linux/net/ipv4/udp_offload.c
Eric Dumazet 575b65bc5b udp: avoid refcount_t saturation in __udp_gso_segment()
For some reason, Willem thought that the issue we fixed for TCP
in commit 7ec318feee ("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: ad405857b1 ("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 12:29:42 -04:00

486 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);
/* 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 sk_buff **head, struct sk_buff *skb,
struct udphdr *uh, udp_lookup_t lookup)
{
struct sk_buff *p, **pp = NULL;
struct udphdr *uh2;
unsigned int off = skb_gro_offset(skb);
int flush = 1;
struct sock *sk;
if (NAPI_GRO_CB(skb)->encap_mark ||
(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;
for (p = *head; p; p = p->next) {
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:
NAPI_GRO_CB(skb)->flush |= flush;
return pp;
}
EXPORT_SYMBOL(udp_gro_receive);
static struct sk_buff **udp4_gro_receive(struct sk_buff **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);
}