diff options
Diffstat (limited to 'arch/x86')
-rw-r--r-- | arch/x86/kernel/apic_32.c | 4 | ||||
-rw-r--r-- | arch/x86/kernel/apic_64.c | 4 | ||||
-rw-r--r-- | arch/x86/oprofile/Makefile | 2 | ||||
-rw-r--r-- | arch/x86/oprofile/nmi_int.c | 125 | ||||
-rw-r--r-- | arch/x86/oprofile/op_counter.h | 3 | ||||
-rw-r--r-- | arch/x86/oprofile/op_model_amd.c | 559 | ||||
-rw-r--r-- | arch/x86/oprofile/op_model_athlon.c | 190 | ||||
-rw-r--r-- | arch/x86/oprofile/op_model_p4.c | 179 | ||||
-rw-r--r-- | arch/x86/oprofile/op_model_ppro.c | 2 | ||||
-rw-r--r-- | arch/x86/oprofile/op_x86_model.h | 7 |
10 files changed, 780 insertions, 295 deletions
diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c index f88bd0d982b..0ff576d026a 100644 --- a/arch/x86/kernel/apic_32.c +++ b/arch/x86/kernel/apic_32.c @@ -646,6 +646,9 @@ int setup_profiling_timer(unsigned int multiplier) * * Vector mappings are hard coded. On K8 only offset 0 (APIC500) and * MCE interrupts are supported. Thus MCE offset must be set to 0. + * + * If mask=1, the LVT entry does not generate interrupts while mask=0 + * enables the vector. See also the BKDGs. */ #define APIC_EILVT_LVTOFF_MCE 0 @@ -669,6 +672,7 @@ u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask) setup_APIC_eilvt(APIC_EILVT_LVTOFF_IBS, vector, msg_type, mask); return APIC_EILVT_LVTOFF_IBS; } +EXPORT_SYMBOL_GPL(setup_APIC_eilvt_ibs); /* * Local APIC start and shutdown diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c index 446c062e831..57744f4a75b 100644 --- a/arch/x86/kernel/apic_64.c +++ b/arch/x86/kernel/apic_64.c @@ -204,6 +204,9 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen) * * Vector mappings are hard coded. On K8 only offset 0 (APIC500) and * MCE interrupts are supported. Thus MCE offset must be set to 0. + * + * If mask=1, the LVT entry does not generate interrupts while mask=0 + * enables the vector. See also the BKDGs. */ #define APIC_EILVT_LVTOFF_MCE 0 @@ -228,6 +231,7 @@ u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask) setup_APIC_eilvt(APIC_EILVT_LVTOFF_IBS, vector, msg_type, mask); return APIC_EILVT_LVTOFF_IBS; } +EXPORT_SYMBOL_GPL(setup_APIC_eilvt_ibs); /* * Program the next event, relative to now diff --git a/arch/x86/oprofile/Makefile b/arch/x86/oprofile/Makefile index 30f3eb36666..446902b2a6b 100644 --- a/arch/x86/oprofile/Makefile +++ b/arch/x86/oprofile/Makefile @@ -7,6 +7,6 @@ DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \ timer_int.o ) oprofile-y := $(DRIVER_OBJS) init.o backtrace.o -oprofile-$(CONFIG_X86_LOCAL_APIC) += nmi_int.o op_model_athlon.o \ +oprofile-$(CONFIG_X86_LOCAL_APIC) += nmi_int.o op_model_amd.o \ op_model_ppro.o op_model_p4.o oprofile-$(CONFIG_X86_IO_APIC) += nmi_timer_int.o diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index 8a5f1614a3d..114df508b40 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -1,10 +1,11 @@ /** * @file nmi_int.c * - * @remark Copyright 2002 OProfile authors + * @remark Copyright 2002-2008 OProfile authors * @remark Read the file COPYING * * @author John Levon <levon@movementarian.org> + * @author Robert Richter <robert.richter@amd.com> */ #include <linux/init.h> @@ -23,6 +24,8 @@ #include "op_counter.h" #include "op_x86_model.h" +DEFINE_PER_CPU(int, switch_index); + static struct op_x86_model_spec const *model; static DEFINE_PER_CPU(struct op_msrs, cpu_msrs); static DEFINE_PER_CPU(unsigned long, saved_lvtpc); @@ -31,6 +34,8 @@ static int nmi_start(void); static void nmi_stop(void); static void nmi_cpu_start(void *dummy); static void nmi_cpu_stop(void *dummy); +static void nmi_cpu_save_mpx_registers(struct op_msrs *msrs); +static void nmi_cpu_restore_mpx_registers(struct op_msrs *msrs); /* 0 == registered but off, 1 == registered and on */ static int nmi_enabled = 0; @@ -106,6 +111,47 @@ static void exit_sysfs(void) #define exit_sysfs() do { } while (0) #endif /* CONFIG_PM */ +static void nmi_cpu_switch(void *dummy) +{ + int cpu = smp_processor_id(); + int si = per_cpu(switch_index, cpu); + struct op_msrs *msrs = &per_cpu(cpu_msrs, cpu); + + nmi_cpu_stop(NULL); + nmi_cpu_save_mpx_registers(msrs); + + /* move to next set */ + si += model->num_hardware_counters; + if ((si > model->num_counters) || (counter_config[si].count == 0)) + per_cpu(switch_index, smp_processor_id()) = 0; + else + per_cpu(switch_index, smp_processor_id()) = si; + + nmi_cpu_restore_mpx_registers(msrs); + model->setup_ctrs(msrs); + nmi_cpu_start(NULL); +} + +/* + * Quick check to see if multiplexing is necessary. + * The check should be sufficient since counters are used + * in ordre. + */ +static int nmi_multiplex_on(void) +{ + return counter_config[model->num_hardware_counters].count ? 0 : -EINVAL; +} + +static int nmi_switch_event(void) +{ + if (nmi_multiplex_on() < 0) + return -EINVAL; + + on_each_cpu(nmi_cpu_switch, NULL, 1); + + return 0; +} + static int profile_exceptions_notify(struct notifier_block *self, unsigned long val, void *data) { @@ -169,11 +215,10 @@ static void free_msrs(void) static int allocate_msrs(void) { - int success = 1; + int i, success = 1; size_t controls_size = sizeof(struct op_msr) * model->num_controls; size_t counters_size = sizeof(struct op_msr) * model->num_counters; - int i; for_each_possible_cpu(i) { per_cpu(cpu_msrs, i).counters = kmalloc(counters_size, GFP_KERNEL); @@ -181,8 +226,8 @@ static int allocate_msrs(void) success = 0; break; } - per_cpu(cpu_msrs, i).controls = kmalloc(controls_size, - GFP_KERNEL); + per_cpu(cpu_msrs, i).controls = + kmalloc(controls_size, GFP_KERNEL); if (!per_cpu(cpu_msrs, i).controls) { success = 0; break; @@ -226,7 +271,8 @@ static int nmi_setup(void) return err; } - /* We need to serialize save and setup for HT because the subset + /* + * We need to serialize save and setup for HT because the subset * of msrs are distinct for save and setup operations */ @@ -242,7 +288,6 @@ static int nmi_setup(void) per_cpu(cpu_msrs, 0).controls, sizeof(struct op_msr) * model->num_controls); } - } on_each_cpu(nmi_save_registers, NULL, 1); on_each_cpu(nmi_cpu_setup, NULL, 1); @@ -250,7 +295,41 @@ static int nmi_setup(void) return 0; } -static void nmi_restore_registers(struct op_msrs *msrs) +static void nmi_cpu_save_mpx_registers(struct op_msrs *msrs) +{ + unsigned int si = __get_cpu_var(switch_index); + unsigned int const nr_ctrs = model->num_hardware_counters; + struct op_msr *counters = &msrs->counters[si]; + unsigned int i; + + for (i = 0; i < nr_ctrs; ++i) { + int offset = i + si; + if (counters[offset].addr) { + rdmsr(counters[offset].addr, + counters[offset].multiplex.low, + counters[offset].multiplex.high); + } + } +} + +static void nmi_cpu_restore_mpx_registers(struct op_msrs *msrs) +{ + unsigned int si = __get_cpu_var(switch_index); + unsigned int const nr_ctrs = model->num_hardware_counters; + struct op_msr *counters = &msrs->counters[si]; + unsigned int i; + + for (i = 0; i < nr_ctrs; ++i) { + int offset = i + si; + if (counters[offset].addr) { + wrmsr(counters[offset].addr, + counters[offset].multiplex.low, + counters[offset].multiplex.high); + } + } +} + +static void nmi_cpu_restore_registers(struct op_msrs *msrs) { unsigned int const nr_ctrs = model->num_counters; unsigned int const nr_ctrls = model->num_controls; @@ -290,7 +369,8 @@ static void nmi_cpu_shutdown(void *dummy) apic_write(APIC_LVTERR, v | APIC_LVT_MASKED); apic_write(APIC_LVTPC, per_cpu(saved_lvtpc, cpu)); apic_write(APIC_LVTERR, v); - nmi_restore_registers(msrs); + nmi_cpu_restore_registers(msrs); + __get_cpu_var(switch_index) = 0; } static void nmi_shutdown(void) @@ -355,6 +435,7 @@ static int nmi_create_files(struct super_block *sb, struct dentry *root) 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); + counter_config[i].save_count_low = 0; } return 0; @@ -439,6 +520,7 @@ int __init op_nmi_init(struct oprofile_operations *ops) __u8 vendor = boot_cpu_data.x86_vendor; __u8 family = boot_cpu_data.x86; char *cpu_type; + int ret = 0; if (!cpu_has_apic) return -ENODEV; @@ -451,19 +533,23 @@ int __init op_nmi_init(struct oprofile_operations *ops) default: return -ENODEV; case 6: - model = &op_athlon_spec; + model = &op_amd_spec; cpu_type = "i386/athlon"; break; case 0xf: - model = &op_athlon_spec; + model = &op_amd_spec; /* Actually it could be i386/hammer too, but give user space an consistent name. */ cpu_type = "x86-64/hammer"; break; case 0x10: - model = &op_athlon_spec; + model = &op_amd_spec; cpu_type = "x86-64/family10"; break; + case 0x11: + model = &op_amd_spec; + cpu_type = "x86-64/family11h"; + break; } break; @@ -490,17 +576,26 @@ int __init op_nmi_init(struct oprofile_operations *ops) return -ENODEV; } - init_sysfs(); #ifdef CONFIG_SMP register_cpu_notifier(&oprofile_cpu_nb); #endif - using_nmi = 1; + /* default values, can be overwritten by model */ + __raw_get_cpu_var(switch_index) = 0; ops->create_files = nmi_create_files; ops->setup = nmi_setup; ops->shutdown = nmi_shutdown; ops->start = nmi_start; ops->stop = nmi_stop; ops->cpu_type = cpu_type; + ops->switch_events = nmi_switch_event; + + if (model->init) + ret = model->init(ops); + if (ret) + return ret; + + init_sysfs(); + using_nmi = 1; printk(KERN_INFO "oprofile: using NMI interrupt.\n"); return 0; } @@ -512,5 +607,7 @@ void op_nmi_exit(void) #ifdef CONFIG_SMP unregister_cpu_notifier(&oprofile_cpu_nb); #endif + if (model->exit) + model->exit(); } } diff --git a/arch/x86/oprofile/op_counter.h b/arch/x86/oprofile/op_counter.h index 2880b15c467..786d6e01cf7 100644 --- a/arch/x86/oprofile/op_counter.h +++ b/arch/x86/oprofile/op_counter.h @@ -10,13 +10,14 @@ #ifndef OP_COUNTER_H #define OP_COUNTER_H -#define OP_MAX_COUNTER 8 +#define OP_MAX_COUNTER 32 /* Per-perfctr configuration as set via * oprofilefs. */ struct op_counter_config { unsigned long count; + unsigned long save_count_low; unsigned long enabled; unsigned long event; unsigned long kernel; diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c new file mode 100644 index 00000000000..bbf2b68bcc5 --- /dev/null +++ b/arch/x86/oprofile/op_model_amd.c @@ -0,0 +1,559 @@ +/* + * @file op_model_amd.c + * athlon / K7 / K8 / Family 10h model-specific MSR operations + * + * @remark Copyright 2002-2008 OProfile authors + * @remark Read the file COPYING + * + * @author John Levon + * @author Philippe Elie + * @author Graydon Hoare + * @author Robert Richter <robert.richter@amd.com> + * @author Barry Kasindorf +*/ + +#include <linux/oprofile.h> +#include <linux/device.h> +#include <linux/pci.h> +#include <linux/percpu.h> + +#include <asm/ptrace.h> +#include <asm/msr.h> +#include <asm/nmi.h> + +#include "op_x86_model.h" +#include "op_counter.h" + +#define NUM_COUNTERS 32 +#define NUM_HARDWARE_COUNTERS 4 +#define NUM_CONTROLS 32 +#define NUM_HARDWARE_CONTROLS 4 + +#define CTR_IS_RESERVED(msrs, c) (msrs->counters[(c)].addr ? 1 : 0) +#define CTR_READ(l, h, msrs, c) do {rdmsr(msrs->counters[(c)].addr, (l), (h)); } while (0) +#define CTR_WRITE(l, msrs, c) do {wrmsr(msrs->counters[(c)].addr, -(unsigned int)(l), -1); } while (0) +#define CTR_OVERFLOWED(n) (!((n) & (1U<<31))) + +#define CTRL_IS_RESERVED(msrs, c) (msrs->controls[(c)].addr ? 1 : 0) +#define CTRL_READ(l, h, msrs, c) do {rdmsr(msrs->controls[(c)].addr, (l), (h)); } while (0) +#define CTRL_WRITE(l, h, msrs, c) do {wrmsr(msrs->controls[(c)].addr, (l), (h)); } while (0) +#define CTRL_SET_ACTIVE(n) (n |= (1<<22)) +#define CTRL_SET_INACTIVE(n) (n &= ~(1<<22)) +#define CTRL_CLEAR_LO(x) (x &= (1<<21)) +#define CTRL_CLEAR_HI(x) (x &= 0xfffffcf0) +#define CTRL_SET_ENABLE(val) (val |= 1<<20) +#define CTRL_SET_USR(val, u) (val |= ((u & 1) << 16)) +#define CTRL_SET_KERN(val, k) (val |= ((k & 1) << 17)) +#define CTRL_SET_UM(val, m) (val |= (m << 8)) +#define CTRL_SET_EVENT_LOW(val, e) (val |= (e & 0xff)) +#define CTRL_SET_EVENT_HIGH(val, e) (val |= ((e >> 8) & 0xf)) +#define CTRL_SET_HOST_ONLY(val, h) (val |= ((h & 1) << 9)) +#define CTRL_SET_GUEST_ONLY(val, h) (val |= ((h & 1) << 8)) + +static unsigned long reset_value[NUM_COUNTERS]; +DECLARE_PER_CPU(int, switch_index); + +#ifdef CONFIG_OPROFILE_IBS + +/* IbsFetchCtl bits/masks */ +#define IBS_FETCH_HIGH_VALID_BIT (1UL << 17) /* bit 49 */ +#define IBS_FETCH_HIGH_ENABLE (1UL << 16) /* bit 48 */ +#define IBS_FETCH_LOW_MAX_CNT_MASK 0x0000FFFFUL /* MaxCnt mask */ + +/*IbsOpCtl bits */ +#define IBS_OP_LOW_VALID_BIT (1ULL<<18) /* bit 18 */ +#define IBS_OP_LOW_ENABLE (1ULL<<17) /* bit 17 */ + +/* Codes used in cpu_buffer.c */ +/* This produces duplicate code, need to be fixed */ +#define IBS_FETCH_BEGIN 3 +#define IBS_OP_BEGIN 4 + +/* The function interface needs to be fixed, something like add + data. Should then be added to linux/oprofile.h. */ +extern void oprofile_add_ibs_sample(struct pt_regs *const regs, + unsigned int * const ibs_sample, u8 code); + +struct ibs_fetch_sample { + /* MSRC001_1031 IBS Fetch Linear Address Register */ + unsigned int ibs_fetch_lin_addr_low; + unsigned int ibs_fetch_lin_addr_high; + /* MSRC001_1030 IBS Fetch Control Register */ + unsigned int ibs_fetch_ctl_low; + unsigned int ibs_fetch_ctl_high; + /* MSRC001_1032 IBS Fetch Physical Address Register */ + unsigned int ibs_fetch_phys_addr_low; + unsigned int ibs_fetch_phys_addr_high; +}; + +struct ibs_op_sample { + /* MSRC001_1034 IBS Op Logical Address Register (IbsRIP) */ + unsigned int ibs_op_rip_low; + unsigned int ibs_op_rip_high; + /* MSRC001_1035 IBS Op Data Register */ + unsigned int ibs_op_data1_low; + unsigned int ibs_op_data1_high; + /* MSRC001_1036 IBS Op Data 2 Register */ + unsigned int ibs_op_data2_low; + unsigned int ibs_op_data2_high; + /* MSRC001_1037 IBS Op Data 3 Register */ + unsigned int ibs_op_data3_low; + unsigned int ibs_op_data3_high; + /* MSRC001_1038 IBS DC Linear Address Register (IbsDcLinAd) */ + unsigned int ibs_dc_linear_low; + unsigned int ibs_dc_linear_high; + /* MSRC001_1039 IBS DC Physical Address Register (IbsDcPhysAd) */ + unsigned int ibs_dc_phys_low; + unsigned int ibs_dc_phys_high; +}; + +/* + * unitialize the APIC for the IBS interrupts if needed on AMD Family10h+ +*/ +static void clear_ibs_nmi(void); + +static int ibs_allowed; /* AMD Family10h and later */ + +struct op_ibs_config { + unsigned long op_enabled; + unsigned long fetch_enabled; + unsigned long max_cnt_fetch; + unsigned long max_cnt_op; + unsigned long rand_en; + unsigned long dispatched_ops; +}; + +static struct op_ibs_config ibs_config; + +#endif + +/* functions for op_amd_spec */ + +static void op_amd_fill_in_addresses(struct op_msrs * const msrs) +{ + int i; + + for (i = 0; i < NUM_COUNTERS; i++) { + int hw_counter = i % NUM_HARDWARE_COUNTERS; + if (reserve_perfctr_nmi(MSR_K7_PERFCTR0 + hw_counter)) + msrs->counters[i].addr = MSR_K7_PERFCTR0 + hw_counter; + else + msrs->counters[i].addr = 0; + } + + for (i = 0; i < NUM_CONTROLS; i++) { + int hw_control = i % NUM_HARDWARE_CONTROLS; + if (reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + hw_control)) + msrs->controls[i].addr = MSR_K7_EVNTSEL0 + hw_control; + else + msrs->controls[i].addr = 0; + } +} + + +static void op_amd_setup_ctrs(struct op_msrs const * const msrs) +{ + unsigned int low, high; + int i; + + for (i = 0; i < NUM_HARDWARE_CONTROLS; ++i) { + int offset = i + __get_cpu_var(switch_index); + if (counter_config[offset].enabled) + reset_value[offset] = counter_config[offset].count; + else + reset_value[offset] = 0; + } + + /* clear all counters */ + for (i = 0 ; i < NUM_HARDWARE_CONTROLS; ++i) { + if (unlikely(!CTRL_IS_RESERVED(msrs, i))) + continue; + CTRL_READ(low, high, msrs, i); + CTRL_CLEAR_LO(low); + CTRL_CLEAR_HI(high); + CTRL_WRITE(low, high, msrs, i); + } + + /* avoid a false detection of ctr overflows in NMI handler */ + for (i = 0; i < NUM_HARDWARE_COUNTERS; ++i) { + if (unlikely(!CTR_IS_RESERVED(msrs, i))) + continue; + CTR_WRITE(1, msrs, i); + } + + /* enable active counters */ + for (i = 0; i < NUM_HARDWARE_COUNTERS; ++i) { + int offset = i + __get_cpu_var(switch_index); + if ((counter_config[offset].enabled) && (CTR_IS_RESERVED(msrs, i))) { + CTR_WRITE(counter_config[offset].count, msrs, i); + + CTRL_READ(low, high, msrs, i); + CTRL_CLEAR_LO(low); + CTRL_CLEAR_HI(high); + CTRL_SET_ENABLE(low); + CTRL_SET_USR(low, counter_config[offset].user); + CTRL_SET_KERN(low, counter_config[offset].kernel); + CTRL_SET_UM(low, counter_config[offset].unit_mask); + CTRL_SET_EVENT_LOW(low, counter_config[offset].event); + CTRL_SET_EVENT_HIGH(high, counter_config[offset].event); + CTRL_SET_HOST_ONLY(high, 0); + CTRL_SET_GUEST_ONLY(high, 0); + + CTRL_WRITE(low, high, msrs, i); + } + } +} + +#ifdef CONFIG_OPROFILE_IBS + +static inline int +op_amd_handle_ibs(struct pt_regs * const regs, + struct op_msrs const * const msrs) +{ + unsigned int low, high; + struct ibs_fetch_sample ibs_fetch; + struct ibs_op_sample ibs_op; + + if (!ibs_allowed) + return 1; + + if (ibs_config.fetch_enabled) { + rdmsr(MSR_AMD64_IBSFETCHCTL, low, high); + if (high & IBS_FETCH_HIGH_VALID_BIT) { + ibs_fetch.ibs_fetch_ctl_high = high; + ibs_fetch.ibs_fetch_ctl_low = low; + rdmsr(MSR_AMD64_IBSFETCHLINAD, low, high); + ibs_fetch.ibs_fetch_lin_addr_high = high; + ibs_fetch.ibs_fetch_lin_addr_low = low; + rdmsr(MSR_AMD64_IBSFETCHPHYSAD, low, high); + ibs_fetch.ibs_fetch_phys_addr_high = high; + ibs_fetch.ibs_fetch_phys_addr_low = low; + + oprofile_add_ibs_sample(regs, + (unsigned int *)&ibs_fetch, + IBS_FETCH_BEGIN); + + /*reenable the IRQ */ + rdmsr(MSR_AMD64_IBSFETCHCTL, low, high); + high &= ~IBS_FETCH_HIGH_VALID_BIT; + high |= IBS_FETCH_HIGH_ENABLE; + low &= IBS_FETCH_LOW_MAX_CNT_MASK; + wrmsr(MSR_AMD64_IBSFETCHCTL, low, high); + } + } + + if (ibs_config.op_enabled) { + rdmsr(MSR_AMD64_IBSOPCTL, low, high); + if (low & IBS_OP_LOW_VALID_BIT) { + rdmsr(MSR_AMD64_IBSOPRIP, low, high); + ibs_op.ibs_op_rip_low = low; + ibs_op.ibs_op_rip_high = high; + rdmsr(MSR_AMD64_IBSOPDATA, low, high); + ibs_op.ibs_op_data1_low = low; + ibs_op.ibs_op_data1_high = high; + rdmsr(MSR_AMD64_IBSOPDATA2, low, high); + ibs_op.ibs_op_data2_low = low; + ibs_op.ibs_op_data2_high = high; + rdmsr(MSR_AMD64_IBSOPDATA3, low, high); + ibs_op.ibs_op_data3_low = low; + ibs_op.ibs_op_data3_high = high; + rdmsr(MSR_AMD64_IBSDCLINAD, low, high); + ibs_op.ibs_dc_linear_low = low; + ibs_op.ibs_dc_linear_high = high; + rdmsr(MSR_AMD64_IBSDCPHYSAD, low, high); + ibs_op.ibs_dc_phys_low = low; + ibs_op.ibs_dc_phys_high = high; + + /* reenable the IRQ */ + oprofile_add_ibs_sample(regs, + (unsigned int *)&ibs_op, + IBS_OP_BEGIN); + rdmsr(MSR_AMD64_IBSOPCTL, low, high); + high = 0; + low &= ~IBS_OP_LOW_VALID_BIT; + low |= IBS_OP_LOW_ENABLE; + wrmsr(MSR_AMD64_IBSOPCTL, low, high); + } + } + + return 1; +} + +#endif + +static int op_amd_check_ctrs(struct pt_regs * const regs, + struct op_msrs const * const msrs) +{ + unsigned int low, high; + int i; + + for (i = 0 ; i < NUM_HARDWARE_COUNTERS ; ++i) { + int offset = i + __get_cpu_var(switch_index); + if (!reset_value[offset]) + continue; + CTR_READ(low, high, msrs, i); + if (CTR_OVERFLOWED(low)) { + oprofile_add_sample(regs, offset); + CTR_WRITE(reset_value[offset], msrs, i); + } + } + +#ifdef CONFIG_OPROFILE_IBS + op_amd_handle_ibs(regs, msrs); +#endif + + /* See op_model_ppro.c */ + return 1; +} + +static void op_amd_start(struct op_msrs const * const msrs) +{ + unsigned int low, high; + int i; + + for (i = 0 ; i < NUM_HARDWARE_COUNTERS ; ++i) { + int offset = i + __get_cpu_var(switch_index); + if (reset_value[offset]) { + CTRL_READ(low, high, msrs, i); + CTRL_SET_ACTIVE(low); + CTRL_WRITE(low, high, msrs, i); + } + } + +#ifdef CONFIG_OPROFILE_IBS + if (ibs_allowed && ibs_config.fetch_enabled) { + low = (ibs_config.max_cnt_fetch >> 4) & 0xFFFF; + high = IBS_FETCH_HIGH_ENABLE; + wrmsr(MSR_AMD64_IBSFETCHCTL, low, high); + } + + if (ibs_allowed && ibs_config.op_enabled) { + low = ((ibs_config.max_cnt_op >> 4) & 0xFFFF) + IBS_OP_LOW_ENABLE; + high = 0; + wrmsr(MSR_AMD64_IBSOPCTL, low, high); + } +#endif +} + + +static void op_amd_stop(struct op_msrs const * const msrs) +{ + unsigned int low, high; + int i; + + /* Subtle: stop on all counters to avoid race with + * setting our pm callback */ + for (i = 0 ; i < NUM_HARDWARE_COUNTERS ; ++i) { + if (!reset_value[i + per_cpu(switch_index, smp_processor_id())]) + continue; + CTRL_READ(low, high, msrs, i); + CTRL_SET_INACTIVE(low); + CTRL_WRITE(low, high, msrs, i); + } + +#ifdef CONFIG_OPROFILE_IBS + if (ibs_allowed && ibs_config.fetch_enabled) { + low = 0; /* clear max count and enable */ + high = 0; + wrmsr(MSR_AMD64_IBSFETCHCTL, low, high); + } + + if (ibs_allowed && ibs_config.op_enabled) { + low = 0; /* clear max count and enable */ + high = 0; + wrmsr(MSR_AMD64_IBSOPCTL, low, high); + } +#endif +} + +static void op_amd_shutdown(struct op_msrs const * const msrs) +{ + int i; + + for (i = 0 ; i < NUM_HARDWARE_COUNTERS ; ++i) { + if (CTR_IS_RESERVED(msrs, i)) + release_perfctr_nmi(MSR_K7_PERFCTR0 + i); + } + for (i = 0 ; i < NUM_HARDWARE_COUNTERS ; ++i) { + if (CTRL_IS_RESERVED(msrs, i)) + release_evntsel_nmi(MSR_K7_EVNTSEL0 + i); + } +} + +#ifndef CONFIG_OPROFILE_IBS + +/* no IBS support */ + +static int op_amd_init(struct oprofile_operations *ops) +{ + return 0; +} + +static void op_amd_exit(void) {} + +#else + +static u8 ibs_eilvt_off; + +static inline void apic_init_ibs_nmi_per_cpu(void *arg) +{ + ibs_eilvt_off = setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_NMI, 0); +} + +static inline void apic_clear_ibs_nmi_per_cpu(void *arg) +{ + setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_FIX, 1); +} + +static int pfm_amd64_setup_eilvt(void) +{ +#define IBSCTL_LVTOFFSETVAL (1 << 8) +#define IBSCTL 0x1cc + struct pci_dev *cpu_cfg; + int nodes; + u32 value = 0; + + /* per CPU setup */ + on_each_cpu(apic_init_ibs_nmi_per_cpu, NULL, 1); + + nodes = 0; + cpu_cfg = NULL; + do { + cpu_cfg = pci_get_device(PCI_VENDOR_ID_AMD, + PCI_DEVICE_ID_AMD_10H_NB_MISC, + cpu_cfg); + if (!cpu_cfg) + break; + ++nodes; + pci_write_config_dword(cpu_cfg, IBSCTL, ibs_eilvt_off + | IBSCTL_LVTOFFSETVAL); + pci_read_config_dword(cpu_cfg, IBSCTL, &value); + if (value != (ibs_eilvt_off | IBSCTL_LVTOFFSETVAL)) { + printk(KERN_DEBUG "Failed to setup IBS LVT offset, " + "IBSCTL = 0x%08x", value); + return 1; + } + } while (1); + + if (!nodes) { + printk(KERN_DEBUG "No CPU node configured for IBS"); + return 1; + } + +#ifdef CONFIG_NUMA + /* Sanity check */ + /* Works only for 64bit with proper numa implementation. */ + if (nodes != num_possible_nodes()) { + printk(KERN_DEBUG "Failed to setup CPU node(s) for IBS, " + "found: %d, expected %d", + nodes, num_possible_nodes()); + return 1; + } +#endif + return 0; +} + +/* + * initialize the APIC for the IBS interrupts + * if available (AMD Family10h rev B0 and later) + */ +static void setup_ibs(void) +{ + ibs_allowed = boot_cpu_has(X86_FEATURE_IBS); + + if (!ibs_allowed) + return; + + if (pfm_amd64_setup_eilvt()) { + ibs_allowed = 0; + return; + } + + printk(KERN_INFO "oprofile: AMD IBS detected\n"); +} + + +/* + * unitialize the APIC for the IBS interrupts if needed on AMD Family10h + * rev B0 and later */ +static void clear_ibs_nmi(void) +{ + if (ibs_allowed) + on_each_cpu(apic_clear_ibs_nmi_per_cpu, NULL, 1); +} + +static int (*create_arch_files)(struct super_block * sb, struct dentry * root); + +static int setup_ibs_files(struct super_block * sb, struct dentry * root) +{ + char buf[12]; + struct dentry *dir; + int ret = 0; + + /* architecture specific files */ + if (create_arch_files) + ret = create_arch_files(sb, root); + + if (ret) + return ret; + + if (!ibs_allowed) + return ret; + + /* model specific files */ + + /* setup some reasonable defaults */ + ibs_config.max_cnt_fetch = 250000; + ibs_config.fetch_enabled = 0; + ibs_config.max_cnt_op = 250000; + ibs_config.op_enabled = 0; + ibs_config.dispatched_ops = 1; + snprintf(buf, sizeof(buf), "ibs_fetch"); + dir = oprofilefs_mkdir(sb, root, buf); + oprofilefs_create_ulong(sb, dir, "rand_enable", + &ibs_config.rand_en); + oprofilefs_create_ulong(sb, dir, "enable", + &ibs_config.fetch_enabled); + oprofilefs_create_ulong(sb, dir, "max_count", + &ibs_config.max_cnt_fetch); + snprintf(buf, sizeof(buf), "ibs_uops"); + dir = oprofilefs_mkdir(sb, root, buf); + oprofilefs_create_ulong(sb, dir, "enable", + &ibs_config.op_enabled); + oprofilefs_create_ulong(sb, dir, "max_count", + &ibs_config.max_cnt_op); + oprofilefs_create_ulong(sb, dir, "dispatched_ops", + &ibs_config.dispatched_ops); + + return 0; +} + +static int op_amd_init(struct oprofile_operations *ops) +{ + setup_ibs(); + create_arch_files = ops->create_files; + ops->create_files = setup_ibs_files; + return 0; +} + +static void op_amd_exit(void) +{ + clear_ibs_nmi(); +} + +#endif + +struct op_x86_model_spec const op_amd_spec = { + .init = op_amd_init, + .exit = op_amd_exit, + .num_counters = NUM_COUNTERS, + .num_controls = NUM_CONTROLS, + .num_hardware_counters = NUM_HARDWARE_COUNTERS, + .num_hardware_controls = NUM_HARDWARE_CONTROLS, + .fill_in_addresses = &op_amd_fill_in_addresses, + .setup_ctrs = &op_amd_setup_ctrs, + .check_ctrs = &op_amd_check_ctrs, + .start = &op_amd_start, + .stop = &op_amd_stop, + .shutdown = &op_amd_shutdown +}; diff --git a/arch/x86/oprofile/op_model_athlon.c b/arch/x86/oprofile/op_model_athlon.c deleted file mode 100644 index 3d534879a9d..00000000000 --- a/arch/x86/oprofile/op_model_athlon.c +++ /dev/null @@ -1,190 +0,0 @@ -/* - * @file op_model_athlon.h - * athlon / K7 / K8 / Family 10h model-specific MSR operations - * - * @remark Copyright 2002 OProfile authors - * @remark Read the file COPYING - * - * @author John Levon - * @author Philippe Elie - * @author Graydon Hoare - */ - -#include <linux/oprofile.h> -#include <asm/ptrace.h> -#include <asm/msr.h> -#include <asm/nmi.h> - -#include "op_x86_model.h" -#include "op_counter.h" - -#define NUM_COUNTERS 4 -#define NUM_CONTROLS 4 - -#define CTR_IS_RESERVED(msrs, c) (msrs->counters[(c)].addr ? 1 : 0) -#define CTR_READ(l, h, msrs, c) do {rdmsr(msrs->counters[(c)].addr, (l), (h)); } while (0) -#define CTR_WRITE(l, msrs, c) do {wrmsr(msrs->counters[(c)].addr, -(unsigned int)(l), -1); } while (0) -#define CTR_OVERFLOWED(n) (!((n) & (1U<<31))) - -#define CTRL_IS_RESERVED(msrs, c) (msrs->controls[(c)].addr ? 1 : 0) -#define CTRL_READ(l, h, msrs, c) do {rdmsr(msrs->controls[(c)].addr, (l), (h)); } while (0) -#define CTRL_WRITE(l, h, msrs, c) do {wrmsr(msrs->controls[(c)].addr, (l), (h)); } while (0) -#define CTRL_SET_ACTIVE(n) (n |= (1<<22)) -#define CTRL_SET_INACTIVE(n) (n &= ~(1<<22)) -#define CTRL_CLEAR_LO(x) (x &= (1<<21)) -#define CTRL_CLEAR_HI(x) (x &= 0xfffffcf0) -#define CTRL_SET_ENABLE(val) (val |= 1<<20) -#define CTRL_SET_USR(val, u) (val |= ((u & 1) << 16)) -#define CTRL_SET_KERN(val, k) (val |= ((k & 1) << 17)) -#define CTRL_SET_UM(val, m) (val |= (m << 8)) -#define CTRL_SET_EVENT_LOW(val, e) (val |= (e & 0xff)) -#define CTRL_SET_EVENT_HIGH(val, e) (val |= ((e >> 8) & 0xf)) -#define CTRL_SET_HOST_ONLY(val, h) (val |= ((h & 1) << 9)) -#define CTRL_SET_GUEST_ONLY(val, h) (val |= ((h & 1) << 8)) - -static unsigned long reset_value[NUM_COUNTERS]; - -static void athlon_fill_in_addresses(struct op_msrs * const msrs) -{ - int i; - - for (i = 0; i < NUM_COUNTERS; i++) { - if (reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i)) - msrs->counters[i].addr = MSR_K7_PERFCTR0 + i; - else - msrs->counters[i].addr = 0; - } - - for (i = 0; i < NUM_CONTROLS; i++) { - if (reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i)) - msrs->controls[i].addr = MSR_K7_EVNTSEL0 + i; - else - msrs->controls[i].addr = 0; - } -} - - -static void athlon_setup_ctrs(struct op_msrs const * const msrs) -{ - unsigned int low, high; - int i; - - /* clear all counters */ - for (i = 0 ; i < NUM_CONTROLS; ++i) { - if (unlikely(!CTRL_IS_RESERVED(msrs, i))) - continue; - CTRL_READ(low, high, msrs, i); - CTRL_CLEAR_LO(low); - CTRL_CLEAR_HI(high); - CTRL_WRITE(low, high, msrs, i); - } - - /* avoid a false detection of ctr overflows in NMI handler */ - for (i = 0; i < NUM_COUNTERS; ++i) { - if (unlikely(!CTR_IS_RESERVED(msrs, i))) - continue; - CTR_WRITE(1, msrs, i); - } - - /* enable active counters */ - for (i = 0; i < NUM_COUNTERS; ++i) { - if ((counter_config[i].enabled) && (CTR_IS_RESERVED(msrs, i))) { - reset_value[i] = counter_config[i].count; - - CTR_WRITE(counter_config[i].count, msrs, i); - - CTRL_READ(low, high, msrs, i); - CTRL_CLEAR_LO(low); - CTRL_CLEAR_HI(high); - CTRL_SET_ENABLE(low); - CTRL_SET_USR(low, counter_config[i].user); - CTRL_SET_KERN(low, counter_config[i].kernel); - CTRL_SET_UM(low, counter_config[i].unit_mask); - CTRL_SET_EVENT_LOW(low, counter_config[i].event); - CTRL_SET_EVENT_HIGH(high, counter_config[i].event); - CTRL_SET_HOST_ONLY(high, 0); - CTRL_SET_GUEST_ONLY(high, 0); - - CTRL_WRITE(low, high, msrs, i); - } else { - reset_value[i] = 0; - } - } -} - - -static int athlon_check_ctrs(struct pt_regs * const regs, - struct op_msrs const * const msrs) -{ - unsigned int low, high; - int i; - - for (i = 0 ; i < NUM_COUNTERS; ++i) { - if (!reset_value[i]) - continue; - CTR_READ(low, high, msrs, i); - if (CTR_OVERFLOWED(low)) { - oprofile_add_sample(regs, i); - CTR_WRITE(reset_value[i], msrs, i); - } - } - - /* See op_model_ppro.c */ - return 1; -} - - -static void athlon_start(struct op_msrs const * const msrs) -{ - unsigned int low, high; - int i; - for (i = 0 ; i < NUM_COUNTERS ; ++i) { - if (reset_value[i]) { - CTRL_READ(low, high, msrs, i); - CTRL_SET_ACTIVE(low); - CTRL_WRITE(low, high, msrs, i); - } - } -} - - -static void athlon_stop(struct op_msrs const * const msrs) -{ - unsigned int low, high; - int i; - - /* Subtle: stop on all counters to avoid race with - * setting our pm callback */ - for (i = 0 ; i < NUM_COUNTERS ; ++i) { - if (!reset_value[i]) - continue; - CTRL_READ(low, high, msrs, i); - CTRL_SET_INACTIVE(low); - CTRL_WRITE(low, high, msrs, i); - } -} - -static void athlon_shutdown(struct op_msrs const * const msrs) -{ - int i; - - for (i = 0 ; i < NUM_COUNTERS ; ++i) { - if (CTR_IS_RESERVED(msrs, i)) - release_perfctr_nmi(MSR_K7_PERFCTR0 + i); - } - for (i = 0 ; i < NUM_CONTROLS ; ++i) { - if (CTRL_IS_RESERVED(msrs, i)) - release_evntsel_nmi(MSR_K7_EVNTSEL0 + i); - } -} - -struct op_x86_model_spec const op_athlon_spec = { - .num_counters = NUM_COUNTERS, - .num_controls = NUM_CONTROLS, - .fill_in_addresses = &athlon_fill_in_addresses, - .setup_ctrs = &athlon_setup_ctrs, - .check_ctrs = &athlon_check_ctrs, - .start = &athlon_start, - .stop = &athlon_stop, - .shutdown = &athlon_shutdown -}; diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c index 56b4757a1f4..cacba61ffba 100644 --- a/arch/x86/oprofile/op_model_p4.c +++ b/arch/x86/oprofile/op_model_p4.c @@ -10,11 +10,12 @@ #include <linux/oprofile.h> #include <linux/smp.h> +#include <linux/ptrace.h> +#include <linux/nmi.h> #include <asm/msr.h> -#include <asm/ptrace.h> #include <asm/fixmap.h> #include <asm/apic.h> -#include <asm/nmi.h> + #include "op_x86_model.h" #include "op_counter.h" @@ -40,7 +41,7 @@ static unsigned int num_controls = NUM_CONTROLS_NON_HT; static inline void setup_num_counters(void) { #ifdef CONFIG_SMP - if (smp_num_siblings == 2){ + if (smp_num_siblings == 2) { num_counters = NUM_COUNTERS_HT2; num_controls = NUM_CONTROLS_HT2; } @@ -86,7 +87,7 @@ struct p4_event_binding { #define CTR_FLAME_2 (1 << 6) #define CTR_IQ_5 (1 << 7) -static struct p4_counter_binding p4_counters [NUM_COUNTERS_NON_HT] = { +static struct p4_counter_binding p4_counters[NUM_COUNTERS_NON_HT] = { { CTR_BPU_0, MSR_P4_BPU_PERFCTR0, MSR_P4_BPU_CCCR0 }, { CTR_MS_0, MSR_P4_MS_PERFCTR0, MSR_P4_MS_CCCR0 }, { CTR_FLAME_0, MSR_P4_FLAME_PERFCTR0, MSR_P4_FLAME_CCCR0 }, @@ -97,32 +98,32 @@ static struct p4_counter_binding p4_counters [NUM_COUNTERS_NON_HT] = { { CTR_IQ_5, MSR_P4_IQ_PERFCTR5, MSR_P4_IQ_CCCR5 } }; -#define NUM_UNUSED_CCCRS NUM_CCCRS_NON_HT - NUM_COUNTERS_NON_HT +#define NUM_UNUSED_CCCRS (NUM_CCCRS_NON_HT - NUM_COUNTERS_NON_HT) /* p4 event codes in libop/op_event.h are indices into this table. */ static struct p4_event_binding p4_events[NUM_EVENTS] = { - + { /* BRANCH_RETIRED */ - 0x05, 0x06, + 0x05, 0x06, { {CTR_IQ_4, MSR_P4_CRU_ESCR2}, {CTR_IQ_5, MSR_P4_CRU_ESCR3} } }, - + { /* MISPRED_BRANCH_RETIRED */ - 0x04, 0x03, + 0x04, 0x03, { { CTR_IQ_4, MSR_P4_CRU_ESCR0}, { CTR_IQ_5, MSR_P4_CRU_ESCR1} } }, - + { /* TC_DELIVER_MODE */ 0x01, 0x01, - { { CTR_MS_0, MSR_P4_TC_ESCR0}, + { { CTR_MS_0, MSR_P4_TC_ESCR0}, { CTR_MS_2, MSR_P4_TC_ESCR1} } }, - + { /* BPU_FETCH_REQUEST */ - 0x00, 0x03, + 0x00, 0x03, { { CTR_BPU_0, MSR_P4_BPU_ESCR0}, { CTR_BPU_2, MSR_P4_BPU_ESCR1} } }, @@ -146,7 +147,7 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = { }, { /* LOAD_PORT_REPLAY */ - 0x02, 0x04, + 0x02, 0x04, { { CTR_FLAME_0, MSR_P4_SAAT_ESCR0}, { CTR_FLAME_2, MSR_P4_SAAT_ESCR1} } }, @@ -170,43 +171,43 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = { }, { /* BSQ_CACHE_REFERENCE */ - 0x07, 0x0c, + 0x07, 0x0c, { { CTR_BPU_0, MSR_P4_BSU_ESCR0}, { CTR_BPU_2, MSR_P4_BSU_ESCR1} } }, { /* IOQ_ALLOCATION */ - 0x06, 0x03, + 0x06, 0x03, { { CTR_BPU_0, MSR_P4_FSB_ESCR0}, { 0, 0 } } }, { /* IOQ_ACTIVE_ENTRIES */ - 0x06, 0x1a, + 0x06, 0x1a, { { CTR_BPU_2, MSR_P4_FSB_ESCR1}, { 0, 0 } } }, { /* FSB_DATA_ACTIVITY */ - 0x06, 0x17, + 0x06, 0x17, { { CTR_BPU_0, MSR_P4_FSB_ESCR0}, { CTR_BPU_2, MSR_P4_FSB_ESCR1} } }, { /* BSQ_ALLOCATION */ - 0x07, 0x05, + 0x07, 0x05, { { CTR_BPU_0, MSR_P4_BSU_ESCR0}, { 0, 0 } } }, { /* BSQ_ACTIVE_ENTRIES */ 0x07, 0x06, - { { CTR_BPU_2, MSR_P4_BSU_ESCR1 /* guess */}, + { { CTR_BPU_2, MSR_P4_BSU_ESCR1 /* guess */}, { 0, 0 } } }, { /* X87_ASSIST */ - 0x05, 0x03, + 0x05, 0x03, { { CTR_IQ_4, MSR_P4_CRU_ESCR2}, { CTR_IQ_5, MSR_P4_CRU_ESCR3} } }, @@ -216,21 +217,21 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = { { { CTR_FLAME_0, MSR_P4_FIRM_ESCR0}, { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} } }, - + { /* PACKED_SP_UOP */ - 0x01, 0x08, + 0x01, 0x08, { { CTR_FLAME_0, MSR_P4_FIRM_ESCR0}, { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} } }, - + { /* PACKED_DP_UOP */ - 0x01, 0x0c, + 0x01, 0x0c, { { CTR_FLAME_0, MSR_P4_FIRM_ESCR0}, { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} } }, { /* SCALAR_SP_UOP */ - 0x01, 0x0a, + 0x01, 0x0a, { { CTR_FLAME_0, MSR_P4_FIRM_ESCR0}, { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} } }, @@ -242,31 +243,31 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = { }, { /* 64BIT_MMX_UOP */ - 0x01, 0x02, + 0x01, 0x02, { { CTR_FLAME_0, MSR_P4_FIRM_ESCR0}, { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} } }, - + { /* 128BIT_MMX_UOP */ - 0x01, 0x1a, + 0x01, 0x1a, { { CTR_FLAME_0, MSR_P4_FIRM_ESCR0}, { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} } }, { /* X87_FP_UOP */ - 0x01, 0x04, + 0x01, 0x04, { { CTR_FLAME_0, MSR_P4_FIRM_ESCR0}, { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} } }, - + { /* X87_SIMD_MOVES_UOP */ - 0x01, 0x2e, + 0x01, 0x2e, { { CTR_FLAME_0, MSR_P4_FIRM_ESCR0}, { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} } }, - + { /* MACHINE_CLEAR */ - 0x05, 0x02, + 0x05, 0x02, { { CTR_IQ_4, MSR_P4_CRU_ESCR2}, { CTR_IQ_5, MSR_P4_CRU_ESCR3} } }, @@ -276,9 +277,9 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = { { { CTR_BPU_0, MSR_P4_FSB_ESCR0}, { CTR_BPU_2, MSR_P4_FSB_ESCR1} } }, - + { /* TC_MS_XFER */ - 0x00, 0x05, + 0x00, 0x05, { { CTR_MS_0, MSR_P4_MS_ESCR0}, { CTR_MS_2, MSR_P4_MS_ESCR1} } }, @@ -308,7 +309,7 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = { }, { /* INSTR_RETIRED */ - 0x04, 0x02, + 0x04, 0x02, { { CTR_IQ_4, MSR_P4_CRU_ESCR0}, { CTR_IQ_5, MSR_P4_CRU_ESCR1} } }, @@ -319,14 +320,14 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = { { CTR_IQ_5, MSR_P4_CRU_ESCR1} } }, - { /* UOP_TYPE */ - 0x02, 0x02, + { /* UOP_TYPE */ + 0x02, 0x02, { { CTR_IQ_4, MSR_P4_RAT_ESCR0}, { CTR_IQ_5, MSR_P4_RAT_ESCR1} } }, { /* RETIRED_MISPRED_BRANCH_TYPE */ - 0x02, 0x05, + 0x02, 0x05, { { CTR_MS_0, MSR_P4_TBPU_ESCR0}, { CTR_MS_2, MSR_P4_TBPU_ESCR1} } }, @@ -349,8 +350,8 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = { #define ESCR_SET_OS_1(escr, os) ((escr) |= (((os) & 1) << 1)) #define ESCR_SET_EVENT_SELECT(escr, sel) ((escr) |= (((sel) & 0x3f) << 25)) #define ESCR_SET_EVENT_MASK(escr, mask) ((escr) |= (((mask) & 0xffff) << 9)) -#define ESCR_READ(escr,high,ev,i) do {rdmsr(ev->bindings[(i)].escr_address, (escr), (high));} while (0) -#define ESCR_WRITE(escr,high,ev,i) do {wrmsr(ev->bindings[(i)].escr_address, (escr), (high));} while (0) +#define ESCR_READ(escr, high, ev, i) do {rdmsr(ev->bindings[(i)].escr_address, (escr), (high)); } while (0) +#define ESCR_WRITE(escr, high, ev, i) do {wrmsr(ev->bindings[(i)].escr_address, (escr), (high)); } while (0) #define CCCR_RESERVED_BITS 0x38030FFF #define CCCR_CLEAR(cccr) ((cccr) &= CCCR_RESERVED_BITS) @@ -360,15 +361,15 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = { #define CCCR_SET_PMI_OVF_1(cccr) ((cccr) |= (1<<27)) #define CCCR_SET_ENABLE(cccr) ((cccr) |= (1<<12)) #define CCCR_SET_DISABLE(cccr) ((cccr) &= ~(1<<12)) -#define CCCR_READ(low, high, i) do {rdmsr(p4_counters[(i)].cccr_address, (low), (high));} while (0) -#define CCCR_WRITE(low, high, i) do {wrmsr(p4_counters[(i)].cccr_address, (low), (high));} while (0) +#define CCCR_READ(low, high, i) do {rdmsr(p4_counters[(i)].cccr_address, (low), (high)); } while (0) +#define CCCR_WRITE(low, high, i) do {wrmsr(p4_counters[(i)].cccr_address, (low), (high)); } while (0) #define CCCR_OVF_P(cccr) ((cccr) & (1U<<31)) #define CCCR_CLEAR_OVF(cccr) ((cccr) &= (~(1U<<31))) -#define CTRL_IS_RESERVED(msrs,c) (msrs->controls[(c)].addr ? 1 : 0) -#define CTR_IS_RESERVED(msrs,c) (msrs->counters[(c)].addr ? 1 : 0) -#define CTR_READ(l,h,i) do {rdmsr(p4_counters[(i)].counter_address, (l), (h));} while (0) -#define CTR_WRITE(l,i) do {wrmsr(p4_counters[(i)].counter_address, -(u32)(l), -1);} while (0) +#define CTRL_IS_RESERVED(msrs, c) (msrs->controls[(c)].addr ? 1 : 0) +#define CTR_IS_RESERVED(msrs, c) (msrs->counters[(c)].addr ? 1 : 0) +#define CTR_READ(l, h, i) do {rdmsr(p4_counters[(i)].counter_address, (l), (h)); } while (0) +#define CTR_WRITE(l, i) do {wrmsr(p4_counters[(i)].counter_address, -(u32)(l), -1); } while (0) #define CTR_OVERFLOW_P(ctr) (!((ctr) & 0x80000000)) @@ -380,7 +381,7 @@ static unsigned int get_stagger(void) #ifdef CONFIG_SMP int cpu = smp_processor_id(); return (cpu != first_cpu(per_cpu(cpu_sibling_map, cpu))); -#endif +#endif return 0; } @@ -395,25 +396,23 @@ static unsigned long reset_value[NUM_COUNTERS_NON_HT]; static void p4_fill_in_addresses(struct op_msrs * const msrs) { - unsigned int i; + unsigned int i; unsigned int addr, cccraddr, stag; setup_num_counters(); stag = get_stagger(); /* initialize some registers */ - for (i = 0; i < num_counters; ++i) { + for (i = 0; i < num_counters; ++i) msrs->counters[i].addr = 0; - } - for (i = 0; i < num_controls; ++i) { + for (i = 0; i < num_controls; ++i) msrs->controls[i].addr = 0; - } - + /* the counter & cccr registers we pay attention to */ for (i = 0; i < num_counters; ++i) { addr = p4_counters[VIRT_CTR(stag, i)].counter_address; cccraddr = p4_counters[VIRT_CTR(stag, i)].cccr_address; - if (reserve_perfctr_nmi(addr)){ + if (reserve_perfctr_nmi(addr)) { msrs->counters[i].addr = addr; msrs->controls[i].addr = cccraddr; } @@ -447,22 +446,22 @@ static void p4_fill_in_addresses(struct op_msrs * const msrs) if (reserve_evntsel_nmi(addr)) msrs->controls[i].addr = addr; } - + for (addr = MSR_P4_MS_ESCR0 + stag; - addr <= MSR_P4_TC_ESCR1; ++i, addr += addr_increment()) { + addr <= MSR_P4_TC_ESCR1; ++i, addr += addr_increment()) { if (reserve_evntsel_nmi(addr)) msrs->controls[i].addr = addr; } - + for (addr = MSR_P4_IX_ESCR0 + stag; - addr <= MSR_P4_CRU_ESCR3; ++i, addr += addr_increment()) { + addr <= MSR_P4_CRU_ESCR3; ++i, addr += addr_increment()) { if (reserve_evntsel_nmi(addr)) msrs->controls[i].addr = addr; } /* there are 2 remaining non-contiguously located ESCRs */ - if (num_counters == NUM_COUNTERS_NON_HT) { + if (num_counters == NUM_COUNTERS_NON_HT) { /* standard non-HT CPUs handle both remaining ESCRs*/ if (reserve_evntsel_nmi(MSR_P4_CRU_ESCR5)) msrs->controls[i++].addr = MSR_P4_CRU_ESCR5; @@ -498,20 +497,20 @@ static void pmc_setup_one_p4_counter(unsigned int ctr) unsigned int stag; stag = get_stagger(); - + /* convert from counter *number* to counter *bit* */ counter_bit = 1 << VIRT_CTR(stag, ctr); - + /* find our event binding structure. */ if (counter_config[ctr].event <= 0 || counter_config[ctr].event > NUM_EVENTS) { - printk(KERN_ERR - "oprofile: P4 event code 0x%lx out of range\n", + printk(KERN_ERR + "oprofile: P4 event code 0x%lx out of range\n", counter_config[ctr].event); return; } - + ev = &(p4_events[counter_config[ctr].event - 1]); - + for (i = 0; i < maxbind; i++) { if (ev->bindings[i].virt_counter & counter_bit) { @@ -526,25 +525,24 @@ static void pmc_setup_one_p4_counter(unsigned int ctr) ESCR_SET_OS_1(escr, counter_config[ctr].kernel); } ESCR_SET_EVENT_SELECT(escr, ev->event_select); - ESCR_SET_EVENT_MASK(escr, counter_config[ctr].unit_mask); + ESCR_SET_EVENT_MASK(escr, counter_config[ctr].unit_mask); ESCR_WRITE(escr, high, ev, i); - + /* modify CCCR */ CCCR_READ(cccr, high, VIRT_CTR(stag, ctr)); CCCR_CLEAR(cccr); CCCR_SET_REQUIRED_BITS(cccr); CCCR_SET_ESCR_SELECT(cccr, ev->escr_select); - if (stag == 0) { + if (stag == 0) CCCR_SET_PMI_OVF_0(cccr); - } else { + else CCCR_SET_PMI_OVF_1(cccr); - } CCCR_WRITE(cccr, high, VIRT_CTR(stag, ctr)); return; } } - printk(KERN_ERR + printk(KERN_ERR "oprofile: P4 event code 0x%lx no binding, stag %d ctr %d\n", counter_config[ctr].event, stag, ctr); } @@ -559,14 +557,14 @@ static void p4_setup_ctrs(struct op_msrs const * const msrs) stag = get_stagger(); rdmsr(MSR_IA32_MISC_ENABLE, low, high); - if (! MISC_PMC_ENABLED_P(low)) { + if (!MISC_PMC_ENABLED_P(low)) { printk(KERN_ERR "oprofile: P4 PMC not available\n"); return; } /* clear the cccrs we will use */ for (i = 0 ; i < num_counters ; i++) { - if (unlikely(!CTRL_IS_RESERVED(msrs,i))) + if (unlikely(!CTRL_IS_RESERVED(msrs, i))) continue; rdmsr(p4_counters[VIRT_CTR(stag, i)].cccr_address, low, high); CCCR_CLEAR(low); @@ -576,14 +574,14 @@ static void p4_setup_ctrs(struct op_msrs const * const msrs) /* clear all escrs (including those outside our concern) */ for (i = num_counters; i < num_controls; i++) { - if (unlikely(!CTRL_IS_RESERVED(msrs,i))) + if (unlikely(!CTRL_IS_RESERVED(msrs, i))) continue; wrmsr(msrs->controls[i].addr, 0, 0); } /* setup all counters */ for (i = 0 ; i < num_counters ; ++i) { - if ((counter_config[i].enabled) && (CTRL_IS_RESERVED(msrs,i))) { + if ((counter_config[i].enabled) && (CTRL_IS_RESERVED(msrs, i))) { reset_value[i] = counter_config[i].count; pmc_setup_one_p4_counter(i); CTR_WRITE(counter_config[i].count, VIRT_CTR(stag, i)); @@ -603,11 +601,11 @@ static int p4_check_ctrs(struct pt_regs * const regs, stag = get_stagger(); for (i = 0; i < num_counters; ++i) { - - if (!reset_value[i]) + + if (!reset_value[i]) continue; - /* + /* * there is some eccentricity in the hardware which * requires that we perform 2 extra corrections: * @@ -616,24 +614,24 @@ static int p4_check_ctrs(struct pt_regs * const regs, * * - write the counter back twice to ensure it gets * updated properly. - * + * * the former seems to be related to extra NMIs happening * during the current NMI; the latter is reported as errata * N15 in intel doc 249199-029, pentium 4 specification * update, though their suggested work-around does not * appear to solve the problem. */ - + real = VIRT_CTR(stag, i); CCCR_READ(low, high, real); - CTR_READ(ctr, high, real); + CTR_READ(ctr, high, real); if (CCCR_OVF_P(low) || CTR_OVERFLOW_P(ctr)) { oprofile_add_sample(regs, i); - CTR_WRITE(reset_value[i], real); + CTR_WRITE(reset_value[i], real); CCCR_CLEAR_OVF(low); CCCR_WRITE(low, high, real); - CTR_WRITE(reset_value[i], real); + CTR_WRITE(reset_value[i], real); } } @@ -683,15 +681,16 @@ static void p4_shutdown(struct op_msrs const * const msrs) int i; for (i = 0 ; i < num_counters ; ++i) { - if (CTR_IS_RESERVED(msrs,i)) + if (CTR_IS_RESERVED(msrs, i)) release_perfctr_nmi(msrs->counters[i].addr); } - /* some of the control registers are specially reserved in + /* + * some of the control registers are specially reserved in * conjunction with the counter registers (hence the starting offset). * This saves a few bits. */ for (i = num_counters ; i < num_controls ; ++i) { - if (CTRL_IS_RESERVED(msrs,i)) + if (CTRL_IS_RESERVED(msrs, i)) release_evntsel_nmi(msrs->controls[i].addr); } } @@ -701,6 +700,8 @@ static void p4_shutdown(struct op_msrs const * const msrs) struct op_x86_model_spec const op_p4_ht2_spec = { .num_counters = NUM_COUNTERS_HT2, .num_controls = NUM_CONTROLS_HT2, + .num_hardware_counters = NUM_COUNTERS_HT2, + .num_hardware_controls = NUM_CONTROLS_HT2, .fill_in_addresses = &p4_fill_in_addresses, .setup_ctrs = &p4_setup_ctrs, .check_ctrs = &p4_check_ctrs, @@ -713,6 +714,8 @@ struct op_x86_model_spec const op_p4_ht2_spec = { struct op_x86_model_spec const op_p4_spec = { .num_counters = NUM_COUNTERS_NON_HT, .num_controls = NUM_CONTROLS_NON_HT, + .num_hardware_counters = NUM_COUNTERS_NON_HT, + .num_hardware_controls = NUM_CONTROLS_NON_HT, .fill_in_addresses = &p4_fill_in_addresses, .setup_ctrs = &p4_setup_ctrs, .check_ctrs = &p4_check_ctrs, diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c index eff431f6c57..e5811aa480e 100644 --- a/arch/x86/oprofile/op_model_ppro.c +++ b/arch/x86/oprofile/op_model_ppro.c @@ -183,6 +183,8 @@ static void ppro_shutdown(struct op_msrs const * const msrs) struct op_x86_model_spec const op_ppro_spec = { .num_counters = NUM_COUNTERS, .num_controls = NUM_CONTROLS, + .num_hardware_counters = NUM_COUNTERS, + .num_hardware_controls = NUM_CONTROLS, .fill_in_addresses = &ppro_fill_in_addresses, .setup_ctrs = &ppro_setup_ctrs, .check_ctrs = &ppro_check_ctrs, diff --git a/arch/x86/oprofile/op_x86_model.h b/arch/x86/oprofile/op_x86_model.h index 45b605fa71d..e07ba107637 100644 --- a/arch/x86/oprofile/op_x86_model.h +++ b/arch/x86/oprofile/op_x86_model.h @@ -19,6 +19,7 @@ struct op_saved_msr { struct op_msr { unsigned long addr; struct op_saved_msr saved; + struct op_saved_msr multiplex; }; struct op_msrs { @@ -32,6 +33,10 @@ struct pt_regs; * various x86 CPU models' perfctr support. */ struct op_x86_model_spec { + int (*init)(struct oprofile_operations *ops); + void (*exit)(void); + unsigned int const num_hardware_counters; + unsigned int const num_hardware_controls; unsigned int const num_counters; unsigned int const num_controls; void (*fill_in_addresses)(struct op_msrs * const msrs); @@ -46,6 +51,6 @@ struct op_x86_model_spec { extern struct op_x86_model_spec const op_ppro_spec; extern struct op_x86_model_spec const op_p4_spec; extern struct op_x86_model_spec const op_p4_ht2_spec; -extern struct op_x86_model_spec const op_athlon_spec; +extern struct op_x86_model_spec const op_amd_spec; #endif /* OP_X86_MODEL_H */ |