Revision d1908362ae0b97374eb8328fbb471576332f9fb1 authored by Minchan Kim on 22 September 2010, 20:05:01 UTC, committed by Linus Torvalds on 23 September 2010, 00:22:39 UTC
M. Vefa Bicakci reported 2.6.35 kernel hang up when hibernation on his 32bit 3GB mem machine. (https://bugzilla.kernel.org/show_bug.cgi?id=16771). Also he bisected the regression to commit bb21c7ce18eff8e6e7877ca1d06c6db719376e3c Author: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Date: Fri Jun 4 14:15:05 2010 -0700 vmscan: fix do_try_to_free_pages() return value when priority==0 reclaim failure At first impression, this seemed very strange because the above commit only chenged function return value and hibernate_preallocate_memory() ignore return value of shrink_all_memory(). But it's related. Now, page allocation from hibernation code may enter infinite loop if the system has highmem. The reasons are that vmscan don't care enough OOM case when oom_killer_disabled. The problem sequence is following as. 1. hibernation 2. oom_disable 3. alloc_pages 4. do_try_to_free_pages if (scanning_global_lru(sc) && !all_unreclaimable) return 1; If kswapd is not freozen, it would set zone->all_unreclaimable to 1 and then shrink_zones maybe return true(ie, all_unreclaimable is true). So at last, alloc_pages could go to _nopage_. If it is, it should have no problem. This patch adds all_unreclaimable check to protect in direct reclaim path, too. It can care of hibernation OOM case and help bailout all_unreclaimable case slightly. Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Minchan Kim <minchan.kim@gmail.com> Reported-by: M. Vefa Bicakci <bicave@superonline.com> Reported-by: <caiqian@redhat.com> Reviewed-by: Johannes Weiner <hannes@cmpxchg.org> Tested-by: <caiqian@redhat.com> Acked-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent eba93fc
sched_cpupri.c
/*
* kernel/sched_cpupri.c
*
* CPU priority management
*
* Copyright (C) 2007-2008 Novell
*
* Author: Gregory Haskins <ghaskins@novell.com>
*
* This code tracks the priority of each CPU so that global migration
* decisions are easy to calculate. Each CPU can be in a state as follows:
*
* (INVALID), IDLE, NORMAL, RT1, ... RT99
*
* going from the lowest priority to the highest. CPUs in the INVALID state
* are not eligible for routing. The system maintains this state with
* a 2 dimensional bitmap (the first for priority class, the second for cpus
* in that class). Therefore a typical application without affinity
* restrictions can find a suitable CPU with O(1) complexity (e.g. two bit
* searches). For tasks with affinity restrictions, the algorithm has a
* worst case complexity of O(min(102, nr_domcpus)), though the scenario that
* yields the worst case search is fairly contrived.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; version 2
* of the License.
*/
#include <linux/gfp.h>
#include "sched_cpupri.h"
/* Convert between a 140 based task->prio, and our 102 based cpupri */
static int convert_prio(int prio)
{
int cpupri;
if (prio == CPUPRI_INVALID)
cpupri = CPUPRI_INVALID;
else if (prio == MAX_PRIO)
cpupri = CPUPRI_IDLE;
else if (prio >= MAX_RT_PRIO)
cpupri = CPUPRI_NORMAL;
else
cpupri = MAX_RT_PRIO - prio + 1;
return cpupri;
}
#define for_each_cpupri_active(array, idx) \
for_each_set_bit(idx, array, CPUPRI_NR_PRIORITIES)
/**
* cpupri_find - find the best (lowest-pri) CPU in the system
* @cp: The cpupri context
* @p: The task
* @lowest_mask: A mask to fill in with selected CPUs (or NULL)
*
* Note: This function returns the recommended CPUs as calculated during the
* current invocation. By the time the call returns, the CPUs may have in
* fact changed priorities any number of times. While not ideal, it is not
* an issue of correctness since the normal rebalancer logic will correct
* any discrepancies created by racing against the uncertainty of the current
* priority configuration.
*
* Returns: (int)bool - CPUs were found
*/
int cpupri_find(struct cpupri *cp, struct task_struct *p,
struct cpumask *lowest_mask)
{
int idx = 0;
int task_pri = convert_prio(p->prio);
for_each_cpupri_active(cp->pri_active, idx) {
struct cpupri_vec *vec = &cp->pri_to_cpu[idx];
if (idx >= task_pri)
break;
if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids)
continue;
if (lowest_mask) {
cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask);
/*
* We have to ensure that we have at least one bit
* still set in the array, since the map could have
* been concurrently emptied between the first and
* second reads of vec->mask. If we hit this
* condition, simply act as though we never hit this
* priority level and continue on.
*/
if (cpumask_any(lowest_mask) >= nr_cpu_ids)
continue;
}
return 1;
}
return 0;
}
/**
* cpupri_set - update the cpu priority setting
* @cp: The cpupri context
* @cpu: The target cpu
* @pri: The priority (INVALID-RT99) to assign to this CPU
*
* Note: Assumes cpu_rq(cpu)->lock is locked
*
* Returns: (void)
*/
void cpupri_set(struct cpupri *cp, int cpu, int newpri)
{
int *currpri = &cp->cpu_to_pri[cpu];
int oldpri = *currpri;
unsigned long flags;
newpri = convert_prio(newpri);
BUG_ON(newpri >= CPUPRI_NR_PRIORITIES);
if (newpri == oldpri)
return;
/*
* If the cpu was currently mapped to a different value, we
* need to map it to the new value then remove the old value.
* Note, we must add the new value first, otherwise we risk the
* cpu being cleared from pri_active, and this cpu could be
* missed for a push or pull.
*/
if (likely(newpri != CPUPRI_INVALID)) {
struct cpupri_vec *vec = &cp->pri_to_cpu[newpri];
raw_spin_lock_irqsave(&vec->lock, flags);
cpumask_set_cpu(cpu, vec->mask);
vec->count++;
if (vec->count == 1)
set_bit(newpri, cp->pri_active);
raw_spin_unlock_irqrestore(&vec->lock, flags);
}
if (likely(oldpri != CPUPRI_INVALID)) {
struct cpupri_vec *vec = &cp->pri_to_cpu[oldpri];
raw_spin_lock_irqsave(&vec->lock, flags);
vec->count--;
if (!vec->count)
clear_bit(oldpri, cp->pri_active);
cpumask_clear_cpu(cpu, vec->mask);
raw_spin_unlock_irqrestore(&vec->lock, flags);
}
*currpri = newpri;
}
/**
* cpupri_init - initialize the cpupri structure
* @cp: The cpupri context
* @bootmem: true if allocations need to use bootmem
*
* Returns: -ENOMEM if memory fails.
*/
int cpupri_init(struct cpupri *cp)
{
int i;
memset(cp, 0, sizeof(*cp));
for (i = 0; i < CPUPRI_NR_PRIORITIES; i++) {
struct cpupri_vec *vec = &cp->pri_to_cpu[i];
raw_spin_lock_init(&vec->lock);
vec->count = 0;
if (!zalloc_cpumask_var(&vec->mask, GFP_KERNEL))
goto cleanup;
}
for_each_possible_cpu(i)
cp->cpu_to_pri[i] = CPUPRI_INVALID;
return 0;
cleanup:
for (i--; i >= 0; i--)
free_cpumask_var(cp->pri_to_cpu[i].mask);
return -ENOMEM;
}
/**
* cpupri_cleanup - clean up the cpupri structure
* @cp: The cpupri context
*/
void cpupri_cleanup(struct cpupri *cp)
{
int i;
for (i = 0; i < CPUPRI_NR_PRIORITIES; i++)
free_cpumask_var(cp->pri_to_cpu[i].mask);
}
Computing file changes ...