Merge branch 'bpf: tcp: Allow bpf-tcp-cc to call bpf_(get|set)sockopt'

Martin KaFai says:

====================

This set allows the bpf-tcp-cc to call bpf_setsockopt.  One use
case is to allow a bpf-tcp-cc switching to another cc during init().
For example, when the tcp flow is not ecn ready, the bpf_dctcp
can switch to another cc by calling setsockopt(TCP_CONGESTION).

bpf_getsockopt() is also added to have a symmetrical API, so
less usage surprise.

v2:
- Not allow switching to kernel's tcp_cdg because it is the only
  kernel tcp-cc that stores a pointer to icsk_ca_priv.
  Please see the commit log in patch 1 for details.
  Test is added in patch 4 to check switching to tcp_cdg.
- Refactor the logic finding the offset of a func ptr
  in the "struct tcp_congestion_ops" to prog_ops_moff()
  in patch 1.
- bpf_setsockopt() has been disabled in release() since v1 (please
  see commit log in patch 1 for reason).  bpf_getsockopt() is
  also disabled together in release() in v2 to avoid usage surprise
  because both of them are usually expected to be available together.
  bpf-tcp-cc can already use PTR_TO_BTF_ID to read from tcp_sock.
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

kernel/bpf/bpf_struct_ops.c

@@ -28,6 +28,7 @@ struct bpf_struct_ops_value {
 
 struct bpf_struct_ops_map {
 	struct bpf_map map;
+	struct rcu_head rcu;
 	const struct bpf_struct_ops *st_ops;
 	/* protect map_update */
 	struct mutex lock;
@@ -622,6 +623,14 @@ bool bpf_struct_ops_get(const void *kdata)
 	return refcount_inc_not_zero(&kvalue->refcnt);
 }
 
+static void bpf_struct_ops_put_rcu(struct rcu_head *head)
+{
+	struct bpf_struct_ops_map *st_map;
+
+	st_map = container_of(head, struct bpf_struct_ops_map, rcu);
+	bpf_map_put(&st_map->map);
+}
+
 void bpf_struct_ops_put(const void *kdata)
 {
 	struct bpf_struct_ops_value *kvalue;
@@ -632,6 +641,17 @@ void bpf_struct_ops_put(const void *kdata)
 
 		st_map = container_of(kvalue, struct bpf_struct_ops_map,
 				      kvalue);
-		bpf_map_put(&st_map->map);
+		/* The struct_ops's function may switch to another struct_ops.
+		 *
+		 * For example, bpf_tcp_cc_x->init() may switch to
+		 * another tcp_cc_y by calling
+		 * setsockopt(TCP_CONGESTION, "tcp_cc_y").
+		 * During the switch,  bpf_struct_ops_put(tcp_cc_x) is called
+		 * and its map->refcnt may reach 0 which then free its
+		 * trampoline image while tcp_cc_x is still running.
+		 *
+		 * Thus, a rcu grace period is needed here.
+		 */
+		call_rcu(&st_map->rcu, bpf_struct_ops_put_rcu);
 	}
 }

net/core/filter.c

@@ -5051,6 +5051,12 @@ err_clear:
 BPF_CALL_5(bpf_sk_setsockopt, struct sock *, sk, int, level,
 	   int, optname, char *, optval, int, optlen)
 {
+	if (level == SOL_TCP && optname == TCP_CONGESTION) {
+		if (optlen >= sizeof("cdg") - 1 &&
+		    !strncmp("cdg", optval, optlen))
+			return -ENOTSUPP;
+	}
+
 	return _bpf_setsockopt(sk, level, optname, optval, optlen);
 }
 

net/ipv4/bpf_tcp_ca.c

@@ -10,6 +10,9 @@
 #include <net/tcp.h>
 #include <net/bpf_sk_storage.h>
 
+/* "extern" is to avoid sparse warning.  It is only used in bpf_struct_ops.c. */
+extern struct bpf_struct_ops bpf_tcp_congestion_ops;
+
 static u32 optional_ops[] = {
 	offsetof(struct tcp_congestion_ops, init),
 	offsetof(struct tcp_congestion_ops, release),
@@ -163,6 +166,19 @@ static const struct bpf_func_proto bpf_tcp_send_ack_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
+static u32 prog_ops_moff(const struct bpf_prog *prog)
+{
+	const struct btf_member *m;
+	const struct btf_type *t;
+	u32 midx;
+
+	midx = prog->expected_attach_type;
+	t = bpf_tcp_congestion_ops.type;
+	m = &btf_type_member(t)[midx];
+
+	return btf_member_bit_offset(t, m) / 8;
+}
+
 static const struct bpf_func_proto *
 bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id,
 			  const struct bpf_prog *prog)
@@ -174,6 +190,28 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id,
 		return &bpf_sk_storage_get_proto;
 	case BPF_FUNC_sk_storage_delete:
 		return &bpf_sk_storage_delete_proto;
+	case BPF_FUNC_setsockopt:
+		/* Does not allow release() to call setsockopt.
+		 * release() is called when the current bpf-tcp-cc
+		 * is retiring.  It is not allowed to call
+		 * setsockopt() to make further changes which
+		 * may potentially allocate new resources.
+		 */
+		if (prog_ops_moff(prog) !=
+		    offsetof(struct tcp_congestion_ops, release))
+			return &bpf_sk_setsockopt_proto;
+		return NULL;
+	case BPF_FUNC_getsockopt:
+		/* Since get/setsockopt is usually expected to
+		 * be available together, disable getsockopt for
+		 * release also to avoid usage surprise.
+		 * The bpf-tcp-cc already has a more powerful way
+		 * to read tcp_sock from the PTR_TO_BTF_ID.
+		 */
+		if (prog_ops_moff(prog) !=
+		    offsetof(struct tcp_congestion_ops, release))
+			return &bpf_sk_getsockopt_proto;
+		return NULL;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -286,9 +324,6 @@ static void bpf_tcp_ca_unreg(void *kdata)
 	tcp_unregister_congestion_control(kdata);
 }
 
-/* Avoid sparse warning.  It is only used in bpf_struct_ops.c. */
-extern struct bpf_struct_ops bpf_tcp_congestion_ops;
-
 struct bpf_struct_ops bpf_tcp_congestion_ops = {
 	.verifier_ops = &bpf_tcp_ca_verifier_ops,
 	.reg = bpf_tcp_ca_reg,

tools/testing/selftests/bpf/bpf_tcp_helpers.h

@@ -31,6 +31,7 @@ enum sk_pacing {
 
 struct sock {
 	struct sock_common	__sk_common;
+#define sk_state		__sk_common.skc_state
 	unsigned long		sk_pacing_rate;
 	__u32			sk_pacing_status; /* see enum sk_pacing */
 } __attribute__((preserve_access_index));

tools/testing/selftests/bpf/network_helpers.c

@@ -218,13 +218,18 @@ static int connect_fd_to_addr(int fd,
 	return 0;
 }
 
-int connect_to_fd(int server_fd, int timeout_ms)
+static const struct network_helper_opts default_opts;
+
+int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts)
 {
 	struct sockaddr_storage addr;
 	struct sockaddr_in *addr_in;
 	socklen_t addrlen, optlen;
 	int fd, type;
 
+	if (!opts)
+		opts = &default_opts;
+
 	optlen = sizeof(type);
 	if (getsockopt(server_fd, SOL_SOCKET, SO_TYPE, &type, &optlen)) {
 		log_err("getsockopt(SOL_TYPE)");
@@ -244,7 +249,12 @@ int connect_to_fd(int server_fd, int timeout_ms)
 		return -1;
 	}
 
-	if (settimeo(fd, timeout_ms))
+	if (settimeo(fd, opts->timeout_ms))
+		goto error_close;
+
+	if (opts->cc && opts->cc[0] &&
+	    setsockopt(fd, SOL_TCP, TCP_CONGESTION, opts->cc,
+		       strlen(opts->cc) + 1))
 		goto error_close;
 
 	if (connect_fd_to_addr(fd, &addr, addrlen))
@@ -257,6 +267,15 @@ error_close:
 	return -1;
 }
 
+int connect_to_fd(int server_fd, int timeout_ms)
+{
+	struct network_helper_opts opts = {
+		.timeout_ms = timeout_ms,
+	};
+
+	return connect_to_fd_opts(server_fd, &opts);
+}
+
 int connect_fd_to_fd(int client_fd, int server_fd, int timeout_ms)
 {
 	struct sockaddr_storage addr;

tools/testing/selftests/bpf/network_helpers.h

@@ -17,6 +17,11 @@ typedef __u16 __sum16;
 #define VIP_NUM 5
 #define MAGIC_BYTES 123
 
+struct network_helper_opts {
+	const char *cc;
+	int timeout_ms;
+};
+
 /* ipv4 test vector */
 struct ipv4_packet {
 	struct ethhdr eth;
@@ -41,6 +46,7 @@ int *start_reuseport_server(int family, int type, const char *addr_str,
 			    unsigned int nr_listens);
 void free_fds(int *fds, unsigned int nr_close_fds);
 int connect_to_fd(int server_fd, int timeout_ms);
+int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts);
 int connect_fd_to_fd(int client_fd, int server_fd, int timeout_ms);
 int fastopen_connect(int server_fd, const char *data, unsigned int data_len,
 		     int timeout_ms);

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

@@ -4,37 +4,22 @@
 #include <linux/err.h>
 #include <netinet/tcp.h>
 #include <test_progs.h>
+#include "network_helpers.h"
 #include "bpf_dctcp.skel.h"
 #include "bpf_cubic.skel.h"
 #include "bpf_tcp_nogpl.skel.h"
+#include "bpf_dctcp_release.skel.h"
 
 #define min(a, b) ((a) < (b) ? (a) : (b))
 
+#ifndef ENOTSUPP
+#define ENOTSUPP 524
+#endif
+
 static const unsigned int total_bytes = 10 * 1024 * 1024;
-static const struct timeval timeo_sec = { .tv_sec = 10 };
-static const size_t timeo_optlen = sizeof(timeo_sec);
 static int expected_stg = 0xeB9F;
 static int stop, duration;
 
-static int settimeo(int fd)
-{
-	int err;
-
-	err = setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &timeo_sec,
-			 timeo_optlen);
-	if (CHECK(err == -1, "setsockopt(fd, SO_RCVTIMEO)", "errno:%d\n",
-		  errno))
-		return -1;
-
-	err = setsockopt(fd, SOL_SOCKET, SO_SNDTIMEO, &timeo_sec,
-			 timeo_optlen);
-	if (CHECK(err == -1, "setsockopt(fd, SO_SNDTIMEO)", "errno:%d\n",
-		  errno))
-		return -1;
-
-	return 0;
-}
-
 static int settcpca(int fd, const char *tcp_ca)
 {
 	int err;
@@ -61,7 +46,7 @@ static void *server(void *arg)
 		goto done;
 	}
 
-	if (settimeo(fd)) {
+	if (settimeo(fd, 0)) {
 		err = -errno;
 		goto done;
 	}
@@ -114,7 +99,7 @@ static void do_test(const char *tcp_ca, const struct bpf_map *sk_stg_map)
 	}
 
 	if (settcpca(lfd, tcp_ca) || settcpca(fd, tcp_ca) ||
-	    settimeo(lfd) || settimeo(fd))
+	    settimeo(lfd, 0) || settimeo(fd, 0))
 		goto done;
 
 	/* bind, listen and start server thread to accept */
@@ -267,6 +252,77 @@ static void test_invalid_license(void)
 	libbpf_set_print(old_print_fn);
 }
 
+static void test_dctcp_fallback(void)
+{
+	int err, lfd = -1, cli_fd = -1, srv_fd = -1;
+	struct network_helper_opts opts = {
+		.cc = "cubic",
+	};
+	struct bpf_dctcp *dctcp_skel;
+	struct bpf_link *link = NULL;
+	char srv_cc[16];
+	socklen_t cc_len = sizeof(srv_cc);
+
+	dctcp_skel = bpf_dctcp__open();
+	if (!ASSERT_OK_PTR(dctcp_skel, "dctcp_skel"))
+		return;
+	strcpy(dctcp_skel->rodata->fallback, "cubic");
+	if (!ASSERT_OK(bpf_dctcp__load(dctcp_skel), "bpf_dctcp__load"))
+		goto done;
+
+	link = bpf_map__attach_struct_ops(dctcp_skel->maps.dctcp);
+	if (!ASSERT_OK_PTR(link, "dctcp link"))
+		goto done;
+
+	lfd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0);
+	if (!ASSERT_GE(lfd, 0, "lfd") ||
+	    !ASSERT_OK(settcpca(lfd, "bpf_dctcp"), "lfd=>bpf_dctcp"))
+		goto done;
+
+	cli_fd = connect_to_fd_opts(lfd, &opts);
+	if (!ASSERT_GE(cli_fd, 0, "cli_fd"))
+		goto done;
+
+	srv_fd = accept(lfd, NULL, 0);
+	if (!ASSERT_GE(srv_fd, 0, "srv_fd"))
+		goto done;
+	ASSERT_STREQ(dctcp_skel->bss->cc_res, "cubic", "cc_res");
+	ASSERT_EQ(dctcp_skel->bss->tcp_cdg_res, -ENOTSUPP, "tcp_cdg_res");
+
+	err = getsockopt(srv_fd, SOL_TCP, TCP_CONGESTION, srv_cc, &cc_len);
+	if (!ASSERT_OK(err, "getsockopt(srv_fd, TCP_CONGESTION)"))
+		goto done;
+	ASSERT_STREQ(srv_cc, "cubic", "srv_fd cc");
+
+done:
+	bpf_link__destroy(link);
+	bpf_dctcp__destroy(dctcp_skel);
+	if (lfd != -1)
+		close(lfd);
+	if (srv_fd != -1)
+		close(srv_fd);
+	if (cli_fd != -1)
+		close(cli_fd);
+}
+
+static void test_rel_setsockopt(void)
+{
+	struct bpf_dctcp_release *rel_skel;
+	libbpf_print_fn_t old_print_fn;
+
+	err_str = "unknown func bpf_setsockopt";
+	found = false;
+
+	old_print_fn = libbpf_set_print(libbpf_debug_print);
+	rel_skel = bpf_dctcp_release__open_and_load();
+	libbpf_set_print(old_print_fn);
+
+	ASSERT_ERR_PTR(rel_skel, "rel_skel");
+	ASSERT_TRUE(found, "expected_err_msg");
+
+	bpf_dctcp_release__destroy(rel_skel);
+}
+
 void test_bpf_tcp_ca(void)
 {
 	if (test__start_subtest("dctcp"))
@@ -275,4 +331,8 @@ void test_bpf_tcp_ca(void)
 		test_cubic();
 	if (test__start_subtest("invalid_license"))
 		test_invalid_license();
+	if (test__start_subtest("dctcp_fallback"))
+		test_dctcp_fallback();
+	if (test__start_subtest("rel_setsockopt"))
+		test_rel_setsockopt();
 }

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

@@ -44,7 +44,7 @@ static void test_subprog(void)
 	ASSERT_OK(err, "bpf_prog_test_run(test1)");
 	ASSERT_EQ(retval, 10, "test1-retval");
 	ASSERT_NEQ(skel->data->active_res, -1, "active_res");
-	ASSERT_EQ(skel->data->sk_state, BPF_TCP_CLOSE, "sk_state");
+	ASSERT_EQ(skel->data->sk_state_res, BPF_TCP_CLOSE, "sk_state_res");
 
 	kfunc_call_test_subprog__destroy(skel);
 }

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

@@ -17,6 +17,11 @@
 
 char _license[] SEC("license") = "GPL";
 
+volatile const char fallback[TCP_CA_NAME_MAX];
+const char bpf_dctcp[] = "bpf_dctcp";
+const char tcp_cdg[] = "cdg";
+char cc_res[TCP_CA_NAME_MAX];
+int tcp_cdg_res = 0;
 int stg_result = 0;
 
 struct {
@@ -57,6 +62,26 @@ void BPF_PROG(dctcp_init, struct sock *sk)
 	struct dctcp *ca = inet_csk_ca(sk);
 	int *stg;
 
+	if (!(tp->ecn_flags & TCP_ECN_OK) && fallback[0]) {
+		/* Switch to fallback */
+		bpf_setsockopt(sk, SOL_TCP, TCP_CONGESTION,
+			       (void *)fallback, sizeof(fallback));
+		/* Switch back to myself which the bpf trampoline
+		 * stopped calling dctcp_init recursively.
+		 */
+		bpf_setsockopt(sk, SOL_TCP, TCP_CONGESTION,
+			       (void *)bpf_dctcp, sizeof(bpf_dctcp));
+		/* Switch back to fallback */
+		bpf_setsockopt(sk, SOL_TCP, TCP_CONGESTION,
+			       (void *)fallback, sizeof(fallback));
+		/* Expecting -ENOTSUPP for tcp_cdg_res */
+		tcp_cdg_res = bpf_setsockopt(sk, SOL_TCP, TCP_CONGESTION,
+					     (void *)tcp_cdg, sizeof(tcp_cdg));
+		bpf_getsockopt(sk, SOL_TCP, TCP_CONGESTION,
+			       (void *)cc_res, sizeof(cc_res));
+		return;
+	}
+
 	ca->prior_rcv_nxt = tp->rcv_nxt;
 	ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
 	ca->loss_cwnd = 0;

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

@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <linux/tcp.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_tcp_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+const char cubic[] = "cubic";
+
+void BPF_STRUCT_OPS(dctcp_nouse_release, struct sock *sk)
+{
+	bpf_setsockopt(sk, SOL_TCP, TCP_CONGESTION,
+		       (void *)cubic, sizeof(cubic));
+}
+
+SEC(".struct_ops")
+struct tcp_congestion_ops dctcp_rel = {
+	.release	= (void *)dctcp_nouse_release,
+	.name		= "bpf_dctcp_rel",
+};

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

@@ -9,7 +9,7 @@ extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b,
 				  __u32 c, __u64 d) __ksym;
 extern struct sock *bpf_kfunc_call_test3(struct sock *sk) __ksym;
 int active_res = -1;
-int sk_state = -1;
+int sk_state_res = -1;
 
 int __noinline f1(struct __sk_buff *skb)
 {
@@ -28,7 +28,7 @@ int __noinline f1(struct __sk_buff *skb)
 	if (active)
 		active_res = *active;
 
-	sk_state = bpf_kfunc_call_test3((struct sock *)sk)->__sk_common.skc_state;
+	sk_state_res = bpf_kfunc_call_test3((struct sock *)sk)->sk_state;
 
 	return (__u32)bpf_kfunc_call_test1((struct sock *)sk, 1, 2, 3, 4);
 }