Merge branch 'sockmap-fixes'

John Fastabend says:

====================
sockmap fixes for net

The following implements a set of fixes for sockmap and changes the
API slightly in a few places to reduce preempt_disable/enable scope.
We do this here in net because it requires an API change and this
avoids getting stuck with legacy API going forward.

The short description:

Access to skb mark is removed, it is problematic when we add
features in the future because mark is a union and used by the
TCP/socket code internally. We don't want to expose this to the
BPF programs or let programs change the values.

The other change is caching metadata in the skb itself between
when the BPF program returns a redirect code and the core code
implements the redirect. This avoids having per cpu metadata.

Finally, tighten restriction on using sockmap to CAP_NET_ADMIN and
only SOCK_STREAM sockets.
====================

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

1 files changed, 16 insertions, 15 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 74b8c91fb5f4..aa0265997f93 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1839,31 +1839,31 @@ static const struct bpf_func_proto bpf_redirect_proto = {
 	.arg2_type      = ARG_ANYTHING,
 };
 
-BPF_CALL_3(bpf_sk_redirect_map, struct bpf_map *, map, u32, key, u64, flags)
+BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb,
+	   struct bpf_map *, map, u32, key, u64, flags)
 {
-	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+	struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
 
 	if (unlikely(flags))
 		return SK_ABORTED;
 
-	ri->ifindex = key;
-	ri->flags = flags;
-	ri->map = map;
+	tcb->bpf.key = key;
+	tcb->bpf.flags = flags;
+	tcb->bpf.map = map;
 
 	return SK_REDIRECT;
 }
 
-struct sock *do_sk_redirect_map(void)
+struct sock *do_sk_redirect_map(struct sk_buff *skb)
 {
-	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+	struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
 	struct sock *sk = NULL;
 
-	if (ri->map) {
-		sk = __sock_map_lookup_elem(ri->map, ri->ifindex);
+	if (tcb->bpf.map) {
+		sk = __sock_map_lookup_elem(tcb->bpf.map, tcb->bpf.key);
 
-		ri->ifindex = 0;
-		ri->map = NULL;
-		/* we do not clear flags for future lookup */
+		tcb->bpf.key = 0;
+		tcb->bpf.map = NULL;
 	}
 
 	return sk;
@@ -1873,9 +1873,10 @@ static const struct bpf_func_proto bpf_sk_redirect_map_proto = {
 	.func           = bpf_sk_redirect_map,
 	.gpl_only       = false,
 	.ret_type       = RET_INTEGER,
-	.arg1_type      = ARG_CONST_MAP_PTR,
-	.arg2_type      = ARG_ANYTHING,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_CONST_MAP_PTR,
 	.arg3_type      = ARG_ANYTHING,
+	.arg4_type      = ARG_ANYTHING,
 };
 
 BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb)
@@ -3683,7 +3684,6 @@ static bool sk_skb_is_valid_access(int off, int size,
 {
 	if (type == BPF_WRITE) {
 		switch (off) {
-		case bpf_ctx_range(struct __sk_buff, mark):
 		case bpf_ctx_range(struct __sk_buff, tc_index):
 		case bpf_ctx_range(struct __sk_buff, priority):
 			break;
@@ -3693,6 +3693,7 @@ static bool sk_skb_is_valid_access(int off, int size,
 	}
 
 	switch (off) {
+	case bpf_ctx_range(struct __sk_buff, mark):
 	case bpf_ctx_range(struct __sk_buff, tc_classid):
 		return false;
 	case bpf_ctx_range(struct __sk_buff, data):