Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Alexei Starovoitov says:

====================
pull-request: bpf-next 2021-05-19

The following pull-request contains BPF updates for your *net-next* tree.

We've added 43 non-merge commits during the last 11 day(s) which contain
a total of 74 files changed, 3717 insertions(+), 578 deletions(-).

The main changes are:

1) syscall program type, fd array, and light skeleton, from Alexei.

2) Stop emitting static variables in skeleton, from Andrii.

3) Low level tc-bpf api, from Kumar.

4) Reduce verifier kmalloc/kfree churn, from Lorenz.
====================

5 files changed, 62 insertions, 25 deletions

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index a5d72c48fb66..aa47af349ba8 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -409,7 +409,7 @@ static void *bpf_ctx_init(const union bpf_attr *kattr, u32 max_size)
 		return ERR_PTR(-ENOMEM);
 
 	if (data_in) {
-		err = bpf_check_uarg_tail_zero(data_in, max_size, size);
+		err = bpf_check_uarg_tail_zero(USER_BPFPTR(data_in), max_size, size);
 		if (err) {
 			kfree(data);
 			return ERR_PTR(err);
@@ -918,3 +918,46 @@ out:
 	kfree(user_ctx);
 	return ret;
 }
+
+int bpf_prog_test_run_syscall(struct bpf_prog *prog,
+			      const union bpf_attr *kattr,
+			      union bpf_attr __user *uattr)
+{
+	void __user *ctx_in = u64_to_user_ptr(kattr->test.ctx_in);
+	__u32 ctx_size_in = kattr->test.ctx_size_in;
+	void *ctx = NULL;
+	u32 retval;
+	int err = 0;
+
+	/* doesn't support data_in/out, ctx_out, duration, or repeat or flags */
+	if (kattr->test.data_in || kattr->test.data_out ||
+	    kattr->test.ctx_out || kattr->test.duration ||
+	    kattr->test.repeat || kattr->test.flags)
+		return -EINVAL;
+
+	if (ctx_size_in < prog->aux->max_ctx_offset ||
+	    ctx_size_in > U16_MAX)
+		return -EINVAL;
+
+	if (ctx_size_in) {
+		ctx = kzalloc(ctx_size_in, GFP_USER);
+		if (!ctx)
+			return -ENOMEM;
+		if (copy_from_user(ctx, ctx_in, ctx_size_in)) {
+			err = -EFAULT;
+			goto out;
+		}
+	}
+	retval = bpf_prog_run_pin_on_cpu(prog, ctx);
+
+	if (copy_to_user(&uattr->test.retval, &retval, sizeof(u32))) {
+		err = -EFAULT;
+		goto out;
+	}
+	if (ctx_size_in)
+		if (copy_to_user(ctx_in, ctx, ctx_size_in))
+			err = -EFAULT;
+out:
+	kfree(ctx);
+	return err;
+}
diff --git a/net/core/filter.c b/net/core/filter.c
index cae56d08a670..582ac196fd94 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3235,7 +3235,7 @@ static int bpf_skb_net_hdr_pop(struct sk_buff *skb, u32 off, u32 len)
 	return ret;
 }
 
-static int bpf_skb_proto_4_to_6(struct sk_buff *skb)
+static int bpf_skb_proto_4_to_6(struct sk_buff *skb, u64 flags)
 {
 	const u32 len_diff = sizeof(struct ipv6hdr) - sizeof(struct iphdr);
 	u32 off = skb_mac_header_len(skb);
@@ -3264,7 +3264,9 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb)
 		}
 
 		/* Due to IPv6 header, MSS needs to be downgraded. */
-		skb_decrease_gso_size(shinfo, len_diff);
+		if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO))
+			skb_decrease_gso_size(shinfo, len_diff);
+
 		/* Header must be checked, and gso_segs recomputed. */
 		shinfo->gso_type |= SKB_GSO_DODGY;
 		shinfo->gso_segs = 0;
@@ -3276,7 +3278,7 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb)
 	return 0;
 }
 
-static int bpf_skb_proto_6_to_4(struct sk_buff *skb)
+static int bpf_skb_proto_6_to_4(struct sk_buff *skb, u64 flags)
 {
 	const u32 len_diff = sizeof(struct ipv6hdr) - sizeof(struct iphdr);
 	u32 off = skb_mac_header_len(skb);
@@ -3305,7 +3307,9 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb)
 		}
 
 		/* Due to IPv4 header, MSS can be upgraded. */
-		skb_increase_gso_size(shinfo, len_diff);
+		if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO))
+			skb_increase_gso_size(shinfo, len_diff);
+
 		/* Header must be checked, and gso_segs recomputed. */
 		shinfo->gso_type |= SKB_GSO_DODGY;
 		shinfo->gso_segs = 0;
@@ -3317,17 +3321,17 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb)
 	return 0;
 }
 
-static int bpf_skb_proto_xlat(struct sk_buff *skb, __be16 to_proto)
+static int bpf_skb_proto_xlat(struct sk_buff *skb, __be16 to_proto, u64 flags)
 {
 	__be16 from_proto = skb->protocol;
 
 	if (from_proto == htons(ETH_P_IP) &&
 	      to_proto == htons(ETH_P_IPV6))
-		return bpf_skb_proto_4_to_6(skb);
+		return bpf_skb_proto_4_to_6(skb, flags);
 
 	if (from_proto == htons(ETH_P_IPV6) &&
 	      to_proto == htons(ETH_P_IP))
-		return bpf_skb_proto_6_to_4(skb);
+		return bpf_skb_proto_6_to_4(skb, flags);
 
 	return -ENOTSUPP;
 }
@@ -3337,7 +3341,7 @@ BPF_CALL_3(bpf_skb_change_proto, struct sk_buff *, skb, __be16, proto,
 {
 	int ret;
 
-	if (unlikely(flags))
+	if (unlikely(flags & ~(BPF_F_ADJ_ROOM_FIXED_GSO)))
 		return -EINVAL;
 
 	/* General idea is that this helper does the basic groundwork
@@ -3357,7 +3361,7 @@ BPF_CALL_3(bpf_skb_change_proto, struct sk_buff *, skb, __be16, proto,
 	 * that. For offloads, we mark packet as dodgy, so that headers
 	 * need to be verified first.
 	 */
-	ret = bpf_skb_proto_xlat(skb, proto);
+	ret = bpf_skb_proto_xlat(skb, proto, flags);
 	bpf_compute_data_pointers(skb);
 	return ret;
 }
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 43ce17a6a585..f0b9decdf279 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -399,8 +399,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter);
 
-int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, int flags,
-		     long timeo, int *err)
+int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, long timeo)
 {
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	int ret = 0;
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index ad9d17923fc5..a80de92ea3b6 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -184,11 +184,11 @@ static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 msg_bytes_ready:
 	copied = sk_msg_recvmsg(sk, psock, msg, len, flags);
 	if (!copied) {
-		int data, err = 0;
 		long timeo;
+		int data;
 
 		timeo = sock_rcvtimeo(sk, nonblock);
-		data = sk_msg_wait_data(sk, psock, flags, timeo, &err);
+		data = sk_msg_wait_data(sk, psock, timeo);
 		if (data) {
 			if (!sk_psock_queue_empty(psock))
 				goto msg_bytes_ready;
@@ -196,14 +196,9 @@ msg_bytes_ready:
 			sk_psock_put(sk, psock);
 			return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 		}
-		if (err) {
-			ret = err;
-			goto out;
-		}
 		copied = -EAGAIN;
 	}
 	ret = copied;
-out:
 	release_sock(sk);
 	sk_psock_put(sk, psock);
 	return ret;
diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
index 954c4591a6fd..b07e4b6dda25 100644
--- a/net/ipv4/udp_bpf.c
+++ b/net/ipv4/udp_bpf.c
@@ -43,21 +43,17 @@ static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 msg_bytes_ready:
 	copied = sk_msg_recvmsg(sk, psock, msg, len, flags);
 	if (!copied) {
-		int data, err = 0;
 		long timeo;
+		int data;
 
 		timeo = sock_rcvtimeo(sk, nonblock);
-		data = sk_msg_wait_data(sk, psock, flags, timeo, &err);
+		data = sk_msg_wait_data(sk, psock, timeo);
 		if (data) {
 			if (!sk_psock_queue_empty(psock))
 				goto msg_bytes_ready;
 			ret = sk_udp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 			goto out;
 		}
-		if (err) {
-			ret = err;
-			goto out;
-		}
 		copied = -EAGAIN;
 	}
 	ret = copied;