bpf: Add bpf_skc_to_tcp6_sock() helper

The helper is used in tracing programs to cast a socket
pointer to a tcp6_sock pointer.
The return value could be NULL if the casting is illegal.

A new helper return type RET_PTR_TO_BTF_ID_OR_NULL is added
so the verifier is able to deduce proper return types for the helper.

Different from the previous BTF_ID based helpers,
the bpf_skc_to_tcp6_sock() argument can be several possible
btf_ids. More specifically, all possible socket data structures
with sock_common appearing in the first in the memory layout.
This patch only added socket types related to tcp and udp.

All possible argument btf_id and return value btf_id
for helper bpf_skc_to_tcp6_sock() are pre-calculcated and
cached. In the future, it is even possible to precompute
these btf_id's at kernel build time.
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200623230809.3988195-1-yhs@fb.com

include/linux/bpf.h

@@ -265,6 +265,7 @@ enum bpf_return_type {
 	RET_PTR_TO_TCP_SOCK_OR_NULL,	/* returns a pointer to a tcp_sock or NULL */
 	RET_PTR_TO_SOCK_COMMON_OR_NULL,	/* returns a pointer to a sock_common or NULL */
 	RET_PTR_TO_ALLOC_MEM_OR_NULL,	/* returns a pointer to dynamically allocated memory or NULL */
+	RET_PTR_TO_BTF_ID_OR_NULL,	/* returns a pointer to a btf_id or NULL */
 };
 
 /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs
@@ -287,6 +288,12 @@ struct bpf_func_proto {
 		enum bpf_arg_type arg_type[5];
 	};
 	int *btf_id; /* BTF ids of arguments */
+	bool (*check_btf_id)(u32 btf_id, u32 arg); /* if the argument btf_id is
+						    * valid. Often used if more
+						    * than one btf id is permitted
+						    * for this argument.
+						    */
+	int *ret_btf_id; /* return value btf_id */
 };
 
 /* bpf_context is intentionally undefined structure. Pointer to bpf_context is
@@ -1524,6 +1531,7 @@ static inline bool bpf_map_is_dev_bound(struct bpf_map *map)
 
 struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr);
 void bpf_map_offload_map_free(struct bpf_map *map);
+void init_btf_sock_ids(struct btf *btf);
 #else
 static inline int bpf_prog_offload_init(struct bpf_prog *prog,
 					union bpf_attr *attr)
@@ -1549,6 +1557,9 @@ static inline struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
 static inline void bpf_map_offload_map_free(struct bpf_map *map)
 {
 }
+static inline void init_btf_sock_ids(struct btf *btf)
+{
+}
 #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */
 
 #if defined(CONFIG_BPF_STREAM_PARSER)
@@ -1638,6 +1649,7 @@ extern const struct bpf_func_proto bpf_ringbuf_reserve_proto;
 extern const struct bpf_func_proto bpf_ringbuf_submit_proto;
 extern const struct bpf_func_proto bpf_ringbuf_discard_proto;
 extern const struct bpf_func_proto bpf_ringbuf_query_proto;
+extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
 	enum bpf_func_id func_id, const struct bpf_prog *prog);

include/uapi/linux/bpf.h

@@ -3255,6 +3255,12 @@ union bpf_attr {
  * 		case of **BPF_CSUM_LEVEL_QUERY**, the current skb->csum_level
  * 		is returned or the error code -EACCES in case the skb is not
  * 		subject to CHECKSUM_UNNECESSARY.
+ *
+ * struct tcp6_sock *bpf_skc_to_tcp6_sock(void *sk)
+ *	Description
+ *		Dynamically cast a *sk* pointer to a *tcp6_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or NULL otherwise.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3392,7 +3398,8 @@ union bpf_attr {
 	FN(ringbuf_submit),		\
 	FN(ringbuf_discard),		\
 	FN(ringbuf_query),		\
-	FN(csum_level),
+	FN(csum_level),			\
+	FN(skc_to_tcp6_sock),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call

kernel/bpf/btf.c

@@ -3674,6 +3674,7 @@ struct btf *btf_parse_vmlinux(void)
 		goto errout;
 
 	bpf_struct_ops_init(btf, log);
+	init_btf_sock_ids(btf);
 
 	btf_verifier_env_free(env);
 	refcount_set(&btf->refcnt, 1);

kernel/bpf/verifier.c

@@ -3800,12 +3800,14 @@ static int int_ptr_type_to_size(enum bpf_arg_type type)
 	return -EINVAL;
 }
 
-static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
-			  enum bpf_arg_type arg_type,
-			  struct bpf_call_arg_meta *meta)
+static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
+			  struct bpf_call_arg_meta *meta,
+			  const struct bpf_func_proto *fn)
 {
+	u32 regno = BPF_REG_1 + arg;
 	struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
 	enum bpf_reg_type expected_type, type = reg->type;
+	enum bpf_arg_type arg_type = fn->arg_type[arg];
 	int err = 0;
 
 	if (arg_type == ARG_DONTCARE)
@@ -3885,6 +3887,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 		expected_type = PTR_TO_BTF_ID;
 		if (type != expected_type)
 			goto err_type;
+		if (!fn->check_btf_id) {
 			if (reg->btf_id != meta->btf_id) {
 				verbose(env, "Helper has type %s got %s in R%d\n",
 					kernel_type_name(meta->btf_id),
@@ -3892,6 +3895,12 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 
 				return -EACCES;
 			}
+		} else if (!fn->check_btf_id(reg->btf_id, arg)) {
+			verbose(env, "Helper does not support %s in R%d\n",
+				kernel_type_name(reg->btf_id), regno);
+
+			return -EACCES;
+		}
 		if (!tnum_is_const(reg->var_off) || reg->var_off.value || reg->off) {
 			verbose(env, "R%d is a pointer to in-kernel struct with non-zero offset\n",
 				regno);
@@ -4709,10 +4718,12 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 	meta.func_id = func_id;
 	/* check args */
 	for (i = 0; i < 5; i++) {
+		if (!fn->check_btf_id) {
 			err = btf_resolve_helper_id(&env->log, fn, i);
 			if (err > 0)
 				meta.btf_id = err;
-		err = check_func_arg(env, BPF_REG_1 + i, fn->arg_type[i], &meta);
+		}
+		err = check_func_arg(env, i, &meta, fn);
 		if (err)
 			return err;
 	}
@@ -4815,6 +4826,18 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 		regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL;
 		regs[BPF_REG_0].id = ++env->id_gen;
 		regs[BPF_REG_0].mem_size = meta.mem_size;
+	} else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL) {
+		int ret_btf_id;
+
+		mark_reg_known_zero(env, regs, BPF_REG_0);
+		regs[BPF_REG_0].type = PTR_TO_BTF_ID_OR_NULL;
+		ret_btf_id = *fn->ret_btf_id;
+		if (ret_btf_id == 0) {
+			verbose(env, "invalid return type %d of func %s#%d\n",
+				fn->ret_type, func_id_name(func_id), func_id);
+			return -EINVAL;
+		}
+		regs[BPF_REG_0].btf_id = ret_btf_id;
 	} else {
 		verbose(env, "unknown return type %d of func %s#%d\n",
 			fn->ret_type, func_id_name(func_id), func_id);

kernel/trace/bpf_trace.c

@@ -1515,6 +1515,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_skb_output_proto;
 	case BPF_FUNC_xdp_output:
 		return &bpf_xdp_output_proto;
+	case BPF_FUNC_skc_to_tcp6_sock:
+		return &bpf_skc_to_tcp6_sock_proto;
 #endif
 	case BPF_FUNC_seq_printf:
 		return prog->expected_attach_type == BPF_TRACE_ITER ?

net/core/filter.c

@@ -47,6 +47,7 @@
 #include <linux/seccomp.h>
 #include <linux/if_vlan.h>
 #include <linux/bpf.h>
+#include <linux/btf.h>
 #include <net/sch_generic.h>
 #include <net/cls_cgroup.h>
 #include <net/dst_metadata.h>
@@ -9225,3 +9226,84 @@ void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog)
 {
 	bpf_dispatcher_change_prog(BPF_DISPATCHER_PTR(xdp), prev_prog, prog);
 }
+
+/* Define a list of socket types which can be the argument for
+ * skc_to_*_sock() helpers. All these sockets should have
+ * sock_common as the first argument in its memory layout.
+ */
+#define BTF_SOCK_TYPE_xxx \
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET, "inet_sock")			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_CONN, "inet_connection_sock")	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_REQ, "inet_request_sock")	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_TW, "inet_timewait_sock")	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_REQ, "request_sock")		\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK, "sock")			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK_COMMON, "sock_common")		\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP, "tcp_sock")			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_REQ, "tcp_request_sock")	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_TW, "tcp_timewait_sock")	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP6, "tcp6_sock")			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, "udp_sock")			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, "udp6_sock")
+
+enum {
+#define BTF_SOCK_TYPE(name, str) name,
+BTF_SOCK_TYPE_xxx
+#undef BTF_SOCK_TYPE
+MAX_BTF_SOCK_TYPE,
+};
+
+static int btf_sock_ids[MAX_BTF_SOCK_TYPE];
+
+#ifdef CONFIG_BPF_SYSCALL
+static const char *bpf_sock_types[] = {
+#define BTF_SOCK_TYPE(name, str) str,
+BTF_SOCK_TYPE_xxx
+#undef BTF_SOCK_TYPE
+};
+
+void init_btf_sock_ids(struct btf *btf)
+{
+	int i, btf_id;
+
+	for (i = 0; i < MAX_BTF_SOCK_TYPE; i++) {
+		btf_id = btf_find_by_name_kind(btf, bpf_sock_types[i],
+					       BTF_KIND_STRUCT);
+		if (btf_id > 0)
+			btf_sock_ids[i] = btf_id;
+	}
+}
+#endif
+
+static bool check_arg_btf_id(u32 btf_id, u32 arg)
+{
+	int i;
+
+	/* only one argument, no need to check arg */
+	for (i = 0; i < MAX_BTF_SOCK_TYPE; i++)
+		if (btf_sock_ids[i] == btf_id)
+			return true;
+	return false;
+}
+
+BPF_CALL_1(bpf_skc_to_tcp6_sock, struct sock *, sk)
+{
+	/* tcp6_sock type is not generated in dwarf and hence btf,
+	 * trigger an explicit type generation here.
+	 */
+	BTF_TYPE_EMIT(struct tcp6_sock);
+	if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP &&
+	    sk->sk_family == AF_INET6)
+		return (unsigned long)sk;
+
+	return (unsigned long)NULL;
+}
+
+const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto = {
+	.func			= bpf_skc_to_tcp6_sock,
+	.gpl_only		= false,
+	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
+	.arg1_type		= ARG_PTR_TO_BTF_ID,
+	.check_btf_id		= check_arg_btf_id,
+	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP6],
+};

scripts/bpf_helpers_doc.py

@@ -421,6 +421,7 @@ class PrinterHelpers(Printer):
             'struct sockaddr',
             'struct tcphdr',
             'struct seq_file',
+            'struct tcp6_sock',
 
             'struct __sk_buff',
             'struct sk_msg_md',
@@ -458,6 +459,7 @@ class PrinterHelpers(Printer):
             'struct sockaddr',
             'struct tcphdr',
             'struct seq_file',
+            'struct tcp6_sock',
     }
     mapped_types = {
             'u8': '__u8',

tools/include/uapi/linux/bpf.h

@@ -3255,6 +3255,12 @@ union bpf_attr {
  * 		case of **BPF_CSUM_LEVEL_QUERY**, the current skb->csum_level
  * 		is returned or the error code -EACCES in case the skb is not
  * 		subject to CHECKSUM_UNNECESSARY.
+ *
+ * struct tcp6_sock *bpf_skc_to_tcp6_sock(void *sk)
+ *	Description
+ *		Dynamically cast a *sk* pointer to a *tcp6_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or NULL otherwise.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3392,7 +3398,8 @@ union bpf_attr {
 	FN(ringbuf_submit),		\
 	FN(ringbuf_discard),		\
 	FN(ringbuf_query),		\
-	FN(csum_level),
+	FN(csum_level),			\
+	FN(skc_to_tcp6_sock),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call