bpf: Add hashtab support for bpf_for_each_map_elem() helper

This patch added support for hashmap, percpu hashmap,
lru hashmap and percpu lru hashmap.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210226204927.3885020-1-yhs@fb.com

2 files changed, 92 insertions, 0 deletions

diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index d63912e73ad9..330d721dd2af 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -1869,6 +1869,63 @@ static const struct bpf_iter_seq_info iter_seq_info = {
 	.seq_priv_size		= sizeof(struct bpf_iter_seq_hash_map_info),
 };
 
+static int bpf_for_each_hash_elem(struct bpf_map *map, void *callback_fn,
+				  void *callback_ctx, u64 flags)
+{
+	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+	struct hlist_nulls_head *head;
+	struct hlist_nulls_node *n;
+	struct htab_elem *elem;
+	u32 roundup_key_size;
+	int i, num_elems = 0;
+	void __percpu *pptr;
+	struct bucket *b;
+	void *key, *val;
+	bool is_percpu;
+	u64 ret = 0;
+
+	if (flags != 0)
+		return -EINVAL;
+
+	is_percpu = htab_is_percpu(htab);
+
+	roundup_key_size = round_up(map->key_size, 8);
+	/* disable migration so percpu value prepared here will be the
+	 * same as the one seen by the bpf program with bpf_map_lookup_elem().
+	 */
+	if (is_percpu)
+		migrate_disable();
+	for (i = 0; i < htab->n_buckets; i++) {
+		b = &htab->buckets[i];
+		rcu_read_lock();
+		head = &b->head;
+		hlist_nulls_for_each_entry_rcu(elem, n, head, hash_node) {
+			key = elem->key;
+			if (is_percpu) {
+				/* current cpu value for percpu map */
+				pptr = htab_elem_get_ptr(elem, map->key_size);
+				val = this_cpu_ptr(pptr);
+			} else {
+				val = elem->key + roundup_key_size;
+			}
+			num_elems++;
+			ret = BPF_CAST_CALL(callback_fn)((u64)(long)map,
+					(u64)(long)key, (u64)(long)val,
+					(u64)(long)callback_ctx, 0);
+			/* return value: 0 - continue, 1 - stop and return */
+			if (ret) {
+				rcu_read_unlock();
+				goto out;
+			}
+		}
+		rcu_read_unlock();
+	}
+out:
+	if (is_percpu)
+		migrate_enable();
+	return num_elems;
+}
+
 static int htab_map_btf_id;
 const struct bpf_map_ops htab_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
@@ -1881,6 +1938,8 @@ const struct bpf_map_ops htab_map_ops = {
 	.map_delete_elem = htab_map_delete_elem,
 	.map_gen_lookup = htab_map_gen_lookup,
 	.map_seq_show_elem = htab_map_seq_show_elem,
+	.map_set_for_each_callback_args = map_set_for_each_callback_args,
+	.map_for_each_callback = bpf_for_each_hash_elem,
 	BATCH_OPS(htab),
 	.map_btf_name = "bpf_htab",
 	.map_btf_id = &htab_map_btf_id,
@@ -1900,6 +1959,8 @@ const struct bpf_map_ops htab_lru_map_ops = {
 	.map_delete_elem = htab_lru_map_delete_elem,
 	.map_gen_lookup = htab_lru_map_gen_lookup,
 	.map_seq_show_elem = htab_map_seq_show_elem,
+	.map_set_for_each_callback_args = map_set_for_each_callback_args,
+	.map_for_each_callback = bpf_for_each_hash_elem,
 	BATCH_OPS(htab_lru),
 	.map_btf_name = "bpf_htab",
 	.map_btf_id = &htab_lru_map_btf_id,
@@ -2019,6 +2080,8 @@ const struct bpf_map_ops htab_percpu_map_ops = {
 	.map_update_elem = htab_percpu_map_update_elem,
 	.map_delete_elem = htab_map_delete_elem,
 	.map_seq_show_elem = htab_percpu_map_seq_show_elem,
+	.map_set_for_each_callback_args = map_set_for_each_callback_args,
+	.map_for_each_callback = bpf_for_each_hash_elem,
 	BATCH_OPS(htab_percpu),
 	.map_btf_name = "bpf_htab",
 	.map_btf_id = &htab_percpu_map_btf_id,
@@ -2036,6 +2099,8 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = {
 	.map_update_elem = htab_lru_percpu_map_update_elem,
 	.map_delete_elem = htab_lru_map_delete_elem,
 	.map_seq_show_elem = htab_percpu_map_seq_show_elem,
+	.map_set_for_each_callback_args = map_set_for_each_callback_args,
+	.map_for_each_callback = bpf_for_each_hash_elem,
 	BATCH_OPS(htab_lru_percpu),
 	.map_btf_name = "bpf_htab",
 	.map_btf_id = &htab_lru_percpu_map_btf_id,
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 53afe9461b03..9fe90ce52a65 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5403,6 +5403,33 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 	return 0;
 }
 
+int map_set_for_each_callback_args(struct bpf_verifier_env *env,
+				   struct bpf_func_state *caller,
+				   struct bpf_func_state *callee)
+{
+	/* bpf_for_each_map_elem(struct bpf_map *map, void *callback_fn,
+	 *      void *callback_ctx, u64 flags);
+	 * callback_fn(struct bpf_map *map, void *key, void *value,
+	 *      void *callback_ctx);
+	 */
+	callee->regs[BPF_REG_1] = caller->regs[BPF_REG_1];
+
+	callee->regs[BPF_REG_2].type = PTR_TO_MAP_KEY;
+	__mark_reg_known_zero(&callee->regs[BPF_REG_2]);
+	callee->regs[BPF_REG_2].map_ptr = caller->regs[BPF_REG_1].map_ptr;
+
+	callee->regs[BPF_REG_3].type = PTR_TO_MAP_VALUE;
+	__mark_reg_known_zero(&callee->regs[BPF_REG_3]);
+	callee->regs[BPF_REG_3].map_ptr = caller->regs[BPF_REG_1].map_ptr;
+
+	/* pointer to stack or null */
+	callee->regs[BPF_REG_4] = caller->regs[BPF_REG_3];
+
+	/* unused */
+	__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
+	return 0;
+}
+
 static int set_callee_state(struct bpf_verifier_env *env,
 			    struct bpf_func_state *caller,
 			    struct bpf_func_state *callee, int insn_idx)