mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2026-08-14 06:22:34 +02:00
fujunjie
ed384eb3a3
should_compact_retry() handles COMPACT_SKIPPED by asking
compaction_zonelist_suitable() whether reclaim can make a later compaction
attempt worthwhile. That answer is used for the current allocation, so it
should follow the same zone eligibility rules as the allocation itself.
When cpusets are enabled, allocator slowpath decisions are marked with
ALLOC_CPUSET. The allocation path, direct compaction and reclaim retry
all skip zones rejected by __cpuset_zone_allowed().
compaction_zonelist_suitable() does not apply that filter. It only walks
ac->zonelist/ac->nodemask, so it can return true because a zone that is
not usable for the current allocation would pass __compaction_suitable().
That does not let the allocation use the disallowed zone. Later
allocation and direct compaction paths still apply cpuset filtering.
However, it can make should_compact_retry() retry based on memory that
this allocation cannot use.
Pass gfp_mask down and apply the same ALLOC_CPUSET check in
compaction_zonelist_suitable(). This keeps the retry decision aligned
with the zones that the allocation is allowed to use.
A temporary debugfs probe was also used to call the old and new
compaction_zonelist_suitable() predicates in the same two-node NUMA guest.
The task was restricted to mems=0 while ac->nodemask covered nodes 0-1.
After putting pressure on node0, node0 failed __compaction_suitable() for
order-10 and node1 passed it, but node1 was rejected by
__cpuset_zone_allowed(). In that state the old predicate returned true
and the patched predicate returned false.
Link: https://lore.kernel.org/tencent_F59F2BA2CC5779308E10DF54593C736D3E0A@qq.com
Fixes: 435b3894e7 ("mm:page_alloc: fix the NULL ac->nodemask in __alloc_pages_slowpath()")
Signed-off-by: fujunjie <fujunjie1@qq.com>
Reviewed-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
154 lines
4.6 KiB
C
154 lines
4.6 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_COMPACTION_H
|
|
#define _LINUX_COMPACTION_H
|
|
|
|
/*
|
|
* Determines how hard direct compaction should try to succeed.
|
|
* Lower value means higher priority, analogically to reclaim priority.
|
|
*/
|
|
enum compact_priority {
|
|
COMPACT_PRIO_SYNC_FULL,
|
|
MIN_COMPACT_PRIORITY = COMPACT_PRIO_SYNC_FULL,
|
|
COMPACT_PRIO_SYNC_LIGHT,
|
|
MIN_COMPACT_COSTLY_PRIORITY = COMPACT_PRIO_SYNC_LIGHT,
|
|
DEF_COMPACT_PRIORITY = COMPACT_PRIO_SYNC_LIGHT,
|
|
COMPACT_PRIO_ASYNC,
|
|
INIT_COMPACT_PRIORITY = COMPACT_PRIO_ASYNC
|
|
};
|
|
|
|
/* Return values for compact_zone() and try_to_compact_pages() */
|
|
/* When adding new states, please adjust include/trace/events/compaction.h */
|
|
enum compact_result {
|
|
/* For more detailed tracepoint output - internal to compaction */
|
|
COMPACT_NOT_SUITABLE_ZONE,
|
|
/*
|
|
* compaction didn't start as it was not possible or direct reclaim
|
|
* was more suitable
|
|
*/
|
|
COMPACT_SKIPPED,
|
|
/* compaction didn't start as it was deferred due to past failures */
|
|
COMPACT_DEFERRED,
|
|
|
|
/* For more detailed tracepoint output - internal to compaction */
|
|
COMPACT_NO_SUITABLE_PAGE,
|
|
/* compaction should continue to another pageblock */
|
|
COMPACT_CONTINUE,
|
|
|
|
/*
|
|
* The full zone was compacted scanned but wasn't successful to compact
|
|
* suitable pages.
|
|
*/
|
|
COMPACT_COMPLETE,
|
|
/*
|
|
* direct compaction has scanned part of the zone but wasn't successful
|
|
* to compact suitable pages.
|
|
*/
|
|
COMPACT_PARTIAL_SKIPPED,
|
|
|
|
/* compaction terminated prematurely due to lock contentions */
|
|
COMPACT_CONTENDED,
|
|
|
|
/*
|
|
* direct compaction terminated after concluding that the allocation
|
|
* should now succeed
|
|
*/
|
|
COMPACT_SUCCESS,
|
|
};
|
|
|
|
struct alloc_context; /* in mm/internal.h */
|
|
|
|
/*
|
|
* Number of free order-0 pages that should be available above given watermark
|
|
* to make sure compaction has reasonable chance of not running out of free
|
|
* pages that it needs to isolate as migration target during its work.
|
|
*/
|
|
static inline unsigned long compact_gap(unsigned int order)
|
|
{
|
|
/*
|
|
* Although all the isolations for migration are temporary, compaction
|
|
* free scanner may have up to 1 << order pages on its list and then
|
|
* try to split an (order - 1) free page. At that point, a gap of
|
|
* 1 << order might not be enough, so it's safer to require twice that
|
|
* amount. Note that the number of pages on the list is also
|
|
* effectively limited by COMPACT_CLUSTER_MAX, as that's the maximum
|
|
* that the migrate scanner can have isolated on migrate list, and free
|
|
* scanner is only invoked when the number of isolated free pages is
|
|
* lower than that. But it's not worth to complicate the formula here
|
|
* as a bigger gap for higher orders than strictly necessary can also
|
|
* improve chances of compaction success.
|
|
*/
|
|
return 2UL << order;
|
|
}
|
|
|
|
static inline int current_is_kcompactd(void)
|
|
{
|
|
return current->flags & PF_KCOMPACTD;
|
|
}
|
|
|
|
#ifdef CONFIG_COMPACTION
|
|
|
|
extern unsigned int extfrag_for_order(struct zone *zone, unsigned int order);
|
|
extern int fragmentation_index(struct zone *zone, unsigned int order);
|
|
extern enum compact_result try_to_compact_pages(gfp_t gfp_mask,
|
|
unsigned int order, unsigned int alloc_flags,
|
|
const struct alloc_context *ac, enum compact_priority prio,
|
|
struct page **page);
|
|
extern void reset_isolation_suitable(pg_data_t *pgdat);
|
|
extern bool compaction_suitable(struct zone *zone, int order,
|
|
unsigned long watermark, int highest_zoneidx);
|
|
|
|
extern void compaction_defer_reset(struct zone *zone, int order,
|
|
bool alloc_success);
|
|
|
|
bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
|
|
int alloc_flags, gfp_t gfp_mask);
|
|
|
|
extern void __meminit kcompactd_run(int nid);
|
|
extern void __meminit kcompactd_stop(int nid);
|
|
extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx);
|
|
|
|
#else
|
|
static inline void reset_isolation_suitable(pg_data_t *pgdat)
|
|
{
|
|
}
|
|
|
|
static inline bool compaction_suitable(struct zone *zone, int order,
|
|
unsigned long watermark,
|
|
int highest_zoneidx)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline void kcompactd_run(int nid)
|
|
{
|
|
}
|
|
static inline void kcompactd_stop(int nid)
|
|
{
|
|
}
|
|
|
|
static inline void wakeup_kcompactd(pg_data_t *pgdat,
|
|
int order, int highest_zoneidx)
|
|
{
|
|
}
|
|
|
|
#endif /* CONFIG_COMPACTION */
|
|
|
|
struct node;
|
|
#if defined(CONFIG_COMPACTION) && defined(CONFIG_SYSFS) && defined(CONFIG_NUMA)
|
|
extern int compaction_register_node(struct node *node);
|
|
extern void compaction_unregister_node(struct node *node);
|
|
|
|
#else
|
|
|
|
static inline int compaction_register_node(struct node *node)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void compaction_unregister_node(struct node *node)
|
|
{
|
|
}
|
|
#endif /* CONFIG_COMPACTION && CONFIG_SYSFS && CONFIG_NUMA */
|
|
|
|
#endif /* _LINUX_COMPACTION_H */
|