diff options
author | 2020-12-14 19:10:59 -0800 | |
---|---|---|
committer | 2020-12-15 12:13:43 -0800 | |
commit | ec6e8c7e03147c65380e6c04c4cf4290e96280b6 (patch) | |
tree | 6bac0857cc5fccd8d67116f9e3bcb87867accf80 /mm/page_alloc.c | |
parent | mm, page_alloc: move draining pcplists to page isolation users (diff) | |
download | linux-ec6e8c7e03147c65380e6c04c4cf4290e96280b6.tar.gz linux-ec6e8c7e03147c65380e6c04c4cf4290e96280b6.tar.bz2 linux-ec6e8c7e03147c65380e6c04c4cf4290e96280b6.zip |
mm, page_alloc: disable pcplists during memory offline
Memory offlining relies on page isolation to guarantee a forward progress
because pages cannot be reused while they are isolated. But the page
isolation itself doesn't prevent from races while freed pages are stored
on pcp lists and thus can be reused. This can be worked around by
repeated draining of pcplists, as done by commit 968318261221
("mm/memory_hotplug: drain per-cpu pages again during memory offline").
David and Michal would prefer that this race was closed in a way that
callers of page isolation who need stronger guarantees don't need to
repeatedly drain. David suggested disabling pcplists usage completely
during page isolation, instead of repeatedly draining them.
To achieve this without adding special cases in alloc/free fastpath, we
can use the same approach as boot pagesets - when pcp->high is 0, any
pcplist addition will be immediately flushed.
The race can thus be closed by setting pcp->high to 0 and draining
pcplists once, before calling start_isolate_page_range(). The draining
will serialize after processes that already disabled interrupts and read
the old value of pcp->high in free_unref_page_commit(), and processes that
have not yet disabled interrupts, will observe pcp->high == 0 when they
are rescheduled, and skip pcplists. This guarantees no stray pages on
pcplists in zones where isolation happens.
This patch thus adds zone_pcp_disable() and zone_pcp_enable() functions
that page isolation users can call before start_isolate_page_range() and
after unisolating (or offlining) the isolated pages.
Also, drain_all_pages() is optimized to only execute on cpus where
pcplists are not empty. The check can however race with a free to pcplist
that has not yet increased the pcp->count from 0 to 1. Thus make the
drain optionally skip the racy check and drain on all cpus, and use this
option in zone_pcp_disable().
As we have to avoid external updates to high and batch while pcplists are
disabled, we take pcp_batch_high_lock in zone_pcp_disable() and release it
in zone_pcp_enable(). This also synchronizes multiple users of
zone_pcp_disable()/enable().
Currently the only user of this functionality is offline_pages().
[vbabka@suse.cz: add comment, per David]
Link: https://lkml.kernel.org/r/527480ef-ed72-e1c1-52a0-1c5b0113df45@suse.cz
Link: https://lkml.kernel.org/r/20201111092812.11329-8-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Suggested-by: David Hildenbrand <david@redhat.com>
Suggested-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: David Hildenbrand <david@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/page_alloc.c')
-rw-r--r-- | mm/page_alloc.c | 73 |
1 files changed, 61 insertions, 12 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c index a259c22e4609..40baa2421136 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3026,13 +3026,16 @@ static void drain_local_pages_wq(struct work_struct *work) } /* - * Spill all the per-cpu pages from all CPUs back into the buddy allocator. - * - * When zone parameter is non-NULL, spill just the single zone's pages. + * The implementation of drain_all_pages(), exposing an extra parameter to + * drain on all cpus. * - * Note that this can be extremely slow as the draining happens in a workqueue. + * drain_all_pages() is optimized to only execute on cpus where pcplists are + * not empty. The check for non-emptiness can however race with a free to + * pcplist that has not yet increased the pcp->count from 0 to 1. Callers + * that need the guarantee that every CPU has drained can disable the + * optimizing racy check. */ -void drain_all_pages(struct zone *zone) +void __drain_all_pages(struct zone *zone, bool force_all_cpus) { int cpu; @@ -3071,7 +3074,13 @@ void drain_all_pages(struct zone *zone) struct zone *z; bool has_pcps = false; - if (zone) { + if (force_all_cpus) { + /* + * The pcp.count check is racy, some callers need a + * guarantee that no cpu is missed. + */ + has_pcps = true; + } else if (zone) { pcp = per_cpu_ptr(zone->pageset, cpu); if (pcp->pcp.count) has_pcps = true; @@ -3104,6 +3113,18 @@ void drain_all_pages(struct zone *zone) mutex_unlock(&pcpu_drain_mutex); } +/* + * Spill all the per-cpu pages from all CPUs back into the buddy allocator. + * + * When zone parameter is non-NULL, spill just the single zone's pages. + * + * Note that this can be extremely slow as the draining happens in a workqueue. + */ +void drain_all_pages(struct zone *zone) +{ + __drain_all_pages(zone, false); +} + #ifdef CONFIG_HIBERNATION /* @@ -6316,6 +6337,18 @@ static void pageset_init(struct per_cpu_pageset *p) pcp->batch = BOOT_PAGESET_BATCH; } +void __zone_set_pageset_high_and_batch(struct zone *zone, unsigned long high, + unsigned long batch) +{ + struct per_cpu_pageset *p; + int cpu; + + for_each_possible_cpu(cpu) { + p = per_cpu_ptr(zone->pageset, cpu); + pageset_update(&p->pcp, high, batch); + } +} + /* * Calculate and set new high and batch values for all per-cpu pagesets of a * zone, based on the zone's size and the percpu_pagelist_fraction sysctl. @@ -6323,8 +6356,6 @@ static void pageset_init(struct per_cpu_pageset *p) static void zone_set_pageset_high_and_batch(struct zone *zone) { unsigned long new_high, new_batch; - struct per_cpu_pageset *p; - int cpu; if (percpu_pagelist_fraction) { new_high = zone_managed_pages(zone) / percpu_pagelist_fraction; @@ -6344,10 +6375,7 @@ static void zone_set_pageset_high_and_batch(struct zone *zone) zone->pageset_high = new_high; zone->pageset_batch = new_batch; - for_each_possible_cpu(cpu) { - p = per_cpu_ptr(zone->pageset, cpu); - pageset_update(&p->pcp, new_high, new_batch); - } + __zone_set_pageset_high_and_batch(zone, new_high, new_batch); } void __meminit setup_zone_pageset(struct zone *zone) @@ -8742,6 +8770,27 @@ void __meminit zone_pcp_update(struct zone *zone) mutex_unlock(&pcp_batch_high_lock); } +/* + * Effectively disable pcplists for the zone by setting the high limit to 0 + * and draining all cpus. A concurrent page freeing on another CPU that's about + * to put the page on pcplist will either finish before the drain and the page + * will be drained, or observe the new high limit and skip the pcplist. + * + * Must be paired with a call to zone_pcp_enable(). + */ +void zone_pcp_disable(struct zone *zone) +{ + mutex_lock(&pcp_batch_high_lock); + __zone_set_pageset_high_and_batch(zone, 0, 1); + __drain_all_pages(zone, true); +} + +void zone_pcp_enable(struct zone *zone) +{ + __zone_set_pageset_high_and_batch(zone, zone->pageset_high, zone->pageset_batch); + mutex_unlock(&pcp_batch_high_lock); +} + void zone_pcp_reset(struct zone *zone) { unsigned long flags; |