bpf: Convert percpu hash map to per-cpu bpf_mem_alloc.

Convert dynamic allocations in percpu hash map from alloc_percpu() to
bpf_mem_cache_alloc() from per-cpu bpf_mem_alloc. Since bpf_mem_alloc frees
objects after RCU gp the call_rcu() is removed. pcpu_init_value() now needs to
zero-fill per-cpu allocations, since dynamically allocated map elements are now
similar to full prealloc, since alloc_percpu() is not called inline and the
elements are reused in the freelist.
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/20220902211058.60789-12-alexei.starovoitov@gmail.com

kernel/bpf/hashtab.c

@@ -94,6 +94,7 @@ struct bucket {
 struct bpf_htab {
 	struct bpf_map map;
 	struct bpf_mem_alloc ma;
+	struct bpf_mem_alloc pcpu_ma;
 	struct bucket *buckets;
 	void *elems;
 	union {
@@ -121,14 +122,14 @@ struct htab_elem {
 		struct {
 			void *padding;
 			union {
-				struct bpf_htab *htab;
 				struct pcpu_freelist_node fnode;
 				struct htab_elem *batch_flink;
 			};
 		};
 	};
 	union {
-		struct rcu_head rcu;
+		/* pointer to per-cpu pointer */
+		void *ptr_to_pptr;
 		struct bpf_lru_node lru_node;
 	};
 	u32 hash;
@@ -448,8 +449,6 @@ static int htab_map_alloc_check(union bpf_attr *attr)
 	bool zero_seed = (attr->map_flags & BPF_F_ZERO_SEED);
 	int numa_node = bpf_map_attr_numa_node(attr);
 
-	BUILD_BUG_ON(offsetof(struct htab_elem, htab) !=
-		     offsetof(struct htab_elem, hash_node.pprev));
 	BUILD_BUG_ON(offsetof(struct htab_elem, fnode.next) !=
 		     offsetof(struct htab_elem, hash_node.pprev));
 
@@ -610,6 +609,12 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 		err = bpf_mem_alloc_init(&htab->ma, htab->elem_size, false);
 		if (err)
 			goto free_map_locked;
+		if (percpu) {
+			err = bpf_mem_alloc_init(&htab->pcpu_ma,
+						 round_up(htab->map.value_size, 8), true);
+			if (err)
+				goto free_map_locked;
+		}
 	}
 
 	return &htab->map;
@@ -620,6 +625,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 	for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++)
 		free_percpu(htab->map_locked[i]);
 	bpf_map_area_free(htab->buckets);
+	bpf_mem_alloc_destroy(&htab->pcpu_ma);
 	bpf_mem_alloc_destroy(&htab->ma);
 free_htab:
 	lockdep_unregister_key(&htab->lockdep_key);
@@ -895,19 +901,11 @@ static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l)
 {
 	if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH)
-		free_percpu(htab_elem_get_ptr(l, htab->map.key_size));
+		bpf_mem_cache_free(&htab->pcpu_ma, l->ptr_to_pptr);
 	check_and_free_fields(htab, l);
 	bpf_mem_cache_free(&htab->ma, l);
 }
 
-static void htab_elem_free_rcu(struct rcu_head *head)
-{
-	struct htab_elem *l = container_of(head, struct htab_elem, rcu);
-	struct bpf_htab *htab = l->htab;
-
-	htab_elem_free(htab, l);
-}
-
 static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l)
 {
 	struct bpf_map *map = &htab->map;
@@ -953,13 +951,8 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
 		__pcpu_freelist_push(&htab->freelist, &l->fnode);
 	} else {
 		dec_elem_count(htab);
-		if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH) {
-			l->htab = htab;
-			call_rcu(&l->rcu, htab_elem_free_rcu);
-		} else {
 		htab_elem_free(htab, l);
 	}
-	}
 }
 
 static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr,
@@ -983,13 +976,12 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr,
 static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr,
 			    void *value, bool onallcpus)
 {
-	/* When using prealloc and not setting the initial value on all cpus,
-	 * zero-fill element values for other cpus (just as what happens when
-	 * not using prealloc). Otherwise, bpf program has no way to ensure
+	/* When not setting the initial value on all cpus, zero-fill element
+	 * values for other cpus. Otherwise, bpf program has no way to ensure
 	 * known initial values for cpus other than current one
 	 * (onallcpus=false always when coming from bpf prog).
 	 */
-	if (htab_is_prealloc(htab) && !onallcpus) {
+	if (!onallcpus) {
 		u32 size = round_up(htab->map.value_size, 8);
 		int current_cpu = raw_smp_processor_id();
 		int cpu;
@@ -1060,18 +1052,18 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 
 	memcpy(l_new->key, key, key_size);
 	if (percpu) {
-		size = round_up(size, 8);
 		if (prealloc) {
 			pptr = htab_elem_get_ptr(l_new, key_size);
 		} else {
 			/* alloc_percpu zero-fills */
-			pptr = bpf_map_alloc_percpu(&htab->map, size, 8,
-						    GFP_NOWAIT | __GFP_NOWARN);
+			pptr = bpf_mem_cache_alloc(&htab->pcpu_ma);
 			if (!pptr) {
 				bpf_mem_cache_free(&htab->ma, l_new);
 				l_new = ERR_PTR(-ENOMEM);
 				goto dec_count;
 			}
+			l_new->ptr_to_pptr = pptr;
+			pptr = *(void **)pptr;
 		}
 
 		pcpu_init_value(htab, pptr, value, onallcpus);
@@ -1568,6 +1560,7 @@ static void htab_map_free(struct bpf_map *map)
 	bpf_map_free_kptr_off_tab(map);
 	free_percpu(htab->extra_elems);
 	bpf_map_area_free(htab->buckets);
+	bpf_mem_alloc_destroy(&htab->pcpu_ma);
 	bpf_mem_alloc_destroy(&htab->ma);
 	if (htab->use_percpu_counter)
 		percpu_counter_destroy(&htab->pcount);