Revision 03049269de433cb5fe2859be9ae4469ceb1163ed authored by Michal Hocko on 25 March 2016, 21:20:33 UTC, committed by Linus Torvalds on 25 March 2016, 23:37:42 UTC
wake_oom_reaper has allowed only 1 oom victim to be queued. The main
reason for that was the simplicity as other solutions would require some
way of queuing. The current approach is racy and that was deemed
sufficient as the oom_reaper is considered a best effort approach to
help with oom handling when the OOM victim cannot terminate in a
reasonable time. The race could lead to missing an oom victim which can
get stuck
out_of_memory
wake_oom_reaper
cmpxchg // OK
oom_reaper
oom_reap_task
__oom_reap_task
oom_victim terminates
atomic_inc_not_zero // fail
out_of_memory
wake_oom_reaper
cmpxchg // fails
task_to_reap = NULL
This race requires 2 OOM invocations in a short time period which is not
very likely but certainly not impossible. E.g. the original victim
might have not released a lot of memory for some reason.
The situation would improve considerably if wake_oom_reaper used a more
robust queuing. This is what this patch implements. This means adding
oom_reaper_list list_head into task_struct (eat a hole before embeded
thread_struct for that purpose) and a oom_reaper_lock spinlock for
queuing synchronization. wake_oom_reaper will then add the task on the
queue and oom_reaper will dequeue it.
Signed-off-by: Michal Hocko <mhocko@suse.com>
Cc: Vladimir Davydov <vdavydov@virtuozzo.com>
Cc: Andrea Argangeli <andrea@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent bc448e8
blk-mq.h
#ifndef INT_BLK_MQ_H
#define INT_BLK_MQ_H
struct blk_mq_tag_set;
struct blk_mq_ctx {
struct {
spinlock_t lock;
struct list_head rq_list;
} ____cacheline_aligned_in_smp;
unsigned int cpu;
unsigned int index_hw;
unsigned int last_tag ____cacheline_aligned_in_smp;
/* incremented at dispatch time */
unsigned long rq_dispatched[2];
unsigned long rq_merged;
/* incremented at completion time */
unsigned long ____cacheline_aligned_in_smp rq_completed[2];
struct request_queue *queue;
struct kobject kobj;
} ____cacheline_aligned_in_smp;
void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
void blk_mq_freeze_queue(struct request_queue *q);
void blk_mq_free_queue(struct request_queue *q);
int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
void blk_mq_wake_waiters(struct request_queue *q);
/*
* CPU hotplug helpers
*/
struct blk_mq_cpu_notifier;
void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier,
int (*fn)(void *, unsigned long, unsigned int),
void *data);
void blk_mq_register_cpu_notifier(struct blk_mq_cpu_notifier *notifier);
void blk_mq_unregister_cpu_notifier(struct blk_mq_cpu_notifier *notifier);
void blk_mq_cpu_init(void);
void blk_mq_enable_hotplug(void);
void blk_mq_disable_hotplug(void);
/*
* CPU -> queue mappings
*/
extern unsigned int *blk_mq_make_queue_map(struct blk_mq_tag_set *set);
extern int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues,
const struct cpumask *online_mask);
extern int blk_mq_hw_queue_to_node(unsigned int *map, unsigned int);
/*
* sysfs helpers
*/
extern int blk_mq_sysfs_register(struct request_queue *q);
extern void blk_mq_sysfs_unregister(struct request_queue *q);
extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
extern void blk_mq_rq_timed_out(struct request *req, bool reserved);
void blk_mq_release(struct request_queue *q);
/*
* Basic implementation of sparser bitmap, allowing the user to spread
* the bits over more cachelines.
*/
struct blk_align_bitmap {
unsigned long word;
unsigned long depth;
} ____cacheline_aligned_in_smp;
static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
unsigned int cpu)
{
return per_cpu_ptr(q->queue_ctx, cpu);
}
/*
* This assumes per-cpu software queueing queues. They could be per-node
* as well, for instance. For now this is hardcoded as-is. Note that we don't
* care about preemption, since we know the ctx's are persistent. This does
* mean that we can't rely on ctx always matching the currently running CPU.
*/
static inline struct blk_mq_ctx *blk_mq_get_ctx(struct request_queue *q)
{
return __blk_mq_get_ctx(q, get_cpu());
}
static inline void blk_mq_put_ctx(struct blk_mq_ctx *ctx)
{
put_cpu();
}
struct blk_mq_alloc_data {
/* input parameter */
struct request_queue *q;
unsigned int flags;
/* input & output parameter */
struct blk_mq_ctx *ctx;
struct blk_mq_hw_ctx *hctx;
};
static inline void blk_mq_set_alloc_data(struct blk_mq_alloc_data *data,
struct request_queue *q, unsigned int flags,
struct blk_mq_ctx *ctx, struct blk_mq_hw_ctx *hctx)
{
data->q = q;
data->flags = flags;
data->ctx = ctx;
data->hctx = hctx;
}
static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx)
{
return hctx->nr_ctx && hctx->tags;
}
#endif
Computing file changes ...
