slab: Make slub local_(try)lock more precise for LOCKDEP

kmalloc_nolock() can be called from any context
the ___slab_alloc() can acquire local_trylock_t (which is rt_spin_lock
in PREEMPT_RT) and attempt to acquire a different local_trylock_t
while in the same task context.

The calling sequence might look like:
kmalloc() -> tracepoint -> bpf -> kmalloc_nolock()

or more precisely:
__lock_acquire+0x12ad/0x2590
lock_acquire+0x133/0x2d0
rt_spin_lock+0x6f/0x250
___slab_alloc+0xb7/0xec0
kmalloc_nolock_noprof+0x15a/0x430
my_debug_callback+0x20e/0x390 [testmod]
___slab_alloc+0x256/0xec0
__kmalloc_cache_noprof+0xd6/0x3b0

Make LOCKDEP understand that local_trylock_t-s protect
different kmem_caches. In order to do that add lock_class_key
for each kmem_cache and use that key in local_trylock_t.

This stack trace is possible on both PREEMPT_RT and !PREEMPT_RT,
but teach lockdep about it only for PREEMPT_RT, since
in !PREEMPT_RT the ___slab_alloc() code is using
local_trylock_irqsave() when lockdep is on.

Note, this patch applies this logic to local_lock_t
while the next one converts it to local_trylock_t.
Both are mapped to rt_spin_lock in PREEMPT_RT.

Signed-off-by: Alexei Starovoitov <[email protected]>
Signed-off-by: Vlastimil Babka <[email protected]>

Author: Alexei Starovoitov

mm/slab.h

@@ -234,6 +234,7 @@ struct kmem_cache_order_objects {
 struct kmem_cache {
 #ifndef CONFIG_SLUB_TINY
 	struct kmem_cache_cpu __percpu *cpu_slab;
+	struct lock_class_key lock_key;
 #endif
 	struct slub_percpu_sheaves __percpu *cpu_sheaves;
 	/* Used for retrieving partial slabs, etc. */

mm/slub.c

@@ -3586,12 +3586,29 @@ static inline void note_cmpxchg_failure(const char *n,
 
 static void init_kmem_cache_cpus(struct kmem_cache *s)
 {
+#ifdef CONFIG_PREEMPT_RT
+	/*
+	 * Register lockdep key for non-boot kmem caches to avoid
+	 * WARN_ON_ONCE(static_obj(key))) in lockdep_register_key()
+	 */
+	bool finegrain_lockdep = !init_section_contains(s, 1);
+#else
+	/*
+	 * Don't bother with different lockdep classes for each
+	 * kmem_cache, since we only use local_trylock_irqsave().
+	 */
+	bool finegrain_lockdep = false;
+#endif
 	int cpu;
 	struct kmem_cache_cpu *c;
 
+	if (finegrain_lockdep)
+		lockdep_register_key(&s->lock_key);
 	for_each_possible_cpu(cpu) {
 		c = per_cpu_ptr(s->cpu_slab, cpu);
 		local_lock_init(&c->lock);
+		if (finegrain_lockdep)
+			lockdep_set_class(&c->lock, &s->lock_key);
 		c->tid = init_tid(cpu);
 	}
 }
@@ -7210,6 +7227,9 @@ void __kmem_cache_release(struct kmem_cache *s)
 	if (s->cpu_sheaves)
 		pcs_destroy(s);
 #ifndef CONFIG_SLUB_TINY
+#ifdef CONFIG_PREEMPT_RT
+	lockdep_unregister_key(&s->lock_key);
+#endif
 	free_percpu(s->cpu_slab);
 #endif
 	free_kmem_cache_nodes(s);