mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-04 01:49:36 +00:00
![Alan Stern](/assets/img/avatar_default.png)
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>
280 lines
7.2 KiB
C
280 lines
7.2 KiB
C
/*
|
|
* linux/arch/parisc/kernel/power.c
|
|
* HP PARISC soft power switch support driver
|
|
*
|
|
* Copyright (c) 2001-2005 Helge Deller <deller@gmx.de>
|
|
* All rights reserved.
|
|
*
|
|
*
|
|
* Redistribution and use in source and binary forms, with or without
|
|
* modification, are permitted provided that the following conditions
|
|
* are met:
|
|
* 1. Redistributions of source code must retain the above copyright
|
|
* notice, this list of conditions, and the following disclaimer,
|
|
* without modification.
|
|
* 2. The name of the author may not be used to endorse or promote products
|
|
* derived from this software without specific prior written permission.
|
|
*
|
|
* Alternatively, this software may be distributed under the terms of the
|
|
* GNU General Public License ("GPL").
|
|
*
|
|
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
|
|
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
|
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
|
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE FOR
|
|
* ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
|
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
|
|
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
|
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
|
|
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
|
|
*
|
|
*
|
|
*
|
|
* HINT:
|
|
* Support of the soft power switch button may be enabled or disabled at
|
|
* runtime through the "/proc/sys/kernel/power" procfs entry.
|
|
*/
|
|
|
|
#include <linux/config.h>
|
|
#include <linux/module.h>
|
|
#include <linux/init.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/string.h>
|
|
#include <linux/notifier.h>
|
|
#include <linux/reboot.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/workqueue.h>
|
|
|
|
#include <asm/pdc.h>
|
|
#include <asm/io.h>
|
|
#include <asm/led.h>
|
|
#include <asm/uaccess.h>
|
|
|
|
|
|
#ifdef DEBUG
|
|
# define DPRINTK(x...) printk(x)
|
|
#else
|
|
# define DPRINTK(x...)
|
|
#endif
|
|
|
|
|
|
/* filename in /proc which can be used to enable/disable the power switch */
|
|
#define SYSCTL_FILENAME "sys/kernel/power"
|
|
|
|
|
|
#define DIAG_CODE(code) (0x14000000 + ((code)<<5))
|
|
|
|
/* this will go to processor.h or any other place... */
|
|
/* taken from PCXL ERS page 82 */
|
|
#define MFCPU_X(rDiagReg, t_ch, t_th, code) \
|
|
(DIAG_CODE(code) + ((rDiagReg)<<21) + ((t_ch)<<16) + ((t_th)<<0) )
|
|
|
|
#define MTCPU(dr, gr) MFCPU_X(dr, gr, 0, 0x12) /* move value of gr to dr[dr] */
|
|
#define MFCPU_C(dr, gr) MFCPU_X(dr, gr, 0, 0x30) /* for dr0 and dr8 only ! */
|
|
#define MFCPU_T(dr, gr) MFCPU_X(dr, 0, gr, 0xa0) /* all dr except dr0 and dr8 */
|
|
|
|
#define __getDIAG(dr) ( { \
|
|
register unsigned long __res asm("r28");\
|
|
__asm__ __volatile__ ( \
|
|
".word %1\n nop\n" : "=&r" (__res) : "i" (MFCPU_T(dr,28)) \
|
|
); \
|
|
__res; \
|
|
} )
|
|
|
|
|
|
static void deferred_poweroff(void *dummy)
|
|
{
|
|
extern int cad_pid; /* from kernel/sys.c */
|
|
if (kill_proc(cad_pid, SIGINT, 1)) {
|
|
/* just in case killing init process failed */
|
|
machine_power_off();
|
|
}
|
|
}
|
|
|
|
/*
|
|
* This function gets called from interrupt context.
|
|
* As it's called within an interrupt, it wouldn't sync if we don't
|
|
* use schedule_work().
|
|
*/
|
|
|
|
static DECLARE_WORK(poweroff_work, deferred_poweroff, NULL);
|
|
|
|
static void poweroff(void)
|
|
{
|
|
static int powering_off __read_mostly;
|
|
|
|
if (powering_off)
|
|
return;
|
|
|
|
powering_off++;
|
|
schedule_work(&poweroff_work);
|
|
}
|
|
|
|
|
|
/* local time-counter for shutdown */
|
|
static int shutdown_timer __read_mostly;
|
|
|
|
/* check, give feedback and start shutdown after one second */
|
|
static void process_shutdown(void)
|
|
{
|
|
if (shutdown_timer == 0)
|
|
DPRINTK(KERN_INFO "Shutdown requested...\n");
|
|
|
|
shutdown_timer++;
|
|
|
|
/* wait until the button was pressed for 1 second */
|
|
if (shutdown_timer == HZ) {
|
|
#if defined (DEBUG) || defined(CONFIG_CHASSIS_LCD_LED)
|
|
static char msg[] = "Shutting down...";
|
|
#endif
|
|
DPRINTK(KERN_INFO "%s\n", msg);
|
|
lcd_print(msg);
|
|
poweroff();
|
|
}
|
|
}
|
|
|
|
|
|
/* main power switch tasklet struct (scheduled from time.c) */
|
|
DECLARE_TASKLET_DISABLED(power_tasklet, NULL, 0);
|
|
|
|
/* soft power switch enabled/disabled */
|
|
int pwrsw_enabled __read_mostly = 1;
|
|
|
|
/*
|
|
* On gecko style machines (e.g. 712/xx and 715/xx)
|
|
* the power switch status is stored in Bit 0 ("the highest bit")
|
|
* of CPU diagnose register 25.
|
|
*
|
|
*/
|
|
static void gecko_tasklet_func(unsigned long unused)
|
|
{
|
|
if (unlikely(!pwrsw_enabled))
|
|
return;
|
|
|
|
if (__getDIAG(25) & 0x80000000) {
|
|
/* power switch button not pressed or released again */
|
|
/* Warning: Some machines do never reset this DIAG flag! */
|
|
shutdown_timer = 0;
|
|
} else {
|
|
process_shutdown();
|
|
}
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
* Check the power switch status which is read from the
|
|
* real I/O location at soft_power_reg.
|
|
* Bit 31 ("the lowest bit) is the status of the power switch.
|
|
*/
|
|
|
|
static void polling_tasklet_func(unsigned long soft_power_reg)
|
|
{
|
|
unsigned long current_status;
|
|
|
|
if (unlikely(!pwrsw_enabled))
|
|
return;
|
|
|
|
current_status = gsc_readl(soft_power_reg);
|
|
if (current_status & 0x1) {
|
|
/* power switch button not pressed */
|
|
shutdown_timer = 0;
|
|
} else {
|
|
process_shutdown();
|
|
}
|
|
}
|
|
|
|
|
|
/*
|
|
* powerfail interruption handler (irq IRQ_FROM_REGION(CPU_IRQ_REGION)+2)
|
|
*/
|
|
#if 0
|
|
static void powerfail_interrupt(int code, void *x, struct pt_regs *regs)
|
|
{
|
|
printk(KERN_CRIT "POWERFAIL INTERRUPTION !\n");
|
|
poweroff();
|
|
}
|
|
#endif
|
|
|
|
|
|
|
|
|
|
/* parisc_panic_event() is called by the panic handler.
|
|
* As soon as a panic occurs, our tasklets above will not be
|
|
* executed any longer. This function then re-enables the
|
|
* soft-power switch and allows the user to switch off the system
|
|
*/
|
|
static int parisc_panic_event(struct notifier_block *this,
|
|
unsigned long event, void *ptr)
|
|
{
|
|
/* re-enable the soft-power switch */
|
|
pdc_soft_power_button(0);
|
|
return NOTIFY_DONE;
|
|
}
|
|
|
|
static struct notifier_block parisc_panic_block = {
|
|
.notifier_call = parisc_panic_event,
|
|
.priority = INT_MAX,
|
|
};
|
|
|
|
|
|
static int __init power_init(void)
|
|
{
|
|
unsigned long ret;
|
|
unsigned long soft_power_reg = 0;
|
|
|
|
#if 0
|
|
request_irq( IRQ_FROM_REGION(CPU_IRQ_REGION)+2, &powerfail_interrupt,
|
|
0, "powerfail", NULL);
|
|
#endif
|
|
|
|
/* enable the soft power switch if possible */
|
|
ret = pdc_soft_power_info(&soft_power_reg);
|
|
if (ret == PDC_OK)
|
|
ret = pdc_soft_power_button(1);
|
|
if (ret != PDC_OK)
|
|
soft_power_reg = -1UL;
|
|
|
|
switch (soft_power_reg) {
|
|
case 0: printk(KERN_INFO "Gecko-style soft power switch enabled.\n");
|
|
power_tasklet.func = gecko_tasklet_func;
|
|
break;
|
|
|
|
case -1UL: printk(KERN_INFO "Soft power switch support not available.\n");
|
|
return -ENODEV;
|
|
|
|
default: printk(KERN_INFO "Soft power switch enabled, polling @ 0x%08lx.\n",
|
|
soft_power_reg);
|
|
power_tasklet.data = soft_power_reg;
|
|
power_tasklet.func = polling_tasklet_func;
|
|
}
|
|
|
|
/* Register a call for panic conditions. */
|
|
atomic_notifier_chain_register(&panic_notifier_list,
|
|
&parisc_panic_block);
|
|
|
|
tasklet_enable(&power_tasklet);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void __exit power_exit(void)
|
|
{
|
|
if (!power_tasklet.func)
|
|
return;
|
|
|
|
tasklet_disable(&power_tasklet);
|
|
atomic_notifier_chain_unregister(&panic_notifier_list,
|
|
&parisc_panic_block);
|
|
power_tasklet.func = NULL;
|
|
pdc_soft_power_button(0);
|
|
}
|
|
|
|
module_init(power_init);
|
|
module_exit(power_exit);
|
|
|
|
|
|
MODULE_AUTHOR("Helge Deller");
|
|
MODULE_DESCRIPTION("Soft power switch driver");
|
|
MODULE_LICENSE("Dual BSD/GPL");
|