From 1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 16 Apr 2005 15:20:36 -0700 Subject: Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip! --- arch/arm/oprofile/Kconfig | 23 ++ arch/arm/oprofile/Makefile | 11 + arch/arm/oprofile/common.c | 156 +++++++++++++ arch/arm/oprofile/init.c | 31 +++ arch/arm/oprofile/op_arm_model.h | 29 +++ arch/arm/oprofile/op_counter.h | 29 +++ arch/arm/oprofile/op_model_xscale.c | 443 ++++++++++++++++++++++++++++++++++++ 7 files changed, 722 insertions(+) create mode 100644 arch/arm/oprofile/Kconfig create mode 100644 arch/arm/oprofile/Makefile create mode 100644 arch/arm/oprofile/common.c create mode 100644 arch/arm/oprofile/init.c create mode 100644 arch/arm/oprofile/op_arm_model.h create mode 100644 arch/arm/oprofile/op_counter.h create mode 100644 arch/arm/oprofile/op_model_xscale.c (limited to 'arch/arm/oprofile') diff --git a/arch/arm/oprofile/Kconfig b/arch/arm/oprofile/Kconfig new file mode 100644 index 0000000..19d3773 --- /dev/null +++ b/arch/arm/oprofile/Kconfig @@ -0,0 +1,23 @@ + +menu "Profiling support" + depends on EXPERIMENTAL + +config PROFILING + bool "Profiling support (EXPERIMENTAL)" + help + Say Y here to enable the extended profiling support mechanisms used + by profilers such as OProfile. + + +config OPROFILE + tristate "OProfile system profiling (EXPERIMENTAL)" + depends on PROFILING + help + OProfile is a profiling system capable of profiling the + whole system, include the kernel, kernel modules, libraries, + and applications. + + If unsure, say N. + +endmenu + diff --git a/arch/arm/oprofile/Makefile b/arch/arm/oprofile/Makefile new file mode 100644 index 0000000..ba1a6e9 --- /dev/null +++ b/arch/arm/oprofile/Makefile @@ -0,0 +1,11 @@ +obj-$(CONFIG_OPROFILE) += oprofile.o + +DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \ + oprof.o cpu_buffer.o buffer_sync.o \ + event_buffer.o oprofile_files.o \ + oprofilefs.o oprofile_stats.o \ + timer_int.o ) + +oprofile-y := $(DRIVER_OBJS) init.o +oprofile-$(CONFIG_CPU_XSCALE) += common.o op_model_xscale.o + diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c new file mode 100644 index 0000000..e57dde8 --- /dev/null +++ b/arch/arm/oprofile/common.c @@ -0,0 +1,156 @@ +/** + * @file common.c + * + * @remark Copyright 2004 Oprofile Authors + * @remark Read the file COPYING + * + * @author Zwane Mwaikambo + */ + +#include +#include +#include +#include +#include + +#include "op_counter.h" +#include "op_arm_model.h" + +static struct op_arm_model_spec *pmu_model; +static int pmu_enabled; +static struct semaphore pmu_sem; + +static int pmu_start(void); +static int pmu_setup(void); +static void pmu_stop(void); +static int pmu_create_files(struct super_block *, struct dentry *); + +#ifdef CONFIG_PM +static int pmu_suspend(struct sys_device *dev, pm_message_t state) +{ + if (pmu_enabled) + pmu_stop(); + return 0; +} + +static int pmu_resume(struct sys_device *dev) +{ + if (pmu_enabled) + pmu_start(); + return 0; +} + +static struct sysdev_class oprofile_sysclass = { + set_kset_name("oprofile"), + .resume = pmu_resume, + .suspend = pmu_suspend, +}; + +static struct sys_device device_oprofile = { + .id = 0, + .cls = &oprofile_sysclass, +}; + +static int __init init_driverfs(void) +{ + int ret; + + if (!(ret = sysdev_class_register(&oprofile_sysclass))) + ret = sysdev_register(&device_oprofile); + + return ret; +} + +static void exit_driverfs(void) +{ + sysdev_unregister(&device_oprofile); + sysdev_class_unregister(&oprofile_sysclass); +} +#else +#define init_driverfs() do { } while (0) +#define exit_driverfs() do { } while (0) +#endif /* CONFIG_PM */ + +struct op_counter_config counter_config[OP_MAX_COUNTER]; + +static int pmu_create_files(struct super_block *sb, struct dentry *root) +{ + unsigned int i; + + for (i = 0; i < pmu_model->num_counters; i++) { + struct dentry *dir; + char buf[2]; + + snprintf(buf, sizeof buf, "%d", i); + dir = oprofilefs_mkdir(sb, root, buf); + oprofilefs_create_ulong(sb, dir, "enabled", &counter_config[i].enabled); + oprofilefs_create_ulong(sb, dir, "event", &counter_config[i].event); + oprofilefs_create_ulong(sb, dir, "count", &counter_config[i].count); + oprofilefs_create_ulong(sb, dir, "unit_mask", &counter_config[i].unit_mask); + oprofilefs_create_ulong(sb, dir, "kernel", &counter_config[i].kernel); + oprofilefs_create_ulong(sb, dir, "user", &counter_config[i].user); + } + + return 0; +} + +static int pmu_setup(void) +{ + int ret; + + spin_lock(&oprofilefs_lock); + ret = pmu_model->setup_ctrs(); + spin_unlock(&oprofilefs_lock); + return ret; +} + +static int pmu_start(void) +{ + int ret = -EBUSY; + + down(&pmu_sem); + if (!pmu_enabled) { + ret = pmu_model->start(); + pmu_enabled = !ret; + } + up(&pmu_sem); + return ret; +} + +static void pmu_stop(void) +{ + down(&pmu_sem); + if (pmu_enabled) + pmu_model->stop(); + pmu_enabled = 0; + up(&pmu_sem); +} + +int __init pmu_init(struct oprofile_operations *ops, struct op_arm_model_spec *spec) +{ + init_MUTEX(&pmu_sem); + + if (spec->init() < 0) + return -ENODEV; + + pmu_model = spec; + init_driverfs(); + ops->create_files = pmu_create_files; + ops->setup = pmu_setup; + ops->shutdown = pmu_stop; + ops->start = pmu_start; + ops->stop = pmu_stop; + ops->cpu_type = pmu_model->name; + printk(KERN_INFO "oprofile: using %s PMU\n", spec->name); + + return 0; +} + +void pmu_exit(void) +{ + if (pmu_model) { + exit_driverfs(); + pmu_model = NULL; + } +} + diff --git a/arch/arm/oprofile/init.c b/arch/arm/oprofile/init.c new file mode 100644 index 0000000..cce3d30 --- /dev/null +++ b/arch/arm/oprofile/init.c @@ -0,0 +1,31 @@ +/** + * @file init.c + * + * @remark Copyright 2004 Oprofile Authors + * @remark Read the file COPYING + * + * @author Zwane Mwaikambo + */ + +#include +#include +#include +#include "op_arm_model.h" + +int __init oprofile_arch_init(struct oprofile_operations *ops) +{ + int ret = -ENODEV; + +#ifdef CONFIG_CPU_XSCALE + ret = pmu_init(ops, &op_xscale_spec); +#endif + + return ret; +} + +void oprofile_arch_exit(void) +{ +#ifdef CONFIG_CPU_XSCALE + pmu_exit(); +#endif +} diff --git a/arch/arm/oprofile/op_arm_model.h b/arch/arm/oprofile/op_arm_model.h new file mode 100644 index 0000000..2d4caf4 --- /dev/null +++ b/arch/arm/oprofile/op_arm_model.h @@ -0,0 +1,29 @@ +/** + * @file op_arm_model.h + * interface to ARM machine specific operations + * + * @remark Copyright 2004 Oprofile Authors + * @remark Read the file COPYING + * + * @author Zwane Mwaikambo + */ + +#ifndef OP_ARM_MODEL_H +#define OP_ARM_MODEL_H + +struct op_arm_model_spec { + int (*init)(void); + unsigned int num_counters; + int (*setup_ctrs)(void); + int (*start)(void); + void (*stop)(void); + char *name; +}; + +#ifdef CONFIG_CPU_XSCALE +extern struct op_arm_model_spec op_xscale_spec; +#endif + +extern int __init pmu_init(struct oprofile_operations *ops, struct op_arm_model_spec *spec); +extern void pmu_exit(void); +#endif /* OP_ARM_MODEL_H */ diff --git a/arch/arm/oprofile/op_counter.h b/arch/arm/oprofile/op_counter.h new file mode 100644 index 0000000..153c1d4 --- /dev/null +++ b/arch/arm/oprofile/op_counter.h @@ -0,0 +1,29 @@ +/** + * @file op_counter.h + * + * @remark Copyright 2004 Oprofile Authors + * @remark Read the file COPYING + * + * @author Zwane Mwaikambo + */ + +#ifndef OP_COUNTER_H +#define OP_COUNTER_H + +#define OP_MAX_COUNTER 5 + +/* Per performance monitor configuration as set via + * oprofilefs. + */ +struct op_counter_config { + unsigned long count; + unsigned long enabled; + unsigned long event; + unsigned long unit_mask; + unsigned long kernel; + unsigned long user; +}; + +extern struct op_counter_config counter_config[]; + +#endif /* OP_COUNTER_H */ diff --git a/arch/arm/oprofile/op_model_xscale.c b/arch/arm/oprofile/op_model_xscale.c new file mode 100644 index 0000000..e0f0b32 --- /dev/null +++ b/arch/arm/oprofile/op_model_xscale.c @@ -0,0 +1,443 @@ +/** + * @file op_model_xscale.c + * XScale Performance Monitor Driver + * + * @remark Copyright 2000-2004 Deepak Saxena + * @remark Copyright 2000-2004 MontaVista Software Inc + * @remark Copyright 2004 Dave Jiang + * @remark Copyright 2004 Intel Corporation + * @remark Copyright 2004 Zwane Mwaikambo + * @remark Copyright 2004 OProfile Authors + * + * @remark Read the file COPYING + * + * @author Zwane Mwaikambo + */ + +/* #define DEBUG */ +#include +#include +#include +#include +#include +#include +#include + +#include "op_counter.h" +#include "op_arm_model.h" + +#define PMU_ENABLE 0x001 /* Enable counters */ +#define PMN_RESET 0x002 /* Reset event counters */ +#define CCNT_RESET 0x004 /* Reset clock counter */ +#define PMU_RESET (CCNT_RESET | PMN_RESET) +#define PMU_CNT64 0x008 /* Make CCNT count every 64th cycle */ + +/* TODO do runtime detection */ +#ifdef CONFIG_ARCH_IOP310 +#define XSCALE_PMU_IRQ IRQ_XS80200_PMU +#endif +#ifdef CONFIG_ARCH_IOP321 +#define XSCALE_PMU_IRQ IRQ_IOP321_CORE_PMU +#endif +#ifdef CONFIG_ARCH_IOP331 +#define XSCALE_PMU_IRQ IRQ_IOP331_CORE_PMU +#endif +#ifdef CONFIG_ARCH_PXA +#define XSCALE_PMU_IRQ IRQ_PMU +#endif + +/* + * Different types of events that can be counted by the XScale PMU + * as used by Oprofile userspace. Here primarily for documentation + * purposes. + */ + +#define EVT_ICACHE_MISS 0x00 +#define EVT_ICACHE_NO_DELIVER 0x01 +#define EVT_DATA_STALL 0x02 +#define EVT_ITLB_MISS 0x03 +#define EVT_DTLB_MISS 0x04 +#define EVT_BRANCH 0x05 +#define EVT_BRANCH_MISS 0x06 +#define EVT_INSTRUCTION 0x07 +#define EVT_DCACHE_FULL_STALL 0x08 +#define EVT_DCACHE_FULL_STALL_CONTIG 0x09 +#define EVT_DCACHE_ACCESS 0x0A +#define EVT_DCACHE_MISS 0x0B +#define EVT_DCACE_WRITE_BACK 0x0C +#define EVT_PC_CHANGED 0x0D +#define EVT_BCU_REQUEST 0x10 +#define EVT_BCU_FULL 0x11 +#define EVT_BCU_DRAIN 0x12 +#define EVT_BCU_ECC_NO_ELOG 0x14 +#define EVT_BCU_1_BIT_ERR 0x15 +#define EVT_RMW 0x16 +/* EVT_CCNT is not hardware defined */ +#define EVT_CCNT 0xFE +#define EVT_UNUSED 0xFF + +struct pmu_counter { + volatile unsigned long ovf; + unsigned long reset_counter; +}; + +enum { CCNT, PMN0, PMN1, PMN2, PMN3, MAX_COUNTERS }; + +static struct pmu_counter results[MAX_COUNTERS]; + +/* + * There are two versions of the PMU in current XScale processors + * with differing register layouts and number of performance counters. + * e.g. IOP321 is xsc1 whilst IOP331 is xsc2. + * We detect which register layout to use in xscale_detect_pmu() + */ +enum { PMU_XSC1, PMU_XSC2 }; + +struct pmu_type { + int id; + char *name; + int num_counters; + unsigned int int_enable; + unsigned int cnt_ovf[MAX_COUNTERS]; + unsigned int int_mask[MAX_COUNTERS]; +}; + +static struct pmu_type pmu_parms[] = { + { + .id = PMU_XSC1, + .name = "arm/xscale1", + .num_counters = 3, + .int_mask = { [PMN0] = 0x10, [PMN1] = 0x20, + [CCNT] = 0x40 }, + .cnt_ovf = { [CCNT] = 0x400, [PMN0] = 0x100, + [PMN1] = 0x200}, + }, + { + .id = PMU_XSC2, + .name = "arm/xscale2", + .num_counters = 5, + .int_mask = { [CCNT] = 0x01, [PMN0] = 0x02, + [PMN1] = 0x04, [PMN2] = 0x08, + [PMN3] = 0x10 }, + .cnt_ovf = { [CCNT] = 0x01, [PMN0] = 0x02, + [PMN1] = 0x04, [PMN2] = 0x08, + [PMN3] = 0x10 }, + }, +}; + +static struct pmu_type *pmu; + +static void write_pmnc(u32 val) +{ + if (pmu->id == PMU_XSC1) { + /* upper 4bits and 7, 11 are write-as-0 */ + val &= 0xffff77f; + __asm__ __volatile__ ("mcr p14, 0, %0, c0, c0, 0" : : "r" (val)); + } else { + /* 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 u32 read_pmnc(void) +{ + u32 val; + + if (pmu->id == PMU_XSC1) + __asm__ __volatile__ ("mrc p14, 0, %0, c0, c0, 0" : "=r" (val)); + else { + __asm__ __volatile__ ("mrc p14, 0, %0, c0, c1, 0" : "=r" (val)); + /* bits 1-2 and 4-23 are read-unpredictable */ + val &= 0xff000009; + } + + return val; +} + +static u32 __xsc1_read_counter(int counter) +{ + u32 val = 0; + + switch (counter) { + case CCNT: + __asm__ __volatile__ ("mrc p14, 0, %0, c1, c0, 0" : "=r" (val)); + break; + case PMN0: + __asm__ __volatile__ ("mrc p14, 0, %0, c2, c0, 0" : "=r" (val)); + break; + case PMN1: + __asm__ __volatile__ ("mrc p14, 0, %0, c3, c0, 0" : "=r" (val)); + break; + } + return val; +} + +static u32 __xsc2_read_counter(int counter) +{ + u32 val = 0; + + switch (counter) { + case CCNT: + __asm__ __volatile__ ("mrc p14, 0, %0, c1, c1, 0" : "=r" (val)); + break; + case PMN0: + __asm__ __volatile__ ("mrc p14, 0, %0, c0, c2, 0" : "=r" (val)); + break; + case PMN1: + __asm__ __volatile__ ("mrc p14, 0, %0, c1, c2, 0" : "=r" (val)); + break; + case PMN2: + __asm__ __volatile__ ("mrc p14, 0, %0, c2, c2, 0" : "=r" (val)); + break; + case PMN3: + __asm__ __volatile__ ("mrc p14, 0, %0, c3, c2, 0" : "=r" (val)); + break; + } + return val; +} + +static u32 read_counter(int counter) +{ + u32 val; + + if (pmu->id == PMU_XSC1) + val = __xsc1_read_counter(counter); + else + val = __xsc2_read_counter(counter); + + return val; +} + +static void __xsc1_write_counter(int counter, u32 val) +{ + switch (counter) { + case CCNT: + __asm__ __volatile__ ("mcr p14, 0, %0, c1, c0, 0" : : "r" (val)); + break; + case PMN0: + __asm__ __volatile__ ("mcr p14, 0, %0, c2, c0, 0" : : "r" (val)); + break; + case PMN1: + __asm__ __volatile__ ("mcr p14, 0, %0, c3, c0, 0" : : "r" (val)); + break; + } +} + +static void __xsc2_write_counter(int counter, u32 val) +{ + switch (counter) { + case CCNT: + __asm__ __volatile__ ("mcr p14, 0, %0, c1, c1, 0" : : "r" (val)); + break; + case PMN0: + __asm__ __volatile__ ("mcr p14, 0, %0, c0, c2, 0" : : "r" (val)); + break; + case PMN1: + __asm__ __volatile__ ("mcr p14, 0, %0, c1, c2, 0" : : "r" (val)); + break; + case PMN2: + __asm__ __volatile__ ("mcr p14, 0, %0, c2, c2, 0" : : "r" (val)); + break; + case PMN3: + __asm__ __volatile__ ("mcr p14, 0, %0, c3, c2, 0" : : "r" (val)); + break; + } +} + +static void write_counter(int counter, u32 val) +{ + if (pmu->id == PMU_XSC1) + __xsc1_write_counter(counter, val); + else + __xsc2_write_counter(counter, val); +} + +static int xscale_setup_ctrs(void) +{ + u32 evtsel, pmnc; + int i; + + for (i = CCNT; i < MAX_COUNTERS; i++) { + if (counter_config[i].enabled) + continue; + + counter_config[i].event = EVT_UNUSED; + } + + switch (pmu->id) { + case PMU_XSC1: + pmnc = (counter_config[PMN1].event << 20) | (counter_config[PMN0].event << 12); + pr_debug("xscale_setup_ctrs: pmnc: %#08x\n", pmnc); + write_pmnc(pmnc); + break; + + case PMU_XSC2: + evtsel = counter_config[PMN0].event | (counter_config[PMN1].event << 8) | + (counter_config[PMN2].event << 16) | (counter_config[PMN3].event << 24); + + pr_debug("xscale_setup_ctrs: evtsel %#08x\n", evtsel); + __asm__ __volatile__ ("mcr p14, 0, %0, c8, c1, 0" : : "r" (evtsel)); + break; + } + + for (i = CCNT; i < MAX_COUNTERS; i++) { + if (counter_config[i].event == EVT_UNUSED) { + counter_config[i].event = 0; + pmu->int_enable &= ~pmu->int_mask[i]; + continue; + } + + results[i].reset_counter = counter_config[i].count; + write_counter(i, -(u32)counter_config[i].count); + pmu->int_enable |= pmu->int_mask[i]; + pr_debug("xscale_setup_ctrs: counter%d %#08x from %#08lx\n", i, + read_counter(i), counter_config[i].count); + } + + return 0; +} + +static void inline __xsc1_check_ctrs(void) +{ + int i; + u32 pmnc = read_pmnc(); + + /* NOTE: there's an A stepping errata 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 */ + + /* Write the value back to clear the overflow flags. Overflow */ + /* flags remain in pmnc for use below */ + write_pmnc(pmnc & ~PMU_ENABLE); + + for (i = CCNT; i <= PMN1; i++) { + if (!(pmu->int_mask[i] & pmu->int_enable)) + continue; + + if (pmnc & pmu->cnt_ovf[i]) + results[i].ovf++; + } +} + +static void inline __xsc2_check_ctrs(void) +{ + int i; + u32 flag = 0, pmnc = read_pmnc(); + + pmnc &= ~PMU_ENABLE; + write_pmnc(pmnc); + + /* read overflow flag register */ + __asm__ __volatile__ ("mrc p14, 0, %0, c5, c1, 0" : "=r" (flag)); + + for (i = CCNT; i <= PMN3; i++) { + if (!(pmu->int_mask[i] & pmu->int_enable)) + continue; + + if (flag & pmu->cnt_ovf[i]) + results[i].ovf++; + } + + /* writeback clears overflow bits */ + __asm__ __volatile__ ("mcr p14, 0, %0, c5, c1, 0" : : "r" (flag)); +} + +static irqreturn_t xscale_pmu_interrupt(int irq, void *arg, struct pt_regs *regs) +{ + int i; + u32 pmnc; + + if (pmu->id == PMU_XSC1) + __xsc1_check_ctrs(); + else + __xsc2_check_ctrs(); + + for (i = CCNT; i < MAX_COUNTERS; i++) { + if (!results[i].ovf) + continue; + + write_counter(i, -(u32)results[i].reset_counter); + oprofile_add_sample(regs, i); + results[i].ovf--; + } + + pmnc = read_pmnc() | PMU_ENABLE; + write_pmnc(pmnc); + + return IRQ_HANDLED; +} + +static void xscale_pmu_stop(void) +{ + u32 pmnc = read_pmnc(); + + pmnc &= ~PMU_ENABLE; + write_pmnc(pmnc); + + free_irq(XSCALE_PMU_IRQ, results); +} + +static int xscale_pmu_start(void) +{ + int ret; + u32 pmnc = read_pmnc(); + + ret = request_irq(XSCALE_PMU_IRQ, xscale_pmu_interrupt, SA_INTERRUPT, + "XScale PMU", (void *)results); + + if (ret < 0) { + printk(KERN_ERR "oprofile: unable to request IRQ%d for XScale PMU\n", + XSCALE_PMU_IRQ); + return ret; + } + + if (pmu->id == PMU_XSC1) + pmnc |= pmu->int_enable; + else { + __asm__ __volatile__ ("mcr p14, 0, %0, c4, c1, 0" : : "r" (pmu->int_enable)); + pmnc &= ~PMU_CNT64; + } + + pmnc |= PMU_ENABLE; + write_pmnc(pmnc); + pr_debug("xscale_pmu_start: pmnc: %#08x mask: %08x\n", pmnc, pmu->int_enable); + return 0; +} + +static int xscale_detect_pmu(void) +{ + int ret = 0; + u32 id; + + id = (read_cpuid(CPUID_ID) >> 13) & 0x7; + + switch (id) { + case 1: + pmu = &pmu_parms[PMU_XSC1]; + break; + case 2: + pmu = &pmu_parms[PMU_XSC2]; + break; + default: + ret = -ENODEV; + break; + } + + if (!ret) { + op_xscale_spec.name = pmu->name; + op_xscale_spec.num_counters = pmu->num_counters; + pr_debug("xscale_detect_pmu: detected %s PMU\n", pmu->name); + } + + return ret; +} + +struct op_arm_model_spec op_xscale_spec = { + .init = xscale_detect_pmu, + .setup_ctrs = xscale_setup_ctrs, + .start = xscale_pmu_start, + .stop = xscale_pmu_stop, +}; + -- cgit v1.1