[PATCH 3/6] memcg: group the write-hot fields of struct mem_cgroup

[Shakeel Butt <shakeel.butt@linux.dev>]

These fields are written on the charge, reclaim and socket paths:

  socket_pressure       written by reclaim, read on every socket charge
  memory_events         bumped for this memcg and every ancestor, so a
                        busy child dirties the whole chain
  memory_events_local
  vmpressure            written on every reclaim iteration
  private_id_ref        written on every swap charge and uncharge
  kmem_stat
  high_irq_work, high_work

They are spread over the struct today and share cache lines with
read-mostly fields. Put them in one cache line group.

socket_pressure is kept next to memory_events because
mem_cgroup_sk_under_memory_pressure() reads one and bumps the other.

Add memcg_struct_check() so the build fails if a field lands outside
its group.

No functional change.

Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev>
---
 include/linux/memcontrol.h | 59 ++++++++++++++++++++++----------------
 mm/memcontrol.c            | 32 +++++++++++++++++++++
 2 files changed, 66 insertions(+), 25 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 46fc99786ebd..32b77ec5ba98 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -185,7 +185,6 @@ struct mem_cgroup {
 
 	/* Private memcg ID. Used to ID objects that outlive the cgroup */
 	int private_id;
-	refcount_t private_id_ref;
 
 	/* Accounted resources */
 	struct page_counter memory;		/* Both v1 & v2 */
@@ -195,15 +194,45 @@ struct mem_cgroup {
 		struct page_counter memsw;	/* v1 only */
 	};
 
-	/* registered local peak watchers */
-	struct list_head memory_peaks;
-	struct list_head swap_peaks;
-	spinlock_t	 peaks_lock;
+	/* Written on the charge, reclaim and socket paths. */
+	__cacheline_group_begin_aligned(memcg_write_hot);
+	/*
+	 * Hint of reclaim pressure for socket memory management. Note
+	 * that this indicator should NOT be used in legacy cgroup mode
+	 * where socket memory is accounted/charged separately.
+	 */
+	u64			socket_pressure;
+#if BITS_PER_LONG < 64
+	seqlock_t		socket_pressure_seqlock;
+#endif
+	/*
+	 * memory.events is bumped for this memcg and all its ancestors, so a
+	 * busy child dirties every ancestor.
+	 */
+	atomic_long_t		memory_events[MEMCG_NR_MEMORY_EVENTS];
+	atomic_long_t		memory_events_local[MEMCG_NR_MEMORY_EVENTS];
+
+	/* vmpressure notifications. Written on every reclaim iteration. */
+	struct vmpressure vmpressure;
+
+	/* Written on every swap charge and uncharge. */
+	refcount_t private_id_ref;
 
+#ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC
+	/* MEMCG_KMEM for nmi context */
+	atomic_t		kmem_stat;
+#endif
 	/* Range enforcement for interrupt charges */
 	struct irq_work high_irq_work;
 	struct work_struct high_work;
 
+	__cacheline_group_end_aligned(memcg_write_hot);
+
+	/* registered local peak watchers */
+	struct list_head memory_peaks;
+	struct list_head swap_peaks;
+	spinlock_t	 peaks_lock;
+
 #ifdef CONFIG_ZSWAP
 	unsigned long zswap_max;
 
@@ -214,9 +243,6 @@ struct mem_cgroup {
 	bool zswap_writeback;
 #endif
 
-	/* vmpressure notifications */
-	struct vmpressure vmpressure;
-
 	/*
 	 * Should the OOM killer kill all belonging tasks, had it kill one?
 	 */
@@ -232,23 +258,6 @@ struct mem_cgroup {
 	/* memory.stat */
 	struct memcg_vmstats	*vmstats;
 
-	/* memory.events */
-	atomic_long_t		memory_events[MEMCG_NR_MEMORY_EVENTS];
-	atomic_long_t		memory_events_local[MEMCG_NR_MEMORY_EVENTS];
-
-#ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC
-	/* MEMCG_KMEM for nmi context */
-	atomic_t		kmem_stat;
-#endif
-	/*
-	 * Hint of reclaim pressure for socket memroy management. Note
-	 * that this indicator should NOT be used in legacy cgroup mode
-	 * where socket memory is accounted/charged separately.
-	 */
-	u64			socket_pressure;
-#if BITS_PER_LONG < 64
-	seqlock_t		socket_pressure_seqlock;
-#endif
 	int kmemcg_id;
 
 #ifdef CONFIG_CGROUP_WRITEBACK
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c42297ae3b0e..2e209dedeb4f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5726,6 +5726,36 @@ __setup("cgroup.memory=", cgroup_memory);
  * basically everything that doesn't depend on a specific mem_cgroup structure
  * should be initialized from here.
  */
+/*
+ * Fields are grouped by access pattern. Putting a field in the wrong group
+ * breaks the build here.
+ */
+static void __init memcg_struct_check(void)
+{
+	CACHELINE_ASSERT_GROUP_MEMBER(struct mem_cgroup, memcg_write_hot,
+				      socket_pressure);
+#if BITS_PER_LONG < 64
+	CACHELINE_ASSERT_GROUP_MEMBER(struct mem_cgroup, memcg_write_hot,
+				      socket_pressure_seqlock);
+#endif
+	CACHELINE_ASSERT_GROUP_MEMBER(struct mem_cgroup, memcg_write_hot,
+				      memory_events);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct mem_cgroup, memcg_write_hot,
+				      memory_events_local);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct mem_cgroup, memcg_write_hot,
+				      vmpressure);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct mem_cgroup, memcg_write_hot,
+				      private_id_ref);
+#ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC
+	CACHELINE_ASSERT_GROUP_MEMBER(struct mem_cgroup, memcg_write_hot,
+				      kmem_stat);
+#endif
+	CACHELINE_ASSERT_GROUP_MEMBER(struct mem_cgroup, memcg_write_hot,
+				      high_irq_work);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct mem_cgroup, memcg_write_hot,
+				      high_work);
+}
+
 int __init mem_cgroup_init(void)
 {
 	unsigned int memcg_size;
@@ -5739,6 +5769,8 @@ int __init mem_cgroup_init(void)
 	 */
 	BUILD_BUG_ON(MEMCG_CHARGE_BATCH > S32_MAX / PAGE_SIZE);
 
+	memcg_struct_check();
+
 	cpuhp_setup_state_nocalls(CPUHP_MM_MEMCQ_DEAD, "mm/memctrl:dead", NULL,
 				  memcg_hotplug_cpu_dead);
 
-- 
2.53.0-Meta