Regression was observed when the system is in high memory pressure with
swap on, where migrc might keep a number of folios in its pending queue,
which possibly makes it worse. So temporarily prevented migrc from
working on that condition.
Signed-off-by: Byungchul Park <byungchul@xxxxxx>
---
mm/internal.h | 20 ++++++++++++++++++++
mm/migrate.c | 18 +++++++++++++++++-
mm/page_alloc.c | 13 +++++++++++++
3 files changed, 50 insertions(+), 1 deletion(-)
diff --git a/mm/internal.h b/mm/internal.h
index 5b93e5abf953..7643ccb7c156 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1285,6 +1285,8 @@ static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry,
#endif /* CONFIG_SHRINKER_DEBUG */
#if defined(CONFIG_MIGRATION) && defined(CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH)
+extern atomic_t migrc_pause_cnt;
+
/*
* Reset the indicator indicating there are no writable mappings at the
* beginning of every rmap traverse for unmap. Migrc can work only when
@@ -1313,6 +1315,21 @@ static inline bool can_migrc_test(void)
return current->can_migrc && current->tlb_ubc_ro.flush_required;
}
+static inline void migrc_pause(void)
+{
+ atomic_inc(&migrc_pause_cnt);
+}
+
+static inline void migrc_resume(void)
+{
+ atomic_dec(&migrc_pause_cnt);
+}
+
+static inline bool migrc_paused(void)
+{
+ return !!atomic_read(&migrc_pause_cnt);
+}
+
/*
* Return the number of folios pending TLB flush that have yet to get
* freed in the zone.
@@ -1330,6 +1347,9 @@ bool migrc_flush_free_folios(void);
static inline void can_migrc_init(void) {}
static inline void can_migrc_fail(void) {}
static inline bool can_migrc_test(void) { return false; }
+static inline void migrc_pause(void) {}
+static inline void migrc_resume(void) {}
+static inline bool migrc_paused(void) { return false; }
static inline int migrc_pending_nr_in_zone(struct zone *z) { return 0; }
static inline bool migrc_flush_free_folios(void) { return false; }
#endif
diff --git a/mm/migrate.c b/mm/migrate.c
index da4d43ac2622..b838f279f050 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -62,6 +62,12 @@ static struct tlbflush_unmap_batch migrc_ubc;
static LIST_HEAD(migrc_folios);
static DEFINE_SPINLOCK(migrc_lock);
+/*
+ * Increase on entry of handling high memory pressure e.g. direct
+ * reclaim, decrease on the exit. See __alloc_pages_slowpath().
+ */
+atomic_t migrc_pause_cnt = ATOMIC_INIT(0);
+
static void init_tlb_ubc(struct tlbflush_unmap_batch *ubc)
{
arch_tlbbatch_clear(&ubc->arch);
@@ -1922,7 +1928,8 @@ static int migrate_pages_batch(struct list_head *from,
*/
init_tlb_ubc(&pending_ubc);
do_migrc = IS_ENABLED(CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH) &&
- (reason == MR_DEMOTION || reason == MR_NUMA_MISPLACED);
+ (reason == MR_DEMOTION || reason == MR_NUMA_MISPLACED) &&
+ !migrc_paused();
for (pass = 0; pass < nr_pass && retry; pass++) {
retry = 0;
@@ -1961,6 +1968,15 @@ static int migrate_pages_batch(struct list_head *from,
continue;
}
+ /*
+ * In case that the system is in high memory
+ * pressure, give up migrc mechanism this turn.
+ */
+ if (unlikely(do_migrc && migrc_paused())) {
+ fold_ubc(tlb_ubc, &pending_ubc);
+ do_migrc = false;
+ }
+
can_migrc_init();
rc = migrate_folio_unmap(get_new_folio, put_new_folio,
private, folio, &dst, mode, reason,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6ef0c22b1109..366777afce7f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4072,6 +4072,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
unsigned int cpuset_mems_cookie;
unsigned int zonelist_iter_cookie;
int reserve_flags;
+ bool migrc_paused = false;
restart:
compaction_retries = 0;
@@ -4203,6 +4204,16 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
if (page)
goto got_pg;
+ /*
+ * The system is in very high memory pressure. Pause migrc from
+ * expanding its pending queue temporarily.
+ */
+ if (!migrc_paused) {
+ migrc_pause();
+ migrc_paused = true;
+ migrc_flush_free_folios();
+ }
+
/* Caller is not willing to reclaim, we can't balance anything */
if (!can_direct_reclaim)
goto nopage;
@@ -4330,6 +4341,8 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
warn_alloc(gfp_mask, ac->nodemask,
"page allocation failure: order:%u", order);
got_pg:
+ if (migrc_paused)
+ migrc_resume();
return page;
}
--
2.17.1
