OpenCloudOS-Kernel/kernel/cpu.c

326 lines
7.0 KiB
C
Raw Normal View History

/* 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 <linux/mutex.h>
/* This protects CPUs going up and down... */
static DEFINE_MUTEX(cpu_add_remove_lock);
static DEFINE_MUTEX(cpu_bitmask_lock);
static __cpuinitdata RAW_NOTIFIER_HEAD(cpu_chain);
/* If set, cpu_up and cpu_down will return -EBUSY and do nothing.
* Should always be manipulated under cpu_add_remove_lock
*/
static int cpu_hotplug_disabled;
#ifdef CONFIG_HOTPLUG_CPU
/* Crappy recursive lock-takers in cpufreq! Complain loudly about idiots */
static struct task_struct *recursive;
static int recursive_depth;
void lock_cpu_hotplug(void)
{
struct task_struct *tsk = current;
if (tsk == recursive) {
static int warnings = 10;
if (warnings) {
printk(KERN_ERR "Lukewarm IQ detected in hotplug locking\n");
WARN_ON(1);
warnings--;
}
recursive_depth++;
return;
}
mutex_lock(&cpu_bitmask_lock);
recursive = tsk;
}
EXPORT_SYMBOL_GPL(lock_cpu_hotplug);
void unlock_cpu_hotplug(void)
{
WARN_ON(recursive != current);
if (recursive_depth) {
recursive_depth--;
return;
}
recursive = NULL;
mutex_unlock(&cpu_bitmask_lock);
}
EXPORT_SYMBOL_GPL(unlock_cpu_hotplug);
#endif /* CONFIG_HOTPLUG_CPU */
/* Need to know about CPUs going up/down? */
int __cpuinit register_cpu_notifier(struct notifier_block *nb)
{
int ret;
mutex_lock(&cpu_add_remove_lock);
ret = raw_notifier_chain_register(&cpu_chain, nb);
mutex_unlock(&cpu_add_remove_lock);
return ret;
}
#ifdef CONFIG_HOTPLUG_CPU
EXPORT_SYMBOL(register_cpu_notifier);
void unregister_cpu_notifier(struct notifier_block *nb)
{
mutex_lock(&cpu_add_remove_lock);
raw_notifier_chain_unregister(&cpu_chain, nb);
mutex_unlock(&cpu_add_remove_lock);
}
EXPORT_SYMBOL(unregister_cpu_notifier);
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)
[PATCH] i386 CPU hotplug (The i386 CPU hotplug patch provides infrastructure for some work which Pavel is doing as well as for ACPI S3 (suspend-to-RAM) work which Li Shaohua <shaohua.li@intel.com> is doing) The following provides i386 architecture support for safely unregistering and registering processors during runtime, updated for the current -mm tree. In order to avoid dumping cpu hotplug code into kernel/irq/* i dropped the cpu_online check in do_IRQ() by modifying fixup_irqs(). The difference being that on cpu offline, fixup_irqs() is called before we clear the cpu from cpu_online_map and a long delay in order to ensure that we never have any queued external interrupts on the APICs. There are additional changes to s390 and ppc64 to account for this change. 1) Add CONFIG_HOTPLUG_CPU 2) disable local APIC timer on dead cpus. 3) Disable preempt around irq balancing to prevent CPUs going down. 4) Print irq stats for all possible cpus. 5) Debugging check for interrupts on offline cpus. 6) Hacky fixup_irqs() to redirect irqs when cpus go off/online. 7) play_dead() for offline cpus to spin inside. 8) Handle offline cpus set in flush_tlb_others(). 9) Grab lock earlier in smp_call_function() to prevent CPUs going down. 10) Implement __cpu_disable() and __cpu_die(). 11) Enable local interrupts in cpu_enable() after fixup_irqs() 12) Don't fiddle with NMI on dead cpu, but leave intact on other cpus. 13) Program IRQ affinity whilst cpu is still in cpu_online_map on offline. Signed-off-by: Zwane Mwaikambo <zwane@linuxpower.ca> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-26 05:54:50 +08:00
return err;
[PATCH] i386 CPU hotplug (The i386 CPU hotplug patch provides infrastructure for some work which Pavel is doing as well as for ACPI S3 (suspend-to-RAM) work which Li Shaohua <shaohua.li@intel.com> is doing) The following provides i386 architecture support for safely unregistering and registering processors during runtime, updated for the current -mm tree. In order to avoid dumping cpu hotplug code into kernel/irq/* i dropped the cpu_online check in do_IRQ() by modifying fixup_irqs(). The difference being that on cpu offline, fixup_irqs() is called before we clear the cpu from cpu_online_map and a long delay in order to ensure that we never have any queued external interrupts on the APICs. There are additional changes to s390 and ppc64 to account for this change. 1) Add CONFIG_HOTPLUG_CPU 2) disable local APIC timer on dead cpus. 3) Disable preempt around irq balancing to prevent CPUs going down. 4) Print irq stats for all possible cpus. 5) Debugging check for interrupts on offline cpus. 6) Hacky fixup_irqs() to redirect irqs when cpus go off/online. 7) play_dead() for offline cpus to spin inside. 8) Handle offline cpus set in flush_tlb_others(). 9) Grab lock earlier in smp_call_function() to prevent CPUs going down. 10) Implement __cpu_disable() and __cpu_die(). 11) Enable local interrupts in cpu_enable() after fixup_irqs() 12) Don't fiddle with NMI on dead cpu, but leave intact on other cpus. 13) Program IRQ affinity whilst cpu is still in cpu_online_map on offline. Signed-off-by: Zwane Mwaikambo <zwane@linuxpower.ca> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-26 05:54:50 +08:00
/* 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;
}
/* Requires cpu_add_remove_lock to be held */
static int _cpu_down(unsigned int cpu)
{
int err;
struct task_struct *p;
cpumask_t old_allowed, tmp;
if (num_online_cpus() == 1)
return -EBUSY;
if (!cpu_online(cpu))
return -EINVAL;
err = raw_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);
return -EINVAL;
}
/* 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);
mutex_lock(&cpu_bitmask_lock);
p = __stop_machine_run(take_cpu_down, NULL, cpu);
mutex_unlock(&cpu_bitmask_lock);
if (IS_ERR(p) || cpu_online(cpu)) {
/* CPU didn't die: tell everyone. Can't complain. */
if (raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED,
(void *)(long)cpu) == NOTIFY_BAD)
BUG();
if (IS_ERR(p)) {
err = PTR_ERR(p);
goto out_allowed;
}
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 (raw_notifier_call_chain(&cpu_chain, CPU_DEAD,
[PATCH] Notifier chain update: API changes 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>
2006-03-27 17:16:30 +08:00
(void *)(long)cpu) == NOTIFY_BAD)
BUG();
check_for_tasks(cpu);
out_thread:
err = kthread_stop(p);
out_allowed:
set_cpus_allowed(current, old_allowed);
return err;
}
int cpu_down(unsigned int cpu)
{
int err = 0;
mutex_lock(&cpu_add_remove_lock);
if (cpu_hotplug_disabled)
err = -EBUSY;
else
err = _cpu_down(cpu);
mutex_unlock(&cpu_add_remove_lock);
return err;
}
#endif /*CONFIG_HOTPLUG_CPU*/
/* Requires cpu_add_remove_lock to be held */
static int __devinit _cpu_up(unsigned int cpu)
{
int ret;
void *hcpu = (void *)(long)cpu;
if (cpu_online(cpu) || !cpu_present(cpu))
return -EINVAL;
ret = raw_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. */
mutex_lock(&cpu_bitmask_lock);
ret = __cpu_up(cpu);
mutex_unlock(&cpu_bitmask_lock);
if (ret != 0)
goto out_notify;
BUG_ON(!cpu_online(cpu));
/* Now call notifier in preparation. */
raw_notifier_call_chain(&cpu_chain, CPU_ONLINE, hcpu);
out_notify:
if (ret != 0)
raw_notifier_call_chain(&cpu_chain,
[PATCH] Notifier chain update: API changes 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>
2006-03-27 17:16:30 +08:00
CPU_UP_CANCELED, hcpu);
return ret;
}
int __devinit cpu_up(unsigned int cpu)
{
int err = 0;
mutex_lock(&cpu_add_remove_lock);
if (cpu_hotplug_disabled)
err = -EBUSY;
else
err = _cpu_up(cpu);
mutex_unlock(&cpu_add_remove_lock);
return err;
}
#ifdef CONFIG_SUSPEND_SMP
static cpumask_t frozen_cpus;
int disable_nonboot_cpus(void)
{
int cpu, first_cpu, error;
mutex_lock(&cpu_add_remove_lock);
first_cpu = first_cpu(cpu_present_map);
if (!cpu_online(first_cpu)) {
error = _cpu_up(first_cpu);
if (error) {
printk(KERN_ERR "Could not bring CPU%d up.\n",
first_cpu);
goto out;
}
}
/* We take down all of the non-boot CPUs in one shot to avoid races
* with the userspace trying to use the CPU hotplug at the same time
*/
cpus_clear(frozen_cpus);
printk("Disabling non-boot CPUs ...\n");
for_each_online_cpu(cpu) {
if (cpu == first_cpu)
continue;
error = _cpu_down(cpu);
if (!error) {
cpu_set(cpu, frozen_cpus);
printk("CPU%d is down\n", cpu);
} else {
printk(KERN_ERR "Error taking CPU%d down: %d\n",
cpu, error);
break;
}
}
if (!error) {
BUG_ON(num_online_cpus() > 1);
/* Make sure the CPUs won't be enabled by someone else */
cpu_hotplug_disabled = 1;
} else {
printk(KERN_ERR "Non-boot CPUs are not disabled");
}
out:
mutex_unlock(&cpu_add_remove_lock);
return error;
}
void enable_nonboot_cpus(void)
{
int cpu, error;
/* Allow everyone to use the CPU hotplug again */
mutex_lock(&cpu_add_remove_lock);
cpu_hotplug_disabled = 0;
mutex_unlock(&cpu_add_remove_lock);
printk("Enabling non-boot CPUs ...\n");
for_each_cpu_mask(cpu, frozen_cpus) {
error = cpu_up(cpu);
if (!error) {
printk("CPU%d is up\n", cpu);
continue;
}
printk(KERN_WARNING "Error taking CPU%d up: %d\n",
cpu, error);
}
cpus_clear(frozen_cpus);
}
#endif