From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Tue, 17 Apr 2018 16:46:37 +0200
Subject: xdp: transition into using xdp_frame for ndo_xdp_xmit
Patch-mainline: v4.18-rc1
Git-commit: 44fa2dbd475996ddc8f3a0e6113dee983e0ee3aa
References: bsc#1109837 bsc#1111981 FATE#326312 FATE#326313 bsc#1113994 FATE#326315 FATE#326317
Changing API ndo_xdp_xmit to take a struct xdp_frame instead of struct
xdp_buff. This brings xdp_return_frame and ndp_xdp_xmit in sync.
This builds towards changing the API further to become a bulk API,
because xdp_buff is not a queue-able object while xdp_frame is.
V4: Adjust for commit 59655a5b6c83 ("tuntap: XDP_TX can use native XDP")
V7: Adjust for commit d9314c474d4f ("i40e: add support for XDP_REDIRECT")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
drivers/net/ethernet/intel/i40e/i40e_txrx.c | 30 ++++++++++++++------------
drivers/net/ethernet/intel/i40e/i40e_txrx.h | 2 -
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 24 +++++++++++---------
drivers/net/tun.c | 19 ++++++++++------
drivers/net/virtio_net.c | 24 ++++++++++++--------
include/linux/netdevice.h | 4 +--
net/core/filter.c | 17 +++++++++++++-
7 files changed, 74 insertions(+), 46 deletions(-)
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2202,9 +2202,20 @@ static bool i40e_is_non_eop(struct i40e_
#define I40E_XDP_CONSUMED 1
#define I40E_XDP_TX 2
-static int i40e_xmit_xdp_ring(struct xdp_buff *xdp,
+static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf,
struct i40e_ring *xdp_ring);
+static int i40e_xmit_xdp_tx_ring(struct xdp_buff *xdp,
+ struct i40e_ring *xdp_ring)
+{
+ struct xdp_frame *xdpf = convert_to_xdp_frame(xdp);
+
+ if (unlikely(!xdpf))
+ return I40E_XDP_CONSUMED;
+
+ return i40e_xmit_xdp_ring(xdpf, xdp_ring);
+}
+
/**
* i40e_run_xdp - run an XDP program
* @rx_ring: Rx ring being processed
@@ -2232,7 +2243,7 @@ static struct sk_buff *i40e_run_xdp(stru
break;
case XDP_TX:
xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index];
- result = i40e_xmit_xdp_ring(xdp, xdp_ring);
+ result = i40e_xmit_xdp_tx_ring(xdp, xdp_ring);
break;
case XDP_REDIRECT:
err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
@@ -3479,21 +3490,14 @@ dma_error:
* @xdp: data to transmit
* @xdp_ring: XDP Tx ring
**/
-static int i40e_xmit_xdp_ring(struct xdp_buff *xdp,
+static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf,
struct i40e_ring *xdp_ring)
{
u16 i = xdp_ring->next_to_use;
struct i40e_tx_buffer *tx_bi;
struct i40e_tx_desc *tx_desc;
- struct xdp_frame *xdpf;
+ u32 size = xdpf->len;
dma_addr_t dma;
- u32 size;
-
- xdpf = convert_to_xdp_frame(xdp);
- if (unlikely(!xdpf))
- return I40E_XDP_CONSUMED;
-
- size = xdpf->len;
if (!unlikely(I40E_DESC_UNUSED(xdp_ring))) {
xdp_ring->tx_stats.tx_busy++;
@@ -3683,7 +3687,7 @@ netdev_tx_t i40e_lan_xmit_frame(struct s
*
* Returns Zero if sent, else an error code
**/
-int i40e_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp)
+int i40e_xdp_xmit(struct net_device *dev, struct xdp_frame *xdpf)
{
struct i40e_netdev_priv *np = netdev_priv(dev);
unsigned int queue_index = smp_processor_id();
@@ -3696,7 +3700,7 @@ int i40e_xdp_xmit(struct net_device *dev
if (!i40e_enabled_xdp_vsi(vsi) || queue_index >= vsi->num_queue_pairs)
return -ENXIO;
- err = i40e_xmit_xdp_ring(xdp, vsi->xdp_rings[queue_index]);
+ err = i40e_xmit_xdp_ring(xdpf, vsi->xdp_rings[queue_index]);
if (err != I40E_XDP_TX)
return -ENOSPC;
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -510,7 +510,7 @@ u32 i40e_get_tx_pending(struct i40e_ring
void i40e_detect_recover_hung(struct i40e_vsi *vsi);
int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size);
bool __i40e_chk_linearize(struct sk_buff *skb);
-int i40e_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp);
+int i40e_xdp_xmit(struct net_device *dev, struct xdp_frame *xdpf);
void i40e_xdp_flush(struct net_device *dev);
/**
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2262,7 +2262,7 @@ static struct sk_buff *ixgbe_build_skb(s
#define IXGBE_XDP_TX 2
static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
- struct xdp_buff *xdp);
+ struct xdp_frame *xdpf);
static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
struct ixgbe_ring *rx_ring,
@@ -2270,6 +2270,7 @@ static struct sk_buff *ixgbe_run_xdp(str
{
int err, result = IXGBE_XDP_PASS;
struct bpf_prog *xdp_prog;
+ struct xdp_frame *xdpf;
u32 act;
rcu_read_lock();
@@ -2278,12 +2279,19 @@ static struct sk_buff *ixgbe_run_xdp(str
if (!xdp_prog)
goto xdp_out;
+ prefetchw(xdp->data_hard_start); /* xdp_frame write */
+
act = bpf_prog_run_xdp(xdp_prog, xdp);
switch (act) {
case XDP_PASS:
break;
case XDP_TX:
- result = ixgbe_xmit_xdp_ring(adapter, xdp);
+ xdpf = convert_to_xdp_frame(xdp);
+ if (unlikely(!xdpf)) {
+ result = IXGBE_XDP_CONSUMED;
+ break;
+ }
+ result = ixgbe_xmit_xdp_ring(adapter, xdpf);
break;
case XDP_REDIRECT:
err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog);
@@ -2386,7 +2394,6 @@ static int ixgbe_clean_rx_irq(struct ixg
xdp.data_hard_start = xdp.data -
ixgbe_rx_offset(rx_ring);
xdp.data_end = xdp.data + size;
- prefetchw(xdp.data_hard_start); /* xdp_frame write */
skb = ixgbe_run_xdp(adapter, rx_ring, &xdp);
}
@@ -8344,20 +8351,15 @@ static u16 ixgbe_select_queue(struct net
}
static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
- struct xdp_buff *xdp)
+ struct xdp_frame *xdpf)
{
struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()];
struct ixgbe_tx_buffer *tx_buffer;
union ixgbe_adv_tx_desc *tx_desc;
- struct xdp_frame *xdpf;
u32 len, cmd_type;
dma_addr_t dma;
u16 i;
- xdpf = convert_to_xdp_frame(xdp);
- if (unlikely(!xdpf))
- return -EOVERFLOW;
-
len = xdpf->len;
if (unlikely(!ixgbe_desc_unused(ring)))
@@ -10009,7 +10011,7 @@ static int ixgbe_xdp(struct net_device *
}
}
-static int ixgbe_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp)
+static int ixgbe_xdp_xmit(struct net_device *dev, struct xdp_frame *xdpf)
{
struct ixgbe_adapter *adapter = netdev_priv(dev);
struct ixgbe_ring *ring;
@@ -10025,7 +10027,7 @@ static int ixgbe_xdp_xmit(struct net_dev
if (unlikely(!ring))
return -ENXIO;
- err = ixgbe_xmit_xdp_ring(adapter, xdp);
+ err = ixgbe_xmit_xdp_ring(adapter, xdpf);
if (err != IXGBE_XDP_TX)
return -ENOSPC;
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1289,18 +1289,13 @@ static const struct net_device_ops tun_n
.ndo_get_stats64 = tun_net_get_stats64,
};
-static int tun_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp)
+static int tun_xdp_xmit(struct net_device *dev, struct xdp_frame *frame)
{
struct tun_struct *tun = netdev_priv(dev);
- struct xdp_frame *frame;
struct tun_file *tfile;
u32 numqueues;
int ret = 0;
- frame = convert_to_xdp_frame(xdp);
- if (unlikely(!frame))
- return -EOVERFLOW;
-
rcu_read_lock();
numqueues = READ_ONCE(tun->numqueues);
@@ -1324,6 +1319,16 @@ out:
return ret;
}
+static int tun_xdp_tx(struct net_device *dev, struct xdp_buff *xdp)
+{
+ struct xdp_frame *frame = convert_to_xdp_frame(xdp);
+
+ if (unlikely(!frame))
+ return -EOVERFLOW;
+
+ return tun_xdp_xmit(dev, frame);
+}
+
static void tun_xdp_flush(struct net_device *dev)
{
struct tun_struct *tun = netdev_priv(dev);
@@ -1680,7 +1685,7 @@ static struct sk_buff *tun_build_skb(str
case XDP_TX:
get_page(alloc_frag->page);
alloc_frag->offset += buflen;
- if (tun_xdp_xmit(tun->dev, &xdp))
+ if (tun_xdp_tx(tun->dev, &xdp))
goto err_redirect;
tun_xdp_flush(tun->dev);
rcu_read_unlock();
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -420,10 +420,10 @@ static void virtnet_xdp_flush(struct net
}
static int __virtnet_xdp_xmit(struct virtnet_info *vi,
- struct xdp_buff *xdp)
+ struct xdp_frame *xdpf)
{
struct virtio_net_hdr_mrg_rxbuf *hdr;
- struct xdp_frame *xdpf, *xdpf_sent;
+ struct xdp_frame *xdpf_sent;
struct send_queue *sq;
unsigned int len;
unsigned int qp;
@@ -436,10 +436,6 @@ static int __virtnet_xdp_xmit(struct vir
while ((xdpf_sent = virtqueue_get_buf(sq->vq, &len)) != NULL)
xdp_return_frame(xdpf_sent);
- xdpf = convert_to_xdp_frame(xdp);
- if (unlikely(!xdpf))
- return -EOVERFLOW;
-
/* virtqueue want to use data area in-front of packet */
if (unlikely(xdpf->metasize > 0))
return -EOPNOTSUPP;
@@ -463,7 +459,7 @@ static int __virtnet_xdp_xmit(struct vir
return 0;
}
-static int virtnet_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp)
+static int virtnet_xdp_xmit(struct net_device *dev, struct xdp_frame *xdpf)
{
struct virtnet_info *vi = netdev_priv(dev);
struct receive_queue *rq = vi->rq;
@@ -476,7 +472,7 @@ static int virtnet_xdp_xmit(struct net_d
if (!xdp_prog)
return -ENXIO;
- return __virtnet_xdp_xmit(vi, xdp);
+ return __virtnet_xdp_xmit(vi, xdpf);
}
static unsigned int virtnet_get_headroom(struct virtnet_info *vi)
@@ -573,6 +569,7 @@ static struct sk_buff *receive_small(str
xdp_prog = rcu_dereference(rq->xdp_prog);
if (xdp_prog) {
struct virtio_net_hdr_mrg_rxbuf *hdr = buf + header_offset;
+ struct xdp_frame *xdpf;
struct xdp_buff xdp;
void *orig_data;
u32 act;
@@ -615,7 +612,10 @@ static struct sk_buff *receive_small(str
delta = orig_data - xdp.data;
break;
case XDP_TX:
- err = __virtnet_xdp_xmit(vi, &xdp);
+ xdpf = convert_to_xdp_frame(&xdp);
+ if (unlikely(!xdpf))
+ goto err_xdp;
+ err = __virtnet_xdp_xmit(vi, xdpf);
if (unlikely(err)) {
trace_xdp_exception(vi->dev, xdp_prog, act);
goto err_xdp;
@@ -706,6 +706,7 @@ static struct sk_buff *receive_mergeable
rcu_read_lock();
xdp_prog = rcu_dereference(rq->xdp_prog);
if (xdp_prog) {
+ struct xdp_frame *xdpf;
struct page *xdp_page;
struct xdp_buff xdp;
void *data;
@@ -769,7 +770,10 @@ static struct sk_buff *receive_mergeable
}
break;
case XDP_TX:
- err = __virtnet_xdp_xmit(vi, &xdp);
+ xdpf = convert_to_xdp_frame(&xdp);
+ if (unlikely(!xdpf))
+ goto err_xdp;
+ err = __virtnet_xdp_xmit(vi, xdpf);
if (unlikely(err)) {
trace_xdp_exception(vi->dev, xdp_prog, act);
if (unlikely(xdp_page != page))
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1150,7 +1150,7 @@ struct xfrmdev_ops {
* This function is used to set or query state related to XDP on the
* netdevice and manage BPF offload. See definition of
* enum bpf_netdev_command for details.
- * int (*ndo_xdp_xmit)(struct net_device *dev, struct xdp_buff *xdp);
+ * int (*ndo_xdp_xmit)(struct net_device *dev, struct xdp_frame *xdp);
* This function is used to submit a XDP packet for transmit on a
* netdevice.
* void (*ndo_xdp_flush)(struct net_device *dev);
@@ -1341,7 +1341,7 @@ struct net_device_ops {
int (*ndo_bpf)(struct net_device *dev,
struct netdev_bpf *bpf);
int (*ndo_xdp_xmit)(struct net_device *dev,
- struct xdp_buff *xdp);
+ struct xdp_frame *xdp);
void (*ndo_xdp_flush)(struct net_device *dev);
};
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2743,13 +2743,18 @@ static int __bpf_tx_xdp(struct net_devic
struct xdp_buff *xdp,
u32 index)
{
+ struct xdp_frame *xdpf;
int err;
if (!dev->netdev_ops->ndo_xdp_xmit) {
return -EOPNOTSUPP;
}
- err = dev->netdev_ops->ndo_xdp_xmit(dev, xdp);
+ xdpf = convert_to_xdp_frame(xdp);
+ if (unlikely(!xdpf))
+ return -EOVERFLOW;
+
+ err = dev->netdev_ops->ndo_xdp_xmit(dev, xdpf);
if (err)
return err;
dev->netdev_ops->ndo_xdp_flush(dev);
@@ -2765,11 +2770,19 @@ static int __bpf_tx_xdp_map(struct net_d
if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
struct net_device *dev = fwd;
+ struct xdp_frame *xdpf;
if (!dev->netdev_ops->ndo_xdp_xmit)
return -EOPNOTSUPP;
- err = dev->netdev_ops->ndo_xdp_xmit(dev, xdp);
+ xdpf = convert_to_xdp_frame(xdp);
+ if (unlikely(!xdpf))
+ return -EOVERFLOW;
+
+ /* TODO: move to inside map code instead, for bulk support
+ * err = dev_map_enqueue(dev, xdp);
+ */
+ err = dev->netdev_ops->ndo_xdp_xmit(dev, xdpf);
if (err)
return err;
__dev_map_insert_ctx(map, index);