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 v3 2/4] net: tap: track dropped skb via kfree_skb_reason()
Date: Sun, 20 Feb 2022 21:34:38 -0800 [thread overview]
Message-ID: <20220221053440.7320-3-dongli.zhang@oracle.com> (raw)
In-Reply-To: <20220221053440.7320-1-dongli.zhang@oracle.com>
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_COPY_DATA
- SKB_DROP_REASON_SKB_GSO_SEG
- SKB_DROP_REASON_DEV_HDR
- SKB_DROP_REASON_FULL_RING
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"
- handle the drop in skb_list_walk_safe() case
drivers/net/tap.c | 35 +++++++++++++++++++++++++----------
include/linux/skbuff.h | 9 +++++++++
include/trace/events/skb.h | 5 +++++
3 files changed, 39 insertions(+), 10 deletions(-)
diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 8e3a28b..b48f519 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_COPY_DATA;
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 87ebe2f..52550c7 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -380,6 +380,15 @@ enum skb_drop_reason {
* the ofo queue, corresponding to
* LINUX_MIB_TCPOFOMERGE
*/
+ SKB_DROP_REASON_SKB_CSUM, /* sk_buff checksum error */
+ SKB_DROP_REASON_SKB_COPY_DATA, /* failed to copy data from or to
+ * sk_buff
+ */
+ SKB_DROP_REASON_SKB_GSO_SEG, /* gso segmentation error */
+ SKB_DROP_REASON_DEV_HDR, /* there is something wrong with
+ * device driver specific header
+ */
+ 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 2ab7193..5b5f135 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -37,6 +37,11 @@
EM(SKB_DROP_REASON_TCP_OLD_DATA, TCP_OLD_DATA) \
EM(SKB_DROP_REASON_TCP_OVERWINDOW, TCP_OVERWINDOW) \
EM(SKB_DROP_REASON_TCP_OFOMERGE, TCP_OFOMERGE) \
+ 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_DEV_HDR, DEV_HDR) \
+ EM(SKB_DROP_REASON_FULL_RING, FULL_RING) \
EMe(SKB_DROP_REASON_MAX, MAX)
#undef EM
--
1.8.3.1
next prev parent reply other threads:[~2022-02-21 5:38 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-02-21 5:34 [PATCH net-next v3 0/3] tun/tap: use kfree_skb_reason() to trace dropped skb Dongli Zhang
2022-02-21 5:34 ` [PATCH net-next v3 1/4] skbuff: introduce kfree_skb_list_reason() Dongli Zhang
2022-02-22 3:20 ` David Ahern
2022-02-21 5:34 ` Dongli Zhang [this message]
2022-02-22 3:24 ` [PATCH net-next v3 2/4] net: tap: track dropped skb via kfree_skb_reason() David Ahern
2022-02-22 4:31 ` Dongli Zhang
2022-02-26 8:52 ` Dongli Zhang
2022-02-21 5:34 ` [PATCH net-next v3 3/4] net: tun: split run_ebpf_filter() and pskb_trim() into different "if statement" Dongli Zhang
2022-02-22 3:28 ` David Ahern
2022-02-21 5:34 ` [PATCH net-next v3 4/4] net: tun: track dropped skb via kfree_skb_reason() Dongli Zhang
2022-02-22 3:28 ` David Ahern
2022-02-22 4:45 ` Dongli Zhang
2022-02-22 14:39 ` David Ahern
2022-02-22 18:20 ` Dongli Zhang
2022-02-25 5:57 ` Menglong Dong
2022-02-25 15:48 ` David Ahern
2022-02-25 16:49 ` Dongli Zhang
2022-02-21 22:53 ` [PATCH net-next v3 0/3] tun/tap: use kfree_skb_reason() to trace dropped skb 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=20220221053440.7320-3-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).