While testing UDP GSO fraglists forwarding through driver that uses
Fast GRO (via napi_gro_frags()), I was observing lots of out-of-order
iperf packets:
[ ID] Interval Transfer Bitrate Jitter
[SUM] 0.0-40.0 sec 12106 datagrams received out-of-order
Simple switch to napi_gro_receive() any other method without frag0
shortcut completely resolved them.
I've found that UDP GRO uses udp_hdr(skb) in its .gro_receive()
callback. While it's probably OK for non-frag0 paths (when all
headers or even the entire frame are already in skb->data), this
inline points to junk when using Fast GRO (napi_gro_frags() or
napi_gro_receive() with only Ethernet header in skb->data and all
the rest in shinfo->frags) and breaks GRO packet compilation and
the packet flow itself.
To support both modes, skb_gro_header_fast() + skb_gro_header_slow()
are typically used. UDP even has an inline helper that makes use of
them, udp_gro_udphdr(). Use that instead of troublemaking udp_hdr()
to get rid of the out-of-order delivers.
Present since the introduction of plain UDP GRO in 5.0-rc1.
Since v2 [1]:
- dropped redundant check introduced in v2 as it's performed right
before (thanks to Eric);
- udp_hdr() switched to data + off for skbs from list (also Eric);
- fixed possible malfunction of {,__}udp{4,6}_lib_lookup_skb() with
Fast/frag0 due to ip{,v6}_hdr() usage (Willem).
Since v1 [2]:
- added a NULL pointer check for "uh" as suggested by Willem.
[1]
https://lore.kernel.org/netdev/0eag8xtbtky1dekctkububgic9qawggb3tvztnq...@cp4-web-030.plabs.ch
[2]
https://lore.kernel.org/netdev/yazu6gezbdpyzmdmwjirxdx7b4sualpdg68adzy...@cp4-web-034.plabs.ch
Fixes: e20cf8d3f1f7 ("udp: implement GRO for plain UDP sockets.")
Signed-off-by: Alexander Lobakin <aloba...@pm.me>
---
net/ipv4/udp.c | 4 ++--
net/ipv4/udp_offload.c | 9 ++++++---
net/ipv6/udp.c | 4 ++--
3 files changed, 10 insertions(+), 7 deletions(-)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 09f0a23d1a01..948ddc9a0212 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -534,7 +534,7 @@ static inline struct sock *__udp4_lib_lookup_skb(struct
sk_buff *skb,
__be16 sport, __be16 dport,
struct udp_table *udptable)
{
- const struct iphdr *iph = ip_hdr(skb);
+ const struct iphdr *iph = skb_gro_network_header(skb);
return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport,
iph->daddr, dport, inet_iif(skb),
@@ -544,7 +544,7 @@ static inline struct sock *__udp4_lib_lookup_skb(struct
sk_buff *skb,
struct sock *udp4_lib_lookup_skb(struct sk_buff *skb,
__be16 sport, __be16 dport)
{
- const struct iphdr *iph = ip_hdr(skb);
+ const struct iphdr *iph = skb_gro_network_header(skb);
return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport,
iph->daddr, dport, inet_iif(skb),
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index e67a66fbf27b..dbc4d17c55e9 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -366,11 +366,11 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff
*skb,
static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
struct sk_buff *skb)
{
- struct udphdr *uh = udp_hdr(skb);
+ struct udphdr *uh = udp_gro_udphdr(skb);
struct sk_buff *pp = NULL;
struct udphdr *uh2;
struct sk_buff *p;
- unsigned int ulen;
+ u32 ulen, off;
int ret = 0;
/* requires non zero csum, for symmetry with GSO */
@@ -385,6 +385,9 @@ static struct sk_buff *udp_gro_receive_segment(struct
list_head *head,
NAPI_GRO_CB(skb)->flush = 1;
return NULL;
}
+
+ off = skb_gro_offset(skb);
+
/* pull encapsulating udp header */
skb_gro_pull(skb, sizeof(struct udphdr));
@@ -392,7 +395,7 @@ static struct sk_buff *udp_gro_receive_segment(struct
list_head *head,
if (!NAPI_GRO_CB(p)->same_flow)
continue;
- uh2 = udp_hdr(p);
+ uh2 = (void *)p->data + off;
/* Match ports only, as csum is always non zero */
if ((*(u32 *)&uh->source != *(u32 *)&uh2->source)) {
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 29d9691359b9..a256ecce76b2 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -269,7 +269,7 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff
*skb,
__be16 sport, __be16 dport,
struct udp_table *udptable)
{
- const struct ipv6hdr *iph = ipv6_hdr(skb);
+ const struct ipv6hdr *iph = skb_gro_network_header(skb);
return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport,
&iph->daddr, dport, inet6_iif(skb),
@@ -279,7 +279,7 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff
*skb,
struct sock *udp6_lib_lookup_skb(struct sk_buff *skb,
__be16 sport, __be16 dport)
{
- const struct ipv6hdr *iph = ipv6_hdr(skb);
+ const struct ipv6hdr *iph = skb_gro_network_header(skb);
return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport,
&iph->daddr, dport, inet6_iif(skb),
--
2.29.2
