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 <[email protected]>
Cc: Joe Jin <[email protected]>
Signed-off-by: Dongli Zhang <[email protected]>
---
drivers/net/tun.c | 33 +++++++++++++++++++++++++--------
include/linux/skbuff.h | 6 ++++++
include/trace/events/skb.h | 6 ++++++
3 files changed, 37 insertions(+), 8 deletions(-)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index fed85447701a..d67f2419dbb4 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;
+ int drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
rcu_read_lock();
tfile = rcu_dereference(tun->tfiles[txq]);
/* Drop packet if interface is not attached */
- if (!tfile)
+ if (!tfile) {
+ drop_reason = SKB_DROP_REASON_DEV_NOT_ATTACHED;
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_reason = SKB_DROP_REASON_TAP_RUN_FILTER;
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_SKB_TRIM;
goto drop;
+ }
len = run_ebpf_filter(tun, skb, len);
- if (len == 0 || pskb_trim(skb, len))
+ if (len == 0 || pskb_trim(skb, len)) {
+ drop_reason = SKB_DROP_REASON_SKB_TRIM;
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_ORPHAN_FRAGS;
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_reason = SKB_DROP_REASON_PTR_FULL;
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, drop_reason);
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);
+ int drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
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_reason = SKB_DROP_REASON_SKB_COPY_DATA;
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);
@@ -1869,6 +1884,7 @@ 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_SKB_PULL;
goto drop;
}
skb->protocol = eth_type_trans(skb, tun->dev);
@@ -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_reason = SKB_DROP_REASON_DEV_DOWN;
goto drop;
}
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 16c30d2e20dc..db2ef8e8d878 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -323,8 +323,14 @@ enum skb_drop_reason {
SKB_DROP_REASON_SKB_GSO_SEGMENT,
SKB_DROP_REASON_SKB_CHECKSUM,
SKB_DROP_REASON_SKB_COPY_DATA,
+ SKB_DROP_REASON_SKB_TRIM,
+ SKB_DROP_REASON_SKB_ORPHAN_FRAGS,
+ SKB_DROP_REASON_SKB_PULL,
+ SKB_DROP_REASON_DEV_NOT_ATTACHED,
+ SKB_DROP_REASON_DEV_DOWN,
SKB_DROP_REASON_PTR_FULL,
SKB_DROP_REASON_VIRTNET_HDR,
+ SKB_DROP_REASON_TAP_RUN_FILTER,
SKB_DROP_REASON_MAX,
};
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index bf1509c31cea..03121373d2f0 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -19,8 +19,14 @@
EM(SKB_DROP_REASON_SKB_GSO_SEGMENT, SKB_GSO_SEGMENT) \
EM(SKB_DROP_REASON_SKB_CHECKSUM, SKB_CHECKSUM) \
EM(SKB_DROP_REASON_SKB_COPY_DATA, SKB_COPY_DATA) \
+ EM(SKB_DROP_REASON_SKB_TRIM, SKB_TRIM) \
+ EM(SKB_DROP_REASON_SKB_ORPHAN_FRAGS, SKB_ORPHAN_FRAGS) \
+ EM(SKB_DROP_REASON_SKB_PULL, SKB_PULL) \
+ EM(SKB_DROP_REASON_DEV_NOT_ATTACHED, DEV_NOT_ATTACHED) \
+ EM(SKB_DROP_REASON_DEV_DOWN, DEV_DOWN) \
EM(SKB_DROP_REASON_PTR_FULL, PTR_FULL) \
EM(SKB_DROP_REASON_VIRTNET_HDR, VIRTNET_HDR) \
+ EM(SKB_DROP_REASON_TAP_RUN_FILTER, TAP_RUN_FILTER) \
EMe(SKB_DROP_REASON_MAX, MAX)
#undef EM
--
2.17.1
On 2/7/22 7:55 PM, Dongli Zhang wrote:
> 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 <[email protected]>
> Cc: Joe Jin <[email protected]>
> Signed-off-by: Dongli Zhang <[email protected]>
> ---
> drivers/net/tun.c | 33 +++++++++++++++++++++++++--------
> include/linux/skbuff.h | 6 ++++++
> include/trace/events/skb.h | 6 ++++++
> 3 files changed, 37 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/net/tun.c b/drivers/net/tun.c
> index fed85447701a..d67f2419dbb4 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;
> + int drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
>
> rcu_read_lock();
> tfile = rcu_dereference(tun->tfiles[txq]);
>
> /* Drop packet if interface is not attached */
> - if (!tfile)
> + if (!tfile) {
> + drop_reason = SKB_DROP_REASON_DEV_NOT_ATTACHED;
That is going to be a confusing reason code (tap device existed to get
here) and does not really explain this error.
> 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_reason = SKB_DROP_REASON_TAP_RUN_FILTER;
just SKB_DROP_REASON_TAP_FILTER
> 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_SKB_TRIM;
SKB_DROP_REASON_SOCKET_FILTER
The remainder of your changes feels like another variant of your
previous "function / line" reason code. You are creating new reason
codes for every goto failure with a code based name. The reason needs to
be the essence of the failure in a user friendly label.
Hi David,
On 2/7/22 9:03 PM, David Ahern wrote:
> On 2/7/22 7:55 PM, Dongli Zhang wrote:
>> 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 <[email protected]>
>> Cc: Joe Jin <[email protected]>
>> Signed-off-by: Dongli Zhang <[email protected]>
>> ---
>> drivers/net/tun.c | 33 +++++++++++++++++++++++++--------
>> include/linux/skbuff.h | 6 ++++++
>> include/trace/events/skb.h | 6 ++++++
>> 3 files changed, 37 insertions(+), 8 deletions(-)
>>
>> diff --git a/drivers/net/tun.c b/drivers/net/tun.c
>> index fed85447701a..d67f2419dbb4 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;
>> + int drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
>
I will avoid initializing here.
>
>>
>> rcu_read_lock();
>> tfile = rcu_dereference(tun->tfiles[txq]);
>>
>> /* Drop packet if interface is not attached */
>> - if (!tfile)
>> + if (!tfile) {
>> + drop_reason = SKB_DROP_REASON_DEV_NOT_ATTACHED;
Initially I was using TUN_NOT_ATTACHED. I used a more generic DEV_NOT_ATTACHED
in order to re-use the reason in the future.
How about TUN specific TUN_NOT_ATTACHED, as the core issue is because the below
is not hit.
rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile);
>
> That is going to be a confusing reason code (tap device existed to get
> here) and does not really explain this error.
>
>
>> 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_reason = SKB_DROP_REASON_TAP_RUN_FILTER;
>
> just SKB_DROP_REASON_TAP_FILTER
I will use SKB_DROP_REASON_TAP_FILTER.
>
>> 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_SKB_TRIM;
>
> SKB_DROP_REASON_SOCKET_FILTER
Sorry for my mistake, I should have re-used this SKB_DROP_REASON_SOCKET_FILTER.
>
> The remainder of your changes feels like another variant of your
> previous "function / line" reason code. You are creating new reason
> codes for every goto failure with a code based name. The reason needs to
> be the essence of the failure in a user friendly label.
>
The remainder are:
- SKB_DROP_REASON_SKB_TRIM
- SKB_DROP_REASON_SKB_ORPHAN_FRAGS
- SKB_DROP_REASON_SKB_PULL
- SKB_DROP_REASON_DEV_DOWN
- SKB_DROP_REASON_SKB_COPY_DATA (introduced by Patch 1/2)
I tried to make them self-explaining and re-usable to other developers.
Yes, I am creating new reason codes for every goto failure with a code based
name because each function might be failed due to many reasons. In addition, I
need to avoid duplicate 'drop_reason' returned by a function in order to help
developer identify the specific line of code that the sk_buff is dropped.
Thank you very much!
Dongli Zhang