The commit c504e5c2f964 ("net: skb: introduce kfree_skb_reason()") has
introduced the kfree_skb_reason() to help track the reason.
The tun and tap are commonly used as virtio-net/vhost-net backend. This is to
use kfree_skb_reason() to trace the dropped skb for those two drivers.
Changed since v1:
- I have renamed many of the reasons since v1. I make them as generic as
possible so that they can be re-used by core networking and drivers.
Changed since v2:
- declare drop_reason as type "enum skb_drop_reason"
- handle the drop in skb_list_walk_safe() case for tap driver, and
kfree_skb_list_reason() is introduced
Changed since v3 (only for PATCH 4/4):
- rename to TAP_FILTER and TAP_TXFILTER
- honor reverse xmas tree style declaration for 'drop_reason' in
tun_net_xmit()
Changed since v4:
- make kfree_skb_list() static inline
- add 'computation' to SKB_CSUM comment
- change COPY_DATA to UCOPY_FAULT
- add 'metadata' to DEV_HDR comment
- expand comment on DEV_READY
- change SKB_TRIM to NOMEM
- chnage SKB_PULL to HDR_TRUNC
The following reasons are introduced.
- SKB_DROP_REASON_SKB_CSUM
- SKB_DROP_REASON_SKB_GSO_SEG
- SKB_DROP_REASON_SKB_UCOPY_FAULT
- SKB_DROP_REASON_DEV_HDR
- SKB_DROP_REASON_FULL_RING
- SKB_DROP_REASON_DEV_READY
- SKB_DROP_REASON_NOMEM
- SKB_DROP_REASON_HDR_TRUNC
- SKB_DROP_REASON_TAP_FILTER
- SKB_DROP_REASON_TAP_TXFILTER
This is the output for TUN device.
# cat /sys/kernel/debug/tracing/trace_pipe
<idle>-0 [029] ..s1. 450.727651: kfree_skb: skbaddr=0000000023d235cc protocol=0 location=00000000a6748854 reason: NOT_SPECIFIED
<idle>-0 [000] b.s3. 451.165671: kfree_skb: skbaddr=000000006b5de7cc protocol=4 location=000000007c2b9eae reason: FULL_RING
<idle>-0 [000] b.s3. 453.149650: kfree_skb: skbaddr=000000006b5de7cc protocol=4 location=000000007c2b9eae reason: FULL_RING
<idle>-0 [000] b.s3. 455.133576: kfree_skb: skbaddr=000000006b5de7cc protocol=4 location=000000007c2b9eae reason: FULL_RING
<idle>-0 [000] b.s3. 457.117566: kfree_skb: skbaddr=000000006b5de7cc protocol=4 location=000000007c2b9eae reason: FULL_RING
This is the output for TAP device.
# cat /sys/kernel/debug/tracing/trace_pipe
arping-7053 [006] ..s1. 1000.047753: kfree_skb: skbaddr=000000008618a587 protocol=2054 location=00000000743ad4a7 reason: FULL_RING
<idle>-0 [022] ..s1. 1000.778514: kfree_skb: skbaddr=000000002c1e706c protocol=0 location=00000000a6748854 reason: NOT_SPECIFIED
arping-7053 [006] ..s1. 1001.047830: kfree_skb: skbaddr=000000008618a587 protocol=2054 location=00000000743ad4a7 reason: FULL_RING
arping-7053 [006] ..s1. 1002.047918: kfree_skb: skbaddr=000000008618a587 protocol=2054 location=00000000743ad4a7 reason: FULL_RING
arping-7053 [006] ..s1. 1003.048017: kfree_skb: skbaddr=000000008618a587 protocol=2054 location=00000000743ad4a7 reason: FULL_RING
drivers/net/tap.c | 35 +++++++++++++++++++++++++----------
drivers/net/tun.c | 38 ++++++++++++++++++++++++++++++--------
include/linux/skbuff.h | 39 ++++++++++++++++++++++++++++++++++++++-
include/trace/events/skb.h | 10 ++++++++++
net/core/skbuff.c | 7 ++++---
5 files changed, 107 insertions(+), 22 deletions(-)
Thank you very much!
Dongli Zhang
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 <[email protected]>
Cc: Joe Jin <[email protected]>
Signed-off-by: Dongli Zhang <[email protected]>
---
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(-)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 6e06c846fe82..bab92e489fba 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_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;
}
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index e5d5371a543b..4e5b725302ca 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -406,7 +406,25 @@ 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,
};
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index 9d91ec9755b8..e167a6657748 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -49,7 +49,12 @@
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
--
2.17.1
The TAP can be used as vhost-net backend. E.g., the tap_handle_frame() is
the interface to forward the skb from TAP to vhost-net/virtio-net.
However, there are many "goto drop" in the TAP 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_CSUM
- SKB_DROP_REASON_SKB_GSO_SEG
- SKB_DROP_REASON_SKB_UCOPY_FAULT
- SKB_DROP_REASON_DEV_HDR
- SKB_DROP_REASON_FULL_RING
Cc: Joao Martins <[email protected]>
Cc: Joe Jin <[email protected]>
Signed-off-by: Dongli Zhang <[email protected]>
---
Changed since v1:
- revise the reason name
Changed since v2:
- declare drop_reason as type "enum skb_drop_reason"
- handle the drop in skb_list_walk_safe() case
Changed since v4:
- add 'computation' to SKB_CSUM comment
- change COPY_DATA to UCOPY_FAULT
- add 'metadata' to DEV_HDR comment
drivers/net/tap.c | 35 +++++++++++++++++++++++++----------
include/linux/skbuff.h | 13 +++++++++++++
include/trace/events/skb.h | 5 +++++
3 files changed, 43 insertions(+), 10 deletions(-)
diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index ba2ef5437e16..c3d42062559d 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -322,6 +322,7 @@ rx_handler_result_t tap_handle_frame(struct sk_buff **pskb)
struct tap_dev *tap;
struct tap_queue *q;
netdev_features_t features = TAP_FEATURES;
+ enum skb_drop_reason drop_reason;
tap = tap_dev_get_rcu(dev);
if (!tap)
@@ -343,12 +344,16 @@ rx_handler_result_t tap_handle_frame(struct sk_buff **pskb)
struct sk_buff *segs = __skb_gso_segment(skb, features, false);
struct sk_buff *next;
- if (IS_ERR(segs))
+ if (IS_ERR(segs)) {
+ drop_reason = SKB_DROP_REASON_SKB_GSO_SEG;
goto drop;
+ }
if (!segs) {
- if (ptr_ring_produce(&q->ring, skb))
+ if (ptr_ring_produce(&q->ring, skb)) {
+ drop_reason = SKB_DROP_REASON_FULL_RING;
goto drop;
+ }
goto wake_up;
}
@@ -356,8 +361,9 @@ rx_handler_result_t tap_handle_frame(struct sk_buff **pskb)
skb_list_walk_safe(segs, skb, next) {
skb_mark_not_on_list(skb);
if (ptr_ring_produce(&q->ring, skb)) {
- kfree_skb(skb);
- kfree_skb_list(next);
+ drop_reason = SKB_DROP_REASON_FULL_RING;
+ kfree_skb_reason(skb, drop_reason);
+ kfree_skb_list_reason(next, drop_reason);
break;
}
}
@@ -369,10 +375,14 @@ rx_handler_result_t tap_handle_frame(struct sk_buff **pskb)
*/
if (skb->ip_summed == CHECKSUM_PARTIAL &&
!(features & NETIF_F_CSUM_MASK) &&
- skb_checksum_help(skb))
+ skb_checksum_help(skb)) {
+ drop_reason = SKB_DROP_REASON_SKB_CSUM;
goto drop;
- if (ptr_ring_produce(&q->ring, skb))
+ }
+ if (ptr_ring_produce(&q->ring, skb)) {
+ drop_reason = SKB_DROP_REASON_FULL_RING;
goto drop;
+ }
}
wake_up:
@@ -383,7 +393,7 @@ rx_handler_result_t tap_handle_frame(struct sk_buff **pskb)
/* Count errors/drops only here, thus don't care about args. */
if (tap->count_rx_dropped)
tap->count_rx_dropped(tap);
- kfree_skb(skb);
+ kfree_skb_reason(skb, drop_reason);
return RX_HANDLER_CONSUMED;
}
EXPORT_SYMBOL_GPL(tap_handle_frame);
@@ -632,6 +642,7 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control,
int depth;
bool zerocopy = false;
size_t linear;
+ enum skb_drop_reason drop_reason;
if (q->flags & IFF_VNET_HDR) {
vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
@@ -696,8 +707,10 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control,
else
err = skb_copy_datagram_from_iter(skb, 0, from, len);
- if (err)
+ if (err) {
+ drop_reason = SKB_DROP_REASON_SKB_UCOPY_FAULT;
goto err_kfree;
+ }
skb_set_network_header(skb, ETH_HLEN);
skb_reset_mac_header(skb);
@@ -706,8 +719,10 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control,
if (vnet_hdr_len) {
err = virtio_net_hdr_to_skb(skb, &vnet_hdr,
tap_is_little_endian(q));
- if (err)
+ if (err) {
+ drop_reason = SKB_DROP_REASON_DEV_HDR;
goto err_kfree;
+ }
}
skb_probe_transport_header(skb);
@@ -738,7 +753,7 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control,
return total_len;
err_kfree:
- kfree_skb(skb);
+ kfree_skb_reason(skb, drop_reason);
err:
rcu_read_lock();
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index bb00f86791e0..e5d5371a543b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -394,6 +394,19 @@ enum skb_drop_reason {
* entry is full
*/
SKB_DROP_REASON_NEIGH_DEAD, /* neigh entry is dead */
+ SKB_DROP_REASON_SKB_CSUM, /* sk_buff checksum computation
+ * error
+ */
+ SKB_DROP_REASON_SKB_GSO_SEG, /* gso segmentation error */
+ SKB_DROP_REASON_SKB_UCOPY_FAULT, /* failed to copy data from
+ * user space, e.g., via
+ * zerocopy_sg_from_iter()
+ * or skb_orphan_frags_rx()
+ */
+ SKB_DROP_REASON_DEV_HDR, /* device driver specific
+ * header/metadata is invalid
+ */
+ SKB_DROP_REASON_FULL_RING, /* ring buffer is full */
SKB_DROP_REASON_MAX,
};
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index 1977f301260d..9d91ec9755b8 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -45,6 +45,11 @@
EM(SKB_DROP_REASON_NEIGH_FAILED, NEIGH_FAILED) \
EM(SKB_DROP_REASON_NEIGH_QUEUEFULL, NEIGH_QUEUEFULL) \
EM(SKB_DROP_REASON_NEIGH_DEAD, NEIGH_DEAD) \
+ EM(SKB_DROP_REASON_SKB_CSUM, SKB_CSUM) \
+ 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_FULL_RING, FULL_RING) \
EMe(SKB_DROP_REASON_MAX, MAX)
#undef EM
--
2.17.1
From: Dongli Zhang <[email protected]>
Date: Thu, 3 Mar 2022 22:33:03 -0800
> The commit c504e5c2f964 ("net: skb: introduce kfree_skb_reason()") has
> introduced the kfree_skb_reason() to help track the reason.
>
> The tun and tap are commonly used as virtio-net/vhost-net backend. This is to
> use kfree_skb_reason() to trace the dropped skb for those two drivers.
This patch series does not apply cleanly against net-next, plewase respin.
Thank you.
This is to introduce kfree_skb_list_reason() to drop a list of sk_buff with
a specific reason.
Cc: Joao Martins <[email protected]>
Cc: Joe Jin <[email protected]>
Signed-off-by: Dongli Zhang <[email protected]>
---
Changed since v4:
- make kfree_skb_list() static inline
include/linux/skbuff.h | 8 +++++++-
net/core/skbuff.c | 7 ++++---
2 files changed, 11 insertions(+), 4 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 5445860e1ba6..bb00f86791e0 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1201,10 +1201,16 @@ static inline void kfree_skb(struct sk_buff *skb)
}
void skb_release_head_state(struct sk_buff *skb);
-void kfree_skb_list(struct sk_buff *segs);
+void kfree_skb_list_reason(struct sk_buff *segs,
+ enum skb_drop_reason reason);
void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt);
void skb_tx_error(struct sk_buff *skb);
+static inline void kfree_skb_list(struct sk_buff *segs)
+{
+ kfree_skb_list_reason(segs, SKB_DROP_REASON_NOT_SPECIFIED);
+}
+
#ifdef CONFIG_TRACEPOINTS
void consume_skb(struct sk_buff *skb);
#else
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 23f3ba343661..10bde7c6db44 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -777,16 +777,17 @@ void kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason)
}
EXPORT_SYMBOL(kfree_skb_reason);
-void kfree_skb_list(struct sk_buff *segs)
+void kfree_skb_list_reason(struct sk_buff *segs,
+ enum skb_drop_reason reason)
{
while (segs) {
struct sk_buff *next = segs->next;
- kfree_skb(segs);
+ kfree_skb_reason(segs, reason);
segs = next;
}
}
-EXPORT_SYMBOL(kfree_skb_list);
+EXPORT_SYMBOL(kfree_skb_list_reason);
/* Dump skb information and contents.
*
--
2.17.1
Hi David,
On 3/4/22 4:25 AM, David Miller wrote:
> From: Dongli Zhang <[email protected]>
> Date: Thu, 3 Mar 2022 22:33:03 -0800
>
>> The commit c504e5c2f964 ("net: skb: introduce kfree_skb_reason()") has
>> introduced the kfree_skb_reason() to help track the reason.
>>
>> The tun and tap are commonly used as virtio-net/vhost-net backend. This is to
>> use kfree_skb_reason() to trace the dropped skb for those two drivers.
>
> This patch series does not apply cleanly against net-next, plewase respin.
>
Sorry for that. I will rebase to the most recent net-next.
Unfortunately, one patch just merged to net-next has already been in my patchset ...
https://lore.kernel.org/netdev/[email protected]/
... so that I will need to remove my PATCH 1/4 and rebase.
Thank you very much!
Dongli Zhang