summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2018-01-28 21:22:46 -0500
committerDavid S. Miller <davem@davemloft.net>2018-01-28 21:22:46 -0500
commit457740a903db30b14d53060f4e10d8cdecf464ac (patch)
tree18dd5d2200031fba1d4784e1376ca2b81ee88523 /net/ipv4
parent6b2e2829c11ea677aa97ecfe95d9544aa0208b8c (diff)
parent8223967fe0b8eb2448cca5cfe3c64a0838e6f60d (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Alexei Starovoitov says: ==================== pull-request: bpf-next 2018-01-26 The following pull-request contains BPF updates for your *net-next* tree. The main changes are: 1) A number of extensions to tcp-bpf, from Lawrence. - direct R or R/W access to many tcp_sock fields via bpf_sock_ops - passing up to 3 arguments to bpf_sock_ops functions - tcp_sock field bpf_sock_ops_cb_flags for controlling callbacks - optionally calling bpf_sock_ops program when RTO fires - optionally calling bpf_sock_ops program when packet is retransmitted - optionally calling bpf_sock_ops program when TCP state changes - access to tclass and sk_txhash - new selftest 2) div/mod exception handling, from Daniel. One of the ugly leftovers from the early eBPF days is that div/mod operations based on registers have a hard-coded src_reg == 0 test in the interpreter as well as in JIT code generators that would return from the BPF program with exit code 0. This was basically adopted from cBPF interpreter for historical reasons. There are multiple reasons why this is very suboptimal and prone to bugs. To name one: the return code mapping for such abnormal program exit of 0 does not always match with a suitable program type's exit code mapping. For example, '0' in tc means action 'ok' where the packet gets passed further up the stack, which is just undesirable for such cases (e.g. when implementing policy) and also does not match with other program types. After considering _four_ different ways to address the problem, we adapt the same behavior as on some major archs like ARMv8: X div 0 results in 0, and X mod 0 results in X. aarch64 and aarch32 ISA do not generate any traps or otherwise aborts of program execution for unsigned divides. Given the options, it seems the most suitable from all of them, also since major archs have similar schemes in place. Given this is all in the realm of undefined behavior, we still have the option to adapt if deemed necessary. 3) sockmap sample refactoring, from John. 4) lpm map get_next_key fixes, from Yonghong. 5) test cleanups, from Alexei and Prashant. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/tcp.c26
-rw-r--r--net/ipv4/tcp_nv.c2
-rw-r--r--net/ipv4/tcp_output.c6
-rw-r--r--net/ipv4/tcp_timer.c7
4 files changed, 38 insertions, 3 deletions
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index d7cf861bf699..f013ddc191e0 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -463,7 +463,7 @@ void tcp_init_transfer(struct sock *sk, int bpf_op)
tcp_mtup_init(sk);
icsk->icsk_af_ops->rebuild_header(sk);
tcp_init_metrics(sk);
- tcp_call_bpf(sk, bpf_op);
+ tcp_call_bpf(sk, bpf_op, 0, NULL);
tcp_init_congestion_control(sk);
tcp_init_buffer_space(sk);
}
@@ -2042,6 +2042,30 @@ void tcp_set_state(struct sock *sk, int state)
{
int oldstate = sk->sk_state;
+ /* We defined a new enum for TCP states that are exported in BPF
+ * so as not force the internal TCP states to be frozen. The
+ * following checks will detect if an internal state value ever
+ * differs from the BPF value. If this ever happens, then we will
+ * need to remap the internal value to the BPF value before calling
+ * tcp_call_bpf_2arg.
+ */
+ BUILD_BUG_ON((int)BPF_TCP_ESTABLISHED != (int)TCP_ESTABLISHED);
+ BUILD_BUG_ON((int)BPF_TCP_SYN_SENT != (int)TCP_SYN_SENT);
+ BUILD_BUG_ON((int)BPF_TCP_SYN_RECV != (int)TCP_SYN_RECV);
+ BUILD_BUG_ON((int)BPF_TCP_FIN_WAIT1 != (int)TCP_FIN_WAIT1);
+ BUILD_BUG_ON((int)BPF_TCP_FIN_WAIT2 != (int)TCP_FIN_WAIT2);
+ BUILD_BUG_ON((int)BPF_TCP_TIME_WAIT != (int)TCP_TIME_WAIT);
+ BUILD_BUG_ON((int)BPF_TCP_CLOSE != (int)TCP_CLOSE);
+ BUILD_BUG_ON((int)BPF_TCP_CLOSE_WAIT != (int)TCP_CLOSE_WAIT);
+ BUILD_BUG_ON((int)BPF_TCP_LAST_ACK != (int)TCP_LAST_ACK);
+ BUILD_BUG_ON((int)BPF_TCP_LISTEN != (int)TCP_LISTEN);
+ BUILD_BUG_ON((int)BPF_TCP_CLOSING != (int)TCP_CLOSING);
+ BUILD_BUG_ON((int)BPF_TCP_NEW_SYN_RECV != (int)TCP_NEW_SYN_RECV);
+ BUILD_BUG_ON((int)BPF_TCP_MAX_STATES != (int)TCP_MAX_STATES);
+
+ if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_STATE_CB_FLAG))
+ tcp_call_bpf_2arg(sk, BPF_SOCK_OPS_STATE_CB, oldstate, state);
+
switch (state) {
case TCP_ESTABLISHED:
if (oldstate != TCP_ESTABLISHED)
diff --git a/net/ipv4/tcp_nv.c b/net/ipv4/tcp_nv.c
index 0b5a05bd82e3..ddbce73edae8 100644
--- a/net/ipv4/tcp_nv.c
+++ b/net/ipv4/tcp_nv.c
@@ -146,7 +146,7 @@ static void tcpnv_init(struct sock *sk)
* within a datacenter, where we have reasonable estimates of
* RTTs
*/
- base_rtt = tcp_call_bpf(sk, BPF_SOCK_OPS_BASE_RTT);
+ base_rtt = tcp_call_bpf(sk, BPF_SOCK_OPS_BASE_RTT, 0, NULL);
if (base_rtt > 0) {
ca->nv_base_rtt = base_rtt;
ca->nv_lower_bound_rtt = (base_rtt * 205) >> 8; /* 80% */
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 95461f02ac9a..e9f985e42405 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2905,6 +2905,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
}
+ if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RETRANS_CB_FLAG))
+ tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RETRANS_CB,
+ TCP_SKB_CB(skb)->seq, segs, err);
+
if (likely(!err)) {
TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
trace_tcp_retransmit_skb(sk, skb);
@@ -3469,7 +3473,7 @@ int tcp_connect(struct sock *sk)
struct sk_buff *buff;
int err;
- tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB);
+ tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB, 0, NULL);
if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk))
return -EHOSTUNREACH; /* Routing failure or similar. */
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 6db3124cdbda..257abdde23b0 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -213,11 +213,18 @@ static int tcp_write_timeout(struct sock *sk)
icsk->icsk_user_timeout);
}
tcp_fastopen_active_detect_blackhole(sk, expired);
+
+ if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTO_CB_FLAG))
+ tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RTO_CB,
+ icsk->icsk_retransmits,
+ icsk->icsk_rto, (int)expired);
+
if (expired) {
/* Has it gone just too far? */
tcp_write_err(sk);
return 1;
}
+
return 0;
}