If unsure, say N.
+config OPROFILE_IBS
+ bool "OProfile AMD IBS support (EXPERIMENTAL)"
+ default n
+ depends on OPROFILE && SMP && X86
+ help
+ Instruction-Based Sampling (IBS) is a new profiling
+ technique that provides rich, precise program performance
+ information. IBS is introduced by AMD Family10h processors
+ (AMD Opteron Quad-Core processor “Barcelona”) to overcome
+ the limitations of conventional performance counter
+ sampling.
+
+ If unsure, say N.
+
config HAVE_OPROFILE
def_bool n
*
* 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
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
*
* 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
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
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
/**
* @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>
#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);
static int nmi_start(void);
static void nmi_stop(void);
+static void nmi_cpu_save_mpx_registers(struct op_msrs *msrs);
+static void nmi_cpu_restore_mpx_registers(struct op_msrs *msrs);
+static void nmi_cpu_stop(void *dummy);
+static void nmi_cpu_start(void *dummy);
/* 0 == registered but off, 1 == registered and on */
static int nmi_enabled = 0;
#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)
{
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);
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;
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
*/
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);
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;
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)
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;
__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;
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;
return -ENODEV;
}
- init_sysfs();
- using_nmi = 1;
+ /* default values, can be overwritten by model */
+ __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;
}
{
if (using_nmi)
exit_sysfs();
+ if (model->exit)
+ model->exit();
}
#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;
--- /dev/null
+/*
+ * @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
+};
+++ /dev/null
-/*
- * @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
-};
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,
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,
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,
struct op_msr {
unsigned long addr;
struct op_saved_msr saved;
+ struct op_saved_msr multiplex;
};
struct op_msrs {
* 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);
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 */
* @remark Read the file COPYING
*
* @author John Levon <levon@movementarian.org>
+ * @author Barry Kasindorf
*
* This is the core of the buffer management. Each
* CPU buffer is processed and entered into the
#include "event_buffer.h"
#include "cpu_buffer.h"
#include "buffer_sync.h"
-
+
static LIST_HEAD(dying_tasks);
static LIST_HEAD(dead_tasks);
static cpumask_t marked_cpus = CPU_MASK_NONE;
* Can be invoked from softirq via RCU callback due to
* call_rcu() of the task struct, hence the _irqsave.
*/
-static int task_free_notify(struct notifier_block * self, unsigned long val, void * data)
+static int
+task_free_notify(struct notifier_block *self, unsigned long val, void *data)
{
unsigned long flags;
- struct task_struct * task = data;
+ struct task_struct *task = data;
spin_lock_irqsave(&task_mortuary, flags);
list_add(&task->tasks, &dying_tasks);
spin_unlock_irqrestore(&task_mortuary, flags);
/* The task is on its way out. A sync of the buffer means we can catch
* any remaining samples for this task.
*/
-static int task_exit_notify(struct notifier_block * self, unsigned long val, void * data)
+static int
+task_exit_notify(struct notifier_block *self, unsigned long val, void *data)
{
/* To avoid latency problems, we only process the current CPU,
* hoping that most samples for the task are on this CPU
*/
sync_buffer(raw_smp_processor_id());
- return 0;
+ return 0;
}
* we don't lose any. This does not have to be exact, it's a QoI issue
* only.
*/
-static int munmap_notify(struct notifier_block * self, unsigned long val, void * data)
+static int
+munmap_notify(struct notifier_block *self, unsigned long val, void *data)
{
unsigned long addr = (unsigned long)data;
- struct mm_struct * mm = current->mm;
- struct vm_area_struct * mpnt;
+ struct mm_struct *mm = current->mm;
+ struct vm_area_struct *mpnt;
down_read(&mm->mmap_sem);
return 0;
}
-
+
/* We need to be told about new modules so we don't attribute to a previously
* loaded module, or drop the samples on the floor.
*/
-static int module_load_notify(struct notifier_block * self, unsigned long val, void * data)
+static int
+module_load_notify(struct notifier_block *self, unsigned long val, void *data)
{
#ifdef CONFIG_MODULES
if (val != MODULE_STATE_COMING)
return 0;
}
-
+
static struct notifier_block task_free_nb = {
.notifier_call = task_free_notify,
};
.notifier_call = module_load_notify,
};
-
+
static void end_sync(void)
{
end_cpu_work();
* not strictly necessary but allows oprofile to associate
* shared-library samples with particular applications
*/
-static unsigned long get_exec_dcookie(struct mm_struct * mm)
+static unsigned long get_exec_dcookie(struct mm_struct *mm)
{
unsigned long cookie = NO_COOKIE;
- struct vm_area_struct * vma;
-
+ struct vm_area_struct *vma;
+
if (!mm)
goto out;
-
+
for (vma = mm->mmap; vma; vma = vma->vm_next) {
if (!vma->vm_file)
continue;
* sure to do this lookup before a mm->mmap modification happens so
* we don't lose track.
*/
-static unsigned long lookup_dcookie(struct mm_struct * mm, unsigned long addr, off_t * offset)
+static unsigned long
+lookup_dcookie(struct mm_struct *mm, unsigned long addr, off_t *offset)
{
unsigned long cookie = NO_COOKIE;
- struct vm_area_struct * vma;
+ struct vm_area_struct *vma;
for (vma = find_vma(mm, addr); vma; vma = vma->vm_next) {
-
+
if (addr < vma->vm_start || addr >= vma->vm_end)
continue;
return cookie;
}
+static void increment_tail(struct oprofile_cpu_buffer *b)
+{
+ unsigned long new_tail = b->tail_pos + 1;
+
+ rmb(); /* be sure fifo pointers are synchromized */
+
+ if (new_tail < b->buffer_size)
+ b->tail_pos = new_tail;
+ else
+ b->tail_pos = 0;
+}
static unsigned long last_cookie = INVALID_COOKIE;
-
+
static void add_cpu_switch(int i)
{
add_event_entry(ESCAPE_CODE);
{
add_event_entry(ESCAPE_CODE);
if (in_kernel)
- add_event_entry(KERNEL_ENTER_SWITCH_CODE);
+ add_event_entry(KERNEL_ENTER_SWITCH_CODE);
else
- add_event_entry(KERNEL_EXIT_SWITCH_CODE);
+ add_event_entry(KERNEL_EXIT_SWITCH_CODE);
}
-
+
static void
-add_user_ctx_switch(struct task_struct const * task, unsigned long cookie)
+add_user_ctx_switch(struct task_struct const *task, unsigned long cookie)
{
add_event_entry(ESCAPE_CODE);
- add_event_entry(CTX_SWITCH_CODE);
+ add_event_entry(CTX_SWITCH_CODE);
add_event_entry(task->pid);
add_event_entry(cookie);
/* Another code for daemon back-compat */
add_event_entry(task->tgid);
}
-
+
static void add_cookie_switch(unsigned long cookie)
{
add_event_entry(ESCAPE_CODE);
add_event_entry(cookie);
}
-
+
static void add_trace_begin(void)
{
add_event_entry(ESCAPE_CODE);
add_event_entry(TRACE_BEGIN_CODE);
}
+#ifdef CONFIG_OPROFILE_IBS
+
+#define IBS_FETCH_CODE_SIZE 2
+#define IBS_OP_CODE_SIZE 5
+#define IBS_EIP(offset) \
+ (((struct op_sample *)&cpu_buf->buffer[(offset)])->eip)
+#define IBS_EVENT(offset) \
+ (((struct op_sample *)&cpu_buf->buffer[(offset)])->event)
+
+/*
+ * Add IBS fetch and op entries to event buffer
+ */
+static void add_ibs_begin(struct oprofile_cpu_buffer *cpu_buf, int code,
+ int in_kernel, struct mm_struct *mm)
+{
+ unsigned long rip;
+ int i, count;
+ unsigned long ibs_cookie = 0;
+ off_t offset;
+
+ increment_tail(cpu_buf); /* move to RIP entry */
+
+ rip = IBS_EIP(cpu_buf->tail_pos);
+
+#ifdef __LP64__
+ rip += IBS_EVENT(cpu_buf->tail_pos) << 32;
+#endif
+
+ if (mm) {
+ ibs_cookie = lookup_dcookie(mm, rip, &offset);
+
+ if (ibs_cookie == NO_COOKIE)
+ offset = rip;
+ if (ibs_cookie == INVALID_COOKIE) {
+ atomic_inc(&oprofile_stats.sample_lost_no_mapping);
+ offset = rip;
+ }
+ if (ibs_cookie != last_cookie) {
+ add_cookie_switch(ibs_cookie);
+ last_cookie = ibs_cookie;
+ }
+ } else
+ offset = rip;
+
+ add_event_entry(ESCAPE_CODE);
+ add_event_entry(code);
+ add_event_entry(offset); /* Offset from Dcookie */
+
+ /* we send the Dcookie offset, but send the raw Linear Add also*/
+ add_event_entry(IBS_EIP(cpu_buf->tail_pos));
+ add_event_entry(IBS_EVENT(cpu_buf->tail_pos));
+
+ if (code == IBS_FETCH_CODE)
+ count = IBS_FETCH_CODE_SIZE; /*IBS FETCH is 2 int64s*/
+ else
+ count = IBS_OP_CODE_SIZE; /*IBS OP is 5 int64s*/
+
+ for (i = 0; i < count; i++) {
+ increment_tail(cpu_buf);
+ add_event_entry(IBS_EIP(cpu_buf->tail_pos));
+ add_event_entry(IBS_EVENT(cpu_buf->tail_pos));
+ }
+}
+
+#endif
static void add_sample_entry(unsigned long offset, unsigned long event)
{
}
-static int add_us_sample(struct mm_struct * mm, struct op_sample * s)
+static int add_us_sample(struct mm_struct *mm, struct op_sample *s)
{
unsigned long cookie;
off_t offset;
-
- cookie = lookup_dcookie(mm, s->eip, &offset);
-
+
+ cookie = lookup_dcookie(mm, s->eip, &offset);
+
if (cookie == INVALID_COOKIE) {
atomic_inc(&oprofile_stats.sample_lost_no_mapping);
return 0;
return 1;
}
-
+
/* Add a sample to the global event buffer. If possible the
* sample is converted into a persistent dentry/offset pair
* for later lookup from userspace.
*/
static int
-add_sample(struct mm_struct * mm, struct op_sample * s, int in_kernel)
+add_sample(struct mm_struct *mm, struct op_sample *s, int in_kernel)
{
if (in_kernel) {
add_sample_entry(s->eip, s->event);
}
return 0;
}
-
-static void release_mm(struct mm_struct * mm)
+
+static void release_mm(struct mm_struct *mm)
{
if (!mm)
return;
}
-static struct mm_struct * take_tasks_mm(struct task_struct * task)
+static struct mm_struct *take_tasks_mm(struct task_struct *task)
{
- struct mm_struct * mm = get_task_mm(task);
+ struct mm_struct *mm = get_task_mm(task);
if (mm)
down_read(&mm->mmap_sem);
return mm;
{
return val == ESCAPE_CODE;
}
-
+
/* "acquire" as many cpu buffer slots as we can */
-static unsigned long get_slots(struct oprofile_cpu_buffer * b)
+static unsigned long get_slots(struct oprofile_cpu_buffer *b)
{
unsigned long head = b->head_pos;
unsigned long tail = b->tail_pos;
}
-static void increment_tail(struct oprofile_cpu_buffer * b)
-{
- unsigned long new_tail = b->tail_pos + 1;
-
- rmb();
-
- if (new_tail < b->buffer_size)
- b->tail_pos = new_tail;
- else
- b->tail_pos = 0;
-}
-
-
/* Move tasks along towards death. Any tasks on dead_tasks
* will definitely have no remaining references in any
* CPU buffers at this point, because we use two lists,
{
unsigned long flags;
LIST_HEAD(local_dead_tasks);
- struct task_struct * task;
- struct task_struct * ttask;
+ struct task_struct *task;
+ struct task_struct *ttask;
spin_lock_irqsave(&task_mortuary, flags);
{
struct oprofile_cpu_buffer *cpu_buf = &per_cpu(cpu_buffer, cpu);
struct mm_struct *mm = NULL;
- struct task_struct * new;
+ struct task_struct *new;
unsigned long cookie = 0;
int in_kernel = 1;
unsigned int i;
unsigned long available;
mutex_lock(&buffer_mutex);
-
+
add_cpu_switch(cpu);
/* Remember, only we can modify tail_pos */
available = get_slots(cpu_buf);
for (i = 0; i < available; ++i) {
- struct op_sample * s = &cpu_buf->buffer[cpu_buf->tail_pos];
-
+ struct op_sample *s = &cpu_buf->buffer[cpu_buf->tail_pos];
+
if (is_code(s->eip)) {
if (s->event <= CPU_IS_KERNEL) {
/* kernel/userspace switch */
} else if (s->event == CPU_TRACE_BEGIN) {
state = sb_bt_start;
add_trace_begin();
+#ifdef CONFIG_OPROFILE_IBS
+ } else if (s->event == IBS_FETCH_BEGIN) {
+ state = sb_bt_start;
+ add_ibs_begin(cpu_buf,
+ IBS_FETCH_CODE, in_kernel, mm);
+ } else if (s->event == IBS_OP_BEGIN) {
+ state = sb_bt_start;
+ add_ibs_begin(cpu_buf,
+ IBS_OP_CODE, in_kernel, mm);
+#endif
} else {
- struct mm_struct * oldmm = mm;
+ struct mm_struct *oldmm = mm;
/* userspace context switch */
new = (struct task_struct *)s->event;
cookie = get_exec_dcookie(mm);
add_user_ctx_switch(new, cookie);
}
- } else {
- if (state >= sb_bt_start &&
- !add_sample(mm, s, in_kernel)) {
- if (state == sb_bt_start) {
- state = sb_bt_ignore;
- atomic_inc(&oprofile_stats.bt_lost_no_mapping);
- }
+ } else if (state >= sb_bt_start &&
+ !add_sample(mm, s, in_kernel)) {
+ if (state == sb_bt_start) {
+ state = sb_bt_ignore;
+ atomic_inc(&oprofile_stats.bt_lost_no_mapping);
}
}
* @remark Read the file COPYING
*
* @author John Levon <levon@movementarian.org>
+ * @author Barry Kasindorf <barry.kasindorf@amd.com>
*
* Each CPU has a local buffer that stores PC value/event
* pairs. We also log context switches when we notice them.
return 1;
}
-static int oprofile_begin_trace(struct oprofile_cpu_buffer * cpu_buf)
+static int oprofile_begin_trace(struct oprofile_cpu_buffer *cpu_buf)
{
if (nr_available_slots(cpu_buf) < 4) {
cpu_buf->sample_lost_overflow++;
oprofile_add_ext_sample(pc, regs, event, is_kernel);
}
+#ifdef CONFIG_OPROFILE_IBS
+
+#define MAX_IBS_SAMPLE_SIZE 14
+static int log_ibs_sample(struct oprofile_cpu_buffer *cpu_buf,
+ unsigned long pc, int is_kernel, unsigned int *ibs, int ibs_code)
+{
+ struct task_struct *task;
+
+ cpu_buf->sample_received++;
+
+ if (nr_available_slots(cpu_buf) < MAX_IBS_SAMPLE_SIZE) {
+ cpu_buf->sample_lost_overflow++;
+ return 0;
+ }
+
+ is_kernel = !!is_kernel;
+
+ /* notice a switch from user->kernel or vice versa */
+ if (cpu_buf->last_is_kernel != is_kernel) {
+ cpu_buf->last_is_kernel = is_kernel;
+ add_code(cpu_buf, is_kernel);
+ }
+
+ /* notice a task switch */
+ if (!is_kernel) {
+ task = current;
+
+ if (cpu_buf->last_task != task) {
+ cpu_buf->last_task = task;
+ add_code(cpu_buf, (unsigned long)task);
+ }
+ }
+
+ add_code(cpu_buf, ibs_code);
+ add_sample(cpu_buf, ibs[0], ibs[1]);
+ add_sample(cpu_buf, ibs[2], ibs[3]);
+ add_sample(cpu_buf, ibs[4], ibs[5]);
+
+ if (ibs_code == IBS_OP_BEGIN) {
+ add_sample(cpu_buf, ibs[6], ibs[7]);
+ add_sample(cpu_buf, ibs[8], ibs[9]);
+ add_sample(cpu_buf, ibs[10], ibs[11]);
+ }
+
+ return 1;
+}
+
+void oprofile_add_ibs_sample(struct pt_regs *const regs,
+ unsigned int * const ibs_sample, u8 code)
+{
+ int is_kernel = !user_mode(regs);
+ unsigned long pc = profile_pc(regs);
+
+ struct oprofile_cpu_buffer *cpu_buf =
+ &per_cpu(cpu_buffer, smp_processor_id());
+
+ if (!backtrace_depth) {
+ log_ibs_sample(cpu_buf, pc, is_kernel, ibs_sample, code);
+ return;
+ }
+
+ /* if log_sample() fails we can't backtrace since we lost the source
+ * of this event */
+ if (log_ibs_sample(cpu_buf, pc, is_kernel, ibs_sample, code))
+ oprofile_ops.backtrace(regs, backtrace_depth);
+}
+
+#endif
+
void oprofile_add_pc(unsigned long pc, int is_kernel, unsigned long event)
{
struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(cpu_buffer);
struct oprofile_cpu_buffer * b =
container_of(work, struct oprofile_cpu_buffer, work.work);
if (b->cpu != smp_processor_id()) {
- printk("WQ on CPU%d, prefer CPU%d\n",
+ printk(KERN_DEBUG "WQ on CPU%d, prefer CPU%d\n",
smp_processor_id(), b->cpu);
}
sync_buffer(b->cpu);
/* transient events for the CPU buffer -> event buffer */
#define CPU_IS_KERNEL 1
#define CPU_TRACE_BEGIN 2
+#define IBS_FETCH_BEGIN 3
+#define IBS_OP_BEGIN 4
#endif /* OPROFILE_CPU_BUFFER_H */
#include <linux/init.h>
#include <linux/oprofile.h>
#include <linux/moduleparam.h>
+#include <linux/workqueue.h>
+#include <linux/time.h>
#include <asm/mutex.h>
#include "oprof.h"
#include "cpu_buffer.h"
#include "buffer_sync.h"
#include "oprofile_stats.h"
+
+static unsigned long is_setup;
+static void switch_worker(struct work_struct *work);
+static DECLARE_DELAYED_WORK(switch_work, switch_worker);
+static DEFINE_MUTEX(start_mutex);
struct oprofile_operations oprofile_ops;
+unsigned long timeout_jiffies;
unsigned long oprofile_started;
unsigned long backtrace_depth;
-static unsigned long is_setup;
-static DEFINE_MUTEX(start_mutex);
+/* Multiplexing defaults at 1 msec*/
/* timer
0 - use performance monitoring hardware if available
return err;
}
+static void start_switch_worker(void)
+{
+ schedule_delayed_work(&switch_work, timeout_jiffies);
+}
+
+static void switch_worker(struct work_struct *work)
+{
+ if (!oprofile_ops.switch_events())
+ start_switch_worker();
+}
/* Actually start profiling (echo 1>/dev/oprofile/enable) */
int oprofile_start(void)
int err = -EINVAL;
mutex_lock(&start_mutex);
-
if (!is_setup)
goto out;
if ((err = oprofile_ops.start()))
goto out;
+ if (oprofile_ops.switch_events)
+ start_switch_worker();
+
oprofile_started = 1;
out:
mutex_unlock(&start_mutex);
goto out;
oprofile_ops.stop();
oprofile_started = 0;
+ cancel_delayed_work_sync(&switch_work);
/* wake up the daemon to read what remains */
wake_up_buffer_waiter();
out:
mutex_unlock(&start_mutex);
}
+/* User inputs in ms, converts to jiffies */
+int oprofile_set_timeout(unsigned long val_msec)
+{
+ int err = 0;
+
+ mutex_lock(&start_mutex);
+
+ if (oprofile_started) {
+ err = -EBUSY;
+ goto out;
+ }
+
+ if (!oprofile_ops.switch_events) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ timeout_jiffies = msecs_to_jiffies(val_msec);
+ if (timeout_jiffies == MAX_JIFFY_OFFSET)
+ timeout_jiffies = msecs_to_jiffies(1);
+
+out:
+ mutex_unlock(&start_mutex);
+ return err;
+
+}
int oprofile_set_backtrace(unsigned long val)
{
return err;
}
+static void __init oprofile_switch_timer_init(void)
+{
+ timeout_jiffies = msecs_to_jiffies(1);
+}
+
static int __init oprofile_init(void)
{
int err;
+ oprofile_switch_timer_init();
err = oprofile_arch_init(&oprofile_ops);
if (err < 0 || timer) {
extern struct oprofile_operations oprofile_ops;
extern unsigned long oprofile_started;
extern unsigned long backtrace_depth;
-
+extern unsigned long timeout_jiffies;
+
struct super_block;
struct dentry;
void oprofile_timer_init(struct oprofile_operations * ops);
int oprofile_set_backtrace(unsigned long depth);
+int oprofile_set_timeout(unsigned long time);
#endif /* OPROF_H */
#include <linux/fs.h>
#include <linux/oprofile.h>
+#include <linux/jiffies.h>
#include "event_buffer.h"
#include "oprofile_stats.h"
unsigned long fs_cpu_buffer_size = 8192;
unsigned long fs_buffer_watershed = 32768; /* FIXME: tune */
+static ssize_t timeout_read(struct file *file, char __user *buf,
+ size_t count, loff_t *offset)
+{
+ return oprofilefs_ulong_to_user(jiffies_to_msecs(timeout_jiffies),
+ buf, count, offset);
+}
+
+
+static ssize_t timeout_write(struct file *file, char const __user *buf,
+ size_t count, loff_t *offset)
+{
+ unsigned long val;
+ int retval;
+
+ if (*offset)
+ return -EINVAL;
+
+ retval = oprofilefs_ulong_from_user(&val, buf, count);
+ if (retval)
+ return retval;
+
+ retval = oprofile_set_timeout(val);
+
+ if (retval)
+ return retval;
+ return count;
+}
+
+static const struct file_operations timeout_fops = {
+ .read = timeout_read,
+ .write = timeout_write,
+};
+
+
static ssize_t depth_read(struct file * file, char __user * buf, size_t count, loff_t * offset)
{
return oprofilefs_ulong_to_user(backtrace_depth, buf, count, offset);
if (*offset)
return -EINVAL;
-
retval = oprofilefs_ulong_from_user(&val, buf, count);
if (retval)
return retval;
-
+
if (val)
retval = oprofile_start();
else
oprofilefs_create_file(sb, root, "cpu_type", &cpu_type_fops);
oprofilefs_create_file(sb, root, "backtrace_depth", &depth_fops);
oprofilefs_create_file(sb, root, "pointer_size", &pointer_size_fops);
+ oprofilefs_create_file(sb, root, "timeout_ms", &timeout_fops);
oprofile_create_stats_files(sb, root);
if (oprofile_ops.create_files)
oprofile_ops.create_files(sb, root);
#define XEN_ENTER_SWITCH_CODE 10
#define SPU_PROFILING_CODE 11
#define SPU_CTX_SWITCH_CODE 12
+#define IBS_FETCH_CODE 13
+#define IBS_OP_CODE 14
struct super_block;
struct dentry;
/* Initiate a stack backtrace. Optional. */
void (*backtrace)(struct pt_regs * const regs, unsigned int depth);
+
+ /* Multiplex between different events. Optional. */
+ int (*switch_events)(void);
/* CPU identification string. */
char * cpu_type;
};
#define PCI_DEVICE_ID_AMD_K8_NB_ADDRMAP 0x1101
#define PCI_DEVICE_ID_AMD_K8_NB_MEMCTL 0x1102
#define PCI_DEVICE_ID_AMD_K8_NB_MISC 0x1103
+#define PCI_DEVICE_ID_AMD_10H_NB_HT 0x1200
+#define PCI_DEVICE_ID_AMD_10H_NB_MAP 0x1201
+#define PCI_DEVICE_ID_AMD_10H_NB_DRAM 0x1202
+#define PCI_DEVICE_ID_AMD_10H_NB_MISC 0x1203
+#define PCI_DEVICE_ID_AMD_10H_NB_LINK 0x1204
#define PCI_DEVICE_ID_AMD_LANCE 0x2000
#define PCI_DEVICE_ID_AMD_LANCE_HOME 0x2001
#define PCI_DEVICE_ID_AMD_SCSI 0x2020
git.samba.org / sfrench / cifs-2.6.git / commitdiff