Merge branch 'sockmap-fixes'

John Fastabend says:

====================
sockmap fixes for net

The following implements a set of fixes for sockmap and changes the
API slightly in a few places to reduce preempt_disable/enable scope.
We do this here in net because it requires an API change and this
avoids getting stuck with legacy API going forward.

The short description:

Access to skb mark is removed, it is problematic when we add
features in the future because mark is a union and used by the
TCP/socket code internally. We don't want to expose this to the
BPF programs or let programs change the values.

The other change is caching metadata in the skb itself between
when the BPF program returns a redirect code and the core code
implements the redirect. This avoids having per cpu metadata.

Finally, tighten restriction on using sockmap to CAP_NET_ADMIN and
only SOCK_STREAM sockets.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 30 insertions, 7 deletions

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 43ab5c402f98..be9a631a69f7 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -569,9 +569,10 @@ union bpf_attr {
  *     @flags: reserved for future use
  *     Return: 0 on success or negative error code
  *
- * int bpf_sk_redirect_map(map, key, flags)
+ * int bpf_sk_redirect_map(skb, map, key, flags)
  *     Redirect skb to a sock in map using key as a lookup key for the
  *     sock in map.
+ *     @skb: pointer to skb
  *     @map: pointer to sockmap
  *     @key: key to lookup sock in map
  *     @flags: reserved for future use
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 36fb9161b34a..b2e02bdcd098 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -65,7 +65,7 @@ static int (*bpf_xdp_adjust_head)(void *ctx, int offset) =
 static int (*bpf_setsockopt)(void *ctx, int level, int optname, void *optval,
 			     int optlen) =
 	(void *) BPF_FUNC_setsockopt;
-static int (*bpf_sk_redirect_map)(void *map, int key, int flags) =
+static int (*bpf_sk_redirect_map)(void *ctx, void *map, int key, int flags) =
 	(void *) BPF_FUNC_sk_redirect_map;
 static int (*bpf_sock_map_update)(void *map, void *key, void *value,
 				  unsigned long long flags) =
diff --git a/tools/testing/selftests/bpf/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/sockmap_verdict_prog.c
index 9b99bd10807d..2cd2d552938b 100644
--- a/tools/testing/selftests/bpf/sockmap_verdict_prog.c
+++ b/tools/testing/selftests/bpf/sockmap_verdict_prog.c
@@ -61,8 +61,8 @@ int bpf_prog2(struct __sk_buff *skb)
 	bpf_printk("verdict: data[0] = redir(%u:%u)\n", map, sk);
 
 	if (!map)
-		return bpf_sk_redirect_map(&sock_map_rx, sk, 0);
-	return bpf_sk_redirect_map(&sock_map_tx, sk, 0);
+		return bpf_sk_redirect_map(skb, &sock_map_rx, sk, 0);
+	return bpf_sk_redirect_map(skb, &sock_map_tx, sk, 0);
 }
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index fe3a443a1102..50ce52d2013d 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -466,7 +466,7 @@ static void test_sockmap(int tasks, void *data)
 	int one = 1, map_fd_rx, map_fd_tx, map_fd_break, s, sc, rc;
 	struct bpf_map *bpf_map_rx, *bpf_map_tx, *bpf_map_break;
 	int ports[] = {50200, 50201, 50202, 50204};
-	int err, i, fd, sfd[6] = {0xdeadbeef};
+	int err, i, fd, udp, sfd[6] = {0xdeadbeef};
 	u8 buf[20] = {0x0, 0x5, 0x3, 0x2, 0x1, 0x0};
 	int parse_prog, verdict_prog;
 	struct sockaddr_in addr;
@@ -548,6 +548,16 @@ static void test_sockmap(int tasks, void *data)
 		goto out_sockmap;
 	}
 
+	/* Test update with unsupported UDP socket */
+	udp = socket(AF_INET, SOCK_DGRAM, 0);
+	i = 0;
+	err = bpf_map_update_elem(fd, &i, &udp, BPF_ANY);
+	if (!err) {
+		printf("Failed socket SOCK_DGRAM allowed '%i:%i'\n",
+		       i, udp);
+		goto out_sockmap;
+	}
+
 	/* Test update without programs */
 	for (i = 0; i < 6; i++) {
 		err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_ANY);
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 3c7d3a45a3c5..50e15cedbb7f 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -1130,15 +1130,27 @@ static struct bpf_test tests[] = {
 		.errstr = "invalid bpf_context access",
 	},
 	{
-		"check skb->mark is writeable by SK_SKB",
+		"invalid access of skb->mark for SK_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_EXIT_INSN(),
+		},
+		.result =  REJECT,
+		.prog_type = BPF_PROG_TYPE_SK_SKB,
+		.errstr = "invalid bpf_context access",
+	},
+	{
+		"check skb->mark is not writeable by SK_SKB",
 		.insns = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
 				    offsetof(struct __sk_buff, mark)),
 			BPF_EXIT_INSN(),
 		},
-		.result = ACCEPT,
+		.result =  REJECT,
 		.prog_type = BPF_PROG_TYPE_SK_SKB,
+		.errstr = "invalid bpf_context access",
 	},
 	{
 		"check skb->tc_index is writeable by SK_SKB",