forked from luck/tmp_suning_uos_patched
64c7c8f885
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>
401 lines
10 KiB
C
401 lines
10 KiB
C
/*
|
|
* arch/s390/kernel/process.c
|
|
*
|
|
* S390 version
|
|
* Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation
|
|
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com),
|
|
* Hartmut Penner (hp@de.ibm.com),
|
|
* Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com),
|
|
*
|
|
* Derived from "arch/i386/kernel/process.c"
|
|
* Copyright (C) 1995, Linus Torvalds
|
|
*/
|
|
|
|
/*
|
|
* This file handles the architecture-dependent parts of process handling..
|
|
*/
|
|
|
|
#include <linux/config.h>
|
|
#include <linux/compiler.h>
|
|
#include <linux/cpu.h>
|
|
#include <linux/errno.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/smp_lock.h>
|
|
#include <linux/stddef.h>
|
|
#include <linux/unistd.h>
|
|
#include <linux/ptrace.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/vmalloc.h>
|
|
#include <linux/user.h>
|
|
#include <linux/a.out.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/delay.h>
|
|
#include <linux/reboot.h>
|
|
#include <linux/init.h>
|
|
#include <linux/module.h>
|
|
#include <linux/notifier.h>
|
|
|
|
#include <asm/uaccess.h>
|
|
#include <asm/pgtable.h>
|
|
#include <asm/system.h>
|
|
#include <asm/io.h>
|
|
#include <asm/processor.h>
|
|
#include <asm/irq.h>
|
|
#include <asm/timer.h>
|
|
|
|
asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
|
|
|
|
/*
|
|
* Return saved PC of a blocked thread. used in kernel/sched.
|
|
* resume in entry.S does not create a new stack frame, it
|
|
* just stores the registers %r6-%r15 to the frame given by
|
|
* schedule. We want to return the address of the caller of
|
|
* schedule, so we have to walk the backchain one time to
|
|
* find the frame schedule() store its return address.
|
|
*/
|
|
unsigned long thread_saved_pc(struct task_struct *tsk)
|
|
{
|
|
struct stack_frame *sf;
|
|
|
|
sf = (struct stack_frame *) tsk->thread.ksp;
|
|
sf = (struct stack_frame *) sf->back_chain;
|
|
return sf->gprs[8];
|
|
}
|
|
|
|
/*
|
|
* Need to know about CPUs going idle?
|
|
*/
|
|
static struct notifier_block *idle_chain;
|
|
|
|
int register_idle_notifier(struct notifier_block *nb)
|
|
{
|
|
return notifier_chain_register(&idle_chain, nb);
|
|
}
|
|
EXPORT_SYMBOL(register_idle_notifier);
|
|
|
|
int unregister_idle_notifier(struct notifier_block *nb)
|
|
{
|
|
return notifier_chain_unregister(&idle_chain, nb);
|
|
}
|
|
EXPORT_SYMBOL(unregister_idle_notifier);
|
|
|
|
void do_monitor_call(struct pt_regs *regs, long interruption_code)
|
|
{
|
|
/* disable monitor call class 0 */
|
|
__ctl_clear_bit(8, 15);
|
|
|
|
notifier_call_chain(&idle_chain, CPU_NOT_IDLE,
|
|
(void *)(long) smp_processor_id());
|
|
}
|
|
|
|
extern void s390_handle_mcck(void);
|
|
/*
|
|
* The idle loop on a S390...
|
|
*/
|
|
void default_idle(void)
|
|
{
|
|
int cpu, rc;
|
|
|
|
/* CPU is going idle. */
|
|
cpu = smp_processor_id();
|
|
|
|
local_irq_disable();
|
|
if (need_resched()) {
|
|
local_irq_enable();
|
|
return;
|
|
}
|
|
|
|
rc = notifier_call_chain(&idle_chain, CPU_IDLE, (void *)(long) cpu);
|
|
if (rc != NOTIFY_OK && rc != NOTIFY_DONE)
|
|
BUG();
|
|
if (rc != NOTIFY_OK) {
|
|
local_irq_enable();
|
|
return;
|
|
}
|
|
|
|
/* enable monitor call class 0 */
|
|
__ctl_set_bit(8, 15);
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
if (cpu_is_offline(cpu))
|
|
cpu_die();
|
|
#endif
|
|
|
|
local_mcck_disable();
|
|
if (test_thread_flag(TIF_MCCK_PENDING)) {
|
|
local_mcck_enable();
|
|
local_irq_enable();
|
|
s390_handle_mcck();
|
|
return;
|
|
}
|
|
|
|
/* Wait for external, I/O or machine check interrupt. */
|
|
__load_psw_mask(PSW_KERNEL_BITS | PSW_MASK_WAIT |
|
|
PSW_MASK_IO | PSW_MASK_EXT);
|
|
}
|
|
|
|
void cpu_idle(void)
|
|
{
|
|
for (;;) {
|
|
while (!need_resched())
|
|
default_idle();
|
|
|
|
preempt_enable_no_resched();
|
|
schedule();
|
|
preempt_disable();
|
|
}
|
|
}
|
|
|
|
void show_regs(struct pt_regs *regs)
|
|
{
|
|
struct task_struct *tsk = current;
|
|
|
|
printk("CPU: %d %s\n", tsk->thread_info->cpu, print_tainted());
|
|
printk("Process %s (pid: %d, task: %p, ksp: %p)\n",
|
|
current->comm, current->pid, (void *) tsk,
|
|
(void *) tsk->thread.ksp);
|
|
|
|
show_registers(regs);
|
|
/* Show stack backtrace if pt_regs is from kernel mode */
|
|
if (!(regs->psw.mask & PSW_MASK_PSTATE))
|
|
show_trace(0,(unsigned long *) regs->gprs[15]);
|
|
}
|
|
|
|
extern void kernel_thread_starter(void);
|
|
|
|
__asm__(".align 4\n"
|
|
"kernel_thread_starter:\n"
|
|
" la 2,0(10)\n"
|
|
" basr 14,9\n"
|
|
" la 2,0\n"
|
|
" br 11\n");
|
|
|
|
int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
|
|
{
|
|
struct pt_regs regs;
|
|
|
|
memset(®s, 0, sizeof(regs));
|
|
regs.psw.mask = PSW_KERNEL_BITS | PSW_MASK_IO | PSW_MASK_EXT;
|
|
regs.psw.addr = (unsigned long) kernel_thread_starter | PSW_ADDR_AMODE;
|
|
regs.gprs[9] = (unsigned long) fn;
|
|
regs.gprs[10] = (unsigned long) arg;
|
|
regs.gprs[11] = (unsigned long) do_exit;
|
|
regs.orig_gpr2 = -1;
|
|
|
|
/* Ok, create the new process.. */
|
|
return do_fork(flags | CLONE_VM | CLONE_UNTRACED,
|
|
0, ®s, 0, NULL, NULL);
|
|
}
|
|
|
|
/*
|
|
* Free current thread data structures etc..
|
|
*/
|
|
void exit_thread(void)
|
|
{
|
|
}
|
|
|
|
void flush_thread(void)
|
|
{
|
|
clear_used_math();
|
|
clear_tsk_thread_flag(current, TIF_USEDFPU);
|
|
}
|
|
|
|
void release_thread(struct task_struct *dead_task)
|
|
{
|
|
}
|
|
|
|
int copy_thread(int nr, unsigned long clone_flags, unsigned long new_stackp,
|
|
unsigned long unused,
|
|
struct task_struct * p, struct pt_regs * regs)
|
|
{
|
|
struct fake_frame
|
|
{
|
|
struct stack_frame sf;
|
|
struct pt_regs childregs;
|
|
} *frame;
|
|
|
|
frame = ((struct fake_frame *)
|
|
(THREAD_SIZE + (unsigned long) p->thread_info)) - 1;
|
|
p->thread.ksp = (unsigned long) frame;
|
|
/* Store access registers to kernel stack of new process. */
|
|
frame->childregs = *regs;
|
|
frame->childregs.gprs[2] = 0; /* child returns 0 on fork. */
|
|
frame->childregs.gprs[15] = new_stackp;
|
|
frame->sf.back_chain = 0;
|
|
|
|
/* new return point is ret_from_fork */
|
|
frame->sf.gprs[8] = (unsigned long) ret_from_fork;
|
|
|
|
/* fake return stack for resume(), don't go back to schedule */
|
|
frame->sf.gprs[9] = (unsigned long) frame;
|
|
|
|
/* Save access registers to new thread structure. */
|
|
save_access_regs(&p->thread.acrs[0]);
|
|
|
|
#ifndef CONFIG_ARCH_S390X
|
|
/*
|
|
* save fprs to current->thread.fp_regs to merge them with
|
|
* the emulated registers and then copy the result to the child.
|
|
*/
|
|
save_fp_regs(¤t->thread.fp_regs);
|
|
memcpy(&p->thread.fp_regs, ¤t->thread.fp_regs,
|
|
sizeof(s390_fp_regs));
|
|
p->thread.user_seg = __pa((unsigned long) p->mm->pgd) | _SEGMENT_TABLE;
|
|
/* Set a new TLS ? */
|
|
if (clone_flags & CLONE_SETTLS)
|
|
p->thread.acrs[0] = regs->gprs[6];
|
|
#else /* CONFIG_ARCH_S390X */
|
|
/* Save the fpu registers to new thread structure. */
|
|
save_fp_regs(&p->thread.fp_regs);
|
|
p->thread.user_seg = __pa((unsigned long) p->mm->pgd) | _REGION_TABLE;
|
|
/* Set a new TLS ? */
|
|
if (clone_flags & CLONE_SETTLS) {
|
|
if (test_thread_flag(TIF_31BIT)) {
|
|
p->thread.acrs[0] = (unsigned int) regs->gprs[6];
|
|
} else {
|
|
p->thread.acrs[0] = (unsigned int)(regs->gprs[6] >> 32);
|
|
p->thread.acrs[1] = (unsigned int) regs->gprs[6];
|
|
}
|
|
}
|
|
#endif /* CONFIG_ARCH_S390X */
|
|
/* start new process with ar4 pointing to the correct address space */
|
|
p->thread.mm_segment = get_fs();
|
|
/* Don't copy debug registers */
|
|
memset(&p->thread.per_info,0,sizeof(p->thread.per_info));
|
|
|
|
return 0;
|
|
}
|
|
|
|
asmlinkage long sys_fork(struct pt_regs regs)
|
|
{
|
|
return do_fork(SIGCHLD, regs.gprs[15], ®s, 0, NULL, NULL);
|
|
}
|
|
|
|
asmlinkage long sys_clone(struct pt_regs regs)
|
|
{
|
|
unsigned long clone_flags;
|
|
unsigned long newsp;
|
|
int __user *parent_tidptr, *child_tidptr;
|
|
|
|
clone_flags = regs.gprs[3];
|
|
newsp = regs.orig_gpr2;
|
|
parent_tidptr = (int __user *) regs.gprs[4];
|
|
child_tidptr = (int __user *) regs.gprs[5];
|
|
if (!newsp)
|
|
newsp = regs.gprs[15];
|
|
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 long sys_vfork(struct pt_regs regs)
|
|
{
|
|
return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD,
|
|
regs.gprs[15], ®s, 0, NULL, NULL);
|
|
}
|
|
|
|
/*
|
|
* sys_execve() executes a new program.
|
|
*/
|
|
asmlinkage long sys_execve(struct pt_regs regs)
|
|
{
|
|
int error;
|
|
char * filename;
|
|
|
|
filename = getname((char __user *) regs.orig_gpr2);
|
|
error = PTR_ERR(filename);
|
|
if (IS_ERR(filename))
|
|
goto out;
|
|
error = do_execve(filename, (char __user * __user *) regs.gprs[3],
|
|
(char __user * __user *) regs.gprs[4], ®s);
|
|
if (error == 0) {
|
|
task_lock(current);
|
|
current->ptrace &= ~PT_DTRACE;
|
|
task_unlock(current);
|
|
current->thread.fp_regs.fpc = 0;
|
|
if (MACHINE_HAS_IEEE)
|
|
asm volatile("sfpc %0,%0" : : "d" (0));
|
|
}
|
|
putname(filename);
|
|
out:
|
|
return error;
|
|
}
|
|
|
|
|
|
/*
|
|
* fill in the FPU structure for a core dump.
|
|
*/
|
|
int dump_fpu (struct pt_regs * regs, s390_fp_regs *fpregs)
|
|
{
|
|
#ifndef CONFIG_ARCH_S390X
|
|
/*
|
|
* save fprs to current->thread.fp_regs to merge them with
|
|
* the emulated registers and then copy the result to the dump.
|
|
*/
|
|
save_fp_regs(¤t->thread.fp_regs);
|
|
memcpy(fpregs, ¤t->thread.fp_regs, sizeof(s390_fp_regs));
|
|
#else /* CONFIG_ARCH_S390X */
|
|
save_fp_regs(fpregs);
|
|
#endif /* CONFIG_ARCH_S390X */
|
|
return 1;
|
|
}
|
|
|
|
/*
|
|
* fill in the user structure for a core dump..
|
|
*/
|
|
void dump_thread(struct pt_regs * regs, struct user * dump)
|
|
{
|
|
|
|
/* changed the size calculations - should hopefully work better. lbt */
|
|
dump->magic = CMAGIC;
|
|
dump->start_code = 0;
|
|
dump->start_stack = regs->gprs[15] & ~(PAGE_SIZE - 1);
|
|
dump->u_tsize = current->mm->end_code >> PAGE_SHIFT;
|
|
dump->u_dsize = (current->mm->brk + PAGE_SIZE - 1) >> PAGE_SHIFT;
|
|
dump->u_dsize -= dump->u_tsize;
|
|
dump->u_ssize = 0;
|
|
if (dump->start_stack < TASK_SIZE)
|
|
dump->u_ssize = (TASK_SIZE - dump->start_stack) >> PAGE_SHIFT;
|
|
memcpy(&dump->regs, regs, sizeof(s390_regs));
|
|
dump_fpu (regs, &dump->regs.fp_regs);
|
|
dump->regs.per_info = current->thread.per_info;
|
|
}
|
|
|
|
unsigned long get_wchan(struct task_struct *p)
|
|
{
|
|
struct stack_frame *sf, *low, *high;
|
|
unsigned long return_address;
|
|
int count;
|
|
|
|
if (!p || p == current || p->state == TASK_RUNNING || !p->thread_info)
|
|
return 0;
|
|
low = (struct stack_frame *) p->thread_info;
|
|
high = (struct stack_frame *)
|
|
((unsigned long) p->thread_info + THREAD_SIZE) - 1;
|
|
sf = (struct stack_frame *) (p->thread.ksp & PSW_ADDR_INSN);
|
|
if (sf <= low || sf > high)
|
|
return 0;
|
|
for (count = 0; count < 16; count++) {
|
|
sf = (struct stack_frame *) (sf->back_chain & PSW_ADDR_INSN);
|
|
if (sf <= low || sf > high)
|
|
return 0;
|
|
return_address = sf->gprs[8] & PSW_ADDR_INSN;
|
|
if (!in_sched_functions(return_address))
|
|
return return_address;
|
|
}
|
|
return 0;
|
|
}
|
|
|