The commit c504e5c2f964 ("net: skb: introduce kfree_skb_reason()") has
introduced the kfree_skb_reason() to help track the reason. This is to
use kfree_skb_reason() to trace the dropped skb for those two drivers. The
tun and tap are commonly used as virtio-net/vhost-net backend.
This is the 'stacktrace' example for tap when the skb is dropped because
the ptr ring between tap and vhost-net is full.
kworker/13:0-9759 [013] ..s1. 1439.053393: kfree_skb: skbaddr=000000004109db76 protocol=2054 location=00000000db8dd81c reason: PTR_FULL
kworker/13:0-9759 [013] ..s2. 1439.053431: <stack trace>
=> trace_event_raw_event_kfree_skb
=> kfree_skb_reason.part.0
=> tap_handle_frame
=> __netif_receive_skb_core
=> __netif_receive_skb_one_core
=> process_backlog
=> __napi_poll
=> net_rx_action
=> __do_softirq
=> do_softirq.part.0
=> netif_rx_ni
=> macvlan_broadcast
=> macvlan_process_broadcast
=> process_one_work
=> worker_thread
=> kthread
=> ret_from_fork
This is the 'stacktrace' example for tun when the skb is dropped because
the ptr ring between run and vhost-net is full.
<idle>-0 [000] b.s2. 499.675592: kfree_skb: skbaddr=00000000ff79867d protocol=2054 location=00000000635128db reason: PTR_FULL
<idle>-0 [000] b.s3. 499.675612: <stack trace>
=> trace_event_raw_event_kfree_skb
=> kfree_skb_reason.part.0
=> tun_net_xmit
=> dev_hard_start_xmit
=> sch_direct_xmit
=> __dev_queue_xmit
=> br_dev_queue_push_xmit
=> br_handle_frame_finish
=> br_handle_frame
=> __netif_receive_skb_core
=> __netif_receive_skb_list_core
=> netif_receive_skb_list_internal
=> napi_complete_done
=> ixgbe_poll
=> __napi_poll
=> net_rx_action
=> __do_softirq
=> __irq_exit_rcu
=> common_interrupt
=> asm_common_interrupt
=> cpuidle_enter_state
=> cpuidle_enter
=> do_idle
=> cpu_startup_entry
=> start_kernel
=> secondary_startup_64_no_verify
drivers/net/tap.c | 30 ++++++++++++++++++++++--------
drivers/net/tun.c | 33 +++++++++++++++++++++++++--------
include/linux/skbuff.h | 11 +++++++++++
include/trace/events/skb.h | 11 +++++++++++
4 files changed, 69 insertions(+), 16 deletions(-)
Thank you very much!
Dongli Zhang
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
Cc: Joao Martins <[email protected]>
Cc: Joe Jin <[email protected]>
Signed-off-by: Dongli Zhang <[email protected]>
---
drivers/net/tap.c | 30 ++++++++++++++++++++++--------
include/linux/skbuff.h | 5 +++++
include/trace/events/skb.h | 5 +++++
3 files changed, 32 insertions(+), 8 deletions(-)
diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 8e3a28ba6b28..232572289e63 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;
+ int drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
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_SEGMENT;
goto drop;
+ }
if (!segs) {
- if (ptr_ring_produce(&q->ring, skb))
+ if (ptr_ring_produce(&q->ring, skb)) {
+ drop_reason = SKB_DROP_REASON_PTR_FULL;
goto drop;
+ }
goto wake_up;
}
@@ -369,10 +374,14 @@ 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_CHECKSUM;
goto drop;
- if (ptr_ring_produce(&q->ring, skb))
+ }
+ if (ptr_ring_produce(&q->ring, skb)) {
+ drop_reason = SKB_DROP_REASON_PTR_FULL;
goto drop;
+ }
}
wake_up:
@@ -383,7 +392,7 @@ 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 +641,7 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control,
int depth;
bool zerocopy = false;
size_t linear;
+ int drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
if (q->flags & IFF_VNET_HDR) {
vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
@@ -696,8 +706,10 @@ 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_COPY_DATA;
goto err_kfree;
+ }
skb_set_network_header(skb, ETH_HLEN);
skb_reset_mac_header(skb);
@@ -706,8 +718,10 @@ 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_VIRTNET_HDR;
goto err_kfree;
+ }
}
skb_probe_transport_header(skb);
@@ -738,7 +752,7 @@ 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 8a636e678902..16c30d2e20dc 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -320,6 +320,11 @@ enum skb_drop_reason {
SKB_DROP_REASON_TCP_CSUM,
SKB_DROP_REASON_SOCKET_FILTER,
SKB_DROP_REASON_UDP_CSUM,
+ SKB_DROP_REASON_SKB_GSO_SEGMENT,
+ SKB_DROP_REASON_SKB_CHECKSUM,
+ SKB_DROP_REASON_SKB_COPY_DATA,
+ SKB_DROP_REASON_PTR_FULL,
+ SKB_DROP_REASON_VIRTNET_HDR,
SKB_DROP_REASON_MAX,
};
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index a8a64b97504d..bf1509c31cea 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -16,6 +16,11 @@
EM(SKB_DROP_REASON_TCP_CSUM, TCP_CSUM) \
EM(SKB_DROP_REASON_SOCKET_FILTER, SOCKET_FILTER) \
EM(SKB_DROP_REASON_UDP_CSUM, UDP_CSUM) \
+ 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_PTR_FULL, PTR_FULL) \
+ EM(SKB_DROP_REASON_VIRTNET_HDR, VIRTNET_HDR) \
EMe(SKB_DROP_REASON_MAX, MAX)
#undef EM
--
2.17.1