From 747670fd9a2d1b7774030dba65ca022ba442ce71 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 25 Feb 2022 14:02:41 +0100 Subject: netfilter: nf_queue: don't assume sk is full socket There is no guarantee that state->sk refers to a full socket. If refcount transitions to 0, sock_put calls sk_free which then ends up with garbage fields. I'd like to thank Oleksandr Natalenko and Jiri Benc for considerable debug work and pointing out state->sk oddities. Fixes: ca6fb0651883 ("tcp: attach SYNACK messages to request sockets instead of listener") Tested-by: Oleksandr Natalenko Signed-off-by: Florian Westphal --- net/netfilter/nf_queue.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'net/netfilter/nf_queue.c') diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 6d12afabfe8a..5ab0680db445 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -46,6 +46,15 @@ void nf_unregister_queue_handler(void) } EXPORT_SYMBOL(nf_unregister_queue_handler); +static void nf_queue_sock_put(struct sock *sk) +{ +#ifdef CONFIG_INET + sock_gen_put(sk); +#else + sock_put(sk); +#endif +} + static void nf_queue_entry_release_refs(struct nf_queue_entry *entry) { struct nf_hook_state *state = &entry->state; @@ -54,7 +63,7 @@ static void nf_queue_entry_release_refs(struct nf_queue_entry *entry) dev_put(state->in); dev_put(state->out); if (state->sk) - sock_put(state->sk); + nf_queue_sock_put(state->sk); #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) dev_put(entry->physin); -- cgit v1.2.3-70-g09d2 From c3873070247d9e3c7a6b0cf9bf9b45e8018427b1 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 28 Feb 2022 06:22:22 +0100 Subject: netfilter: nf_queue: fix possible use-after-free Eric Dumazet says: The sock_hold() side seems suspect, because there is no guarantee that sk_refcnt is not already 0. On failure, we cannot queue the packet and need to indicate an error. The packet will be dropped by the caller. v2: split skb prefetch hunk into separate change Fixes: 271b72c7fa82c ("udp: RCU handling for Unicast packets.") Reported-by: Eric Dumazet Reviewed-by: Eric Dumazet Signed-off-by: Florian Westphal --- include/net/netfilter/nf_queue.h | 2 +- net/netfilter/nf_queue.c | 13 +++++++++---- net/netfilter/nfnetlink_queue.c | 12 +++++++++--- 3 files changed, 19 insertions(+), 8 deletions(-) (limited to 'net/netfilter/nf_queue.c') diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index 9eed51e920e8..980daa6e1e3a 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -37,7 +37,7 @@ void nf_register_queue_handler(const struct nf_queue_handler *qh); void nf_unregister_queue_handler(void); void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict); -void nf_queue_entry_get_refs(struct nf_queue_entry *entry); +bool nf_queue_entry_get_refs(struct nf_queue_entry *entry); void nf_queue_entry_free(struct nf_queue_entry *entry); static inline void init_hashrandom(u32 *jhash_initval) diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 5ab0680db445..e39549c55945 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -96,19 +96,21 @@ static void __nf_queue_entry_init_physdevs(struct nf_queue_entry *entry) } /* Bump dev refs so they don't vanish while packet is out */ -void nf_queue_entry_get_refs(struct nf_queue_entry *entry) +bool nf_queue_entry_get_refs(struct nf_queue_entry *entry) { struct nf_hook_state *state = &entry->state; + if (state->sk && !refcount_inc_not_zero(&state->sk->sk_refcnt)) + return false; + dev_hold(state->in); dev_hold(state->out); - if (state->sk) - sock_hold(state->sk); #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) dev_hold(entry->physin); dev_hold(entry->physout); #endif + return true; } EXPORT_SYMBOL_GPL(nf_queue_entry_get_refs); @@ -196,7 +198,10 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state, __nf_queue_entry_init_physdevs(entry); - nf_queue_entry_get_refs(entry); + if (!nf_queue_entry_get_refs(entry)) { + kfree(entry); + return -ENOTCONN; + } switch (entry->state.pf) { case AF_INET: diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index ea2d9c2a44cf..64a6acb6aeae 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -710,9 +710,15 @@ static struct nf_queue_entry * nf_queue_entry_dup(struct nf_queue_entry *e) { struct nf_queue_entry *entry = kmemdup(e, e->size, GFP_ATOMIC); - if (entry) - nf_queue_entry_get_refs(entry); - return entry; + + if (!entry) + return NULL; + + if (nf_queue_entry_get_refs(entry)) + return entry; + + kfree(entry); + return NULL; } #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) -- cgit v1.2.3-70-g09d2 From 3b836da4081fa585cf6c392f62557496f2cb0efe Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 1 Mar 2022 00:46:19 +0100 Subject: netfilter: nf_queue: handle socket prefetch In case someone combines bpf socket assign and nf_queue, then we will queue an skb who references a struct sock that did not have its reference count incremented. As we leave rcu protection, there is no guarantee that skb->sk is still valid. For refcount-less skb->sk case, try to increment the reference count and then override the destructor. In case of failure we have two choices: orphan the skb and 'delete' preselect or let nf_queue() drop the packet. Do the latter, it should not happen during normal operation. Fixes: cf7fbe660f2d ("bpf: Add socket assign support") Acked-by: Joe Stringer Signed-off-by: Florian Westphal --- net/netfilter/nf_queue.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'net/netfilter/nf_queue.c') diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index e39549c55945..63d1516816b1 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -180,6 +180,18 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state, break; } + if (skb_sk_is_prefetched(skb)) { + struct sock *sk = skb->sk; + + if (!sk_is_refcounted(sk)) { + if (!refcount_inc_not_zero(&sk->sk_refcnt)) + return -ENOTCONN; + + /* drop refcount on skb_orphan */ + skb->destructor = sock_edemux; + } + } + entry = kmalloc(sizeof(*entry) + route_key_size, GFP_ATOMIC); if (!entry) return -ENOMEM; -- cgit v1.2.3-70-g09d2