int bpf_iw(struct bpf_sock_ops *skops)
{
int bufsize = 1500000;
int rwnd_init = 40;
int iw = 40;
int rv = 0;
int op;
/* For testing purposes, only execute rest of BPF program
* if neither port numberis 55601
*/
if (bpf_ntohl(skops->remote_port) != 55601 &&
skops->local_port != 55601) {
skops->reply = -1;
return 1;
}
op = (int) skops->op;
#ifdef DEBUG
bpf_printk("BPF command: %d\n", op);
#endif
/* Usually there would be a check to insure the hosts are far
* from each other so it makes sense to increase buffer sizes
*/
switch (op) {
case BPF_SOCK_OPS_RWND_INIT:
rv = rwnd_init;
break;
case BPF_SOCK_OPS_TCP_CONNECT_CB:
/* Set sndbuf and rcvbuf of active connections */
rv = bpf_setsockopt(skops, SOL_SOCKET, SO_SNDBUF, &bufsize,
sizeof(bufsize));
rv += bpf_setsockopt(skops, SOL_SOCKET, SO_RCVBUF,
&bufsize, sizeof(bufsize));
break;
case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
rv = bpf_setsockopt(skops, SOL_TCP, TCP_BPF_IW, &iw,
sizeof(iw));
break;
case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
/* Set sndbuf and rcvbuf of passive connections */
rv = bpf_setsockopt(skops, SOL_SOCKET, SO_SNDBUF, &bufsize,
sizeof(bufsize));
rv += bpf_setsockopt(skops, SOL_SOCKET, SO_RCVBUF,
&bufsize, sizeof(bufsize));
break;
default:
rv = -1;
}
#ifdef DEBUG
bpf_printk("Returning %d\n", rv);
#endif
skops->reply = rv;
return 1;
}
int bpf_prog2(struct __sk_buff *skb)
{
void *data_end = (void *)(long) skb->data_end;
void *data = (void *)(long) skb->data;
__u32 lport = skb->local_port;
__u32 rport = skb->remote_port;
__u8 *d = data;
__u8 sk, map;
if (data + 8 > data_end)
return SK_DROP;
map = d[0];
sk = d[1];
d[0] = 0xd;
d[1] = 0xe;
d[2] = 0xa;
d[3] = 0xd;
d[4] = 0xb;
d[5] = 0xe;
d[6] = 0xe;
d[7] = 0xf;
bpf_printk("verdict: data[0] = redir(%u:%u)\n", map, sk);
if (!map)
return bpf_sk_redirect_map(skb, &sock_map_rx, sk, 0);
return bpf_sk_redirect_map(skb, &sock_map_tx, sk, 0);
}
int bpf_sockmap(struct bpf_sock_ops *skops)
{
__u32 lport, rport;
int op, err = 0, index, key, ret;
op = (int) skops->op;
switch (op) {
case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
lport = skops->local_port;
rport = skops->remote_port;
if (lport == 10000) {
ret = 1;
err = bpf_sock_map_update(skops, &sock_map, &ret,
BPF_NOEXIST);
bpf_printk("passive(%i -> %i) map ctx update err: %d\n",
lport, bpf_ntohl(rport), err);
}
break;
case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
lport = skops->local_port;
rport = skops->remote_port;
if (bpf_ntohl(rport) == 10001) {
ret = 10;
err = bpf_sock_map_update(skops, &sock_map, &ret,
BPF_NOEXIST);
bpf_printk("active(%i -> %i) map ctx update err: %d\n",
lport, bpf_ntohl(rport), err);
}
break;
default:
break;
}
return 0;
}
int bpf_synrto(struct bpf_sock_ops *skops)
{
int rv = -1;
int op;
/* For testing purposes, only execute rest of BPF program
* if neither port numberis 55601
*/
if (bpf_ntohl(skops->remote_port) != 55601 &&
skops->local_port != 55601) {
skops->reply = -1;
return 1;
}
op = (int) skops->op;
#ifdef DEBUG
bpf_printk("BPF command: %d\n", op);
#endif
/* Check for TIMEOUT_INIT operation and IPv6 addresses */
if (op == BPF_SOCK_OPS_TIMEOUT_INIT &&
skops->family == AF_INET6) {
/* If the first 5.5 bytes of the IPv6 address are the same
* then both hosts are in the same datacenter
* so use an RTO of 10ms
*/
if (skops->local_ip6[0] == skops->remote_ip6[0] &&
(bpf_ntohl(skops->local_ip6[1]) & 0xfff00000) ==
(bpf_ntohl(skops->remote_ip6[1]) & 0xfff00000))
rv = 10;
}
#ifdef DEBUG
bpf_printk("Returning %d\n", rv);
#endif
skops->reply = rv;
return 1;
}
int bpf_prog2(struct __sk_buff *skb)
{
__u32 lport = skb->local_port;
__u32 rport = skb->remote_port;
int ret = 0;
if (lport == 10000)
ret = 10;
else
ret = 1;
bpf_printk("sockmap: %d -> %d @ %d\n", lport, bpf_ntohl(rport), ret);
return bpf_sk_redirect_map(&sock_map, ret, 0);
}
int xdp_sample_prog(struct xdp_md *ctx)
{
void *data_end = (void *)(long)ctx->data_end;
void *data = (void *)(long)ctx->data;
/* Metadata will be in the perf event before the packet data. */
struct S {
u16 cookie;
u16 pkt_len;
} __packed metadata;
if (data < data_end) {
/* The XDP perf_event_output handler will use the upper 32 bits
* of the flags argument as a number of bytes to include of the
* packet payload in the event data. If the size is too big, the
* call to bpf_perf_event_output will fail and return -EFAULT.
*
* See bpf_xdp_event_output in net/core/filter.c.
*
* The BPF_F_CURRENT_CPU flag means that the event output fd
* will be indexed by the CPU number in the event map.
*/
u64 flags = BPF_F_CURRENT_CPU;
u16 sample_size;
int ret;
metadata.cookie = 0xdead;
metadata.pkt_len = (u16)(data_end - data);
sample_size = min(metadata.pkt_len, SAMPLE_SIZE);
flags |= (u64)sample_size << 32;
ret = bpf_perf_event_output(ctx, &my_map, flags,
&metadata, sizeof(metadata));
if (ret)
bpf_printk("perf_event_output failed: %d\n", ret);
}
return XDP_PASS;
}
int _hbm_out_cg(struct __sk_buff *skb)
{
struct hbm_pkt_info pkti;
int len = skb->len;
unsigned int queue_index = 0;
unsigned long long curtime;
int credit;
signed long long delta = 0, zero = 0;
int max_credit = MAX_CREDIT;
bool congestion_flag = false;
bool drop_flag = false;
bool cwr_flag = false;
struct hbm_vqueue *qdp;
struct hbm_queue_stats *qsp = NULL;
int rv = ALLOW_PKT;
qsp = bpf_map_lookup_elem(&queue_stats, &queue_index);
if (qsp != NULL && !qsp->loopback && (skb->ifindex == 1))
return ALLOW_PKT;
hbm_get_pkt_info(skb, &pkti);
// We may want to account for the length of headers in len
// calculation, like ETH header + overhead, specially if it
// is a gso packet. But I am not doing it right now.
qdp = bpf_get_local_storage(&queue_state, 0);
if (!qdp)
return ALLOW_PKT;
else if (qdp->lasttime == 0)
hbm_init_vqueue(qdp, 1024);
curtime = bpf_ktime_get_ns();
// Begin critical section
bpf_spin_lock(&qdp->lock);
credit = qdp->credit;
delta = curtime - qdp->lasttime;
/* delta < 0 implies that another process with a curtime greater
* than ours beat us to the critical section and already added
* the new credit, so we should not add it ourselves
*/
if (delta > 0) {
qdp->lasttime = curtime;
credit += CREDIT_PER_NS(delta, qdp->rate);
if (credit > MAX_CREDIT)
credit = MAX_CREDIT;
}
credit -= len;
qdp->credit = credit;
bpf_spin_unlock(&qdp->lock);
// End critical section
// Check if we should update rate
if (qsp != NULL && (qsp->rate * 128) != qdp->rate) {
qdp->rate = qsp->rate * 128;
bpf_printk("Updating rate: %d (1sec:%llu bits)\n",
(int)qdp->rate,
CREDIT_PER_NS(1000000000, qdp->rate) * 8);
}
// Set flags (drop, congestion, cwr)
// Dropping => we are congested, so ignore congestion flag
if (credit < -DROP_THRESH ||
(len > LARGE_PKT_THRESH &&
credit < -LARGE_PKT_DROP_THRESH)) {
// Very congested, set drop flag
drop_flag = true;
} else if (credit < 0) {
// Congested, set congestion flag
if (pkti.ecn) {
if (credit < -MARK_THRESH)
congestion_flag = true;
else
congestion_flag = false;
} else {
congestion_flag = true;
}
}
if (congestion_flag) {
if (!bpf_skb_ecn_set_ce(skb)) {
if (len > LARGE_PKT_THRESH) {
// Problem if too many small packets?
drop_flag = true;
}
}
}
if (drop_flag)
rv = DROP_PKT;
hbm_update_stats(qsp, len, curtime, congestion_flag, drop_flag);
if (rv == DROP_PKT)
__sync_add_and_fetch(&(qdp->credit), len);
return rv;
}