aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorJakub Kicinski <kuba@kernel.org>2020-11-12 09:55:58 -0800
committerJakub Kicinski <kuba@kernel.org>2020-11-12 09:55:59 -0800
commit5861c8cb1c90fc171d56994827a66a5595a44d56 (patch)
tree30734917e8330ab74b80440fd3dcc6dc29e29f5c
parent8a5c2906c52f4a81939b4f8536e0004a4193a154 (diff)
parent55e729889bb07d68ab071660ce3f5e7a7872ebe8 (diff)
downloadlinux-5861c8cb1c90fc171d56994827a66a5595a44d56.tar.gz
Merge branch 'net-udp-fix-fast-frag0-udp-gro'
Alexander Lobakin says: ==================== net: udp: fix Fast/frag0 UDP GRO 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() or any other method without frag0 shortcut completely resolved them. I've found two incorrect header accesses in GRO receive callback(s): - udp_hdr() (instead of udp_gro_udphdr()) that always points to junk in "fast" mode and could probably do this in "regular". This was the actual bug that caused all out-of-order delivers; - udp{4,6}_lib_lookup_skb() -> ip{,v6}_hdr() (instead of skb_gro_network_header()) that potentionally might return odd pointers in both modes. Each patch addresses one of these two issues. This doesn't cover a support for nested tunnels as it's out of the subject and requires more invasive changes. It will be handled separately in net-next series. Credits: Cc: Eric Dumazet <edumazet@google.com> Cc: Jakub Kicinski <kuba@kernel.org> Cc: Willem de Bruijn <willemb@google.com> Since v4 [0]: - split the fix into two logical ones (Willem); - replace ternaries with plain ifs to beautify the code (Jakub); - drop p->data part to reintroduce it later in abovementioned set. Since v3 [1]: - restore the original {,__}udp{4,6}_lib_lookup_skb() and use private versions of them inside GRO code (Willem). Since v2 [2]: - 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 [3]: - added a NULL pointer check for "uh" as suggested by Willem. [0] https://lore.kernel.org/netdev/Ha2hou5eJPcblo4abjAqxZRzIl1RaLs2Hy0oOAgFs@cp4-web-036.plabs.ch [1] https://lore.kernel.org/netdev/MgZce9htmEtCtHg7pmWxXXfdhmQ6AHrnltXC41zOoo@cp7-web-042.plabs.ch [2] https://lore.kernel.org/netdev/0eaG8xtbtKY1dEKCTKUBubGiC9QawGgB3tVZtNqVdY@cp4-web-030.plabs.ch [3] https://lore.kernel.org/netdev/YazU6GEzBdpyZMDMwJirxDX7B4sualpDG68ADZYvJI@cp4-web-034.plabs.ch ==================== Link: https://lore.kernel.org/r/hjGOh0iCOYyo1FPiZh6TMXcx3YCgNs1T1eGKLrDz8@cp4-web-037.plabs.ch Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-rw-r--r--net/ipv4/udp_offload.c19
-rw-r--r--net/ipv6/udp_offload.c17
2 files changed, 31 insertions, 5 deletions
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index e67a66fbf27b83..c62805cd31319f 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -366,7 +366,7 @@ out:
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;
@@ -500,12 +500,22 @@ out:
}
EXPORT_SYMBOL(udp_gro_receive);
+static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
+ __be16 dport)
+{
+ 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),
+ inet_sdif(skb), &udp_table, NULL);
+}
+
INDIRECT_CALLABLE_SCOPE
struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb)
{
struct udphdr *uh = udp_gro_udphdr(skb);
+ struct sock *sk = NULL;
struct sk_buff *pp;
- struct sock *sk;
if (unlikely(!uh))
goto flush;
@@ -523,7 +533,10 @@ struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb)
skip:
NAPI_GRO_CB(skb)->is_ipv6 = 0;
rcu_read_lock();
- sk = static_branch_unlikely(&udp_encap_needed_key) ? udp4_lib_lookup_skb(skb, uh->source, uh->dest) : NULL;
+
+ if (static_branch_unlikely(&udp_encap_needed_key))
+ sk = udp4_gro_lookup_skb(skb, uh->source, uh->dest);
+
pp = udp_gro_receive(head, skb, uh, sk);
rcu_read_unlock();
return pp;
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 584157a0775969..f9e888d1b9af8b 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -111,12 +111,22 @@ out:
return segs;
}
+static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
+ __be16 dport)
+{
+ 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),
+ inet6_sdif(skb), &udp_table, NULL);
+}
+
INDIRECT_CALLABLE_SCOPE
struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb)
{
struct udphdr *uh = udp_gro_udphdr(skb);
+ struct sock *sk = NULL;
struct sk_buff *pp;
- struct sock *sk;
if (unlikely(!uh))
goto flush;
@@ -135,7 +145,10 @@ struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb)
skip:
NAPI_GRO_CB(skb)->is_ipv6 = 1;
rcu_read_lock();
- sk = static_branch_unlikely(&udpv6_encap_needed_key) ? udp6_lib_lookup_skb(skb, uh->source, uh->dest) : NULL;
+
+ if (static_branch_unlikely(&udpv6_encap_needed_key))
+ sk = udp6_gro_lookup_skb(skb, uh->source, uh->dest);
+
pp = udp_gro_receive(head, skb, uh, sk);
rcu_read_unlock();
return pp;