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

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-10-21

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

The main changes are:

1) Implement two new kind of BPF maps, that is, queue and stack
   map along with new peek, push and pop operations, from Mauricio.

2) Add support for MSG_PEEK flag when redirecting into an ingress
   psock sk_msg queue, and add a new helper bpf_msg_push_data() for
   insert data into the message, from John.

3) Allow for BPF programs of type BPF_PROG_TYPE_CGROUP_SKB to use
   direct packet access for __skb_buff, from Song.

4) Use more lightweight barriers for walking perf ring buffer for
   libbpf and perf tool as well. Also, various fixes and improvements
   from verifier side, from Daniel.

5) Add per-symbol visibility for DSO in libbpf and hide by default
   global symbols such as netlink related functions, from Andrey.

6) Two improvements to nfp's BPF offload to check vNIC capabilities
   in case prog is shared with multiple vNICs and to protect against
   mis-initializing atomic counters, from Jakub.

7) Fix for bpftool to use 4 context mode for the nfp disassembler,
   also from Jakub.

8) Fix a return value comparison in test_libbpf.sh and add several
   bpftool improvements in bash completion, documentation of bpf fs
   restrictions and batch mode summary print, from Quentin.

9) Fix a file resource leak in BPF selftest's load_kallsyms()
   helper, from Peng.

10) Fix an unused variable warning in map_lookup_and_delete_elem(),
    from Alexei.

11) Fix bpf_skb_adjust_room() signature in BPF UAPI helper doc,
    from Nicolas.

12) Add missing executables to .gitignore in BPF selftests, from Anders.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 27 insertions, 14 deletions

diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 80debb0daf37..b7918d4caa30 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -39,17 +39,19 @@ static int tcp_bpf_wait_data(struct sock *sk, struct sk_psock *psock,
 }
 
 int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
-		      struct msghdr *msg, int len)
+		      struct msghdr *msg, int len, int flags)
 {
 	struct iov_iter *iter = &msg->msg_iter;
+	int peek = flags & MSG_PEEK;
 	int i, ret, copied = 0;
+	struct sk_msg *msg_rx;
+
+	msg_rx = list_first_entry_or_null(&psock->ingress_msg,
+					  struct sk_msg, list);
 
 	while (copied != len) {
 		struct scatterlist *sge;
-		struct sk_msg *msg_rx;
 
-		msg_rx = list_first_entry_or_null(&psock->ingress_msg,
-						  struct sk_msg, list);
 		if (unlikely(!msg_rx))
 			break;
 
@@ -70,21 +72,30 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
 			}
 
 			copied += copy;
-			sge->offset += copy;
-			sge->length -= copy;
-			sk_mem_uncharge(sk, copy);
-			if (!sge->length) {
-				i++;
-				if (i == MAX_SKB_FRAGS)
-					i = 0;
-				if (!msg_rx->skb)
-					put_page(page);
+			if (likely(!peek)) {
+				sge->offset += copy;
+				sge->length -= copy;
+				sk_mem_uncharge(sk, copy);
+				msg_rx->sg.size -= copy;
+
+				if (!sge->length) {
+					sk_msg_iter_var_next(i);
+					if (!msg_rx->skb)
+						put_page(page);
+				}
+			} else {
+				sk_msg_iter_var_next(i);
 			}
 
 			if (copied == len)
 				break;
 		} while (i != msg_rx->sg.end);
 
+		if (unlikely(peek)) {
+			msg_rx = list_next_entry(msg_rx, list);
+			continue;
+		}
+
 		msg_rx->sg.start = i;
 		if (!sge->length && msg_rx->sg.start == msg_rx->sg.end) {
 			list_del(&msg_rx->list);
@@ -92,6 +103,8 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
 				consume_skb(msg_rx->skb);
 			kfree(msg_rx);
 		}
+		msg_rx = list_first_entry_or_null(&psock->ingress_msg,
+						  struct sk_msg, list);
 	}
 
 	return copied;
@@ -114,7 +127,7 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 	lock_sock(sk);
 msg_bytes_ready:
-	copied = __tcp_bpf_recvmsg(sk, psock, msg, len);
+	copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags);
 	if (!copied) {
 		int data, err = 0;
 		long timeo;