mirror of
https://github.com/torvalds/linux.git
synced 2024-12-13 06:32:50 +00:00
f689054aac
The percpu_counter is used for scenarios where performance is more important than the accuracy. For percpu_counter users, who want more accurate information in their slowpath, percpu_counter_sum is provided which traverses all the online CPUs to accumulate the data. The reason it only needs to traverse online CPUs is because percpu_counter does implement CPU offline callback which syncs the local data of the offlined CPU. However there is a small race window between the online CPUs traversal of percpu_counter_sum and the CPU offline callback. The offline callback has to traverse all the percpu_counters on the system to flush the CPU local data which can be a lot. During that time, the CPU which is going offline has already been published as offline to all the readers. So, as the offline callback is running, percpu_counter_sum can be called for one counter which has some state on the CPU going offline. Since percpu_counter_sum only traverses online CPUs, it will skip that specific CPU and the offline callback might not have flushed the state for that specific percpu_counter on that offlined CPU. Normally this is not an issue because percpu_counter users can deal with some inaccuracy for small time window. However a new user i.e. mm_struct on the cleanup path wants to check the exact state of the percpu_counter through check_mm(). For such users, this patch introduces percpu_counter_sum_all() which traverses all possible CPUs and it is used in fork.c:check_mm() to avoid the potential race. This issue is exposed by the later patch "mm: convert mm's rss stats into percpu_counter". Link: https://lkml.kernel.org/r/20221109012011.881058-1-shakeelb@google.com Signed-off-by: Shakeel Butt <shakeelb@google.com> Reported-by: Marek Szyprowski <m.szyprowski@samsung.com> Tested-by: Marek Szyprowski <m.szyprowski@samsung.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
275 lines
6.9 KiB
C
275 lines
6.9 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* Fast batching percpu counters.
|
|
*/
|
|
|
|
#include <linux/percpu_counter.h>
|
|
#include <linux/mutex.h>
|
|
#include <linux/init.h>
|
|
#include <linux/cpu.h>
|
|
#include <linux/module.h>
|
|
#include <linux/debugobjects.h>
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
static LIST_HEAD(percpu_counters);
|
|
static DEFINE_SPINLOCK(percpu_counters_lock);
|
|
#endif
|
|
|
|
#ifdef CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER
|
|
|
|
static const struct debug_obj_descr percpu_counter_debug_descr;
|
|
|
|
static bool percpu_counter_fixup_free(void *addr, enum debug_obj_state state)
|
|
{
|
|
struct percpu_counter *fbc = addr;
|
|
|
|
switch (state) {
|
|
case ODEBUG_STATE_ACTIVE:
|
|
percpu_counter_destroy(fbc);
|
|
debug_object_free(fbc, &percpu_counter_debug_descr);
|
|
return true;
|
|
default:
|
|
return false;
|
|
}
|
|
}
|
|
|
|
static const struct debug_obj_descr percpu_counter_debug_descr = {
|
|
.name = "percpu_counter",
|
|
.fixup_free = percpu_counter_fixup_free,
|
|
};
|
|
|
|
static inline void debug_percpu_counter_activate(struct percpu_counter *fbc)
|
|
{
|
|
debug_object_init(fbc, &percpu_counter_debug_descr);
|
|
debug_object_activate(fbc, &percpu_counter_debug_descr);
|
|
}
|
|
|
|
static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc)
|
|
{
|
|
debug_object_deactivate(fbc, &percpu_counter_debug_descr);
|
|
debug_object_free(fbc, &percpu_counter_debug_descr);
|
|
}
|
|
|
|
#else /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */
|
|
static inline void debug_percpu_counter_activate(struct percpu_counter *fbc)
|
|
{ }
|
|
static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc)
|
|
{ }
|
|
#endif /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */
|
|
|
|
void percpu_counter_set(struct percpu_counter *fbc, s64 amount)
|
|
{
|
|
int cpu;
|
|
unsigned long flags;
|
|
|
|
raw_spin_lock_irqsave(&fbc->lock, flags);
|
|
for_each_possible_cpu(cpu) {
|
|
s32 *pcount = per_cpu_ptr(fbc->counters, cpu);
|
|
*pcount = 0;
|
|
}
|
|
fbc->count = amount;
|
|
raw_spin_unlock_irqrestore(&fbc->lock, flags);
|
|
}
|
|
EXPORT_SYMBOL(percpu_counter_set);
|
|
|
|
/*
|
|
* This function is both preempt and irq safe. The former is due to explicit
|
|
* preemption disable. The latter is guaranteed by the fact that the slow path
|
|
* is explicitly protected by an irq-safe spinlock whereas the fast patch uses
|
|
* this_cpu_add which is irq-safe by definition. Hence there is no need muck
|
|
* with irq state before calling this one
|
|
*/
|
|
void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch)
|
|
{
|
|
s64 count;
|
|
|
|
preempt_disable();
|
|
count = __this_cpu_read(*fbc->counters) + amount;
|
|
if (abs(count) >= batch) {
|
|
unsigned long flags;
|
|
raw_spin_lock_irqsave(&fbc->lock, flags);
|
|
fbc->count += count;
|
|
__this_cpu_sub(*fbc->counters, count - amount);
|
|
raw_spin_unlock_irqrestore(&fbc->lock, flags);
|
|
} else {
|
|
this_cpu_add(*fbc->counters, amount);
|
|
}
|
|
preempt_enable();
|
|
}
|
|
EXPORT_SYMBOL(percpu_counter_add_batch);
|
|
|
|
/*
|
|
* For percpu_counter with a big batch, the devication of its count could
|
|
* be big, and there is requirement to reduce the deviation, like when the
|
|
* counter's batch could be runtime decreased to get a better accuracy,
|
|
* which can be achieved by running this sync function on each CPU.
|
|
*/
|
|
void percpu_counter_sync(struct percpu_counter *fbc)
|
|
{
|
|
unsigned long flags;
|
|
s64 count;
|
|
|
|
raw_spin_lock_irqsave(&fbc->lock, flags);
|
|
count = __this_cpu_read(*fbc->counters);
|
|
fbc->count += count;
|
|
__this_cpu_sub(*fbc->counters, count);
|
|
raw_spin_unlock_irqrestore(&fbc->lock, flags);
|
|
}
|
|
EXPORT_SYMBOL(percpu_counter_sync);
|
|
|
|
static s64 __percpu_counter_sum_mask(struct percpu_counter *fbc,
|
|
const struct cpumask *cpu_mask)
|
|
{
|
|
s64 ret;
|
|
int cpu;
|
|
unsigned long flags;
|
|
|
|
raw_spin_lock_irqsave(&fbc->lock, flags);
|
|
ret = fbc->count;
|
|
for_each_cpu(cpu, cpu_mask) {
|
|
s32 *pcount = per_cpu_ptr(fbc->counters, cpu);
|
|
ret += *pcount;
|
|
}
|
|
raw_spin_unlock_irqrestore(&fbc->lock, flags);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Add up all the per-cpu counts, return the result. This is a more accurate
|
|
* but much slower version of percpu_counter_read_positive()
|
|
*/
|
|
s64 __percpu_counter_sum(struct percpu_counter *fbc)
|
|
{
|
|
return __percpu_counter_sum_mask(fbc, cpu_online_mask);
|
|
}
|
|
EXPORT_SYMBOL(__percpu_counter_sum);
|
|
|
|
/*
|
|
* This is slower version of percpu_counter_sum as it traverses all possible
|
|
* cpus. Use this only in the cases where accurate data is needed in the
|
|
* presense of CPUs getting offlined.
|
|
*/
|
|
s64 percpu_counter_sum_all(struct percpu_counter *fbc)
|
|
{
|
|
return __percpu_counter_sum_mask(fbc, cpu_possible_mask);
|
|
}
|
|
EXPORT_SYMBOL(percpu_counter_sum_all);
|
|
|
|
int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp,
|
|
struct lock_class_key *key)
|
|
{
|
|
unsigned long flags __maybe_unused;
|
|
|
|
raw_spin_lock_init(&fbc->lock);
|
|
lockdep_set_class(&fbc->lock, key);
|
|
fbc->count = amount;
|
|
fbc->counters = alloc_percpu_gfp(s32, gfp);
|
|
if (!fbc->counters)
|
|
return -ENOMEM;
|
|
|
|
debug_percpu_counter_activate(fbc);
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
INIT_LIST_HEAD(&fbc->list);
|
|
spin_lock_irqsave(&percpu_counters_lock, flags);
|
|
list_add(&fbc->list, &percpu_counters);
|
|
spin_unlock_irqrestore(&percpu_counters_lock, flags);
|
|
#endif
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(__percpu_counter_init);
|
|
|
|
void percpu_counter_destroy(struct percpu_counter *fbc)
|
|
{
|
|
unsigned long flags __maybe_unused;
|
|
|
|
if (!fbc->counters)
|
|
return;
|
|
|
|
debug_percpu_counter_deactivate(fbc);
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
spin_lock_irqsave(&percpu_counters_lock, flags);
|
|
list_del(&fbc->list);
|
|
spin_unlock_irqrestore(&percpu_counters_lock, flags);
|
|
#endif
|
|
free_percpu(fbc->counters);
|
|
fbc->counters = NULL;
|
|
}
|
|
EXPORT_SYMBOL(percpu_counter_destroy);
|
|
|
|
int percpu_counter_batch __read_mostly = 32;
|
|
EXPORT_SYMBOL(percpu_counter_batch);
|
|
|
|
static int compute_batch_value(unsigned int cpu)
|
|
{
|
|
int nr = num_online_cpus();
|
|
|
|
percpu_counter_batch = max(32, nr*2);
|
|
return 0;
|
|
}
|
|
|
|
static int percpu_counter_cpu_dead(unsigned int cpu)
|
|
{
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
struct percpu_counter *fbc;
|
|
|
|
compute_batch_value(cpu);
|
|
|
|
spin_lock_irq(&percpu_counters_lock);
|
|
list_for_each_entry(fbc, &percpu_counters, list) {
|
|
s32 *pcount;
|
|
|
|
raw_spin_lock(&fbc->lock);
|
|
pcount = per_cpu_ptr(fbc->counters, cpu);
|
|
fbc->count += *pcount;
|
|
*pcount = 0;
|
|
raw_spin_unlock(&fbc->lock);
|
|
}
|
|
spin_unlock_irq(&percpu_counters_lock);
|
|
#endif
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Compare counter against given value.
|
|
* Return 1 if greater, 0 if equal and -1 if less
|
|
*/
|
|
int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch)
|
|
{
|
|
s64 count;
|
|
|
|
count = percpu_counter_read(fbc);
|
|
/* Check to see if rough count will be sufficient for comparison */
|
|
if (abs(count - rhs) > (batch * num_online_cpus())) {
|
|
if (count > rhs)
|
|
return 1;
|
|
else
|
|
return -1;
|
|
}
|
|
/* Need to use precise count */
|
|
count = percpu_counter_sum(fbc);
|
|
if (count > rhs)
|
|
return 1;
|
|
else if (count < rhs)
|
|
return -1;
|
|
else
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(__percpu_counter_compare);
|
|
|
|
static int __init percpu_counter_startup(void)
|
|
{
|
|
int ret;
|
|
|
|
ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "lib/percpu_cnt:online",
|
|
compute_batch_value, NULL);
|
|
WARN_ON(ret < 0);
|
|
ret = cpuhp_setup_state_nocalls(CPUHP_PERCPU_CNT_DEAD,
|
|
"lib/percpu_cnt:dead", NULL,
|
|
percpu_counter_cpu_dead);
|
|
WARN_ON(ret < 0);
|
|
return 0;
|
|
}
|
|
module_init(percpu_counter_startup);
|