From d163a925ebbc6eb5b562b0f1d72c7e817aa75c40 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 7 Apr 2021 21:43:40 +0200 Subject: netfilter: arp_tables: add pre_exit hook for table unregister Same problem that also existed in iptables/ip(6)tables, when arptable_filter is removed there is no longer a wait period before the table/ruleset is free'd. Unregister the hook in pre_exit, then remove the table in the exit function. This used to work correctly because the old nf_hook_unregister API did unconditional synchronize_net. The per-net hook unregister function uses call_rcu instead. Fixes: b9e69e127397 ("netfilter: xtables: don't hook tables by default") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/arp_tables.c | 9 +++++++-- net/ipv4/netfilter/arptable_filter.c | 10 +++++++++- 2 files changed, 16 insertions(+), 3 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index d1e04d2b5170..6c26533480dd 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1539,10 +1539,15 @@ out_free: return ret; } -void arpt_unregister_table(struct net *net, struct xt_table *table, - const struct nf_hook_ops *ops) +void arpt_unregister_table_pre_exit(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops) { nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); +} +EXPORT_SYMBOL(arpt_unregister_table_pre_exit); + +void arpt_unregister_table(struct net *net, struct xt_table *table) +{ __arpt_unregister_table(net, table); } diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index c216b9ad3bb2..6c300ba5634e 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -56,16 +56,24 @@ static int __net_init arptable_filter_table_init(struct net *net) return err; } +static void __net_exit arptable_filter_net_pre_exit(struct net *net) +{ + if (net->ipv4.arptable_filter) + arpt_unregister_table_pre_exit(net, net->ipv4.arptable_filter, + arpfilter_ops); +} + static void __net_exit arptable_filter_net_exit(struct net *net) { if (!net->ipv4.arptable_filter) return; - arpt_unregister_table(net, net->ipv4.arptable_filter, arpfilter_ops); + arpt_unregister_table(net, net->ipv4.arptable_filter); net->ipv4.arptable_filter = NULL; } static struct pernet_operations arptable_filter_net_ops = { .exit = arptable_filter_net_exit, + .pre_exit = arptable_filter_net_pre_exit, }; static int __init arptable_filter_init(void) -- cgit v1.2.3 From b29c457a6511435960115c0f548c4360d5f4801d Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 7 Apr 2021 21:38:57 +0200 Subject: netfilter: x_tables: fix compat match/target pad out-of-bound write xt_compat_match/target_from_user doesn't check that zeroing the area to start of next rule won't write past end of allocated ruleset blob. Remove this code and zero the entire blob beforehand. Reported-by: syzbot+cfc0247ac173f597aaaa@syzkaller.appspotmail.com Reported-by: Andy Nguyen Fixes: 9fa492cdc160c ("[NETFILTER]: x_tables: simplify compat API") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/arp_tables.c | 2 ++ net/ipv4/netfilter/ip_tables.c | 2 ++ net/ipv6/netfilter/ip6_tables.c | 2 ++ net/netfilter/x_tables.c | 10 ++-------- 4 files changed, 8 insertions(+), 8 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 6c26533480dd..d6d45d820d79 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1193,6 +1193,8 @@ static int translate_compat_table(struct net *net, if (!newinfo) goto out_unlock; + memset(newinfo->entries, 0, size); + newinfo->number = compatr->num_entries; for (i = 0; i < NF_ARP_NUMHOOKS; i++) { newinfo->hook_entry[i] = compatr->hook_entry[i]; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index f15bc21d7301..f77ea0dbe656 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1428,6 +1428,8 @@ translate_compat_table(struct net *net, if (!newinfo) goto out_unlock; + memset(newinfo->entries, 0, size); + newinfo->number = compatr->num_entries; for (i = 0; i < NF_INET_NUMHOOKS; i++) { newinfo->hook_entry[i] = compatr->hook_entry[i]; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 2e2119bfcf13..eb2b5404806c 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1443,6 +1443,8 @@ translate_compat_table(struct net *net, if (!newinfo) goto out_unlock; + memset(newinfo->entries, 0, size); + newinfo->number = compatr->num_entries; for (i = 0; i < NF_INET_NUMHOOKS; i++) { newinfo->hook_entry[i] = compatr->hook_entry[i]; diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 6bd31a7a27fc..92e9d4ebc5e8 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -733,7 +733,7 @@ void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr, { const struct xt_match *match = m->u.kernel.match; struct compat_xt_entry_match *cm = (struct compat_xt_entry_match *)m; - int pad, off = xt_compat_match_offset(match); + int off = xt_compat_match_offset(match); u_int16_t msize = cm->u.user.match_size; char name[sizeof(m->u.user.name)]; @@ -743,9 +743,6 @@ void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr, match->compat_from_user(m->data, cm->data); else memcpy(m->data, cm->data, msize - sizeof(*cm)); - pad = XT_ALIGN(match->matchsize) - match->matchsize; - if (pad > 0) - memset(m->data + match->matchsize, 0, pad); msize += off; m->u.user.match_size = msize; @@ -1116,7 +1113,7 @@ void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr, { const struct xt_target *target = t->u.kernel.target; struct compat_xt_entry_target *ct = (struct compat_xt_entry_target *)t; - int pad, off = xt_compat_target_offset(target); + int off = xt_compat_target_offset(target); u_int16_t tsize = ct->u.user.target_size; char name[sizeof(t->u.user.name)]; @@ -1126,9 +1123,6 @@ void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr, target->compat_from_user(t->data, ct->data); else memcpy(t->data, ct->data, tsize - sizeof(*ct)); - pad = XT_ALIGN(target->targetsize) - target->targetsize; - if (pad > 0) - memset(t->data + target->targetsize, 0, pad); tsize += off; t->u.user.target_size = tsize; -- cgit v1.2.3 From 97684f0970f6e112926de631fdd98d9693c7e5c1 Mon Sep 17 00:00:00 2001 From: Jonathon Reinhart Date: Tue, 13 Apr 2021 03:08:48 -0400 Subject: net: Make tcp_allowed_congestion_control readonly in non-init netns Currently, tcp_allowed_congestion_control is global and writable; writing to it in any net namespace will leak into all other net namespaces. tcp_available_congestion_control and tcp_allowed_congestion_control are the only sysctls in ipv4_net_table (the per-netns sysctl table) with a NULL data pointer; their handlers (proc_tcp_available_congestion_control and proc_allowed_congestion_control) have no other way of referencing a struct net. Thus, they operate globally. Because ipv4_net_table does not use designated initializers, there is no easy way to fix up this one "bad" table entry. However, the data pointer updating logic shouldn't be applied to NULL pointers anyway, so we instead force these entries to be read-only. These sysctls used to exist in ipv4_table (init-net only), but they were moved to the per-net ipv4_net_table, presumably without realizing that tcp_allowed_congestion_control was writable and thus introduced a leak. Because the intent of that commit was only to know (i.e. read) "which congestion algorithms are available or allowed", this read-only solution should be sufficient. The logic added in recent commit 31c4d2f160eb: ("net: Ensure net namespace isolation of sysctls") does not and cannot check for NULL data pointers, because other table entries (e.g. /proc/sys/net/netfilter/nf_log/) have .data=NULL but use other methods (.extra2) to access the struct net. Fixes: 9cb8e048e5d9 ("net/ipv4/sysctl: show tcp_{allowed, available}_congestion_control in non-initial netns") Signed-off-by: Jonathon Reinhart Signed-off-by: David S. Miller --- net/ipv4/sysctl_net_ipv4.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index f55095d3ed16..60465f077497 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -1378,9 +1378,19 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) if (!table) goto err_alloc; - /* Update the variables to point into the current struct net */ - for (i = 0; i < ARRAY_SIZE(ipv4_net_table) - 1; i++) - table[i].data += (void *)net - (void *)&init_net; + for (i = 0; i < ARRAY_SIZE(ipv4_net_table) - 1; i++) { + if (table[i].data) { + /* Update the variables to point into + * the current struct net + */ + table[i].data += (void *)net - (void *)&init_net; + } else { + /* Entries without data pointer are global; + * Make them read-only in non-init_net ns + */ + table[i].mode &= ~0222; + } + } } net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table); -- cgit v1.2.3