &= ~XSCALE2_COUNT1_EVT_MASK; + evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT1_EVT_SHFT; + break; + case XSCALE_COUNTER2: + ien &= ~XSCALE2_COUNT2_INT_EN; + evtsel &= ~XSCALE2_COUNT2_EVT_MASK; + evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT2_EVT_SHFT; + break; + case XSCALE_COUNTER3: + ien &= ~XSCALE2_COUNT3_INT_EN; + evtsel &= ~XSCALE2_COUNT3_EVT_MASK; + evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT3_EVT_SHFT; + break; + default: + WARN_ONCE(1, "invalid counter number (%d)\n", idx); + return; + } + + spin_lock_irqsave(&pmu_lock, flags); + xscale2pmu_write_event_select(evtsel); + xscale2pmu_write_int_enable(ien); + spin_unlock_irqrestore(&pmu_lock, flags); +} + +static int +xscale2pmu_get_event_idx(struct cpu_hw_events *cpuc, + struct hw_perf_event *event) +{ + int idx = xscale1pmu_get_event_idx(cpuc, event); + if (idx >= 0) + goto out; + + if (!test_and_set_bit(XSCALE_COUNTER3, cpuc->used_mask)) + idx = XSCALE_COUNTER3; + else if (!test_and_set_bit(XSCALE_COUNTER2, cpuc->used_mask)) + idx = XSCALE_COUNTER2; +out: + return idx; +} + +static void +xscale2pmu_start(void) +{ + unsigned long flags, val; + + spin_lock_irqsave(&pmu_lock, flags); + val = xscale2pmu_read_pmnc() & ~XSCALE_PMU_CNT64; + val |= XSCALE_PMU_ENABLE; + xscale2pmu_write_pmnc(val); + spin_unlock_irqrestore(&pmu_lock, flags); +} + +static void +xscale2pmu_stop(void) +{ + unsigned long flags, val; + + spin_lock_irqsave(&pmu_lock, flags); + val = xscale2pmu_read_pmnc(); + val &= ~XSCALE_PMU_ENABLE; + xscale2pmu_write_pmnc(val); + spin_unlock_irqrestore(&pmu_lock, flags); +} + +static inline u32 +xscale2pmu_read_counter(int counter) +{ + u32 val = 0; + + switch (counter) { + case XSCALE_CYCLE_COUNTER: + asm volatile("mrc p14, 0, %0, c1, c1, 0" : "=r" (val)); + break; + case XSCALE_COUNTER0: + asm volatile("mrc p14, 0, %0, c0, c2, 0" : "=r" (val)); + break; + case XSCALE_COUNTER1: + asm volatile("mrc p14, 0, %0, c1, c2, 0" : "=r" (val)); + break; + case XSCALE_COUNTER2: + asm volatile("mrc p14, 0, %0, c2, c2, 0" : "=r" (val)); + break; + case XSCALE_COUNTER3: + asm volatile("mrc p14, 0, %0, c3, c2, 0" : "=r" (val)); + break; + } + + return val; +} + +static inline void +xscale2pmu_write_counter(int counter, u32 val) +{ + switch (counter) { + case XSCALE_CYCLE_COUNTER: + asm volatile("mcr p14, 0, %0, c1, c1, 0" : : "r" (val)); + break; + case XSCALE_COUNTER0: + asm volatile("mcr p14, 0, %0, c0, c2, 0" : : "r" (val)); + break; + case XSCALE_COUNTER1: + asm volatile("mcr p14, 0, %0, c1, c2, 0" : : "r" (val)); + break; + case XSCALE_COUNTER2: + asm volatile("mcr p14, 0, %0, c2, c2, 0" : : "r" (val)); + break; + case XSCALE_COUNTER3: + asm volatile("mcr p14, 0, %0, c3, c2, 0" : : "r" (val)); + break; + } +} + +static const struct arm_pmu xscale2pmu = { + .id = ARM_PERF_PMU_ID_XSCALE2, + .handle_irq = xscale2pmu_handle_irq, + .enable = xscale2pmu_enable_event, + .disable = xscale2pmu_disable_event, + .event_map = xscalepmu_event_map, + .raw_event = xscalepmu_raw_event, + .read_counter = xscale2pmu_read_counter, + .write_counter = xscale2pmu_write_counter, + .get_event_idx = xscale2pmu_get_event_idx, + .start = xscale2pmu_start, + .stop = xscale2pmu_stop, + .num_events = 5, + .max_period = (1LLU << 32) - 1, +}; + static int __init init_hw_perf_events(void) { @@ -2115,7 +2912,7 @@ init_hw_perf_events(void) unsigned long implementor = (cpuid & 0xFF000000) >> 24; unsigned long part_number = (cpuid & 0xFFF0); - /* We only support ARM CPUs implemented by ARM at the moment. */ + /* ARM Ltd CPUs. */ if (0x41 == implementor) { switch (part_number) { case 0xB360: /* ARM1136 */ @@ -2157,15 +2954,33 @@ init_hw_perf_events(void) 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; + } + /* Intel CPUs [xscale]. */ + } else if (0x69 == implementor) { + part_number = (cpuid >> 13) & 0x7; + switch (part_number) { + case 1: + armpmu = &xscale1pmu; + memcpy(armpmu_perf_cache_map, xscale_perf_cache_map, + sizeof(xscale_perf_cache_map)); + perf_max_events = xscale1pmu.num_events; + break; + case 2: + armpmu = &xscale2pmu; + memcpy(armpmu_perf_cache_map, xscale_perf_cache_map, + sizeof(xscale_perf_cache_map)); + perf_max_events = xscale2pmu.num_events; + break; } } - if (armpmu) + if (armpmu) { pr_info("enabled with %s PMU driver, %d counters available\n", - arm_pmu_names[armpmu->id], armpmu->num_events); + arm_pmu_names[armpmu->id], armpmu->num_events); + } else { + pr_info("no hardware support available\n"); + perf_max_events = -1; + } return 0; } -- cgit v1.2.3-70-g09d2 From 929f5199448a67d41bb249d58815ef77bcd53622 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 30 Apr 2010 11:34:26 +0100 Subject: ARM: 6071/1: perf-events: allow modules to query the number of hardware counters For OProfile to initialise oprofilefs correctly, it needs to know the number of counters it can represent. This patch adds a function to the ARM perf-events backend to return the number of hardware counters available for the current PMU. Cc: Jamie Iles Signed-off-by: Will Deacon Signed-off-by: Russell King --- arch/arm/include/asm/perf_event.h | 3 +++ arch/arm/kernel/perf_event.c | 12 ++++++++++++ 2 files changed, 15 insertions(+) (limited to 'arch/arm/kernel') diff --git a/arch/arm/include/asm/perf_event.h b/arch/arm/include/asm/perf_event.h index fa4b32625d3..48837e6d888 100644 --- a/arch/arm/include/asm/perf_event.h +++ b/arch/arm/include/asm/perf_event.h @@ -42,4 +42,7 @@ enum arm_perf_pmu_ids { extern enum arm_perf_pmu_ids armpmu_get_pmu_id(void); +extern int +armpmu_get_max_events(void); + #endif /* __ARM_PERF_EVENT_H__ */ diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 381f1211233..c45768614c8 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -111,6 +111,18 @@ armpmu_get_pmu_id(void) } EXPORT_SYMBOL_GPL(armpmu_get_pmu_id); +int +armpmu_get_max_events(void) +{ + int max_events = 0; + + if (armpmu != NULL) + max_events = armpmu->num_events; + + return max_events; +} +EXPORT_SYMBOL_GPL(armpmu_get_max_events); + #define HW_OP_UNSUPPORTED 0xFFFF #define C(_x) \ -- cgit v1.2.3-70-g09d2