2005-04-16 18:20:36 -04:00
|
|
|
/*
|
|
|
|
* linux/arch/i386/kernel/process.c
|
|
|
|
*
|
|
|
|
* Copyright (C) 1995 Linus Torvalds
|
|
|
|
*
|
|
|
|
* Pentium III FXSR, SSE support
|
|
|
|
* Gareth Hughes <gareth@valinux.com>, May 2000
|
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This file handles the architecture-dependent parts of process handling..
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <stdarg.h>
|
|
|
|
|
2005-06-25 17:54:50 -04:00
|
|
|
#include <linux/cpu.h>
|
2005-04-16 18:20:36 -04:00
|
|
|
#include <linux/errno.h>
|
|
|
|
#include <linux/sched.h>
|
|
|
|
#include <linux/fs.h>
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/elfcore.h>
|
|
|
|
#include <linux/smp.h>
|
|
|
|
#include <linux/smp_lock.h>
|
|
|
|
#include <linux/stddef.h>
|
|
|
|
#include <linux/slab.h>
|
|
|
|
#include <linux/vmalloc.h>
|
|
|
|
#include <linux/user.h>
|
|
|
|
#include <linux/a.out.h>
|
|
|
|
#include <linux/interrupt.h>
|
|
|
|
#include <linux/utsname.h>
|
|
|
|
#include <linux/delay.h>
|
|
|
|
#include <linux/reboot.h>
|
|
|
|
#include <linux/init.h>
|
|
|
|
#include <linux/mc146818rtc.h>
|
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/kallsyms.h>
|
|
|
|
#include <linux/ptrace.h>
|
|
|
|
#include <linux/random.h>
|
2006-09-26 04:52:28 -04:00
|
|
|
#include <linux/personality.h>
|
2005-04-16 18:20:36 -04:00
|
|
|
|
|
|
|
#include <asm/uaccess.h>
|
|
|
|
#include <asm/pgtable.h>
|
|
|
|
#include <asm/system.h>
|
|
|
|
#include <asm/io.h>
|
|
|
|
#include <asm/ldt.h>
|
|
|
|
#include <asm/processor.h>
|
|
|
|
#include <asm/i387.h>
|
|
|
|
#include <asm/desc.h>
|
2006-01-08 04:05:26 -05:00
|
|
|
#include <asm/vm86.h>
|
2005-04-16 18:20:36 -04:00
|
|
|
#ifdef CONFIG_MATH_EMULATION
|
|
|
|
#include <asm/math_emu.h>
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#include <linux/err.h>
|
|
|
|
|
2005-06-25 17:54:50 -04:00
|
|
|
#include <asm/tlbflush.h>
|
|
|
|
#include <asm/cpu.h>
|
[PATCH] i386: Use %gs as the PDA base-segment in the kernel
This patch is the meat of the PDA change. This patch makes several related
changes:
1: Most significantly, %gs is now used in the kernel. This means that on
entry, the old value of %gs is saved away, and it is reloaded with
__KERNEL_PDA.
2: entry.S constructs the stack in the shape of struct pt_regs, and this
is passed around the kernel so that the process's saved register
state can be accessed.
Unfortunately struct pt_regs doesn't currently have space for %gs
(or %fs). This patch extends pt_regs to add space for gs (no space
is allocated for %fs, since it won't be used, and it would just
complicate the code in entry.S to work around the space).
3: Because %gs is now saved on the stack like %ds, %es and the integer
registers, there are a number of places where it no longer needs to
be handled specially; namely context switch, and saving/restoring the
register state in a signal context.
4: And since kernel threads run in kernel space and call normal kernel
code, they need to be created with their %gs == __KERNEL_PDA.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Cc: Chuck Ebbert <76306.1226@compuserve.com>
Cc: Zachary Amsden <zach@vmware.com>
Cc: Jan Beulich <jbeulich@novell.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
2006-12-06 20:14:02 -05:00
|
|
|
#include <asm/pda.h>
|
2005-06-25 17:54:50 -04:00
|
|
|
|
2005-04-16 18:20:36 -04:00
|
|
|
asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
|
|
|
|
|
|
|
|
static int hlt_counter;
|
|
|
|
|
|
|
|
unsigned long boot_option_idle_override = 0;
|
|
|
|
EXPORT_SYMBOL(boot_option_idle_override);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Return saved PC of a blocked thread.
|
|
|
|
*/
|
|
|
|
unsigned long thread_saved_pc(struct task_struct *tsk)
|
|
|
|
{
|
|
|
|
return ((unsigned long *)tsk->thread.esp)[3];
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Powermanagement idle function, if any..
|
|
|
|
*/
|
|
|
|
void (*pm_idle)(void);
|
2005-06-23 03:08:33 -04:00
|
|
|
EXPORT_SYMBOL(pm_idle);
|
2005-04-16 18:20:36 -04:00
|
|
|
static DEFINE_PER_CPU(unsigned int, cpu_idle_state);
|
|
|
|
|
|
|
|
void disable_hlt(void)
|
|
|
|
{
|
|
|
|
hlt_counter++;
|
|
|
|
}
|
|
|
|
|
|
|
|
EXPORT_SYMBOL(disable_hlt);
|
|
|
|
|
|
|
|
void enable_hlt(void)
|
|
|
|
{
|
|
|
|
hlt_counter--;
|
|
|
|
}
|
|
|
|
|
|
|
|
EXPORT_SYMBOL(enable_hlt);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We use this if we don't have any better
|
|
|
|
* idle routine..
|
|
|
|
*/
|
|
|
|
void default_idle(void)
|
|
|
|
{
|
|
|
|
if (!hlt_counter && boot_cpu_data.hlt_works_ok) {
|
2006-06-26 07:59:11 -04:00
|
|
|
current_thread_info()->status &= ~TS_POLLING;
|
[PATCH] sched: fix bad missed wakeups in the i386, x86_64, ia64, ACPI and APM idle code
Fernando Lopez-Lezcano reported frequent scheduling latencies and audio
xruns starting at the 2.6.18-rt kernel, and those problems persisted all
until current -rt kernels. The latencies were serious and unjustified by
system load, often in the milliseconds range.
After a patient and heroic multi-month effort of Fernando, where he
tested dozens of kernels, tried various configs, boot options,
test-patches of mine and provided latency traces of those incidents, the
following 'smoking gun' trace was captured by him:
_------=> CPU#
/ _-----=> irqs-off
| / _----=> need-resched
|| / _---=> hardirq/softirq
||| / _--=> preempt-depth
|||| /
||||| delay
cmd pid ||||| time | caller
\ / ||||| \ | /
IRQ_19-1479 1D..1 0us : __trace_start_sched_wakeup (try_to_wake_up)
IRQ_19-1479 1D..1 0us : __trace_start_sched_wakeup <<...>-5856> (37 0)
IRQ_19-1479 1D..1 0us : __trace_start_sched_wakeup (c01262ba 0 0)
IRQ_19-1479 1D..1 0us : resched_task (try_to_wake_up)
IRQ_19-1479 1D..1 0us : __spin_unlock_irqrestore (try_to_wake_up)
...
<idle>-0 1...1 11us!: default_idle (cpu_idle)
...
<idle>-0 0Dn.1 602us : smp_apic_timer_interrupt (c0103baf 1 0)
...
<...>-5856 0D..2 618us : __switch_to (__schedule)
<...>-5856 0D..2 618us : __schedule <<idle>-0> (20 162)
<...>-5856 0D..2 619us : __spin_unlock_irq (__schedule)
<...>-5856 0...1 619us : trace_stop_sched_switched (__schedule)
<...>-5856 0D..1 619us : trace_stop_sched_switched <<...>-5856> (37 0)
what is visible in this trace is that CPU#1 ran try_to_wake_up() for
PID:5856, it placed PID:5856 on CPU#0's runqueue and ran resched_task()
for CPU#0. But it decided to not send an IPI that no CPU - due to
TS_POLLING. But CPU#0 never woke up after its NEED_RESCHED bit was set,
and only rescheduled to PID:5856 upon the next lapic timer IRQ. The
result was a 600+ usecs latency and a missed wakeup!
the bug turned out to be an idle-wakeup bug introduced into the mainline
kernel this summer via an optimization in the x86_64 tree:
commit 495ab9c045e1b0e5c82951b762257fe1c9d81564
Author: Andi Kleen <ak@suse.de>
Date: Mon Jun 26 13:59:11 2006 +0200
[PATCH] i386/x86-64/ia64: Move polling flag into thread_info_status
During some profiling I noticed that default_idle causes a lot of
memory traffic. I think that is caused by the atomic operations
to clear/set the polling flag in thread_info. There is actually
no reason to make this atomic - only the idle thread does it
to itself, other CPUs only read it. So I moved it into ti->status.
the problem is this type of change:
if (!hlt_counter && boot_cpu_data.hlt_works_ok) {
- clear_thread_flag(TIF_POLLING_NRFLAG);
+ current_thread_info()->status &= ~TS_POLLING;
smp_mb__after_clear_bit();
while (!need_resched()) {
local_irq_disable();
this changes clear_thread_flag() to an explicit clearing of TS_POLLING.
clear_thread_flag() is defined as:
clear_bit(flag, &ti->flags);
and clear_bit() is a LOCK-ed atomic instruction on all x86 platforms:
static inline void clear_bit(int nr, volatile unsigned long * addr)
{
__asm__ __volatile__( LOCK_PREFIX
"btrl %1,%0"
hence smp_mb__after_clear_bit() is defined as a simple compile barrier:
#define smp_mb__after_clear_bit() barrier()
but the explicit TS_POLLING clearing introduced by the patch:
+ current_thread_info()->status &= ~TS_POLLING;
is not an atomic op! So the clearing of the TS_POLLING bit is freely
reorderable with the reading of the NEED_RESCHED bit - and both now
reside in different memory addresses.
CPU idle wakeup very much depends on ordered memory ops, the clearing of
the TS_POLLING flag must always be done before we test need_resched()
and hit the idle instruction(s). [Symmetrically, the wakeup code needs
to set NEED_RESCHED before it tests the TS_POLLING flag, so memory
ordering is paramount.]
Fernando's dual-core Athlon64 system has a sufficiently advanced memory
ordering model so that it triggered this scenario very often.
( And it also turned out that the reason why these latencies never
triggered on my testsystems is that i routinely use idle=poll, which
was the only idle variant not affected by this bug. )
The fix is to change the smp_mb__after_clear_bit() to an smp_mb(), to
act as an absolute barrier between the TS_POLLING write and the
NEED_RESCHED read. This affects almost all idling methods (default,
ACPI, APM), on all 3 x86 architectures: i386, x86_64, ia64.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Tested-by: Fernando Lopez-Lezcano <nando@ccrma.Stanford.EDU>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-22 04:11:56 -05:00
|
|
|
/*
|
|
|
|
* TS_POLLING-cleared state must be visible before we
|
|
|
|
* test NEED_RESCHED:
|
|
|
|
*/
|
|
|
|
smp_mb();
|
|
|
|
|
2006-12-06 20:14:03 -05:00
|
|
|
local_irq_disable();
|
|
|
|
if (!need_resched())
|
|
|
|
safe_halt(); /* enables interrupts racelessly */
|
|
|
|
else
|
|
|
|
local_irq_enable();
|
2006-06-26 07:59:11 -04:00
|
|
|
current_thread_info()->status |= TS_POLLING;
|
2005-04-16 18:20:36 -04:00
|
|
|
} else {
|
2006-12-06 20:14:03 -05:00
|
|
|
/* loop is done by the caller */
|
|
|
|
cpu_relax();
|
2005-04-16 18:20:36 -04:00
|
|
|
}
|
|
|
|
}
|
2005-06-23 03:08:33 -04:00
|
|
|
#ifdef CONFIG_APM_MODULE
|
|
|
|
EXPORT_SYMBOL(default_idle);
|
|
|
|
#endif
|
2005-04-16 18:20:36 -04:00
|
|
|
|
|
|
|
/*
|
|
|
|
* On SMP it's slightly faster (but much more power-consuming!)
|
|
|
|
* to poll the ->work.need_resched flag instead of waiting for the
|
|
|
|
* cross-CPU IPI to arrive. Use this option with caution.
|
|
|
|
*/
|
|
|
|
static void poll_idle (void)
|
|
|
|
{
|
2006-12-06 20:14:03 -05:00
|
|
|
cpu_relax();
|
2005-04-16 18:20:36 -04:00
|
|
|
}
|
|
|
|
|
2005-06-25 17:54:50 -04:00
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
|
|
#include <asm/nmi.h>
|
|
|
|
/* We don't actually take CPU down, just spin without interrupts. */
|
|
|
|
static inline void play_dead(void)
|
|
|
|
{
|
2005-06-25 17:54:56 -04:00
|
|
|
/* This must be done before dead CPU ack */
|
|
|
|
cpu_exit_clear();
|
|
|
|
wbinvd();
|
|
|
|
mb();
|
2005-06-25 17:54:50 -04:00
|
|
|
/* Ack it */
|
|
|
|
__get_cpu_var(cpu_state) = CPU_DEAD;
|
|
|
|
|
2005-06-25 17:54:56 -04:00
|
|
|
/*
|
|
|
|
* With physical CPU hotplug, we should halt the cpu
|
|
|
|
*/
|
2005-06-25 17:54:50 -04:00
|
|
|
local_irq_disable();
|
2005-06-25 17:54:56 -04:00
|
|
|
while (1)
|
2005-09-03 18:56:42 -04:00
|
|
|
halt();
|
2005-06-25 17:54:50 -04:00
|
|
|
}
|
|
|
|
#else
|
|
|
|
static inline void play_dead(void)
|
|
|
|
{
|
|
|
|
BUG();
|
|
|
|
}
|
|
|
|
#endif /* CONFIG_HOTPLUG_CPU */
|
|
|
|
|
2005-04-16 18:20:36 -04:00
|
|
|
/*
|
|
|
|
* The idle thread. There's no useful work to be
|
|
|
|
* done, so just try to conserve power and have a
|
|
|
|
* low exit latency (ie sit in a loop waiting for
|
|
|
|
* somebody to say that they'd like to reschedule)
|
|
|
|
*/
|
2005-06-25 17:54:50 -04:00
|
|
|
void cpu_idle(void)
|
2005-04-16 18:20:36 -04:00
|
|
|
{
|
2005-11-09 00:39:01 -05:00
|
|
|
int cpu = smp_processor_id();
|
2005-06-25 17:54:50 -04:00
|
|
|
|
2006-06-26 07:59:11 -04:00
|
|
|
current_thread_info()->status |= TS_POLLING;
|
[PATCH] sched: resched and cpu_idle rework
Make some changes to the NEED_RESCHED and POLLING_NRFLAG to reduce
confusion, and make their semantics rigid. Improves efficiency of
resched_task and some cpu_idle routines.
* In resched_task:
- TIF_NEED_RESCHED is only cleared with the task's runqueue lock held,
and as we hold it during resched_task, then there is no need for an
atomic test and set there. The only other time this should be set is
when the task's quantum expires, in the timer interrupt - this is
protected against because the rq lock is irq-safe.
- If TIF_NEED_RESCHED is set, then we don't need to do anything. It
won't get unset until the task get's schedule()d off.
- If we are running on the same CPU as the task we resched, then set
TIF_NEED_RESCHED and no further action is required.
- If we are running on another CPU, and TIF_POLLING_NRFLAG is *not* set
after TIF_NEED_RESCHED has been set, then we need to send an IPI.
Using these rules, we are able to remove the test and set operation in
resched_task, and make clear the previously vague semantics of
POLLING_NRFLAG.
* In idle routines:
- Enter cpu_idle with preempt disabled. When the need_resched() condition
becomes true, explicitly call schedule(). This makes things a bit clearer
(IMO), but haven't updated all architectures yet.
- Many do a test and clear of TIF_NEED_RESCHED for some reason. According
to the resched_task rules, this isn't needed (and actually breaks the
assumption that TIF_NEED_RESCHED is only cleared with the runqueue lock
held). So remove that. Generally one less locked memory op when switching
to the idle thread.
- Many idle routines clear TIF_POLLING_NRFLAG, and only set it in the inner
most polling idle loops. The above resched_task semantics allow it to be
set until before the last time need_resched() is checked before going into
a halt requiring interrupt wakeup.
Many idle routines simply never enter such a halt, and so POLLING_NRFLAG
can be always left set, completely eliminating resched IPIs when rescheduling
the idle task.
POLLING_NRFLAG width can be increased, to reduce the chance of resched IPIs.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Con Kolivas <kernel@kolivas.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-11-09 00:39:04 -05:00
|
|
|
|
2005-04-16 18:20:36 -04:00
|
|
|
/* endless idle loop with no priority at all */
|
|
|
|
while (1) {
|
|
|
|
while (!need_resched()) {
|
|
|
|
void (*idle)(void);
|
|
|
|
|
|
|
|
if (__get_cpu_var(cpu_idle_state))
|
|
|
|
__get_cpu_var(cpu_idle_state) = 0;
|
|
|
|
|
|
|
|
rmb();
|
|
|
|
idle = pm_idle;
|
|
|
|
|
|
|
|
if (!idle)
|
|
|
|
idle = default_idle;
|
|
|
|
|
2005-06-25 17:54:50 -04:00
|
|
|
if (cpu_is_offline(cpu))
|
|
|
|
play_dead();
|
|
|
|
|
2005-04-16 18:20:36 -04:00
|
|
|
__get_cpu_var(irq_stat).idle_timestamp = jiffies;
|
|
|
|
idle();
|
|
|
|
}
|
2005-11-09 00:39:01 -05:00
|
|
|
preempt_enable_no_resched();
|
2005-04-16 18:20:36 -04:00
|
|
|
schedule();
|
2005-11-09 00:39:01 -05:00
|
|
|
preempt_disable();
|
2005-04-16 18:20:36 -04:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
void cpu_idle_wait(void)
|
|
|
|
{
|
|
|
|
unsigned int cpu, this_cpu = get_cpu();
|
2006-11-17 08:26:18 -05:00
|
|
|
cpumask_t map, tmp = current->cpus_allowed;
|
2005-04-16 18:20:36 -04:00
|
|
|
|
|
|
|
set_cpus_allowed(current, cpumask_of_cpu(this_cpu));
|
|
|
|
put_cpu();
|
|
|
|
|
|
|
|
cpus_clear(map);
|
|
|
|
for_each_online_cpu(cpu) {
|
|
|
|
per_cpu(cpu_idle_state, cpu) = 1;
|
|
|
|
cpu_set(cpu, map);
|
|
|
|
}
|
|
|
|
|
|
|
|
__get_cpu_var(cpu_idle_state) = 0;
|
|
|
|
|
|
|
|
wmb();
|
|
|
|
do {
|
|
|
|
ssleep(1);
|
|
|
|
for_each_online_cpu(cpu) {
|
|
|
|
if (cpu_isset(cpu, map) && !per_cpu(cpu_idle_state, cpu))
|
|
|
|
cpu_clear(cpu, map);
|
|
|
|
}
|
|
|
|
cpus_and(map, map, cpu_online_map);
|
|
|
|
} while (!cpus_empty(map));
|
2006-11-17 08:26:18 -05:00
|
|
|
|
|
|
|
set_cpus_allowed(current, tmp);
|
2005-04-16 18:20:36 -04:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(cpu_idle_wait);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This uses new MONITOR/MWAIT instructions on P4 processors with PNI,
|
|
|
|
* which can obviate IPI to trigger checking of need_resched.
|
|
|
|
* We execute MONITOR against need_resched and enter optimized wait state
|
|
|
|
* through MWAIT. Whenever someone changes need_resched, we would be woken
|
|
|
|
* up from MWAIT (without an IPI).
|
2006-09-25 19:28:13 -04:00
|
|
|
*
|
|
|
|
* New with Core Duo processors, MWAIT can take some hints based on CPU
|
|
|
|
* capability.
|
2005-04-16 18:20:36 -04:00
|
|
|
*/
|
2006-09-25 19:28:13 -04:00
|
|
|
void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
|
2005-04-16 18:20:36 -04:00
|
|
|
{
|
2006-09-25 19:28:13 -04:00
|
|
|
if (!need_resched()) {
|
[PATCH] sched: resched and cpu_idle rework
Make some changes to the NEED_RESCHED and POLLING_NRFLAG to reduce
confusion, and make their semantics rigid. Improves efficiency of
resched_task and some cpu_idle routines.
* In resched_task:
- TIF_NEED_RESCHED is only cleared with the task's runqueue lock held,
and as we hold it during resched_task, then there is no need for an
atomic test and set there. The only other time this should be set is
when the task's quantum expires, in the timer interrupt - this is
protected against because the rq lock is irq-safe.
- If TIF_NEED_RESCHED is set, then we don't need to do anything. It
won't get unset until the task get's schedule()d off.
- If we are running on the same CPU as the task we resched, then set
TIF_NEED_RESCHED and no further action is required.
- If we are running on another CPU, and TIF_POLLING_NRFLAG is *not* set
after TIF_NEED_RESCHED has been set, then we need to send an IPI.
Using these rules, we are able to remove the test and set operation in
resched_task, and make clear the previously vague semantics of
POLLING_NRFLAG.
* In idle routines:
- Enter cpu_idle with preempt disabled. When the need_resched() condition
becomes true, explicitly call schedule(). This makes things a bit clearer
(IMO), but haven't updated all architectures yet.
- Many do a test and clear of TIF_NEED_RESCHED for some reason. According
to the resched_task rules, this isn't needed (and actually breaks the
assumption that TIF_NEED_RESCHED is only cleared with the runqueue lock
held). So remove that. Generally one less locked memory op when switching
to the idle thread.
- Many idle routines clear TIF_POLLING_NRFLAG, and only set it in the inner
most polling idle loops. The above resched_task semantics allow it to be
set until before the last time need_resched() is checked before going into
a halt requiring interrupt wakeup.
Many idle routines simply never enter such a halt, and so POLLING_NRFLAG
can be always left set, completely eliminating resched IPIs when rescheduling
the idle task.
POLLING_NRFLAG width can be increased, to reduce the chance of resched IPIs.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Con Kolivas <kernel@kolivas.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-11-09 00:39:04 -05:00
|
|
|
__monitor((void *)¤t_thread_info()->flags, 0, 0);
|
|
|
|
smp_mb();
|
2006-09-25 19:28:13 -04:00
|
|
|
if (!need_resched())
|
|
|
|
__mwait(eax, ecx);
|
2005-04-16 18:20:36 -04:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2006-09-25 19:28:13 -04:00
|
|
|
/* Default MONITOR/MWAIT with no hints, used for default C1 state */
|
|
|
|
static void mwait_idle(void)
|
|
|
|
{
|
|
|
|
local_irq_enable();
|
2006-12-06 20:14:03 -05:00
|
|
|
mwait_idle_with_hints(0, 0);
|
2006-09-25 19:28:13 -04:00
|
|
|
}
|
|
|
|
|
2005-06-25 17:54:55 -04:00
|
|
|
void __devinit select_idle_routine(const struct cpuinfo_x86 *c)
|
2005-04-16 18:20:36 -04:00
|
|
|
{
|
|
|
|
if (cpu_has(c, X86_FEATURE_MWAIT)) {
|
|
|
|
printk("monitor/mwait feature present.\n");
|
|
|
|
/*
|
|
|
|
* Skip, if setup has overridden idle.
|
|
|
|
* One CPU supports mwait => All CPUs supports mwait
|
|
|
|
*/
|
|
|
|
if (!pm_idle) {
|
|
|
|
printk("using mwait in idle threads.\n");
|
|
|
|
pm_idle = mwait_idle;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static int __init idle_setup (char *str)
|
|
|
|
{
|
|
|
|
if (!strncmp(str, "poll", 4)) {
|
|
|
|
printk("using polling idle threads.\n");
|
|
|
|
pm_idle = poll_idle;
|
|
|
|
#ifdef CONFIG_X86_SMP
|
|
|
|
if (smp_num_siblings > 1)
|
|
|
|
printk("WARNING: polling idle and HT enabled, performance may degrade.\n");
|
|
|
|
#endif
|
|
|
|
} else if (!strncmp(str, "halt", 4)) {
|
|
|
|
printk("using halt in idle threads.\n");
|
|
|
|
pm_idle = default_idle;
|
|
|
|
}
|
|
|
|
|
|
|
|
boot_option_idle_override = 1;
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
__setup("idle=", idle_setup);
|
|
|
|
|
|
|
|
void show_regs(struct pt_regs * regs)
|
|
|
|
{
|
|
|
|
unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L;
|
|
|
|
|
|
|
|
printk("\n");
|
|
|
|
printk("Pid: %d, comm: %20s\n", current->pid, current->comm);
|
|
|
|
printk("EIP: %04x:[<%08lx>] CPU: %d\n",0xffff & regs->xcs,regs->eip, smp_processor_id());
|
|
|
|
print_symbol("EIP is at %s\n", regs->eip);
|
|
|
|
|
2006-03-23 05:59:46 -05:00
|
|
|
if (user_mode_vm(regs))
|
2005-04-16 18:20:36 -04:00
|
|
|
printk(" ESP: %04x:%08lx",0xffff & regs->xss,regs->esp);
|
2006-02-05 02:28:04 -05:00
|
|
|
printk(" EFLAGS: %08lx %s (%s %.*s)\n",
|
2006-10-02 05:18:13 -04:00
|
|
|
regs->eflags, print_tainted(), init_utsname()->release,
|
|
|
|
(int)strcspn(init_utsname()->version, " "),
|
|
|
|
init_utsname()->version);
|
2005-04-16 18:20:36 -04:00
|
|
|
printk("EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
|
|
|
|
regs->eax,regs->ebx,regs->ecx,regs->edx);
|
|
|
|
printk("ESI: %08lx EDI: %08lx EBP: %08lx",
|
|
|
|
regs->esi, regs->edi, regs->ebp);
|
2007-02-13 07:26:20 -05:00
|
|
|
printk(" DS: %04x ES: %04x FS: %04x\n",
|
|
|
|
0xffff & regs->xds,0xffff & regs->xes, 0xffff & regs->xfs);
|
2005-04-16 18:20:36 -04:00
|
|
|
|
2005-09-03 18:56:36 -04:00
|
|
|
cr0 = read_cr0();
|
|
|
|
cr2 = read_cr2();
|
|
|
|
cr3 = read_cr3();
|
2006-01-06 03:11:50 -05:00
|
|
|
cr4 = read_cr4_safe();
|
2005-04-16 18:20:36 -04:00
|
|
|
printk("CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n", cr0, cr2, cr3, cr4);
|
2006-06-26 07:57:41 -04:00
|
|
|
show_trace(NULL, regs, ®s->esp);
|
2005-04-16 18:20:36 -04:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This gets run with %ebx containing the
|
|
|
|
* function to call, and %edx containing
|
|
|
|
* the "args".
|
|
|
|
*/
|
|
|
|
extern void kernel_thread_helper(void);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Create a kernel thread
|
|
|
|
*/
|
|
|
|
int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
|
|
|
|
{
|
|
|
|
struct pt_regs regs;
|
|
|
|
|
|
|
|
memset(®s, 0, sizeof(regs));
|
|
|
|
|
|
|
|
regs.ebx = (unsigned long) fn;
|
|
|
|
regs.edx = (unsigned long) arg;
|
|
|
|
|
|
|
|
regs.xds = __USER_DS;
|
|
|
|
regs.xes = __USER_DS;
|
2007-02-13 07:26:20 -05:00
|
|
|
regs.xfs = __KERNEL_PDA;
|
2005-04-16 18:20:36 -04:00
|
|
|
regs.orig_eax = -1;
|
|
|
|
regs.eip = (unsigned long) kernel_thread_helper;
|
2006-09-26 04:52:39 -04:00
|
|
|
regs.xcs = __KERNEL_CS | get_kernel_rpl();
|
2005-04-16 18:20:36 -04:00
|
|
|
regs.eflags = X86_EFLAGS_IF | X86_EFLAGS_SF | X86_EFLAGS_PF | 0x2;
|
|
|
|
|
|
|
|
/* Ok, create the new process.. */
|
2006-10-21 12:37:02 -04:00
|
|
|
return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, ®s, 0, NULL, NULL);
|
2005-04-16 18:20:36 -04:00
|
|
|
}
|
2005-06-23 03:08:33 -04:00
|
|
|
EXPORT_SYMBOL(kernel_thread);
|
2005-04-16 18:20:36 -04:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Free current thread data structures etc..
|
|
|
|
*/
|
|
|
|
void exit_thread(void)
|
|
|
|
{
|
|
|
|
/* The process may have allocated an io port bitmap... nuke it. */
|
2006-07-09 21:12:39 -04:00
|
|
|
if (unlikely(test_thread_flag(TIF_IO_BITMAP))) {
|
|
|
|
struct task_struct *tsk = current;
|
|
|
|
struct thread_struct *t = &tsk->thread;
|
2005-04-16 18:20:36 -04:00
|
|
|
int cpu = get_cpu();
|
|
|
|
struct tss_struct *tss = &per_cpu(init_tss, cpu);
|
|
|
|
|
|
|
|
kfree(t->io_bitmap_ptr);
|
|
|
|
t->io_bitmap_ptr = NULL;
|
2006-07-09 21:12:39 -04:00
|
|
|
clear_thread_flag(TIF_IO_BITMAP);
|
2005-04-16 18:20:36 -04:00
|
|
|
/*
|
|
|
|
* Careful, clear this in the TSS too:
|
|
|
|
*/
|
|
|
|
memset(tss->io_bitmap, 0xff, tss->io_bitmap_max);
|
|
|
|
t->io_bitmap_max = 0;
|
|
|
|
tss->io_bitmap_owner = NULL;
|
|
|
|
tss->io_bitmap_max = 0;
|
|
|
|
tss->io_bitmap_base = INVALID_IO_BITMAP_OFFSET;
|
|
|
|
put_cpu();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
void flush_thread(void)
|
|
|
|
{
|
|
|
|
struct task_struct *tsk = current;
|
|
|
|
|
|
|
|
memset(tsk->thread.debugreg, 0, sizeof(unsigned long)*8);
|
|
|
|
memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
|
2006-07-09 21:12:39 -04:00
|
|
|
clear_tsk_thread_flag(tsk, TIF_DEBUG);
|
2005-04-16 18:20:36 -04:00
|
|
|
/*
|
|
|
|
* Forget coprocessor state..
|
|
|
|
*/
|
|
|
|
clear_fpu(tsk);
|
|
|
|
clear_used_math();
|
|
|
|
}
|
|
|
|
|
|
|
|
void release_thread(struct task_struct *dead_task)
|
|
|
|
{
|
2006-01-06 03:11:59 -05:00
|
|
|
BUG_ON(dead_task->mm);
|
2005-04-16 18:20:36 -04:00
|
|
|
release_vm86_irqs(dead_task);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This gets called before we allocate a new thread and copy
|
|
|
|
* the current task into it.
|
|
|
|
*/
|
|
|
|
void prepare_to_copy(struct task_struct *tsk)
|
|
|
|
{
|
|
|
|
unlazy_fpu(tsk);
|
|
|
|
}
|
|
|
|
|
|
|
|
int copy_thread(int nr, unsigned long clone_flags, unsigned long esp,
|
|
|
|
unsigned long unused,
|
|
|
|
struct task_struct * p, struct pt_regs * regs)
|
|
|
|
{
|
|
|
|
struct pt_regs * childregs;
|
|
|
|
struct task_struct *tsk;
|
|
|
|
int err;
|
|
|
|
|
2006-01-12 04:05:41 -05:00
|
|
|
childregs = task_pt_regs(p);
|
2005-05-05 19:15:03 -04:00
|
|
|
*childregs = *regs;
|
|
|
|
childregs->eax = 0;
|
|
|
|
childregs->esp = esp;
|
|
|
|
|
|
|
|
p->thread.esp = (unsigned long) childregs;
|
|
|
|
p->thread.esp0 = (unsigned long) (childregs+1);
|
2005-04-16 18:20:36 -04:00
|
|
|
|
|
|
|
p->thread.eip = (unsigned long) ret_from_fork;
|
|
|
|
|
2007-02-13 07:26:20 -05:00
|
|
|
savesegment(gs,p->thread.gs);
|
2005-04-16 18:20:36 -04:00
|
|
|
|
|
|
|
tsk = current;
|
2006-07-09 21:12:39 -04:00
|
|
|
if (unlikely(test_tsk_thread_flag(tsk, TIF_IO_BITMAP))) {
|
2006-10-01 02:27:21 -04:00
|
|
|
p->thread.io_bitmap_ptr = kmemdup(tsk->thread.io_bitmap_ptr,
|
|
|
|
IO_BITMAP_BYTES, GFP_KERNEL);
|
2005-04-16 18:20:36 -04:00
|
|
|
if (!p->thread.io_bitmap_ptr) {
|
|
|
|
p->thread.io_bitmap_max = 0;
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
2006-07-09 21:12:39 -04:00
|
|
|
set_tsk_thread_flag(p, TIF_IO_BITMAP);
|
2005-04-16 18:20:36 -04:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Set a new TLS for the child thread?
|
|
|
|
*/
|
|
|
|
if (clone_flags & CLONE_SETTLS) {
|
|
|
|
struct desc_struct *desc;
|
|
|
|
struct user_desc info;
|
|
|
|
int idx;
|
|
|
|
|
|
|
|
err = -EFAULT;
|
|
|
|
if (copy_from_user(&info, (void __user *)childregs->esi, sizeof(info)))
|
|
|
|
goto out;
|
|
|
|
err = -EINVAL;
|
|
|
|
if (LDT_empty(&info))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
idx = info.entry_number;
|
|
|
|
if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
desc = p->thread.tls_array + idx - GDT_ENTRY_TLS_MIN;
|
|
|
|
desc->a = LDT_entry_a(&info);
|
|
|
|
desc->b = LDT_entry_b(&info);
|
|
|
|
}
|
|
|
|
|
|
|
|
err = 0;
|
|
|
|
out:
|
|
|
|
if (err && p->thread.io_bitmap_ptr) {
|
|
|
|
kfree(p->thread.io_bitmap_ptr);
|
|
|
|
p->thread.io_bitmap_max = 0;
|
|
|
|
}
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* fill in the user structure for a core dump..
|
|
|
|
*/
|
|
|
|
void dump_thread(struct pt_regs * regs, struct user * dump)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
/* changed the size calculations - should hopefully work better. lbt */
|
|
|
|
dump->magic = CMAGIC;
|
|
|
|
dump->start_code = 0;
|
|
|
|
dump->start_stack = regs->esp & ~(PAGE_SIZE - 1);
|
|
|
|
dump->u_tsize = ((unsigned long) current->mm->end_code) >> PAGE_SHIFT;
|
|
|
|
dump->u_dsize = ((unsigned long) (current->mm->brk + (PAGE_SIZE-1))) >> PAGE_SHIFT;
|
|
|
|
dump->u_dsize -= dump->u_tsize;
|
|
|
|
dump->u_ssize = 0;
|
|
|
|
for (i = 0; i < 8; i++)
|
|
|
|
dump->u_debugreg[i] = current->thread.debugreg[i];
|
|
|
|
|
|
|
|
if (dump->start_stack < TASK_SIZE)
|
|
|
|
dump->u_ssize = ((unsigned long) (TASK_SIZE - dump->start_stack)) >> PAGE_SHIFT;
|
|
|
|
|
|
|
|
dump->regs.ebx = regs->ebx;
|
|
|
|
dump->regs.ecx = regs->ecx;
|
|
|
|
dump->regs.edx = regs->edx;
|
|
|
|
dump->regs.esi = regs->esi;
|
|
|
|
dump->regs.edi = regs->edi;
|
|
|
|
dump->regs.ebp = regs->ebp;
|
|
|
|
dump->regs.eax = regs->eax;
|
|
|
|
dump->regs.ds = regs->xds;
|
|
|
|
dump->regs.es = regs->xes;
|
2007-02-13 07:26:20 -05:00
|
|
|
dump->regs.fs = regs->xfs;
|
|
|
|
savesegment(gs,dump->regs.gs);
|
2005-04-16 18:20:36 -04:00
|
|
|
dump->regs.orig_eax = regs->orig_eax;
|
|
|
|
dump->regs.eip = regs->eip;
|
|
|
|
dump->regs.cs = regs->xcs;
|
|
|
|
dump->regs.eflags = regs->eflags;
|
|
|
|
dump->regs.esp = regs->esp;
|
|
|
|
dump->regs.ss = regs->xss;
|
|
|
|
|
|
|
|
dump->u_fpvalid = dump_fpu (regs, &dump->i387);
|
|
|
|
}
|
2005-06-23 03:08:33 -04:00
|
|
|
EXPORT_SYMBOL(dump_thread);
|
2005-04-16 18:20:36 -04:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Capture the user space registers if the task is not running (in user space)
|
|
|
|
*/
|
|
|
|
int dump_task_regs(struct task_struct *tsk, elf_gregset_t *regs)
|
|
|
|
{
|
2006-01-12 04:05:41 -05:00
|
|
|
struct pt_regs ptregs = *task_pt_regs(tsk);
|
2005-04-16 18:20:36 -04:00
|
|
|
ptregs.xcs &= 0xffff;
|
|
|
|
ptregs.xds &= 0xffff;
|
|
|
|
ptregs.xes &= 0xffff;
|
|
|
|
ptregs.xss &= 0xffff;
|
|
|
|
|
|
|
|
elf_core_copy_regs(regs, &ptregs);
|
|
|
|
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
2006-07-09 21:12:39 -04:00
|
|
|
static noinline void __switch_to_xtra(struct task_struct *next_p,
|
|
|
|
struct tss_struct *tss)
|
2005-04-16 18:20:36 -04:00
|
|
|
{
|
2006-07-09 21:12:39 -04:00
|
|
|
struct thread_struct *next;
|
|
|
|
|
|
|
|
next = &next_p->thread;
|
|
|
|
|
|
|
|
if (test_tsk_thread_flag(next_p, TIF_DEBUG)) {
|
|
|
|
set_debugreg(next->debugreg[0], 0);
|
|
|
|
set_debugreg(next->debugreg[1], 1);
|
|
|
|
set_debugreg(next->debugreg[2], 2);
|
|
|
|
set_debugreg(next->debugreg[3], 3);
|
|
|
|
/* no 4 and 5 */
|
|
|
|
set_debugreg(next->debugreg[6], 6);
|
|
|
|
set_debugreg(next->debugreg[7], 7);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) {
|
2005-04-16 18:20:36 -04:00
|
|
|
/*
|
|
|
|
* Disable the bitmap via an invalid offset. We still cache
|
|
|
|
* the previous bitmap owner and the IO bitmap contents:
|
|
|
|
*/
|
|
|
|
tss->io_bitmap_base = INVALID_IO_BITMAP_OFFSET;
|
|
|
|
return;
|
|
|
|
}
|
2006-07-09 21:12:39 -04:00
|
|
|
|
2005-04-16 18:20:36 -04:00
|
|
|
if (likely(next == tss->io_bitmap_owner)) {
|
|
|
|
/*
|
|
|
|
* Previous owner of the bitmap (hence the bitmap content)
|
|
|
|
* matches the next task, we dont have to do anything but
|
|
|
|
* to set a valid offset in the TSS:
|
|
|
|
*/
|
|
|
|
tss->io_bitmap_base = IO_BITMAP_OFFSET;
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* Lazy TSS's I/O bitmap copy. We set an invalid offset here
|
|
|
|
* and we let the task to get a GPF in case an I/O instruction
|
|
|
|
* is performed. The handler of the GPF will verify that the
|
|
|
|
* faulting task has a valid I/O bitmap and, it true, does the
|
|
|
|
* real copy and restart the instruction. This will save us
|
|
|
|
* redundant copies when the currently switched task does not
|
|
|
|
* perform any I/O during its timeslice.
|
|
|
|
*/
|
|
|
|
tss->io_bitmap_base = INVALID_IO_BITMAP_OFFSET_LAZY;
|
|
|
|
}
|
|
|
|
|
2005-06-27 17:36:36 -04:00
|
|
|
/*
|
|
|
|
* This function selects if the context switch from prev to next
|
|
|
|
* has to tweak the TSC disable bit in the cr4.
|
|
|
|
*/
|
|
|
|
static inline void disable_tsc(struct task_struct *prev_p,
|
|
|
|
struct task_struct *next_p)
|
|
|
|
{
|
|
|
|
struct thread_info *prev, *next;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* gcc should eliminate the ->thread_info dereference if
|
|
|
|
* has_secure_computing returns 0 at compile time (SECCOMP=n).
|
|
|
|
*/
|
2006-01-12 04:05:40 -05:00
|
|
|
prev = task_thread_info(prev_p);
|
|
|
|
next = task_thread_info(next_p);
|
2005-06-27 17:36:36 -04:00
|
|
|
|
|
|
|
if (has_secure_computing(prev) || has_secure_computing(next)) {
|
|
|
|
/* slow path here */
|
|
|
|
if (has_secure_computing(prev) &&
|
|
|
|
!has_secure_computing(next)) {
|
|
|
|
write_cr4(read_cr4() & ~X86_CR4_TSD);
|
|
|
|
} else if (!has_secure_computing(prev) &&
|
|
|
|
has_secure_computing(next))
|
|
|
|
write_cr4(read_cr4() | X86_CR4_TSD);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2005-04-16 18:20:36 -04:00
|
|
|
/*
|
|
|
|
* switch_to(x,yn) should switch tasks from x to y.
|
|
|
|
*
|
|
|
|
* We fsave/fwait so that an exception goes off at the right time
|
|
|
|
* (as a call from the fsave or fwait in effect) rather than to
|
|
|
|
* the wrong process. Lazy FP saving no longer makes any sense
|
|
|
|
* with modern CPU's, and this simplifies a lot of things (SMP
|
|
|
|
* and UP become the same).
|
|
|
|
*
|
|
|
|
* NOTE! We used to use the x86 hardware context switching. The
|
|
|
|
* reason for not using it any more becomes apparent when you
|
|
|
|
* try to recover gracefully from saved state that is no longer
|
|
|
|
* valid (stale segment register values in particular). With the
|
|
|
|
* hardware task-switch, there is no way to fix up bad state in
|
|
|
|
* a reasonable manner.
|
|
|
|
*
|
|
|
|
* The fact that Intel documents the hardware task-switching to
|
|
|
|
* be slow is a fairly red herring - this code is not noticeably
|
|
|
|
* faster. However, there _is_ some room for improvement here,
|
|
|
|
* so the performance issues may eventually be a valid point.
|
|
|
|
* More important, however, is the fact that this allows us much
|
|
|
|
* more flexibility.
|
|
|
|
*
|
|
|
|
* The return value (in %eax) will be the "prev" task after
|
|
|
|
* the task-switch, and shows up in ret_from_fork in entry.S,
|
|
|
|
* for example.
|
|
|
|
*/
|
|
|
|
struct task_struct fastcall * __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
|
|
|
|
{
|
|
|
|
struct thread_struct *prev = &prev_p->thread,
|
|
|
|
*next = &next_p->thread;
|
|
|
|
int cpu = smp_processor_id();
|
|
|
|
struct tss_struct *tss = &per_cpu(init_tss, cpu);
|
|
|
|
|
|
|
|
/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
|
|
|
|
|
|
|
|
__unlazy_fpu(prev_p);
|
|
|
|
|
2006-12-06 20:14:01 -05:00
|
|
|
|
|
|
|
/* we're going to use this soon, after a few expensive things */
|
|
|
|
if (next_p->fpu_counter > 5)
|
|
|
|
prefetch(&next->i387.fxsave);
|
|
|
|
|
2005-04-16 18:20:36 -04:00
|
|
|
/*
|
2005-09-03 18:56:39 -04:00
|
|
|
* Reload esp0.
|
2005-04-16 18:20:36 -04:00
|
|
|
*/
|
|
|
|
load_esp0(tss, next);
|
|
|
|
|
|
|
|
/*
|
2007-02-13 07:26:20 -05:00
|
|
|
* Save away %gs. No need to save %fs, as it was saved on the
|
[PATCH] i386: Use %gs as the PDA base-segment in the kernel
This patch is the meat of the PDA change. This patch makes several related
changes:
1: Most significantly, %gs is now used in the kernel. This means that on
entry, the old value of %gs is saved away, and it is reloaded with
__KERNEL_PDA.
2: entry.S constructs the stack in the shape of struct pt_regs, and this
is passed around the kernel so that the process's saved register
state can be accessed.
Unfortunately struct pt_regs doesn't currently have space for %gs
(or %fs). This patch extends pt_regs to add space for gs (no space
is allocated for %fs, since it won't be used, and it would just
complicate the code in entry.S to work around the space).
3: Because %gs is now saved on the stack like %ds, %es and the integer
registers, there are a number of places where it no longer needs to
be handled specially; namely context switch, and saving/restoring the
register state in a signal context.
4: And since kernel threads run in kernel space and call normal kernel
code, they need to be created with their %gs == __KERNEL_PDA.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Cc: Chuck Ebbert <76306.1226@compuserve.com>
Cc: Zachary Amsden <zach@vmware.com>
Cc: Jan Beulich <jbeulich@novell.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
2006-12-06 20:14:02 -05:00
|
|
|
* stack on entry. No need to save %es and %ds, as those are
|
|
|
|
* always kernel segments while inside the kernel. Doing this
|
|
|
|
* before setting the new TLS descriptors avoids the situation
|
|
|
|
* where we temporarily have non-reloadable segments in %fs
|
|
|
|
* and %gs. This could be an issue if the NMI handler ever
|
|
|
|
* used %fs or %gs (it does not today), or if the kernel is
|
|
|
|
* running inside of a hypervisor layer.
|
2005-04-16 18:20:36 -04:00
|
|
|
*/
|
2007-02-13 07:26:20 -05:00
|
|
|
savesegment(gs, prev->gs);
|
2005-04-16 18:20:36 -04:00
|
|
|
|
|
|
|
/*
|
2005-09-03 18:56:39 -04:00
|
|
|
* Load the per-thread Thread-Local Storage descriptor.
|
2005-04-16 18:20:36 -04:00
|
|
|
*/
|
2005-09-03 18:56:39 -04:00
|
|
|
load_TLS(next, cpu);
|
2005-04-16 18:20:36 -04:00
|
|
|
|
|
|
|
/*
|
2007-02-13 07:26:20 -05:00
|
|
|
* Restore %gs if needed (which is common)
|
2005-04-16 18:20:36 -04:00
|
|
|
*/
|
2007-02-13 07:26:20 -05:00
|
|
|
if (prev->gs | next->gs)
|
|
|
|
loadsegment(gs, next->gs);
|
2005-07-22 15:23:47 -04:00
|
|
|
|
2006-12-06 20:14:03 -05:00
|
|
|
write_pda(pcurrent, next_p);
|
2005-04-16 18:20:36 -04:00
|
|
|
|
|
|
|
/*
|
2006-07-09 21:12:39 -04:00
|
|
|
* Now maybe handle debug registers and/or IO bitmaps
|
2005-04-16 18:20:36 -04:00
|
|
|
*/
|
2006-07-25 16:15:16 -04:00
|
|
|
if (unlikely((task_thread_info(next_p)->flags & _TIF_WORK_CTXSW)
|
|
|
|
|| test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)))
|
2006-07-09 21:12:39 -04:00
|
|
|
__switch_to_xtra(next_p, tss);
|
2005-04-16 18:20:36 -04:00
|
|
|
|
2005-06-27 17:36:36 -04:00
|
|
|
disable_tsc(prev_p, next_p);
|
|
|
|
|
2006-12-06 20:14:01 -05:00
|
|
|
/* If the task has used fpu the last 5 timeslices, just do a full
|
|
|
|
* restore of the math state immediately to avoid the trap; the
|
|
|
|
* chances of needing FPU soon are obviously high now
|
|
|
|
*/
|
|
|
|
if (next_p->fpu_counter > 5)
|
|
|
|
math_state_restore();
|
|
|
|
|
2005-04-16 18:20:36 -04:00
|
|
|
return prev_p;
|
|
|
|
}
|
|
|
|
|
|
|
|
asmlinkage int sys_fork(struct pt_regs regs)
|
|
|
|
{
|
|
|
|
return do_fork(SIGCHLD, regs.esp, ®s, 0, NULL, NULL);
|
|
|
|
}
|
|
|
|
|
|
|
|
asmlinkage int sys_clone(struct pt_regs regs)
|
|
|
|
{
|
|
|
|
unsigned long clone_flags;
|
|
|
|
unsigned long newsp;
|
|
|
|
int __user *parent_tidptr, *child_tidptr;
|
|
|
|
|
|
|
|
clone_flags = regs.ebx;
|
|
|
|
newsp = regs.ecx;
|
|
|
|
parent_tidptr = (int __user *)regs.edx;
|
|
|
|
child_tidptr = (int __user *)regs.edi;
|
|
|
|
if (!newsp)
|
|
|
|
newsp = regs.esp;
|
|
|
|
return do_fork(clone_flags, newsp, ®s, 0, parent_tidptr, child_tidptr);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This is trivial, and on the face of it looks like it
|
|
|
|
* could equally well be done in user mode.
|
|
|
|
*
|
|
|
|
* Not so, for quite unobvious reasons - register pressure.
|
|
|
|
* In user mode vfork() cannot have a stack frame, and if
|
|
|
|
* done by calling the "clone()" system call directly, you
|
|
|
|
* do not have enough call-clobbered registers to hold all
|
|
|
|
* the information you need.
|
|
|
|
*/
|
|
|
|
asmlinkage int sys_vfork(struct pt_regs regs)
|
|
|
|
{
|
|
|
|
return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs.esp, ®s, 0, NULL, NULL);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* sys_execve() executes a new program.
|
|
|
|
*/
|
|
|
|
asmlinkage int sys_execve(struct pt_regs regs)
|
|
|
|
{
|
|
|
|
int error;
|
|
|
|
char * filename;
|
|
|
|
|
|
|
|
filename = getname((char __user *) regs.ebx);
|
|
|
|
error = PTR_ERR(filename);
|
|
|
|
if (IS_ERR(filename))
|
|
|
|
goto out;
|
|
|
|
error = do_execve(filename,
|
|
|
|
(char __user * __user *) regs.ecx,
|
|
|
|
(char __user * __user *) regs.edx,
|
|
|
|
®s);
|
|
|
|
if (error == 0) {
|
|
|
|
task_lock(current);
|
|
|
|
current->ptrace &= ~PT_DTRACE;
|
|
|
|
task_unlock(current);
|
|
|
|
/* Make sure we don't return using sysenter.. */
|
|
|
|
set_thread_flag(TIF_IRET);
|
|
|
|
}
|
|
|
|
putname(filename);
|
|
|
|
out:
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
#define top_esp (THREAD_SIZE - sizeof(unsigned long))
|
|
|
|
#define top_ebp (THREAD_SIZE - 2*sizeof(unsigned long))
|
|
|
|
|
|
|
|
unsigned long get_wchan(struct task_struct *p)
|
|
|
|
{
|
|
|
|
unsigned long ebp, esp, eip;
|
|
|
|
unsigned long stack_page;
|
|
|
|
int count = 0;
|
|
|
|
if (!p || p == current || p->state == TASK_RUNNING)
|
|
|
|
return 0;
|
2006-01-12 04:05:41 -05:00
|
|
|
stack_page = (unsigned long)task_stack_page(p);
|
2005-04-16 18:20:36 -04:00
|
|
|
esp = p->thread.esp;
|
|
|
|
if (!stack_page || esp < stack_page || esp > top_esp+stack_page)
|
|
|
|
return 0;
|
|
|
|
/* include/asm-i386/system.h:switch_to() pushes ebp last. */
|
|
|
|
ebp = *(unsigned long *) esp;
|
|
|
|
do {
|
|
|
|
if (ebp < stack_page || ebp > top_ebp+stack_page)
|
|
|
|
return 0;
|
|
|
|
eip = *(unsigned long *) (ebp+4);
|
|
|
|
if (!in_sched_functions(eip))
|
|
|
|
return eip;
|
|
|
|
ebp = *(unsigned long *) ebp;
|
|
|
|
} while (count++ < 16);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* sys_alloc_thread_area: get a yet unused TLS descriptor index.
|
|
|
|
*/
|
|
|
|
static int get_free_idx(void)
|
|
|
|
{
|
|
|
|
struct thread_struct *t = ¤t->thread;
|
|
|
|
int idx;
|
|
|
|
|
|
|
|
for (idx = 0; idx < GDT_ENTRY_TLS_ENTRIES; idx++)
|
|
|
|
if (desc_empty(t->tls_array + idx))
|
|
|
|
return idx + GDT_ENTRY_TLS_MIN;
|
|
|
|
return -ESRCH;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Set a given TLS descriptor:
|
|
|
|
*/
|
|
|
|
asmlinkage int sys_set_thread_area(struct user_desc __user *u_info)
|
|
|
|
{
|
|
|
|
struct thread_struct *t = ¤t->thread;
|
|
|
|
struct user_desc info;
|
|
|
|
struct desc_struct *desc;
|
|
|
|
int cpu, idx;
|
|
|
|
|
|
|
|
if (copy_from_user(&info, u_info, sizeof(info)))
|
|
|
|
return -EFAULT;
|
|
|
|
idx = info.entry_number;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* index -1 means the kernel should try to find and
|
|
|
|
* allocate an empty descriptor:
|
|
|
|
*/
|
|
|
|
if (idx == -1) {
|
|
|
|
idx = get_free_idx();
|
|
|
|
if (idx < 0)
|
|
|
|
return idx;
|
|
|
|
if (put_user(idx, &u_info->entry_number))
|
|
|
|
return -EFAULT;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
desc = t->tls_array + idx - GDT_ENTRY_TLS_MIN;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We must not get preempted while modifying the TLS.
|
|
|
|
*/
|
|
|
|
cpu = get_cpu();
|
|
|
|
|
|
|
|
if (LDT_empty(&info)) {
|
|
|
|
desc->a = 0;
|
|
|
|
desc->b = 0;
|
|
|
|
} else {
|
|
|
|
desc->a = LDT_entry_a(&info);
|
|
|
|
desc->b = LDT_entry_b(&info);
|
|
|
|
}
|
|
|
|
load_TLS(t, cpu);
|
|
|
|
|
|
|
|
put_cpu();
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Get the current Thread-Local Storage area:
|
|
|
|
*/
|
|
|
|
|
|
|
|
#define GET_BASE(desc) ( \
|
|
|
|
(((desc)->a >> 16) & 0x0000ffff) | \
|
|
|
|
(((desc)->b << 16) & 0x00ff0000) | \
|
|
|
|
( (desc)->b & 0xff000000) )
|
|
|
|
|
|
|
|
#define GET_LIMIT(desc) ( \
|
|
|
|
((desc)->a & 0x0ffff) | \
|
|
|
|
((desc)->b & 0xf0000) )
|
|
|
|
|
|
|
|
#define GET_32BIT(desc) (((desc)->b >> 22) & 1)
|
|
|
|
#define GET_CONTENTS(desc) (((desc)->b >> 10) & 3)
|
|
|
|
#define GET_WRITABLE(desc) (((desc)->b >> 9) & 1)
|
|
|
|
#define GET_LIMIT_PAGES(desc) (((desc)->b >> 23) & 1)
|
|
|
|
#define GET_PRESENT(desc) (((desc)->b >> 15) & 1)
|
|
|
|
#define GET_USEABLE(desc) (((desc)->b >> 20) & 1)
|
|
|
|
|
|
|
|
asmlinkage int sys_get_thread_area(struct user_desc __user *u_info)
|
|
|
|
{
|
|
|
|
struct user_desc info;
|
|
|
|
struct desc_struct *desc;
|
|
|
|
int idx;
|
|
|
|
|
|
|
|
if (get_user(idx, &u_info->entry_number))
|
|
|
|
return -EFAULT;
|
|
|
|
if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
|
|
|
|
return -EINVAL;
|
|
|
|
|
2005-07-27 14:45:18 -04:00
|
|
|
memset(&info, 0, sizeof(info));
|
|
|
|
|
2005-04-16 18:20:36 -04:00
|
|
|
desc = current->thread.tls_array + idx - GDT_ENTRY_TLS_MIN;
|
|
|
|
|
|
|
|
info.entry_number = idx;
|
|
|
|
info.base_addr = GET_BASE(desc);
|
|
|
|
info.limit = GET_LIMIT(desc);
|
|
|
|
info.seg_32bit = GET_32BIT(desc);
|
|
|
|
info.contents = GET_CONTENTS(desc);
|
|
|
|
info.read_exec_only = !GET_WRITABLE(desc);
|
|
|
|
info.limit_in_pages = GET_LIMIT_PAGES(desc);
|
|
|
|
info.seg_not_present = !GET_PRESENT(desc);
|
|
|
|
info.useable = GET_USEABLE(desc);
|
|
|
|
|
|
|
|
if (copy_to_user(u_info, &info, sizeof(info)))
|
|
|
|
return -EFAULT;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned long arch_align_stack(unsigned long sp)
|
|
|
|
{
|
2006-09-26 04:52:28 -04:00
|
|
|
if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
|
2005-04-16 18:20:36 -04:00
|
|
|
sp -= get_random_int() % 8192;
|
|
|
|
return sp & ~0xf;
|
|
|
|
}
|