linux/net/ipv4/udp_offload.c

768 lines
21 KiB
C
Raw Permalink Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* IPV4 GSO/GRO offload support
* Linux INET implementation
*
* UDPv4 GSO support
*/
#include <linux/skbuff.h>
#include <net/gro.h>
#include <net/gso.h>
#include <net/udp.h>
#include <net/protocol.h>
#include <net/inet_common.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_set_transport_header(skb, skb_inner_transport_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;
if (need_csum)
features &= ~NETIF_F_SCTP_CRC;
/* 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)
{
fou: remove sparse errors We need to add __rcu qualifier to avoid these errors: net/ipv4/fou.c:250:18: warning: incorrect type in assignment (different address spaces) net/ipv4/fou.c:250:18: expected struct net_offload const **offloads net/ipv4/fou.c:250:18: got struct net_offload const [noderef] __rcu ** net/ipv4/fou.c:251:15: error: incompatible types in comparison expression (different address spaces): net/ipv4/fou.c:251:15: struct net_offload const [noderef] __rcu * net/ipv4/fou.c:251:15: struct net_offload const * net/ipv4/fou.c:272:18: warning: incorrect type in assignment (different address spaces) net/ipv4/fou.c:272:18: expected struct net_offload const **offloads net/ipv4/fou.c:272:18: got struct net_offload const [noderef] __rcu ** net/ipv4/fou.c:273:15: error: incompatible types in comparison expression (different address spaces): net/ipv4/fou.c:273:15: struct net_offload const [noderef] __rcu * net/ipv4/fou.c:273:15: struct net_offload const * net/ipv4/fou.c:442:18: warning: incorrect type in assignment (different address spaces) net/ipv4/fou.c:442:18: expected struct net_offload const **offloads net/ipv4/fou.c:442:18: got struct net_offload const [noderef] __rcu ** net/ipv4/fou.c:443:15: error: incompatible types in comparison expression (different address spaces): net/ipv4/fou.c:443:15: struct net_offload const [noderef] __rcu * net/ipv4/fou.c:443:15: struct net_offload const * net/ipv4/fou.c:489:18: warning: incorrect type in assignment (different address spaces) net/ipv4/fou.c:489:18: expected struct net_offload const **offloads net/ipv4/fou.c:489:18: got struct net_offload const [noderef] __rcu ** net/ipv4/fou.c:490:15: error: incompatible types in comparison expression (different address spaces): net/ipv4/fou.c:490:15: struct net_offload const [noderef] __rcu * net/ipv4/fou.c:490:15: struct net_offload const * net/ipv4/udp_offload.c:170:26: warning: incorrect type in assignment (different address spaces) net/ipv4/udp_offload.c:170:26: expected struct net_offload const **offloads net/ipv4/udp_offload.c:170:26: got struct net_offload const [noderef] __rcu ** net/ipv4/udp_offload.c:171:23: error: incompatible types in comparison expression (different address spaces): net/ipv4/udp_offload.c:171:23: struct net_offload const [noderef] __rcu * net/ipv4/udp_offload.c:171:23: struct net_offload const * Fixes: efc98d08e1ec ("fou: eliminate IPv4,v6 specific GRO functions") Fixes: 8bce6d7d0d1e ("udp: Generalize skb_udp_segment") Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-08-31 03:26:08 +00:00
const struct net_offload __rcu **offloads;
__be16 protocol = skb->protocol;
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);
static void __udpv4_gso_segment_csum(struct sk_buff *seg,
__be32 *oldip, __be32 *newip,
__be16 *oldport, __be16 *newport)
{
struct udphdr *uh;
struct iphdr *iph;
if (*oldip == *newip && *oldport == *newport)
return;
uh = udp_hdr(seg);
iph = ip_hdr(seg);
if (uh->check) {
inet_proto_csum_replace4(&uh->check, seg, *oldip, *newip,
true);
inet_proto_csum_replace2(&uh->check, seg, *oldport, *newport,
false);
if (!uh->check)
uh->check = CSUM_MANGLED_0;
}
*oldport = *newport;
csum_replace4(&iph->check, *oldip, *newip);
*oldip = *newip;
}
static struct sk_buff *__udpv4_gso_segment_list_csum(struct sk_buff *segs)
{
struct sk_buff *seg;
struct udphdr *uh, *uh2;
struct iphdr *iph, *iph2;
seg = segs;
uh = udp_hdr(seg);
iph = ip_hdr(seg);
if ((udp_hdr(seg)->dest == udp_hdr(seg->next)->dest) &&
(udp_hdr(seg)->source == udp_hdr(seg->next)->source) &&
(ip_hdr(seg)->daddr == ip_hdr(seg->next)->daddr) &&
(ip_hdr(seg)->saddr == ip_hdr(seg->next)->saddr))
return segs;
while ((seg = seg->next)) {
uh2 = udp_hdr(seg);
iph2 = ip_hdr(seg);
__udpv4_gso_segment_csum(seg,
&iph2->saddr, &iph->saddr,
&uh2->source, &uh->source);
__udpv4_gso_segment_csum(seg,
&iph2->daddr, &iph->daddr,
&uh2->dest, &uh->dest);
}
return segs;
}
static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb,
netdev_features_t features,
bool is_ipv6)
{
unsigned int mss = skb_shinfo(skb)->gso_size;
skb = skb_segment_list(skb, features, skb_mac_header_len(skb));
if (IS_ERR(skb))
return skb;
udp_hdr(skb)->len = htons(sizeof(struct udphdr) + mss);
return is_ipv6 ? skb : __udpv4_gso_segment_list_csum(skb);
}
struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
netdev_features_t features, bool is_ipv6)
{
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);
net: drop bad gso csum_start and offset in virtio_net_hdr Tighten csum_start and csum_offset checks in virtio_net_hdr_to_skb for GSO packets. The function already checks that a checksum requested with VIRTIO_NET_HDR_F_NEEDS_CSUM is in skb linear. But for GSO packets this might not hold for segs after segmentation. Syzkaller demonstrated to reach this warning in skb_checksum_help offset = skb_checksum_start_offset(skb); ret = -EINVAL; if (WARN_ON_ONCE(offset >= skb_headlen(skb))) By injecting a TSO packet: WARNING: CPU: 1 PID: 3539 at net/core/dev.c:3284 skb_checksum_help+0x3d0/0x5b0 ip_do_fragment+0x209/0x1b20 net/ipv4/ip_output.c:774 ip_finish_output_gso net/ipv4/ip_output.c:279 [inline] __ip_finish_output+0x2bd/0x4b0 net/ipv4/ip_output.c:301 iptunnel_xmit+0x50c/0x930 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x2296/0x2c70 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x759/0xa60 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4850 [inline] netdev_start_xmit include/linux/netdevice.h:4864 [inline] xmit_one net/core/dev.c:3595 [inline] dev_hard_start_xmit+0x261/0x8c0 net/core/dev.c:3611 __dev_queue_xmit+0x1b97/0x3c90 net/core/dev.c:4261 packet_snd net/packet/af_packet.c:3073 [inline] The geometry of the bad input packet at tcp_gso_segment: [ 52.003050][ T8403] skb len=12202 headroom=244 headlen=12093 tailroom=0 [ 52.003050][ T8403] mac=(168,24) mac_len=24 net=(192,52) trans=244 [ 52.003050][ T8403] shinfo(txflags=0 nr_frags=1 gso(size=1552 type=3 segs=0)) [ 52.003050][ T8403] csum(0x60000c7 start=199 offset=1536 ip_summed=3 complete_sw=0 valid=0 level=0) Mitigate with stricter input validation. csum_offset: for GSO packets, deduce the correct value from gso_type. This is already done for USO. Extend it to TSO. Let UFO be: udp[46]_ufo_fragment ignores these fields and always computes the checksum in software. csum_start: finding the real offset requires parsing to the transport header. Do not add a parser, use existing segmentation parsing. Thanks to SKB_GSO_DODGY, that also catches bad packets that are hw offloaded. Again test both TSO and USO. Do not test UFO for the above reason, and do not test UDP tunnel offload. GSO packet are almost always CHECKSUM_PARTIAL. USO packets may be CHECKSUM_NONE since commit 10154dbded6d6 ("udp: Allow GSO transmit from devices with no checksum offload"), but then still these fields are initialized correctly in udp4_hwcsum/udp6_hwcsum_outgoing. So no need to test for ip_summed == CHECKSUM_PARTIAL first. This revises an existing fix mentioned in the Fixes tag, which broke small packets with GSO offload, as detected by kselftests. Link: https://syzkaller.appspot.com/bug?extid=e1db31216c789f552871 Link: https://lore.kernel.org/netdev/20240723223109.2196886-1-kuba@kernel.org Fixes: e269d79c7d35 ("net: missing check virtio") Cc: stable@vger.kernel.org Signed-off-by: Willem de Bruijn <willemb@google.com> Link: https://patch.msgid.link/20240729201108.1615114-1-willemdebruijn.kernel@gmail.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-07-29 20:10:12 +00:00
if (unlikely(skb_checksum_start(gso_skb) !=
skb_transport_header(gso_skb) &&
!(skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST)))
net: drop bad gso csum_start and offset in virtio_net_hdr Tighten csum_start and csum_offset checks in virtio_net_hdr_to_skb for GSO packets. The function already checks that a checksum requested with VIRTIO_NET_HDR_F_NEEDS_CSUM is in skb linear. But for GSO packets this might not hold for segs after segmentation. Syzkaller demonstrated to reach this warning in skb_checksum_help offset = skb_checksum_start_offset(skb); ret = -EINVAL; if (WARN_ON_ONCE(offset >= skb_headlen(skb))) By injecting a TSO packet: WARNING: CPU: 1 PID: 3539 at net/core/dev.c:3284 skb_checksum_help+0x3d0/0x5b0 ip_do_fragment+0x209/0x1b20 net/ipv4/ip_output.c:774 ip_finish_output_gso net/ipv4/ip_output.c:279 [inline] __ip_finish_output+0x2bd/0x4b0 net/ipv4/ip_output.c:301 iptunnel_xmit+0x50c/0x930 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x2296/0x2c70 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x759/0xa60 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4850 [inline] netdev_start_xmit include/linux/netdevice.h:4864 [inline] xmit_one net/core/dev.c:3595 [inline] dev_hard_start_xmit+0x261/0x8c0 net/core/dev.c:3611 __dev_queue_xmit+0x1b97/0x3c90 net/core/dev.c:4261 packet_snd net/packet/af_packet.c:3073 [inline] The geometry of the bad input packet at tcp_gso_segment: [ 52.003050][ T8403] skb len=12202 headroom=244 headlen=12093 tailroom=0 [ 52.003050][ T8403] mac=(168,24) mac_len=24 net=(192,52) trans=244 [ 52.003050][ T8403] shinfo(txflags=0 nr_frags=1 gso(size=1552 type=3 segs=0)) [ 52.003050][ T8403] csum(0x60000c7 start=199 offset=1536 ip_summed=3 complete_sw=0 valid=0 level=0) Mitigate with stricter input validation. csum_offset: for GSO packets, deduce the correct value from gso_type. This is already done for USO. Extend it to TSO. Let UFO be: udp[46]_ufo_fragment ignores these fields and always computes the checksum in software. csum_start: finding the real offset requires parsing to the transport header. Do not add a parser, use existing segmentation parsing. Thanks to SKB_GSO_DODGY, that also catches bad packets that are hw offloaded. Again test both TSO and USO. Do not test UFO for the above reason, and do not test UDP tunnel offload. GSO packet are almost always CHECKSUM_PARTIAL. USO packets may be CHECKSUM_NONE since commit 10154dbded6d6 ("udp: Allow GSO transmit from devices with no checksum offload"), but then still these fields are initialized correctly in udp4_hwcsum/udp6_hwcsum_outgoing. So no need to test for ip_summed == CHECKSUM_PARTIAL first. This revises an existing fix mentioned in the Fixes tag, which broke small packets with GSO offload, as detected by kselftests. Link: https://syzkaller.appspot.com/bug?extid=e1db31216c789f552871 Link: https://lore.kernel.org/netdev/20240723223109.2196886-1-kuba@kernel.org Fixes: e269d79c7d35 ("net: missing check virtio") Cc: stable@vger.kernel.org Signed-off-by: Willem de Bruijn <willemb@google.com> Link: https://patch.msgid.link/20240729201108.1615114-1-willemdebruijn.kernel@gmail.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-07-29 20:10:12 +00:00
return ERR_PTR(-EINVAL);
udp: Fall back to software USO if IPv6 extension headers are present In commit 10154dbded6d ("udp: Allow GSO transmit from devices with no checksum offload") we have intentionally allowed UDP GSO packets marked CHECKSUM_NONE to pass to the GSO stack, so that they can be segmented and checksummed by a software fallback when the egress device lacks these features. What was not taken into consideration is that a CHECKSUM_NONE skb can be handed over to the GSO stack also when the egress device advertises the tx-udp-segmentation / NETIF_F_GSO_UDP_L4 feature. This will happen when there are IPv6 extension headers present, which we check for in __ip6_append_data(). Syzbot has discovered this scenario, producing a warning as below: ip6tnl0: caps=(0x00000006401d7869, 0x00000006401d7869) WARNING: CPU: 0 PID: 5112 at net/core/dev.c:3293 skb_warn_bad_offload+0x166/0x1a0 net/core/dev.c:3291 Modules linked in: CPU: 0 PID: 5112 Comm: syz-executor391 Not tainted 6.10.0-rc7-syzkaller-01603-g80ab5445da62 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 06/07/2024 RIP: 0010:skb_warn_bad_offload+0x166/0x1a0 net/core/dev.c:3291 [...] Call Trace: <TASK> __skb_gso_segment+0x3be/0x4c0 net/core/gso.c:127 skb_gso_segment include/net/gso.h:83 [inline] validate_xmit_skb+0x585/0x1120 net/core/dev.c:3661 __dev_queue_xmit+0x17a4/0x3e90 net/core/dev.c:4415 neigh_output include/net/neighbour.h:542 [inline] ip6_finish_output2+0xffa/0x1680 net/ipv6/ip6_output.c:137 ip6_finish_output+0x41e/0x810 net/ipv6/ip6_output.c:222 ip6_send_skb+0x112/0x230 net/ipv6/ip6_output.c:1958 udp_v6_send_skb+0xbf5/0x1870 net/ipv6/udp.c:1292 udpv6_sendmsg+0x23b3/0x3270 net/ipv6/udp.c:1588 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0xef/0x270 net/socket.c:745 ____sys_sendmsg+0x525/0x7d0 net/socket.c:2585 ___sys_sendmsg net/socket.c:2639 [inline] __sys_sendmmsg+0x3b2/0x740 net/socket.c:2725 __do_sys_sendmmsg net/socket.c:2754 [inline] __se_sys_sendmmsg net/socket.c:2751 [inline] __x64_sys_sendmmsg+0xa0/0xb0 net/socket.c:2751 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f [...] </TASK> We are hitting the bad offload warning because when an egress device is capable of handling segmentation offload requested by skb_shinfo(skb)->gso_type, the chain of gso_segment callbacks won't produce any segment skbs and return NULL. See the skb_gso_ok() branch in {__udp,tcp,sctp}_gso_segment helpers. To fix it, force a fallback to software USO when processing a packet with IPv6 extension headers, since we don't know if these can checksummed by all devices which offer USO. Fixes: 10154dbded6d ("udp: Allow GSO transmit from devices with no checksum offload") Reported-by: syzbot+e15b7e15b8a751a91d9a@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/000000000000e1609a061d5330ce@google.com/ Reviewed-by: Willem de Bruijn <willemb@google.com> Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com> Link: https://patch.msgid.link/20240808-udp-gso-egress-from-tunnel-v4-2-f5c5b4149ab9@cloudflare.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-08-08 09:56:22 +00:00
/* We don't know if egress device can segment and checksum the packet
* when IPv6 extension headers are present. Fall back to software GSO.
*/
if (gso_skb->ip_summed != CHECKSUM_PARTIAL)
features &= ~(NETIF_F_GSO_UDP_L4 | NETIF_F_CSUM_MASK);
if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) {
/* Packet is from an untrusted source, reset gso_segs. */
skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh),
mss);
return NULL;
}
if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST) {
/* Detect modified geometry and pass those to skb_segment. */
if (skb_pagelen(gso_skb) - sizeof(*uh) == skb_shinfo(gso_skb)->gso_size)
return __udp_gso_segment_list(gso_skb, features, is_ipv6);
/* Setup csum, as fraglist skips this in udp4_gro_receive. */
gso_skb->csum_start = skb_transport_header(gso_skb) - gso_skb->head;
gso_skb->csum_offset = offsetof(struct udphdr, check);
gso_skb->ip_summed = CHECKSUM_PARTIAL;
uh = udp_hdr(gso_skb);
if (is_ipv6)
uh->check = ~udp_v6_check(gso_skb->len,
&ipv6_hdr(gso_skb)->saddr,
&ipv6_hdr(gso_skb)->daddr, 0);
else
uh->check = ~udp_v4_check(gso_skb->len,
ip_hdr(gso_skb)->saddr,
ip_hdr(gso_skb)->daddr, 0);
}
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 (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);
net/udp_gso: Allow TX timestamp with UDP GSO Fixes an issue where TX Timestamps are not arriving on the error queue when UDP_SEGMENT CMSG type is combined with CMSG type SO_TIMESTAMPING. This can be illustrated with an updated updgso_bench_tx program which includes the '-T' option to test for this condition. It also introduces the '-P' option which will call poll() before reading the error queue. ./udpgso_bench_tx -4ucTPv -S 1472 -l2 -D 172.16.120.18 poll timeout udp tx: 0 MB/s 1 calls/s 1 msg/s The "poll timeout" message above indicates that TX timestamp never arrived. This patch preserves tx_flags for the first UDP GSO segment. Only the first segment is timestamped, even though in some cases there may be benefital in timestamping both the first and last segment. Factors in deciding on first segment timestamp only: - Timestamping both first and last segmented is not feasible. Hardware can only have one outstanding TS request at a time. - Timestamping last segment may under report network latency of the previous segments. Even though the doorbell is suppressed, the ring producer counter has been incremented. - Timestamping the first segment has the upside in that it reports timestamps from the application's view, e.g. RTT. - Timestamping the first segment has the downside that it may underreport tx host network latency. It appears that we have to pick one or the other. And possibly follow-up with a config flag to choose behavior. v2: Remove tests as noted by Willem de Bruijn <willemb@google.com> Moving tests from net to net-next v3: Update only relevant tx_flag bits as per Willem de Bruijn <willemb@google.com> v4: Update comments and commit message as per Willem de Bruijn <willemb@google.com> Fixes: ee80d1ebe5ba ("udp: add udp gso") Signed-off-by: Fred Klassen <fklassen@appneta.com> Acked-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-17 19:05:07 +00:00
/* 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;
udp: Allow GSO transmit from devices with no checksum offload Today sending a UDP GSO packet from a TUN device results in an EIO error: import fcntl, os, struct from socket import * TUNSETIFF = 0x400454CA IFF_TUN = 0x0001 IFF_NO_PI = 0x1000 UDP_SEGMENT = 103 tun_fd = os.open("/dev/net/tun", os.O_RDWR) ifr = struct.pack("16sH", b"tun0", IFF_TUN | IFF_NO_PI) fcntl.ioctl(tun_fd, TUNSETIFF, ifr) os.system("ip addr add 192.0.2.1/24 dev tun0") os.system("ip link set dev tun0 up") s = socket(AF_INET, SOCK_DGRAM) s.setsockopt(SOL_UDP, UDP_SEGMENT, 1200) s.sendto(b"x" * 3000, ("192.0.2.2", 9)) # EIO This is due to a check in the udp stack if the egress device offers checksum offload. While TUN/TAP devices, by default, don't advertise this capability because it requires support from the TUN/TAP reader. However, the GSO stack has a software fallback for checksum calculation, which we can use. This way we don't force UDP_SEGMENT users to handle the EIO error and implement a segmentation fallback. Lift the restriction so that UDP_SEGMENT can be used with any egress device. We also need to adjust the UDP GSO code to match the GSO stack expectation about ip_summed field, as set in commit 8d63bee643f1 ("net: avoid skb_warn_bad_offload false positives on UFO"). Otherwise we will hit the bad offload check. Users should, however, expect a potential performance impact when batch-sending packets with UDP_SEGMENT without checksum offload on the egress device. In such case the packet payload is read twice: first during the sendmsg syscall when copying data from user memory, and then in the GSO stack for checksum computation. This double memory read can be less efficient than a regular sendmsg where the checksum is calculated during the initial data copy from user memory. Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com> Reviewed-by: Willem de Bruijn <willemb@google.com> Link: https://patch.msgid.link/20240626-linux-udpgso-v2-1-422dfcbd6b48@cloudflare.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-06-26 17:51:26 +00:00
/* On the TX path, CHECKSUM_NONE and CHECKSUM_UNNECESSARY have the same
* meaning. However, check for bad offloads in the GSO stack expects the
* latter, if the checksum was calculated in software. To vouch for the
* segment skbs we actually need to set it on the gso_skb.
*/
if (gso_skb->ip_summed == CHECKSUM_NONE)
gso_skb->ip_summed = CHECKSUM_UNNECESSARY;
/* update refcount for the packet */
udp: avoid refcount_t saturation in __udp_gso_segment() For some reason, Willem thought that the issue we fixed for TCP in commit 7ec318feeed1 ("tcp: gso: avoid refcount_t warning from tcp_gso_segment()") was not relevant for UDP GSO. But syzbot found its way. refcount_t: saturated; leaking memory. WARNING: CPU: 0 PID: 10261 at lib/refcount.c:78 refcount_add_not_zero+0x2d4/0x320 lib/refcount.c:78 Kernel panic - not syncing: panic_on_warn set ... CPU: 0 PID: 10261 Comm: syz-executor5 Not tainted 4.17.0-rc3+ #38 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1b9/0x294 lib/dump_stack.c:113 panic+0x22f/0x4de kernel/panic.c:184 __warn.cold.8+0x163/0x1b3 kernel/panic.c:536 report_bug+0x252/0x2d0 lib/bug.c:186 fixup_bug arch/x86/kernel/traps.c:178 [inline] do_error_trap+0x1de/0x490 arch/x86/kernel/traps.c:296 do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:315 invalid_op+0x14/0x20 arch/x86/entry/entry_64.S:992 RIP: 0010:refcount_add_not_zero+0x2d4/0x320 lib/refcount.c:78 RSP: 0018:ffff880196db6b90 EFLAGS: 00010282 RAX: 0000000000000026 RBX: 00000000ffffff01 RCX: ffffc900040d9000 RDX: 0000000000004a29 RSI: ffffffff8160f6f1 RDI: ffff880196db66f0 RBP: ffff880196db6c78 R08: ffff8801b33d6740 R09: 0000000000000002 R10: ffff8801b33d6740 R11: 0000000000000000 R12: 0000000000000000 R13: 00000000ffffffff R14: ffff880196db6c50 R15: 0000000000020101 refcount_add+0x1b/0x70 lib/refcount.c:102 __udp_gso_segment+0xaa5/0xee0 net/ipv4/udp_offload.c:272 udp4_ufo_fragment+0x592/0x7a0 net/ipv4/udp_offload.c:301 inet_gso_segment+0x639/0x12b0 net/ipv4/af_inet.c:1342 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792 __skb_gso_segment+0x3bb/0x870 net/core/dev.c:2865 skb_gso_segment include/linux/netdevice.h:4050 [inline] validate_xmit_skb+0x54d/0xd90 net/core/dev.c:3122 __dev_queue_xmit+0xbf8/0x34c0 net/core/dev.c:3579 dev_queue_xmit+0x17/0x20 net/core/dev.c:3620 neigh_direct_output+0x15/0x20 net/core/neighbour.c:1401 neigh_output include/net/neighbour.h:483 [inline] ip_finish_output2+0xa5f/0x1840 net/ipv4/ip_output.c:229 ip_finish_output+0x828/0xf80 net/ipv4/ip_output.c:317 NF_HOOK_COND include/linux/netfilter.h:277 [inline] ip_output+0x21b/0x850 net/ipv4/ip_output.c:405 dst_output include/net/dst.h:444 [inline] ip_local_out+0xc5/0x1b0 net/ipv4/ip_output.c:124 ip_send_skb+0x40/0xe0 net/ipv4/ip_output.c:1434 udp_send_skb.isra.37+0x5eb/0x1000 net/ipv4/udp.c:825 udp_push_pending_frames+0x5c/0xf0 net/ipv4/udp.c:853 udp_v6_push_pending_frames+0x380/0x3e0 net/ipv6/udp.c:1105 udp_lib_setsockopt+0x59a/0x600 net/ipv4/udp.c:2403 udpv6_setsockopt+0x95/0xa0 net/ipv6/udp.c:1447 sock_common_setsockopt+0x9a/0xe0 net/core/sock.c:3046 __sys_setsockopt+0x1bd/0x390 net/socket.c:1903 __do_sys_setsockopt net/socket.c:1914 [inline] __se_sys_setsockopt net/socket.c:1911 [inline] __x64_sys_setsockopt+0xbe/0x150 net/socket.c:1911 do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x49/0xbe Fixes: ad405857b174 ("udp: better wmem accounting on gso") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Willem de Bruijn <willemb@google.com> Cc: Alexander Duyck <alexander.h.duyck@intel.com> Reported-by: syzbot <syzkaller@googlegroups.com> Acked-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-11 02:07:13 +00:00
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);
net: accept UFO datagrams from tuntap and packet Tuntap and similar devices can inject GSO packets. Accept type VIRTIO_NET_HDR_GSO_UDP, even though not generating UFO natively. Processes are expected to use feature negotiation such as TUNSETOFFLOAD to detect supported offload types and refrain from injecting other packets. This process breaks down with live migration: guest kernels do not renegotiate flags, so destination hosts need to expose all features that the source host does. Partially revert the UFO removal from 182e0b6b5846~1..d9d30adf5677. This patch introduces nearly(*) no new code to simplify verification. It brings back verbatim tuntap UFO negotiation, VIRTIO_NET_HDR_GSO_UDP insertion and software UFO segmentation. It does not reinstate protocol stack support, hardware offload (NETIF_F_UFO), SKB_GSO_UDP tunneling in SKB_GSO_SOFTWARE or reception of VIRTIO_NET_HDR_GSO_UDP packets in tuntap. To support SKB_GSO_UDP reappearing in the stack, also reinstate logic in act_csum and openvswitch. Achieve equivalence with v4.13 HEAD by squashing in commit 939912216fa8 ("net: skb_needs_check() removes CHECKSUM_UNNECESSARY check for tx.") and reverting commit 8d63bee643f1 ("net: avoid skb_warn_bad_offload false positives on UFO"). (*) To avoid having to bring back skb_shinfo(skb)->ip6_frag_id, ipv6_proxy_select_ident is changed to return a __be32 and this is assigned directly to the frag_hdr. Also, SKB_GSO_UDP is inserted at the end of the enum to minimize code churn. Tested Booted a v4.13 guest kernel with QEMU. On a host kernel before this patch `ethtool -k eth0` shows UFO disabled. After the patch, it is enabled, same as on a v4.13 host kernel. A UFO packet sent from the guest appears on the tap device: host: nc -l -p -u 8000 & tcpdump -n -i tap0 guest: dd if=/dev/zero of=payload.txt bs=1 count=2000 nc -u 192.16.1.1 8000 < payload.txt Direct tap to tap transmission of VIRTIO_NET_HDR_GSO_UDP succeeds, packets arriving fragmented: ./with_tap_pair.sh ./tap_send_ufo tap0 tap1 (from https://github.com/wdebruij/kerneltools/tree/master/tests) Changes v1 -> v2 - simplified set_offload change (review comment) - documented test procedure Link: http://lkml.kernel.org/r/<CAF=yD-LuUeDuL9YWPJD9ykOZ0QCjNeznPDr6whqZ9NGMNF12Mw@mail.gmail.com> Fixes: fb652fdfe837 ("macvlan/macvtap: Remove NETIF_F_UFO advertisement.") Reported-by: Michal Kubecek <mkubecek@suse.cz> Signed-off-by: Willem de Bruijn <willemb@google.com> Acked-by: Jason Wang <jasowang@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-11-21 15:22:25 +00:00
static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
net: accept UFO datagrams from tuntap and packet Tuntap and similar devices can inject GSO packets. Accept type VIRTIO_NET_HDR_GSO_UDP, even though not generating UFO natively. Processes are expected to use feature negotiation such as TUNSETOFFLOAD to detect supported offload types and refrain from injecting other packets. This process breaks down with live migration: guest kernels do not renegotiate flags, so destination hosts need to expose all features that the source host does. Partially revert the UFO removal from 182e0b6b5846~1..d9d30adf5677. This patch introduces nearly(*) no new code to simplify verification. It brings back verbatim tuntap UFO negotiation, VIRTIO_NET_HDR_GSO_UDP insertion and software UFO segmentation. It does not reinstate protocol stack support, hardware offload (NETIF_F_UFO), SKB_GSO_UDP tunneling in SKB_GSO_SOFTWARE or reception of VIRTIO_NET_HDR_GSO_UDP packets in tuntap. To support SKB_GSO_UDP reappearing in the stack, also reinstate logic in act_csum and openvswitch. Achieve equivalence with v4.13 HEAD by squashing in commit 939912216fa8 ("net: skb_needs_check() removes CHECKSUM_UNNECESSARY check for tx.") and reverting commit 8d63bee643f1 ("net: avoid skb_warn_bad_offload false positives on UFO"). (*) To avoid having to bring back skb_shinfo(skb)->ip6_frag_id, ipv6_proxy_select_ident is changed to return a __be32 and this is assigned directly to the frag_hdr. Also, SKB_GSO_UDP is inserted at the end of the enum to minimize code churn. Tested Booted a v4.13 guest kernel with QEMU. On a host kernel before this patch `ethtool -k eth0` shows UFO disabled. After the patch, it is enabled, same as on a v4.13 host kernel. A UFO packet sent from the guest appears on the tap device: host: nc -l -p -u 8000 & tcpdump -n -i tap0 guest: dd if=/dev/zero of=payload.txt bs=1 count=2000 nc -u 192.16.1.1 8000 < payload.txt Direct tap to tap transmission of VIRTIO_NET_HDR_GSO_UDP succeeds, packets arriving fragmented: ./with_tap_pair.sh ./tap_send_ufo tap0 tap1 (from https://github.com/wdebruij/kerneltools/tree/master/tests) Changes v1 -> v2 - simplified set_offload change (review comment) - documented test procedure Link: http://lkml.kernel.org/r/<CAF=yD-LuUeDuL9YWPJD9ykOZ0QCjNeznPDr6whqZ9NGMNF12Mw@mail.gmail.com> Fixes: fb652fdfe837 ("macvlan/macvtap: Remove NETIF_F_UFO advertisement.") Reported-by: Michal Kubecek <mkubecek@suse.cz> Signed-off-by: Willem de Bruijn <willemb@google.com> Acked-by: Jason Wang <jasowang@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-11-21 15:22:25 +00:00
unsigned int mss;
__wsum csum;
struct udphdr *uh;
struct iphdr *iph;
if (skb->encapsulation &&
(skb_shinfo(skb)->gso_type &
net: accept UFO datagrams from tuntap and packet Tuntap and similar devices can inject GSO packets. Accept type VIRTIO_NET_HDR_GSO_UDP, even though not generating UFO natively. Processes are expected to use feature negotiation such as TUNSETOFFLOAD to detect supported offload types and refrain from injecting other packets. This process breaks down with live migration: guest kernels do not renegotiate flags, so destination hosts need to expose all features that the source host does. Partially revert the UFO removal from 182e0b6b5846~1..d9d30adf5677. This patch introduces nearly(*) no new code to simplify verification. It brings back verbatim tuntap UFO negotiation, VIRTIO_NET_HDR_GSO_UDP insertion and software UFO segmentation. It does not reinstate protocol stack support, hardware offload (NETIF_F_UFO), SKB_GSO_UDP tunneling in SKB_GSO_SOFTWARE or reception of VIRTIO_NET_HDR_GSO_UDP packets in tuntap. To support SKB_GSO_UDP reappearing in the stack, also reinstate logic in act_csum and openvswitch. Achieve equivalence with v4.13 HEAD by squashing in commit 939912216fa8 ("net: skb_needs_check() removes CHECKSUM_UNNECESSARY check for tx.") and reverting commit 8d63bee643f1 ("net: avoid skb_warn_bad_offload false positives on UFO"). (*) To avoid having to bring back skb_shinfo(skb)->ip6_frag_id, ipv6_proxy_select_ident is changed to return a __be32 and this is assigned directly to the frag_hdr. Also, SKB_GSO_UDP is inserted at the end of the enum to minimize code churn. Tested Booted a v4.13 guest kernel with QEMU. On a host kernel before this patch `ethtool -k eth0` shows UFO disabled. After the patch, it is enabled, same as on a v4.13 host kernel. A UFO packet sent from the guest appears on the tap device: host: nc -l -p -u 8000 & tcpdump -n -i tap0 guest: dd if=/dev/zero of=payload.txt bs=1 count=2000 nc -u 192.16.1.1 8000 < payload.txt Direct tap to tap transmission of VIRTIO_NET_HDR_GSO_UDP succeeds, packets arriving fragmented: ./with_tap_pair.sh ./tap_send_ufo tap0 tap1 (from https://github.com/wdebruij/kerneltools/tree/master/tests) Changes v1 -> v2 - simplified set_offload change (review comment) - documented test procedure Link: http://lkml.kernel.org/r/<CAF=yD-LuUeDuL9YWPJD9ykOZ0QCjNeznPDr6whqZ9NGMNF12Mw@mail.gmail.com> Fixes: fb652fdfe837 ("macvlan/macvtap: Remove NETIF_F_UFO advertisement.") Reported-by: Michal Kubecek <mkubecek@suse.cz> Signed-off-by: Willem de Bruijn <willemb@google.com> Acked-by: Jason Wang <jasowang@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-11-21 15:22:25 +00:00
(SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))) {
segs = skb_udp_tunnel_segment(skb, features, false);
net: accept UFO datagrams from tuntap and packet Tuntap and similar devices can inject GSO packets. Accept type VIRTIO_NET_HDR_GSO_UDP, even though not generating UFO natively. Processes are expected to use feature negotiation such as TUNSETOFFLOAD to detect supported offload types and refrain from injecting other packets. This process breaks down with live migration: guest kernels do not renegotiate flags, so destination hosts need to expose all features that the source host does. Partially revert the UFO removal from 182e0b6b5846~1..d9d30adf5677. This patch introduces nearly(*) no new code to simplify verification. It brings back verbatim tuntap UFO negotiation, VIRTIO_NET_HDR_GSO_UDP insertion and software UFO segmentation. It does not reinstate protocol stack support, hardware offload (NETIF_F_UFO), SKB_GSO_UDP tunneling in SKB_GSO_SOFTWARE or reception of VIRTIO_NET_HDR_GSO_UDP packets in tuntap. To support SKB_GSO_UDP reappearing in the stack, also reinstate logic in act_csum and openvswitch. Achieve equivalence with v4.13 HEAD by squashing in commit 939912216fa8 ("net: skb_needs_check() removes CHECKSUM_UNNECESSARY check for tx.") and reverting commit 8d63bee643f1 ("net: avoid skb_warn_bad_offload false positives on UFO"). (*) To avoid having to bring back skb_shinfo(skb)->ip6_frag_id, ipv6_proxy_select_ident is changed to return a __be32 and this is assigned directly to the frag_hdr. Also, SKB_GSO_UDP is inserted at the end of the enum to minimize code churn. Tested Booted a v4.13 guest kernel with QEMU. On a host kernel before this patch `ethtool -k eth0` shows UFO disabled. After the patch, it is enabled, same as on a v4.13 host kernel. A UFO packet sent from the guest appears on the tap device: host: nc -l -p -u 8000 & tcpdump -n -i tap0 guest: dd if=/dev/zero of=payload.txt bs=1 count=2000 nc -u 192.16.1.1 8000 < payload.txt Direct tap to tap transmission of VIRTIO_NET_HDR_GSO_UDP succeeds, packets arriving fragmented: ./with_tap_pair.sh ./tap_send_ufo tap0 tap1 (from https://github.com/wdebruij/kerneltools/tree/master/tests) Changes v1 -> v2 - simplified set_offload change (review comment) - documented test procedure Link: http://lkml.kernel.org/r/<CAF=yD-LuUeDuL9YWPJD9ykOZ0QCjNeznPDr6whqZ9NGMNF12Mw@mail.gmail.com> Fixes: fb652fdfe837 ("macvlan/macvtap: Remove NETIF_F_UFO advertisement.") Reported-by: Michal Kubecek <mkubecek@suse.cz> Signed-off-by: Willem de Bruijn <willemb@google.com> Acked-by: Jason Wang <jasowang@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-11-21 15:22:25 +00:00
goto out;
}
if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_UDP | SKB_GSO_UDP_L4)))
goto out;
net: accept UFO datagrams from tuntap and packet Tuntap and similar devices can inject GSO packets. Accept type VIRTIO_NET_HDR_GSO_UDP, even though not generating UFO natively. Processes are expected to use feature negotiation such as TUNSETOFFLOAD to detect supported offload types and refrain from injecting other packets. This process breaks down with live migration: guest kernels do not renegotiate flags, so destination hosts need to expose all features that the source host does. Partially revert the UFO removal from 182e0b6b5846~1..d9d30adf5677. This patch introduces nearly(*) no new code to simplify verification. It brings back verbatim tuntap UFO negotiation, VIRTIO_NET_HDR_GSO_UDP insertion and software UFO segmentation. It does not reinstate protocol stack support, hardware offload (NETIF_F_UFO), SKB_GSO_UDP tunneling in SKB_GSO_SOFTWARE or reception of VIRTIO_NET_HDR_GSO_UDP packets in tuntap. To support SKB_GSO_UDP reappearing in the stack, also reinstate logic in act_csum and openvswitch. Achieve equivalence with v4.13 HEAD by squashing in commit 939912216fa8 ("net: skb_needs_check() removes CHECKSUM_UNNECESSARY check for tx.") and reverting commit 8d63bee643f1 ("net: avoid skb_warn_bad_offload false positives on UFO"). (*) To avoid having to bring back skb_shinfo(skb)->ip6_frag_id, ipv6_proxy_select_ident is changed to return a __be32 and this is assigned directly to the frag_hdr. Also, SKB_GSO_UDP is inserted at the end of the enum to minimize code churn. Tested Booted a v4.13 guest kernel with QEMU. On a host kernel before this patch `ethtool -k eth0` shows UFO disabled. After the patch, it is enabled, same as on a v4.13 host kernel. A UFO packet sent from the guest appears on the tap device: host: nc -l -p -u 8000 & tcpdump -n -i tap0 guest: dd if=/dev/zero of=payload.txt bs=1 count=2000 nc -u 192.16.1.1 8000 < payload.txt Direct tap to tap transmission of VIRTIO_NET_HDR_GSO_UDP succeeds, packets arriving fragmented: ./with_tap_pair.sh ./tap_send_ufo tap0 tap1 (from https://github.com/wdebruij/kerneltools/tree/master/tests) Changes v1 -> v2 - simplified set_offload change (review comment) - documented test procedure Link: http://lkml.kernel.org/r/<CAF=yD-LuUeDuL9YWPJD9ykOZ0QCjNeznPDr6whqZ9NGMNF12Mw@mail.gmail.com> Fixes: fb652fdfe837 ("macvlan/macvtap: Remove NETIF_F_UFO advertisement.") Reported-by: Michal Kubecek <mkubecek@suse.cz> Signed-off-by: Willem de Bruijn <willemb@google.com> Acked-by: Jason Wang <jasowang@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-11-21 15:22:25 +00:00
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, false);
net: accept UFO datagrams from tuntap and packet Tuntap and similar devices can inject GSO packets. Accept type VIRTIO_NET_HDR_GSO_UDP, even though not generating UFO natively. Processes are expected to use feature negotiation such as TUNSETOFFLOAD to detect supported offload types and refrain from injecting other packets. This process breaks down with live migration: guest kernels do not renegotiate flags, so destination hosts need to expose all features that the source host does. Partially revert the UFO removal from 182e0b6b5846~1..d9d30adf5677. This patch introduces nearly(*) no new code to simplify verification. It brings back verbatim tuntap UFO negotiation, VIRTIO_NET_HDR_GSO_UDP insertion and software UFO segmentation. It does not reinstate protocol stack support, hardware offload (NETIF_F_UFO), SKB_GSO_UDP tunneling in SKB_GSO_SOFTWARE or reception of VIRTIO_NET_HDR_GSO_UDP packets in tuntap. To support SKB_GSO_UDP reappearing in the stack, also reinstate logic in act_csum and openvswitch. Achieve equivalence with v4.13 HEAD by squashing in commit 939912216fa8 ("net: skb_needs_check() removes CHECKSUM_UNNECESSARY check for tx.") and reverting commit 8d63bee643f1 ("net: avoid skb_warn_bad_offload false positives on UFO"). (*) To avoid having to bring back skb_shinfo(skb)->ip6_frag_id, ipv6_proxy_select_ident is changed to return a __be32 and this is assigned directly to the frag_hdr. Also, SKB_GSO_UDP is inserted at the end of the enum to minimize code churn. Tested Booted a v4.13 guest kernel with QEMU. On a host kernel before this patch `ethtool -k eth0` shows UFO disabled. After the patch, it is enabled, same as on a v4.13 host kernel. A UFO packet sent from the guest appears on the tap device: host: nc -l -p -u 8000 & tcpdump -n -i tap0 guest: dd if=/dev/zero of=payload.txt bs=1 count=2000 nc -u 192.16.1.1 8000 < payload.txt Direct tap to tap transmission of VIRTIO_NET_HDR_GSO_UDP succeeds, packets arriving fragmented: ./with_tap_pair.sh ./tap_send_ufo tap0 tap1 (from https://github.com/wdebruij/kerneltools/tree/master/tests) Changes v1 -> v2 - simplified set_offload change (review comment) - documented test procedure Link: http://lkml.kernel.org/r/<CAF=yD-LuUeDuL9YWPJD9ykOZ0QCjNeznPDr6whqZ9NGMNF12Mw@mail.gmail.com> Fixes: fb652fdfe837 ("macvlan/macvtap: Remove NETIF_F_UFO advertisement.") Reported-by: Michal Kubecek <mkubecek@suse.cz> Signed-off-by: Willem de Bruijn <willemb@google.com> Acked-by: Jason Wang <jasowang@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-11-21 15:22:25 +00:00
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.
*/
net: accept UFO datagrams from tuntap and packet Tuntap and similar devices can inject GSO packets. Accept type VIRTIO_NET_HDR_GSO_UDP, even though not generating UFO natively. Processes are expected to use feature negotiation such as TUNSETOFFLOAD to detect supported offload types and refrain from injecting other packets. This process breaks down with live migration: guest kernels do not renegotiate flags, so destination hosts need to expose all features that the source host does. Partially revert the UFO removal from 182e0b6b5846~1..d9d30adf5677. This patch introduces nearly(*) no new code to simplify verification. It brings back verbatim tuntap UFO negotiation, VIRTIO_NET_HDR_GSO_UDP insertion and software UFO segmentation. It does not reinstate protocol stack support, hardware offload (NETIF_F_UFO), SKB_GSO_UDP tunneling in SKB_GSO_SOFTWARE or reception of VIRTIO_NET_HDR_GSO_UDP packets in tuntap. To support SKB_GSO_UDP reappearing in the stack, also reinstate logic in act_csum and openvswitch. Achieve equivalence with v4.13 HEAD by squashing in commit 939912216fa8 ("net: skb_needs_check() removes CHECKSUM_UNNECESSARY check for tx.") and reverting commit 8d63bee643f1 ("net: avoid skb_warn_bad_offload false positives on UFO"). (*) To avoid having to bring back skb_shinfo(skb)->ip6_frag_id, ipv6_proxy_select_ident is changed to return a __be32 and this is assigned directly to the frag_hdr. Also, SKB_GSO_UDP is inserted at the end of the enum to minimize code churn. Tested Booted a v4.13 guest kernel with QEMU. On a host kernel before this patch `ethtool -k eth0` shows UFO disabled. After the patch, it is enabled, same as on a v4.13 host kernel. A UFO packet sent from the guest appears on the tap device: host: nc -l -p -u 8000 & tcpdump -n -i tap0 guest: dd if=/dev/zero of=payload.txt bs=1 count=2000 nc -u 192.16.1.1 8000 < payload.txt Direct tap to tap transmission of VIRTIO_NET_HDR_GSO_UDP succeeds, packets arriving fragmented: ./with_tap_pair.sh ./tap_send_ufo tap0 tap1 (from https://github.com/wdebruij/kerneltools/tree/master/tests) Changes v1 -> v2 - simplified set_offload change (review comment) - documented test procedure Link: http://lkml.kernel.org/r/<CAF=yD-LuUeDuL9YWPJD9ykOZ0QCjNeznPDr6whqZ9NGMNF12Mw@mail.gmail.com> Fixes: fb652fdfe837 ("macvlan/macvtap: Remove NETIF_F_UFO advertisement.") Reported-by: Michal Kubecek <mkubecek@suse.cz> Signed-off-by: Willem de Bruijn <willemb@google.com> Acked-by: Jason Wang <jasowang@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-11-21 15:22:25 +00:00
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;
}
#define UDP_GRO_CNT_MAX 64
static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
struct sk_buff *skb)
{
struct udphdr *uh = udp_gro_udphdr(skb);
struct sk_buff *pp = NULL;
struct udphdr *uh2;
struct sk_buff *p;
udp: fix GRO packet of death syzbot was able to crash host by sending UDP packets with a 0 payload. TCP does not have this issue since we do not aggregate packets without payload. Since dev_gro_receive() sets gso_size based on skb_gro_len(skb) it seems not worth trying to cope with padded packets. BUG: KASAN: slab-out-of-bounds in skb_gro_receive+0xf5f/0x10e0 net/core/skbuff.c:3826 Read of size 16 at addr ffff88808893fff0 by task syz-executor612/7889 CPU: 0 PID: 7889 Comm: syz-executor612 Not tainted 5.1.0-rc7+ #96 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x172/0x1f0 lib/dump_stack.c:113 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:187 kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317 __asan_report_load16_noabort+0x14/0x20 mm/kasan/generic_report.c:133 skb_gro_receive+0xf5f/0x10e0 net/core/skbuff.c:3826 udp_gro_receive_segment net/ipv4/udp_offload.c:382 [inline] call_gro_receive include/linux/netdevice.h:2349 [inline] udp_gro_receive+0xb61/0xfd0 net/ipv4/udp_offload.c:414 udp4_gro_receive+0x763/0xeb0 net/ipv4/udp_offload.c:478 inet_gro_receive+0xe72/0x1110 net/ipv4/af_inet.c:1510 dev_gro_receive+0x1cd0/0x23c0 net/core/dev.c:5581 napi_gro_frags+0x36b/0xd10 net/core/dev.c:5843 tun_get_user+0x2f24/0x3fb0 drivers/net/tun.c:1981 tun_chr_write_iter+0xbd/0x156 drivers/net/tun.c:2027 call_write_iter include/linux/fs.h:1866 [inline] do_iter_readv_writev+0x5e1/0x8e0 fs/read_write.c:681 do_iter_write fs/read_write.c:957 [inline] do_iter_write+0x184/0x610 fs/read_write.c:938 vfs_writev+0x1b3/0x2f0 fs/read_write.c:1002 do_writev+0x15e/0x370 fs/read_write.c:1037 __do_sys_writev fs/read_write.c:1110 [inline] __se_sys_writev fs/read_write.c:1107 [inline] __x64_sys_writev+0x75/0xb0 fs/read_write.c:1107 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x441cc0 Code: 05 48 3d 01 f0 ff ff 0f 83 9d 09 fc ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 83 3d 51 93 29 00 00 75 14 b8 14 00 00 00 0f 05 <48> 3d 01 f0 ff ff 0f 83 74 09 fc ff c3 48 83 ec 08 e8 ba 2b 00 00 RSP: 002b:00007ffe8c716118 EFLAGS: 00000246 ORIG_RAX: 0000000000000014 RAX: ffffffffffffffda RBX: 00007ffe8c716150 RCX: 0000000000441cc0 RDX: 0000000000000001 RSI: 00007ffe8c716170 RDI: 00000000000000f0 RBP: 0000000000000000 R08: 000000000000ffff R09: 0000000000a64668 R10: 0000000020000040 R11: 0000000000000246 R12: 000000000000c2d9 R13: 0000000000402b50 R14: 0000000000000000 R15: 0000000000000000 Allocated by task 5143: save_stack+0x45/0xd0 mm/kasan/common.c:75 set_track mm/kasan/common.c:87 [inline] __kasan_kmalloc mm/kasan/common.c:497 [inline] __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:470 kasan_slab_alloc+0xf/0x20 mm/kasan/common.c:505 slab_post_alloc_hook mm/slab.h:437 [inline] slab_alloc mm/slab.c:3393 [inline] kmem_cache_alloc+0x11a/0x6f0 mm/slab.c:3555 mm_alloc+0x1d/0xd0 kernel/fork.c:1030 bprm_mm_init fs/exec.c:363 [inline] __do_execve_file.isra.0+0xaa3/0x23f0 fs/exec.c:1791 do_execveat_common fs/exec.c:1865 [inline] do_execve fs/exec.c:1882 [inline] __do_sys_execve fs/exec.c:1958 [inline] __se_sys_execve fs/exec.c:1953 [inline] __x64_sys_execve+0x8f/0xc0 fs/exec.c:1953 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 5351: save_stack+0x45/0xd0 mm/kasan/common.c:75 set_track mm/kasan/common.c:87 [inline] __kasan_slab_free+0x102/0x150 mm/kasan/common.c:459 kasan_slab_free+0xe/0x10 mm/kasan/common.c:467 __cache_free mm/slab.c:3499 [inline] kmem_cache_free+0x86/0x260 mm/slab.c:3765 __mmdrop+0x238/0x320 kernel/fork.c:677 mmdrop include/linux/sched/mm.h:49 [inline] finish_task_switch+0x47b/0x780 kernel/sched/core.c:2746 context_switch kernel/sched/core.c:2880 [inline] __schedule+0x81b/0x1cc0 kernel/sched/core.c:3518 preempt_schedule_irq+0xb5/0x140 kernel/sched/core.c:3745 retint_kernel+0x1b/0x2d arch_local_irq_restore arch/x86/include/asm/paravirt.h:767 [inline] kmem_cache_free+0xab/0x260 mm/slab.c:3766 anon_vma_chain_free mm/rmap.c:134 [inline] unlink_anon_vmas+0x2ba/0x870 mm/rmap.c:401 free_pgtables+0x1af/0x2f0 mm/memory.c:394 exit_mmap+0x2d1/0x530 mm/mmap.c:3144 __mmput kernel/fork.c:1046 [inline] mmput+0x15f/0x4c0 kernel/fork.c:1067 exec_mmap fs/exec.c:1046 [inline] flush_old_exec+0x8d9/0x1c20 fs/exec.c:1279 load_elf_binary+0x9bc/0x53f0 fs/binfmt_elf.c:864 search_binary_handler fs/exec.c:1656 [inline] search_binary_handler+0x17f/0x570 fs/exec.c:1634 exec_binprm fs/exec.c:1698 [inline] __do_execve_file.isra.0+0x1394/0x23f0 fs/exec.c:1818 do_execveat_common fs/exec.c:1865 [inline] do_execve fs/exec.c:1882 [inline] __do_sys_execve fs/exec.c:1958 [inline] __se_sys_execve fs/exec.c:1953 [inline] __x64_sys_execve+0x8f/0xc0 fs/exec.c:1953 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe The buggy address belongs to the object at ffff88808893f7c0 which belongs to the cache mm_struct of size 1496 The buggy address is located 600 bytes to the right of 1496-byte region [ffff88808893f7c0, ffff88808893fd98) The buggy address belongs to the page: page:ffffea0002224f80 count:1 mapcount:0 mapping:ffff88821bc40ac0 index:0xffff88808893f7c0 compound_mapcount: 0 flags: 0x1fffc0000010200(slab|head) raw: 01fffc0000010200 ffffea00025b4f08 ffffea00027b9d08 ffff88821bc40ac0 raw: ffff88808893f7c0 ffff88808893e440 0000000100000001 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88808893fe80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff88808893ff00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffff88808893ff80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ^ ffff888088940000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff888088940080: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 Fixes: e20cf8d3f1f7 ("udp: implement GRO for plain UDP sockets.") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Paolo Abeni <pabeni@redhat.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-02 01:56:28 +00:00
unsigned int ulen;
int ret = 0;
int flush;
/* requires non zero csum, for symmetry with GSO */
if (!uh->check) {
NAPI_GRO_CB(skb)->flush = 1;
return NULL;
}
udp: fix GRO packet of death syzbot was able to crash host by sending UDP packets with a 0 payload. TCP does not have this issue since we do not aggregate packets without payload. Since dev_gro_receive() sets gso_size based on skb_gro_len(skb) it seems not worth trying to cope with padded packets. BUG: KASAN: slab-out-of-bounds in skb_gro_receive+0xf5f/0x10e0 net/core/skbuff.c:3826 Read of size 16 at addr ffff88808893fff0 by task syz-executor612/7889 CPU: 0 PID: 7889 Comm: syz-executor612 Not tainted 5.1.0-rc7+ #96 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x172/0x1f0 lib/dump_stack.c:113 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:187 kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317 __asan_report_load16_noabort+0x14/0x20 mm/kasan/generic_report.c:133 skb_gro_receive+0xf5f/0x10e0 net/core/skbuff.c:3826 udp_gro_receive_segment net/ipv4/udp_offload.c:382 [inline] call_gro_receive include/linux/netdevice.h:2349 [inline] udp_gro_receive+0xb61/0xfd0 net/ipv4/udp_offload.c:414 udp4_gro_receive+0x763/0xeb0 net/ipv4/udp_offload.c:478 inet_gro_receive+0xe72/0x1110 net/ipv4/af_inet.c:1510 dev_gro_receive+0x1cd0/0x23c0 net/core/dev.c:5581 napi_gro_frags+0x36b/0xd10 net/core/dev.c:5843 tun_get_user+0x2f24/0x3fb0 drivers/net/tun.c:1981 tun_chr_write_iter+0xbd/0x156 drivers/net/tun.c:2027 call_write_iter include/linux/fs.h:1866 [inline] do_iter_readv_writev+0x5e1/0x8e0 fs/read_write.c:681 do_iter_write fs/read_write.c:957 [inline] do_iter_write+0x184/0x610 fs/read_write.c:938 vfs_writev+0x1b3/0x2f0 fs/read_write.c:1002 do_writev+0x15e/0x370 fs/read_write.c:1037 __do_sys_writev fs/read_write.c:1110 [inline] __se_sys_writev fs/read_write.c:1107 [inline] __x64_sys_writev+0x75/0xb0 fs/read_write.c:1107 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x441cc0 Code: 05 48 3d 01 f0 ff ff 0f 83 9d 09 fc ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 83 3d 51 93 29 00 00 75 14 b8 14 00 00 00 0f 05 <48> 3d 01 f0 ff ff 0f 83 74 09 fc ff c3 48 83 ec 08 e8 ba 2b 00 00 RSP: 002b:00007ffe8c716118 EFLAGS: 00000246 ORIG_RAX: 0000000000000014 RAX: ffffffffffffffda RBX: 00007ffe8c716150 RCX: 0000000000441cc0 RDX: 0000000000000001 RSI: 00007ffe8c716170 RDI: 00000000000000f0 RBP: 0000000000000000 R08: 000000000000ffff R09: 0000000000a64668 R10: 0000000020000040 R11: 0000000000000246 R12: 000000000000c2d9 R13: 0000000000402b50 R14: 0000000000000000 R15: 0000000000000000 Allocated by task 5143: save_stack+0x45/0xd0 mm/kasan/common.c:75 set_track mm/kasan/common.c:87 [inline] __kasan_kmalloc mm/kasan/common.c:497 [inline] __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:470 kasan_slab_alloc+0xf/0x20 mm/kasan/common.c:505 slab_post_alloc_hook mm/slab.h:437 [inline] slab_alloc mm/slab.c:3393 [inline] kmem_cache_alloc+0x11a/0x6f0 mm/slab.c:3555 mm_alloc+0x1d/0xd0 kernel/fork.c:1030 bprm_mm_init fs/exec.c:363 [inline] __do_execve_file.isra.0+0xaa3/0x23f0 fs/exec.c:1791 do_execveat_common fs/exec.c:1865 [inline] do_execve fs/exec.c:1882 [inline] __do_sys_execve fs/exec.c:1958 [inline] __se_sys_execve fs/exec.c:1953 [inline] __x64_sys_execve+0x8f/0xc0 fs/exec.c:1953 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 5351: save_stack+0x45/0xd0 mm/kasan/common.c:75 set_track mm/kasan/common.c:87 [inline] __kasan_slab_free+0x102/0x150 mm/kasan/common.c:459 kasan_slab_free+0xe/0x10 mm/kasan/common.c:467 __cache_free mm/slab.c:3499 [inline] kmem_cache_free+0x86/0x260 mm/slab.c:3765 __mmdrop+0x238/0x320 kernel/fork.c:677 mmdrop include/linux/sched/mm.h:49 [inline] finish_task_switch+0x47b/0x780 kernel/sched/core.c:2746 context_switch kernel/sched/core.c:2880 [inline] __schedule+0x81b/0x1cc0 kernel/sched/core.c:3518 preempt_schedule_irq+0xb5/0x140 kernel/sched/core.c:3745 retint_kernel+0x1b/0x2d arch_local_irq_restore arch/x86/include/asm/paravirt.h:767 [inline] kmem_cache_free+0xab/0x260 mm/slab.c:3766 anon_vma_chain_free mm/rmap.c:134 [inline] unlink_anon_vmas+0x2ba/0x870 mm/rmap.c:401 free_pgtables+0x1af/0x2f0 mm/memory.c:394 exit_mmap+0x2d1/0x530 mm/mmap.c:3144 __mmput kernel/fork.c:1046 [inline] mmput+0x15f/0x4c0 kernel/fork.c:1067 exec_mmap fs/exec.c:1046 [inline] flush_old_exec+0x8d9/0x1c20 fs/exec.c:1279 load_elf_binary+0x9bc/0x53f0 fs/binfmt_elf.c:864 search_binary_handler fs/exec.c:1656 [inline] search_binary_handler+0x17f/0x570 fs/exec.c:1634 exec_binprm fs/exec.c:1698 [inline] __do_execve_file.isra.0+0x1394/0x23f0 fs/exec.c:1818 do_execveat_common fs/exec.c:1865 [inline] do_execve fs/exec.c:1882 [inline] __do_sys_execve fs/exec.c:1958 [inline] __se_sys_execve fs/exec.c:1953 [inline] __x64_sys_execve+0x8f/0xc0 fs/exec.c:1953 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe The buggy address belongs to the object at ffff88808893f7c0 which belongs to the cache mm_struct of size 1496 The buggy address is located 600 bytes to the right of 1496-byte region [ffff88808893f7c0, ffff88808893fd98) The buggy address belongs to the page: page:ffffea0002224f80 count:1 mapcount:0 mapping:ffff88821bc40ac0 index:0xffff88808893f7c0 compound_mapcount: 0 flags: 0x1fffc0000010200(slab|head) raw: 01fffc0000010200 ffffea00025b4f08 ffffea00027b9d08 ffff88821bc40ac0 raw: ffff88808893f7c0 ffff88808893e440 0000000100000001 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88808893fe80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff88808893ff00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffff88808893ff80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ^ ffff888088940000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff888088940080: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 Fixes: e20cf8d3f1f7 ("udp: implement GRO for plain UDP sockets.") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Paolo Abeni <pabeni@redhat.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-02 01:56:28 +00:00
/* Do not deal with padded or malicious packets, sorry ! */
ulen = ntohs(uh->len);
if (ulen <= sizeof(*uh) || ulen != skb_gro_len(skb)) {
NAPI_GRO_CB(skb)->flush = 1;
return NULL;
}
/* pull encapsulating udp header */
skb_gro_pull(skb, sizeof(struct udphdr));
list_for_each_entry(p, head, list) {
if (!NAPI_GRO_CB(p)->same_flow)
continue;
uh2 = udp_hdr(p);
/* Match ports only, as csum is always non zero */
if ((*(u32 *)&uh->source != *(u32 *)&uh2->source)) {
NAPI_GRO_CB(p)->same_flow = 0;
continue;
}
if (NAPI_GRO_CB(skb)->is_flist != NAPI_GRO_CB(p)->is_flist) {
NAPI_GRO_CB(skb)->flush = 1;
return p;
}
net: gro: move L3 flush checks to tcp_gro_receive and udp_gro_receive_segment {inet,ipv6}_gro_receive functions perform flush checks (ttl, flags, iph->id, ...) against all packets in a loop. These flush checks are used in all merging UDP and TCP flows. These checks need to be done only once and only against the found p skb, since they only affect flush and not same_flow. This patch leverages correct network header offsets from the cb for both outer and inner network headers - allowing these checks to be done only once, in tcp_gro_receive and udp_gro_receive_segment. As a result, NAPI_GRO_CB(p)->flush is not used at all. In addition, flush_id checks are more declarative and contained in inet_gro_flush, thus removing the need for flush_id in napi_gro_cb. This results in less parsing code for non-loop flush tests for TCP and UDP flows. To make sure results are not within noise range - I've made netfilter drop all TCP packets, and measured CPU performance in GRO (in this case GRO is responsible for about 50% of the CPU utilization). perf top while replaying 64 parallel IP/TCP streams merging in GRO: (gro_receive_network_flush is compiled inline to tcp_gro_receive) net-next: 6.94% [kernel] [k] inet_gro_receive 3.02% [kernel] [k] tcp_gro_receive patch applied: 4.27% [kernel] [k] tcp_gro_receive 4.22% [kernel] [k] inet_gro_receive perf top while replaying 64 parallel IP/IP/TCP streams merging in GRO (same results for any encapsulation, in this case inet_gro_receive is top offender in net-next) net-next: 10.09% [kernel] [k] inet_gro_receive 2.08% [kernel] [k] tcp_gro_receive patch applied: 6.97% [kernel] [k] inet_gro_receive 3.68% [kernel] [k] tcp_gro_receive Signed-off-by: Richard Gobert <richardbgobert@gmail.com> Reviewed-by: Willem de Bruijn <willemb@google.com> Link: https://lore.kernel.org/r/20240509190819.2985-3-richardbgobert@gmail.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-05-09 19:08:18 +00:00
flush = gro_receive_network_flush(uh, uh2, p);
/* Terminate the flow on len mismatch or if it grow "too much".
* Under small packet flood GRO count could elsewhere grow a lot
udp: fix GRO packet of death syzbot was able to crash host by sending UDP packets with a 0 payload. TCP does not have this issue since we do not aggregate packets without payload. Since dev_gro_receive() sets gso_size based on skb_gro_len(skb) it seems not worth trying to cope with padded packets. BUG: KASAN: slab-out-of-bounds in skb_gro_receive+0xf5f/0x10e0 net/core/skbuff.c:3826 Read of size 16 at addr ffff88808893fff0 by task syz-executor612/7889 CPU: 0 PID: 7889 Comm: syz-executor612 Not tainted 5.1.0-rc7+ #96 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x172/0x1f0 lib/dump_stack.c:113 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:187 kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317 __asan_report_load16_noabort+0x14/0x20 mm/kasan/generic_report.c:133 skb_gro_receive+0xf5f/0x10e0 net/core/skbuff.c:3826 udp_gro_receive_segment net/ipv4/udp_offload.c:382 [inline] call_gro_receive include/linux/netdevice.h:2349 [inline] udp_gro_receive+0xb61/0xfd0 net/ipv4/udp_offload.c:414 udp4_gro_receive+0x763/0xeb0 net/ipv4/udp_offload.c:478 inet_gro_receive+0xe72/0x1110 net/ipv4/af_inet.c:1510 dev_gro_receive+0x1cd0/0x23c0 net/core/dev.c:5581 napi_gro_frags+0x36b/0xd10 net/core/dev.c:5843 tun_get_user+0x2f24/0x3fb0 drivers/net/tun.c:1981 tun_chr_write_iter+0xbd/0x156 drivers/net/tun.c:2027 call_write_iter include/linux/fs.h:1866 [inline] do_iter_readv_writev+0x5e1/0x8e0 fs/read_write.c:681 do_iter_write fs/read_write.c:957 [inline] do_iter_write+0x184/0x610 fs/read_write.c:938 vfs_writev+0x1b3/0x2f0 fs/read_write.c:1002 do_writev+0x15e/0x370 fs/read_write.c:1037 __do_sys_writev fs/read_write.c:1110 [inline] __se_sys_writev fs/read_write.c:1107 [inline] __x64_sys_writev+0x75/0xb0 fs/read_write.c:1107 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x441cc0 Code: 05 48 3d 01 f0 ff ff 0f 83 9d 09 fc ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 83 3d 51 93 29 00 00 75 14 b8 14 00 00 00 0f 05 <48> 3d 01 f0 ff ff 0f 83 74 09 fc ff c3 48 83 ec 08 e8 ba 2b 00 00 RSP: 002b:00007ffe8c716118 EFLAGS: 00000246 ORIG_RAX: 0000000000000014 RAX: ffffffffffffffda RBX: 00007ffe8c716150 RCX: 0000000000441cc0 RDX: 0000000000000001 RSI: 00007ffe8c716170 RDI: 00000000000000f0 RBP: 0000000000000000 R08: 000000000000ffff R09: 0000000000a64668 R10: 0000000020000040 R11: 0000000000000246 R12: 000000000000c2d9 R13: 0000000000402b50 R14: 0000000000000000 R15: 0000000000000000 Allocated by task 5143: save_stack+0x45/0xd0 mm/kasan/common.c:75 set_track mm/kasan/common.c:87 [inline] __kasan_kmalloc mm/kasan/common.c:497 [inline] __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:470 kasan_slab_alloc+0xf/0x20 mm/kasan/common.c:505 slab_post_alloc_hook mm/slab.h:437 [inline] slab_alloc mm/slab.c:3393 [inline] kmem_cache_alloc+0x11a/0x6f0 mm/slab.c:3555 mm_alloc+0x1d/0xd0 kernel/fork.c:1030 bprm_mm_init fs/exec.c:363 [inline] __do_execve_file.isra.0+0xaa3/0x23f0 fs/exec.c:1791 do_execveat_common fs/exec.c:1865 [inline] do_execve fs/exec.c:1882 [inline] __do_sys_execve fs/exec.c:1958 [inline] __se_sys_execve fs/exec.c:1953 [inline] __x64_sys_execve+0x8f/0xc0 fs/exec.c:1953 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 5351: save_stack+0x45/0xd0 mm/kasan/common.c:75 set_track mm/kasan/common.c:87 [inline] __kasan_slab_free+0x102/0x150 mm/kasan/common.c:459 kasan_slab_free+0xe/0x10 mm/kasan/common.c:467 __cache_free mm/slab.c:3499 [inline] kmem_cache_free+0x86/0x260 mm/slab.c:3765 __mmdrop+0x238/0x320 kernel/fork.c:677 mmdrop include/linux/sched/mm.h:49 [inline] finish_task_switch+0x47b/0x780 kernel/sched/core.c:2746 context_switch kernel/sched/core.c:2880 [inline] __schedule+0x81b/0x1cc0 kernel/sched/core.c:3518 preempt_schedule_irq+0xb5/0x140 kernel/sched/core.c:3745 retint_kernel+0x1b/0x2d arch_local_irq_restore arch/x86/include/asm/paravirt.h:767 [inline] kmem_cache_free+0xab/0x260 mm/slab.c:3766 anon_vma_chain_free mm/rmap.c:134 [inline] unlink_anon_vmas+0x2ba/0x870 mm/rmap.c:401 free_pgtables+0x1af/0x2f0 mm/memory.c:394 exit_mmap+0x2d1/0x530 mm/mmap.c:3144 __mmput kernel/fork.c:1046 [inline] mmput+0x15f/0x4c0 kernel/fork.c:1067 exec_mmap fs/exec.c:1046 [inline] flush_old_exec+0x8d9/0x1c20 fs/exec.c:1279 load_elf_binary+0x9bc/0x53f0 fs/binfmt_elf.c:864 search_binary_handler fs/exec.c:1656 [inline] search_binary_handler+0x17f/0x570 fs/exec.c:1634 exec_binprm fs/exec.c:1698 [inline] __do_execve_file.isra.0+0x1394/0x23f0 fs/exec.c:1818 do_execveat_common fs/exec.c:1865 [inline] do_execve fs/exec.c:1882 [inline] __do_sys_execve fs/exec.c:1958 [inline] __se_sys_execve fs/exec.c:1953 [inline] __x64_sys_execve+0x8f/0xc0 fs/exec.c:1953 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe The buggy address belongs to the object at ffff88808893f7c0 which belongs to the cache mm_struct of size 1496 The buggy address is located 600 bytes to the right of 1496-byte region [ffff88808893f7c0, ffff88808893fd98) The buggy address belongs to the page: page:ffffea0002224f80 count:1 mapcount:0 mapping:ffff88821bc40ac0 index:0xffff88808893f7c0 compound_mapcount: 0 flags: 0x1fffc0000010200(slab|head) raw: 01fffc0000010200 ffffea00025b4f08 ffffea00027b9d08 ffff88821bc40ac0 raw: ffff88808893f7c0 ffff88808893e440 0000000100000001 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88808893fe80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff88808893ff00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffff88808893ff80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ^ ffff888088940000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff888088940080: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 Fixes: e20cf8d3f1f7 ("udp: implement GRO for plain UDP sockets.") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Paolo Abeni <pabeni@redhat.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-02 01:56:28 +00:00
* leading to excessive truesize values.
* On len mismatch merge the first packet shorter than gso_size,
* otherwise complete the GRO packet.
*/
if (ulen > ntohs(uh2->len) || flush) {
pp = p;
} else {
if (NAPI_GRO_CB(skb)->is_flist) {
if (!pskb_may_pull(skb, skb_gro_offset(skb))) {
NAPI_GRO_CB(skb)->flush = 1;
return NULL;
}
if ((skb->ip_summed != p->ip_summed) ||
(skb->csum_level != p->csum_level)) {
NAPI_GRO_CB(skb)->flush = 1;
return NULL;
}
ret = skb_gro_receive_list(p, skb);
} else {
skb_gro_postpull_rcsum(skb, uh,
sizeof(struct udphdr));
ret = skb_gro_receive(p, skb);
}
}
if (ret || ulen != ntohs(uh2->len) ||
NAPI_GRO_CB(p)->count >= UDP_GRO_CNT_MAX)
pp = p;
return pp;
}
/* mismatch, but we never need to flush */
return NULL;
}
struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
struct udphdr *uh, struct sock *sk)
{
struct sk_buff *pp = NULL;
struct sk_buff *p;
struct udphdr *uh2;
unsigned int off = skb_gro_offset(skb);
int flush = 1;
udp: do not accept non-tunnel GSO skbs landing in a tunnel When rx-udp-gro-forwarding is enabled UDP packets might be GROed when being forwarded. If such packets might land in a tunnel this can cause various issues and udp_gro_receive makes sure this isn't the case by looking for a matching socket. This is performed in udp4/6_gro_lookup_skb but only in the current netns. This is an issue with tunneled packets when the endpoint is in another netns. In such cases the packets will be GROed at the UDP level, which leads to various issues later on. The same thing can happen with rx-gro-list. We saw this with geneve packets being GROed at the UDP level. In such case gso_size is set; later the packet goes through the geneve rx path, the geneve header is pulled, the offset are adjusted and frag_list skbs are not adjusted with regard to geneve. When those skbs hit skb_fragment, it will misbehave. Different outcomes are possible depending on what the GROed skbs look like; from corrupted packets to kernel crashes. One example is a BUG_ON[1] triggered in skb_segment while processing the frag_list. Because gso_size is wrong (geneve header was pulled) skb_segment thinks there is "geneve header size" of data in frag_list, although it's in fact the next packet. The BUG_ON itself has nothing to do with the issue. This is only one of the potential issues. Looking up for a matching socket in udp_gro_receive is fragile: the lookup could be extended to all netns (not speaking about performances) but nothing prevents those packets from being modified in between and we could still not find a matching socket. It's OK to keep the current logic there as it should cover most cases but we also need to make sure we handle tunnel packets being GROed too early. This is done by extending the checks in udp_unexpected_gso: GSO packets lacking the SKB_GSO_UDP_TUNNEL/_CSUM bits and landing in a tunnel must be segmented. [1] kernel BUG at net/core/skbuff.c:4408! RIP: 0010:skb_segment+0xd2a/0xf70 __udp_gso_segment+0xaa/0x560 Fixes: 9fd1ff5d2ac7 ("udp: Support UDP fraglist GRO/GSO.") Fixes: 36707061d6ba ("udp: allow forwarding of plain (non-fraglisted) UDP GRO packets") Signed-off-by: Antoine Tenart <atenart@kernel.org> Reviewed-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2024-03-26 11:33:58 +00:00
/* We can do L4 aggregation only if the packet can't land in a tunnel
* otherwise we could corrupt the inner stream. Detecting such packets
* cannot be foolproof and the aggregation might still happen in some
* cases. Such packets should be caught in udp_unexpected_gso later.
*/
NAPI_GRO_CB(skb)->is_flist = 0;
if (!sk || !udp_sk(sk)->gro_receive) {
/* If the packet was locally encapsulated in a UDP tunnel that
* wasn't detected above, do not GRO.
*/
if (skb->encapsulation)
goto out;
if (skb->dev->features & NETIF_F_GRO_FRAGLIST)
NAPI_GRO_CB(skb)->is_flist = sk ? !udp_test_bit(GRO_ENABLED, sk) : 1;
if ((!sk && (skb->dev->features & NETIF_F_GRO_UDP_FWD)) ||
(sk && udp_test_bit(GRO_ENABLED, sk)) || NAPI_GRO_CB(skb)->is_flist)
return call_gro_receive(udp_gro_receive_segment, head, skb);
/* no GRO, be sure flush the current packet */
goto out;
}
if (NAPI_GRO_CB(skb)->encap_mark ||
net: Fix gro aggregation for udp encaps with zero csum 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 2abb7cdc0dc8 ("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 57c67ff4bd92 ("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 662880f44203 ("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: 57c67ff4bd92 ("udp: additional GRO support") Fixes: 662880f44203 ("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>
2021-02-26 21:22:48 +00:00
(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;
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:
skb_gro_flush_final(skb, pp, flush);
return pp;
}
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);
struct net *net = dev_net(skb->dev);
int iif, sdif;
inet_get_iif_sdif(skb, &iif, &sdif);
return __udp4_lib_lookup(net, iph->saddr, sport,
iph->daddr, dport, iif,
sdif, net->ipv4.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;
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,
inet_gro_compute_pseudo);
skip:
NAPI_GRO_CB(skb)->is_ipv6 = 0;
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);
return pp;
flush:
NAPI_GRO_CB(skb)->flush = 1;
return NULL;
}
static int udp_gro_complete_segment(struct sk_buff *skb)
{
struct udphdr *uh = udp_hdr(skb);
skb->csum_start = (unsigned char *)uh - skb->head;
skb->csum_offset = offsetof(struct udphdr, check);
skb->ip_summed = CHECKSUM_PARTIAL;
skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_L4;
net, gro: Set inner transport header offset in tcp/udp GRO hook GSO expects inner transport header offset to be valid when skb->encapsulation flag is set. GSO uses this value to calculate the length of an individual segment of a GSO packet in skb_gso_transport_seglen(). However, tcp/udp gro_complete callbacks don't update the skb->inner_transport_header when processing an encapsulated TCP/UDP segment. As a result a GRO skb has ->inner_transport_header set to a value carried over from earlier skb processing. This can have mild to tragic consequences. From miscalculating the GSO segment length to triggering a page fault [1], when trying to read TCP/UDP header at an address past the skb->data page. The latter scenario leads to an oops report like so: BUG: unable to handle page fault for address: ffff9fa7ec00d008 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 123f201067 P4D 123f201067 PUD 123f209067 PMD 0 Oops: 0000 [#1] SMP NOPTI CPU: 44 PID: 0 Comm: swapper/44 Not tainted 5.4.53-cloudflare-2020.7.21 #1 Hardware name: HYVE EDGE-METAL-GEN10/HS-1811DLite1, BIOS V2.15 02/21/2020 RIP: 0010:skb_gso_transport_seglen+0x44/0xa0 Code: c0 41 83 e0 11 f6 87 81 00 00 00 20 74 30 0f b7 87 aa 00 00 00 0f [...] RSP: 0018:ffffad8640bacbb8 EFLAGS: 00010202 RAX: 000000000000feda RBX: ffff9fcc8d31bc00 RCX: ffff9fa7ec00cffc RDX: ffff9fa7ebffdec0 RSI: 000000000000feda RDI: 0000000000000122 RBP: 00000000000005c4 R08: 0000000000000001 R09: 0000000000000000 R10: ffff9fe588ae3800 R11: ffff9fe011fc92f0 R12: ffff9fcc8d31bc00 R13: ffff9fe0119d4300 R14: 00000000000005c4 R15: ffff9fba57d70900 FS: 0000000000000000(0000) GS:ffff9fe68df00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff9fa7ec00d008 CR3: 0000003e99b1c000 CR4: 0000000000340ee0 Call Trace: <IRQ> skb_gso_validate_network_len+0x11/0x70 __ip_finish_output+0x109/0x1c0 ip_sublist_rcv_finish+0x57/0x70 ip_sublist_rcv+0x2aa/0x2d0 ? ip_rcv_finish_core.constprop.0+0x390/0x390 ip_list_rcv+0x12b/0x14f __netif_receive_skb_list_core+0x2a9/0x2d0 netif_receive_skb_list_internal+0x1b5/0x2e0 napi_complete_done+0x93/0x140 veth_poll+0xc0/0x19f [veth] ? mlx5e_napi_poll+0x221/0x610 [mlx5_core] net_rx_action+0x1f8/0x790 __do_softirq+0xe1/0x2bf irq_exit+0x8e/0xc0 do_IRQ+0x58/0xe0 common_interrupt+0xf/0xf </IRQ> The bug can be observed in a simple setup where we send IP/GRE/IP/TCP packets into a netns over a veth pair. Inside the netns, packets are forwarded to dummy device: trafgen -> [veth A]--[veth B] -forward-> [dummy] For veth B to GRO aggregate packets on receive, it needs to have an XDP program attached (for example, a trivial XDP_PASS). Additionally, for UDP, we need to enable GSO_UDP_L4 feature on the device: ip netns exec A ethtool -K AB rx-udp-gro-forwarding on The last component is an artificial delay to increase the chances of GRO batching happening: ip netns exec A tc qdisc add dev AB root \ netem delay 200us slot 5ms 10ms packets 2 bytes 64k With such a setup in place, the bug can be observed by tracing the skb outer and inner offsets when GSO skb is transmitted from the dummy device: tcp: FUNC DEV SKB_LEN NH TH ENC INH ITH GSO_SIZE GSO_TYPE ip_finish_output dumB 2830 270 290 1 294 254 1383 (tcpv4,gre,) ^^^ udp: FUNC DEV SKB_LEN NH TH ENC INH ITH GSO_SIZE GSO_TYPE ip_finish_output dumB 2818 270 290 1 294 254 1383 (gre,udp_l4,) ^^^ Fix it by updating the inner transport header offset in tcp/udp gro_complete callbacks, similar to how {inet,ipv6}_gro_complete callbacks update the inner network header offset, when skb->encapsulation flag is set. [1] https://lore.kernel.org/netdev/CAKxSbF01cLpZem2GFaUaifh0S-5WYViZemTicAg7FCHOnh6kug@mail.gmail.com/ Fixes: bf296b125b21 ("tcp: Add GRO support") Fixes: f993bc25e519 ("net: core: handle encapsulation offloads when computing segment lengths") Fixes: e20cf8d3f1f7 ("udp: implement GRO for plain UDP sockets.") Reported-by: Alex Forster <aforster@cloudflare.com> Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-07-29 13:48:20 +00:00
if (skb->encapsulation)
skb->inner_transport_header = skb->transport_header;
return 0;
}
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);
struct sock *sk;
int err;
uh->len = newlen;
sk = INDIRECT_CALL_INET(lookup, udp6_lib_lookup_skb,
udp4_lib_lookup_skb, skb, uh->source, uh->dest);
if (sk && udp_sk(sk)->gro_complete) {
skb_shinfo(skb)->gso_type = uh->check ? SKB_GSO_UDP_TUNNEL_CSUM
: SKB_GSO_UDP_TUNNEL;
/* clear the encap mark, so that inner frag_list gro_complete
* can take place
*/
NAPI_GRO_CB(skb)->encap_mark = 0;
/* Set encapsulation before calling into inner gro_complete()
* functions to make them set up the inner offsets.
*/
skb->encapsulation = 1;
err = udp_sk(sk)->gro_complete(sk, skb,
nhoff + sizeof(struct udphdr));
} else {
err = udp_gro_complete_segment(skb);
}
if (skb->remcsum_offload)
skb_shinfo(skb)->gso_type |= SKB_GSO_TUNNEL_REMCSUM;
return err;
}
EXPORT_SYMBOL(udp_gro_complete);
INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff)
{
net: gro: fix udp bad offset in socket lookup by adding {inner_}network_offset to napi_gro_cb Commits a602456 ("udp: Add GRO functions to UDP socket") and 57c67ff ("udp: additional GRO support") introduce incorrect usage of {ip,ipv6}_hdr in the complete phase of gro. The functions always return skb->network_header, which in the case of encapsulated packets at the gro complete phase, is always set to the innermost L3 of the packet. That means that calling {ip,ipv6}_hdr for skbs which completed the GRO receive phase (both in gro_list and *_gro_complete) when parsing an encapsulated packet's _outer_ L3/L4 may return an unexpected value. This incorrect usage leads to a bug in GRO's UDP socket lookup. udp{4,6}_lib_lookup_skb functions use ip_hdr/ipv6_hdr respectively. These *_hdr functions return network_header which will point to the innermost L3, resulting in the wrong offset being used in __udp{4,6}_lib_lookup with encapsulated packets. This patch adds network_offset and inner_network_offset to napi_gro_cb, and makes sure both are set correctly. To fix the issue, network_offsets union is used inside napi_gro_cb, in which both the outer and the inner network offsets are saved. Reproduction example: Endpoint configuration example (fou + local address bind) # ip fou add port 6666 ipproto 4 # ip link add name tun1 type ipip remote 2.2.2.1 local 2.2.2.2 encap fou encap-dport 5555 encap-sport 6666 mode ipip # ip link set tun1 up # ip a add 1.1.1.2/24 dev tun1 Netperf TCP_STREAM result on net-next before patch is applied: net-next main, GRO enabled: $ netperf -H 1.1.1.2 -t TCP_STREAM -l 5 Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 131072 16384 16384 5.28 2.37 net-next main, GRO disabled: $ netperf -H 1.1.1.2 -t TCP_STREAM -l 5 Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 131072 16384 16384 5.01 2745.06 patch applied, GRO enabled: $ netperf -H 1.1.1.2 -t TCP_STREAM -l 5 Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 131072 16384 16384 5.01 2877.38 Fixes: a6024562ffd7 ("udp: Add GRO functions to UDP socket") Signed-off-by: Richard Gobert <richardbgobert@gmail.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Reviewed-by: Willem de Bruijn <willemb@google.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2024-04-30 14:35:54 +00:00
const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation];
const struct iphdr *iph = (struct iphdr *)(skb->data + offset);
struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
/* do fraglist only if there is no outer UDP encap (or we already processed it) */
if (NAPI_GRO_CB(skb)->is_flist && !NAPI_GRO_CB(skb)->encap_mark) {
uh->len = htons(skb->len - nhoff);
skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4);
skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
__skb_incr_checksum_unnecessary(skb);
return 0;
}
if (uh->check)
uh->check = ~udp_v4_check(skb->len - nhoff, iph->saddr,
iph->daddr, 0);
return udp_gro_complete(skb, nhoff, udp4_lib_lookup_skb);
}
int __init udpv4_offload_init(void)
{
net_hotdata.udpv4_offload = (struct net_offload) {
.callbacks = {
.gso_segment = udp4_ufo_fragment,
.gro_receive = udp4_gro_receive,
.gro_complete = udp4_gro_complete,
},
};
return inet_add_offload(&net_hotdata.udpv4_offload, IPPROTO_UDP);
}