linux/arch/powerpc/oprofile/common.c

200 lines
4.6 KiB
C
Raw Normal View History

/*
* PPC 64 oprofile support:
* Copyright (C) 2004 Anton Blanchard <anton@au.ibm.com>, IBM
* PPC 32 oprofile support: (based on PPC 64 support)
* Copyright (C) Freescale Semiconductor, Inc 2004
* Author: Andy Fleming
*
* Based on alpha version.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/oprofile.h>
#include <linux/init.h>
#include <linux/smp.h>
#include <linux/errno.h>
#include <asm/ptrace.h>
#include <asm/system.h>
#include <asm/pmc.h>
#include <asm/cputable.h>
#include <asm/oprofile_impl.h>
#include <asm/firmware.h>
static struct op_powerpc_model *model;
static struct op_counter_config ctr[OP_MAX_COUNTER];
static struct op_system_config sys;
static void op_handle_interrupt(struct pt_regs *regs)
{
model->handle_interrupt(regs, ctr);
}
static void op_powerpc_cpu_setup(void *dummy)
{
model->cpu_setup(ctr);
}
static int op_powerpc_setup(void)
{
int err;
/* Grab the hardware */
err = reserve_pmc_hardware(op_handle_interrupt);
if (err)
return err;
/* Pre-compute the values to stuff in the hardware registers. */
model->reg_setup(ctr, &sys, model->num_counters);
/* Configure the registers on all cpus. */
on_each_cpu(op_powerpc_cpu_setup, NULL, 0, 1);
return 0;
}
static void op_powerpc_shutdown(void)
{
release_pmc_hardware();
}
static void op_powerpc_cpu_start(void *dummy)
{
model->start(ctr);
}
static int op_powerpc_start(void)
{
[POWERPC] cell: Add oprofile support Add PPU event-based and cycle-based profiling support to Oprofile for Cell. Oprofile is expected to collect data on all CPUs simultaneously. However, there is one set of performance counters per node. There are two hardware threads or virtual CPUs on each node. Hence, OProfile must multiplex in time the performance counter collection on the two virtual CPUs. The multiplexing of the performance counters is done by a virtual counter routine. Initially, the counters are configured to collect data on the even CPUs in the system, one CPU per node. In order to capture the PC for the virtual CPU when the performance counter interrupt occurs (the specified number of events between samples has occurred), the even processors are configured to handle the performance counter interrupts for their node. The virtual counter routine is called via a kernel timer after the virtual sample time. The routine stops the counters, saves the current counts, loads the last counts for the other virtual CPU on the node, sets interrupts to be handled by the other virtual CPU and restarts the counters, the virtual timer routine is scheduled to run again. The virtual sample time is kept relatively small to make sure sampling occurs on both CPUs on the node with a relatively small granularity. Whenever the counters overflow, the performance counter interrupt is called to collect the PC for the CPU where data is being collected. The oprofile driver relies on a firmware RTAS call to setup the debug bus to route the desired signals to the performance counter hardware to be counted. The RTAS call must set the routing registers appropriately in each of the islands to pass the signals down the debug bus as well as routing the signals from a particular island onto the bus. There is a second firmware RTAS call to reset the debug bus to the non pass thru state when the counters are not in use. Signed-off-by: Carl Love <carll@us.ibm.com> Signed-off-by: Maynard Johnson <mpjohn@us.ibm.com> Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-11-20 17:45:16 +00:00
if (model->global_start)
model->global_start(ctr);
if (model->start)
on_each_cpu(op_powerpc_cpu_start, NULL, 0, 1);
return 0;
}
static inline void op_powerpc_cpu_stop(void *dummy)
{
model->stop();
}
static void op_powerpc_stop(void)
{
[POWERPC] cell: Add oprofile support Add PPU event-based and cycle-based profiling support to Oprofile for Cell. Oprofile is expected to collect data on all CPUs simultaneously. However, there is one set of performance counters per node. There are two hardware threads or virtual CPUs on each node. Hence, OProfile must multiplex in time the performance counter collection on the two virtual CPUs. The multiplexing of the performance counters is done by a virtual counter routine. Initially, the counters are configured to collect data on the even CPUs in the system, one CPU per node. In order to capture the PC for the virtual CPU when the performance counter interrupt occurs (the specified number of events between samples has occurred), the even processors are configured to handle the performance counter interrupts for their node. The virtual counter routine is called via a kernel timer after the virtual sample time. The routine stops the counters, saves the current counts, loads the last counts for the other virtual CPU on the node, sets interrupts to be handled by the other virtual CPU and restarts the counters, the virtual timer routine is scheduled to run again. The virtual sample time is kept relatively small to make sure sampling occurs on both CPUs on the node with a relatively small granularity. Whenever the counters overflow, the performance counter interrupt is called to collect the PC for the CPU where data is being collected. The oprofile driver relies on a firmware RTAS call to setup the debug bus to route the desired signals to the performance counter hardware to be counted. The RTAS call must set the routing registers appropriately in each of the islands to pass the signals down the debug bus as well as routing the signals from a particular island onto the bus. There is a second firmware RTAS call to reset the debug bus to the non pass thru state when the counters are not in use. Signed-off-by: Carl Love <carll@us.ibm.com> Signed-off-by: Maynard Johnson <mpjohn@us.ibm.com> Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-11-20 17:45:16 +00:00
if (model->stop)
on_each_cpu(op_powerpc_cpu_stop, NULL, 0, 1);
if (model->global_stop)
model->global_stop();
}
static int op_powerpc_create_files(struct super_block *sb, struct dentry *root)
{
int i;
#ifdef CONFIG_PPC64
/*
* There is one mmcr0, mmcr1 and mmcra for setting the events for
* all of the counters.
*/
oprofilefs_create_ulong(sb, root, "mmcr0", &sys.mmcr0);
oprofilefs_create_ulong(sb, root, "mmcr1", &sys.mmcr1);
oprofilefs_create_ulong(sb, root, "mmcra", &sys.mmcra);
#endif
for (i = 0; i < model->num_counters; ++i) {
struct dentry *dir;
char buf[4];
snprintf(buf, sizeof buf, "%d", i);
dir = oprofilefs_mkdir(sb, root, buf);
oprofilefs_create_ulong(sb, dir, "enabled", &ctr[i].enabled);
oprofilefs_create_ulong(sb, dir, "event", &ctr[i].event);
oprofilefs_create_ulong(sb, dir, "count", &ctr[i].count);
/*
* Classic PowerPC doesn't support per-counter
* control like this, but the options are
* expected, so they remain. For Freescale
* Book-E style performance monitors, we do
* support them.
*/
oprofilefs_create_ulong(sb, dir, "kernel", &ctr[i].kernel);
oprofilefs_create_ulong(sb, dir, "user", &ctr[i].user);
oprofilefs_create_ulong(sb, dir, "unit_mask", &ctr[i].unit_mask);
}
oprofilefs_create_ulong(sb, root, "enable_kernel", &sys.enable_kernel);
oprofilefs_create_ulong(sb, root, "enable_user", &sys.enable_user);
/* Default to tracing both kernel and user */
sys.enable_kernel = 1;
sys.enable_user = 1;
return 0;
}
int __init oprofile_arch_init(struct oprofile_operations *ops)
{
if (!cur_cpu_spec->oprofile_cpu_type)
return -ENODEV;
if (firmware_has_feature(FW_FEATURE_ISERIES))
return -ENODEV;
switch (cur_cpu_spec->oprofile_type) {
#ifdef CONFIG_PPC64
#ifdef CONFIG_PPC_CELL_NATIVE
[POWERPC] cell: Add oprofile support Add PPU event-based and cycle-based profiling support to Oprofile for Cell. Oprofile is expected to collect data on all CPUs simultaneously. However, there is one set of performance counters per node. There are two hardware threads or virtual CPUs on each node. Hence, OProfile must multiplex in time the performance counter collection on the two virtual CPUs. The multiplexing of the performance counters is done by a virtual counter routine. Initially, the counters are configured to collect data on the even CPUs in the system, one CPU per node. In order to capture the PC for the virtual CPU when the performance counter interrupt occurs (the specified number of events between samples has occurred), the even processors are configured to handle the performance counter interrupts for their node. The virtual counter routine is called via a kernel timer after the virtual sample time. The routine stops the counters, saves the current counts, loads the last counts for the other virtual CPU on the node, sets interrupts to be handled by the other virtual CPU and restarts the counters, the virtual timer routine is scheduled to run again. The virtual sample time is kept relatively small to make sure sampling occurs on both CPUs on the node with a relatively small granularity. Whenever the counters overflow, the performance counter interrupt is called to collect the PC for the CPU where data is being collected. The oprofile driver relies on a firmware RTAS call to setup the debug bus to route the desired signals to the performance counter hardware to be counted. The RTAS call must set the routing registers appropriately in each of the islands to pass the signals down the debug bus as well as routing the signals from a particular island onto the bus. There is a second firmware RTAS call to reset the debug bus to the non pass thru state when the counters are not in use. Signed-off-by: Carl Love <carll@us.ibm.com> Signed-off-by: Maynard Johnson <mpjohn@us.ibm.com> Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-11-20 17:45:16 +00:00
case PPC_OPROFILE_CELL:
if (firmware_has_feature(FW_FEATURE_LPAR))
return -ENODEV;
[POWERPC] cell: Add oprofile support Add PPU event-based and cycle-based profiling support to Oprofile for Cell. Oprofile is expected to collect data on all CPUs simultaneously. However, there is one set of performance counters per node. There are two hardware threads or virtual CPUs on each node. Hence, OProfile must multiplex in time the performance counter collection on the two virtual CPUs. The multiplexing of the performance counters is done by a virtual counter routine. Initially, the counters are configured to collect data on the even CPUs in the system, one CPU per node. In order to capture the PC for the virtual CPU when the performance counter interrupt occurs (the specified number of events between samples has occurred), the even processors are configured to handle the performance counter interrupts for their node. The virtual counter routine is called via a kernel timer after the virtual sample time. The routine stops the counters, saves the current counts, loads the last counts for the other virtual CPU on the node, sets interrupts to be handled by the other virtual CPU and restarts the counters, the virtual timer routine is scheduled to run again. The virtual sample time is kept relatively small to make sure sampling occurs on both CPUs on the node with a relatively small granularity. Whenever the counters overflow, the performance counter interrupt is called to collect the PC for the CPU where data is being collected. The oprofile driver relies on a firmware RTAS call to setup the debug bus to route the desired signals to the performance counter hardware to be counted. The RTAS call must set the routing registers appropriately in each of the islands to pass the signals down the debug bus as well as routing the signals from a particular island onto the bus. There is a second firmware RTAS call to reset the debug bus to the non pass thru state when the counters are not in use. Signed-off-by: Carl Love <carll@us.ibm.com> Signed-off-by: Maynard Johnson <mpjohn@us.ibm.com> Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-11-20 17:45:16 +00:00
model = &op_model_cell;
break;
#endif
case PPC_OPROFILE_RS64:
model = &op_model_rs64;
break;
case PPC_OPROFILE_POWER4:
model = &op_model_power4;
break;
case PPC_OPROFILE_PA6T:
model = &op_model_pa6t;
break;
#endif
#ifdef CONFIG_6xx
case PPC_OPROFILE_G4:
model = &op_model_7450;
break;
#endif
#ifdef CONFIG_FSL_BOOKE
case PPC_OPROFILE_BOOKE:
model = &op_model_fsl_booke;
break;
#endif
default:
return -ENODEV;
}
model->num_counters = cur_cpu_spec->num_pmcs;
ops->cpu_type = cur_cpu_spec->oprofile_cpu_type;
ops->create_files = op_powerpc_create_files;
ops->setup = op_powerpc_setup;
ops->shutdown = op_powerpc_shutdown;
ops->start = op_powerpc_start;
ops->stop = op_powerpc_stop;
ops->backtrace = op_powerpc_backtrace;
printk(KERN_DEBUG "oprofile: using %s performance monitoring.\n",
ops->cpu_type);
return 0;
}
void oprofile_arch_exit(void)
{
}