linux/net/sched/sch_frag.c
Davide Caratti 31fe34a011 net/sched: sch_frag: fix stack OOB read while fragmenting IPv4 packets
when 'act_mirred' tries to fragment IPv4 packets that had been previously
re-assembled using 'act_ct', splats like the following can be observed on
kernels built with KASAN:

 BUG: KASAN: stack-out-of-bounds in ip_do_fragment+0x1b03/0x1f60
 Read of size 1 at addr ffff888147009574 by task ping/947

 CPU: 0 PID: 947 Comm: ping Not tainted 5.12.0-rc6+ #418
 Hardware name: Red Hat KVM, BIOS 1.11.1-4.module+el8.1.0+4066+0f1aadab 04/01/2014
 Call Trace:
  <IRQ>
  dump_stack+0x92/0xc1
  print_address_description.constprop.7+0x1a/0x150
  kasan_report.cold.13+0x7f/0x111
  ip_do_fragment+0x1b03/0x1f60
  sch_fragment+0x4bf/0xe40
  tcf_mirred_act+0xc3d/0x11a0 [act_mirred]
  tcf_action_exec+0x104/0x3e0
  fl_classify+0x49a/0x5e0 [cls_flower]
  tcf_classify_ingress+0x18a/0x820
  __netif_receive_skb_core+0xae7/0x3340
  __netif_receive_skb_one_core+0xb6/0x1b0
  process_backlog+0x1ef/0x6c0
  __napi_poll+0xaa/0x500
  net_rx_action+0x702/0xac0
  __do_softirq+0x1e4/0x97f
  do_softirq+0x71/0x90
  </IRQ>
  __local_bh_enable_ip+0xdb/0xf0
  ip_finish_output2+0x760/0x2120
  ip_do_fragment+0x15a5/0x1f60
  __ip_finish_output+0x4c2/0xea0
  ip_output+0x1ca/0x4d0
  ip_send_skb+0x37/0xa0
  raw_sendmsg+0x1c4b/0x2d00
  sock_sendmsg+0xdb/0x110
  __sys_sendto+0x1d7/0x2b0
  __x64_sys_sendto+0xdd/0x1b0
  do_syscall_64+0x33/0x40
  entry_SYSCALL_64_after_hwframe+0x44/0xae
 RIP: 0033:0x7f82e13853eb
 Code: 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 f3 0f 1e fa 48 8d 05 75 42 2c 00 41 89 ca 8b 00 85 c0 75 14 b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 75 c3 0f 1f 40 00 41 57 4d 89 c7 41 56 41 89
 RSP: 002b:00007ffe01fad888 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
 RAX: ffffffffffffffda RBX: 00005571aac13700 RCX: 00007f82e13853eb
 RDX: 0000000000002330 RSI: 00005571aac13700 RDI: 0000000000000003
 RBP: 0000000000002330 R08: 00005571aac10500 R09: 0000000000000010
 R10: 0000000000000000 R11: 0000000000000246 R12: 00007ffe01faefb0
 R13: 00007ffe01fad890 R14: 00007ffe01fad980 R15: 00005571aac0f0a0

 The buggy address belongs to the page:
 page:000000001dff2e03 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x147009
 flags: 0x17ffffc0001000(reserved)
 raw: 0017ffffc0001000 ffffea00051c0248 ffffea00051c0248 0000000000000000
 raw: 0000000000000000 0000000000000000 00000001ffffffff 0000000000000000
 page dumped because: kasan: bad access detected

 Memory state around the buggy address:
  ffff888147009400: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
  ffff888147009480: f1 f1 f1 f1 04 f2 f2 f2 f2 f2 f2 f2 00 00 00 00
 >ffff888147009500: 00 00 00 00 00 00 00 00 00 00 f2 f2 f2 f2 f2 f2
                                                              ^
  ffff888147009580: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
  ffff888147009600: 00 00 00 00 00 00 00 00 00 00 00 00 00 f2 f2 f2

for IPv4 packets, sch_fragment() uses a temporary struct dst_entry. Then,
in the following call graph:

  ip_do_fragment()
    ip_skb_dst_mtu()
      ip_dst_mtu_maybe_forward()
        ip_mtu_locked()

the pointer to struct dst_entry is used as pointer to struct rtable: this
turns the access to struct members like rt_mtu_locked into an OOB read in
the stack. Fix this changing the temporary variable used for IPv4 packets
in sch_fragment(), similarly to what is done for IPv6 few lines below.

Fixes: c129412f74 ("net/sched: sch_frag: add generic packet fragment support.")
Cc: <stable@vger.kernel.org> # 5.11
Reported-by: Shuang Li <shuali@redhat.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-04-29 15:31:53 -07:00

151 lines
3.8 KiB
C

// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
#include <net/netlink.h>
#include <net/sch_generic.h>
#include <net/dst.h>
#include <net/ip.h>
#include <net/ip6_fib.h>
struct sch_frag_data {
unsigned long dst;
struct qdisc_skb_cb cb;
__be16 inner_protocol;
u16 vlan_tci;
__be16 vlan_proto;
unsigned int l2_len;
u8 l2_data[VLAN_ETH_HLEN];
int (*xmit)(struct sk_buff *skb);
};
static DEFINE_PER_CPU(struct sch_frag_data, sch_frag_data_storage);
static int sch_frag_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct sch_frag_data *data = this_cpu_ptr(&sch_frag_data_storage);
if (skb_cow_head(skb, data->l2_len) < 0) {
kfree_skb(skb);
return -ENOMEM;
}
__skb_dst_copy(skb, data->dst);
*qdisc_skb_cb(skb) = data->cb;
skb->inner_protocol = data->inner_protocol;
if (data->vlan_tci & VLAN_CFI_MASK)
__vlan_hwaccel_put_tag(skb, data->vlan_proto,
data->vlan_tci & ~VLAN_CFI_MASK);
else
__vlan_hwaccel_clear_tag(skb);
/* Reconstruct the MAC header. */
skb_push(skb, data->l2_len);
memcpy(skb->data, &data->l2_data, data->l2_len);
skb_postpush_rcsum(skb, skb->data, data->l2_len);
skb_reset_mac_header(skb);
return data->xmit(skb);
}
static void sch_frag_prepare_frag(struct sk_buff *skb,
int (*xmit)(struct sk_buff *skb))
{
unsigned int hlen = skb_network_offset(skb);
struct sch_frag_data *data;
data = this_cpu_ptr(&sch_frag_data_storage);
data->dst = skb->_skb_refdst;
data->cb = *qdisc_skb_cb(skb);
data->xmit = xmit;
data->inner_protocol = skb->inner_protocol;
if (skb_vlan_tag_present(skb))
data->vlan_tci = skb_vlan_tag_get(skb) | VLAN_CFI_MASK;
else
data->vlan_tci = 0;
data->vlan_proto = skb->vlan_proto;
data->l2_len = hlen;
memcpy(&data->l2_data, skb->data, hlen);
memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
skb_pull(skb, hlen);
}
static unsigned int
sch_frag_dst_get_mtu(const struct dst_entry *dst)
{
return dst->dev->mtu;
}
static struct dst_ops sch_frag_dst_ops = {
.family = AF_UNSPEC,
.mtu = sch_frag_dst_get_mtu,
};
static int sch_fragment(struct net *net, struct sk_buff *skb,
u16 mru, int (*xmit)(struct sk_buff *skb))
{
int ret = -1;
if (skb_network_offset(skb) > VLAN_ETH_HLEN) {
net_warn_ratelimited("L2 header too long to fragment\n");
goto err;
}
if (skb_protocol(skb, true) == htons(ETH_P_IP)) {
struct rtable sch_frag_rt = { 0 };
unsigned long orig_dst;
sch_frag_prepare_frag(skb, xmit);
dst_init(&sch_frag_rt.dst, &sch_frag_dst_ops, NULL, 1,
DST_OBSOLETE_NONE, DST_NOCOUNT);
sch_frag_rt.dst.dev = skb->dev;
orig_dst = skb->_skb_refdst;
skb_dst_set_noref(skb, &sch_frag_rt.dst);
IPCB(skb)->frag_max_size = mru;
ret = ip_do_fragment(net, skb->sk, skb, sch_frag_xmit);
refdst_drop(orig_dst);
} else if (skb_protocol(skb, true) == htons(ETH_P_IPV6)) {
unsigned long orig_dst;
struct rt6_info sch_frag_rt;
sch_frag_prepare_frag(skb, xmit);
memset(&sch_frag_rt, 0, sizeof(sch_frag_rt));
dst_init(&sch_frag_rt.dst, &sch_frag_dst_ops, NULL, 1,
DST_OBSOLETE_NONE, DST_NOCOUNT);
sch_frag_rt.dst.dev = skb->dev;
orig_dst = skb->_skb_refdst;
skb_dst_set_noref(skb, &sch_frag_rt.dst);
IP6CB(skb)->frag_max_size = mru;
ret = ipv6_stub->ipv6_fragment(net, skb->sk, skb,
sch_frag_xmit);
refdst_drop(orig_dst);
} else {
net_warn_ratelimited("Fail frag %s: eth=%x, MRU=%d, MTU=%d\n",
netdev_name(skb->dev),
ntohs(skb_protocol(skb, true)), mru,
skb->dev->mtu);
goto err;
}
return ret;
err:
kfree_skb(skb);
return ret;
}
int sch_frag_xmit_hook(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb))
{
u16 mru = qdisc_skb_cb(skb)->mru;
int err;
if (mru && skb->len > mru + skb->dev->hard_header_len)
err = sch_fragment(dev_net(skb->dev), skb, mru, xmit);
else
err = xmit(skb);
return err;
}
EXPORT_SYMBOL_GPL(sch_frag_xmit_hook);