[PATCH v20 6/6] lib: inline percpu_counter_tree_items_size with boot-safety sentinel

[Mathieu Desnoyers]

Replace the out-of-line percpu_counter_tree_items_size() function with a
static inline that loads the __ro_after_init variable
__percpu_counter_tree_items_size directly. This eliminates a function
call on paths that compute mm_struct flexible array layout offsets.

Initialize the variable to SIZE_MAX as a sentinel value, and add a
WARN_ON_ONCE check in the inline accessor to catch any accidental use
before percpu_counter_tree_subsystem_init() sets the real value based on
nr_cpu_ids. An early misuse would produce an absurd offset that triggers
the warning with a stack trace pointing at the offending caller, rather
than silently computing wrong memory offsets.

percpu_counter_tree_subsystem_init() sets the variable to the runtime
value immediately after deriving counter_config from nr_cpu_ids,
before calculate_accuracy_topology(). After boot, __ro_after_init moves
the variable into read-only memory.

On !CONFIG_SMP, the existing inline returning 0 is unchanged and
requires no sentinel.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
---
 include/linux/percpu_counter_tree.h | 19 ++++++++++++++++++-
 lib/percpu_counter_tree.c           | 24 ++++++++----------------
 2 files changed, 26 insertions(+), 17 deletions(-)

diff --git a/include/linux/percpu_counter_tree.h b/include/linux/percpu_counter_tree.h
index 3e8a820e2d1d..4095acdc879b 100644
--- a/include/linux/percpu_counter_tree.h
+++ b/include/linux/percpu_counter_tree.h
@@ -101,7 +101,24 @@ struct percpu_counter_tree {
 	} approx_accuracy_range;
 };
 
-size_t percpu_counter_tree_items_size(void);
+extern size_t __percpu_counter_tree_items_size __ro_after_init;
+
+/*
+ * percpu_counter_tree_items_size - Query the size required for counter tree items.
+ *
+ * Query the size of the memory area required to hold the counter tree
+ * items. This depends on the hardware topology and is invariant after
+ * boot.
+ *
+ * Return: Size required to hold tree items.
+ */
+static inline
+size_t percpu_counter_tree_items_size(void)
+{
+	WARN_ON_ONCE(__percpu_counter_tree_items_size == SIZE_MAX);
+	return __percpu_counter_tree_items_size;
+}
+
 int percpu_counter_tree_init_many(struct percpu_counter_tree *counters, struct percpu_counter_tree_level_item *items,
 				  unsigned int nr_counters, unsigned long batch_size, gfp_t gfp_flags);
 int percpu_counter_tree_init(struct percpu_counter_tree *counter, struct percpu_counter_tree_level_item *items,
diff --git a/lib/percpu_counter_tree.c b/lib/percpu_counter_tree.c
index 5c8fc2dcdc16..cfa5b04e05d7 100644
--- a/lib/percpu_counter_tree.c
+++ b/lib/percpu_counter_tree.c
@@ -653,22 +653,9 @@ void percpu_counter_tree_set(struct percpu_counter_tree *counter, long v)
 }
 EXPORT_SYMBOL_GPL(percpu_counter_tree_set);
 
-/*
- * percpu_counter_tree_items_size - Query the size required for counter tree items.
- *
- * Query the size of the memory area required to hold the counter tree
- * items. This depends on the hardware topology and is invariant after
- * boot.
- *
- * Return: Size required to hold tree items.
- */
-size_t percpu_counter_tree_items_size(void)
-{
-	if (!nr_cpus_order)
-		return 0;
-	return counter_config->nr_items * sizeof(struct percpu_counter_tree_level_item);
-}
-EXPORT_SYMBOL_GPL(percpu_counter_tree_items_size);
+/* Initialize to SIZE_MAX to catch early boot misuses. */
+size_t __percpu_counter_tree_items_size __ro_after_init = SIZE_MAX;
+EXPORT_SYMBOL_GPL(__percpu_counter_tree_items_size);
 
 static void __init calculate_accuracy_topology(void)
 {
@@ -697,6 +684,11 @@ int __init percpu_counter_tree_subsystem_init(void)
 		return -1;
 	}
 	counter_config = &per_nr_cpu_order_config[nr_cpus_order];
+	if (!nr_cpus_order)
+		__percpu_counter_tree_items_size = 0;
+	else
+		__percpu_counter_tree_items_size = counter_config->nr_items *
+			sizeof(struct percpu_counter_tree_level_item);
 	calculate_accuracy_topology();
 	return 0;
 }
-- 
2.43.0