[PATCH v6 2/5] mm/page_counter: introduce per-CPU stock

[Joshua Hahn <joshua.hahnjy@gmail.com>]

Introduce a copy of the seven-slot per-CPU stock representation from
memcg in the page_counter layer. struct page_counter_stock_pcp preserves
everything from struct memcg_stock_pcp, but adds a new backpointer to
the base of the percpu stock, since there will be multiple percpu stock
base pointers later in the series (one for memory, one for memsw).

struct page_counter also gets a pointer to the base of the percpu stock,
as well as a struct cgroup_subsys_state pointer to pin its owning CSS
as long as the cached counter remains reachable.

Let's also copy over the drain, refill, and "flush required" functions,
preserving all behaviors from the memcg equivalent. In this patch they
are not connected.

No functional changes intended.

Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Joshua Hahn <joshua.hahnjy@gmail.com>
---
 include/linux/page_counter.h |  31 +++++++++
 mm/page_counter.c            | 127 +++++++++++++++++++++++++++++++++++
 2 files changed, 158 insertions(+)

diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h
index 07b7cb12249c7..9cb5612fe190f 100644
--- a/include/linux/page_counter.h
+++ b/include/linux/page_counter.h
@@ -5,8 +5,30 @@
 #include <linux/atomic.h>
 #include <linux/cache.h>
 #include <linux/limits.h>
+#include <linux/percpu.h>
+#include <linux/local_lock.h>
+#include <linux/workqueue_types.h>
 #include <asm/page.h>
 
+/*
+ * The value of NR_PAGE_COUNTER_STOCK is selected to keep the cached counters
+ * and their nr_pages in a single cacheline. This may change in the future.
+ */
+#define NR_PAGE_COUNTER_STOCK 7
+#define PAGE_COUNTER_STOCK_BATCH 64UL
+struct cgroup_subsys_state;
+struct page_counter;
+struct page_counter_stock_pcp {
+	local_trylock_t lock;
+	u8 nr_pages[NR_PAGE_COUNTER_STOCK];
+	struct page_counter *cached[NR_PAGE_COUNTER_STOCK];
+
+	struct page_counter_stock_pcp __percpu *base;
+	struct work_struct work;
+	unsigned long flags;
+	u8 drain_idx;
+};
+
 struct page_counter {
 	/*
 	 * Make sure 'usage' does not share cacheline with any other field in
@@ -41,6 +63,8 @@ struct page_counter {
 	unsigned long high;
 	unsigned long max;
 	struct page_counter *parent;
+	struct page_counter_stock_pcp __percpu *stock;
+	struct cgroup_subsys_state *stock_css;
 } ____cacheline_internodealigned_in_smp;
 
 #if BITS_PER_LONG == 32
@@ -61,6 +85,8 @@ static inline void page_counter_init(struct page_counter *counter,
 	counter->parent = parent;
 	counter->protection_support = protection_support;
 	counter->track_failcnt = false;
+	counter->stock = NULL;
+	counter->stock_css = NULL;
 }
 
 static inline unsigned long page_counter_read(struct page_counter *counter)
@@ -74,6 +100,11 @@ void page_counter_charge(struct page_counter *counter, unsigned long nr_pages);
 bool page_counter_try_charge(struct page_counter *counter,
 			     unsigned long nr_pages,
 			     struct page_counter **fail);
+void page_counter_refill_stock(struct page_counter *counter,
+			       unsigned long nr_pages);
+void page_counter_drain_stock_fully(struct page_counter_stock_pcp *stock);
+bool page_counter_stock_flush_required(struct page_counter_stock_pcp *stock,
+				       struct cgroup_subsys_state *root_css);
 void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages);
 void page_counter_set_min(struct page_counter *counter, unsigned long nr_pages);
 void page_counter_set_low(struct page_counter *counter, unsigned long nr_pages);
diff --git a/mm/page_counter.c b/mm/page_counter.c
index 98322803941a7..480a447bd7265 100644
--- a/mm/page_counter.c
+++ b/mm/page_counter.c
@@ -7,6 +7,7 @@
 
 #include <linux/page_counter.h>
 #include <linux/atomic.h>
+#include <linux/cgroup.h>
 #include <linux/kernel.h>
 #include <linux/math64.h>
 #include <linux/string.h>
@@ -14,6 +15,14 @@
 #include <linux/bug.h>
 #include <asm/page.h>
 
+/*
+ * Watermarks for a charge stock slot, in the spirit of pcp->high and
+ * pcp->batch: PAGE_COUNTER_STOCK_HIGH is the high watermark at which a slot is
+ * trimmed down to PAGE_COUNTER_STOCK_LOW rather than emptied.
+ */
+#define PAGE_COUNTER_STOCK_LOW (PAGE_COUNTER_STOCK_BATCH / 2)
+#define PAGE_COUNTER_STOCK_HIGH PAGE_COUNTER_STOCK_BATCH
+
 static bool track_protection(struct page_counter *c)
 {
 	return c->protection_support;
@@ -192,6 +201,124 @@ bool page_counter_try_charge(struct page_counter *counter,
 	return false;
 }
 
+static void page_counter_drain_stock(struct page_counter_stock_pcp *stock,
+				     int i)
+{
+	struct page_counter *counter = READ_ONCE(stock->cached[i]);
+	u8 nr_pages;
+
+	if (!counter)
+		return;
+
+	nr_pages = READ_ONCE(stock->nr_pages[i]);
+	if (nr_pages) {
+		page_counter_uncharge(counter, nr_pages);
+		WRITE_ONCE(stock->nr_pages[i], 0);
+	}
+	css_put(counter->stock_css);
+	WRITE_ONCE(stock->cached[i], NULL);
+}
+
+void page_counter_drain_stock_fully(struct page_counter_stock_pcp *stock)
+{
+	int i;
+
+	for (i = 0; i < NR_PAGE_COUNTER_STOCK; i++)
+		page_counter_drain_stock(stock, i);
+}
+
+bool page_counter_stock_flush_required(struct page_counter_stock_pcp *stock,
+				       struct cgroup_subsys_state *root_css)
+{
+	struct cgroup_subsys_state *css;
+	struct page_counter *counter;
+	bool flush = false;
+	int i;
+
+	rcu_read_lock();
+	for (i = 0; i < NR_PAGE_COUNTER_STOCK; i++) {
+		counter = READ_ONCE(stock->cached[i]);
+		if (!counter)
+			continue;
+		css = READ_ONCE(counter->stock_css);
+
+		if (READ_ONCE(stock->nr_pages[i]) &&
+		    cgroup_is_descendant(css->cgroup, root_css->cgroup)) {
+			flush = true;
+			break;
+		}
+	}
+	rcu_read_unlock();
+	return flush;
+}
+
+/**
+ * page_counter_refill_stock - return pages to a counter's stock
+ * @counter: counter to return pages to
+ * @nr_pages: number of pages to return
+ *
+ * If the stock cannot accept the pages, uncharge them from the hierarchy.
+ */
+void page_counter_refill_stock(struct page_counter *counter,
+			       unsigned long nr_pages)
+{
+	struct page_counter_stock_pcp __percpu *stock = counter->stock;
+	struct page_counter_stock_pcp *pcp_stock;
+	unsigned int stock_pages;
+	int empty_slot = -1;
+	int i;
+
+	/*
+	 * nr_pages[] is a u8 and a slot is capped at PAGE_COUNTER_STOCK_HIGH.
+	 * Raising PAGE_COUNTER_STOCK_BATCH beyond 127 would need careful
+	 * handling of nr_pages[] in struct page_counter_stock_pcp.
+	 */
+	BUILD_BUG_ON(PAGE_COUNTER_STOCK_BATCH > S8_MAX);
+	BUILD_BUG_ON(PAGE_COUNTER_STOCK_HIGH > U8_MAX);
+
+	if (!stock || nr_pages > PAGE_COUNTER_STOCK_BATCH ||
+	    !local_trylock(&stock->lock)) {
+		/*
+		 * For a larger-than-batch refill or an unlikely failure to lock
+		 * the per-CPU stock, uncharge the hierarchy directly.
+		 */
+		page_counter_uncharge(counter, nr_pages);
+		return;
+	}
+
+	pcp_stock = this_cpu_ptr(stock);
+	for (i = 0; i < NR_PAGE_COUNTER_STOCK; i++) {
+		struct page_counter *cached = READ_ONCE(pcp_stock->cached[i]);
+
+		if (!cached && empty_slot == -1)
+			empty_slot = i;
+		if (counter != cached)
+			continue;
+
+		stock_pages = READ_ONCE(pcp_stock->nr_pages[i]) + nr_pages;
+		if (stock_pages > PAGE_COUNTER_STOCK_HIGH) {
+			page_counter_uncharge(counter,
+					      stock_pages - PAGE_COUNTER_STOCK_LOW);
+			stock_pages = PAGE_COUNTER_STOCK_LOW;
+		}
+		WRITE_ONCE(pcp_stock->nr_pages[i], stock_pages);
+		local_unlock(&stock->lock);
+		return;
+	}
+
+	i = empty_slot;
+	if (i == -1) {
+		i = pcp_stock->drain_idx++;
+		if (pcp_stock->drain_idx == NR_PAGE_COUNTER_STOCK)
+			pcp_stock->drain_idx = 0;
+		page_counter_drain_stock(pcp_stock, i);
+	}
+	css_get(counter->stock_css);
+	WRITE_ONCE(pcp_stock->cached[i], counter);
+	WRITE_ONCE(pcp_stock->nr_pages[i], nr_pages);
+	local_unlock(&stock->lock);
+}
+
 /**
  * page_counter_uncharge - hierarchically uncharge pages
  * @counter: counter
-- 
2.53.0-Meta