Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2023-08-16

We've added 17 non-merge commits during the last 6 day(s) which contain
a total of 20 files changed, 1179 insertions(+), 37 deletions(-).

The main changes are:

1) Add a BPF hook in sys_socket() to change the protocol ID
   from IPPROTO_TCP to IPPROTO_MPTCP to cover migration for legacy
   applications, from Geliang Tang.

2) Follow-up/fallout fix from the SO_REUSEPORT + bpf_sk_assign work
   to fix a splat on non-fullsock sks in inet[6]_steal_sock,
   from Lorenz Bauer.

3) Improvements to struct_ops links to avoid forcing presence of
   update/validate callbacks. Also add bpf_struct_ops fields documentation,
   from David Vernet.

4) Ensure libbpf sets close-on-exec flag on gzopen, from Marco Vedovati.

5) Several new tcx selftest additions and bpftool link show support for
   tcx and xdp links, from Daniel Borkmann.

6) Fix a smatch warning on uninitialized symbol in
   bpf_perf_link_fill_kprobe, from Yafang Shao.

7) BPF selftest fixes e.g. misplaced break in kfunc_call test,
   from Yipeng Zou.

8) Small cleanup to remove unused declaration bpf_link_new_file,
   from Yue Haibing.

9) Small typo fix to bpftool's perf help message, from Daniel T. Lee.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next:
  selftests/bpf: Add mptcpify test
  selftests/bpf: Fix error checks of mptcp open_and_load
  selftests/bpf: Add two mptcp netns helpers
  bpf: Add update_socket_protocol hook
  bpftool: Implement link show support for xdp
  bpftool: Implement link show support for tcx
  selftests/bpf: Add selftest for fill_link_info
  bpf: Fix uninitialized symbol in bpf_perf_link_fill_kprobe()
  net: Fix slab-out-of-bounds in inet[6]_steal_sock
  bpf: Document struct bpf_struct_ops fields
  bpf: Support default .validate() and .update() behavior for struct_ops links
  selftests/bpf: Add various more tcx test cases
  selftests/bpf: Clean up fmod_ret in bench_rename test script
  selftests/bpf: Fix repeat option when kfunc_call verification fails
  libbpf: Set close-on-exec flag on gzopen
  bpftool: fix perf help message
  bpf: Remove unused declaration bpf_link_new_file()
====================

Link: https://lore.kernel.org/r/20230816212840.1539-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Author: kuba-moo

include/linux/bpf.h

@@ -1550,6 +1550,53 @@ struct bpf_struct_ops_value;
 struct btf_member;
 
 #define BPF_STRUCT_OPS_MAX_NR_MEMBERS 64
+/**
+ * struct bpf_struct_ops - A structure of callbacks allowing a subsystem to
+ *			   define a BPF_MAP_TYPE_STRUCT_OPS map type composed
+ *			   of BPF_PROG_TYPE_STRUCT_OPS progs.
+ * @verifier_ops: A structure of callbacks that are invoked by the verifier
+ *		  when determining whether the struct_ops progs in the
+ *		  struct_ops map are valid.
+ * @init: A callback that is invoked a single time, and before any other
+ *	  callback, to initialize the structure. A nonzero return value means
+ *	  the subsystem could not be initialized.
+ * @check_member: When defined, a callback invoked by the verifier to allow
+ *		  the subsystem to determine if an entry in the struct_ops map
+ *		  is valid. A nonzero return value means that the map is
+ *		  invalid and should be rejected by the verifier.
+ * @init_member: A callback that is invoked for each member of the struct_ops
+ *		 map to allow the subsystem to initialize the member. A nonzero
+ *		 value means the member could not be initialized. This callback
+ *		 is exclusive with the @type, @type_id, @value_type, and
+ *		 @value_id fields.
+ * @reg: A callback that is invoked when the struct_ops map has been
+ *	 initialized and is being attached to. Zero means the struct_ops map
+ *	 has been successfully registered and is live. A nonzero return value
+ *	 means the struct_ops map could not be registered.
+ * @unreg: A callback that is invoked when the struct_ops map should be
+ *	   unregistered.
+ * @update: A callback that is invoked when the live struct_ops map is being
+ *	    updated to contain new values. This callback is only invoked when
+ *	    the struct_ops map is loaded with BPF_F_LINK. If not defined, the
+ *	    it is assumed that the struct_ops map cannot be updated.
+ * @validate: A callback that is invoked after all of the members have been
+ *	      initialized. This callback should perform static checks on the
+ *	      map, meaning that it should either fail or succeed
+ *	      deterministically. A struct_ops map that has been validated may
+ *	      not necessarily succeed in being registered if the call to @reg
+ *	      fails. For example, a valid struct_ops map may be loaded, but
+ *	      then fail to be registered due to there being another active
+ *	      struct_ops map on the system in the subsystem already. For this
+ *	      reason, if this callback is not defined, the check is skipped as
+ *	      the struct_ops map will have final verification performed in
+ *	      @reg.
+ * @type: BTF type.
+ * @value_type: Value type.
+ * @name: The name of the struct bpf_struct_ops object.
+ * @func_models: Func models
+ * @type_id: BTF type id.
+ * @value_id: BTF value id.
+ */
 struct bpf_struct_ops {
 	const struct bpf_verifier_ops *verifier_ops;
 	int (*init)(struct btf *btf);
@@ -2120,7 +2167,6 @@ void bpf_link_cleanup(struct bpf_link_primer *primer);
 void bpf_link_inc(struct bpf_link *link);
 void bpf_link_put(struct bpf_link *link);
 int bpf_link_new_fd(struct bpf_link *link);
-struct file *bpf_link_new_file(struct bpf_link *link, int *reserved_fd);
 struct bpf_link *bpf_link_get_from_fd(u32 ufd);
 struct bpf_link *bpf_link_get_curr_or_next(u32 *id);
 

include/net/inet6_hashtables.h

@@ -116,7 +116,7 @@ struct sock *inet6_steal_sock(struct net *net, struct sk_buff *skb, int doff,
 	if (!sk)
 		return NULL;
 
-	if (!prefetched)
+	if (!prefetched || !sk_fullsock(sk))
 		return sk;
 
 	if (sk->sk_protocol == IPPROTO_TCP) {

include/net/inet_hashtables.h

@@ -462,7 +462,7 @@ struct sock *inet_steal_sock(struct net *net, struct sk_buff *skb, int doff,
 	if (!sk)
 		return NULL;
 
-	if (!prefetched)
+	if (!prefetched || !sk_fullsock(sk))
 		return sk;
 
 	if (sk->sk_protocol == IPPROTO_TCP) {

kernel/bpf/bpf_struct_ops.c

@@ -509,9 +509,12 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 	}
 
 	if (st_map->map.map_flags & BPF_F_LINK) {
-		err = st_ops->validate(kdata);
-		if (err)
-			goto reset_unlock;
+		err = 0;
+		if (st_ops->validate) {
+			err = st_ops->validate(kdata);
+			if (err)
+				goto reset_unlock;
+		}
 		set_memory_rox((long)st_map->image, 1);
 		/* Let bpf_link handle registration & unregistration.
 		 *
@@ -663,9 +666,6 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 	if (attr->value_size != vt->size)
 		return ERR_PTR(-EINVAL);
 
-	if (attr->map_flags & BPF_F_LINK && (!st_ops->validate || !st_ops->update))
-		return ERR_PTR(-EOPNOTSUPP);
-
 	t = st_ops->type;
 
 	st_map_size = sizeof(*st_map) +
@@ -823,6 +823,9 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map
 	if (!bpf_struct_ops_valid_to_reg(new_map))
 		return -EINVAL;
 
+	if (!st_map->st_ops->update)
+		return -EOPNOTSUPP;
+
 	mutex_lock(&update_mutex);
 
 	old_map = rcu_dereference_protected(st_link->map, lockdep_is_held(&update_mutex));

kernel/bpf/syscall.c

@@ -3378,14 +3378,13 @@ static int bpf_perf_link_fill_common(const struct perf_event *event,
 
 	if (!ulen ^ !uname)
 		return -EINVAL;
-	if (!uname)
-		return 0;
 
 	err = bpf_get_perf_event_info(event, &prog_id, fd_type, &buf,
 				      probe_offset, probe_addr);
 	if (err)
 		return err;
-
+	if (!uname)
+		return 0;
 	if (buf) {
 		len = strlen(buf);
 		err = bpf_copy_to_user(uname, buf, ulen, len);

net/mptcp/bpf.c

@@ -19,3 +19,18 @@ struct mptcp_sock *bpf_mptcp_sock_from_subflow(struct sock *sk)
 
 	return NULL;
 }
+
+BTF_SET8_START(bpf_mptcp_fmodret_ids)
+BTF_ID_FLAGS(func, update_socket_protocol)
+BTF_SET8_END(bpf_mptcp_fmodret_ids)
+
+static const struct btf_kfunc_id_set bpf_mptcp_fmodret_set = {
+	.owner = THIS_MODULE,
+	.set   = &bpf_mptcp_fmodret_ids,
+};
+
+static int __init bpf_mptcp_kfunc_init(void)
+{
+	return register_btf_fmodret_id_set(&bpf_mptcp_fmodret_set);
+}
+late_initcall(bpf_mptcp_kfunc_init);

net/socket.c

@@ -1657,12 +1657,36 @@ struct file *__sys_socket_file(int family, int type, int protocol)
 	return sock_alloc_file(sock, flags, NULL);
 }
 
+/*	A hook for bpf progs to attach to and update socket protocol.
+ *
+ *	A static noinline declaration here could cause the compiler to
+ *	optimize away the function. A global noinline declaration will
+ *	keep the definition, but may optimize away the callsite.
+ *	Therefore, __weak is needed to ensure that the call is still
+ *	emitted, by telling the compiler that we don't know what the
+ *	function might eventually be.
+ *
+ *	__diag_* below are needed to dismiss the missing prototype warning.
+ */
+
+__diag_push();
+__diag_ignore_all("-Wmissing-prototypes",
+		  "A fmod_ret entry point for BPF programs");
+
+__weak noinline int update_socket_protocol(int family, int type, int protocol)
+{
+	return protocol;
+}
+
+__diag_pop();
+
 int __sys_socket(int family, int type, int protocol)
 {
 	struct socket *sock;
 	int flags;
 
-	sock = __sys_socket_create(family, type, protocol);
+	sock = __sys_socket_create(family, type,
+				   update_socket_protocol(family, type, protocol));
 	if (IS_ERR(sock))
 		return PTR_ERR(sock);
 

tools/bpf/bpftool/link.c

@@ -150,6 +150,18 @@ static void show_link_attach_type_json(__u32 attach_type, json_writer_t *wtr)
 		jsonw_uint_field(wtr, "attach_type", attach_type);
 }
 
+static void show_link_ifindex_json(__u32 ifindex, json_writer_t *wtr)
+{
+	char devname[IF_NAMESIZE] = "(unknown)";
+
+	if (ifindex)
+		if_indextoname(ifindex, devname);
+	else
+		snprintf(devname, sizeof(devname), "(detached)");
+	jsonw_string_field(wtr, "devname", devname);
+	jsonw_uint_field(wtr, "ifindex", ifindex);
+}
+
 static bool is_iter_map_target(const char *target_name)
 {
 	return strcmp(target_name, "bpf_map_elem") == 0 ||
@@ -433,6 +445,13 @@ static int show_link_close_json(int fd, struct bpf_link_info *info)
 	case BPF_LINK_TYPE_NETFILTER:
 		netfilter_dump_json(info, json_wtr);
 		break;
+	case BPF_LINK_TYPE_TCX:
+		show_link_ifindex_json(info->tcx.ifindex, json_wtr);
+		show_link_attach_type_json(info->tcx.attach_type, json_wtr);
+		break;
+	case BPF_LINK_TYPE_XDP:
+		show_link_ifindex_json(info->xdp.ifindex, json_wtr);
+		break;
 	case BPF_LINK_TYPE_STRUCT_OPS:
 		jsonw_uint_field(json_wtr, "map_id",
 				 info->struct_ops.map_id);
@@ -509,6 +528,22 @@ static void show_link_attach_type_plain(__u32 attach_type)
 		printf("attach_type %u  ", attach_type);
 }
 
+static void show_link_ifindex_plain(__u32 ifindex)
+{
+	char devname[IF_NAMESIZE * 2] = "(unknown)";
+	char tmpname[IF_NAMESIZE];
+	char *ret = NULL;
+
+	if (ifindex)
+		ret = if_indextoname(ifindex, tmpname);
+	else
+		snprintf(devname, sizeof(devname), "(detached)");
+	if (ret)
+		snprintf(devname, sizeof(devname), "%s(%d)",
+			 tmpname, ifindex);
+	printf("ifindex %s  ", devname);
+}
+
 static void show_iter_plain(struct bpf_link_info *info)
 {
 	const char *target_name = u64_to_ptr(info->iter.target_name);
@@ -745,6 +780,15 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info)
 	case BPF_LINK_TYPE_NETFILTER:
 		netfilter_dump_plain(info);
 		break;
+	case BPF_LINK_TYPE_TCX:
+		printf("\n\t");
+		show_link_ifindex_plain(info->tcx.ifindex);
+		show_link_attach_type_plain(info->tcx.attach_type);
+		break;
+	case BPF_LINK_TYPE_XDP:
+		printf("\n\t");
+		show_link_ifindex_plain(info->xdp.ifindex);
+		break;
 	case BPF_LINK_TYPE_KPROBE_MULTI:
 		show_kprobe_multi_plain(info);
 		break;

tools/bpf/bpftool/perf.c

@@ -236,7 +236,7 @@ static int do_help(int argc, char **argv)
 {
 	fprintf(stderr,
 		"Usage: %1$s %2$s { show | list }\n"
-		"       %1$s %2$s help }\n"
+		"       %1$s %2$s help\n"
 		"\n"
 		"       " HELP_SPEC_OPTIONS " }\n"
 		"",

tools/lib/bpf/libbpf.c

@@ -1978,9 +1978,9 @@ static int bpf_object__read_kconfig_file(struct bpf_object *obj, void *data)
 		return -ENAMETOOLONG;
 
 	/* gzopen also accepts uncompressed files. */
-	file = gzopen(buf, "r");
+	file = gzopen(buf, "re");
 	if (!file)
-		file = gzopen("/proc/config.gz", "r");
+		file = gzopen("/proc/config.gz", "re");
 
 	if (!file) {
 		pr_warn("failed to open system Kconfig\n");