Commit d56c1584 authored by Miaohe Lin's avatar Miaohe Lin Committed by Andrew Morton
Browse files

mm: compaction: clean up comment for sched contention 

Since commit cf66f070 ("mm, compaction: do not consider a need to
reschedule as contention"), async compaction won't abort when scheduling
is needed.  Correct the relevant comment accordingly.

Link: https://lkml.kernel.org/r/20220418141253.24298-5-linmiaohe@huawei.com


Signed-off-by: default avatarMiaohe Lin <linmiaohe@huawei.com>
Cc: Charan Teja Kalla <charante@codeaurora.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Pintu Kumar <pintu@codeaurora.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
parent 00bc102f

mm/compaction.c

+4 −7
Original line number Diff line number Diff line
@@ -513,15 +513,12 @@ static bool compact_lock_irqsave(spinlock_t *lock, unsigned long *flags, 
 * very heavily contended. The lock should be periodically unlocked to avoid

 * having disabled IRQs for a long time, even when there is nobody waiting on

 * the lock. It might also be that allowing the IRQs will result in

 * need_resched() becoming true. If scheduling is needed, async compaction

 * aborts. Sync compaction schedules.

 * need_resched() becoming true. If scheduling is needed, compaction schedules.

 * Either compaction type will also abort if a fatal signal is pending.

 * In either case if the lock was locked, it is dropped and not regained.

 *

 * Returns true if compaction should abort due to fatal signal pending, or

 *		async compaction due to need_resched()

 * Returns false when compaction can continue (sync compaction might have

 *		scheduled)

 * Returns true if compaction should abort due to fatal signal pending.

 * Returns false when compaction can continue.

 */

static bool compact_unlock_should_abort(spinlock_t *lock,

		unsigned long flags, bool *locked, struct compact_control *cc)
@@ -574,7 +571,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, 
		/*

		 * Periodically drop the lock (if held) regardless of its

		 * contention, to give chance to IRQs. Abort if fatal signal

		 * pending or async compaction detects need_resched()

		 * pending.

		 */

		if (!(blockpfn % SWAP_CLUSTER_MAX)

		    && compact_unlock_should_abort(&cc->zone->lock, flags,

mm/internal.h

+1 −1
Original line number Diff line number Diff line
@@ -402,7 +402,7 @@ struct compact_control { 
	bool direct_compaction;		/* False from kcompactd or /proc/... */

	bool proactive_compaction;	/* kcompactd proactive compaction */

	bool whole_zone;		/* Whole zone should/has been scanned */

	bool contended;			/* Signal lock or sched contention */

	bool contended;			/* Signal lock contention */

	bool rescan;			/* Rescanning the same pageblock */

	bool alloc_contig;		/* alloc_contig_range allocation */

};