e1e7338893
After a period of intense memory pressure is over, it's common for vmpressure to still have old reclaim efficiency data accumulated from this time. When memory pressure starts to rise again, this stale data will factor into vmpressure's calculations, and can cause vmpressure to report an erroneously high pressure. The reverse is possible, too: vmpressure may report pressures that are erroneously low due to stale data that's been stored. Furthermore, since kswapd can still be performing reclaim when there are no failed memory allocations stuck in the page allocator's slow path, vmpressure may still report pressures when there aren't any memory allocations to satisfy. This can cause last-resort memory reclaimers to kill processes to free memory when it's not needed. To fix the rampant stale data, keep track of when there are processes utilizing reclaim in the page allocator's slow path, and reset the accumulated data in vmpressure when a new period of elevated memory pressure begins. Extra measures are taken for the kswapd issue mentioned above by ignoring all reclaim efficiency data reported by kswapd when there aren't any failed memory allocations in the page allocator which utilize reclaim. Note that since sr_lock can now be used from IRQ context, IRQs must be disabled whenever sr_lock is used to prevent deadlocks. Signed-off-by: Sultan Alsawaf <sultan@kerneltoast.com>
63 lines
1.9 KiB
C
63 lines
1.9 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef __LINUX_VMPRESSURE_H
|
|
#define __LINUX_VMPRESSURE_H
|
|
|
|
#include <linux/mutex.h>
|
|
#include <linux/list.h>
|
|
#include <linux/workqueue.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/types.h>
|
|
#include <linux/cgroup.h>
|
|
#include <linux/eventfd.h>
|
|
|
|
struct vmpressure {
|
|
unsigned long scanned;
|
|
unsigned long reclaimed;
|
|
|
|
unsigned long tree_scanned;
|
|
unsigned long tree_reclaimed;
|
|
unsigned long stall;
|
|
/* The lock is used to keep the scanned/reclaimed above in sync. */
|
|
struct spinlock sr_lock;
|
|
|
|
/* The list of vmpressure_event structs. */
|
|
struct list_head events;
|
|
/* Have to grab the lock on events traversal or modifications. */
|
|
struct mutex events_lock;
|
|
|
|
struct work_struct work;
|
|
|
|
atomic_long_t users;
|
|
rwlock_t users_lock;
|
|
};
|
|
|
|
struct mem_cgroup;
|
|
|
|
extern int vmpressure_notifier_register(struct notifier_block *nb);
|
|
extern int vmpressure_notifier_unregister(struct notifier_block *nb);
|
|
extern void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree,
|
|
unsigned long scanned, unsigned long reclaimed,
|
|
int order);
|
|
extern void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio,
|
|
int order);
|
|
extern bool vmpressure_inc_users(int order);
|
|
extern void vmpressure_dec_users(void);
|
|
|
|
#ifdef CONFIG_MEMCG
|
|
extern void vmpressure_init(struct vmpressure *vmpr);
|
|
extern void vmpressure_cleanup(struct vmpressure *vmpr);
|
|
extern struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg);
|
|
extern struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr);
|
|
extern int vmpressure_register_event(struct mem_cgroup *memcg,
|
|
struct eventfd_ctx *eventfd,
|
|
const char *args);
|
|
extern void vmpressure_unregister_event(struct mem_cgroup *memcg,
|
|
struct eventfd_ctx *eventfd);
|
|
#else
|
|
static inline struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg)
|
|
{
|
|
return NULL;
|
|
}
|
|
#endif /* CONFIG_MEMCG */
|
|
#endif /* __LINUX_VMPRESSURE_H */
|