e041c68341
The kernel's implementation of notifier chains is unsafe. There is no protection against entries being added to or removed from a chain while the chain is in use. The issues were discussed in this thread: http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2 We noticed that notifier chains in the kernel fall into two basic usage classes: "Blocking" chains are always called from a process context and the callout routines are allowed to sleep; "Atomic" chains can be called from an atomic context and the callout routines are not allowed to sleep. We decided to codify this distinction and make it part of the API. Therefore this set of patches introduces three new, parallel APIs: one for blocking notifiers, one for atomic notifiers, and one for "raw" notifiers (which is really just the old API under a new name). New kinds of data structures are used for the heads of the chains, and new routines are defined for registration, unregistration, and calling a chain. The three APIs are explained in include/linux/notifier.h and their implementation is in kernel/sys.c. With atomic and blocking chains, the implementation guarantees that the chain links will not be corrupted and that chain callers will not get messed up by entries being added or removed. For raw chains the implementation provides no guarantees at all; users of this API must provide their own protections. (The idea was that situations may come up where the assumptions of the atomic and blocking APIs are not appropriate, so it should be possible for users to handle these things in their own way.) There are some limitations, which should not be too hard to live with. For atomic/blocking chains, registration and unregistration must always be done in a process context since the chain is protected by a mutex/rwsem. Also, a callout routine for a non-raw chain must not try to register or unregister entries on its own chain. (This did happen in a couple of places and the code had to be changed to avoid it.) Since atomic chains may be called from within an NMI handler, they cannot use spinlocks for synchronization. Instead we use RCU. The overhead falls almost entirely in the unregister routine, which is okay since unregistration is much less frequent that calling a chain. Here is the list of chains that we adjusted and their classifications. None of them use the raw API, so for the moment it is only a placeholder. ATOMIC CHAINS ------------- arch/i386/kernel/traps.c: i386die_chain arch/ia64/kernel/traps.c: ia64die_chain arch/powerpc/kernel/traps.c: powerpc_die_chain arch/sparc64/kernel/traps.c: sparc64die_chain arch/x86_64/kernel/traps.c: die_chain drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list kernel/panic.c: panic_notifier_list kernel/profile.c: task_free_notifier net/bluetooth/hci_core.c: hci_notifier net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain net/ipv6/addrconf.c: inet6addr_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain net/netlink/af_netlink.c: netlink_chain BLOCKING CHAINS --------------- arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain arch/s390/kernel/process.c: idle_chain arch/x86_64/kernel/process.c idle_notifier drivers/base/memory.c: memory_chain drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list drivers/macintosh/adb.c: adb_client_list drivers/macintosh/via-pmu.c sleep_notifier_list drivers/macintosh/via-pmu68k.c sleep_notifier_list drivers/macintosh/windfarm_core.c wf_client_list drivers/usb/core/notify.c usb_notifier_list drivers/video/fbmem.c fb_notifier_list kernel/cpu.c cpu_chain kernel/module.c module_notify_list kernel/profile.c munmap_notifier kernel/profile.c task_exit_notifier kernel/sys.c reboot_notifier_list net/core/dev.c netdev_chain net/decnet/dn_dev.c: dnaddr_chain net/ipv4/devinet.c: inetaddr_chain It's possible that some of these classifications are wrong. If they are, please let us know or submit a patch to fix them. Note that any chain that gets called very frequently should be atomic, because the rwsem read-locking used for blocking chains is very likely to incur cache misses on SMP systems. (However, if the chain's callout routines may sleep then the chain cannot be atomic.) The patch set was written by Alan Stern and Chandra Seetharaman, incorporating material written by Keith Owens and suggestions from Paul McKenney and Andrew Morton. [jes@sgi.com: restructure the notifier chain initialization macros] Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com> Signed-off-by: Jes Sorensen <jes@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
247 lines
6.0 KiB
C
247 lines
6.0 KiB
C
/*
|
|
* This file is subject to the terms and conditions of the GNU General Public
|
|
* License. See the file "COPYING" in the main directory of this archive
|
|
* for more details.
|
|
*
|
|
* Copyright (C) 1997, 1998, 2001, 03, 05, 06 by Ralf Baechle
|
|
*/
|
|
#include <linux/linkage.h>
|
|
#include <linux/init.h>
|
|
#include <linux/ds1286.h>
|
|
#include <linux/module.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/notifier.h>
|
|
#include <linux/pm.h>
|
|
#include <linux/timer.h>
|
|
|
|
#include <asm/io.h>
|
|
#include <asm/irq.h>
|
|
#include <asm/system.h>
|
|
#include <asm/reboot.h>
|
|
#include <asm/sgialib.h>
|
|
#include <asm/sgi/ioc.h>
|
|
#include <asm/sgi/hpc3.h>
|
|
#include <asm/sgi/mc.h>
|
|
#include <asm/sgi/ip22.h>
|
|
|
|
/*
|
|
* Just powerdown if init hasn't done after POWERDOWN_TIMEOUT seconds.
|
|
* I'm not sure if this feature is a good idea, for now it's here just to
|
|
* make the power button make behave just like under IRIX.
|
|
*/
|
|
#define POWERDOWN_TIMEOUT 120
|
|
|
|
/*
|
|
* Blink frequency during reboot grace period and when paniced.
|
|
*/
|
|
#define POWERDOWN_FREQ (HZ / 4)
|
|
#define PANIC_FREQ (HZ / 8)
|
|
|
|
static struct timer_list power_timer, blink_timer, debounce_timer, volume_timer;
|
|
|
|
#define MACHINE_PANICED 1
|
|
#define MACHINE_SHUTTING_DOWN 2
|
|
|
|
static int machine_state;
|
|
|
|
static void ATTRIB_NORET sgi_machine_power_off(void)
|
|
{
|
|
unsigned int tmp;
|
|
|
|
local_irq_disable();
|
|
|
|
/* Disable watchdog */
|
|
tmp = hpc3c0->rtcregs[RTC_CMD] & 0xff;
|
|
hpc3c0->rtcregs[RTC_CMD] = tmp | RTC_WAM;
|
|
hpc3c0->rtcregs[RTC_WSEC] = 0;
|
|
hpc3c0->rtcregs[RTC_WHSEC] = 0;
|
|
|
|
while (1) {
|
|
sgioc->panel = ~SGIOC_PANEL_POWERON;
|
|
/* Good bye cruel world ... */
|
|
|
|
/* If we're still running, we probably got sent an alarm
|
|
interrupt. Read the flag to clear it. */
|
|
tmp = hpc3c0->rtcregs[RTC_HOURS_ALARM];
|
|
}
|
|
}
|
|
|
|
static void ATTRIB_NORET sgi_machine_restart(char *command)
|
|
{
|
|
if (machine_state & MACHINE_SHUTTING_DOWN)
|
|
sgi_machine_power_off();
|
|
sgimc->cpuctrl0 |= SGIMC_CCTRL0_SYSINIT;
|
|
while (1);
|
|
}
|
|
|
|
static void ATTRIB_NORET sgi_machine_halt(void)
|
|
{
|
|
if (machine_state & MACHINE_SHUTTING_DOWN)
|
|
sgi_machine_power_off();
|
|
ArcEnterInteractiveMode();
|
|
}
|
|
|
|
static void power_timeout(unsigned long data)
|
|
{
|
|
sgi_machine_power_off();
|
|
}
|
|
|
|
static void blink_timeout(unsigned long data)
|
|
{
|
|
/* XXX fix this for fullhouse */
|
|
sgi_ioc_reset ^= (SGIOC_RESET_LC0OFF|SGIOC_RESET_LC1OFF);
|
|
sgioc->reset = sgi_ioc_reset;
|
|
|
|
mod_timer(&blink_timer, jiffies + data);
|
|
}
|
|
|
|
static void debounce(unsigned long data)
|
|
{
|
|
del_timer(&debounce_timer);
|
|
if (sgint->istat1 & SGINT_ISTAT1_PWR) {
|
|
/* Interrupt still being sent. */
|
|
debounce_timer.expires = jiffies + (HZ / 20); /* 0.05s */
|
|
add_timer(&debounce_timer);
|
|
|
|
sgioc->panel = SGIOC_PANEL_POWERON | SGIOC_PANEL_POWERINTR |
|
|
SGIOC_PANEL_VOLDNINTR | SGIOC_PANEL_VOLDNHOLD |
|
|
SGIOC_PANEL_VOLUPINTR | SGIOC_PANEL_VOLUPHOLD;
|
|
|
|
return;
|
|
}
|
|
|
|
if (machine_state & MACHINE_PANICED)
|
|
sgimc->cpuctrl0 |= SGIMC_CCTRL0_SYSINIT;
|
|
|
|
enable_irq(SGI_PANEL_IRQ);
|
|
}
|
|
|
|
static inline void power_button(void)
|
|
{
|
|
if (machine_state & MACHINE_PANICED)
|
|
return;
|
|
|
|
if ((machine_state & MACHINE_SHUTTING_DOWN) || kill_proc(1,SIGINT,1)) {
|
|
/* No init process or button pressed twice. */
|
|
sgi_machine_power_off();
|
|
}
|
|
|
|
machine_state |= MACHINE_SHUTTING_DOWN;
|
|
blink_timer.data = POWERDOWN_FREQ;
|
|
blink_timeout(POWERDOWN_FREQ);
|
|
|
|
init_timer(&power_timer);
|
|
power_timer.function = power_timeout;
|
|
power_timer.expires = jiffies + POWERDOWN_TIMEOUT * HZ;
|
|
add_timer(&power_timer);
|
|
}
|
|
|
|
void (*indy_volume_button)(int) = NULL;
|
|
|
|
EXPORT_SYMBOL(indy_volume_button);
|
|
|
|
static inline void volume_up_button(unsigned long data)
|
|
{
|
|
del_timer(&volume_timer);
|
|
|
|
if (indy_volume_button)
|
|
indy_volume_button(1);
|
|
|
|
if (sgint->istat1 & SGINT_ISTAT1_PWR) {
|
|
volume_timer.expires = jiffies + (HZ / 100);
|
|
add_timer(&volume_timer);
|
|
}
|
|
}
|
|
|
|
static inline void volume_down_button(unsigned long data)
|
|
{
|
|
del_timer(&volume_timer);
|
|
|
|
if (indy_volume_button)
|
|
indy_volume_button(-1);
|
|
|
|
if (sgint->istat1 & SGINT_ISTAT1_PWR) {
|
|
volume_timer.expires = jiffies + (HZ / 100);
|
|
add_timer(&volume_timer);
|
|
}
|
|
}
|
|
|
|
static irqreturn_t panel_int(int irq, void *dev_id, struct pt_regs *regs)
|
|
{
|
|
unsigned int buttons;
|
|
|
|
buttons = sgioc->panel;
|
|
sgioc->panel = SGIOC_PANEL_POWERON | SGIOC_PANEL_POWERINTR;
|
|
|
|
if (sgint->istat1 & SGINT_ISTAT1_PWR) {
|
|
/* Wait until interrupt goes away */
|
|
disable_irq(SGI_PANEL_IRQ);
|
|
init_timer(&debounce_timer);
|
|
debounce_timer.function = debounce;
|
|
debounce_timer.expires = jiffies + 5;
|
|
add_timer(&debounce_timer);
|
|
}
|
|
|
|
/* Power button was pressed
|
|
* ioc.ps page 22: "The Panel Register is called Power Control by Full
|
|
* House. Only lowest 2 bits are used. Guiness uses upper four bits
|
|
* for volume control". This is not true, all bits are pulled high
|
|
* on fullhouse */
|
|
if (ip22_is_fullhouse() || !(buttons & SGIOC_PANEL_POWERINTR)) {
|
|
power_button();
|
|
return IRQ_HANDLED;
|
|
}
|
|
/* TODO: mute/unmute */
|
|
/* Volume up button was pressed */
|
|
if (!(buttons & SGIOC_PANEL_VOLUPINTR)) {
|
|
init_timer(&volume_timer);
|
|
volume_timer.function = volume_up_button;
|
|
volume_timer.expires = jiffies + (HZ / 100);
|
|
add_timer(&volume_timer);
|
|
}
|
|
/* Volume down button was pressed */
|
|
if (!(buttons & SGIOC_PANEL_VOLDNINTR)) {
|
|
init_timer(&volume_timer);
|
|
volume_timer.function = volume_down_button;
|
|
volume_timer.expires = jiffies + (HZ / 100);
|
|
add_timer(&volume_timer);
|
|
}
|
|
|
|
return IRQ_HANDLED;
|
|
}
|
|
|
|
static int panic_event(struct notifier_block *this, unsigned long event,
|
|
void *ptr)
|
|
{
|
|
if (machine_state & MACHINE_PANICED)
|
|
return NOTIFY_DONE;
|
|
machine_state |= MACHINE_PANICED;
|
|
|
|
blink_timer.data = PANIC_FREQ;
|
|
blink_timeout(PANIC_FREQ);
|
|
|
|
return NOTIFY_DONE;
|
|
}
|
|
|
|
static struct notifier_block panic_block = {
|
|
.notifier_call = panic_event,
|
|
};
|
|
|
|
static int __init reboot_setup(void)
|
|
{
|
|
_machine_restart = sgi_machine_restart;
|
|
_machine_halt = sgi_machine_halt;
|
|
pm_power_off = sgi_machine_power_off;
|
|
|
|
request_irq(SGI_PANEL_IRQ, panel_int, 0, "Front Panel", NULL);
|
|
init_timer(&blink_timer);
|
|
blink_timer.function = blink_timeout;
|
|
atomic_notifier_chain_register(&panic_notifier_list, &panic_block);
|
|
|
|
return 0;
|
|
}
|
|
|
|
subsys_initcall(reboot_setup);
|