Merge branch 'Sockmap copying'

Lorenz Bauer says:

====================
Changes in v2:
- Check sk_fullsock in map_update_elem (Martin)

Enable calling map_update_elem on sockmaps from bpf_iter context. This
in turn allows us to copy a sockmap by iterating its elements.

The change itself is tiny, all thanks to the ground work from Martin,
whose series [1] this patch is based on. I updated the tests to do some
copying, and also included two cleanups.

I'm sending this out now rather than when Martin's series has landed
because I hope this can get in before the merge window (potentially)
closes this weekend.

1: https://lore.kernel.org/bpf/[email protected]/
====================

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

Author: Alexei Starovoitov

kernel/bpf/verifier.c

@@ -3943,7 +3943,7 @@ static int resolve_map_arg_type(struct bpf_verifier_env *env,
 	case BPF_MAP_TYPE_SOCKMAP:
 	case BPF_MAP_TYPE_SOCKHASH:
 		if (*arg_type == ARG_PTR_TO_MAP_VALUE) {
-			*arg_type = ARG_PTR_TO_SOCKET;
+			*arg_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON;
 		} else {
 			verbose(env, "invalid arg_type for sockmap/sockhash\n");
 			return -EINVAL;

net/core/sock_map.c

@@ -610,6 +610,9 @@ static int sock_map_update_elem(struct bpf_map *map, void *key,
 	struct sock *sk = (struct sock *)value;
 	int ret;
 
+	if (unlikely(!sk || !sk_fullsock(sk)))
+		return -EINVAL;
+
 	if (!sock_map_sk_is_suitable(sk))
 		return -EOPNOTSUPP;
 

tools/testing/selftests/bpf/prog_tests/sockmap_basic.c

@@ -8,8 +8,6 @@
 #include "test_sockmap_invalid_update.skel.h"
 #include "bpf_iter_sockmap.skel.h"
 
-#include "progs/bpf_iter_sockmap.h"
-
 #define TCP_REPAIR		19	/* TCP sock is under repair right now */
 
 #define TCP_REPAIR_ON		1
@@ -50,6 +48,37 @@ static int connected_socket_v4(void)
 	return -1;
 }
 
+static void compare_cookies(struct bpf_map *src, struct bpf_map *dst)
+{
+	__u32 i, max_entries = bpf_map__max_entries(src);
+	int err, duration = 0, src_fd, dst_fd;
+
+	src_fd = bpf_map__fd(src);
+	dst_fd = bpf_map__fd(dst);
+
+	for (i = 0; i < max_entries; i++) {
+		__u64 src_cookie, dst_cookie;
+
+		err = bpf_map_lookup_elem(src_fd, &i, &src_cookie);
+		if (err && errno == ENOENT) {
+			err = bpf_map_lookup_elem(dst_fd, &i, &dst_cookie);
+			CHECK(!err, "map_lookup_elem(dst)", "element %u not deleted\n", i);
+			CHECK(err && errno != ENOENT, "map_lookup_elem(dst)", "%s\n",
+			      strerror(errno));
+			continue;
+		}
+		if (CHECK(err, "lookup_elem(src)", "%s\n", strerror(errno)))
+			continue;
+
+		err = bpf_map_lookup_elem(dst_fd, &i, &dst_cookie);
+		if (CHECK(err, "lookup_elem(dst)", "%s\n", strerror(errno)))
+			continue;
+
+		CHECK(dst_cookie != src_cookie, "cookie mismatch",
+		      "%llu != %llu (pos %u)\n", dst_cookie, src_cookie, i);
+	}
+}
+
 /* Create a map, populate it with one socket, and free the map. */
 static void test_sockmap_create_update_free(enum bpf_map_type map_type)
 {
@@ -109,9 +138,9 @@ static void test_skmsg_helpers(enum bpf_map_type map_type)
 static void test_sockmap_update(enum bpf_map_type map_type)
 {
 	struct bpf_prog_test_run_attr tattr;
-	int err, prog, src, dst, duration = 0;
+	int err, prog, src, duration = 0;
 	struct test_sockmap_update *skel;
-	__u64 src_cookie, dst_cookie;
+	struct bpf_map *dst_map;
 	const __u32 zero = 0;
 	char dummy[14] = {0};
 	__s64 sk;
@@ -127,18 +156,14 @@ static void test_sockmap_update(enum bpf_map_type map_type)
 	prog = bpf_program__fd(skel->progs.copy_sock_map);
 	src = bpf_map__fd(skel->maps.src);
 	if (map_type == BPF_MAP_TYPE_SOCKMAP)
-		dst = bpf_map__fd(skel->maps.dst_sock_map);
+		dst_map = skel->maps.dst_sock_map;
 	else
-		dst = bpf_map__fd(skel->maps.dst_sock_hash);
+		dst_map = skel->maps.dst_sock_hash;
 
 	err = bpf_map_update_elem(src, &zero, &sk, BPF_NOEXIST);
 	if (CHECK(err, "update_elem(src)", "errno=%u\n", errno))
 		goto out;
 
-	err = bpf_map_lookup_elem(src, &zero, &src_cookie);
-	if (CHECK(err, "lookup_elem(src, cookie)", "errno=%u\n", errno))
-		goto out;
-
 	tattr = (struct bpf_prog_test_run_attr){
 		.prog_fd = prog,
 		.repeat = 1,
@@ -151,12 +176,7 @@ static void test_sockmap_update(enum bpf_map_type map_type)
 		       "errno=%u retval=%u\n", errno, tattr.retval))
 		goto out;
 
-	err = bpf_map_lookup_elem(dst, &zero, &dst_cookie);
-	if (CHECK(err, "lookup_elem(dst, cookie)", "errno=%u\n", errno))
-		goto out;
-
-	CHECK(dst_cookie != src_cookie, "cookie mismatch", "%llu != %llu\n",
-	      dst_cookie, src_cookie);
+	compare_cookies(skel->maps.src, dst_map);
 
 out:
 	test_sockmap_update__destroy(skel);
@@ -174,14 +194,14 @@ static void test_sockmap_invalid_update(void)
 		test_sockmap_invalid_update__destroy(skel);
 }
 
-static void test_sockmap_iter(enum bpf_map_type map_type)
+static void test_sockmap_copy(enum bpf_map_type map_type)
 {
 	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
 	int err, len, src_fd, iter_fd, duration = 0;
 	union bpf_iter_link_info linfo = {0};
-	__s64 sock_fd[SOCKMAP_MAX_ENTRIES];
-	__u32 i, num_sockets, max_elems;
+	__u32 i, num_sockets, num_elems;
 	struct bpf_iter_sockmap *skel;
+	__s64 *sock_fd = NULL;
 	struct bpf_link *link;
 	struct bpf_map *src;
 	char buf[64];
@@ -190,22 +210,23 @@ static void test_sockmap_iter(enum bpf_map_type map_type)
 	if (CHECK(!skel, "bpf_iter_sockmap__open_and_load", "skeleton open_and_load failed\n"))
 		return;
 
-	for (i = 0; i < ARRAY_SIZE(sock_fd); i++)
-		sock_fd[i] = -1;
-
-	/* Make sure we have at least one "empty" entry to test iteration of
-	 * an empty slot.
-	 */
-	num_sockets = ARRAY_SIZE(sock_fd) - 1;
-
 	if (map_type == BPF_MAP_TYPE_SOCKMAP) {
 		src = skel->maps.sockmap;
-		max_elems = bpf_map__max_entries(src);
+		num_elems = bpf_map__max_entries(src);
+		num_sockets = num_elems - 1;
 	} else {
 		src = skel->maps.sockhash;
-		max_elems = num_sockets;
+		num_elems = bpf_map__max_entries(src) - 1;
+		num_sockets = num_elems;
 	}
 
+	sock_fd = calloc(num_sockets, sizeof(*sock_fd));
+	if (CHECK(!sock_fd, "calloc(sock_fd)", "failed to allocate\n"))
+		goto out;
+
+	for (i = 0; i < num_sockets; i++)
+		sock_fd[i] = -1;
+
 	src_fd = bpf_map__fd(src);
 
 	for (i = 0; i < num_sockets; i++) {
@@ -221,7 +242,7 @@ static void test_sockmap_iter(enum bpf_map_type map_type)
 	linfo.map.map_fd = src_fd;
 	opts.link_info = &linfo;
 	opts.link_info_len = sizeof(linfo);
-	link = bpf_program__attach_iter(skel->progs.count_elems, &opts);
+	link = bpf_program__attach_iter(skel->progs.copy, &opts);
 	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
 		goto out;
 
@@ -236,23 +257,26 @@ static void test_sockmap_iter(enum bpf_map_type map_type)
 		goto close_iter;
 
 	/* test results */
-	if (CHECK(skel->bss->elems != max_elems, "elems", "got %u expected %u\n",
-		  skel->bss->elems, max_elems))
+	if (CHECK(skel->bss->elems != num_elems, "elems", "got %u expected %u\n",
+		  skel->bss->elems, num_elems))
 		goto close_iter;
 
 	if (CHECK(skel->bss->socks != num_sockets, "socks", "got %u expected %u\n",
 		  skel->bss->socks, num_sockets))
 		goto close_iter;
 
+	compare_cookies(src, skel->maps.dst);
+
 close_iter:
 	close(iter_fd);
 free_link:
 	bpf_link__destroy(link);
 out:
-	for (i = 0; i < num_sockets; i++) {
+	for (i = 0; sock_fd && i < num_sockets; i++)
 		if (sock_fd[i] >= 0)
 			close(sock_fd[i]);
-	}
+	if (sock_fd)
+		free(sock_fd);
 	bpf_iter_sockmap__destroy(skel);
 }
 
@@ -272,8 +296,8 @@ void test_sockmap_basic(void)
 		test_sockmap_update(BPF_MAP_TYPE_SOCKHASH);
 	if (test__start_subtest("sockmap update in unsafe context"))
 		test_sockmap_invalid_update();
-	if (test__start_subtest("sockmap iter"))
-		test_sockmap_iter(BPF_MAP_TYPE_SOCKMAP);
-	if (test__start_subtest("sockhash iter"))
-		test_sockmap_iter(BPF_MAP_TYPE_SOCKHASH);
+	if (test__start_subtest("sockmap copy"))
+		test_sockmap_copy(BPF_MAP_TYPE_SOCKMAP);
+	if (test__start_subtest("sockhash copy"))
+		test_sockmap_copy(BPF_MAP_TYPE_SOCKHASH);
 }

tools/testing/selftests/bpf/progs/bpf_iter_sockmap.c

@@ -2,7 +2,6 @@
 /* Copyright (c) 2020 Cloudflare */
 #include "bpf_iter.h"
 #include "bpf_tracing_net.h"
-#include "bpf_iter_sockmap.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 #include <errno.h>
@@ -11,33 +10,50 @@ char _license[] SEC("license") = "GPL";
 
 struct {
 	__uint(type, BPF_MAP_TYPE_SOCKMAP);
-	__uint(max_entries, SOCKMAP_MAX_ENTRIES);
+	__uint(max_entries, 64);
 	__type(key, __u32);
 	__type(value, __u64);
 } sockmap SEC(".maps");
 
 struct {
 	__uint(type, BPF_MAP_TYPE_SOCKHASH);
-	__uint(max_entries, SOCKMAP_MAX_ENTRIES);
+	__uint(max_entries, 64);
 	__type(key, __u32);
 	__type(value, __u64);
 } sockhash SEC(".maps");
 
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKHASH);
+	__uint(max_entries, 64);
+	__type(key, __u32);
+	__type(value, __u64);
+} dst SEC(".maps");
+
 __u32 elems = 0;
 __u32 socks = 0;
 
 SEC("iter/sockmap")
-int count_elems(struct bpf_iter__sockmap *ctx)
+int copy(struct bpf_iter__sockmap *ctx)
 {
 	struct sock *sk = ctx->sk;
 	__u32 tmp, *key = ctx->key;
 	int ret;
 
-	if (key)
-		elems++;
+	if (!key)
+		return 0;
+
+	elems++;
+
+	/* We need a temporary buffer on the stack, since the verifier doesn't
+	 * let us use the pointer from the context as an argument to the helper.
+	 */
+	tmp = *key;
 
-	if (sk)
+	if (sk) {
 		socks++;
+		return bpf_map_update_elem(&dst, &tmp, sk, 0) != 0;
+	}
 
-	return 0;
+	ret = bpf_map_delete_elem(&dst, &tmp);
+	return ret && ret != -ENOENT;
 }