mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-24 09:50:04 +00:00
dc3ee32e96
Florian Weber reported: > Under full load (unshare() in loop -> OOM conditions) we can > get kernel panic: > > BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 > IP: [<ffffffff81476c85>] nfqnl_nf_hook_drop+0x35/0x70 > [..] > task: ffff88012dfa3840 ti: ffff88012dffc000 task.ti: ffff88012dffc000 > RIP: 0010:[<ffffffff81476c85>] [<ffffffff81476c85>] nfqnl_nf_hook_drop+0x35/0x70 > RSP: 0000:ffff88012dfffd80 EFLAGS: 00010206 > RAX: 0000000000000008 RBX: ffffffff81add0c0 RCX: ffff88013fd80000 > [..] > Call Trace: > [<ffffffff81474d98>] nf_queue_nf_hook_drop+0x18/0x20 > [<ffffffff814738eb>] nf_unregister_net_hook+0xdb/0x150 > [<ffffffff8147398f>] netfilter_net_exit+0x2f/0x60 > [<ffffffff8141b088>] ops_exit_list.isra.4+0x38/0x60 > [<ffffffff8141b652>] setup_net+0xc2/0x120 > [<ffffffff8141bd09>] copy_net_ns+0x79/0x120 > [<ffffffff8106965b>] create_new_namespaces+0x11b/0x1e0 > [<ffffffff810698a7>] unshare_nsproxy_namespaces+0x57/0xa0 > [<ffffffff8104baa2>] SyS_unshare+0x1b2/0x340 > [<ffffffff81608276>] entry_SYSCALL_64_fastpath+0x1e/0xa8 > Code: 65 00 48 89 e5 41 56 41 55 41 54 53 83 e8 01 48 8b 97 70 12 00 00 48 98 49 89 f4 4c 8b 74 c2 18 4d 8d 6e 08 49 81 c6 88 00 00 00 <49> 8b 5d 00 48 85 db 74 1a 48 89 df 4c 89 e2 48 c7 c6 90 68 47 > The simple fix for this requires a new pernet variable for struct nf_queue that indicates when it is safe to use the dynamically allocated nf_queue state. As we need a variable anyway make nf_register_queue_handler and nf_unregister_queue_handler pernet. This allows the existing logic of when it is safe to use the state from the nfnetlink_queue module to be reused with no changes except for making it per net. The syncrhonize_rcu from nf_unregister_queue_handler is moved to a new function nfnl_queue_net_exit_batch so that the worst case of having a syncrhonize_rcu in the pernet exit path is not experienced in batch mode. Reported-by: Florian Westphal <fw@strlen.de> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Acked-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
96 lines
2.6 KiB
C
96 lines
2.6 KiB
C
#ifndef _NF_QUEUE_H
|
|
#define _NF_QUEUE_H
|
|
|
|
#include <linux/ip.h>
|
|
#include <linux/ipv6.h>
|
|
#include <linux/jhash.h>
|
|
|
|
/* Each queued (to userspace) skbuff has one of these. */
|
|
struct nf_queue_entry {
|
|
struct list_head list;
|
|
struct sk_buff *skb;
|
|
unsigned int id;
|
|
|
|
struct nf_hook_ops *elem;
|
|
struct nf_hook_state state;
|
|
u16 size; /* sizeof(entry) + saved route keys */
|
|
|
|
/* extra space to store route keys */
|
|
};
|
|
|
|
#define nf_queue_entry_reroute(x) ((void *)x + sizeof(struct nf_queue_entry))
|
|
|
|
/* Packet queuing */
|
|
struct nf_queue_handler {
|
|
int (*outfn)(struct nf_queue_entry *entry,
|
|
unsigned int queuenum);
|
|
void (*nf_hook_drop)(struct net *net,
|
|
struct nf_hook_ops *ops);
|
|
};
|
|
|
|
void nf_register_queue_handler(struct net *net, const struct nf_queue_handler *qh);
|
|
void nf_unregister_queue_handler(struct net *net);
|
|
void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict);
|
|
|
|
void nf_queue_entry_get_refs(struct nf_queue_entry *entry);
|
|
void nf_queue_entry_release_refs(struct nf_queue_entry *entry);
|
|
|
|
static inline void init_hashrandom(u32 *jhash_initval)
|
|
{
|
|
while (*jhash_initval == 0)
|
|
*jhash_initval = prandom_u32();
|
|
}
|
|
|
|
static inline u32 hash_v4(const struct sk_buff *skb, u32 jhash_initval)
|
|
{
|
|
const struct iphdr *iph = ip_hdr(skb);
|
|
|
|
/* packets in either direction go into same queue */
|
|
if ((__force u32)iph->saddr < (__force u32)iph->daddr)
|
|
return jhash_3words((__force u32)iph->saddr,
|
|
(__force u32)iph->daddr, iph->protocol, jhash_initval);
|
|
|
|
return jhash_3words((__force u32)iph->daddr,
|
|
(__force u32)iph->saddr, iph->protocol, jhash_initval);
|
|
}
|
|
|
|
#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
|
|
static inline u32 hash_v6(const struct sk_buff *skb, u32 jhash_initval)
|
|
{
|
|
const struct ipv6hdr *ip6h = ipv6_hdr(skb);
|
|
u32 a, b, c;
|
|
|
|
if ((__force u32)ip6h->saddr.s6_addr32[3] <
|
|
(__force u32)ip6h->daddr.s6_addr32[3]) {
|
|
a = (__force u32) ip6h->saddr.s6_addr32[3];
|
|
b = (__force u32) ip6h->daddr.s6_addr32[3];
|
|
} else {
|
|
b = (__force u32) ip6h->saddr.s6_addr32[3];
|
|
a = (__force u32) ip6h->daddr.s6_addr32[3];
|
|
}
|
|
|
|
if ((__force u32)ip6h->saddr.s6_addr32[1] <
|
|
(__force u32)ip6h->daddr.s6_addr32[1])
|
|
c = (__force u32) ip6h->saddr.s6_addr32[1];
|
|
else
|
|
c = (__force u32) ip6h->daddr.s6_addr32[1];
|
|
|
|
return jhash_3words(a, b, c, jhash_initval);
|
|
}
|
|
#endif
|
|
|
|
static inline u32
|
|
nfqueue_hash(const struct sk_buff *skb, u16 queue, u16 queues_total, u8 family,
|
|
u32 jhash_initval)
|
|
{
|
|
if (family == NFPROTO_IPV4)
|
|
queue += ((u64) hash_v4(skb, jhash_initval) * queues_total) >> 32;
|
|
#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
|
|
else if (family == NFPROTO_IPV6)
|
|
queue += ((u64) hash_v6(skb, jhash_initval) * queues_total) >> 32;
|
|
#endif
|
|
|
|
return queue;
|
|
}
|
|
|
|
#endif /* _NF_QUEUE_H */
|