percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
570 lines
14 KiB
C
570 lines
14 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 <linux/mutex.h>
|
|
#include <linux/gfp.h>
|
|
|
|
#ifdef CONFIG_SMP
|
|
/* Serializes the updates to cpu_online_mask, cpu_present_mask */
|
|
static DEFINE_MUTEX(cpu_add_remove_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;
|
|
|
|
static struct {
|
|
struct task_struct *active_writer;
|
|
struct mutex lock; /* Synchronizes accesses to refcount, */
|
|
/*
|
|
* Also blocks the new readers during
|
|
* an ongoing cpu hotplug operation.
|
|
*/
|
|
int refcount;
|
|
} cpu_hotplug = {
|
|
.active_writer = NULL,
|
|
.lock = __MUTEX_INITIALIZER(cpu_hotplug.lock),
|
|
.refcount = 0,
|
|
};
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
|
|
void get_online_cpus(void)
|
|
{
|
|
might_sleep();
|
|
if (cpu_hotplug.active_writer == current)
|
|
return;
|
|
mutex_lock(&cpu_hotplug.lock);
|
|
cpu_hotplug.refcount++;
|
|
mutex_unlock(&cpu_hotplug.lock);
|
|
|
|
}
|
|
EXPORT_SYMBOL_GPL(get_online_cpus);
|
|
|
|
void put_online_cpus(void)
|
|
{
|
|
if (cpu_hotplug.active_writer == current)
|
|
return;
|
|
mutex_lock(&cpu_hotplug.lock);
|
|
if (!--cpu_hotplug.refcount && unlikely(cpu_hotplug.active_writer))
|
|
wake_up_process(cpu_hotplug.active_writer);
|
|
mutex_unlock(&cpu_hotplug.lock);
|
|
|
|
}
|
|
EXPORT_SYMBOL_GPL(put_online_cpus);
|
|
|
|
#endif /* CONFIG_HOTPLUG_CPU */
|
|
|
|
/*
|
|
* The following two API's must be used when attempting
|
|
* to serialize the updates to cpu_online_mask, cpu_present_mask.
|
|
*/
|
|
void cpu_maps_update_begin(void)
|
|
{
|
|
mutex_lock(&cpu_add_remove_lock);
|
|
}
|
|
|
|
void cpu_maps_update_done(void)
|
|
{
|
|
mutex_unlock(&cpu_add_remove_lock);
|
|
}
|
|
|
|
/*
|
|
* This ensures that the hotplug operation can begin only when the
|
|
* refcount goes to zero.
|
|
*
|
|
* Note that during a cpu-hotplug operation, the new readers, if any,
|
|
* will be blocked by the cpu_hotplug.lock
|
|
*
|
|
* Since cpu_hotplug_begin() is always called after invoking
|
|
* cpu_maps_update_begin(), we can be sure that only one writer is active.
|
|
*
|
|
* Note that theoretically, there is a possibility of a livelock:
|
|
* - Refcount goes to zero, last reader wakes up the sleeping
|
|
* writer.
|
|
* - Last reader unlocks the cpu_hotplug.lock.
|
|
* - A new reader arrives at this moment, bumps up the refcount.
|
|
* - The writer acquires the cpu_hotplug.lock finds the refcount
|
|
* non zero and goes to sleep again.
|
|
*
|
|
* However, this is very difficult to achieve in practice since
|
|
* get_online_cpus() not an api which is called all that often.
|
|
*
|
|
*/
|
|
static void cpu_hotplug_begin(void)
|
|
{
|
|
cpu_hotplug.active_writer = current;
|
|
|
|
for (;;) {
|
|
mutex_lock(&cpu_hotplug.lock);
|
|
if (likely(!cpu_hotplug.refcount))
|
|
break;
|
|
__set_current_state(TASK_UNINTERRUPTIBLE);
|
|
mutex_unlock(&cpu_hotplug.lock);
|
|
schedule();
|
|
}
|
|
}
|
|
|
|
static void cpu_hotplug_done(void)
|
|
{
|
|
cpu_hotplug.active_writer = NULL;
|
|
mutex_unlock(&cpu_hotplug.lock);
|
|
}
|
|
/* Need to know about CPUs going up/down? */
|
|
int __ref register_cpu_notifier(struct notifier_block *nb)
|
|
{
|
|
int ret;
|
|
cpu_maps_update_begin();
|
|
ret = raw_notifier_chain_register(&cpu_chain, nb);
|
|
cpu_maps_update_done();
|
|
return ret;
|
|
}
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
|
|
EXPORT_SYMBOL(register_cpu_notifier);
|
|
|
|
void __ref unregister_cpu_notifier(struct notifier_block *nb)
|
|
{
|
|
cpu_maps_update_begin();
|
|
raw_notifier_chain_unregister(&cpu_chain, nb);
|
|
cpu_maps_update_done();
|
|
}
|
|
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 && p->state == TASK_RUNNING &&
|
|
(!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 = %x)\n",
|
|
p->comm, task_pid_nr(p), cpu,
|
|
p->state, p->flags);
|
|
}
|
|
write_unlock_irq(&tasklist_lock);
|
|
}
|
|
|
|
struct take_cpu_down_param {
|
|
unsigned long mod;
|
|
void *hcpu;
|
|
};
|
|
|
|
/* Take this CPU down. */
|
|
static int __ref take_cpu_down(void *_param)
|
|
{
|
|
struct take_cpu_down_param *param = _param;
|
|
int err;
|
|
|
|
/* Ensure this CPU doesn't handle any more interrupts. */
|
|
err = __cpu_disable();
|
|
if (err < 0)
|
|
return err;
|
|
|
|
raw_notifier_call_chain(&cpu_chain, CPU_DYING | param->mod,
|
|
param->hcpu);
|
|
|
|
/* 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 __ref _cpu_down(unsigned int cpu, int tasks_frozen)
|
|
{
|
|
int err, nr_calls = 0;
|
|
cpumask_var_t old_allowed;
|
|
void *hcpu = (void *)(long)cpu;
|
|
unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
|
|
struct take_cpu_down_param tcd_param = {
|
|
.mod = mod,
|
|
.hcpu = hcpu,
|
|
};
|
|
|
|
if (num_online_cpus() == 1)
|
|
return -EBUSY;
|
|
|
|
if (!cpu_online(cpu))
|
|
return -EINVAL;
|
|
|
|
if (!alloc_cpumask_var(&old_allowed, GFP_KERNEL))
|
|
return -ENOMEM;
|
|
|
|
cpu_hotplug_begin();
|
|
set_cpu_active(cpu, false);
|
|
err = __raw_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE | mod,
|
|
hcpu, -1, &nr_calls);
|
|
if (err == NOTIFY_BAD) {
|
|
set_cpu_active(cpu, true);
|
|
|
|
nr_calls--;
|
|
__raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod,
|
|
hcpu, nr_calls, NULL);
|
|
printk("%s: attempt to take down CPU %u failed\n",
|
|
__func__, cpu);
|
|
err = -EINVAL;
|
|
goto out_release;
|
|
}
|
|
|
|
/* Ensure that we are not runnable on dying cpu */
|
|
cpumask_copy(old_allowed, ¤t->cpus_allowed);
|
|
set_cpus_allowed_ptr(current, cpu_active_mask);
|
|
|
|
err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
|
|
if (err) {
|
|
set_cpu_active(cpu, true);
|
|
/* CPU didn't die: tell everyone. Can't complain. */
|
|
if (raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod,
|
|
hcpu) == NOTIFY_BAD)
|
|
BUG();
|
|
|
|
goto out_allowed;
|
|
}
|
|
BUG_ON(cpu_online(cpu));
|
|
|
|
/* Wait for it to sleep (leaving idle task). */
|
|
while (!idle_cpu(cpu))
|
|
yield();
|
|
|
|
/* This actually kills the CPU. */
|
|
__cpu_die(cpu);
|
|
|
|
/* CPU is completely dead: tell everyone. Too late to complain. */
|
|
if (raw_notifier_call_chain(&cpu_chain, CPU_DEAD | mod,
|
|
hcpu) == NOTIFY_BAD)
|
|
BUG();
|
|
|
|
check_for_tasks(cpu);
|
|
|
|
out_allowed:
|
|
set_cpus_allowed_ptr(current, old_allowed);
|
|
out_release:
|
|
cpu_hotplug_done();
|
|
if (!err) {
|
|
if (raw_notifier_call_chain(&cpu_chain, CPU_POST_DEAD | mod,
|
|
hcpu) == NOTIFY_BAD)
|
|
BUG();
|
|
}
|
|
free_cpumask_var(old_allowed);
|
|
return err;
|
|
}
|
|
|
|
int __ref cpu_down(unsigned int cpu)
|
|
{
|
|
int err;
|
|
|
|
err = stop_machine_create();
|
|
if (err)
|
|
return err;
|
|
cpu_maps_update_begin();
|
|
|
|
if (cpu_hotplug_disabled) {
|
|
err = -EBUSY;
|
|
goto out;
|
|
}
|
|
|
|
err = _cpu_down(cpu, 0);
|
|
|
|
out:
|
|
cpu_maps_update_done();
|
|
stop_machine_destroy();
|
|
return err;
|
|