summaryrefslogtreecommitdiff
path: root/include/net
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2018-01-29 05:22:46 +0300
committerDavid S. Miller <davem@davemloft.net>2018-01-29 05:22:46 +0300
commit457740a903db30b14d53060f4e10d8cdecf464ac (patch)
tree18dd5d2200031fba1d4784e1376ca2b81ee88523 /include/net
parent6b2e2829c11ea677aa97ecfe95d9544aa0208b8c (diff)
parent8223967fe0b8eb2448cca5cfe3c64a0838e6f60d (diff)
downloadlinux-457740a903db30b14d53060f4e10d8cdecf464ac.tar.xz
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 'include/net')
-rw-r--r--include/net/tcp.h42
1 files changed, 36 insertions, 6 deletions
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 5a1d26a18599..093e967a2960 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2006,12 +2006,12 @@ void tcp_cleanup_ulp(struct sock *sk);
* program loaded).
*/
#ifdef CONFIG_BPF
-static inline int tcp_call_bpf(struct sock *sk, int op)
+static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args)
{
struct bpf_sock_ops_kern sock_ops;
int ret;
- memset(&sock_ops, 0, sizeof(sock_ops));
+ memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
if (sk_fullsock(sk)) {
sock_ops.is_fullsock = 1;
sock_owned_by_me(sk);
@@ -2019,6 +2019,8 @@ static inline int tcp_call_bpf(struct sock *sk, int op)
sock_ops.sk = sk;
sock_ops.op = op;
+ if (nargs > 0)
+ memcpy(sock_ops.args, args, nargs * sizeof(*args));
ret = BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops);
if (ret == 0)
@@ -2027,18 +2029,46 @@ static inline int tcp_call_bpf(struct sock *sk, int op)
ret = -1;
return ret;
}
+
+static inline int tcp_call_bpf_2arg(struct sock *sk, int op, u32 arg1, u32 arg2)
+{
+ u32 args[2] = {arg1, arg2};
+
+ return tcp_call_bpf(sk, op, 2, args);
+}
+
+static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2,
+ u32 arg3)
+{
+ u32 args[3] = {arg1, arg2, arg3};
+
+ return tcp_call_bpf(sk, op, 3, args);
+}
+
#else
-static inline int tcp_call_bpf(struct sock *sk, int op)
+static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args)
{
return -EPERM;
}
+
+static inline int tcp_call_bpf_2arg(struct sock *sk, int op, u32 arg1, u32 arg2)
+{
+ return -EPERM;
+}
+
+static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2,
+ u32 arg3)
+{
+ return -EPERM;
+}
+
#endif
static inline u32 tcp_timeout_init(struct sock *sk)
{
int timeout;
- timeout = tcp_call_bpf(sk, BPF_SOCK_OPS_TIMEOUT_INIT);
+ timeout = tcp_call_bpf(sk, BPF_SOCK_OPS_TIMEOUT_INIT, 0, NULL);
if (timeout <= 0)
timeout = TCP_TIMEOUT_INIT;
@@ -2049,7 +2079,7 @@ static inline u32 tcp_rwnd_init_bpf(struct sock *sk)
{
int rwnd;
- rwnd = tcp_call_bpf(sk, BPF_SOCK_OPS_RWND_INIT);
+ rwnd = tcp_call_bpf(sk, BPF_SOCK_OPS_RWND_INIT, 0, NULL);
if (rwnd < 0)
rwnd = 0;
@@ -2058,7 +2088,7 @@ static inline u32 tcp_rwnd_init_bpf(struct sock *sk)
static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk)
{
- return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN) == 1);
+ return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN, 0, NULL) == 1);
}
#if IS_ENABLED(CONFIG_SMC)