OpenCloudOS-Kernel/arch/powerpc/kernel/smp.c

635 lines
14 KiB
C
Raw Normal View History

/*
* SMP support for ppc.
*
* Written by Cort Dougan (cort@cs.nmt.edu) borrowing a great
* deal of code from the sparc and intel versions.
*
* Copyright (C) 1999 Cort Dougan <cort@cs.nmt.edu>
*
* PowerPC-64 Support added by Dave Engebretsen, Peter Bergner, and
* Mike Corrigan {engebret|bergner|mikec}@us.ibm.com
*
* 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.
*/
#undef DEBUG
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/smp.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/cache.h>
#include <linux/err.h>
#include <linux/sysdev.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <linux/topology.h>
#include <asm/ptrace.h>
#include <asm/atomic.h>
#include <asm/irq.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/prom.h>
#include <asm/smp.h>
#include <asm/time.h>
#include <asm/machdep.h>
#include <asm/cputhreads.h>
#include <asm/cputable.h>
#include <asm/system.h>
#include <asm/mpic.h>
#include <asm/vdso_datapage.h>
#ifdef CONFIG_PPC64
#include <asm/paca.h>
#endif
#ifdef DEBUG
#include <asm/udbg.h>
#define DBG(fmt...) udbg_printf(fmt)
#else
#define DBG(fmt...)
#endif
struct thread_info *secondary_ti;
DEFINE_PER_CPU(cpumask_t, cpu_sibling_map) = CPU_MASK_NONE;
DEFINE_PER_CPU(cpumask_t, cpu_core_map) = CPU_MASK_NONE;
EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
EXPORT_PER_CPU_SYMBOL(cpu_core_map);
/* SMP operations for this machine */
struct smp_ops_t *smp_ops;
/* Can't be static due to PowerMac hackery */
volatile unsigned int cpu_callin_map[NR_CPUS];
int smt_enabled_at_boot = 1;
static void (*crash_ipi_function_ptr)(struct pt_regs *) = NULL;
#ifdef CONFIG_PPC64
void __devinit smp_generic_kick_cpu(int nr)
{
BUG_ON(nr < 0 || nr >= NR_CPUS);
/*
* The processor is currently spinning, waiting for the
* cpu_start field to become non-zero After we set cpu_start,
* the processor will continue on to secondary_start
*/
paca[nr].cpu_start = 1;
smp_mb();
}
#endif
IRQ: Maintain regs pointer globally rather than passing to IRQ handlers Maintain a per-CPU global "struct pt_regs *" variable which can be used instead of passing regs around manually through all ~1800 interrupt handlers in the Linux kernel. The regs pointer is used in few places, but it potentially costs both stack space and code to pass it around. On the FRV arch, removing the regs parameter from all the genirq function results in a 20% speed up of the IRQ exit path (ie: from leaving timer_interrupt() to leaving do_IRQ()). Where appropriate, an arch may override the generic storage facility and do something different with the variable. On FRV, for instance, the address is maintained in GR28 at all times inside the kernel as part of general exception handling. Having looked over the code, it appears that the parameter may be handed down through up to twenty or so layers of functions. Consider a USB character device attached to a USB hub, attached to a USB controller that posts its interrupts through a cascaded auxiliary interrupt controller. A character device driver may want to pass regs to the sysrq handler through the input layer which adds another few layers of parameter passing. I've build this code with allyesconfig for x86_64 and i386. I've runtested the main part of the code on FRV and i386, though I can't test most of the drivers. I've also done partial conversion for powerpc and MIPS - these at least compile with minimal configurations. This will affect all archs. Mostly the changes should be relatively easy. Take do_IRQ(), store the regs pointer at the beginning, saving the old one: struct pt_regs *old_regs = set_irq_regs(regs); And put the old one back at the end: set_irq_regs(old_regs); Don't pass regs through to generic_handle_irq() or __do_IRQ(). In timer_interrupt(), this sort of change will be necessary: - update_process_times(user_mode(regs)); - profile_tick(CPU_PROFILING, regs); + update_process_times(user_mode(get_irq_regs())); + profile_tick(CPU_PROFILING); I'd like to move update_process_times()'s use of get_irq_regs() into itself, except that i386, alone of the archs, uses something other than user_mode(). Some notes on the interrupt handling in the drivers: (*) input_dev() is now gone entirely. The regs pointer is no longer stored in the input_dev struct. (*) finish_unlinks() in drivers/usb/host/ohci-q.c needs checking. It does something different depending on whether it's been supplied with a regs pointer or not. (*) Various IRQ handler function pointers have been moved to type irq_handler_t. Signed-Off-By: David Howells <dhowells@redhat.com> (cherry picked from 1b16e7ac850969f38b375e511e3fa2f474a33867 commit)
2006-10-05 21:55:46 +08:00
void smp_message_recv(int msg)
{
switch(msg) {
case PPC_MSG_CALL_FUNCTION:
generic_smp_call_function_interrupt();
break;
case PPC_MSG_RESCHEDULE:
/* we notice need_resched on exit */
break;
case PPC_MSG_CALL_FUNC_SINGLE:
generic_smp_call_function_single_interrupt();
break;
case PPC_MSG_DEBUGGER_BREAK:
if (crash_ipi_function_ptr) {
IRQ: Maintain regs pointer globally rather than passing to IRQ handlers Maintain a per-CPU global "struct pt_regs *" variable which can be used instead of passing regs around manually through all ~1800 interrupt handlers in the Linux kernel. The regs pointer is used in few places, but it potentially costs both stack space and code to pass it around. On the FRV arch, removing the regs parameter from all the genirq function results in a 20% speed up of the IRQ exit path (ie: from leaving timer_interrupt() to leaving do_IRQ()). Where appropriate, an arch may override the generic storage facility and do something different with the variable. On FRV, for instance, the address is maintained in GR28 at all times inside the kernel as part of general exception handling. Having looked over the code, it appears that the parameter may be handed down through up to twenty or so layers of functions. Consider a USB character device attached to a USB hub, attached to a USB controller that posts its interrupts through a cascaded auxiliary interrupt controller. A character device driver may want to pass regs to the sysrq handler through the input layer which adds another few layers of parameter passing. I've build this code with allyesconfig for x86_64 and i386. I've runtested the main part of the code on FRV and i386, though I can't test most of the drivers. I've also done partial conversion for powerpc and MIPS - these at least compile with minimal configurations. This will affect all archs. Mostly the changes should be relatively easy. Take do_IRQ(), store the regs pointer at the beginning, saving the old one: struct pt_regs *old_regs = set_irq_regs(regs); And put the old one back at the end: set_irq_regs(old_regs); Don't pass regs through to generic_handle_irq() or __do_IRQ(). In timer_interrupt(), this sort of change will be necessary: - update_process_times(user_mode(regs)); - profile_tick(CPU_PROFILING, regs); + update_process_times(user_mode(get_irq_regs())); + profile_tick(CPU_PROFILING); I'd like to move update_process_times()'s use of get_irq_regs() into itself, except that i386, alone of the archs, uses something other than user_mode(). Some notes on the interrupt handling in the drivers: (*) input_dev() is now gone entirely. The regs pointer is no longer stored in the input_dev struct. (*) finish_unlinks() in drivers/usb/host/ohci-q.c needs checking. It does something different depending on whether it's been supplied with a regs pointer or not. (*) Various IRQ handler function pointers have been moved to type irq_handler_t. Signed-Off-By: David Howells <dhowells@redhat.com> (cherry picked from 1b16e7ac850969f38b375e511e3fa2f474a33867 commit)
2006-10-05 21:55:46 +08:00
crash_ipi_function_ptr(get_irq_regs());
break;
}
#ifdef CONFIG_DEBUGGER
IRQ: Maintain regs pointer globally rather than passing to IRQ handlers Maintain a per-CPU global "struct pt_regs *" variable which can be used instead of passing regs around manually through all ~1800 interrupt handlers in the Linux kernel. The regs pointer is used in few places, but it potentially costs both stack space and code to pass it around. On the FRV arch, removing the regs parameter from all the genirq function results in a 20% speed up of the IRQ exit path (ie: from leaving timer_interrupt() to leaving do_IRQ()). Where appropriate, an arch may override the generic storage facility and do something different with the variable. On FRV, for instance, the address is maintained in GR28 at all times inside the kernel as part of general exception handling. Having looked over the code, it appears that the parameter may be handed down through up to twenty or so layers of functions. Consider a USB character device attached to a USB hub, attached to a USB controller that posts its interrupts through a cascaded auxiliary interrupt controller. A character device driver may want to pass regs to the sysrq handler through the input layer which adds another few layers of parameter passing. I've build this code with allyesconfig for x86_64 and i386. I've runtested the main part of the code on FRV and i386, though I can't test most of the drivers. I've also done partial conversion for powerpc and MIPS - these at least compile with minimal configurations. This will affect all archs. Mostly the changes should be relatively easy. Take do_IRQ(), store the regs pointer at the beginning, saving the old one: struct pt_regs *old_regs = set_irq_regs(regs); And put the old one back at the end: set_irq_regs(old_regs); Don't pass regs through to generic_handle_irq() or __do_IRQ(). In timer_interrupt(), this sort of change will be necessary: - update_process_times(user_mode(regs)); - profile_tick(CPU_PROFILING, regs); + update_process_times(user_mode(get_irq_regs())); + profile_tick(CPU_PROFILING); I'd like to move update_process_times()'s use of get_irq_regs() into itself, except that i386, alone of the archs, uses something other than user_mode(). Some notes on the interrupt handling in the drivers: (*) input_dev() is now gone entirely. The regs pointer is no longer stored in the input_dev struct. (*) finish_unlinks() in drivers/usb/host/ohci-q.c needs checking. It does something different depending on whether it's been supplied with a regs pointer or not. (*) Various IRQ handler function pointers have been moved to type irq_handler_t. Signed-Off-By: David Howells <dhowells@redhat.com> (cherry picked from 1b16e7ac850969f38b375e511e3fa2f474a33867 commit)
2006-10-05 21:55:46 +08:00
debugger_ipi(get_irq_regs());
break;
#endif /* CONFIG_DEBUGGER */
/* FALLTHROUGH */
default:
printk("SMP %d: smp_message_recv(): unknown msg %d\n",
smp_processor_id(), msg);
break;
}
}
static irqreturn_t call_function_action(int irq, void *data)
{
generic_smp_call_function_interrupt();
return IRQ_HANDLED;
}
static irqreturn_t reschedule_action(int irq, void *data)
{
/* we just need the return path side effect of checking need_resched */
return IRQ_HANDLED;
}
static irqreturn_t call_function_single_action(int irq, void *data)
{
generic_smp_call_function_single_interrupt();
return IRQ_HANDLED;
}
static irqreturn_t debug_ipi_action(int irq, void *data)
{
smp_message_recv(PPC_MSG_DEBUGGER_BREAK);
return IRQ_HANDLED;
}
static irq_handler_t smp_ipi_action[] = {
[PPC_MSG_CALL_FUNCTION] = call_function_action,
[PPC_MSG_RESCHEDULE] = reschedule_action,
[PPC_MSG_CALL_FUNC_SINGLE] = call_function_single_action,
[PPC_MSG_DEBUGGER_BREAK] = debug_ipi_action,
};
const char *smp_ipi_name[] = {
[PPC_MSG_CALL_FUNCTION] = "ipi call function",
[PPC_MSG_RESCHEDULE] = "ipi reschedule",
[PPC_MSG_CALL_FUNC_SINGLE] = "ipi call function single",
[PPC_MSG_DEBUGGER_BREAK] = "ipi debugger",
};
/* optional function to request ipi, for controllers with >= 4 ipis */
int smp_request_message_ipi(int virq, int msg)
{
int err;
if (msg < 0 || msg > PPC_MSG_DEBUGGER_BREAK) {
return -EINVAL;
}
#if !defined(CONFIG_DEBUGGER) && !defined(CONFIG_KEXEC)
if (msg == PPC_MSG_DEBUGGER_BREAK) {
return 1;
}
#endif
err = request_irq(virq, smp_ipi_action[msg], IRQF_DISABLED|IRQF_PERCPU,
smp_ipi_name[msg], 0);
WARN(err < 0, "unable to request_irq %d for %s (rc %d)\n",
virq, smp_ipi_name[msg], err);
return err;
}
void smp_send_reschedule(int cpu)
{
if (likely(smp_ops))
smp_ops->message_pass(cpu, PPC_MSG_RESCHEDULE);
}
void arch_send_call_function_single_ipi(int cpu)
{
smp_ops->message_pass(cpu, PPC_MSG_CALL_FUNC_SINGLE);
}
void arch_send_call_function_ipi_mask(const struct cpumask *mask)
{
unsigned int cpu;
for_each_cpu(cpu, mask)
smp_ops->message_pass(cpu, PPC_MSG_CALL_FUNCTION);
}
#ifdef CONFIG_DEBUGGER
void smp_send_debugger_break(int cpu)
{
if (likely(smp_ops))
smp_ops->message_pass(cpu, PPC_MSG_DEBUGGER_BREAK);
}
#endif
#ifdef CONFIG_KEXEC
void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *))
{
crash_ipi_function_ptr = crash_ipi_callback;
if (crash_ipi_callback && smp_ops) {
mb();
smp_ops->message_pass(MSG_ALL_BUT_SELF, PPC_MSG_DEBUGGER_BREAK);
}
}
#endif
static void stop_this_cpu(void *dummy)
{
/* Remove this CPU */
set_cpu_online(smp_processor_id(), false);
local_irq_disable();
while (1)
;
}
void smp_send_stop(void)
{
smp_call_function(stop_this_cpu, NULL, 0);
}
struct thread_info *current_set[NR_CPUS];
static void __devinit smp_store_cpu_info(int id)
{
per_cpu(cpu_pvr, id) = mfspr(SPRN_PVR);
}
static void __init smp_create_idle(unsigned int cpu)
{
struct task_struct *p;
/* create a process for the processor */
p = fork_idle(cpu);
if (IS_ERR(p))
panic("failed fork for CPU %u: %li", cpu, PTR_ERR(p));
#ifdef CONFIG_PPC64
paca[cpu].__current = p;
[POWERPC] Bolt in SLB entry for kernel stack on secondary cpus This fixes a regression reported by Kamalesh Bulabel where a POWER4 machine would crash because of an SLB miss at a point where the SLB miss exception was unrecoverable. This regression is tracked at: http://bugzilla.kernel.org/show_bug.cgi?id=10082 SLB misses at such points shouldn't happen because the kernel stack is the only memory accessed other than things in the first segment of the linear mapping (which is mapped at all times by entry 0 of the SLB). The context switch code ensures that SLB entry 2 covers the kernel stack, if it is not already covered by entry 0. None of entries 0 to 2 are ever replaced by the SLB miss handler. Where this went wrong is that the context switch code assumes it doesn't have to write to SLB entry 2 if the new kernel stack is in the same segment as the old kernel stack, since entry 2 should already be correct. However, when we start up a secondary cpu, it calls slb_initialize, which doesn't set up entry 2. This is correct for the boot cpu, where we will be using a stack in the kernel BSS at this point (i.e. init_thread_union), but not necessarily for secondary cpus, whose initial stack can be allocated anywhere. This doesn't cause any immediate problem since the SLB miss handler will just create an SLB entry somewhere else to cover the initial stack. In fact it's possible for the cpu to go quite a long time without SLB entry 2 being valid. Eventually, though, the entry created by the SLB miss handler will get overwritten by some other entry, and if the next access to the stack is at an unrecoverable point, we get the crash. This fixes the problem by making slb_initialize create a suitable entry for the kernel stack, if we are on a secondary cpu and the stack isn't covered by SLB entry 0. This requires initializing the get_paca()->kstack field earlier, so I do that in smp_create_idle where the current field is initialized. This also abstracts a bit of the computation that mk_esid_data in slb.c does so that it can be used in slb_initialize. Signed-off-by: Paul Mackerras <paulus@samba.org>
2008-05-02 12:29:12 +08:00
paca[cpu].kstack = (unsigned long) task_thread_info(p)
+ THREAD_SIZE - STACK_FRAME_OVERHEAD;
#endif
current_set[cpu] = task_thread_info(p);
task_thread_info(p)->cpu = cpu;
}
void __init smp_prepare_cpus(unsigned int max_cpus)
{
unsigned int cpu;
DBG("smp_prepare_cpus\n");
/*
* setup_cpu may need to be called on the boot cpu. We havent
* spun any cpus up but lets be paranoid.
*/
BUG_ON(boot_cpuid != smp_processor_id());
/* Fixup boot cpu */
smp_store_cpu_info(boot_cpuid);
cpu_callin_map[boot_cpuid] = 1;
if (smp_ops)
if (smp_ops->probe)
max_cpus = smp_ops->probe();
else
max_cpus = NR_CPUS;
else
max_cpus = 1;
smp_space_timers(max_cpus);
for_each_possible_cpu(cpu)
if (cpu != boot_cpuid)
smp_create_idle(cpu);
}
void __devinit smp_prepare_boot_cpu(void)
{
BUG_ON(smp_processor_id() != boot_cpuid);
set_cpu_online(boot_cpuid, true);
cpu_set(boot_cpuid, per_cpu(cpu_sibling_map, boot_cpuid));
cpu_set(boot_cpuid, per_cpu(cpu_core_map, boot_cpuid));
#ifdef CONFIG_PPC64
paca[boot_cpuid].__current = current;
#endif
current_set[boot_cpuid] = task_thread_info(current);
}
#ifdef CONFIG_HOTPLUG_CPU
/* State of each CPU during hotplug phases */
DEFINE_PER_CPU(int, cpu_state) = { 0 };
int generic_cpu_disable(void)
{
unsigned int cpu = smp_processor_id();
if (cpu == boot_cpuid)
return -EBUSY;
set_cpu_online(cpu, false);
#ifdef CONFIG_PPC64
vdso_data->processorCount--;
fixup_irqs(cpu_online_map);
#endif
return 0;
}
int generic_cpu_enable(unsigned int cpu)
{
/* Do the normal bootup if we haven't
* already bootstrapped. */
if (system_state != SYSTEM_RUNNING)
return -ENOSYS;
/* get the target out of it's holding state */
per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
smp_wmb();
while (!cpu_online(cpu))
cpu_relax();
#ifdef CONFIG_PPC64
fixup_irqs(cpu_online_map);
/* counter the irq disable in fixup_irqs */
local_irq_enable();
#endif
return 0;
}
void generic_cpu_die(unsigned int cpu)
{
int i;
for (i = 0; i < 100; i++) {
smp_rmb();
if (per_cpu(cpu_state, cpu) == CPU_DEAD)
return;
msleep(100);
}
printk(KERN_ERR "CPU%d didn't die...\n", cpu);
}
void generic_mach_cpu_die(void)
{
unsigned int cpu;
local_irq_disable();
cpu = smp_processor_id();
printk(KERN_DEBUG "CPU%d offline\n", cpu);
__get_cpu_var(cpu_state) = CPU_DEAD;
smp_wmb();
while (__get_cpu_var(cpu_state) != CPU_UP_PREPARE)
cpu_relax();
set_cpu_online(cpu, true);
local_irq_enable();
}
#endif
static int __devinit cpu_enable(unsigned int cpu)
{
if (smp_ops && smp_ops->cpu_enable)
return smp_ops->cpu_enable(cpu);
return -ENOSYS;
}
[PATCH] Change cpu_up and co from __devinit to __cpuinit Compiling the kernel with CONFIG_HOTPLUG = y and CONFIG_HOTPLUG_CPU = n with CONFIG_RELOCATABLE = y generates the following modpost warnings WARNING: vmlinux - Section mismatch: reference to .init.data: from .text between '_cpu_up' (at offset 0xc0141b7d) and 'cpu_up' WARNING: vmlinux - Section mismatch: reference to .init.data: from .text between '_cpu_up' (at offset 0xc0141b9c) and 'cpu_up' WARNING: vmlinux - Section mismatch: reference to .init.text:__cpu_up from .text between '_cpu_up' (at offset 0xc0141bd8) and 'cpu_up' WARNING: vmlinux - Section mismatch: reference to .init.data: from .text between '_cpu_up' (at offset 0xc0141c05) and 'cpu_up' WARNING: vmlinux - Section mismatch: reference to .init.data: from .text between '_cpu_up' (at offset 0xc0141c26) and 'cpu_up' WARNING: vmlinux - Section mismatch: reference to .init.data: from .text between '_cpu_up' (at offset 0xc0141c37) and 'cpu_up' This is because cpu_up, _cpu_up and __cpu_up (in some architectures) are defined as __devinit AND __cpu_up calls some __cpuinit functions. Since __cpuinit would map to __init with this kind of a configuration, we get a .text refering .init.data warning. This patch solves the problem by converting all of __cpu_up, _cpu_up and cpu_up from __devinit to __cpuinit. The approach is justified since the callers of cpu_up are either dependent on CONFIG_HOTPLUG_CPU or are of __init type. Thus when CONFIG_HOTPLUG_CPU=y, all these cpu up functions would land up in .text section, and when CONFIG_HOTPLUG_CPU=n, all these functions would land up in .init section. Tested on a i386 SMP machine running linux-2.6.20-rc3-mm1. Signed-off-by: Gautham R Shenoy <ego@in.ibm.com> Cc: Vivek Goyal <vgoyal@in.ibm.com> Cc: Mikael Starvik <starvik@axis.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: "David S. Miller" <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2007-01-11 15:15:34 +08:00
int __cpuinit __cpu_up(unsigned int cpu)
{
int c;
secondary_ti = current_set[cpu];
if (!cpu_enable(cpu))
return 0;
if (smp_ops == NULL ||
(smp_ops->cpu_bootable && !smp_ops->cpu_bootable(cpu)))
return -EINVAL;
/* Make sure callin-map entry is 0 (can be leftover a CPU
* hotplug
*/
cpu_callin_map[cpu] = 0;
/* The information for processor bringup must
* be written out to main store before we release
* the processor.
*/
smp_mb();
/* wake up cpus */
DBG("smp: kicking cpu %d\n", cpu);
smp_ops->kick_cpu(cpu);
/*
* wait to see if the cpu made a callin (is actually up).
* use this value that I found through experimentation.
* -- Cort
*/
if (system_state < SYSTEM_RUNNING)
for (c = 50000; c && !cpu_callin_map[cpu]; c--)
udelay(100);
#ifdef CONFIG_HOTPLUG_CPU
else
/*
* CPUs can take much longer to come up in the
* hotplug case. Wait five seconds.
*/
for (c = 5000; c && !cpu_callin_map[cpu]; c--)
msleep(1);
#endif
if (!cpu_callin_map[cpu]) {
printk("Processor %u is stuck.\n", cpu);
return -ENOENT;
}
printk("Processor %u found.\n", cpu);
if (smp_ops->give_timebase)
smp_ops->give_timebase();
/* Wait until cpu puts itself in the online map */
while (!cpu_online(cpu))
cpu_relax();
return 0;
}
/* Return the value of the reg property corresponding to the given
* logical cpu.
*/
int cpu_to_core_id(int cpu)
{
struct device_node *np;
const int *reg;
int id = -1;
np = of_get_cpu_node(cpu, NULL);
if (!np)
goto out;
reg = of_get_property(np, "reg", NULL);
if (!reg)
goto out;
id = *reg;
out:
of_node_put(np);
return id;
}
/* Must be called when no change can occur to cpu_present_map,
* i.e. during cpu online or offline.
*/
static struct device_node *cpu_to_l2cache(int cpu)
{
struct device_node *np;
struct device_node *cache;
if (!cpu_present(cpu))
return NULL;
np = of_get_cpu_node(cpu, NULL);
if (np == NULL)
return NULL;
cache = of_find_next_cache_node(np);
of_node_put(np);
return cache;
}
/* Activate a secondary processor. */
int __devinit start_secondary(void *unused)
{
unsigned int cpu = smp_processor_id();
struct device_node *l2_cache;
int i, base;
atomic_inc(&init_mm.mm_count);
current->active_mm = &init_mm;
smp_store_cpu_info(cpu);
set_dec(tb_ticks_per_jiffy);
preempt_disable();
cpu_callin_map[cpu] = 1;
if (smp_ops->setup_cpu)
smp_ops->setup_cpu(cpu);
if (smp_ops->take_timebase)
smp_ops->take_timebase();
if (system_state > SYSTEM_BOOTING)
powerpc: Implement accurate task and CPU time accounting This implements accurate task and cpu time accounting for 64-bit powerpc kernels. Instead of accounting a whole jiffy of time to a task on a timer interrupt because that task happened to be running at the time, we now account time in units of timebase ticks according to the actual time spent by the task in user mode and kernel mode. We also count the time spent processing hardware and software interrupts accurately. This is conditional on CONFIG_VIRT_CPU_ACCOUNTING. If that is not set, we do tick-based approximate accounting as before. To get this accurate information, we read either the PURR (processor utilization of resources register) on POWER5 machines, or the timebase on other machines on * each entry to the kernel from usermode * each exit to usermode * transitions between process context, hard irq context and soft irq context in kernel mode * context switches. On POWER5 systems with shared-processor logical partitioning we also read both the PURR and the timebase at each timer interrupt and context switch in order to determine how much time has been taken by the hypervisor to run other partitions ("steal" time). Unfortunately, since we need values of the PURR on both threads at the same time to accurately calculate the steal time, and since we can only calculate steal time on a per-core basis, the apportioning of the steal time between idle time (time which we ceded to the hypervisor in the idle loop) and actual stolen time is somewhat approximate at the moment. This is all based quite heavily on what s390 does, and it uses the generic interfaces that were added by the s390 developers, i.e. account_system_time(), account_user_time(), etc. This patch doesn't add any new interfaces between the kernel and userspace, and doesn't change the units in which time is reported to userspace by things such as /proc/stat, /proc/<pid>/stat, getrusage(), times(), etc. Internally the various task and cpu times are stored in timebase units, but they are converted to USER_HZ units (1/100th of a second) when reported to userspace. Some precision is therefore lost but there should not be any accumulating error, since the internal accumulation is at full precision. Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-02-24 07:06:59 +08:00
snapshot_timebase();
secondary_cpu_time_init();
ipi_call_lock();
notify_cpu_starting(cpu);
set_cpu_online(cpu, true);
/* Update sibling maps */
base = cpu_first_thread_in_core(cpu);
for (i = 0; i < threads_per_core; i++) {
if (cpu_is_offline(base + i))
continue;
cpu_set(cpu, per_cpu(cpu_sibling_map, base + i));
cpu_set(base + i, per_cpu(cpu_sibling_map, cpu));
/* cpu_core_map should be a superset of
* cpu_sibling_map even if we don't have cache
* information, so update the former here, too.
*/
cpu_set(cpu, per_cpu(cpu_core_map, base +i));
cpu_set(base + i, per_cpu(cpu_core_map, cpu));
}
l2_cache = cpu_to_l2cache(cpu);
for_each_online_cpu(i) {
struct device_node *np = cpu_to_l2cache(i);
if (!np)
continue;
if (np == l2_cache) {
cpu_set(cpu, per_cpu(cpu_core_map, i));
cpu_set(i, per_cpu(cpu_core_map, cpu));
}
of_node_put(np);
}
of_node_put(l2_cache);
ipi_call_unlock();
local_irq_enable();
cpu_idle();
return 0;
}
int setup_profiling_timer(unsigned int multiplier)
{
return 0;
}
void __init smp_cpus_done(unsigned int max_cpus)
{
cpumask_t old_mask;
/* We want the setup_cpu() here to be called from CPU 0, but our
* init thread may have been "borrowed" by another CPU in the meantime
* se we pin us down to CPU 0 for a short while
*/
old_mask = current->cpus_allowed;
set_cpus_allowed_ptr(current, cpumask_of(boot_cpuid));
if (smp_ops && smp_ops->setup_cpu)
smp_ops->setup_cpu(boot_cpuid);
set_cpus_allowed_ptr(current, &old_mask);
powerpc: Implement accurate task and CPU time accounting This implements accurate task and cpu time accounting for 64-bit powerpc kernels. Instead of accounting a whole jiffy of time to a task on a timer interrupt because that task happened to be running at the time, we now account time in units of timebase ticks according to the actual time spent by the task in user mode and kernel mode. We also count the time spent processing hardware and software interrupts accurately. This is conditional on CONFIG_VIRT_CPU_ACCOUNTING. If that is not set, we do tick-based approximate accounting as before. To get this accurate information, we read either the PURR (processor utilization of resources register) on POWER5 machines, or the timebase on other machines on * each entry to the kernel from usermode * each exit to usermode * transitions between process context, hard irq context and soft irq context in kernel mode * context switches. On POWER5 systems with shared-processor logical partitioning we also read both the PURR and the timebase at each timer interrupt and context switch in order to determine how much time has been taken by the hypervisor to run other partitions ("steal" time). Unfortunately, since we need values of the PURR on both threads at the same time to accurately calculate the steal time, and since we can only calculate steal time on a per-core basis, the apportioning of the steal time between idle time (time which we ceded to the hypervisor in the idle loop) and actual stolen time is somewhat approximate at the moment. This is all based quite heavily on what s390 does, and it uses the generic interfaces that were added by the s390 developers, i.e. account_system_time(), account_user_time(), etc. This patch doesn't add any new interfaces between the kernel and userspace, and doesn't change the units in which time is reported to userspace by things such as /proc/stat, /proc/<pid>/stat, getrusage(), times(), etc. Internally the various task and cpu times are stored in timebase units, but they are converted to USER_HZ units (1/100th of a second) when reported to userspace. Some precision is therefore lost but there should not be any accumulating error, since the internal accumulation is at full precision. Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-02-24 07:06:59 +08:00
snapshot_timebases();
dump_numa_cpu_topology();
}
#ifdef CONFIG_HOTPLUG_CPU
int __cpu_disable(void)
{
struct device_node *l2_cache;
int cpu = smp_processor_id();
int base, i;
int err;
if (!smp_ops->cpu_disable)
return -ENOSYS;
err = smp_ops->cpu_disable();
if (err)
return err;
/* Update sibling maps */
base = cpu_first_thread_in_core(cpu);
for (i = 0; i < threads_per_core; i++) {
cpu_clear(cpu, per_cpu(cpu_sibling_map, base + i));
cpu_clear(base + i, per_cpu(cpu_sibling_map, cpu));
cpu_clear(cpu, per_cpu(cpu_core_map, base +i));
cpu_clear(base + i, per_cpu(cpu_core_map, cpu));
}
l2_cache = cpu_to_l2cache(cpu);
for_each_present_cpu(i) {
struct device_node *np = cpu_to_l2cache(i);
if (!np)
continue;
if (np == l2_cache) {
cpu_clear(cpu, per_cpu(cpu_core_map, i));
cpu_clear(i, per_cpu(cpu_core_map, cpu));
}
of_node_put(np);
}
of_node_put(l2_cache);
return 0;
}
void __cpu_die(unsigned int cpu)
{
if (smp_ops->cpu_die)
smp_ops->cpu_die(cpu);
}
static DEFINE_MUTEX(powerpc_cpu_hotplug_driver_mutex);
void cpu_hotplug_driver_lock()
{
mutex_lock(&powerpc_cpu_hotplug_driver_mutex);
}
void cpu_hotplug_driver_unlock()
{
mutex_unlock(&powerpc_cpu_hotplug_driver_mutex);
}
#endif