| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <152180755512.20167.3613953170696539382.stgit@firesoul>
Date: Fri, 23 Mar 2018 13:19:15 +0100
From: Jesper Dangaard Brouer <brouer@...hat.com>
To: netdev@...r.kernel.org,
BjörnTöpel <bjorn.topel@...el.com>,
magnus.karlsson@...el.com
Cc: eugenia@...lanox.com, Jason Wang <jasowang@...hat.com>,
John Fastabend <john.fastabend@...il.com>,
Eran Ben Elisha <eranbe@...lanox.com>,
Saeed Mahameed <saeedm@...lanox.com>, galp@...lanox.com,
Jesper Dangaard Brouer <brouer@...hat.com>,
Daniel Borkmann <borkmann@...earbox.net>,
Alexei Starovoitov <alexei.starovoitov@...il.com>,
Tariq Toukan <tariqt@...lanox.com>
Subject: [bpf-next V5 PATCH 15/15] xdp: transition into using xdp_frame for
ndo_xdp_xmit
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")
Signed-off-by: Jesper Dangaard Brouer <brouer@...hat.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 21 +++++++++++----------
drivers/net/tun.c | 19 ++++++++++++-------
drivers/net/virtio_net.c | 24 ++++++++++++++----------
include/linux/netdevice.h | 4 ++--
net/core/filter.c | 17 +++++++++++++++--
5 files changed, 54 insertions(+), 31 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index e6e9b28ecfba..f78096ed4c86 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2252,7 +2252,7 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
#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,
@@ -2260,6 +2260,7 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
{
int err, result = IXGBE_XDP_PASS;
struct bpf_prog *xdp_prog;
+ struct xdp_frame *xdpf;
u32 act;
rcu_read_lock();
@@ -2273,7 +2274,12 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
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);
@@ -8329,20 +8335,15 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
}
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)))
@@ -9995,7 +9996,7 @@ static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp)
}
}
-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;
@@ -10011,7 +10012,7 @@ static int ixgbe_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp)
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;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index a7e42ae1b220..da0402ebc5ce 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1293,18 +1293,13 @@ static const struct net_device_ops tun_netdev_ops = {
.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);
@@ -1328,6 +1323,16 @@ static int tun_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp)
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);
@@ -1675,7 +1680,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
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();
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 479a80339fad..906fcd9ff49b 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -416,10 +416,10 @@ static void virtnet_xdp_flush(struct net_device *dev)
}
static bool __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;
@@ -432,10 +432,6 @@ static bool __virtnet_xdp_xmit(struct virtnet_info *vi,
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;
@@ -460,7 +456,7 @@ static bool __virtnet_xdp_xmit(struct virtnet_info *vi,
return true;
}
-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;
@@ -474,7 +470,7 @@ static int virtnet_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp)
if (!xdp_prog)
return -ENXIO;
- sent = __virtnet_xdp_xmit(vi, xdp);
+ sent = __virtnet_xdp_xmit(vi, xdpf);
if (!sent)
return -ENOSPC;
return 0;
@@ -575,6 +571,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
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;
@@ -617,7 +614,10 @@ static struct sk_buff *receive_small(struct net_device *dev,
delta = orig_data - xdp.data;
break;
case XDP_TX:
- sent = __virtnet_xdp_xmit(vi, &xdp);
+ xdpf = convert_to_xdp_frame(&xdp);
+ if (unlikely(!xdpf))
+ goto err_xdp;
+ sent = __virtnet_xdp_xmit(vi, xdpf);
if (unlikely(!sent)) {
trace_xdp_exception(vi->dev, xdp_prog, act);
goto err_xdp;
@@ -709,6 +709,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
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;
@@ -773,7 +774,10 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
}
break;
case XDP_TX:
- sent = __virtnet_xdp_xmit(vi, &xdp);
+ xdpf = convert_to_xdp_frame(&xdp);
+ if (unlikely(!xdpf))
+ goto err_xdp;
+ sent = __virtnet_xdp_xmit(vi, xdpf);
if (unlikely(!sent)) {
trace_xdp_exception(vi->dev, xdp_prog, act);
if (unlikely(xdp_page != page))
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 913b1cc882cf..62d984ac6c7c 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1164,7 +1164,7 @@ struct dev_ifalias {
* 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);
@@ -1355,7 +1355,7 @@ 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);
};
diff --git a/net/core/filter.c b/net/core/filter.c
index c86f03fd9ea5..189ae8e4dda3 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2724,13 +2724,18 @@ static int __bpf_tx_xdp(struct net_device *dev,
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);
@@ -2746,11 +2751,19 @@ static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
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);
Powered by blists - more mailing lists