Commit 9fc8d518 authored by Toshiaki Makita's avatar Toshiaki Makita Committed by Daniel Borkmann

veth: Handle xdp_frames in xdp napi ring

This is preparation for XDP TX and ndo_xdp_xmit.
This allows napi handler to handle xdp_frames through xdp ring as well
as sk_buff.

v8:
- Don't use xdp_frame pointer address to calculate skb->head and
  headroom.

v7:
- Use xdp_scrub_frame() instead of memset().

v3:
- Revert v2 change around rings and use a flag to differentiate skb and
  xdp_frame, since bulk skb xmit makes little performance difference
  for now.

v2:
- Use another ring instead of using flag to differentiate skb and
  xdp_frame. This approach makes bulk skb transmit possible in
  veth_xmit later.
- Clear xdp_frame feilds in skb->head.
- Implement adjust_tail.
Signed-off-by: default avatarToshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: default avatarJohn Fastabend <john.fastabend@gmail.com>
Acked-by: default avatarJesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: default avatarDaniel Borkmann <daniel@iogearbox.net>
parent a8d5b4ab
...@@ -22,12 +22,12 @@ ...@@ -22,12 +22,12 @@
#include <linux/bpf.h> #include <linux/bpf.h>
#include <linux/filter.h> #include <linux/filter.h>
#include <linux/ptr_ring.h> #include <linux/ptr_ring.h>
#include <linux/skb_array.h>
#include <linux/bpf_trace.h> #include <linux/bpf_trace.h>
#define DRV_NAME "veth" #define DRV_NAME "veth"
#define DRV_VERSION "1.0" #define DRV_VERSION "1.0"
#define VETH_XDP_FLAG BIT(0)
#define VETH_RING_SIZE 256 #define VETH_RING_SIZE 256
#define VETH_XDP_HEADROOM (XDP_PACKET_HEADROOM + NET_IP_ALIGN) #define VETH_XDP_HEADROOM (XDP_PACKET_HEADROOM + NET_IP_ALIGN)
...@@ -115,6 +115,24 @@ static const struct ethtool_ops veth_ethtool_ops = { ...@@ -115,6 +115,24 @@ static const struct ethtool_ops veth_ethtool_ops = {
/* general routines */ /* general routines */
static bool veth_is_xdp_frame(void *ptr)
{
return (unsigned long)ptr & VETH_XDP_FLAG;
}
static void *veth_ptr_to_xdp(void *ptr)
{
return (void *)((unsigned long)ptr & ~VETH_XDP_FLAG);
}
static void veth_ptr_free(void *ptr)
{
if (veth_is_xdp_frame(ptr))
xdp_return_frame(veth_ptr_to_xdp(ptr));
else
kfree_skb(ptr);
}
static void __veth_xdp_flush(struct veth_priv *priv) static void __veth_xdp_flush(struct veth_priv *priv)
{ {
/* Write ptr_ring before reading rx_notify_masked */ /* Write ptr_ring before reading rx_notify_masked */
...@@ -249,6 +267,63 @@ static struct sk_buff *veth_build_skb(void *head, int headroom, int len, ...@@ -249,6 +267,63 @@ static struct sk_buff *veth_build_skb(void *head, int headroom, int len,
return skb; return skb;
} }
static struct sk_buff *veth_xdp_rcv_one(struct veth_priv *priv,
struct xdp_frame *frame)
{
void *hard_start = frame->data - frame->headroom;
void *head = hard_start - sizeof(struct xdp_frame);
int len = frame->len, delta = 0;
struct bpf_prog *xdp_prog;
unsigned int headroom;
struct sk_buff *skb;
rcu_read_lock();
xdp_prog = rcu_dereference(priv->xdp_prog);
if (likely(xdp_prog)) {
struct xdp_buff xdp;
u32 act;
xdp.data_hard_start = hard_start;
xdp.data = frame->data;
xdp.data_end = frame->data + frame->len;
xdp.data_meta = frame->data - frame->metasize;
xdp.rxq = &priv->xdp_rxq;
act = bpf_prog_run_xdp(xdp_prog, &xdp);
switch (act) {
case XDP_PASS:
delta = frame->data - xdp.data;
len = xdp.data_end - xdp.data;
break;
default:
bpf_warn_invalid_xdp_action(act);
case XDP_ABORTED:
trace_xdp_exception(priv->dev, xdp_prog, act);
case XDP_DROP:
goto err_xdp;
}
}
rcu_read_unlock();
headroom = sizeof(struct xdp_frame) + frame->headroom - delta;
skb = veth_build_skb(head, headroom, len, 0);
if (!skb) {
xdp_return_frame(frame);
goto err;
}
xdp_scrub_frame(frame);
skb->protocol = eth_type_trans(skb, priv->dev);
err:
return skb;
err_xdp:
rcu_read_unlock();
xdp_return_frame(frame);
return NULL;
}
static struct sk_buff *veth_xdp_rcv_skb(struct veth_priv *priv, static struct sk_buff *veth_xdp_rcv_skb(struct veth_priv *priv,
struct sk_buff *skb) struct sk_buff *skb)
{ {
...@@ -359,12 +434,16 @@ static int veth_xdp_rcv(struct veth_priv *priv, int budget) ...@@ -359,12 +434,16 @@ static int veth_xdp_rcv(struct veth_priv *priv, int budget)
int i, done = 0; int i, done = 0;
for (i = 0; i < budget; i++) { for (i = 0; i < budget; i++) {
struct sk_buff *skb = __ptr_ring_consume(&priv->xdp_ring); void *ptr = __ptr_ring_consume(&priv->xdp_ring);
struct sk_buff *skb;
if (!skb) if (!ptr)
break; break;
skb = veth_xdp_rcv_skb(priv, skb); if (veth_is_xdp_frame(ptr))
skb = veth_xdp_rcv_one(priv, veth_ptr_to_xdp(ptr));
else
skb = veth_xdp_rcv_skb(priv, ptr);
if (skb) if (skb)
napi_gro_receive(&priv->xdp_napi, skb); napi_gro_receive(&priv->xdp_napi, skb);
...@@ -417,7 +496,7 @@ static void veth_napi_del(struct net_device *dev) ...@@ -417,7 +496,7 @@ static void veth_napi_del(struct net_device *dev)
napi_disable(&priv->xdp_napi); napi_disable(&priv->xdp_napi);
netif_napi_del(&priv->xdp_napi); netif_napi_del(&priv->xdp_napi);
priv->rx_notify_masked = false; priv->rx_notify_masked = false;
ptr_ring_cleanup(&priv->xdp_ring, __skb_array_destroy_skb); ptr_ring_cleanup(&priv->xdp_ring, veth_ptr_free);
} }
static int veth_enable_xdp(struct net_device *dev) static int veth_enable_xdp(struct net_device *dev)
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment