mirror of
https://github.com/edk2-porting/linux-next.git
synced 2024-12-25 05:34:00 +08:00
b5bd6a0e5f
When racing with CPU hotplug, percpu_counter_sum() can return negative values for the number of observed events. This confuses fprop_new_period(), which uses unsigned type and as a result number of events is set to big *positive* number. From that moment on, things go pear shaped and can result e.g. in division by zero as denominator is later truncated to 32-bits. This bug causes a divide-by-zero oops in bdi_dirty_limit() in Borislav's 3.6.0-rc6 based kernel. Fix the issue by using a signed type in fprop_new_period(). That makes us bail out from the function without doing anything (mistakenly) thinking there are no events to age. That makes aging somewhat inaccurate but getting accurate data would be rather hard. Signed-off-by: Jan Kara <jack@suse.cz> Reported-by: Borislav Petkov <bp@amd64.org> Reported-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
273 lines
6.8 KiB
C
273 lines
6.8 KiB
C
/*
|
|
* Floating proportions with flexible aging period
|
|
*
|
|
* Copyright (C) 2011, SUSE, Jan Kara <jack@suse.cz>
|
|
*
|
|
* The goal of this code is: Given different types of event, measure proportion
|
|
* of each type of event over time. The proportions are measured with
|
|
* exponentially decaying history to give smooth transitions. A formula
|
|
* expressing proportion of event of type 'j' is:
|
|
*
|
|
* p_{j} = (\Sum_{i>=0} x_{i,j}/2^{i+1})/(\Sum_{i>=0} x_i/2^{i+1})
|
|
*
|
|
* Where x_{i,j} is j's number of events in i-th last time period and x_i is
|
|
* total number of events in i-th last time period.
|
|
*
|
|
* Note that p_{j}'s are normalised, i.e.
|
|
*
|
|
* \Sum_{j} p_{j} = 1,
|
|
*
|
|
* This formula can be straightforwardly computed by maintaing denominator
|
|
* (let's call it 'd') and for each event type its numerator (let's call it
|
|
* 'n_j'). When an event of type 'j' happens, we simply need to do:
|
|
* n_j++; d++;
|
|
*
|
|
* When a new period is declared, we could do:
|
|
* d /= 2
|
|
* for each j
|
|
* n_j /= 2
|
|
*
|
|
* To avoid iteration over all event types, we instead shift numerator of event
|
|
* j lazily when someone asks for a proportion of event j or when event j
|
|
* occurs. This can bit trivially implemented by remembering last period in
|
|
* which something happened with proportion of type j.
|
|
*/
|
|
#include <linux/flex_proportions.h>
|
|
|
|
int fprop_global_init(struct fprop_global *p)
|
|
{
|
|
int err;
|
|
|
|
p->period = 0;
|
|
/* Use 1 to avoid dealing with periods with 0 events... */
|
|
err = percpu_counter_init(&p->events, 1);
|
|
if (err)
|
|
return err;
|
|
seqcount_init(&p->sequence);
|
|
return 0;
|
|
}
|
|
|
|
void fprop_global_destroy(struct fprop_global *p)
|
|
{
|
|
percpu_counter_destroy(&p->events);
|
|
}
|
|
|
|
/*
|
|
* Declare @periods new periods. It is upto the caller to make sure period
|
|
* transitions cannot happen in parallel.
|
|
*
|
|
* The function returns true if the proportions are still defined and false
|
|
* if aging zeroed out all events. This can be used to detect whether declaring
|
|
* further periods has any effect.
|
|
*/
|
|
bool fprop_new_period(struct fprop_global *p, int periods)
|
|
{
|
|
s64 events;
|
|
unsigned long flags;
|
|
|
|
local_irq_save(flags);
|
|
events = percpu_counter_sum(&p->events);
|
|
/*
|
|
* Don't do anything if there are no events.
|
|
*/
|
|
if (events <= 1) {
|
|
local_irq_restore(flags);
|
|
return false;
|
|
}
|
|
write_seqcount_begin(&p->sequence);
|
|
if (periods < 64)
|
|
events -= events >> periods;
|
|
/* Use addition to avoid losing events happening between sum and set */
|
|
percpu_counter_add(&p->events, -events);
|
|
p->period += periods;
|
|
write_seqcount_end(&p->sequence);
|
|
local_irq_restore(flags);
|
|
|
|
return true;
|
|
}
|
|
|
|
/*
|
|
* ---- SINGLE ----
|
|
*/
|
|
|
|
int fprop_local_init_single(struct fprop_local_single *pl)
|
|
{
|
|
pl->events = 0;
|
|
pl->period = 0;
|
|
raw_spin_lock_init(&pl->lock);
|
|
return 0;
|
|
}
|
|
|
|
void fprop_local_destroy_single(struct fprop_local_single *pl)
|
|
{
|
|
}
|
|
|
|
static void fprop_reflect_period_single(struct fprop_global *p,
|
|
struct fprop_local_single *pl)
|
|
{
|
|
unsigned int period = p->period;
|
|
unsigned long flags;
|
|
|
|
/* Fast path - period didn't change */
|
|
if (pl->period == period)
|
|
return;
|
|
raw_spin_lock_irqsave(&pl->lock, flags);
|
|
/* Someone updated pl->period while we were spinning? */
|
|
if (pl->period >= period) {
|
|
raw_spin_unlock_irqrestore(&pl->lock, flags);
|
|
return;
|
|
}
|
|
/* Aging zeroed our fraction? */
|
|
if (period - pl->period < BITS_PER_LONG)
|
|
pl->events >>= period - pl->period;
|
|
else
|
|
pl->events = 0;
|
|
pl->period = period;
|
|
raw_spin_unlock_irqrestore(&pl->lock, flags);
|
|
}
|
|
|
|
/* Event of type pl happened */
|
|
void __fprop_inc_single(struct fprop_global *p, struct fprop_local_single *pl)
|
|
{
|
|
fprop_reflect_period_single(p, pl);
|
|
pl->events++;
|
|
percpu_counter_add(&p->events, 1);
|
|
}
|
|
|
|
/* Return fraction of events of type pl */
|
|
void fprop_fraction_single(struct fprop_global *p,
|
|
struct fprop_local_single *pl,
|
|
unsigned long *numerator, unsigned long *denominator)
|
|
{
|
|
unsigned int seq;
|
|
s64 num, den;
|
|
|
|
do {
|
|
seq = read_seqcount_begin(&p->sequence);
|
|
fprop_reflect_period_single(p, pl);
|
|
num = pl->events;
|
|
den = percpu_counter_read_positive(&p->events);
|
|
} while (read_seqcount_retry(&p->sequence, seq));
|
|
|
|
/*
|
|
* Make fraction <= 1 and denominator > 0 even in presence of percpu
|
|
* counter errors
|
|
*/
|
|
if (den <= num) {
|
|
if (num)
|
|
den = num;
|
|
else
|
|
den = 1;
|
|
}
|
|
*denominator = den;
|
|
*numerator = num;
|
|
}
|
|
|
|
/*
|
|
* ---- PERCPU ----
|
|
*/
|
|
#define PROP_BATCH (8*(1+ilog2(nr_cpu_ids)))
|
|
|
|
int fprop_local_init_percpu(struct fprop_local_percpu *pl)
|
|
{
|
|
int err;
|
|
|
|
err = percpu_counter_init(&pl->events, 0);
|
|
if (err)
|
|
return err;
|
|
pl->period = 0;
|
|
raw_spin_lock_init(&pl->lock);
|
|
return 0;
|
|
}
|
|
|
|
void fprop_local_destroy_percpu(struct fprop_local_percpu *pl)
|
|
{
|
|
percpu_counter_destroy(&pl->events);
|
|
}
|
|
|
|
static void fprop_reflect_period_percpu(struct fprop_global *p,
|
|
struct fprop_local_percpu *pl)
|
|
{
|
|
unsigned int period = p->period;
|
|
unsigned long flags;
|
|
|
|
/* Fast path - period didn't change */
|
|
if (pl->period == period)
|
|
return;
|
|
raw_spin_lock_irqsave(&pl->lock, flags);
|
|
/* Someone updated pl->period while we were spinning? */
|
|
if (pl->period >= period) {
|
|
raw_spin_unlock_irqrestore(&pl->lock, flags);
|
|
return;
|
|
}
|
|
/* Aging zeroed our fraction? */
|
|
if (period - pl->period < BITS_PER_LONG) {
|
|
s64 val = percpu_counter_read(&pl->events);
|
|
|
|
if (val < (nr_cpu_ids * PROP_BATCH))
|
|
val = percpu_counter_sum(&pl->events);
|
|
|
|
__percpu_counter_add(&pl->events,
|
|
-val + (val >> (period-pl->period)), PROP_BATCH);
|
|
} else
|
|
percpu_counter_set(&pl->events, 0);
|
|
pl->period = period;
|
|
raw_spin_unlock_irqrestore(&pl->lock, flags);
|
|
}
|
|
|
|
/* Event of type pl happened */
|
|
void __fprop_inc_percpu(struct fprop_global *p, struct fprop_local_percpu *pl)
|
|
{
|
|
fprop_reflect_period_percpu(p, pl);
|
|
__percpu_counter_add(&pl->events, 1, PROP_BATCH);
|
|
percpu_counter_add(&p->events, 1);
|
|
}
|
|
|
|
void fprop_fraction_percpu(struct fprop_global *p,
|
|
struct fprop_local_percpu *pl,
|
|
unsigned long *numerator, unsigned long *denominator)
|
|
{
|
|
unsigned int seq;
|
|
s64 num, den;
|
|
|
|
do {
|
|
seq = read_seqcount_begin(&p->sequence);
|
|
fprop_reflect_period_percpu(p, pl);
|
|
num = percpu_counter_read_positive(&pl->events);
|
|
den = percpu_counter_read_positive(&p->events);
|
|
} while (read_seqcount_retry(&p->sequence, seq));
|
|
|
|
/*
|
|
* Make fraction <= 1 and denominator > 0 even in presence of percpu
|
|
* counter errors
|
|
*/
|
|
if (den <= num) {
|
|
if (num)
|
|
den = num;
|
|
else
|
|
den = 1;
|
|
}
|
|
*denominator = den;
|
|
*numerator = num;
|
|
}
|
|
|
|
/*
|
|
* Like __fprop_inc_percpu() except that event is counted only if the given
|
|
* type has fraction smaller than @max_frac/FPROP_FRAC_BASE
|
|
*/
|
|
void __fprop_inc_percpu_max(struct fprop_global *p,
|
|
struct fprop_local_percpu *pl, int max_frac)
|
|
{
|
|
if (unlikely(max_frac < FPROP_FRAC_BASE)) {
|
|
unsigned long numerator, denominator;
|
|
|
|
fprop_fraction_percpu(p, pl, &numerator, &denominator);
|
|
if (numerator >
|
|
(((u64)denominator) * max_frac) >> FPROP_FRAC_SHIFT)
|
|
return;
|
|
} else
|
|
fprop_reflect_period_percpu(p, pl);
|
|
__percpu_counter_add(&pl->events, 1, PROP_BATCH);
|
|
percpu_counter_add(&p->events, 1);
|
|
}
|