linux/arch/s390/kernel/idle.c
Sven Schnelle 56e62a7370 s390: convert to generic entry
This patch converts s390 to use the generic entry infrastructure from
kernel/entry/*.

There are a few special things on s390:

- PIF_PER_TRAP is moved to TIF_PER_TRAP as the generic code doesn't
  know about our PIF flags in exit_to_user_mode_loop().

- The old code had several ways to restart syscalls:

  a) PIF_SYSCALL_RESTART, which was only set during execve to force a
     restart after upgrading a process (usually qemu-kvm) to pgste page
     table extensions.

  b) PIF_SYSCALL, which is set by do_signal() to indicate that the
     current syscall should be restarted. This is changed so that
     do_signal() now also uses PIF_SYSCALL_RESTART. Continuing to use
     PIF_SYSCALL doesn't work with the generic code, and changing it
     to PIF_SYSCALL_RESTART makes PIF_SYSCALL and PIF_SYSCALL_RESTART
     more unique.

- On s390 calling sys_sigreturn or sys_rt_sigreturn is implemented by
executing a svc instruction on the process stack which causes a fault.
While handling that fault the fault code sets PIF_SYSCALL to hand over
processing to the syscall code on exit to usermode.

The patch introduces PIF_SYSCALL_RET_SET, which is set if ptrace sets
a return value for a syscall. The s390x ptrace ABI uses r2 both for the
syscall number and return value, so ptrace cannot set the syscall number +
return value at the same time. The flag makes handling that a bit easier.
do_syscall() will just skip executing the syscall if PIF_SYSCALL_RET_SET
is set.

CONFIG_DEBUG_ASCE was removd in favour of the generic CONFIG_DEBUG_ENTRY.
CR1/7/13 will be checked both on kernel entry and exit to contain the
correct asces.

Signed-off-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
2021-01-19 12:29:26 +01:00

151 lines
4.0 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* Idle functions for s390.
*
* Copyright IBM Corp. 2014
*
* Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
*/
#include <linux/kernel.h>
#include <linux/kernel_stat.h>
#include <linux/notifier.h>
#include <linux/init.h>
#include <linux/cpu.h>
#include <linux/sched/cputime.h>
#include <trace/events/power.h>
#include <asm/cpu_mf.h>
#include <asm/nmi.h>
#include <asm/smp.h>
#include "entry.h"
static DEFINE_PER_CPU(struct s390_idle_data, s390_idle);
void account_idle_time_irq(void)
{
struct s390_idle_data *idle = this_cpu_ptr(&s390_idle);
u64 cycles_new[8];
int i;
clear_cpu_flag(CIF_ENABLED_WAIT);
if (smp_cpu_mtid) {
stcctm(MT_DIAG, smp_cpu_mtid, cycles_new);
for (i = 0; i < smp_cpu_mtid; i++)
this_cpu_add(mt_cycles[i], cycles_new[i] - idle->mt_cycles_enter[i]);
}
idle->clock_idle_exit = S390_lowcore.int_clock;
idle->timer_idle_exit = S390_lowcore.sys_enter_timer;
S390_lowcore.steal_timer += idle->clock_idle_enter - S390_lowcore.last_update_clock;
S390_lowcore.last_update_clock = idle->clock_idle_exit;
S390_lowcore.system_timer += S390_lowcore.last_update_timer - idle->timer_idle_enter;
S390_lowcore.last_update_timer = idle->timer_idle_exit;
}
void arch_cpu_idle(void)
{
struct s390_idle_data *idle = this_cpu_ptr(&s390_idle);
unsigned long long idle_time;
unsigned long psw_mask;
/* Wait for external, I/O or machine check interrupt. */
psw_mask = PSW_KERNEL_BITS | PSW_MASK_WAIT | PSW_MASK_DAT |
PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
clear_cpu_flag(CIF_NOHZ_DELAY);
/* psw_idle() returns with interrupts disabled. */
psw_idle(idle, psw_mask);
/* Account time spent with enabled wait psw loaded as idle time. */
raw_write_seqcount_begin(&idle->seqcount);
idle_time = idle->clock_idle_exit - idle->clock_idle_enter;
idle->clock_idle_enter = idle->clock_idle_exit = 0ULL;
idle->idle_time += idle_time;
idle->idle_count++;
account_idle_time(cputime_to_nsecs(idle_time));
raw_write_seqcount_end(&idle->seqcount);
raw_local_irq_enable();
}
static ssize_t show_idle_count(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id);
unsigned long long idle_count;
unsigned int seq;
do {
seq = read_seqcount_begin(&idle->seqcount);
idle_count = READ_ONCE(idle->idle_count);
if (READ_ONCE(idle->clock_idle_enter))
idle_count++;
} while (read_seqcount_retry(&idle->seqcount, seq));
return sprintf(buf, "%llu\n", idle_count);
}
DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL);
static ssize_t show_idle_time(struct device *dev,
struct device_attribute *attr, char *buf)
{
unsigned long long now, idle_time, idle_enter, idle_exit, in_idle;
struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id);
unsigned int seq;
do {
seq = read_seqcount_begin(&idle->seqcount);
idle_time = READ_ONCE(idle->idle_time);
idle_enter = READ_ONCE(idle->clock_idle_enter);
idle_exit = READ_ONCE(idle->clock_idle_exit);
} while (read_seqcount_retry(&idle->seqcount, seq));
in_idle = 0;
now = get_tod_clock();
if (idle_enter) {
if (idle_exit) {
in_idle = idle_exit - idle_enter;
} else if (now > idle_enter) {
in_idle = now - idle_enter;
}
}
idle_time += in_idle;
return sprintf(buf, "%llu\n", idle_time >> 12);
}
DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL);
u64 arch_cpu_idle_time(int cpu)
{
struct s390_idle_data *idle = &per_cpu(s390_idle, cpu);
unsigned long long now, idle_enter, idle_exit, in_idle;
unsigned int seq;
do {
seq = read_seqcount_begin(&idle->seqcount);
idle_enter = READ_ONCE(idle->clock_idle_enter);
idle_exit = READ_ONCE(idle->clock_idle_exit);
} while (read_seqcount_retry(&idle->seqcount, seq));
in_idle = 0;
now = get_tod_clock();
if (idle_enter) {
if (idle_exit) {
in_idle = idle_exit - idle_enter;
} else if (now > idle_enter) {
in_idle = now - idle_enter;
}
}
return cputime_to_nsecs(in_idle);
}
void arch_cpu_idle_enter(void)
{
}
void arch_cpu_idle_exit(void)
{
}
void arch_cpu_idle_dead(void)
{
cpu_die();
}