android_kernel_xiaomi_sm7250/net/ipv4/udp_offload.c
Daniel Borkmann e5008f2e91 net: Fix gro aggregation for udp encaps with zero csum
commit 89e5c58fc1e2857ccdaae506fb8bc5fed57ee063 upstream.

We noticed a GRO issue for UDP-based encaps such as vxlan/geneve when the
csum for the UDP header itself is 0. In that case, GRO aggregation does
not take place on the phys dev, but instead is deferred to the vxlan/geneve
driver (see trace below).

The reason is essentially that GRO aggregation bails out in udp_gro_receive()
for such case when drivers marked the skb with CHECKSUM_UNNECESSARY (ice, i40e,
others) where for non-zero csums 2abb7cdc0d ("udp: Add support for doing
checksum unnecessary conversion") promotes those skbs to CHECKSUM_COMPLETE
and napi context has csum_valid set. This is however not the case for zero
UDP csum (here: csum_cnt is still 0 and csum_valid continues to be false).

At the same time 57c67ff4bd ("udp: additional GRO support") added matches
on !uh->check ^ !uh2->check as part to determine candidates for aggregation,
so it certainly is expected to handle zero csums in udp_gro_receive(). The
purpose of the check added via 662880f442 ("net: Allow GRO to use and set
levels of checksum unnecessary") seems to catch bad csum and stop aggregation
right away.

One way to fix aggregation in the zero case is to only perform the !csum_valid
check in udp_gro_receive() if uh->check is infact non-zero.

Before:

  [...]
  swapper     0 [008]   731.946506: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497100400 len=1500   (1)
  swapper     0 [008]   731.946507: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497100200 len=1500
  swapper     0 [008]   731.946507: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497101100 len=1500
  swapper     0 [008]   731.946508: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497101700 len=1500
  swapper     0 [008]   731.946508: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497101b00 len=1500
  swapper     0 [008]   731.946508: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497100600 len=1500
  swapper     0 [008]   731.946508: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497100f00 len=1500
  swapper     0 [008]   731.946509: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497100a00 len=1500
  swapper     0 [008]   731.946516: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497100500 len=1500
  swapper     0 [008]   731.946516: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497100700 len=1500
  swapper     0 [008]   731.946516: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497101d00 len=1500   (2)
  swapper     0 [008]   731.946517: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497101000 len=1500
  swapper     0 [008]   731.946517: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497101c00 len=1500
  swapper     0 [008]   731.946517: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497101400 len=1500
  swapper     0 [008]   731.946518: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497100e00 len=1500
  swapper     0 [008]   731.946518: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497101600 len=1500
  swapper     0 [008]   731.946521: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497100800 len=774
  swapper     0 [008]   731.946530: net:netif_receive_skb: dev=test_vxlan skbaddr=0xffff966497100400 len=14032 (1)
  swapper     0 [008]   731.946530: net:netif_receive_skb: dev=test_vxlan skbaddr=0xffff966497101d00 len=9112  (2)
  [...]

  # netperf -H 10.55.10.4 -t TCP_STREAM -l 20
  MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.55.10.4 () port 0 AF_INET : demo
  Recv   Send    Send
  Socket Socket  Message  Elapsed
  Size   Size    Size     Time     Throughput
  bytes  bytes   bytes    secs.    10^6bits/sec

   87380  16384  16384    20.01    13129.24

After:

  [...]
  swapper     0 [026]   521.862641: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff93ab0d479000 len=11286 (1)
  swapper     0 [026]   521.862643: net:netif_receive_skb: dev=test_vxlan skbaddr=0xffff93ab0d479000 len=11236 (1)
  swapper     0 [026]   521.862650: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff93ab0d478500 len=2898  (2)
  swapper     0 [026]   521.862650: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff93ab0d479f00 len=8490  (3)
  swapper     0 [026]   521.862653: net:netif_receive_skb: dev=test_vxlan skbaddr=0xffff93ab0d478500 len=2848  (2)
  swapper     0 [026]   521.862653: net:netif_receive_skb: dev=test_vxlan skbaddr=0xffff93ab0d479f00 len=8440  (3)
  [...]

  # netperf -H 10.55.10.4 -t TCP_STREAM -l 20
  MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.55.10.4 () port 0 AF_INET : demo
  Recv   Send    Send
  Socket Socket  Message  Elapsed
  Size   Size    Size     Time     Throughput
  bytes  bytes   bytes    secs.    10^6bits/sec

   87380  16384  16384    20.01    24576.53

Fixes: 57c67ff4bd ("udp: additional GRO support")
Fixes: 662880f442 ("net: Allow GRO to use and set levels of checksum unnecessary")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jesse Brandeburg <jesse.brandeburg@intel.com>
Cc: Tom Herbert <tom@herbertland.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/r/20210226212248.8300-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2021-03-17 16:43:42 +01:00

492 lines
13 KiB
C

/*
* IPV4 GSO/GRO offload support
* Linux INET implementation
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
* UDPv4 GSO support
*/
#include <linux/skbuff.h>
#include <net/udp.h>
#include <net/protocol.h>
static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
netdev_features_t features,
struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb,
netdev_features_t features),
__be16 new_protocol, bool is_ipv6)
{
int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb);
bool remcsum, need_csum, offload_csum, gso_partial;
struct sk_buff *segs = ERR_PTR(-EINVAL);
struct udphdr *uh = udp_hdr(skb);
u16 mac_offset = skb->mac_header;
__be16 protocol = skb->protocol;
u16 mac_len = skb->mac_len;
int udp_offset, outer_hlen;
__wsum partial;
bool need_ipsec;
if (unlikely(!pskb_may_pull(skb, tnl_hlen)))
goto out;
/* Adjust partial header checksum to negate old length.
* We cannot rely on the value contained in uh->len as it is
* possible that the actual value exceeds the boundaries of the
* 16 bit length field due to the header being added outside of an
* IP or IPv6 frame that was already limited to 64K - 1.
*/
if (skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL)
partial = (__force __wsum)uh->len;
else
partial = (__force __wsum)htonl(skb->len);
partial = csum_sub(csum_unfold(uh->check), partial);
/* setup inner skb. */
skb->encapsulation = 0;
SKB_GSO_CB(skb)->encap_level = 0;
__skb_pull(skb, tnl_hlen);
skb_reset_mac_header(skb);
skb_set_network_header(skb, skb_inner_network_offset(skb));
skb->mac_len = skb_inner_network_offset(skb);
skb->protocol = new_protocol;
need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM);
skb->encap_hdr_csum = need_csum;
remcsum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TUNNEL_REMCSUM);
skb->remcsum_offload = remcsum;
need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb));
/* Try to offload checksum if possible */
offload_csum = !!(need_csum &&
!need_ipsec &&
(skb->dev->features &
(is_ipv6 ? (NETIF_F_HW_CSUM | NETIF_F_IPV6_CSUM) :
(NETIF_F_HW_CSUM | NETIF_F_IP_CSUM))));
features &= skb->dev->hw_enc_features;
/* The only checksum offload we care about from here on out is the
* outer one so strip the existing checksum feature flags and
* instead set the flag based on our outer checksum offload value.
*/
if (remcsum) {
features &= ~NETIF_F_CSUM_MASK;
if (!need_csum || offload_csum)
features |= NETIF_F_HW_CSUM;
}
/* segment inner packet. */
segs = gso_inner_segment(skb, features);
if (IS_ERR_OR_NULL(segs)) {
skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset,
mac_len);
goto out;
}
gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL);
outer_hlen = skb_tnl_header_len(skb);
udp_offset = outer_hlen - tnl_hlen;
skb = segs;
do {
unsigned int len;
if (remcsum)
skb->ip_summed = CHECKSUM_NONE;
/* Set up inner headers if we are offloading inner checksum */
if (skb->ip_summed == CHECKSUM_PARTIAL) {
skb_reset_inner_headers(skb);
skb->encapsulation = 1;
}
skb->mac_len = mac_len;
skb->protocol = protocol;
__skb_push(skb, outer_hlen);
skb_reset_mac_header(skb);
skb_set_network_header(skb, mac_len);
skb_set_transport_header(skb, udp_offset);
len = skb->len - udp_offset;
uh = udp_hdr(skb);
/* If we are only performing partial GSO the inner header
* will be using a length value equal to only one MSS sized
* segment instead of the entire frame.
*/
if (gso_partial && skb_is_gso(skb)) {
uh->len = htons(skb_shinfo(skb)->gso_size +
SKB_GSO_CB(skb)->data_offset +
skb->head - (unsigned char *)uh);
} else {
uh->len = htons(len);
}
if (!need_csum)
continue;
uh->check = ~csum_fold(csum_add(partial,
(__force __wsum)htonl(len)));
if (skb->encapsulation || !offload_csum) {
uh->check = gso_make_checksum(skb, ~uh->check);
if (uh->check == 0)
uh->check = CSUM_MANGLED_0;
} else {
skb->ip_summed = CHECKSUM_PARTIAL;
skb->csum_start = skb_transport_header(skb) - skb->head;
skb->csum_offset = offsetof(struct udphdr, check);
}
} while ((skb = skb->next));
out:
return segs;
}
struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
netdev_features_t features,
bool is_ipv6)
{
__be16 protocol = skb->protocol;
const struct net_offload **offloads;
const struct net_offload *ops;
struct sk_buff *segs = ERR_PTR(-EINVAL);
struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb,
netdev_features_t features);
rcu_read_lock();
switch (skb->inner_protocol_type) {
case ENCAP_TYPE_ETHER:
protocol = skb->inner_protocol;
gso_inner_segment = skb_mac_gso_segment;
break;
case ENCAP_TYPE_IPPROTO:
offloads = is_ipv6 ? inet6_offloads : inet_offloads;
ops = rcu_dereference(offloads[skb->inner_ipproto]);
if (!ops || !ops->callbacks.gso_segment)
goto out_unlock;
gso_inner_segment = ops->callbacks.gso_segment;
break;
default:
goto out_unlock;
}
segs = __skb_udp_tunnel_segment(skb, features, gso_inner_segment,
protocol, is_ipv6);
out_unlock:
rcu_read_unlock();
return segs;
}
EXPORT_SYMBOL(skb_udp_tunnel_segment);
struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
netdev_features_t features)
{
struct sock *sk = gso_skb->sk;
unsigned int sum_truesize = 0;
struct sk_buff *segs, *seg;
struct udphdr *uh;
unsigned int mss;
bool copy_dtor;
__sum16 check;
__be16 newlen;
mss = skb_shinfo(gso_skb)->gso_size;
if (gso_skb->len <= sizeof(*uh) + mss)
return ERR_PTR(-EINVAL);
skb_pull(gso_skb, sizeof(*uh));
/* clear destructor to avoid skb_segment assigning it to tail */
copy_dtor = gso_skb->destructor == sock_wfree;
if (copy_dtor)
gso_skb->destructor = NULL;
segs = skb_segment(gso_skb, features);
if (unlikely(IS_ERR_OR_NULL(segs))) {
if (copy_dtor)
gso_skb->destructor = sock_wfree;
return segs;
}
/* GSO partial and frag_list segmentation only requires splitting
* the frame into an MSS multiple and possibly a remainder, both
* cases return a GSO skb. So update the mss now.
*/
if (skb_is_gso(segs))
mss *= skb_shinfo(segs)->gso_segs;
seg = segs;
uh = udp_hdr(seg);
/* preserve TX timestamp flags and TS key for first segment */
skb_shinfo(seg)->tskey = skb_shinfo(gso_skb)->tskey;
skb_shinfo(seg)->tx_flags |=
(skb_shinfo(gso_skb)->tx_flags & SKBTX_ANY_TSTAMP);
/* compute checksum adjustment based on old length versus new */
newlen = htons(sizeof(*uh) + mss);
check = csum16_add(csum16_sub(uh->check, uh->len), newlen);
for (;;) {
if (copy_dtor) {
seg->destructor = sock_wfree;
seg->sk = sk;
sum_truesize += seg->truesize;
}
if (!seg->next)
break;
uh->len = newlen;
uh->check = check;
if (seg->ip_summed == CHECKSUM_PARTIAL)
gso_reset_checksum(seg, ~check);
else
uh->check = gso_make_checksum(seg, ~check) ? :
CSUM_MANGLED_0;
seg = seg->next;
uh = udp_hdr(seg);
}
/* last packet can be partial gso_size, account for that in checksum */
newlen = htons(skb_tail_pointer(seg) - skb_transport_header(seg) +
seg->data_len);
check = csum16_add(csum16_sub(uh->check, uh->len), newlen);
uh->len = newlen;
uh->check = check;
if (seg->ip_summed == CHECKSUM_PARTIAL)
gso_reset_checksum(seg, ~check);
else
uh->check = gso_make_checksum(seg, ~check) ? : CSUM_MANGLED_0;
/* update refcount for the packet */
if (copy_dtor) {
int delta = sum_truesize - gso_skb->truesize;
/* In some pathological cases, delta can be negative.
* We need to either use refcount_add() or refcount_sub_and_test()
*/
if (likely(delta >= 0))
refcount_add(delta, &sk->sk_wmem_alloc);
else
WARN_ON_ONCE(refcount_sub_and_test(-delta, &sk->sk_wmem_alloc));
}
return segs;
}
EXPORT_SYMBOL_GPL(__udp_gso_segment);
static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
unsigned int mss;
__wsum csum;
struct udphdr *uh;
struct iphdr *iph;
if (skb->encapsulation &&
(skb_shinfo(skb)->gso_type &
(SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))) {
segs = skb_udp_tunnel_segment(skb, features, false);
goto out;
}
if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_UDP | SKB_GSO_UDP_L4)))
goto out;
if (!pskb_may_pull(skb, sizeof(struct udphdr)))
goto out;
if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
return __udp_gso_segment(skb, features);
mss = skb_shinfo(skb)->gso_size;
if (unlikely(skb->len <= mss))
goto out;
/* Do software UFO. Complete and fill in the UDP checksum as
* HW cannot do checksum of UDP packets sent as multiple
* IP fragments.
*/
uh = udp_hdr(skb);
iph = ip_hdr(skb);
uh->check = 0;
csum = skb_checksum(skb, 0, skb->len, 0);
uh->check = udp_v4_check(skb->len, iph->saddr, iph->daddr, csum);
if (uh->check == 0)
uh->check = CSUM_MANGLED_0;
skb->ip_summed = CHECKSUM_UNNECESSARY;
/* If there is no outer header we can fake a checksum offload
* due to the fact that we have already done the checksum in
* software prior to segmenting the frame.
*/
if (!skb->encap_hdr_csum)
features |= NETIF_F_HW_CSUM;
/* Fragment the skb. IP headers of the fragments are updated in
* inet_gso_segment()
*/
segs = skb_segment(skb, features);
out:
return segs;
}
struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
struct udphdr *uh, udp_lookup_t lookup)
{
struct sk_buff *pp = NULL;
struct sk_buff *p;
struct udphdr *uh2;
unsigned int off = skb_gro_offset(skb);
int flush = 1;
struct sock *sk;
if (NAPI_GRO_CB(skb)->encap_mark ||
(uh->check && skb->ip_summed != CHECKSUM_PARTIAL &&
NAPI_GRO_CB(skb)->csum_cnt == 0 &&
!NAPI_GRO_CB(skb)->csum_valid))
goto out;
/* mark that this skb passed once through the tunnel gro layer */
NAPI_GRO_CB(skb)->encap_mark = 1;
rcu_read_lock();
sk = (*lookup)(skb, uh->source, uh->dest);
if (sk && udp_sk(sk)->gro_receive)
goto unflush;
goto out_unlock;
unflush:
flush = 0;
list_for_each_entry(p, head, list) {
if (!NAPI_GRO_CB(p)->same_flow)
continue;
uh2 = (struct udphdr *)(p->data + off);
/* Match ports and either checksums are either both zero
* or nonzero.
*/
if ((*(u32 *)&uh->source != *(u32 *)&uh2->source) ||
(!uh->check ^ !uh2->check)) {
NAPI_GRO_CB(p)->same_flow = 0;
continue;
}
}
skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */
skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
pp = call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb);
out_unlock:
rcu_read_unlock();
out:
skb_gro_flush_final(skb, pp, flush);
return pp;
}
EXPORT_SYMBOL(udp_gro_receive);
static struct sk_buff *udp4_gro_receive(struct list_head *head,
struct sk_buff *skb)
{
struct udphdr *uh = udp_gro_udphdr(skb);
if (unlikely(!uh))
goto flush;
/* Don't bother verifying checksum if we're going to flush anyway. */
if (NAPI_GRO_CB(skb)->flush)
goto skip;
if (skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check,
inet_gro_compute_pseudo))
goto flush;
else if (uh->check)
skb_gro_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
inet_gro_compute_pseudo);
skip:
NAPI_GRO_CB(skb)->is_ipv6 = 0;
return udp_gro_receive(head, skb, uh, udp4_lib_lookup_skb);
flush:
NAPI_GRO_CB(skb)->flush = 1;
return NULL;
}
int udp_gro_complete(struct sk_buff *skb, int nhoff,
udp_lookup_t lookup)
{
__be16 newlen = htons(skb->len - nhoff);
struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
int err = -ENOSYS;
struct sock *sk;
uh->len = newlen;
/* Set encapsulation before calling into inner gro_complete() functions
* to make them set up the inner offsets.
*/
skb->encapsulation = 1;
rcu_read_lock();
sk = (*lookup)(skb, uh->source, uh->dest);
if (sk && udp_sk(sk)->gro_complete)
err = udp_sk(sk)->gro_complete(sk, skb,
nhoff + sizeof(struct udphdr));
rcu_read_unlock();
if (skb->remcsum_offload)
skb_shinfo(skb)->gso_type |= SKB_GSO_TUNNEL_REMCSUM;
return err;
}
EXPORT_SYMBOL(udp_gro_complete);
static int udp4_gro_complete(struct sk_buff *skb, int nhoff)
{
const struct iphdr *iph = ip_hdr(skb);
struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
if (uh->check) {
skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
uh->check = ~udp_v4_check(skb->len - nhoff, iph->saddr,
iph->daddr, 0);
} else {
skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL;
}
return udp_gro_complete(skb, nhoff, udp4_lib_lookup_skb);
}
static const struct net_offload udpv4_offload = {
.callbacks = {
.gso_segment = udp4_ufo_fragment,
.gro_receive = udp4_gro_receive,
.gro_complete = udp4_gro_complete,
},
};
int __init udpv4_offload_init(void)
{
return inet_add_offload(&udpv4_offload, IPPROTO_UDP);
}