perf: Shrink the size of the recursion counter.

There are four recursion counter, one for each context. The type of the
counter is `int' but the counter is used as `bool' since it is only
incremented if zero.
The main goal here is to shrink the whole struct into 32bit int which
can later be added task_struct into an existing hole.

Reduce the type of the recursion counter to an unsigned char, keep the
increment/ decrement operation.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Marco Elver <elver@google.com>
Link: https://lore.kernel.org/r/20240704170424.1466941-5-bigeasy@linutronix.de

kernel/events/callchain.c

@@ -29,7 +29,7 @@ static inline size_t perf_callchain_entry__sizeof(void)
 				 sysctl_perf_event_max_contexts_per_stack));
 }
 
-static DEFINE_PER_CPU(int, callchain_recursion[PERF_NR_CONTEXTS]);
+static DEFINE_PER_CPU(u8, callchain_recursion[PERF_NR_CONTEXTS]);
 static atomic_t nr_callchain_events;
 static DEFINE_MUTEX(callchain_mutex);
 static struct callchain_cpus_entries *callchain_cpus_entries;

kernel/events/core.c

@@ -9765,7 +9765,7 @@ struct swevent_htable {
 	int				hlist_refcount;
 
 	/* Recursion avoidance in each contexts */
-	int				recursion[PERF_NR_CONTEXTS];
+	u8				recursion[PERF_NR_CONTEXTS];
 };
 
 static DEFINE_PER_CPU(struct swevent_htable, swevent_htable);

kernel/events/internal.h

@@ -208,7 +208,7 @@ arch_perf_out_copy_user(void *dst, const void *src, unsigned long n)
 
 DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user)
 
-static inline int get_recursion_context(int *recursion)
+static inline int get_recursion_context(u8 *recursion)
 {
 	unsigned char rctx = interrupt_context_level();
 
@@ -221,7 +221,7 @@ static inline int get_recursion_context(int *recursion)
 	return rctx;
 }
 
-static inline void put_recursion_context(int *recursion, int rctx)
+static inline void put_recursion_context(u8 *recursion, int rctx)
 {
 	barrier();
 	recursion[rctx]--;