renegade-project/linux-next
2
0
Fork 0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-16 17:23:55 +08:00
Code

bpf: Add redirect_peer helper

Browse Source 
Add an efficient ingress to ingress netns switch that can be used out of tc BPF
programs in order to redirect traffic from host ns ingress into a container
veth device ingress without having to go via CPU backlog queue [0]. For local
containers this can also be utilized and path via CPU backlog queue only needs
to be taken once, not twice. On a high level this borrows from ipvlan which does
similar switch in __netif_receive_skb_core() and then iterates via another_round.
This helps to reduce latency for mentioned use cases.

Pod to remote pod with redirect(), TCP_RR [1]:

  # percpu_netperf 10.217.1.33
          RT_LATENCY:         122.450         (per CPU:         122.666         122.401         122.333         122.401 )
        MEAN_LATENCY:         121.210         (per CPU:         121.100         121.260         121.320         121.160 )
      STDDEV_LATENCY:         120.040         (per CPU:         119.420         119.910         125.460         115.370 )
         MIN_LATENCY:          46.500         (per CPU:          47.000          47.000          47.000          45.000 )
         P50_LATENCY:         118.500         (per CPU:         118.000         119.000         118.000         119.000 )
         P90_LATENCY:         127.500         (per CPU:         127.000         128.000         127.000         128.000 )
         P99_LATENCY:         130.750         (per CPU:         131.000         131.000         129.000         132.000 )

    TRANSACTION_RATE:       32666.400         (per CPU:        8152.200        8169.842        8174.439        8169.897 )

Pod to remote pod with redirect_peer(), TCP_RR:

  # percpu_netperf 10.217.1.33
          RT_LATENCY:          44.449         (per CPU:          43.767          43.127          45.279          45.622 )
        MEAN_LATENCY:          45.065         (per CPU:          44.030          45.530          45.190          45.510 )
      STDDEV_LATENCY:          84.823         (per CPU:          66.770          97.290          84.380          90.850 )
         MIN_LATENCY:          33.500         (per CPU:          33.000          33.000          34.000          34.000 )
         P50_LATENCY:          43.250         (per CPU:          43.000          43.000          43.000          44.000 )
         P90_LATENCY:          46.750         (per CPU:          46.000          47.000          47.000          47.000 )
         P99_LATENCY:          52.750         (per CPU:          51.000          54.000          53.000          53.000 )

    TRANSACTION_RATE:       90039.500         (per CPU:       22848.186       23187.089       22085.077       21919.130 )

  [0] https://linuxplumbersconf.org/event/7/contributions/674/attachments/568/1002/plumbers_2020_cilium_load_balancer.pdf
  [1] https://github.com/borkmann/netperf_scripts/blob/master/percpu_netperf

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20201010234006.7075-3-daniel@iogearbox.net
This commit is contained in:
Daniel Borkmann 2020-10-11 01:40:02 +02:00 committed by Alexei Starovoitov
parent dd2ce6a537
commit 9aa1206e8f
6 changed files with 106 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
drivers/net/veth.c
View File

@ -420,6 +420,14 @@ static int veth_select_rxq(struct net_device *dev)
return smp_processor_id() % dev->real_num_rx_queues;
}
static struct net_device *veth_peer_dev(struct net_device *dev)
{
struct veth_priv *priv = netdev_priv(dev);
/* Callers must be under RCU read side. */
return rcu_dereference(priv->peer);
}
static int veth_xdp_xmit(struct net_device *dev, int n,
struct xdp_frame **frames,
u32 flags, bool ndo_xmit)
@ -1224,6 +1232,7 @@ static const struct net_device_ops veth_netdev_ops = {
.ndo_set_rx_headroom = veth_set_rx_headroom,
.ndo_bpf = veth_xdp,
.ndo_xdp_xmit = veth_ndo_xdp_xmit,
.ndo_get_peer_dev = veth_peer_dev,
};
#define VETH_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | \

4
include/linux/netdevice.h
View File

@ -1277,6 +1277,9 @@ struct netdev_net_notifier {
* int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p,
* int cmd);
* Add, change, delete or get information on an IPv4 tunnel.
* struct net_device *(*ndo_get_peer_dev)(struct net_device *dev);
* If a device is paired with a peer device, return the peer instance.
* The caller must be under RCU read context.
*/
struct net_device_ops {
int (*ndo_init)(struct net_device *dev);
@ -1484,6 +1487,7 @@ struct net_device_ops {
struct devlink_port * (*ndo_get_devlink_port)(struct net_device *dev);
int (*ndo_tunnel_ctl)(struct net_device *dev,
struct ip_tunnel_parm *p, int cmd);
struct net_device * (*ndo_get_peer_dev)(struct net_device *dev);
};
/**

17
include/uapi/linux/bpf.h
View File

@ -3719,6 +3719,22 @@ union bpf_attr {
* never return NULL.
* Return
* A pointer pointing to the kernel percpu variable on this cpu.
*
* long bpf_redirect_peer(u32 ifindex, u64 flags)
* Description
* Redirect the packet to another net device of index *ifindex*.
* This helper is somewhat similar to **bpf_redirect**\ (), except
* that the redirection happens to the *ifindex*' peer device and
* the netns switch takes place from ingress to ingress without
* going through the CPU's backlog queue.
*
* The *flags* argument is reserved and must be 0. The helper is
* currently only supported for tc BPF program types at the ingress
* hook and for veth device types. The peer device must reside in a
* different network namespace.
* Return
* The helper returns **TC_ACT_REDIRECT** on success or
* **TC_ACT_SHOT** on error.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@ -3876,6 +3892,7 @@ union bpf_attr {
FN(redirect_neigh), \
FN(bpf_per_cpu_ptr), \
FN(bpf_this_cpu_ptr), \
FN(redirect_peer), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper

15
net/core/dev.c
View File

@ -4930,7 +4930,7 @@ EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook);
static inline struct sk_buff *
sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
struct net_device *orig_dev)
struct net_device *orig_dev, bool *another)
{
#ifdef CONFIG_NET_CLS_ACT
struct mini_Qdisc *miniq = rcu_dereference_bh(skb->dev->miniq_ingress);
@ -4974,7 +4974,11 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
* redirecting to another netdev
*/
__skb_push(skb, skb->mac_len);
skb_do_redirect(skb);
if (skb_do_redirect(skb) == -EAGAIN) {
__skb_pull(skb, skb->mac_len);
*another = true;
break;
}
return NULL;
case TC_ACT_CONSUMED:
return NULL;
@ -5163,7 +5167,12 @@ another_round:
skip_taps:
#ifdef CONFIG_NET_INGRESS
if (static_branch_unlikely(&ingress_needed_key)) {
skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev);
bool another = false;
skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev,
&another);
if (another)
goto another_round;
if (!skb)
goto out;

52
net/core/filter.c
View File

@ -2381,7 +2381,8 @@ out:
/* Internal, non-exposed redirect flags. */
enum {
BPF_F_NEIGH = (1ULL << 1),
#define BPF_F_REDIRECT_INTERNAL (BPF_F_NEIGH)
BPF_F_PEER = (1ULL << 2),
#define BPF_F_REDIRECT_INTERNAL (BPF_F_NEIGH | BPF_F_PEER)
};
BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags)
@ -2430,19 +2431,35 @@ EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info);
int skb_do_redirect(struct sk_buff *skb)
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
struct net *net = dev_net(skb->dev);
struct net_device *dev;
u32 flags = ri->flags;
dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->tgt_index);
dev = dev_get_by_index_rcu(net, ri->tgt_index);
ri->tgt_index = 0;
if (unlikely(!dev)) {
kfree_skb(skb);
return -EINVAL;
}
ri->flags = 0;
if (unlikely(!dev))
goto out_drop;
if (flags & BPF_F_PEER) {
const struct net_device_ops *ops = dev->netdev_ops;
if (unlikely(!ops->ndo_get_peer_dev ||
!skb_at_tc_ingress(skb)))
goto out_drop;
dev = ops->ndo_get_peer_dev(dev);
if (unlikely(!dev ||
!is_skb_forwardable(dev, skb) ||
net_eq(net, dev_net(dev))))
goto out_drop;
skb->dev = dev;
return -EAGAIN;
}
return flags & BPF_F_NEIGH ?
__bpf_redirect_neigh(skb, dev) :
__bpf_redirect(skb, dev, flags);
out_drop:
kfree_skb(skb);
return -EINVAL;
}
BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags)
@ -2466,6 +2483,27 @@ static const struct bpf_func_proto bpf_redirect_proto = {
.arg2_type = ARG_ANYTHING,
};
BPF_CALL_2(bpf_redirect_peer, u32, ifindex, u64, flags)
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
if (unlikely(flags))
return TC_ACT_SHOT;
ri->flags = BPF_F_PEER;
ri->tgt_index = ifindex;
return TC_ACT_REDIRECT;
}
static const struct bpf_func_proto bpf_redirect_peer_proto = {
.func = bpf_redirect_peer,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_ANYTHING,
.arg2_type = ARG_ANYTHING,
};
BPF_CALL_2(bpf_redirect_neigh, u32, ifindex, u64, flags)
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
@ -7053,6 +7091,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_redirect_proto;
case BPF_FUNC_redirect_neigh:
return &bpf_redirect_neigh_proto;
case BPF_FUNC_redirect_peer:
return &bpf_redirect_peer_proto;
case BPF_FUNC_get_route_realm:
return &bpf_get_route_realm_proto;
case BPF_FUNC_get_hash_recalc:

17
tools/include/uapi/linux/bpf.h
View File

@ -3719,6 +3719,22 @@ union bpf_attr {
* never return NULL.
* Return
* A pointer pointing to the kernel percpu variable on this cpu.
*
* long bpf_redirect_peer(u32 ifindex, u64 flags)
* Description
* Redirect the packet to another net device of index *ifindex*.
* This helper is somewhat similar to **bpf_redirect**\ (), except
* that the redirection happens to the *ifindex*' peer device and
* the netns switch takes place from ingress to ingress without
* going through the CPU's backlog queue.
*
* The *flags* argument is reserved and must be 0. The helper is
* currently only supported for tc BPF program types at the ingress
* hook and for veth device types. The peer device must reside in a
* different network namespace.
* Return
* The helper returns **TC_ACT_REDIRECT** on success or
* **TC_ACT_SHOT** on error.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@ -3876,6 +3892,7 @@ union bpf_attr {
FN(redirect_neigh), \
FN(bpf_per_cpu_ptr), \
FN(bpf_this_cpu_ptr), \
FN(redirect_peer), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper