bpf: Batch call_rcu callbacks instead of SLAB_TYPESAFE_BY_RCU.

SLAB_TYPESAFE_BY_RCU makes kmem_caches non mergeable and slows down
kmem_cache_destroy. All bpf_mem_cache are safe to share across different maps
and programs. Convert SLAB_TYPESAFE_BY_RCU to batched call_rcu. This change
solves the memory consumption issue, avoids kmem_cache_destroy latency and
keeps bpf hash map performance the same.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20220902211058.60789-10-alexei.starovoitov@gmail.com

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 7e5df68..5d8648a 100644 (file)
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -101,6 +101,11 @@ struct bpf_mem_cache {
        /* count of objects in free_llist */
        int free_cnt;
        int low_watermark, high_watermark, batch;
+
+       struct rcu_head rcu;
+       struct llist_head free_by_rcu;
+       struct llist_head waiting_for_gp;
+       atomic_t call_rcu_in_progress;
 };
 
 struct bpf_mem_caches {
@@ -194,6 +199,45 @@ static void free_one(struct bpf_mem_cache *c, void *obj)
                kfree(obj);
 }
 
+static void __free_rcu(struct rcu_head *head)
+{
+       struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu);
+       struct llist_node *llnode = llist_del_all(&c->waiting_for_gp);
+       struct llist_node *pos, *t;
+
+       llist_for_each_safe(pos, t, llnode)
+               free_one(c, pos);
+       atomic_set(&c->call_rcu_in_progress, 0);
+}
+
+static void enque_to_free(struct bpf_mem_cache *c, void *obj)
+{
+       struct llist_node *llnode = obj;
+
+       /* bpf_mem_cache is a per-cpu object. Freeing happens in irq_work.
+        * Nothing races to add to free_by_rcu list.
+        */
+       __llist_add(llnode, &c->free_by_rcu);
+}
+
+static void do_call_rcu(struct bpf_mem_cache *c)
+{
+       struct llist_node *llnode, *t;
+
+       if (atomic_xchg(&c->call_rcu_in_progress, 1))
+               return;
+
+       WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp));
+       llist_for_each_safe(llnode, t, __llist_del_all(&c->free_by_rcu))
+               /* There is no concurrent __llist_add(waiting_for_gp) access.
+                * It doesn't race with llist_del_all either.
+                * But there could be two concurrent llist_del_all(waiting_for_gp):
+                * from __free_rcu() and from drain_mem_cache().
+                */
+               __llist_add(llnode, &c->waiting_for_gp);
+       call_rcu(&c->rcu, __free_rcu);
+}
+
 static void free_bulk(struct bpf_mem_cache *c)
 {
        struct llist_node *llnode, *t;
@@ -212,12 +256,13 @@ static void free_bulk(struct bpf_mem_cache *c)
                local_dec(&c->active);
                if (IS_ENABLED(CONFIG_PREEMPT_RT))
                        local_irq_restore(flags);
-               free_one(c, llnode);
+               enque_to_free(c, llnode);
        } while (cnt > (c->high_watermark + c->low_watermark) / 2);
 
        /* and drain free_llist_extra */
        llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra))
-               free_one(c, llnode);
+               enque_to_free(c, llnode);
+       do_call_rcu(c);
 }
 
 static void bpf_mem_refill(struct irq_work *work)
@@ -303,7 +348,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size)
                        return -ENOMEM;
                size += LLIST_NODE_SZ; /* room for llist_node */
                snprintf(buf, sizeof(buf), "bpf-%u", size);
-               kmem_cache = kmem_cache_create(buf, size, 8, SLAB_TYPESAFE_BY_RCU, NULL);
+               kmem_cache = kmem_cache_create(buf, size, 8, 0, NULL);
                if (!kmem_cache) {
                        free_percpu(pc);
                        return -ENOMEM;
@@ -345,6 +390,15 @@ static void drain_mem_cache(struct bpf_mem_cache *c)
 {
        struct llist_node *llnode, *t;
 
+       /* The caller has done rcu_barrier() and no progs are using this
+        * bpf_mem_cache, but htab_map_free() called bpf_mem_cache_free() for
+        * all remaining elements and they can be in free_by_rcu or in
+        * waiting_for_gp lists, so drain those lists now.
+        */
+       llist_for_each_safe(llnode, t, __llist_del_all(&c->free_by_rcu))
+               free_one(c, llnode);
+       llist_for_each_safe(llnode, t, llist_del_all(&c->waiting_for_gp))
+               free_one(c, llnode);
        llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist))
                free_one(c, llnode);
        llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra))
@@ -366,6 +420,10 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
                kmem_cache_destroy(c->kmem_cache);
                if (c->objcg)
                        obj_cgroup_put(c->objcg);
+               /* c->waiting_for_gp list was drained, but __free_rcu might
+                * still execute. Wait for it now before we free 'c'.
+                */
+               rcu_barrier();
                free_percpu(ma->cache);
                ma->cache = NULL;
        }
@@ -379,6 +437,7 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
                }
                if (c->objcg)
                        obj_cgroup_put(c->objcg);
+               rcu_barrier();
                free_percpu(ma->caches);
                ma->caches = NULL;
        }

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4e9d462..074c901 100644 (file)
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -638,7 +638,10 @@ static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock)
                bpf_map_free_id(map, do_idr_lock);
                btf_put(map->btf);
                INIT_WORK(&map->work, bpf_map_free_deferred);
-               schedule_work(&map->work);
+               /* Avoid spawning kworkers, since they all might contend
+                * for the same mutex like slab_mutex.
+                */
+               queue_work(system_unbound_wq, &map->work);
        }
 }