Merge branch 'bpf-zero-hash-seed'

Lorenz Bauer says:

====================
Allow forcing the seed of a hash table to zero, for deterministic
execution during benchmarking and testing.

Changes from v2:
* Change ordering of BPF_F_ZERO_SEED in linux/bpf.h

Comments adressed from v1:
* Add comment to discourage production use to linux/bpf.h
* Require CAP_SYS_ADMIN
====================

Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

include/uapi/linux/bpf.h

@@ -257,9 +257,6 @@ enum bpf_attach_type {
 /* Specify numa node during map creation */
 #define BPF_F_NUMA_NODE		(1U << 2)
 
-/* flags for BPF_PROG_QUERY */
-#define BPF_F_QUERY_EFFECTIVE	(1U << 0)
-
 #define BPF_OBJ_NAME_LEN 16U
 
 /* Flags for accessing BPF object */
@@ -269,6 +266,12 @@ enum bpf_attach_type {
 /* Flag for stack_map, store build_id+offset instead of pointer */
 #define BPF_F_STACK_BUILD_ID	(1U << 5)
 
+/* Zero-initialize hash function seed. This should only be used for testing. */
+#define BPF_F_ZERO_SEED		(1U << 6)
+
+/* flags for BPF_PROG_QUERY */
+#define BPF_F_QUERY_EFFECTIVE	(1U << 0)
+
 enum bpf_stack_build_id_status {
 	/* user space need an empty entry to identify end of a trace */
 	BPF_STACK_BUILD_ID_EMPTY = 0,

kernel/bpf/hashtab.c

@@ -23,7 +23,7 @@
 
 #define HTAB_CREATE_FLAG_MASK						\
 	(BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE |	\
-	 BPF_F_RDONLY | BPF_F_WRONLY)
+	 BPF_F_RDONLY | BPF_F_WRONLY | BPF_F_ZERO_SEED)
 
 struct bucket {
 	struct hlist_nulls_head head;
@@ -244,6 +244,7 @@ static int htab_map_alloc_check(union bpf_attr *attr)
 	 */
 	bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU);
 	bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC);
+	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) !=
@@ -257,6 +258,10 @@ static int htab_map_alloc_check(union bpf_attr *attr)
 		 */
 		return -EPERM;
 
+	if (zero_seed && !capable(CAP_SYS_ADMIN))
+		/* Guard against local DoS, and discourage production use. */
+		return -EPERM;
+
 	if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK)
 		/* reserved bits should not be used */
 		return -EINVAL;
@@ -373,7 +378,11 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 	if (!htab->buckets)
 		goto free_htab;
 
-	htab->hashrnd = get_random_int();
+	if (htab->map.map_flags & BPF_F_ZERO_SEED)
+		htab->hashrnd = 0;
+	else
+		htab->hashrnd = get_random_int();
+
 	for (i = 0; i < htab->n_buckets; i++) {
 		INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i);
 		raw_spin_lock_init(&htab->buckets[i].lock);

tools/include/uapi/linux/bpf.h

@@ -257,9 +257,6 @@ enum bpf_attach_type {
 /* Specify numa node during map creation */
 #define BPF_F_NUMA_NODE		(1U << 2)
 
-/* flags for BPF_PROG_QUERY */
-#define BPF_F_QUERY_EFFECTIVE	(1U << 0)
-
 #define BPF_OBJ_NAME_LEN 16U
 
 /* Flags for accessing BPF object */
@@ -269,6 +266,12 @@ enum bpf_attach_type {
 /* Flag for stack_map, store build_id+offset instead of pointer */
 #define BPF_F_STACK_BUILD_ID	(1U << 5)
 
+/* Zero-initialize hash function seed. This should only be used for testing. */
+#define BPF_F_ZERO_SEED		(1U << 6)
+
+/* flags for BPF_PROG_QUERY */
+#define BPF_F_QUERY_EFFECTIVE	(1U << 0)
+
 enum bpf_stack_build_id_status {
 	/* user space need an empty entry to identify end of a trace */
 	BPF_STACK_BUILD_ID_EMPTY = 0,
@@ -2201,6 +2204,8 @@ union bpf_attr {
  *		**CONFIG_NET** configuration option.
  *	Return
  *		Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *		For sockets with reuseport option, *struct bpf_sock*
+ *		return is from reuse->socks[] using hash of the packet.
  *
  * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
  *	Description
@@ -2233,6 +2238,8 @@ union bpf_attr {
  *		**CONFIG_NET** configuration option.
  *	Return
  *		Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *		For sockets with reuseport option, *struct bpf_sock*
+ *		return is from reuse->socks[] using hash of the packet.
  *
  * int bpf_sk_release(struct bpf_sock *sk)
  *	Description

tools/testing/selftests/bpf/test_maps.c

@@ -258,23 +258,35 @@ static void test_hashmap_percpu(int task, void *data)
 	close(fd);
 }
 
+static int helper_fill_hashmap(int max_entries)
+{
+	int i, fd, ret;
+	long long key, value;
+
+	fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
+			    max_entries, map_flags);
+	CHECK(fd < 0,
+	      "failed to create hashmap",
+	      "err: %s, flags: 0x%x\n", strerror(errno), map_flags);
+
+	for (i = 0; i < max_entries; i++) {
+		key = i; value = key;
+		ret = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST);
+		CHECK(ret != 0,
+		      "can't update hashmap",
+		      "err: %s\n", strerror(ret));
+	}
+
+	return fd;
+}
+
 static void test_hashmap_walk(int task, void *data)
 {
 	int fd, i, max_entries = 1000;
 	long long key, value, next_key;
 	bool next_key_valid = true;
 
-	fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
-			    max_entries, map_flags);
-	if (fd < 0) {
-		printf("Failed to create hashmap '%s'!\n", strerror(errno));
-		exit(1);
-	}
-
-	for (i = 0; i < max_entries; i++) {
-		key = i; value = key;
-		assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == 0);
-	}
+	fd = helper_fill_hashmap(max_entries);
 
 	for (i = 0; bpf_map_get_next_key(fd, !i ? NULL : &key,
 					 &next_key) == 0; i++) {
@@ -306,6 +318,39 @@ static void test_hashmap_walk(int task, void *data)
 	close(fd);
 }
 
+static void test_hashmap_zero_seed(void)
+{
+	int i, first, second, old_flags;
+	long long key, next_first, next_second;
+
+	old_flags = map_flags;
+	map_flags |= BPF_F_ZERO_SEED;
+
+	first = helper_fill_hashmap(3);
+	second = helper_fill_hashmap(3);
+
+	for (i = 0; ; i++) {
+		void *key_ptr = !i ? NULL : &key;
+
+		if (bpf_map_get_next_key(first, key_ptr, &next_first) != 0)
+			break;
+
+		CHECK(bpf_map_get_next_key(second, key_ptr, &next_second) != 0,
+		      "next_key for second map must succeed",
+		      "key_ptr: %p", key_ptr);
+		CHECK(next_first != next_second,
+		      "keys must match",
+		      "i: %d first: %lld second: %lld\n", i,
+		      next_first, next_second);
+
+		key = next_first;
+	}
+
+	map_flags = old_flags;
+	close(first);
+	close(second);
+}
+
 static void test_arraymap(int task, void *data)
 {
 	int key, next_key, fd;
@@ -1534,6 +1579,7 @@ static void run_all_tests(void)
 	test_hashmap(0, NULL);
 	test_hashmap_percpu(0, NULL);
 	test_hashmap_walk(0, NULL);
+	test_hashmap_zero_seed();
 
 	test_arraymap(0, NULL);
 	test_arraymap_percpu(0, NULL);