@@ -1935,6 +1935,7 @@ struct tcp_iter_state {
struct seq_net_private p;
enum tcp_seq_states state;
struct sock *syn_wait_sk;
+ struct tcp_seq_afinfo *bpf_seq_afinfo;
int bucket, offset, sbucket, num;
loff_t last_pos;
};
@@ -2211,13 +2211,18 @@ EXPORT_SYMBOL(tcp_v4_destroy_sock);
*/
static void *listening_get_next(struct seq_file *seq, void *cur)
{
- struct tcp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file));
+ struct tcp_seq_afinfo *afinfo;
struct tcp_iter_state *st = seq->private;
struct net *net = seq_file_net(seq);
struct inet_listen_hashbucket *ilb;
struct hlist_nulls_node *node;
struct sock *sk = cur;
+ if (st->bpf_seq_afinfo)
+ afinfo = st->bpf_seq_afinfo;
+ else
+ afinfo = PDE_DATA(file_inode(seq->file));
+
if (!sk) {
get_head:
ilb = &tcp_hashinfo.listening_hash[st->bucket];
@@ -2235,7 +2240,8 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
sk_nulls_for_each_from(sk, node) {
if (!net_eq(sock_net(sk), net))
continue;
- if (sk->sk_family == afinfo->family)
+ if (afinfo->family == AF_UNSPEC ||
+ sk->sk_family == afinfo->family)
return sk;
}
spin_unlock(&ilb->lock);
@@ -2272,11 +2278,16 @@ static inline bool empty_bucket(const struct tcp_iter_state *st)
*/
static void *established_get_first(struct seq_file *seq)
{
- struct tcp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file));
+ struct tcp_seq_afinfo *afinfo;
struct tcp_iter_state *st = seq->private;
struct net *net = seq_file_net(seq);
void *rc = NULL;
+ if (st->bpf_seq_afinfo)
+ afinfo = st->bpf_seq_afinfo;
+ else
+ afinfo = PDE_DATA(file_inode(seq->file));
+
st->offset = 0;
for (; st->bucket <= tcp_hashinfo.ehash_mask; ++st->bucket) {
struct sock *sk;
@@ -2289,7 +2300,8 @@ static void *established_get_first(struct seq_file *seq)
spin_lock_bh(lock);
sk_nulls_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) {
- if (sk->sk_family != afinfo->family ||
+ if ((afinfo->family != AF_UNSPEC &&
+ sk->sk_family != afinfo->family) ||
!net_eq(sock_net(sk), net)) {
continue;
}
@@ -2304,19 +2316,25 @@ static void *established_get_first(struct seq_file *seq)
static void *established_get_next(struct seq_file *seq, void *cur)
{
- struct tcp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file));
+ struct tcp_seq_afinfo *afinfo;
struct sock *sk = cur;
struct hlist_nulls_node *node;
struct tcp_iter_state *st = seq->private;
struct net *net = seq_file_net(seq);
+ if (st->bpf_seq_afinfo)
+ afinfo = st->bpf_seq_afinfo;
+ else
+ afinfo = PDE_DATA(file_inode(seq->file));
+
++st->num;
++st->offset;
sk = sk_nulls_next(sk);
sk_nulls_for_each_from(sk, node) {
- if (sk->sk_family == afinfo->family &&
+ if ((afinfo->family == AF_UNSPEC ||
+ sk->sk_family == afinfo->family) &&
net_eq(sock_net(sk), net))
return sk;
}
A new field bpf_seq_afinfo is added to tcp_iter_state to provide bpf tcp iterator afinfo. There are two reasons on why we did this. First, the current way to get afinfo from PDE_DATA does not work for bpf iterator as its seq_file inode does not conform to /proc/net/{tcp,tcp6} inode structures. More specifically, anonymous bpf iterator will use an anonymous inode which is shared in the system and we cannot change inode private data structure at all. Second, bpf iterator for tcp/tcp6 wants to traverse all tcp and tcp6 sockets in one pass and bpf program can control whether they want to skip one sk_family or not. Having a different afinfo with family AF_UNSPEC make it easier to understand in the code. This patch does not change /proc/net/{tcp,tcp6} behavior as the bpf_seq_afinfo will be NULL for these two proc files. Acked-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Yonghong Song <yhs@fb.com> --- include/net/tcp.h | 1 + net/ipv4/tcp_ipv4.c | 30 ++++++++++++++++++++++++------ 2 files changed, 25 insertions(+), 6 deletions(-)