1 files changed, 191 insertions, 129 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 5cc9276f1023..822d662f97ef 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -256,17 +256,6 @@ BPF_CALL_2(bpf_skb_load_helper_32_no_cache, const struct sk_buff *, skb,
 					  offset);
 }
 
-BPF_CALL_0(bpf_get_raw_cpu_id)
-{
-	return raw_smp_processor_id();
-}
-
-static const struct bpf_func_proto bpf_get_raw_smp_processor_id_proto = {
-	.func		= bpf_get_raw_cpu_id,
-	.gpl_only	= false,
-	.ret_type	= RET_INTEGER,
-};
-
 static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg,
 			      struct bpf_insn *insn_buf)
 {
@@ -3422,15 +3411,26 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = {
 
 BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset)
 {
+	void *data_hard_end = xdp_data_hard_end(xdp); /* use xdp->frame_sz */
 	void *data_end = xdp->data_end + offset;
 
-	/* only shrinking is allowed for now. */
-	if (unlikely(offset >= 0))
+	/* Notice that xdp_data_hard_end have reserved some tailroom */
+	if (unlikely(data_end > data_hard_end))
 		return -EINVAL;
 
+	/* ALL drivers MUST init xdp->frame_sz, chicken check below */
+	if (unlikely(xdp->frame_sz > PAGE_SIZE)) {
+		WARN_ONCE(1, "Too BIG xdp->frame_sz = %d\n", xdp->frame_sz);
+		return -EINVAL;
+	}
+
 	if (unlikely(data_end < xdp->data + ETH_HLEN))
 		return -EINVAL;
 
+	/* Clear memory area on grow, can contain uninit kernel memory */
+	if (offset > 0)
+		memset(xdp->data_end, 0, offset);
+
 	xdp->data_end = data_end;
 
 	return 0;
@@ -4014,16 +4014,22 @@ static const struct bpf_func_proto bpf_skb_under_cgroup_proto = {
 };
 
 #ifdef CONFIG_SOCK_CGROUP_DATA
+static inline u64 __bpf_sk_cgroup_id(struct sock *sk)
+{
+	struct cgroup *cgrp;
+
+	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+	return cgroup_id(cgrp);
+}
+
 BPF_CALL_1(bpf_skb_cgroup_id, const struct sk_buff *, skb)
 {
 	struct sock *sk = skb_to_full_sk(skb);
-	struct cgroup *cgrp;
 
 	if (!sk || !sk_fullsock(sk))
 		return 0;
 
-	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
-	return cgroup_id(cgrp);
+	return __bpf_sk_cgroup_id(sk);
 }
 
 static const struct bpf_func_proto bpf_skb_cgroup_id_proto = {
@@ -4033,16 +4039,12 @@ static const struct bpf_func_proto bpf_skb_cgroup_id_proto = {
 	.arg1_type      = ARG_PTR_TO_CTX,
 };
 
-BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int,
-	   ancestor_level)
+static inline u64 __bpf_sk_ancestor_cgroup_id(struct sock *sk,
+					      int ancestor_level)
 {
-	struct sock *sk = skb_to_full_sk(skb);
 	struct cgroup *ancestor;
 	struct cgroup *cgrp;
 
-	if (!sk || !sk_fullsock(sk))
-		return 0;
-
 	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
 	ancestor = cgroup_ancestor(cgrp, ancestor_level);
 	if (!ancestor)
@@ -4051,6 +4053,17 @@ BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int,
 	return cgroup_id(ancestor);
 }
 
+BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int,
+	   ancestor_level)
+{
+	struct sock *sk = skb_to_full_sk(skb);
+
+	if (!sk || !sk_fullsock(sk))
+		return 0;
+
+	return __bpf_sk_ancestor_cgroup_id(sk, ancestor_level);
+}
+
 static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = {
 	.func           = bpf_skb_ancestor_cgroup_id,
 	.gpl_only       = false,
@@ -4058,6 +4071,31 @@ static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = {
 	.arg1_type      = ARG_PTR_TO_CTX,
 	.arg2_type      = ARG_ANYTHING,
 };
+
+BPF_CALL_1(bpf_sk_cgroup_id, struct sock *, sk)
+{
+	return __bpf_sk_cgroup_id(sk);
+}
+
+static const struct bpf_func_proto bpf_sk_cgroup_id_proto = {
+	.func           = bpf_sk_cgroup_id,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_SOCKET,
+};
+
+BPF_CALL_2(bpf_sk_ancestor_cgroup_id, struct sock *, sk, int, ancestor_level)
+{
+	return __bpf_sk_ancestor_cgroup_id(sk, ancestor_level);
+}
+
+static const struct bpf_func_proto bpf_sk_ancestor_cgroup_id_proto = {
+	.func           = bpf_sk_ancestor_cgroup_id,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_SOCKET,
+	.arg2_type      = ARG_ANYTHING,
+};
 #endif
 
 static unsigned long bpf_xdp_copy(void *dst_buff, const void *src_buff,
@@ -4205,36 +4243,19 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = {
 	.arg1_type      = ARG_PTR_TO_CTX,
 };
 
-BPF_CALL_5(bpf_event_output_data, void *, ctx, struct bpf_map *, map, u64, flags,
-	   void *, data, u64, size)
-{
-	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
-		return -EINVAL;
-
-	return bpf_event_output(map, flags, data, size, NULL, 0, NULL);
-}
+#define SOCKOPT_CC_REINIT (1 << 0)
 
-static const struct bpf_func_proto bpf_event_output_data_proto =  {
-	.func		= bpf_event_output_data,
-	.gpl_only       = true,
-	.ret_type       = RET_INTEGER,
-	.arg1_type      = ARG_PTR_TO_CTX,
-	.arg2_type      = ARG_CONST_MAP_PTR,
-	.arg3_type      = ARG_ANYTHING,
-	.arg4_type      = ARG_PTR_TO_MEM,
-	.arg5_type      = ARG_CONST_SIZE_OR_ZERO,
-};
-
-BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
-	   int, level, int, optname, char *, optval, int, optlen)
+static int _bpf_setsockopt(struct sock *sk, int level, int optname,
+			   char *optval, int optlen, u32 flags)
 {
-	struct sock *sk = bpf_sock->sk;
 	int ret = 0;
 	int val;
 
 	if (!sk_fullsock(sk))
 		return -EINVAL;
 
+	sock_owned_by_me(sk);
+
 	if (level == SOL_SOCKET) {
 		if (optlen != sizeof(int))
 			return -EINVAL;
@@ -4329,7 +4350,7 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 		   sk->sk_prot->setsockopt == tcp_setsockopt) {
 		if (optname == TCP_CONGESTION) {
 			char name[TCP_CA_NAME_MAX];
-			bool reinit = bpf_sock->op > BPF_SOCK_OPS_NEEDS_ECN;
+			bool reinit = flags & SOCKOPT_CC_REINIT;
 
 			strncpy(name, optval, min_t(long, optlen,
 						    TCP_CA_NAME_MAX-1));
@@ -4376,24 +4397,14 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 	return ret;
 }
 
-static const struct bpf_func_proto bpf_setsockopt_proto = {
-	.func		= bpf_setsockopt,
-	.gpl_only	= false,
-	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_CTX,
-	.arg2_type	= ARG_ANYTHING,
-	.arg3_type	= ARG_ANYTHING,
-	.arg4_type	= ARG_PTR_TO_MEM,
-	.arg5_type	= ARG_CONST_SIZE,
-};
-
-BPF_CALL_5(bpf_getsockopt, struct bpf_sock_ops_kern *, bpf_sock,
-	   int, level, int, optname, char *, optval, int, optlen)
+static int _bpf_getsockopt(struct sock *sk, int level, int optname,
+			   char *optval, int optlen)
 {
-	struct sock *sk = bpf_sock->sk;
-
 	if (!sk_fullsock(sk))
 		goto err_clear;
+
+	sock_owned_by_me(sk);
+
 #ifdef CONFIG_INET
 	if (level == SOL_TCP && sk->sk_prot->getsockopt == tcp_getsockopt) {
 		struct inet_connection_sock *icsk;
@@ -4459,8 +4470,71 @@ err_clear:
 	return -EINVAL;
 }
 
-static const struct bpf_func_proto bpf_getsockopt_proto = {
-	.func		= bpf_getsockopt,
+BPF_CALL_5(bpf_sock_addr_setsockopt, struct bpf_sock_addr_kern *, ctx,
+	   int, level, int, optname, char *, optval, int, optlen)
+{
+	u32 flags = 0;
+	return _bpf_setsockopt(ctx->sk, level, optname, optval, optlen,
+			       flags);
+}
+
+static const struct bpf_func_proto bpf_sock_addr_setsockopt_proto = {
+	.func		= bpf_sock_addr_setsockopt,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_PTR_TO_MEM,
+	.arg5_type	= ARG_CONST_SIZE,
+};
+
+BPF_CALL_5(bpf_sock_addr_getsockopt, struct bpf_sock_addr_kern *, ctx,
+	   int, level, int, optname, char *, optval, int, optlen)
+{
+	return _bpf_getsockopt(ctx->sk, level, optname, optval, optlen);
+}
+
+static const struct bpf_func_proto bpf_sock_addr_getsockopt_proto = {
+	.func		= bpf_sock_addr_getsockopt,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg5_type	= ARG_CONST_SIZE,
+};
+
+BPF_CALL_5(bpf_sock_ops_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
+	   int, level, int, optname, char *, optval, int, optlen)
+{
+	u32 flags = 0;
+	if (bpf_sock->op > BPF_SOCK_OPS_NEEDS_ECN)
+		flags |= SOCKOPT_CC_REINIT;
+	return _bpf_setsockopt(bpf_sock->sk, level, optname, optval, optlen,
+			       flags);
+}
+
+static const struct bpf_func_proto bpf_sock_ops_setsockopt_proto = {
+	.func		= bpf_sock_ops_setsockopt,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_PTR_TO_MEM,
+	.arg5_type	= ARG_CONST_SIZE,
+};
+
+BPF_CALL_5(bpf_sock_ops_getsockopt, struct bpf_sock_ops_kern *, bpf_sock,
+	   int, level, int, optname, char *, optval, int, optlen)
+{
+	return _bpf_getsockopt(bpf_sock->sk, level, optname, optval, optlen);
+}
+
+static const struct bpf_func_proto bpf_sock_ops_getsockopt_proto = {
+	.func		= bpf_sock_ops_getsockopt,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_CTX,
@@ -4500,30 +4574,28 @@ BPF_CALL_3(bpf_bind, struct bpf_sock_addr_kern *, ctx, struct sockaddr *, addr,
 {
 #ifdef CONFIG_INET
 	struct sock *sk = ctx->sk;
+	u32 flags = BIND_FROM_BPF;
 	int err;
 
-	/* Binding to port can be expensive so it's prohibited in the helper.
-	 * Only binding to IP is supported.
-	 */
 	err = -EINVAL;
 	if (addr_len < offsetofend(struct sockaddr, sa_family))
 		return err;
 	if (addr->sa_family == AF_INET) {
 		if (addr_len < sizeof(struct sockaddr_in))
 			return err;
-		if (((struct sockaddr_in *)addr)->sin_port != htons(0))
-			return err;
-		return __inet_bind(sk, addr, addr_len, true, false);
+		if (((struct sockaddr_in *)addr)->sin_port == htons(0))
+			flags |= BIND_FORCE_ADDRESS_NO_PORT;
+		return __inet_bind(sk, addr, addr_len, flags);
 #if IS_ENABLED(CONFIG_IPV6)
 	} else if (addr->sa_family == AF_INET6) {
 		if (addr_len < SIN6_LEN_RFC2133)
 			return err;
-		if (((struct sockaddr_in6 *)addr)->sin6_port != htons(0))
-			return err;
+		if (((struct sockaddr_in6 *)addr)->sin6_port == htons(0))
+			flags |= BIND_FORCE_ADDRESS_NO_PORT;
 		/* ipv6_bpf_stub cannot be NULL, since it's called from
 		 * bpf_cgroup_inet6_connect hook and ipv6 is already loaded
 		 */
-		return ipv6_bpf_stub->inet6_bind(sk, addr, addr_len, true, false);
+		return ipv6_bpf_stub->inet6_bind(sk, addr, addr_len, flags);
 #endif /* CONFIG_IPV6 */
 	}
 #endif /* CONFIG_INET */
@@ -5983,52 +6055,7 @@ bool bpf_helper_changes_pkt_data(void *func)
 	return false;
 }
 
-const struct bpf_func_proto *
-bpf_base_func_proto(enum bpf_func_id func_id)
-{
-	switch (func_id) {
-	case BPF_FUNC_map_lookup_elem:
-		return &bpf_map_lookup_elem_proto;
-	case BPF_FUNC_map_update_elem:
-		return &bpf_map_update_elem_proto;
-	case BPF_FUNC_map_delete_elem:
-		return &bpf_map_delete_elem_proto;
-	case BPF_FUNC_map_push_elem:
-		return &bpf_map_push_elem_proto;
-	case BPF_FUNC_map_pop_elem:
-		return &bpf_map_pop_elem_proto;
-	case BPF_FUNC_map_peek_elem:
-		return &bpf_map_peek_elem_proto;
-	case BPF_FUNC_get_prandom_u32:
-		return &bpf_get_prandom_u32_proto;
-	case BPF_FUNC_get_smp_processor_id:
-		return &bpf_get_raw_smp_processor_id_proto;
-	case BPF_FUNC_get_numa_node_id:
-		return &bpf_get_numa_node_id_proto;
-	case BPF_FUNC_tail_call:
-		return &bpf_tail_call_proto;
-	case BPF_FUNC_ktime_get_ns:
-		return &bpf_ktime_get_ns_proto;
-	default:
-		break;
-	}
-
-	if (!capable(CAP_SYS_ADMIN))
-		return NULL;
-
-	switch (func_id) {
-	case BPF_FUNC_spin_lock:
-		return &bpf_spin_lock_proto;
-	case BPF_FUNC_spin_unlock:
-		return &bpf_spin_unlock_proto;
-	case BPF_FUNC_trace_printk:
-		return bpf_get_trace_printk_proto();
-	case BPF_FUNC_jiffies64:
-		return &bpf_jiffies64_proto;
-	default:
-		return NULL;
-	}
-}
+const struct bpf_func_proto bpf_event_output_data_proto __weak;
 
 static const struct bpf_func_proto *
 sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
@@ -6119,6 +6146,22 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_storage_get_proto;
 	case BPF_FUNC_sk_storage_delete:
 		return &bpf_sk_storage_delete_proto;
+	case BPF_FUNC_setsockopt:
+		switch (prog->expected_attach_type) {
+		case BPF_CGROUP_INET4_CONNECT:
+		case BPF_CGROUP_INET6_CONNECT:
+			return &bpf_sock_addr_setsockopt_proto;
+		default:
+			return NULL;
+		}
+	case BPF_FUNC_getsockopt:
+		switch (prog->expected_attach_type) {
+		case BPF_CGROUP_INET4_CONNECT:
+		case BPF_CGROUP_INET6_CONNECT:
+			return &bpf_sock_addr_getsockopt_proto;
+		default:
+			return NULL;
+		}
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -6163,8 +6206,22 @@ cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 #ifdef CONFIG_SOCK_CGROUP_DATA
 	case BPF_FUNC_skb_cgroup_id:
 		return &bpf_skb_cgroup_id_proto;
+	case BPF_FUNC_skb_ancestor_cgroup_id:
+		return &bpf_skb_ancestor_cgroup_id_proto;
+	case BPF_FUNC_sk_cgroup_id:
+		return &bpf_sk_cgroup_id_proto;
+	case BPF_FUNC_sk_ancestor_cgroup_id:
+		return &bpf_sk_ancestor_cgroup_id_proto;
 #endif
 #ifdef CONFIG_INET
+	case BPF_FUNC_sk_lookup_tcp:
+		return &bpf_sk_lookup_tcp_proto;
+	case BPF_FUNC_sk_lookup_udp:
+		return &bpf_sk_lookup_udp_proto;
+	case BPF_FUNC_sk_release:
+		return &bpf_sk_release_proto;
+	case BPF_FUNC_skc_lookup_tcp:
+		return &bpf_skc_lookup_tcp_proto;
 	case BPF_FUNC_tcp_sock:
 		return &bpf_tcp_sock_proto;
 	case BPF_FUNC_get_listener_sock:
@@ -6213,6 +6270,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_skb_adjust_room_proto;
 	case BPF_FUNC_skb_change_tail:
 		return &bpf_skb_change_tail_proto;
+	case BPF_FUNC_skb_change_head:
+		return &bpf_skb_change_head_proto;
 	case BPF_FUNC_skb_get_tunnel_key:
 		return &bpf_skb_get_tunnel_key_proto;
 	case BPF_FUNC_skb_set_tunnel_key:
@@ -6335,9 +6394,9 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
 	case BPF_FUNC_setsockopt:
-		return &bpf_setsockopt_proto;
+		return &bpf_sock_ops_setsockopt_proto;
 	case BPF_FUNC_getsockopt:
-		return &bpf_getsockopt_proto;
+		return &bpf_sock_ops_getsockopt_proto;
 	case BPF_FUNC_sock_ops_cb_flags_set:
 		return &bpf_sock_ops_cb_flags_set_proto;
 	case BPF_FUNC_sock_map_update:
@@ -6628,7 +6687,7 @@ static bool cg_skb_is_valid_access(int off, int size,
 		return false;
 	case bpf_ctx_range(struct __sk_buff, data):
 	case bpf_ctx_range(struct __sk_buff, data_end):
-		if (!capable(CAP_SYS_ADMIN))
+		if (!bpf_capable())
 			return false;
 		break;
 	}
@@ -6640,7 +6699,7 @@ static bool cg_skb_is_valid_access(int off, int size,
 		case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]):
 			break;
 		case bpf_ctx_range(struct __sk_buff, tstamp):
-			if (!capable(CAP_SYS_ADMIN))
+			if (!bpf_capable())
 				return false;
 			break;
 		default:
@@ -7033,6 +7092,7 @@ static bool sock_addr_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4):
 	case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0],
 				msg_src_ip6[3]):
+	case bpf_ctx_range(struct bpf_sock_addr, user_port):
 		if (type == BPF_READ) {
 			bpf_ctx_record_field_size(info, size_default);
 
@@ -7063,10 +7123,6 @@ static bool sock_addr_is_valid_access(int off, int size,
 				return false;
 		}
 		break;
-	case bpf_ctx_range(struct bpf_sock_addr, user_port):
-		if (size != size_default)
-			return false;
-		break;
 	case offsetof(struct bpf_sock_addr, sk):
 		if (type != BPF_READ)
 			return false;
@@ -7962,8 +8018,8 @@ static u32 sock_addr_convert_ctx_access(enum bpf_access_type type,
 					struct bpf_insn *insn_buf,
 					struct bpf_prog *prog, u32 *target_size)
 {
+	int off, port_size = sizeof_field(struct sockaddr_in6, sin6_port);
 	struct bpf_insn *insn = insn_buf;
-	int off;
 
 	switch (si->off) {
 	case offsetof(struct bpf_sock_addr, user_family):
@@ -7998,9 +8054,11 @@ static u32 sock_addr_convert_ctx_access(enum bpf_access_type type,
 			     offsetof(struct sockaddr_in6, sin6_port));
 		BUILD_BUG_ON(sizeof_field(struct sockaddr_in, sin_port) !=
 			     sizeof_field(struct sockaddr_in6, sin6_port));
-		SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD(struct bpf_sock_addr_kern,
-						     struct sockaddr_in6, uaddr,
-						     sin6_port, tmp_reg);
+		/* Account for sin6_port being smaller than user_port. */
+		port_size = min(port_size, BPF_LDST_BYTES(si));
+		SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF(
+			struct bpf_sock_addr_kern, struct sockaddr_in6, uaddr,
+			sin6_port, bytes_to_bpf_size(port_size), 0, tmp_reg);
 		break;
 
 	case offsetof(struct bpf_sock_addr, family):
@@ -8786,6 +8844,10 @@ BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern,
 
 	reuse = rcu_dereference(selected_sk->sk_reuseport_cb);
 	if (!reuse) {
+		/* Lookup in sock_map can return TCP ESTABLISHED sockets. */
+		if (sk_is_refcounted(selected_sk))
+			sock_put(selected_sk);
+
 		/* reuseport_array has only sk with non NULL sk_reuseport_cb.
 		 * The only (!reuse) case here is - the sk has already been
 		 * unhashed (e.g. by close()), so treat it as -ENOENT.