#include <linux/if_macvlan.h>
#include <linux/if_bridge.h>
#include <linux/prefetch.h>
+#include <linux/bpf.h>
+#include <linux/bpf_trace.h>
+#include <linux/atomic.h>
#include <scsi/fc/fc_fcoe.h>
#include <net/udp_tunnel.h>
#include <net/pkt_cls.h>
* @rx_desc: pointer to the EOP Rx descriptor
* @skb: pointer to current skb being fixed
*
+ * Check if the skb is valid in the XDP case it will be an error pointer.
+ * Return true in this case to abort processing and advance to next
+ * descriptor.
+ *
* Check for corrupted packet headers caused by senders on the local L2
* embedded NIC switch not setting up their Tx Descriptors right. These
* should be very rare.
{
struct net_device *netdev = rx_ring->netdev;
+ /* XDP packets use error pointer so abort at this point */
+ if (IS_ERR(skb))
+ return true;
+
/* verify that the packet does not have any known errors */
if (unlikely(ixgbe_test_staterr(rx_desc,
IXGBE_RXDADV_ERR_FRAME_ERR_MASK) &&
/* hand second half of page back to the ring */
ixgbe_reuse_rx_page(rx_ring, rx_buffer);
} else {
- if (IXGBE_CB(skb)->dma == rx_buffer->dma) {
+ if (!IS_ERR(skb) && IXGBE_CB(skb)->dma == rx_buffer->dma) {
/* the page has been released from the ring */
IXGBE_CB(skb)->page_released = true;
} else {
static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring,
struct ixgbe_rx_buffer *rx_buffer,
- union ixgbe_adv_rx_desc *rx_desc,
- unsigned int size)
+ struct xdp_buff *xdp,
+ union ixgbe_adv_rx_desc *rx_desc)
{
- void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+ unsigned int size = xdp->data_end - xdp->data;
#if (PAGE_SIZE < 8192)
unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2;
#else
- unsigned int truesize = SKB_DATA_ALIGN(size);
+ unsigned int truesize = SKB_DATA_ALIGN(xdp->data_end -
+ xdp->data_hard_start);
#endif
struct sk_buff *skb;
/* prefetch first cache line of first page */
- prefetch(va);
+ prefetch(xdp->data);
#if L1_CACHE_BYTES < 128
- prefetch(va + L1_CACHE_BYTES);
+ prefetch(xdp->data + L1_CACHE_BYTES);
#endif
/* allocate a skb to store the frags */
IXGBE_CB(skb)->dma = rx_buffer->dma;
skb_add_rx_frag(skb, 0, rx_buffer->page,
- rx_buffer->page_offset,
+ xdp->data - page_address(rx_buffer->page),
size, truesize);
#if (PAGE_SIZE < 8192)
rx_buffer->page_offset ^= truesize;
rx_buffer->page_offset += truesize;
#endif
} else {
- memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));
+ memcpy(__skb_put(skb, size),
+ xdp->data, ALIGN(size, sizeof(long)));
rx_buffer->pagecnt_bias++;
}
static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
struct ixgbe_rx_buffer *rx_buffer,
- union ixgbe_adv_rx_desc *rx_desc,
- unsigned int size)
+ struct xdp_buff *xdp,
+ union ixgbe_adv_rx_desc *rx_desc)
{
- void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
#if (PAGE_SIZE < 8192)
unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2;
#else
unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
- SKB_DATA_ALIGN(IXGBE_SKB_PAD + size);
+ SKB_DATA_ALIGN(xdp->data_end -
+ xdp->data_hard_start);
#endif
struct sk_buff *skb;
/* prefetch first cache line of first page */
- prefetch(va);
+ prefetch(xdp->data);
#if L1_CACHE_BYTES < 128
- prefetch(va + L1_CACHE_BYTES);
+ prefetch(xdp->data + L1_CACHE_BYTES);
#endif
- /* build an skb around the page buffer */
- skb = build_skb(va - IXGBE_SKB_PAD, truesize);
+ /* build an skb to around the page buffer */
+ skb = build_skb(xdp->data_hard_start, truesize);
if (unlikely(!skb))
return NULL;
/* update pointers within the skb to store the data */
- skb_reserve(skb, IXGBE_SKB_PAD);
- __skb_put(skb, size);
+ skb_reserve(skb, xdp->data - xdp->data_hard_start);
+ __skb_put(skb, xdp->data_end - xdp->data);
/* record DMA address if this is the start of a chain of buffers */
if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP))
return skb;
}
+#define IXGBE_XDP_PASS 0
+#define IXGBE_XDP_CONSUMED 1
+
+static struct sk_buff *ixgbe_run_xdp(struct ixgbe_ring *rx_ring,
+ struct xdp_buff *xdp)
+{
+ int result = IXGBE_XDP_PASS;
+ struct bpf_prog *xdp_prog;
+ u32 act;
+
+ rcu_read_lock();
+ xdp_prog = READ_ONCE(rx_ring->xdp_prog);
+
+ if (!xdp_prog)
+ goto xdp_out;
+
+ act = bpf_prog_run_xdp(xdp_prog, xdp);
+ switch (act) {
+ case XDP_PASS:
+ break;
+ default:
+ bpf_warn_invalid_xdp_action(act);
+ case XDP_TX:
+ case XDP_ABORTED:
+ trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
+ /* fallthrough -- handle aborts by dropping packet */
+ case XDP_DROP:
+ result = IXGBE_XDP_CONSUMED;
+ break;
+ }
+xdp_out:
+ rcu_read_unlock();
+ return ERR_PTR(-result);
+}
+
/**
* ixgbe_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
* @q_vector: structure containing interrupt and ring information
union ixgbe_adv_rx_desc *rx_desc;
struct ixgbe_rx_buffer *rx_buffer;
struct sk_buff *skb;
+ struct xdp_buff xdp;
unsigned int size;
/* return some buffers to hardware, one at a time is too slow */
rx_buffer = ixgbe_get_rx_buffer(rx_ring, rx_desc, &skb, size);
/* retrieve a buffer from the ring */
- if (skb)
+ if (!skb) {
+ xdp.data = page_address(rx_buffer->page) +
+ rx_buffer->page_offset;
+ xdp.data_hard_start = xdp.data -
+ ixgbe_rx_offset(rx_ring);
+ xdp.data_end = xdp.data + size;
+
+ skb = ixgbe_run_xdp(rx_ring, &xdp);
+ }
+
+ if (IS_ERR(skb)) {
+ total_rx_packets++;
+ total_rx_bytes += size;
+ rx_buffer->pagecnt_bias++;
+ } else if (skb) {
ixgbe_add_rx_frag(rx_ring, rx_buffer, skb, size);
- else if (ring_uses_build_skb(rx_ring))
+ } else if (ring_uses_build_skb(rx_ring)) {
skb = ixgbe_build_skb(rx_ring, rx_buffer,
- rx_desc, size);
- else
+ &xdp, rx_desc);
+ } else {
skb = ixgbe_construct_skb(rx_ring, rx_buffer,
- rx_desc, size);
+ &xdp, rx_desc);
+ }
/* exit if we failed to retrieve a buffer */
if (!skb) {
*
* Returns 0 on success, negative on failure
**/
-int ixgbe_setup_rx_resources(struct ixgbe_ring *rx_ring)
+int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter,
+ struct ixgbe_ring *rx_ring)
{
struct device *dev = rx_ring->dev;
int orig_node = dev_to_node(dev);
rx_ring->next_to_clean = 0;
rx_ring->next_to_use = 0;
+ rx_ring->xdp_prog = adapter->xdp_prog;
+
return 0;
err:
vfree(rx_ring->rx_buffer_info);
int i, err = 0;
for (i = 0; i < adapter->num_rx_queues; i++) {
- err = ixgbe_setup_rx_resources(adapter->rx_ring[i]);
+ err = ixgbe_setup_rx_resources(adapter, adapter->rx_ring[i]);
if (!err)
continue;
{
ixgbe_clean_rx_ring(rx_ring);
+ rx_ring->xdp_prog = NULL;
vfree(rx_ring->rx_buffer_info);
rx_ring->rx_buffer_info = NULL;
return features;
}
+static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
+{
+ int i, frame_size = dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
+ struct ixgbe_adapter *adapter = netdev_priv(dev);
+ struct bpf_prog *old_prog;
+
+ if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
+ return -EINVAL;
+
+ if (adapter->flags & IXGBE_FLAG_DCB_ENABLED)
+ return -EINVAL;
+
+ /* verify ixgbe ring attributes are sufficient for XDP */
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ struct ixgbe_ring *ring = adapter->rx_ring[i];
+
+ if (ring_is_rsc_enabled(ring))
+ return -EINVAL;
+
+ if (frame_size > ixgbe_rx_bufsz(ring))
+ return -EINVAL;
+ }
+
+ old_prog = xchg(&adapter->xdp_prog, prog);
+ for (i = 0; i < adapter->num_rx_queues; i++)
+ xchg(&adapter->rx_ring[i]->xdp_prog, adapter->xdp_prog);
+
+ if (old_prog)
+ bpf_prog_put(old_prog);
+
+ return 0;
+}
+
+static int ixgbe_xdp(struct net_device *dev, struct netdev_xdp *xdp)
+{
+ struct ixgbe_adapter *adapter = netdev_priv(dev);
+
+ switch (xdp->command) {
+ case XDP_SETUP_PROG:
+ return ixgbe_xdp_setup(dev, xdp->prog);
+ case XDP_QUERY_PROG:
+ xdp->prog_attached = !!(adapter->xdp_prog);
+ return 0;
+ default:
+ return -EINVAL;
+ }
+}
+
static const struct net_device_ops ixgbe_netdev_ops = {
.ndo_open = ixgbe_open,
.ndo_stop = ixgbe_close,
.ndo_udp_tunnel_add = ixgbe_add_udp_tunnel_port,
.ndo_udp_tunnel_del = ixgbe_del_udp_tunnel_port,
.ndo_features_check = ixgbe_features_check,
+ .ndo_xdp = ixgbe_xdp,
};
/**