@@ -1058,6 +1058,7 @@ static unsigned int run_ebpf_filter(struct tun_struct *tun,
static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct tun_struct *tun = netdev_priv(dev);
+ enum skb_drop_reason drop_reason;
int txq = skb->queue_mapping;
struct netdev_queue *queue;
struct tun_file *tfile;
@@ -1067,8 +1068,10 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
tfile = rcu_dereference(tun->tfiles[txq]);
/* Drop packet if interface is not attached */
- if (!tfile)
+ if (!tfile) {
+ drop_reason = SKB_DROP_REASON_DEV_READY;
goto drop;
+ }
if (!rcu_dereference(tun->steering_prog))
tun_automq_xmit(tun, skb);
@@ -1078,22 +1081,32 @@ 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_reason = SKB_DROP_REASON_TAP_TXFILTER;
goto drop;
+ }
if (tfile->socket.sk->sk_filter &&
- sk_filter(tfile->socket.sk, skb))
+ sk_filter(tfile->socket.sk, skb)) {
+ drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
goto drop;
+ }
len = run_ebpf_filter(tun, skb, len);
- if (len == 0)
+ if (len == 0) {
+ drop_reason = SKB_DROP_REASON_TAP_FILTER;
goto drop;
+ }
- if (pskb_trim(skb, len))
+ if (pskb_trim(skb, len)) {
+ drop_reason = SKB_DROP_REASON_NOMEM;
goto drop;
+ }
- if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC)))
+ if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) {
+ drop_reason = SKB_DROP_REASON_SKB_UCOPY_FAULT;
goto drop;
+ }
skb_tx_timestamp(skb);
@@ -1104,8 +1117,10 @@ 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_reason = SKB_DROP_REASON_FULL_RING;
goto drop;
+ }
/* NETIF_F_LLTX requires to do our own update of trans_start */
queue = netdev_get_tx_queue(dev, txq);
@@ -1122,7 +1137,7 @@ 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, drop_reason);
rcu_read_unlock();
return NET_XMIT_DROP;
}
@@ -1720,6 +1735,7 @@ 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);
+ enum skb_drop_reason drop_reason;
if (!(tun->flags & IFF_NO_PI)) {
if (len < sizeof(pi))
@@ -1823,9 +1839,10 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
if (err) {
err = -EFAULT;
+ drop_reason = SKB_DROP_REASON_SKB_UCOPY_FAULT;
drop:
atomic_long_inc(&tun->dev->rx_dropped);
- kfree_skb(skb);
+ kfree_skb_reason(skb, drop_reason);
if (frags) {
tfile->napi.skb = NULL;
mutex_unlock(&tfile->napi_mutex);
@@ -1872,6 +1889,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
case IFF_TAP:
if (frags && !pskb_may_pull(skb, ETH_HLEN)) {
err = -ENOMEM;
+ drop_reason = SKB_DROP_REASON_HDR_TRUNC;
goto drop;
}
skb->protocol = eth_type_trans(skb, tun->dev);
@@ -1925,6 +1943,7 @@ 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_reason = SKB_DROP_REASON_DEV_READY;
goto drop;
}
@@ -424,7 +424,25 @@ enum skb_drop_reason {
SKB_DROP_REASON_DEV_HDR, /* device driver specific
* header/metadata is invalid
*/
+ /* the device is not ready to xmit/recv due to any of its data
+ * structure that is not up/ready/initialized, e.g., the IFF_UP is
+ * not set, or driver specific tun->tfiles[txq] is not initialized
+ */
+ SKB_DROP_REASON_DEV_READY,
SKB_DROP_REASON_FULL_RING, /* ring buffer is full */
+ SKB_DROP_REASON_NOMEM, /* error due to OOM */
+ SKB_DROP_REASON_HDR_TRUNC, /* failed to trunc/extract the header
+ * from networking data, e.g., failed
+ * to pull the protocol header from
+ * frags via pskb_may_pull()
+ */
+ SKB_DROP_REASON_TAP_FILTER, /* dropped by (ebpf) filter directly
+ * attached to tun/tap, e.g., via
+ * TUNSETFILTEREBPF
+ */
+ SKB_DROP_REASON_TAP_TXFILTER, /* dropped by tx filter implemented
+ * at tun/tap, e.g., check_filter()
+ */
SKB_DROP_REASON_MAX,
};
@@ -55,7 +55,12 @@
EM(SKB_DROP_REASON_SKB_GSO_SEG, SKB_GSO_SEG) \
EM(SKB_DROP_REASON_SKB_UCOPY_FAULT, SKB_UCOPY_FAULT) \
EM(SKB_DROP_REASON_DEV_HDR, DEV_HDR) \
+ EM(SKB_DROP_REASON_DEV_READY, DEV_READY) \
EM(SKB_DROP_REASON_FULL_RING, FULL_RING) \
+ EM(SKB_DROP_REASON_NOMEM, NOMEM) \
+ EM(SKB_DROP_REASON_HDR_TRUNC, HDR_TRUNC) \
+ EM(SKB_DROP_REASON_TAP_FILTER, TAP_FILTER) \
+ EM(SKB_DROP_REASON_TAP_TXFILTER, TAP_TXFILTER) \
EMe(SKB_DROP_REASON_MAX, MAX)
#undef EM
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. The below reasons are introduced: - SKB_DROP_REASON_DEV_READY - SKB_DROP_REASON_NOMEM - SKB_DROP_REASON_HDR_TRUNC - SKB_DROP_REASON_TAP_FILTER - SKB_DROP_REASON_TAP_TXFILTER Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Joe Jin <joe.jin@oracle.com> Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com> --- Changed since v1: - revise the reason name Changed since v2: - declare drop_reason as type "enum skb_drop_reason" Changed since v3: - rename to TAP_FILTER and TAP_TXFILTER - honor reverse xmas tree style declaration for 'drop_reason' in tun_net_xmit() Changed since v4: - expand comment on DEV_READY - change SKB_TRIM to NOMEM - chnage SKB_PULL to HDR_TRUNC drivers/net/tun.c | 37 ++++++++++++++++++++++++++++--------- include/linux/skbuff.h | 18 ++++++++++++++++++ include/trace/events/skb.h | 5 +++++ 3 files changed, 51 insertions(+), 9 deletions(-)