Re: [PATCH v4 net] net: udp: fix Fast/frag0 UDP GRO
From: Alexander Lobakin
Date: Mon Nov 09 2020 - 19:29:22 EST
From: Alexander Lobakin <alobakin@xxxxx>
Date: Tue, 10 Nov 2020 00:17:18 +0000
> 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 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 v3 [1]:
> - restore the original {,__}udp{4,6}_lib_lookup_skb() and use
> private versions of them inside GRO code (Willem).
Note: 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.
> 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.
>
> [1] https://lore.kernel.org/netdev/MgZce9htmEtCtHg7pmWxXXfdhmQ6AHrnltXC41zOoo@xxxxxxxxxxxxxxxxxxxx
> [2] https://lore.kernel.org/netdev/0eaG8xtbtKY1dEKCTKUBubGiC9QawGgB3tVZtNqVdY@xxxxxxxxxxxxxxxxxxxx
> [3] https://lore.kernel.org/netdev/YazU6GEzBdpyZMDMwJirxDX7B4sualpDG68ADZYvJI@xxxxxxxxxxxxxxxxxxxx
>
> Fixes: e20cf8d3f1f7 ("udp: implement GRO for plain UDP sockets.")
> Cc: Eric Dumazet <edumazet@xxxxxxxxxx>
> Cc: Willem de Bruijn <willemb@xxxxxxxxxx>
> Signed-off-by: Alexander Lobakin <alobakin@xxxxx>
> ---
> net/ipv4/udp_offload.c | 23 +++++++++++++++++++----
> net/ipv6/udp_offload.c | 14 +++++++++++++-
> 2 files changed, 32 insertions(+), 5 deletions(-)
>
> diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
> index e67a66fbf27b..6064efe17cdb 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)) {
> @@ -500,6 +503,16 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
> }
> 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)
> {
> @@ -523,7 +536,9 @@ 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;
> + sk = static_branch_unlikely(&udp_encap_needed_key) ?
> + udp4_gro_lookup_skb(skb, uh->source, uh->dest) :
> + NULL;
> 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 584157a07759..b126ab2120d9 100644
> --- a/net/ipv6/udp_offload.c
> +++ b/net/ipv6/udp_offload.c
> @@ -111,6 +111,16 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
> 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)
> {
> @@ -135,7 +145,9 @@ 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;
> + sk = static_branch_unlikely(&udpv6_encap_needed_key) ?
> + udp6_gro_lookup_skb(skb, uh->source, uh->dest) :
> + NULL;
> pp = udp_gro_receive(head, skb, uh, sk);
> rcu_read_unlock();
> return pp;
> --
> 2.29.2
Al