summaryrefslogtreecommitdiffstats
path: root/include
diff options
context:
space:
mode:
Diffstat (limited to 'include')
-rw-r--r--include/linux/mm_inline.h36
-rw-r--r--include/linux/mmzone.h41
-rw-r--r--include/linux/page-flags-layout.h5
3 files changed, 81 insertions, 1 deletions
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 2ff703900fd0..f2b2296a42f9 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -121,6 +121,33 @@ static inline int lru_gen_from_seq(unsigned long seq)
return seq % MAX_NR_GENS;
}
+static inline int lru_hist_from_seq(unsigned long seq)
+{
+ return seq % NR_HIST_GENS;
+}
+
+static inline int lru_tier_from_refs(int refs)
+{
+ VM_WARN_ON_ONCE(refs > BIT(LRU_REFS_WIDTH));
+
+ /* see the comment in folio_lru_refs() */
+ return order_base_2(refs + 1);
+}
+
+static inline int folio_lru_refs(struct folio *folio)
+{
+ unsigned long flags = READ_ONCE(folio->flags);
+ bool workingset = flags & BIT(PG_workingset);
+
+ /*
+ * Return the number of accesses beyond PG_referenced, i.e., N-1 if the
+ * total number of accesses is N>1, since N=0,1 both map to the first
+ * tier. lru_tier_from_refs() will account for this off-by-one. Also see
+ * the comment on MAX_NR_TIERS.
+ */
+ return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + workingset;
+}
+
static inline int folio_lru_gen(struct folio *folio)
{
unsigned long flags = READ_ONCE(folio->flags);
@@ -173,6 +200,15 @@ static inline void lru_gen_update_size(struct lruvec *lruvec, struct folio *foli
__update_lru_size(lruvec, lru, zone, -delta);
return;
}
+
+ /* promotion */
+ if (!lru_gen_is_active(lruvec, old_gen) && lru_gen_is_active(lruvec, new_gen)) {
+ __update_lru_size(lruvec, lru, zone, -delta);
+ __update_lru_size(lruvec, lru + LRU_ACTIVE, zone, delta);
+ }
+
+ /* demotion requires isolation, e.g., lru_deactivate_fn() */
+ VM_WARN_ON_ONCE(lru_gen_is_active(lruvec, old_gen) && !lru_gen_is_active(lruvec, new_gen));
}
static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 6f4ea078d90f..7e343420bfb1 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -350,6 +350,28 @@ enum lruvec_flags {
#define MIN_NR_GENS 2U
#define MAX_NR_GENS 4U
+/*
+ * Each generation is divided into multiple tiers. A page accessed N times
+ * through file descriptors is in tier order_base_2(N). A page in the first tier
+ * (N=0,1) is marked by PG_referenced unless it was faulted in through page
+ * tables or read ahead. A page in any other tier (N>1) is marked by
+ * PG_referenced and PG_workingset. This implies a minimum of two tiers is
+ * supported without using additional bits in folio->flags.
+ *
+ * In contrast to moving across generations which requires the LRU lock, moving
+ * across tiers only involves atomic operations on folio->flags and therefore
+ * has a negligible cost in the buffered access path. In the eviction path,
+ * comparisons of refaulted/(evicted+protected) from the first tier and the
+ * rest infer whether pages accessed multiple times through file descriptors
+ * are statistically hot and thus worth protecting.
+ *
+ * MAX_NR_TIERS is set to 4 so that the multi-gen LRU can support twice the
+ * number of categories of the active/inactive LRU when keeping track of
+ * accesses through file descriptors. This uses MAX_NR_TIERS-2 spare bits in
+ * folio->flags.
+ */
+#define MAX_NR_TIERS 4U
+
#ifndef __GENERATING_BOUNDS_H
struct lruvec;
@@ -364,6 +386,16 @@ enum {
LRU_GEN_FILE,
};
+#define MIN_LRU_BATCH BITS_PER_LONG
+#define MAX_LRU_BATCH (MIN_LRU_BATCH * 64)
+
+/* whether to keep historical stats from evicted generations */
+#ifdef CONFIG_LRU_GEN_STATS
+#define NR_HIST_GENS MAX_NR_GENS
+#else
+#define NR_HIST_GENS 1U
+#endif
+
/*
* The youngest generation number is stored in max_seq for both anon and file
* types as they are aged on an equal footing. The oldest generation numbers are
@@ -386,6 +418,15 @@ struct lru_gen_struct {
struct list_head lists[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES];
/* the multi-gen LRU sizes, eventually consistent */
long nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES];
+ /* the exponential moving average of refaulted */
+ unsigned long avg_refaulted[ANON_AND_FILE][MAX_NR_TIERS];
+ /* the exponential moving average of evicted+protected */
+ unsigned long avg_total[ANON_AND_FILE][MAX_NR_TIERS];
+ /* the first tier doesn't need protection, hence the minus one */
+ unsigned long protected[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS - 1];
+ /* can be modified without holding the LRU lock */
+ atomic_long_t evicted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS];
+ atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS];
};
void lru_gen_init_lruvec(struct lruvec *lruvec);
diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h
index 240905407a18..7d79818dc065 100644
--- a/include/linux/page-flags-layout.h
+++ b/include/linux/page-flags-layout.h
@@ -106,7 +106,10 @@
#error "Not enough bits in page flags"
#endif
-#define LRU_REFS_WIDTH 0
+/* see the comment on MAX_NR_TIERS */
+#define LRU_REFS_WIDTH min(__LRU_REFS_WIDTH, BITS_PER_LONG - NR_PAGEFLAGS - \
+ ZONES_WIDTH - LRU_GEN_WIDTH - SECTIONS_WIDTH - \
+ NODES_WIDTH - KASAN_TAG_WIDTH - LAST_CPUPID_WIDTH)
#endif
#endif /* _LINUX_PAGE_FLAGS_LAYOUT */