From: Jason A. Donenfeld Jason@zx2c4.com
commit ee576c47db60432c37e54b1e2b43a8ca6d3a8dca upstream.
The icmp{,v6}_send functions make all sorts of use of skb->cb, casting it with IPCB or IP6CB, assuming the skb to have come directly from the inet layer. But when the packet comes from the ndo layer, especially when forwarded, there's no telling what might be in skb->cb at that point. As a result, the icmp sending code risks reading bogus memory contents, which can result in nasty stack overflows such as this one reported by a user:
panic+0x108/0x2ea __stack_chk_fail+0x14/0x20 __icmp_send+0x5bd/0x5c0 icmp_ndo_send+0x148/0x160
In icmp_send, skb->cb is cast with IPCB and an ip_options struct is read from it. The optlen parameter there is of particular note, as it can induce writes beyond bounds. There are quite a few ways that can happen in __ip_options_echo. For example:
// sptr/skb are attacker-controlled skb bytes sptr = skb_network_header(skb); // dptr/dopt points to stack memory allocated by __icmp_send dptr = dopt->__data; // sopt is the corrupt skb->cb in question if (sopt->rr) { optlen = sptr[sopt->rr+1]; // corrupt skb->cb + skb->data soffset = sptr[sopt->rr+2]; // corrupt skb->cb + skb->data // this now writes potentially attacker-controlled data, over // flowing the stack: memcpy(dptr, sptr+sopt->rr, optlen); }
In the icmpv6_send case, the story is similar, but not as dire, as only IP6CB(skb)->iif and IP6CB(skb)->dsthao are used. The dsthao case is worse than the iif case, but it is passed to ipv6_find_tlv, which does a bit of bounds checking on the value.
This is easy to simulate by doing a `memset(skb->cb, 0x41, sizeof(skb->cb));` before calling icmp{,v6}_ndo_send, and it's only by good fortune and the rarity of icmp sending from that context that we've avoided reports like this until now. For example, in KASAN:
BUG: KASAN: stack-out-of-bounds in __ip_options_echo+0xa0e/0x12b0 Write of size 38 at addr ffff888006f1f80e by task ping/89 CPU: 2 PID: 89 Comm: ping Not tainted 5.10.0-rc7-debug+ #5 Call Trace: dump_stack+0x9a/0xcc print_address_description.constprop.0+0x1a/0x160 __kasan_report.cold+0x20/0x38 kasan_report+0x32/0x40 check_memory_region+0x145/0x1a0 memcpy+0x39/0x60 __ip_options_echo+0xa0e/0x12b0 __icmp_send+0x744/0x1700
Actually, out of the 4 drivers that do this, only gtp zeroed the cb for the v4 case, while the rest did not. So this commit actually removes the gtp-specific zeroing, while putting the code where it belongs in the shared infrastructure of icmp{,v6}_ndo_send.
This commit fixes the issue by passing an empty IPCB or IP6CB along to the functions that actually do the work. For the icmp_send, this was already trivial, thanks to __icmp_send providing the plumbing function. For icmpv6_send, this required a tiny bit of refactoring to make it behave like the v4 case, after which it was straight forward.
Fixes: a2b78e9b2cac ("sunvnet: generate ICMP PTMUD messages for smaller port MTUs") Reported-by: SinYu liuxyon@gmail.com Reviewed-by: Willem de Bruijn willemb@google.com Link: https://lore.kernel.org/netdev/CAF=yD-LOF116aHub6RMe8vB8ZpnrrnoTdqhobEx+bvoA... Signed-off-by: Jason A. Donenfeld Jason@zx2c4.com Link: https://lore.kernel.org/r/20210223131858.72082-1-Jason@zx2c4.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/gtp.c | 1 - include/linux/icmpv6.h | 26 ++++++++++++++++++++------ include/linux/ipv6.h | 1 - include/net/icmp.h | 6 +++++- net/ipv4/icmp.c | 5 +++-- net/ipv6/icmp.c | 16 ++++++++-------- net/ipv6/ip6_icmp.c | 12 +++++++----- 7 files changed, 43 insertions(+), 24 deletions(-)
--- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -545,7 +545,6 @@ static int gtp_build_skb_ip4(struct sk_b if (!skb_is_gso(skb) && (iph->frag_off & htons(IP_DF)) && mtu < ntohs(iph->tot_len)) { netdev_dbg(dev, "packet too big, fragmentation needed\n"); - memset(IPCB(skb), 0, sizeof(*IPCB(skb))); icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); goto err_rt; --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -3,6 +3,7 @@ #define _LINUX_ICMPV6_H
#include <linux/skbuff.h> +#include <linux/ipv6.h> #include <uapi/linux/icmpv6.h>
static inline struct icmp6hdr *icmp6_hdr(const struct sk_buff *skb) @@ -15,13 +16,16 @@ static inline struct icmp6hdr *icmp6_hdr #if IS_ENABLED(CONFIG_IPV6)
typedef void ip6_icmp_send_t(struct sk_buff *skb, u8 type, u8 code, __u32 info, - const struct in6_addr *force_saddr); + const struct in6_addr *force_saddr, + const struct inet6_skb_parm *parm); void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, - const struct in6_addr *force_saddr); + const struct in6_addr *force_saddr, + const struct inet6_skb_parm *parm); #if IS_BUILTIN(CONFIG_IPV6) -static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) +static inline void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, + const struct inet6_skb_parm *parm) { - icmp6_send(skb, type, code, info, NULL); + icmp6_send(skb, type, code, info, NULL, parm); } static inline int inet6_register_icmp_sender(ip6_icmp_send_t *fn) { @@ -34,11 +38,17 @@ static inline int inet6_unregister_icmp_ return 0; } #else -extern void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info); +extern void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, + const struct inet6_skb_parm *parm); extern int inet6_register_icmp_sender(ip6_icmp_send_t *fn); extern int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn); #endif
+static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) +{ + __icmpv6_send(skb, type, code, info, IP6CB(skb)); +} + int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, unsigned int data_len);
@@ -54,7 +64,11 @@ static inline void icmpv6_send(struct sk #if IS_ENABLED(CONFIG_NF_NAT) void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info); #else -#define icmpv6_ndo_send icmpv6_send +static inline void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) +{ + struct inet6_skb_parm parm = { 0 }; + __icmpv6_send(skb_in, type, code, info, &parm); +} #endif
extern int icmpv6_init(void); --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -83,7 +83,6 @@ struct ipv6_params { __s32 autoconf; }; extern struct ipv6_params ipv6_defaults; -#include <linux/icmpv6.h> #include <linux/tcp.h> #include <linux/udp.h>
--- a/include/net/icmp.h +++ b/include/net/icmp.h @@ -46,7 +46,11 @@ static inline void icmp_send(struct sk_b #if IS_ENABLED(CONFIG_NF_NAT) void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info); #else -#define icmp_ndo_send icmp_send +static inline void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) +{ + struct ip_options opts = { 0 }; + __icmp_send(skb_in, type, code, info, &opts); +} #endif
int icmp_rcv(struct sk_buff *skb); --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -755,13 +755,14 @@ EXPORT_SYMBOL(__icmp_send); void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) { struct sk_buff *cloned_skb = NULL; + struct ip_options opts = { 0 }; enum ip_conntrack_info ctinfo; struct nf_conn *ct; __be32 orig_ip;
ct = nf_ct_get(skb_in, &ctinfo); if (!ct || !(ct->status & IPS_SRC_NAT)) { - icmp_send(skb_in, type, code, info); + __icmp_send(skb_in, type, code, info, &opts); return; }
@@ -776,7 +777,7 @@ void icmp_ndo_send(struct sk_buff *skb_i
orig_ip = ip_hdr(skb_in)->saddr; ip_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.ip; - icmp_send(skb_in, type, code, info); + __icmp_send(skb_in, type, code, info, &opts); ip_hdr(skb_in)->saddr = orig_ip; out: consume_skb(cloned_skb); --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -312,10 +312,9 @@ static int icmpv6_getfrag(void *from, ch }
#if IS_ENABLED(CONFIG_IPV6_MIP6) -static void mip6_addr_swap(struct sk_buff *skb) +static void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt) { struct ipv6hdr *iph = ipv6_hdr(skb); - struct inet6_skb_parm *opt = IP6CB(skb); struct ipv6_destopt_hao *hao; struct in6_addr tmp; int off; @@ -332,7 +331,7 @@ static void mip6_addr_swap(struct sk_buf } } #else -static inline void mip6_addr_swap(struct sk_buff *skb) {} +static inline void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt) {} #endif
static struct dst_entry *icmpv6_route_lookup(struct net *net, @@ -427,7 +426,8 @@ static int icmp6_iif(const struct sk_buf * Send an ICMP message in response to a packet in error */ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, - const struct in6_addr *force_saddr) + const struct in6_addr *force_saddr, + const struct inet6_skb_parm *parm) { struct inet6_dev *idev = NULL; struct ipv6hdr *hdr = ipv6_hdr(skb); @@ -520,7 +520,7 @@ void icmp6_send(struct sk_buff *skb, u8 if (!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, type)) goto out_bh_enable;
- mip6_addr_swap(skb); + mip6_addr_swap(skb, parm);
memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_ICMPV6; @@ -606,7 +606,7 @@ EXPORT_SYMBOL(icmp6_send); */ void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos) { - icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL); + icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL, IP6CB(skb)); kfree_skb(skb); }
@@ -663,10 +663,10 @@ int ip6_err_gen_icmpv6_unreach(struct sk } if (type == ICMP_TIME_EXCEEDED) icmp6_send(skb2, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, - info, &temp_saddr); + info, &temp_saddr, IP6CB(skb2)); else icmp6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, - info, &temp_saddr); + info, &temp_saddr, IP6CB(skb2)); if (rt) ip6_rt_put(rt);
--- a/net/ipv6/ip6_icmp.c +++ b/net/ipv6/ip6_icmp.c @@ -33,23 +33,25 @@ int inet6_unregister_icmp_sender(ip6_icm } EXPORT_SYMBOL(inet6_unregister_icmp_sender);
-void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) +void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, + const struct inet6_skb_parm *parm) { ip6_icmp_send_t *send;
rcu_read_lock(); send = rcu_dereference(ip6_icmp_send); if (send) - send(skb, type, code, info, NULL); + send(skb, type, code, info, NULL, parm); rcu_read_unlock(); } -EXPORT_SYMBOL(icmpv6_send); +EXPORT_SYMBOL(__icmpv6_send); #endif
#if IS_ENABLED(CONFIG_NF_NAT) #include <net/netfilter/nf_conntrack.h> void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) { + struct inet6_skb_parm parm = { 0 }; struct sk_buff *cloned_skb = NULL; enum ip_conntrack_info ctinfo; struct in6_addr orig_ip; @@ -57,7 +59,7 @@ void icmpv6_ndo_send(struct sk_buff *skb
ct = nf_ct_get(skb_in, &ctinfo); if (!ct || !(ct->status & IPS_SRC_NAT)) { - icmpv6_send(skb_in, type, code, info); + __icmpv6_send(skb_in, type, code, info, &parm); return; }
@@ -72,7 +74,7 @@ void icmpv6_ndo_send(struct sk_buff *skb
orig_ip = ipv6_hdr(skb_in)->saddr; ipv6_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.in6; - icmpv6_send(skb_in, type, code, info); + __icmpv6_send(skb_in, type, code, info, &parm); ipv6_hdr(skb_in)->saddr = orig_ip; out: consume_skb(cloned_skb);