[RFC PATCH 2/6] mm/page_counter: Introduce tiered memory awareness to page_counter

[Joshua Hahn]

On systems with tiered memory, there is currently no tracking of memory
at the tier-memcg granularity. While per-memcg-lruvec serves at a finer
granularity that can be accumulated to give us the desired
per-tier-memcg accounting, relying on these lruvec stats for limit
checking can prove touch too many hot paths too frequently and can
introduce increased latency for other memcg users.

Instead, add a new cacheline in struct page_counter to track toptier
memcg limits and usage, as well as cached capacity values. This
cacheline is only used by the mem_cgroup->memory page_counter.

Also, introduce helpers that use these new fields to calculate
proportional toptier high and low values, based on the system's
toptier:total capacity ratio.

Signed-off-by: Joshua Hahn <joshua.hahnjy@xxxxxxxxx>
---
 include/linux/page_counter.h | 22 +++++++++++++++++++++-
 mm/page_counter.c            | 34 ++++++++++++++++++++++++++++++++++
 2 files changed, 55 insertions(+), 1 deletion(-)

diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h
index d649b6bbbc87..128c1272c88c 100644
--- a/include/linux/page_counter.h
+++ b/include/linux/page_counter.h
@@ -5,6 +5,7 @@
 #include <linux/atomic.h>
 #include <linux/cache.h>
 #include <linux/limits.h>
+#include <linux/nodemask.h>
 #include <asm/page.h>
 
 struct page_counter {
@@ -31,9 +32,23 @@ struct page_counter {
 	/* Latest cg2 reset watermark */
 	unsigned long local_watermark;
 
-	/* Keep all the read most fields in a separete cacheline. */
+	/* Keep all the tiered memory fields in a separate cacheline. */
 	CACHELINE_PADDING(_pad2_);
 
+	atomic_long_t toptier_usage;
+
+	/* effective toptier-proportional low protection */
+	unsigned long etoptier_low;
+	atomic_long_t toptier_low_usage;
+	atomic_long_t children_toptier_low_usage;
+
+	/* Cached toptier capacity for proportional limit calculations */
+	unsigned long toptier_capacity;
+	unsigned long total_capacity;
+
+	/* Keep all the read most fields in a separate cacheline. */
+	CACHELINE_PADDING(_pad3_);
+
 	bool protection_support;
 	bool track_failcnt;
 	unsigned long min;
@@ -61,6 +76,9 @@ static inline void page_counter_init(struct page_counter *counter,
 	counter->parent = parent;
 	counter->protection_support = protection_support;
 	counter->track_failcnt = false;
+	counter->toptier_usage = (atomic_long_t)ATOMIC_LONG_INIT(0);
+	counter->toptier_capacity = 0;
+	counter->total_capacity = 0;
 }
 
 static inline unsigned long page_counter_read(struct page_counter *counter)
@@ -103,6 +121,8 @@ static inline void page_counter_reset_watermark(struct page_counter *counter)
 void page_counter_calculate_protection(struct page_counter *root,
 				       struct page_counter *counter,
 				       bool recursive_protection);
+unsigned long page_counter_toptier_high(struct page_counter *counter);
+unsigned long page_counter_toptier_low(struct page_counter *counter);
 #else
 static inline void page_counter_calculate_protection(struct page_counter *root,
 						     struct page_counter *counter,
diff --git a/mm/page_counter.c b/mm/page_counter.c
index 661e0f2a5127..5ec97811c418 100644
--- a/mm/page_counter.c
+++ b/mm/page_counter.c
@@ -462,4 +462,38 @@ void page_counter_calculate_protection(struct page_counter *root,
 			atomic_long_read(&parent->children_low_usage),
 			recursive_protection));
 }
+
+unsigned long page_counter_toptier_high(struct page_counter *counter)
+{
+	unsigned long high = READ_ONCE(counter->high);
+	unsigned long toptier_cap, total_cap;
+
+	if (high == PAGE_COUNTER_MAX)
+		return PAGE_COUNTER_MAX;
+
+	toptier_cap = counter->toptier_capacity;
+	total_cap = counter->total_capacity;
+
+	if (!total_cap)
+		return PAGE_COUNTER_MAX;
+
+	return mult_frac(high, toptier_cap, total_cap);
+}
+
+unsigned long page_counter_toptier_low(struct page_counter *counter)
+{
+	unsigned long low = READ_ONCE(counter->low);
+	unsigned long toptier_cap, total_cap;
+
+	if (!low)
+		return 0;
+
+	toptier_cap = counter->toptier_capacity;
+	total_cap = counter->total_capacity;
+
+	if (!total_cap)
+		return 0;
+
+	return mult_frac(low, toptier_cap, total_cap);
+}
 #endif /* CONFIG_MEMCG || CONFIG_CGROUP_DMEM */
-- 
2.47.3