From: Sabrina Dubroca <sd@queasysnail.net> mainline inclusion from mainline-v6.16-rc1 commit b441cf3f8c4b8576639d20c8eb4aa32917602ecd category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/11221 CVE: CVE-2025-40215 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- The ipcomp fallback tunnels currently get deleted (from the various lists and hashtables) as the last user state that needed that fallback is destroyed (not deleted). If a reference to that user state still exists, the fallback state will remain on the hashtables/lists, triggering the WARN in xfrm_state_fini. Because of those remaining references, the fix in commit f75a2804da39 ("xfrm: destroy xfrm_state synchronously on net exit path") is not complete. We recently fixed one such situation in TCP due to defered freeing of skbs (commit 9b6412e6979f ("tcp: drop secpath at the same time as we currently drop dst")). This can also happen due to IP reassembly: skbs with a secpath remain on the reassembly queue until netns destruction. If we can't guarantee that the queues are flushed by the time xfrm_state_fini runs, there may still be references to a (user) xfrm_state, preventing the timely deletion of the corresponding fallback state. Instead of chasing each instance of skbs holding a secpath one by one, this patch fixes the issue directly within xfrm, by deleting the fallback state as soon as the last user state depending on it has been deleted. Destruction will still happen when the final reference is dropped. A separate lockdep class for the fallback state is required since we're going to lock x->tunnel while x is locked. Fixes: 9d4139c76905 ("netns xfrm: per-netns xfrm_state_all list") Signed-off-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com> Conflicts: include/net/xfrm.h net/xfrm/xfrm_ipcomp.c net/xfrm/xfrm_state.c [commit f531d13bdfe3, 152bca090243 and eb2953d26971 are not backport] Signed-off-by: Dong Chenchen <dongchenchen2@huawei.com> --- include/net/xfrm.h | 1 - net/ipv4/ipcomp.c | 2 ++ net/ipv6/ipcomp6.c | 2 ++ net/ipv6/xfrm6_tunnel.c | 2 +- net/xfrm/xfrm_ipcomp.c | 1 - net/xfrm/xfrm_state.c | 19 ++++++++----------- 6 files changed, 13 insertions(+), 14 deletions(-) diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 8bcf40e4e6e3..75735a0125b3 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -390,7 +390,6 @@ int xfrm_input_register_afinfo(const struct xfrm_input_afinfo *afinfo); int xfrm_input_unregister_afinfo(const struct xfrm_input_afinfo *afinfo); void xfrm_flush_gc(void); -void xfrm_state_delete_tunnel(struct xfrm_state *x); struct xfrm_type { char *description; diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index b42683212c65..1ebfab260708 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -53,6 +53,7 @@ static int ipcomp4_err(struct sk_buff *skb, u32 info) } /* We always hold one tunnel user reference to indicate a tunnel */ +static struct lock_class_key xfrm_state_lock_key; static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x) { struct net *net = xs_net(x); @@ -61,6 +62,7 @@ static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x) t = xfrm_state_alloc(net); if (!t) goto out; + lockdep_set_class(&t->lock, &xfrm_state_lock_key); t->id.proto = IPPROTO_IPIP; t->id.spi = x->props.saddr.a4; diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index daef890460b7..4bc0d4c0be14 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -71,6 +71,7 @@ static int ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return 0; } +static struct lock_class_key xfrm_state_lock_key; static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x) { struct net *net = xs_net(x); @@ -79,6 +80,7 @@ static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x) t = xfrm_state_alloc(net); if (!t) goto out; + lockdep_set_class(&t->lock, &xfrm_state_lock_key); t->id.proto = IPPROTO_IPV6; t->id.spi = xfrm6_tunnel_alloc_spi(net, (xfrm_address_t *)&x->props.saddr); diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index f696d46e6910..61ffc01b6c47 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -331,8 +331,8 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net) struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); unsigned int i; - xfrm_flush_gc(); xfrm_state_flush(net, 0, false, true); + xfrm_flush_gc(); for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i])); diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c index 24ac6805275e..5453c038e35a 100644 --- a/net/xfrm/xfrm_ipcomp.c +++ b/net/xfrm/xfrm_ipcomp.c @@ -327,7 +327,6 @@ void ipcomp_destroy(struct xfrm_state *x) struct ipcomp_data *ipcd = x->data; if (!ipcd) return; - xfrm_state_delete_tunnel(x); mutex_lock(&ipcomp_resource_mutex); ipcomp_free_data(ipcd); mutex_unlock(&ipcomp_resource_mutex); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 3d6694a06534..776bd93c2218 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -661,6 +661,7 @@ void __xfrm_state_destroy(struct xfrm_state *x, bool sync) } EXPORT_SYMBOL(__xfrm_state_destroy); +static void xfrm_state_delete_tunnel(struct xfrm_state *x); int __xfrm_state_delete(struct xfrm_state *x) { struct net *net = xs_net(x); @@ -682,6 +683,8 @@ int __xfrm_state_delete(struct xfrm_state *x) xfrm_dev_state_delete(x); + xfrm_state_delete_tunnel(x); + /* All xfrm_state objects are created by xfrm_state_alloc. * The xfrm_state_alloc call gives a reference, and that * is what we are dropping here. @@ -785,10 +788,7 @@ int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync) err = xfrm_state_delete(x); xfrm_audit_state_delete(x, err ? 0 : 1, task_valid); - if (sync) - xfrm_state_put_sync(x); - else - xfrm_state_put(x); + xfrm_state_put(x); if (!err) cnt++; @@ -2576,20 +2576,17 @@ void xfrm_flush_gc(void) } EXPORT_SYMBOL(xfrm_flush_gc); -/* Temporarily located here until net/xfrm/xfrm_tunnel.c is created */ -void xfrm_state_delete_tunnel(struct xfrm_state *x) +static void xfrm_state_delete_tunnel(struct xfrm_state *x) { if (x->tunnel) { struct xfrm_state *t = x->tunnel; - if (atomic_read(&t->tunnel_users) == 2) + if (atomic_dec_return(&t->tunnel_users) == 1) xfrm_state_delete(t); - atomic_dec(&t->tunnel_users); - xfrm_state_put_sync(t); + xfrm_state_put(t); x->tunnel = NULL; } } -EXPORT_SYMBOL(xfrm_state_delete_tunnel); u32 xfrm_state_mtu(struct xfrm_state *x, int mtu) { @@ -2751,8 +2748,8 @@ void xfrm_state_fini(struct net *net) unsigned int sz; flush_work(&net->xfrm.state_hash_work); - flush_work(&xfrm_state_gc_work); xfrm_state_flush(net, 0, false, true); + flush_work(&xfrm_state_gc_work); WARN_ON(!list_empty(&net->xfrm.state_all)); -- 2.25.1