kernel-ark/arch/x86_64/kernel/smp.c
Andi Kleen a8ab26fe5b [PATCH] x86_64: Switch SMP bootup over to new CPU hotplug state machine
This will allow hotplug CPU in the future and in general cleans up a lot of
crufty code.  It also should plug some races that the old hackish way
introduces.  Remove one old race workaround in NMI watchdog setup that is not
needed anymore.

I removed the old total sum of bogomips reporting code.  The brag value of
BogoMips has been greatly devalued in the last years on the open market.

Real CPU hotplug will need some more work, but the infrastructure for it is
there now.

One drawback: the new TSC sync algorithm is less accurate than before.  The
old way of zeroing TSCs is too intrusive to do later.  Instead the TSC of the
BP is duplicated now, which is less accurate.

akpm:

- sync_tsc_bp_init seems to have the sense of `init' inverted.

- SPIN_LOCK_UNLOCKED is deprecated - use DEFINE_SPINLOCK.

Cc: <rusty@rustcorp.com.au>
Cc: <mingo@elte.hu>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-16 15:25:19 -07:00

441 lines
10 KiB
C

/*
* Intel SMP support routines.
*
* (c) 1995 Alan Cox, Building #3 <alan@redhat.com>
* (c) 1998-99, 2000 Ingo Molnar <mingo@redhat.com>
* (c) 2002,2003 Andi Kleen, SuSE Labs.
*
* This code is released under the GNU General Public License version 2 or
* later.
*/
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/irq.h>
#include <linux/delay.h>
#include <linux/spinlock.h>
#include <linux/smp_lock.h>
#include <linux/smp.h>
#include <linux/kernel_stat.h>
#include <linux/mc146818rtc.h>
#include <linux/interrupt.h>
#include <asm/mtrr.h>
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include <asm/mach_apic.h>
#include <asm/mmu_context.h>
#include <asm/proto.h>
#include <asm/apicdef.h>
/*
* Smarter SMP flushing macros.
* c/o Linus Torvalds.
*
* These mean you can really definitely utterly forget about
* writing to user space from interrupts. (Its not allowed anyway).
*
* Optimizations Manfred Spraul <manfred@colorfullife.com>
*/
static cpumask_t flush_cpumask;
static struct mm_struct * flush_mm;
static unsigned long flush_va;
static DEFINE_SPINLOCK(tlbstate_lock);
#define FLUSH_ALL -1ULL
/*
* We cannot call mmdrop() because we are in interrupt context,
* instead update mm->cpu_vm_mask.
*/
static inline void leave_mm (unsigned long cpu)
{
if (read_pda(mmu_state) == TLBSTATE_OK)
BUG();
clear_bit(cpu, &read_pda(active_mm)->cpu_vm_mask);
load_cr3(swapper_pg_dir);
}
/*
*
* The flush IPI assumes that a thread switch happens in this order:
* [cpu0: the cpu that switches]
* 1) switch_mm() either 1a) or 1b)
* 1a) thread switch to a different mm
* 1a1) clear_bit(cpu, &old_mm->cpu_vm_mask);
* Stop ipi delivery for the old mm. This is not synchronized with
* the other cpus, but smp_invalidate_interrupt ignore flush ipis
* for the wrong mm, and in the worst case we perform a superfluous
* tlb flush.
* 1a2) set cpu mmu_state to TLBSTATE_OK
* Now the smp_invalidate_interrupt won't call leave_mm if cpu0
* was in lazy tlb mode.
* 1a3) update cpu active_mm
* Now cpu0 accepts tlb flushes for the new mm.
* 1a4) set_bit(cpu, &new_mm->cpu_vm_mask);
* Now the other cpus will send tlb flush ipis.
* 1a4) change cr3.
* 1b) thread switch without mm change
* cpu active_mm is correct, cpu0 already handles
* flush ipis.
* 1b1) set cpu mmu_state to TLBSTATE_OK
* 1b2) test_and_set the cpu bit in cpu_vm_mask.
* Atomically set the bit [other cpus will start sending flush ipis],
* and test the bit.
* 1b3) if the bit was 0: leave_mm was called, flush the tlb.
* 2) switch %%esp, ie current
*
* The interrupt must handle 2 special cases:
* - cr3 is changed before %%esp, ie. it cannot use current->{active_,}mm.
* - the cpu performs speculative tlb reads, i.e. even if the cpu only
* runs in kernel space, the cpu could load tlb entries for user space
* pages.
*
* The good news is that cpu mmu_state is local to each cpu, no
* write/read ordering problems.
*/
/*
* TLB flush IPI:
*
* 1) Flush the tlb entries if the cpu uses the mm that's being flushed.
* 2) Leave the mm if we are in the lazy tlb mode.
*/
asmlinkage void smp_invalidate_interrupt (void)
{
unsigned long cpu;
cpu = get_cpu();
if (!cpu_isset(cpu, flush_cpumask))
goto out;
/*
* This was a BUG() but until someone can quote me the
* line from the intel manual that guarantees an IPI to
* multiple CPUs is retried _only_ on the erroring CPUs
* its staying as a return
*
* BUG();
*/
if (flush_mm == read_pda(active_mm)) {
if (read_pda(mmu_state) == TLBSTATE_OK) {
if (flush_va == FLUSH_ALL)
local_flush_tlb();
else
__flush_tlb_one(flush_va);
} else
leave_mm(cpu);
}
ack_APIC_irq();
cpu_clear(cpu, flush_cpumask);
out:
put_cpu_no_resched();
}
static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
unsigned long va)
{
cpumask_t tmp;
/*
* A couple of (to be removed) sanity checks:
*
* - we do not send IPIs to not-yet booted CPUs.
* - current CPU must not be in mask
* - mask must exist :)
*/
BUG_ON(cpus_empty(cpumask));
cpus_and(tmp, cpumask, cpu_online_map);
BUG_ON(!cpus_equal(tmp, cpumask));
BUG_ON(cpu_isset(smp_processor_id(), cpumask));
if (!mm)
BUG();
/*
* I'm not happy about this global shared spinlock in the
* MM hot path, but we'll see how contended it is.
* Temporarily this turns IRQs off, so that lockups are
* detected by the NMI watchdog.
*/
spin_lock(&tlbstate_lock);
flush_mm = mm;
flush_va = va;
cpus_or(flush_cpumask, cpumask, flush_cpumask);
/*
* We have to send the IPI only to
* CPUs affected.
*/
send_IPI_mask(cpumask, INVALIDATE_TLB_VECTOR);
while (!cpus_empty(flush_cpumask))
mb(); /* nothing. lockup detection does not belong here */;
flush_mm = NULL;
flush_va = 0;
spin_unlock(&tlbstate_lock);
}
void flush_tlb_current_task(void)
{
struct mm_struct *mm = current->mm;
cpumask_t cpu_mask;
preempt_disable();
cpu_mask = mm->cpu_vm_mask;
cpu_clear(smp_processor_id(), cpu_mask);
local_flush_tlb();
if (!cpus_empty(cpu_mask))
flush_tlb_others(cpu_mask, mm, FLUSH_ALL);
preempt_enable();
}
void flush_tlb_mm (struct mm_struct * mm)
{
cpumask_t cpu_mask;
preempt_disable();
cpu_mask = mm->cpu_vm_mask;
cpu_clear(smp_processor_id(), cpu_mask);
if (current->active_mm == mm) {
if (current->mm)
local_flush_tlb();
else
leave_mm(smp_processor_id());
}
if (!cpus_empty(cpu_mask))
flush_tlb_others(cpu_mask, mm, FLUSH_ALL);
preempt_enable();
}
void flush_tlb_page(struct vm_area_struct * vma, unsigned long va)
{
struct mm_struct *mm = vma->vm_mm;
cpumask_t cpu_mask;
preempt_disable();
cpu_mask = mm->cpu_vm_mask;
cpu_clear(smp_processor_id(), cpu_mask);
if (current->active_mm == mm) {
if(current->mm)
__flush_tlb_one(va);
else
leave_mm(smp_processor_id());
}
if (!cpus_empty(cpu_mask))
flush_tlb_others(cpu_mask, mm, va);
preempt_enable();
}
static void do_flush_tlb_all(void* info)
{
unsigned long cpu = smp_processor_id();
__flush_tlb_all();
if (read_pda(mmu_state) == TLBSTATE_LAZY)
leave_mm(cpu);
}
void flush_tlb_all(void)
{
on_each_cpu(do_flush_tlb_all, NULL, 1, 1);
}
void smp_kdb_stop(void)
{
send_IPI_allbutself(KDB_VECTOR);
}
/*
* this function sends a 'reschedule' IPI to another CPU.
* it goes straight through and wastes no time serializing
* anything. Worst case is that we lose a reschedule ...
*/
void smp_send_reschedule(int cpu)
{
send_IPI_mask(cpumask_of_cpu(cpu), RESCHEDULE_VECTOR);
}
/*
* Structure and data for smp_call_function(). This is designed to minimise
* static memory requirements. It also looks cleaner.
*/
static DEFINE_SPINLOCK(call_lock);
struct call_data_struct {
void (*func) (void *info);
void *info;
atomic_t started;
atomic_t finished;
int wait;
};
static struct call_data_struct * call_data;
/*
* this function sends a 'generic call function' IPI to all other CPUs
* in the system.
*/
static void __smp_call_function (void (*func) (void *info), void *info,
int nonatomic, int wait)
{
struct call_data_struct data;
int cpus = num_online_cpus()-1;
if (!cpus)
return;
data.func = func;
data.info = info;
atomic_set(&data.started, 0);
data.wait = wait;
if (wait)
atomic_set(&data.finished, 0);
call_data = &data;
wmb();
/* Send a message to all other CPUs and wait for them to respond */
send_IPI_allbutself(CALL_FUNCTION_VECTOR);
/* Wait for response */
while (atomic_read(&data.started) != cpus)
cpu_relax();
if (!wait)
return;
while (atomic_read(&data.finished) != cpus)
cpu_relax();
}
/*
* smp_call_function - run a function on all other CPUs.
* @func: The function to run. This must be fast and non-blocking.
* @info: An arbitrary pointer to pass to the function.
* @nonatomic: currently unused.
* @wait: If true, wait (atomically) until function has completed on other
* CPUs.
*
* Returns 0 on success, else a negative status code. Does not return until
* remote CPUs are nearly ready to execute func or are or have executed.
*
* You must not call this function with disabled interrupts or from a
* hardware interrupt handler or from a bottom half handler.
* Actually there are a few legal cases, like panic.
*/
int smp_call_function (void (*func) (void *info), void *info, int nonatomic,
int wait)
{
spin_lock(&call_lock);
__smp_call_function(func,info,nonatomic,wait);
spin_unlock(&call_lock);
return 0;
}
void smp_stop_cpu(void)
{
/*
* Remove this CPU:
*/
cpu_clear(smp_processor_id(), cpu_online_map);
local_irq_disable();
disable_local_APIC();
local_irq_enable();
}
static void smp_really_stop_cpu(void *dummy)
{
smp_stop_cpu();
for (;;)
asm("hlt");
}
void smp_send_stop(void)
{
int nolock = 0;
if (reboot_force)
return;
/* Don't deadlock on the call lock in panic */
if (!spin_trylock(&call_lock)) {
/* ignore locking because we have paniced anyways */
nolock = 1;
}
__smp_call_function(smp_really_stop_cpu, NULL, 0, 0);
if (!nolock)
spin_unlock(&call_lock);
local_irq_disable();
disable_local_APIC();
local_irq_enable();
}
/*
* Reschedule call back. Nothing to do,
* all the work is done automatically when
* we return from the interrupt.
*/
asmlinkage void smp_reschedule_interrupt(void)
{
ack_APIC_irq();
}
asmlinkage void smp_call_function_interrupt(void)
{
void (*func) (void *info) = call_data->func;
void *info = call_data->info;
int wait = call_data->wait;
ack_APIC_irq();
/*
* Notify initiating CPU that I've grabbed the data and am
* about to execute the function
*/
mb();
atomic_inc(&call_data->started);
/*
* At this point the info structure may be out of scope unless wait==1
*/
irq_enter();
(*func)(info);
irq_exit();
if (wait) {
mb();
atomic_inc(&call_data->finished);
}
}
int safe_smp_processor_id(void)
{
int apicid, i;
if (disable_apic)
return 0;
apicid = hard_smp_processor_id();
if (x86_cpu_to_apicid[apicid] == apicid)
return apicid;
for (i = 0; i < NR_CPUS; ++i) {
if (x86_cpu_to_apicid[i] == apicid)
return i;
}
/* No entries in x86_cpu_to_apicid? Either no MPS|ACPI,
* or called too early. Either way, we must be CPU 0. */
if (x86_cpu_to_apicid[0] == BAD_APICID)
return 0;
return 0; /* Should not happen */
}