From: Dongli Zhang <dongli.zhang@oracle.com>
To: netdev@vger.kernel.org, bpf@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, davem@davemloft.net,
kuba@kernel.org, rostedt@goodmis.org, mingo@redhat.com,
ast@kernel.org, daniel@iogearbox.net, andrii@kernel.org,
imagedong@tencent.com, joao.m.martins@oracle.com,
joe.jin@oracle.com, dsahern@gmail.com, edumazet@google.com
Subject: [PATCH net-next v4 4/4] net: tun: track dropped skb via kfree_skb_reason()
Date: Sat, 26 Feb 2022 00:49:29 -0800 [thread overview]
Message-ID: <20220226084929.6417-5-dongli.zhang@oracle.com> (raw)
In-Reply-To: <20220226084929.6417-1-dongli.zhang@oracle.com>
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_SKB_PULL
- SKB_DROP_REASON_SKB_TRIM
- SKB_DROP_REASON_DEV_READY
- 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()
drivers/net/tun.c | 37 ++++++++++++++++++++++++++++---------
include/linux/skbuff.h | 10 ++++++++++
include/trace/events/skb.h | 5 +++++
3 files changed, 43 insertions(+), 9 deletions(-)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index aa27268edc5f..73ad2bb5e8ae 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -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_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_COPY_DATA;
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_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);
@@ -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_SKB_PULL;
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;
}
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 9f523da4d3f2..9a0a15a31591 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -385,10 +385,20 @@ enum skb_drop_reason {
* sk_buff
*/
SKB_DROP_REASON_SKB_GSO_SEG, /* gso segmentation error */
+ SKB_DROP_REASON_SKB_PULL, /* failed to pull sk_buff data */
+ SKB_DROP_REASON_SKB_TRIM, /* failed to trim sk_buff data */
SKB_DROP_REASON_DEV_HDR, /* there is something wrong with
* device driver specific header
*/
+ SKB_DROP_REASON_DEV_READY, /* device is not ready */
SKB_DROP_REASON_FULL_RING, /* ring buffer is full */
+ 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,
};
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index 5b5f1351dcde..e8dcf784ac17 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -40,8 +40,13 @@
EM(SKB_DROP_REASON_SKB_CSUM, SKB_CSUM) \
EM(SKB_DROP_REASON_SKB_COPY_DATA, SKB_COPY_DATA) \
EM(SKB_DROP_REASON_SKB_GSO_SEG, SKB_GSO_SEG) \
+ EM(SKB_DROP_REASON_SKB_PULL, SKB_PULL) \
+ EM(SKB_DROP_REASON_SKB_TRIM, SKB_TRIM) \
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_TAP_FILTER, TAP_FILTER) \
+ EM(SKB_DROP_REASON_TAP_TXFILTER, TAP_TXFILTER) \
EMe(SKB_DROP_REASON_MAX, MAX)
#undef EM
--
2.17.1
next prev parent reply other threads:[~2022-02-26 8:51 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-02-26 8:49 [PATCH net-next v4 0/4] tun/tap: use kfree_skb_reason() to trace dropped skb Dongli Zhang
2022-02-26 8:49 ` [PATCH net-next v4 1/4] skbuff: introduce kfree_skb_list_reason() Dongli Zhang
2022-03-02 2:34 ` Jakub Kicinski
2022-03-02 16:49 ` Dongli Zhang
2022-02-26 8:49 ` [PATCH net-next v4 2/4] net: tap: track dropped skb via kfree_skb_reason() Dongli Zhang
2022-03-02 2:42 ` Jakub Kicinski
2022-03-02 17:43 ` Dongli Zhang
2022-03-02 19:03 ` Jakub Kicinski
2022-03-02 21:44 ` Dongli Zhang
2022-02-26 8:49 ` [PATCH net-next v4 3/4] net: tun: split run_ebpf_filter() and pskb_trim() into different "if statement" Dongli Zhang
2022-02-26 8:49 ` Dongli Zhang [this message]
2022-02-28 1:20 ` [PATCH net-next v4 4/4] net: tun: track dropped skb via kfree_skb_reason() David Ahern
2022-03-02 2:50 ` Jakub Kicinski
2022-03-02 3:29 ` David Ahern
2022-03-02 4:16 ` [Internet]Re: " imagedong(董梦龙)
2022-03-02 18:26 ` Dongli Zhang
2022-03-02 19:22 ` Jakub Kicinski
2022-03-02 18:19 ` Dongli Zhang
2022-03-02 19:17 ` Jakub Kicinski
2022-03-02 22:21 ` Dongli Zhang
2022-03-03 5:21 ` Jakub Kicinski
2022-03-03 5:55 ` Dongli Zhang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20220226084929.6417-5-dongli.zhang@oracle.com \
--to=dongli.zhang@oracle.com \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=dsahern@gmail.com \
--cc=edumazet@google.com \
--cc=imagedong@tencent.com \
--cc=joao.m.martins@oracle.com \
--cc=joe.jin@oracle.com \
--cc=kuba@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=rostedt@goodmis.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).