netdev - [PATCH v4 bpf-next 4/9] veth: Handle xdp

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20180726142557.1765-5-toshiaki.makita1@gmail.com>
Date:   Thu, 26 Jul 2018 23:25:52 +0900
From:   Toshiaki Makita <toshiaki.makita1@...il.com>
To:     netdev@...r.kernel.org, Alexei Starovoitov <ast@...nel.org>,
        Daniel Borkmann <daniel@...earbox.net>
Cc:     Toshiaki Makita <makita.toshiaki@....ntt.co.jp>,
        Jesper Dangaard Brouer <brouer@...hat.com>,
        Jakub Kicinski <jakub.kicinski@...ronome.com>,
        Toshiaki Makita <toshiaki.makita1@...il.com>
Subject: [PATCH v4 bpf-next 4/9] veth: Handle xdp_frames in xdp napi ring

From: Toshiaki Makita <makita.toshiaki@....ntt.co.jp>

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.

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: Toshiaki Makita <makita.toshiaki@....ntt.co.jp>
Signed-off-by: Toshiaki Makita <toshiaki.makita1@...il.com>
---
 drivers/net/veth.c | 87 ++++++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 82 insertions(+), 5 deletions(-)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 1b4006d3df32..ef22d991f678 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -22,12 +22,12 @@
 #include <linux/bpf.h>
 #include <linux/filter.h>
 #include <linux/ptr_ring.h>
-#include <linux/skb_array.h>
 #include <linux/bpf_trace.h>
 
 #define DRV_NAME	"veth"
 #define DRV_VERSION	"1.0"
 
+#define VETH_XDP_FLAG		BIT(0)
 #define VETH_RING_SIZE		256
 #define VETH_XDP_HEADROOM	(XDP_PACKET_HEADROOM + NET_IP_ALIGN)
 
@@ -115,6 +115,24 @@ static const struct ethtool_ops veth_ethtool_ops = {
 
 /* 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)
 {
 	/* Write ptr_ring before reading rx_notify_masked */
@@ -249,6 +267,61 @@ static struct sk_buff *veth_build_skb(void *head, int headroom, int len,
 	return skb;
 }
 
+static struct sk_buff *veth_xdp_rcv_one(struct veth_priv *priv,
+					struct xdp_frame *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 = frame->data - frame->headroom;
+		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 = frame->data - delta - (void *)frame;
+	skb = veth_build_skb(frame, headroom, len, 0);
+	if (!skb) {
+		xdp_return_frame(frame);
+		goto err;
+	}
+
+	memset(frame, 0, sizeof(*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,
 					struct sk_buff *skb)
 {
@@ -358,12 +431,16 @@ static int veth_xdp_rcv(struct veth_priv *priv, int budget)
 	int i, done = 0;
 
 	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;
 
-		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)
 			napi_gro_receive(&priv->xdp_napi, skb);
@@ -416,7 +493,7 @@ static void veth_napi_del(struct net_device *dev)
 	napi_disable(&priv->xdp_napi);
 	netif_napi_del(&priv->xdp_napi);
 	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)
-- 
2.14.3