netdev - [PATCH RFC 3/4] net: tun: track dropped skb via kfree_skb

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: <20220203153731.8992-4-dongli.zhang@oracle.com>
Date:   Thu,  3 Feb 2022 07:37:30 -0800
From:   Dongli Zhang <dongli.zhang@...cle.com>
To:     netdev@...r.kernel.org, bpf@...r.kernel.org
Cc:     linux-kernel@...r.kernel.org, rostedt@...dmis.org,
        mingo@...hat.com, davem@...emloft.net, kuba@...nel.org,
        edumazet@...gle.com, yoshfuji@...ux-ipv6.org, dsahern@...nel.org,
        ast@...nel.org, daniel@...earbox.net, andrii@...nel.org,
        imagedong@...cent.com, joao.m.martins@...cle.com,
        joe.jin@...cle.com
Subject: [PATCH RFC 3/4] net: tun: track dropped skb via kfree_skb_reason()

The TUN can be used as vhost-net backend. E.g, the tun_net_xmit() is the
interface to forward the skb from TUN to vhost-net/virtio-net.

However, there are many "goto drop" in the TUN driver. Therefore, the
kfree_skb_reason() is involved at each "goto drop" to help userspace
ftrace/ebpf to track the reason for the loss of packets.

Cc: Joao Martins <joao.m.martins@...cle.com>
Cc: Joe Jin <joe.jin@...cle.com>
Signed-off-by: Dongli Zhang <dongli.zhang@...cle.com>
---
 drivers/net/tun.c | 33 +++++++++++++++++++++++++--------
 1 file changed, 25 insertions(+), 8 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index fed85447701a..8f6c6d23a787 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1062,13 +1062,16 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct netdev_queue *queue;
 	struct tun_file *tfile;
 	int len = skb->len;
+	unsigned int drop_line = SKB_DROP_LINE_NONE;
 
 	rcu_read_lock();
 	tfile = rcu_dereference(tun->tfiles[txq]);
 
 	/* Drop packet if interface is not attached */
-	if (!tfile)
+	if (!tfile) {
+		drop_line = SKB_DROP_LINE;
 		goto drop;
+	}
 
 	if (!rcu_dereference(tun->steering_prog))
 		tun_automq_xmit(tun, skb);
@@ -1078,19 +1081,27 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* Drop if the filter does not like it.
 	 * This is a noop if the filter is disabled.
 	 * Filter can be enabled only for the TAP devices. */
-	if (!check_filter(&tun->txflt, skb))
+	if (!check_filter(&tun->txflt, skb)) {
+		drop_line = SKB_DROP_LINE;
 		goto drop;
+	}
 
 	if (tfile->socket.sk->sk_filter &&
-	    sk_filter(tfile->socket.sk, skb))
+	    sk_filter(tfile->socket.sk, skb)) {
+		drop_line = SKB_DROP_LINE;
 		goto drop;
+	}
 
 	len = run_ebpf_filter(tun, skb, len);
-	if (len == 0 || pskb_trim(skb, len))
+	if (len == 0 || pskb_trim(skb, len)) {
+		drop_line = SKB_DROP_LINE;
 		goto drop;
+	}
 
-	if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC)))
+	if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) {
+		drop_line = SKB_DROP_LINE;
 		goto drop;
+	}
 
 	skb_tx_timestamp(skb);
 
@@ -1101,8 +1112,10 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	nf_reset_ct(skb);
 
-	if (ptr_ring_produce(&tfile->tx_ring, skb))
+	if (ptr_ring_produce(&tfile->tx_ring, skb)) {
+		drop_line = SKB_DROP_LINE;
 		goto drop;
+	}
 
 	/* NETIF_F_LLTX requires to do our own update of trans_start */
 	queue = netdev_get_tx_queue(dev, txq);
@@ -1119,7 +1132,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 drop:
 	atomic_long_inc(&dev->tx_dropped);
 	skb_tx_error(skb);
-	kfree_skb(skb);
+	kfree_skb_reason(skb, SKB_DROP_FUNC, drop_line);
 	rcu_read_unlock();
 	return NET_XMIT_DROP;
 }
@@ -1717,6 +1730,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	u32 rxhash = 0;
 	int skb_xdp = 1;
 	bool frags = tun_napi_frags_enabled(tfile);
+	unsigned int drop_line = SKB_DROP_LINE_NONE;
 
 	if (!(tun->flags & IFF_NO_PI)) {
 		if (len < sizeof(pi))
@@ -1820,9 +1834,10 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 
 		if (err) {
 			err = -EFAULT;
+			drop_line = SKB_DROP_LINE;
 drop:
 			atomic_long_inc(&tun->dev->rx_dropped);
-			kfree_skb(skb);
+			kfree_skb_reason(skb, SKB_DROP_FUNC, drop_line);
 			if (frags) {
 				tfile->napi.skb = NULL;
 				mutex_unlock(&tfile->napi_mutex);
@@ -1868,6 +1883,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		break;
 	case IFF_TAP:
 		if (frags && !pskb_may_pull(skb, ETH_HLEN)) {
+			drop_line = SKB_DROP_LINE;
 			err = -ENOMEM;
 			goto drop;
 		}
@@ -1922,6 +1938,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	if (unlikely(!(tun->dev->flags & IFF_UP))) {
 		err = -EIO;
 		rcu_read_unlock();
+		drop_line = SKB_DROP_LINE;
 		goto drop;
 	}
 
-- 
2.17.1