linux-kernel-test/arch/x86_64/kernel/time.c

730 lines
18 KiB
C
Raw Normal View History

/*
* linux/arch/x86-64/kernel/time.c
*
* "High Precision Event Timer" based timekeeping.
*
* Copyright (c) 1991,1992,1995 Linus Torvalds
* Copyright (c) 1994 Alan Modra
* Copyright (c) 1995 Markus Kuhn
* Copyright (c) 1996 Ingo Molnar
* Copyright (c) 1998 Andrea Arcangeli
* Copyright (c) 2002,2006 Vojtech Pavlik
* Copyright (c) 2003 Andi Kleen
* RTC support code taken from arch/i386/kernel/timers/time_hpet.c
*/
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/mc146818rtc.h>
#include <linux/time.h>
#include <linux/ioport.h>
#include <linux/module.h>
#include <linux/device.h>
#include <linux/sysdev.h>
#include <linux/bcd.h>
#include <linux/notifier.h>
#include <linux/cpu.h>
#include <linux/kallsyms.h>
#include <linux/acpi.h>
#ifdef CONFIG_ACPI
#include <acpi/achware.h> /* for PM timer frequency */
#include <acpi/acpi_bus.h>
#endif
#include <asm/8253pit.h>
#include <asm/pgtable.h>
#include <asm/vsyscall.h>
#include <asm/timex.h>
#include <asm/proto.h>
#include <asm/hpet.h>
#include <asm/sections.h>
#include <linux/cpufreq.h>
#include <linux/hpet.h>
#include <asm/apic.h>
#include <asm/hpet.h>
#ifdef CONFIG_CPU_FREQ
extern void cpufreq_delayed_get(void);
#endif
extern void i8254_timer_resume(void);
extern int using_apic_timer;
static char *timename = NULL;
DEFINE_SPINLOCK(rtc_lock);
EXPORT_SYMBOL(rtc_lock);
DEFINE_SPINLOCK(i8253_lock);
unsigned long vxtime_hz = PIT_TICK_RATE;
int report_lost_ticks; /* command line option */
unsigned long long monotonic_base;
struct vxtime_data __vxtime __section_vxtime; /* for vsyscalls */
volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES;
struct timespec __xtime __section_xtime;
struct timezone __sys_tz __section_sys_tz;
unsigned int (*do_gettimeoffset)(void) = do_gettimeoffset_tsc;
/*
* This version of gettimeofday() has microsecond resolution and better than
* microsecond precision, as we're using at least a 10 MHz (usually 14.31818
* MHz) HPET timer.
*/
void do_gettimeofday(struct timeval *tv)
{
[PATCH] kill wall_jiffies With 2.6.18-rc4-mm2, now wall_jiffies will always be the same as jiffies. So we can kill wall_jiffies completely. This is just a cleanup and logically should not change any real behavior except for one thing: RTC updating code in (old) ppc and xtensa use a condition "jiffies - wall_jiffies == 1". This condition is never met so I suppose it is just a bug. I just remove that condition only instead of kill the whole "if" block. [heiko.carstens@de.ibm.com: s390 build fix and cleanup] Signed-off-by: Atsushi Nemoto <anemo@mba.ocn.ne.jp> Cc: Andi Kleen <ak@muc.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Ian Molton <spyro@f2s.com> Cc: Mikael Starvik <starvik@axis.com> Cc: David Howells <dhowells@redhat.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: Hirokazu Takata <takata.hirokazu@renesas.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp> Cc: Richard Curnow <rc@rc0.org.uk> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Cc: Miles Bader <uclinux-v850@lsi.nec.co.jp> Cc: Chris Zankel <chris@zankel.net> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Roman Zippel <zippel@linux-m68k.org> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-01 06:28:31 +00:00
unsigned long seq;
unsigned int sec, usec;
do {
seq = read_seqbegin(&xtime_lock);
sec = xtime.tv_sec;
usec = xtime.tv_nsec / NSEC_PER_USEC;
/* i386 does some correction here to keep the clock
monotonous even when ntpd is fixing drift.
But they didn't work for me, there is a non monotonic
clock anyways with ntp.
I dropped all corrections now until a real solution can
be found. Note when you fix it here you need to do the same
in arch/x86_64/kernel/vsyscall.c and export all needed
variables in vmlinux.lds. -AK */
[PATCH] kill wall_jiffies With 2.6.18-rc4-mm2, now wall_jiffies will always be the same as jiffies. So we can kill wall_jiffies completely. This is just a cleanup and logically should not change any real behavior except for one thing: RTC updating code in (old) ppc and xtensa use a condition "jiffies - wall_jiffies == 1". This condition is never met so I suppose it is just a bug. I just remove that condition only instead of kill the whole "if" block. [heiko.carstens@de.ibm.com: s390 build fix and cleanup] Signed-off-by: Atsushi Nemoto <anemo@mba.ocn.ne.jp> Cc: Andi Kleen <ak@muc.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Ian Molton <spyro@f2s.com> Cc: Mikael Starvik <starvik@axis.com> Cc: David Howells <dhowells@redhat.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: Hirokazu Takata <takata.hirokazu@renesas.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp> Cc: Richard Curnow <rc@rc0.org.uk> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Cc: Miles Bader <uclinux-v850@lsi.nec.co.jp> Cc: Chris Zankel <chris@zankel.net> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Roman Zippel <zippel@linux-m68k.org> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-01 06:28:31 +00:00
usec += do_gettimeoffset();
} while (read_seqretry(&xtime_lock, seq));
tv->tv_sec = sec + usec / USEC_PER_SEC;
tv->tv_usec = usec % USEC_PER_SEC;
}
EXPORT_SYMBOL(do_gettimeofday);
/*
* settimeofday() first undoes the correction that gettimeofday would do
* on the time, and then saves it. This is ugly, but has been like this for
* ages already.
*/
int do_settimeofday(struct timespec *tv)
{
time_t wtm_sec, sec = tv->tv_sec;
long wtm_nsec, nsec = tv->tv_nsec;
if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
return -EINVAL;
write_seqlock_irq(&xtime_lock);
[PATCH] kill wall_jiffies With 2.6.18-rc4-mm2, now wall_jiffies will always be the same as jiffies. So we can kill wall_jiffies completely. This is just a cleanup and logically should not change any real behavior except for one thing: RTC updating code in (old) ppc and xtensa use a condition "jiffies - wall_jiffies == 1". This condition is never met so I suppose it is just a bug. I just remove that condition only instead of kill the whole "if" block. [heiko.carstens@de.ibm.com: s390 build fix and cleanup] Signed-off-by: Atsushi Nemoto <anemo@mba.ocn.ne.jp> Cc: Andi Kleen <ak@muc.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Ian Molton <spyro@f2s.com> Cc: Mikael Starvik <starvik@axis.com> Cc: David Howells <dhowells@redhat.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: Hirokazu Takata <takata.hirokazu@renesas.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp> Cc: Richard Curnow <rc@rc0.org.uk> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Cc: Miles Bader <uclinux-v850@lsi.nec.co.jp> Cc: Chris Zankel <chris@zankel.net> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Roman Zippel <zippel@linux-m68k.org> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-01 06:28:31 +00:00
nsec -= do_gettimeoffset() * NSEC_PER_USEC;
wtm_sec = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec);
wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec);
set_normalized_timespec(&xtime, sec, nsec);
set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec);
ntp_clear();
write_sequnlock_irq(&xtime_lock);
clock_was_set();
return 0;
}
EXPORT_SYMBOL(do_settimeofday);
unsigned long profile_pc(struct pt_regs *regs)
{
unsigned long pc = instruction_pointer(regs);
/* Assume the lock function has either no stack frame or a copy
of eflags from PUSHF
Eflags always has bits 22 and up cleared unlike kernel addresses. */
if (!user_mode(regs) && in_lock_functions(pc)) {
unsigned long *sp = (unsigned long *)regs->rsp;
if (sp[0] >> 22)
return sp[0];
if (sp[1] >> 22)
return sp[1];
}
return pc;
}
EXPORT_SYMBOL(profile_pc);
/*
* In order to set the CMOS clock precisely, set_rtc_mmss has to be called 500
* ms after the second nowtime has started, because when nowtime is written
* into the registers of the CMOS clock, it will jump to the next second
* precisely 500 ms later. Check the Motorola MC146818A or Dallas DS12887 data
* sheet for details.
*/
static void set_rtc_mmss(unsigned long nowtime)
{
int real_seconds, real_minutes, cmos_minutes;
unsigned char control, freq_select;
/*
* IRQs are disabled when we're called from the timer interrupt,
* no need for spin_lock_irqsave()
*/
spin_lock(&rtc_lock);
/*
* Tell the clock it's being set and stop it.
*/
control = CMOS_READ(RTC_CONTROL);
CMOS_WRITE(control | RTC_SET, RTC_CONTROL);
freq_select = CMOS_READ(RTC_FREQ_SELECT);
CMOS_WRITE(freq_select | RTC_DIV_RESET2, RTC_FREQ_SELECT);
cmos_minutes = CMOS_READ(RTC_MINUTES);
BCD_TO_BIN(cmos_minutes);
/*
* since we're only adjusting minutes and seconds, don't interfere with hour
* overflow. This avoids messing with unknown time zones but requires your RTC
* not to be off by more than 15 minutes. Since we're calling it only when
* our clock is externally synchronized using NTP, this shouldn't be a problem.
*/
real_seconds = nowtime % 60;
real_minutes = nowtime / 60;
if (((abs(real_minutes - cmos_minutes) + 15) / 30) & 1)
real_minutes += 30; /* correct for half hour time zone */
real_minutes %= 60;
if (abs(real_minutes - cmos_minutes) >= 30) {
printk(KERN_WARNING "time.c: can't update CMOS clock "
"from %d to %d\n", cmos_minutes, real_minutes);
} else {
BIN_TO_BCD(real_seconds);
BIN_TO_BCD(real_minutes);
CMOS_WRITE(real_seconds, RTC_SECONDS);
CMOS_WRITE(real_minutes, RTC_MINUTES);
}
/*
* The following flags have to be released exactly in this order, otherwise the
* DS12887 (popular MC146818A clone with integrated battery and quartz) will
* not reset the oscillator and will not update precisely 500 ms later. You
* won't find this mentioned in the Dallas Semiconductor data sheets, but who
* believes data sheets anyway ... -- Markus Kuhn
*/
CMOS_WRITE(control, RTC_CONTROL);
CMOS_WRITE(freq_select, RTC_FREQ_SELECT);
spin_unlock(&rtc_lock);
}
/* monotonic_clock(): returns # of nanoseconds passed since time_init()
* Note: This function is required to return accurate
* time even in the absence of multiple timer ticks.
*/
extern unsigned long long cycles_2_ns(unsigned long long cyc);
unsigned long long monotonic_clock(void)
{
unsigned long seq;
u32 last_offset, this_offset, offset;
unsigned long long base;
if (vxtime.mode == VXTIME_HPET) {
do {
seq = read_seqbegin(&xtime_lock);
last_offset = vxtime.last;
base = monotonic_base;
this_offset = hpet_readl(HPET_COUNTER);
} while (read_seqretry(&xtime_lock, seq));
offset = (this_offset - last_offset);
offset *= NSEC_PER_TICK / hpet_tick;
} else {
do {
seq = read_seqbegin(&xtime_lock);
last_offset = vxtime.last_tsc;
base = monotonic_base;
} while (read_seqretry(&xtime_lock, seq));
this_offset = get_cycles_sync();
offset = cycles_2_ns(this_offset - last_offset);
}
return base + offset;
}
EXPORT_SYMBOL(monotonic_clock);
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 13:55:46 +00:00
static noinline void handle_lost_ticks(int lost)
{
static long lost_count;
static int warned;
if (report_lost_ticks) {
printk(KERN_WARNING "time.c: Lost %d timer tick(s)! ", lost);
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 13:55:46 +00:00
print_symbol("rip %s)\n", get_irq_regs()->rip);
}
if (lost_count == 1000 && !warned) {
printk(KERN_WARNING "warning: many lost ticks.\n"
KERN_WARNING "Your time source seems to be instable or "
"some driver is hogging interupts\n");
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 13:55:46 +00:00
print_symbol("rip %s\n", get_irq_regs()->rip);
if (vxtime.mode == VXTIME_TSC && hpet_address) {
printk(KERN_WARNING "Falling back to HPET\n");
if (hpet_use_timer)
vxtime.last = hpet_readl(HPET_T0_CMP) -
hpet_tick;
else
vxtime.last = hpet_readl(HPET_COUNTER);
vxtime.mode = VXTIME_HPET;
vxtime.hpet_address = hpet_address;
do_gettimeoffset = do_gettimeoffset_hpet;
}
/* else should fall back to PIT, but code missing. */
warned = 1;
} else
lost_count++;
#ifdef CONFIG_CPU_FREQ
/* In some cases the CPU can change frequency without us noticing
Give cpufreq a change to catch up. */
if ((lost_count+1) % 25 == 0)
cpufreq_delayed_get();
#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 13:55:46 +00:00
void main_timer_handler(void)
{
static unsigned long rtc_update = 0;
unsigned long tsc;
int delay = 0, offset = 0, lost = 0;
/*
* Here we are in the timer irq handler. We have irqs locally disabled (so we
* don't need spin_lock_irqsave()) but we don't know if the timer_bh is running
* on the other CPU, so we need a lock. We also need to lock the vsyscall
* variables, because both do_timer() and us change them -arca+vojtech
*/
write_seqlock(&xtime_lock);
if (hpet_address)
offset = hpet_readl(HPET_COUNTER);
if (hpet_use_timer) {
/* if we're using the hpet timer functionality,
* we can more accurately know the counter value
* when the timer interrupt occured.
*/
offset = hpet_readl(HPET_T0_CMP) - hpet_tick;
delay = hpet_readl(HPET_COUNTER) - offset;
} else if (!pmtmr_ioport) {
spin_lock(&i8253_lock);
outb_p(0x00, 0x43);
delay = inb_p(0x40);
delay |= inb(0x40) << 8;
spin_unlock(&i8253_lock);
delay = LATCH - 1 - delay;
}
tsc = get_cycles_sync();
if (vxtime.mode == VXTIME_HPET) {
if (offset - vxtime.last > hpet_tick) {
lost = (offset - vxtime.last) / hpet_tick - 1;
}
monotonic_base +=
(offset - vxtime.last) * NSEC_PER_TICK / hpet_tick;
vxtime.last = offset;
#ifdef CONFIG_X86_PM_TIMER
} else if (vxtime.mode == VXTIME_PMTMR) {
lost = pmtimer_mark_offset();
#endif
} else {
offset = (((tsc - vxtime.last_tsc) *
vxtime.tsc_quot) >> US_SCALE) - USEC_PER_TICK;
if (offset < 0)
offset = 0;
if (offset > USEC_PER_TICK) {
lost = offset / USEC_PER_TICK;
offset %= USEC_PER_TICK;
}
monotonic_base += cycles_2_ns(tsc - vxtime.last_tsc);
vxtime.last_tsc = tsc - vxtime.quot * delay / vxtime.tsc_quot;
if ((((tsc - vxtime.last_tsc) *
vxtime.tsc_quot) >> US_SCALE) < offset)
vxtime.last_tsc = tsc -
(((long) offset << US_SCALE) / vxtime.tsc_quot) - 1;
}
[PATCH] simplify update_times (avoid jiffies/jiffies_64 aliasing problem) Pass ticks to do_timer() and update_times(), and adjust x86_64 and s390 timer interrupt handler with this change. Currently update_times() calculates ticks by "jiffies - wall_jiffies", but callers of do_timer() should know how many ticks to update. Passing ticks get rid of this redundant calculation. Also there are another redundancy pointed out by Martin Schwidefsky. This cleanup make a barrier added by 5aee405c662ca644980c184774277fc6d0769a84 needless. So this patch removes it. As a bonus, this cleanup make wall_jiffies can be removed easily, since now wall_jiffies is always synced with jiffies. (This patch does not really remove wall_jiffies. It would be another cleanup patch) Signed-off-by: Atsushi Nemoto <anemo@mba.ocn.ne.jp> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: john stultz <johnstul@us.ibm.com> Cc: Andi Kleen <ak@muc.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Acked-by: Russell King <rmk@arm.linux.org.uk> Cc: Ian Molton <spyro@f2s.com> Cc: Mikael Starvik <starvik@axis.com> Acked-by: David Howells <dhowells@redhat.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: Hirokazu Takata <takata.hirokazu@renesas.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp> Cc: Richard Curnow <rc@rc0.org.uk> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Cc: Miles Bader <uclinux-v850@lsi.nec.co.jp> Cc: Chris Zankel <chris@zankel.net> Acked-by: "Luck, Tony" <tony.luck@intel.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Roman Zippel <zippel@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-29 09:00:32 +00:00
if (lost > 0)
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 13:55:46 +00:00
handle_lost_ticks(lost);
[PATCH] simplify update_times (avoid jiffies/jiffies_64 aliasing problem) Pass ticks to do_timer() and update_times(), and adjust x86_64 and s390 timer interrupt handler with this change. Currently update_times() calculates ticks by "jiffies - wall_jiffies", but callers of do_timer() should know how many ticks to update. Passing ticks get rid of this redundant calculation. Also there are another redundancy pointed out by Martin Schwidefsky. This cleanup make a barrier added by 5aee405c662ca644980c184774277fc6d0769a84 needless. So this patch removes it. As a bonus, this cleanup make wall_jiffies can be removed easily, since now wall_jiffies is always synced with jiffies. (This patch does not really remove wall_jiffies. It would be another cleanup patch) Signed-off-by: Atsushi Nemoto <anemo@mba.ocn.ne.jp> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: john stultz <johnstul@us.ibm.com> Cc: Andi Kleen <ak@muc.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Acked-by: Russell King <rmk@arm.linux.org.uk> Cc: Ian Molton <spyro@f2s.com> Cc: Mikael Starvik <starvik@axis.com> Acked-by: David Howells <dhowells@redhat.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: Hirokazu Takata <takata.hirokazu@renesas.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp> Cc: Richard Curnow <rc@rc0.org.uk> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Cc: Miles Bader <uclinux-v850@lsi.nec.co.jp> Cc: Chris Zankel <chris@zankel.net> Acked-by: "Luck, Tony" <tony.luck@intel.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Roman Zippel <zippel@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-29 09:00:32 +00:00
else
lost = 0;
/*
* Do the timer stuff.
*/
[PATCH] simplify update_times (avoid jiffies/jiffies_64 aliasing problem) Pass ticks to do_timer() and update_times(), and adjust x86_64 and s390 timer interrupt handler with this change. Currently update_times() calculates ticks by "jiffies - wall_jiffies", but callers of do_timer() should know how many ticks to update. Passing ticks get rid of this redundant calculation. Also there are another redundancy pointed out by Martin Schwidefsky. This cleanup make a barrier added by 5aee405c662ca644980c184774277fc6d0769a84 needless. So this patch removes it. As a bonus, this cleanup make wall_jiffies can be removed easily, since now wall_jiffies is always synced with jiffies. (This patch does not really remove wall_jiffies. It would be another cleanup patch) Signed-off-by: Atsushi Nemoto <anemo@mba.ocn.ne.jp> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: john stultz <johnstul@us.ibm.com> Cc: Andi Kleen <ak@muc.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Acked-by: Russell King <rmk@arm.linux.org.uk> Cc: Ian Molton <spyro@f2s.com> Cc: Mikael Starvik <starvik@axis.com> Acked-by: David Howells <dhowells@redhat.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: Hirokazu Takata <takata.hirokazu@renesas.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp> Cc: Richard Curnow <rc@rc0.org.uk> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Cc: Miles Bader <uclinux-v850@lsi.nec.co.jp> Cc: Chris Zankel <chris@zankel.net> Acked-by: "Luck, Tony" <tony.luck@intel.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Roman Zippel <zippel@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-29 09:00:32 +00:00
do_timer(lost + 1);
#ifndef CONFIG_SMP
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 13:55:46 +00:00
update_process_times(user_mode(get_irq_regs()));
#endif
/*
* In the SMP case we use the local APIC timer interrupt to do the profiling,
* except when we simulate SMP mode on a uniprocessor system, in that case we
* have to call the local interrupt handler.
*/
if (!using_apic_timer)
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 13:55:46 +00:00
smp_local_timer_interrupt();
/*
* If we have an externally synchronized Linux clock, then update CMOS clock
* accordingly every ~11 minutes. set_rtc_mmss() will be called in the jiffy
* closest to exactly 500 ms before the next second. If the update fails, we
* don't care, as it'll be updated on the next turn, and the problem (time way
* off) isn't likely to go away much sooner anyway.
*/
if (ntp_synced() && xtime.tv_sec > rtc_update &&
abs(xtime.tv_nsec - 500000000) <= tick_nsec / 2) {
set_rtc_mmss(xtime.tv_sec);
rtc_update = xtime.tv_sec + 660;
}
write_sequnlock(&xtime_lock);
}
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 13:55:46 +00:00
static irqreturn_t timer_interrupt(int irq, void *dev_id)
{
if (apic_runs_main_timer > 1)
return IRQ_HANDLED;
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 13:55:46 +00:00
main_timer_handler();
if (using_apic_timer)
smp_send_timer_broadcast_ipi();
return IRQ_HANDLED;
}
static unsigned long get_cmos_time(void)
{
unsigned int year, mon, day, hour, min, sec;
unsigned long flags;
unsigned century = 0;
spin_lock_irqsave(&rtc_lock, flags);
do {
sec = CMOS_READ(RTC_SECONDS);
min = CMOS_READ(RTC_MINUTES);
hour = CMOS_READ(RTC_HOURS);
day = CMOS_READ(RTC_DAY_OF_MONTH);
mon = CMOS_READ(RTC_MONTH);
year = CMOS_READ(RTC_YEAR);
#ifdef CONFIG_ACPI
if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID &&
acpi_gbl_FADT.century)
century = CMOS_READ(acpi_gbl_FADT.century);
#endif
} while (sec != CMOS_READ(RTC_SECONDS));
spin_unlock_irqrestore(&rtc_lock, flags);
/*
* We know that x86-64 always uses BCD format, no need to check the
* config register.
*/
BCD_TO_BIN(sec);
BCD_TO_BIN(min);
BCD_TO_BIN(hour);
BCD_TO_BIN(day);
BCD_TO_BIN(mon);
BCD_TO_BIN(year);
if (century) {
BCD_TO_BIN(century);
year += century * 100;
printk(KERN_INFO "Extended CMOS year: %d\n", century * 100);
} else {
/*
* x86-64 systems only exists since 2002.
* This will work up to Dec 31, 2100
*/
year += 2000;
}
return mktime(year, mon, day, hour, min, sec);
}
/*
* pit_calibrate_tsc() uses the speaker output (channel 2) of
* the PIT. This is better than using the timer interrupt output,
* because we can read the value of the speaker with just one inb(),
* where we need three i/o operations for the interrupt channel.
* We count how many ticks the TSC does in 50 ms.
*/
static unsigned int __init pit_calibrate_tsc(void)
{
unsigned long start, end;
unsigned long flags;
spin_lock_irqsave(&i8253_lock, flags);
outb((inb(0x61) & ~0x02) | 0x01, 0x61);
outb(0xb0, 0x43);
outb((PIT_TICK_RATE / (1000 / 50)) & 0xff, 0x42);
outb((PIT_TICK_RATE / (1000 / 50)) >> 8, 0x42);
start = get_cycles_sync();
while ((inb(0x61) & 0x20) == 0);
end = get_cycles_sync();
spin_unlock_irqrestore(&i8253_lock, flags);
return (end - start) / 50;
}
#define PIT_MODE 0x43
#define PIT_CH0 0x40
static void __init __pit_init(int val, u8 mode)
{
unsigned long flags;
spin_lock_irqsave(&i8253_lock, flags);
outb_p(mode, PIT_MODE);
outb_p(val & 0xff, PIT_CH0); /* LSB */
outb_p(val >> 8, PIT_CH0); /* MSB */
spin_unlock_irqrestore(&i8253_lock, flags);
}
void __init pit_init(void)
{
__pit_init(LATCH, 0x34); /* binary, mode 2, LSB/MSB, ch 0 */
}
void __init pit_stop_interrupt(void)
{
__pit_init(0, 0x30); /* mode 0 */
}
void __init stop_timer_interrupt(void)
{
char *name;
if (hpet_address) {
name = "HPET";
hpet_timer_stop_set_go(0);
} else {
name = "PIT";
pit_stop_interrupt();
}
printk(KERN_INFO "timer: %s interrupt stopped.\n", name);
}
int __init time_setup(char *str)
{
report_lost_ticks = 1;
return 1;
}
static struct irqaction irq0 = {
timer_interrupt, IRQF_DISABLED, CPU_MASK_NONE, "timer", NULL, NULL
};
void __init time_init(void)
{
if (nohpet)
hpet_address = 0;
xtime.tv_sec = get_cmos_time();
xtime.tv_nsec = 0;
set_normalized_timespec(&wall_to_monotonic,
-xtime.tv_sec, -xtime.tv_nsec);
if (!hpet_arch_init())
vxtime_hz = (FSEC_PER_SEC + hpet_period / 2) / hpet_period;
else
hpet_address = 0;
if (hpet_use_timer) {
/* set tick_nsec to use the proper rate for HPET */
tick_nsec = TICK_NSEC_HPET;
cpu_khz = hpet_calibrate_tsc();
timename = "HPET";
#ifdef CONFIG_X86_PM_TIMER
} else if (pmtmr_ioport && !hpet_address) {
vxtime_hz = PM_TIMER_FREQUENCY;
timename = "PM";
pit_init();
cpu_khz = pit_calibrate_tsc();
#endif
} else {
pit_init();
cpu_khz = pit_calibrate_tsc();
timename = "PIT";
}
vxtime.mode = VXTIME_TSC;
vxtime.quot = (USEC_PER_SEC << US_SCALE) / vxtime_hz;
vxtime.tsc_quot = (USEC_PER_MSEC << US_SCALE) / cpu_khz;
vxtime.last_tsc = get_cycles_sync();
set_cyc2ns_scale(cpu_khz);
setup_irq(0, &irq0);
#ifndef CONFIG_SMP
time_init_gtod();
#endif
}
/*
* Decide what mode gettimeofday should use.
*/
void time_init_gtod(void)
{
char *timetype;
if (unsynchronized_tsc())
notsc = 1;
if (cpu_has(&boot_cpu_data, X86_FEATURE_RDTSCP))
vgetcpu_mode = VGETCPU_RDTSCP;
else
vgetcpu_mode = VGETCPU_LSL;
if (hpet_address && notsc) {
timetype = hpet_use_timer ? "HPET" : "PIT/HPET";
if (hpet_use_timer)
vxtime.last = hpet_readl(HPET_T0_CMP) - hpet_tick;
else
vxtime.last = hpet_readl(HPET_COUNTER);
vxtime.mode = VXTIME_HPET;
vxtime.hpet_address = hpet_address;
do_gettimeoffset = do_gettimeoffset_hpet;
#ifdef CONFIG_X86_PM_TIMER
/* Using PM for gettimeofday is quite slow, but we have no other
choice because the TSC is too unreliable on some systems. */
} else if (pmtmr_ioport && !hpet_address && notsc) {
timetype = "PM";
do_gettimeoffset = do_gettimeoffset_pm;
vxtime.mode = VXTIME_PMTMR;
sysctl_vsyscall = 0;
printk(KERN_INFO "Disabling vsyscall due to use of PM timer\n");
#endif
} else {
timetype = hpet_use_timer ? "HPET/TSC" : "PIT/TSC";
vxtime.mode = VXTIME_TSC;
}
printk(KERN_INFO "time.c: Using %ld.%06ld MHz WALL %s GTOD %s timer.\n",
vxtime_hz / 1000000, vxtime_hz % 1000000, timename, timetype);
printk(KERN_INFO "time.c: Detected %d.%03d MHz processor.\n",
cpu_khz / 1000, cpu_khz % 1000);
vxtime.quot = (USEC_PER_SEC << US_SCALE) / vxtime_hz;
vxtime.tsc_quot = (USEC_PER_MSEC << US_SCALE) / cpu_khz;
vxtime.last_tsc = get_cycles_sync();
set_cyc2ns_scale(cpu_khz);
}
__setup("report_lost_ticks", time_setup);
static long clock_cmos_diff;
static unsigned long sleep_start;
/*
* sysfs support for the timer.
*/
static int timer_suspend(struct sys_device *dev, pm_message_t state)
{
/*
* Estimate time zone so that set_time can update the clock
*/
long cmos_time = get_cmos_time();
clock_cmos_diff = -cmos_time;
clock_cmos_diff += get_seconds();
sleep_start = cmos_time;
return 0;
}
static int timer_resume(struct sys_device *dev)
{
unsigned long flags;
unsigned long sec;
unsigned long ctime = get_cmos_time();
long sleep_length = (ctime - sleep_start) * HZ;
if (sleep_length < 0) {
printk(KERN_WARNING "Time skew detected in timer resume!\n");
/* The time after the resume must not be earlier than the time
* before the suspend or some nasty things will happen
*/
sleep_length = 0;
ctime = sleep_start;
}
if (hpet_address)
hpet_reenable();
else
i8254_timer_resume();
sec = ctime + clock_cmos_diff;
write_seqlock_irqsave(&xtime_lock,flags);
xtime.tv_sec = sec;
xtime.tv_nsec = 0;
if (vxtime.mode == VXTIME_HPET) {
if (hpet_use_timer)
vxtime.last = hpet_readl(HPET_T0_CMP) - hpet_tick;
else
vxtime.last = hpet_readl(HPET_COUNTER);
#ifdef CONFIG_X86_PM_TIMER
} else if (vxtime.mode == VXTIME_PMTMR) {
pmtimer_resume();
#endif
} else
vxtime.last_tsc = get_cycles_sync();
write_sequnlock_irqrestore(&xtime_lock,flags);
jiffies += sleep_length;
monotonic_base += sleep_length * (NSEC_PER_SEC/HZ);
touch_softlockup_watchdog();
return 0;
}
static struct sysdev_class timer_sysclass = {
.resume = timer_resume,
.suspend = timer_suspend,
set_kset_name("timer"),
};
/* XXX this driverfs stuff should probably go elsewhere later -john */
static struct sys_device device_timer = {
.id = 0,
.cls = &timer_sysclass,
};
static int time_init_device(void)
{
int error = sysdev_class_register(&timer_sysclass);
if (!error)
error = sysdev_register(&device_timer);
return error;
}
device_initcall(time_init_device);