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>
230 lines
4.8 KiB
C
230 lines
4.8 KiB
C
/* CPU control.
|
|
* (C) 2001, 2002, 2003, 2004 Rusty Russell
|
|
*
|
|
* This code is licenced under the GPL.
|
|
*/
|
|
#include <linux/proc_fs.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/init.h>
|
|
#include <linux/notifier.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/unistd.h>
|
|
#include <linux/cpu.h>
|
|
#include <linux/module.h>
|
|
#include <linux/kthread.h>
|
|
#include <linux/stop_machine.h>
|
|
#include <asm/semaphore.h>
|
|
|
|
/* This protects CPUs going up and down... */
|
|
static DECLARE_MUTEX(cpucontrol);
|
|
|
|
static BLOCKING_NOTIFIER_HEAD(cpu_chain);
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
static struct task_struct *lock_cpu_hotplug_owner;
|
|
static int lock_cpu_hotplug_depth;
|
|
|
|
static int __lock_cpu_hotplug(int interruptible)
|
|
{
|
|
int ret = 0;
|
|
|
|
if (lock_cpu_hotplug_owner != current) {
|
|
if (interruptible)
|
|
ret = down_interruptible(&cpucontrol);
|
|
else
|
|
down(&cpucontrol);
|
|
}
|
|
|
|
/*
|
|
* Set only if we succeed in locking
|
|
*/
|
|
if (!ret) {
|
|
lock_cpu_hotplug_depth++;
|
|
lock_cpu_hotplug_owner = current;
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
void lock_cpu_hotplug(void)
|
|
{
|
|
__lock_cpu_hotplug(0);
|
|
}
|
|
EXPORT_SYMBOL_GPL(lock_cpu_hotplug);
|
|
|
|
void unlock_cpu_hotplug(void)
|
|
{
|
|
if (--lock_cpu_hotplug_depth == 0) {
|
|
lock_cpu_hotplug_owner = NULL;
|
|
up(&cpucontrol);
|
|
}
|
|
}
|
|
EXPORT_SYMBOL_GPL(unlock_cpu_hotplug);
|
|
|
|
int lock_cpu_hotplug_interruptible(void)
|
|
{
|
|
return __lock_cpu_hotplug(1);
|
|
}
|
|
EXPORT_SYMBOL_GPL(lock_cpu_hotplug_interruptible);
|
|
#endif /* CONFIG_HOTPLUG_CPU */
|
|
|
|
/* Need to know about CPUs going up/down? */
|
|
int register_cpu_notifier(struct notifier_block *nb)
|
|
{
|
|
return blocking_notifier_chain_register(&cpu_chain, nb);
|
|
}
|
|
EXPORT_SYMBOL(register_cpu_notifier);
|
|
|
|
void unregister_cpu_notifier(struct notifier_block *nb)
|
|
{
|
|
blocking_notifier_chain_unregister(&cpu_chain, nb);
|
|
}
|
|
EXPORT_SYMBOL(unregister_cpu_notifier);
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
static inline void check_for_tasks(int cpu)
|
|
{
|
|
struct task_struct *p;
|
|
|
|
write_lock_irq(&tasklist_lock);
|
|
for_each_process(p) {
|
|
if (task_cpu(p) == cpu &&
|
|
(!cputime_eq(p->utime, cputime_zero) ||
|
|
!cputime_eq(p->stime, cputime_zero)))
|
|
printk(KERN_WARNING "Task %s (pid = %d) is on cpu %d\
|
|
(state = %ld, flags = %lx) \n",
|
|
p->comm, p->pid, cpu, p->state, p->flags);
|
|
}
|
|
write_unlock_irq(&tasklist_lock);
|
|
}
|
|
|
|
/* Take this CPU down. */
|
|
static int take_cpu_down(void *unused)
|
|
{
|
|
int err;
|
|
|
|
/* Ensure this CPU doesn't handle any more interrupts. */
|
|
err = __cpu_disable();
|
|
if (err < 0)
|
|
return err;
|
|
|
|
/* Force idle task to run as soon as we yield: it should
|
|
immediately notice cpu is offline and die quickly. */
|
|
sched_idle_next();
|
|
return 0;
|
|
}
|
|
|
|
int cpu_down(unsigned int cpu)
|
|
{
|
|
int err;
|
|
struct task_struct *p;
|
|
cpumask_t old_allowed, tmp;
|
|
|
|
if ((err = lock_cpu_hotplug_interruptible()) != 0)
|
|
return err;
|
|
|
|
if (num_online_cpus() == 1) {
|
|
err = -EBUSY;
|
|
goto out;
|
|
}
|
|
|
|
if (!cpu_online(cpu)) {
|
|
err = -EINVAL;
|
|
goto out;
|
|
}
|
|
|
|
err = blocking_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE,
|
|
(void *)(long)cpu);
|
|
if (err == NOTIFY_BAD) {
|
|
printk("%s: attempt to take down CPU %u failed\n",
|
|
__FUNCTION__, cpu);
|
|
err = -EINVAL;
|
|
goto out;
|
|
}
|
|
|
|
/* Ensure that we are not runnable on dying cpu */
|
|
old_allowed = current->cpus_allowed;
|
|
tmp = CPU_MASK_ALL;
|
|
cpu_clear(cpu, tmp);
|
|
set_cpus_allowed(current, tmp);
|
|
|
|
p = __stop_machine_run(take_cpu_down, NULL, cpu);
|
|
if (IS_ERR(p)) {
|
|
/* CPU didn't die: tell everyone. Can't complain. */
|
|
if (blocking_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED,
|
|
(void *)(long)cpu) == NOTIFY_BAD)
|
|
BUG();
|
|
|
|
err = PTR_ERR(p);
|
|
goto out_allowed;
|
|
}
|
|
|
|
if (cpu_online(cpu))
|
|
goto out_thread;
|
|
|
|
/* Wait for it to sleep (leaving idle task). */
|
|
while (!idle_cpu(cpu))
|
|
yield();
|
|
|
|
/* This actually kills the CPU. */
|
|
__cpu_die(cpu);
|
|
|
|
/* Move it here so it can run. */
|
|
kthread_bind(p, get_cpu());
|
|
put_cpu();
|
|
|
|
/* CPU is completely dead: tell everyone. Too late to complain. */
|
|
if (blocking_notifier_call_chain(&cpu_chain, CPU_DEAD,
|
|
(void *)(long)cpu) == NOTIFY_BAD)
|
|
BUG();
|
|
|
|
check_for_tasks(cpu);
|
|
|
|
out_thread:
|
|
err = kthread_stop(p);
|
|
out_allowed:
|
|
set_cpus_allowed(current, old_allowed);
|
|
out:
|
|
unlock_cpu_hotplug();
|
|
return err;
|
|
}
|
|
#endif /*CONFIG_HOTPLUG_CPU*/
|
|
|
|
int __devinit cpu_up(unsigned int cpu)
|
|
{
|
|
int ret;
|
|
void *hcpu = (void *)(long)cpu;
|
|
|
|
if ((ret = lock_cpu_hotplug_interruptible()) != 0)
|
|
return ret;
|
|
|
|
if (cpu_online(cpu) || !cpu_present(cpu)) {
|
|
ret = -EINVAL;
|
|
goto out;
|
|
}
|
|
|
|
ret = blocking_notifier_call_chain(&cpu_chain, CPU_UP_PREPARE, hcpu);
|
|
if (ret == NOTIFY_BAD) {
|
|
printk("%s: attempt to bring up CPU %u failed\n",
|
|
__FUNCTION__, cpu);
|
|
ret = -EINVAL;
|
|
goto out_notify;
|
|
}
|
|
|
|
/* Arch-specific enabling code. */
|
|
ret = __cpu_up(cpu);
|
|
if (ret != 0)
|
|
goto out_notify;
|
|
BUG_ON(!cpu_online(cpu));
|
|
|
|
/* Now call notifier in preparation. */
|
|
blocking_notifier_call_chain(&cpu_chain, CPU_ONLINE, hcpu);
|
|
|
|
out_notify:
|
|
if (ret != 0)
|
|
blocking_notifier_call_chain(&cpu_chain,
|
|
CPU_UP_CANCELED, hcpu);
|
|
out:
|
|
unlock_cpu_hotplug();
|
|
return ret;
|
|
}
|