linux/net/sched/act_connmark.c

266 lines
6.5 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* net/sched/act_connmark.c netfilter connmark retriever action
* skb mark is over-written
*
* Copyright (c) 2011 Felix Fietkau <nbd@openwrt.org>
*/
#include <linux/module.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <linux/pkt_cls.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/act_api.h>
net/sched: act_connmark: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action connmark pass index 90 # tc actions replace action connmark \ > goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action connmark had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: connmark zone 0 goto chain 42 index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 302 Comm: kworker/0:2 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff9bea406c3ad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff8c5dfc009f00 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff9bea406c3a80 RDI: ffff8c5dfb9d6ec0 RBP: ffff9bea406c3b70 R08: ffff8c5dfda222a0 R09: ffffffff90933c3c R10: 0000000000000000 R11: 0000000092793f7d R12: ffff8c5df48b3c00 R13: ffff8c5df48b3c08 R14: 0000000000000001 R15: ffff8c5dfb9d6e40 FS: 0000000000000000(0000) GS:ffff8c5dfda00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000062e0e006 CR4: 00000000001606f0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_connmark nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul mbcache crc32_pclmul jbd2 snd_hda_codec_generic ghash_clmulni_intel snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel snd_timer crypto_simd cryptd snd glue_helper joydev virtio_balloon pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper virtio_net net_failover syscopyarea virtio_blk failover virtio_console sysfillrect sysimgblt fb_sys_fops ttm drm ata_piix crc32c_intel serio_raw libata virtio_pci virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_connmark_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 17:00:05 +03:00
#include <net/pkt_cls.h>
#include <uapi/linux/tc_act/tc_connmark.h>
#include <net/tc_act/tc_connmark.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_zones.h>
netns: make struct pernet_operations::id unsigned int Make struct pernet_operations::id unsigned. There are 2 reasons to do so: 1) This field is really an index into an zero based array and thus is unsigned entity. Using negative value is out-of-bound access by definition. 2) On x86_64 unsigned 32-bit data which are mixed with pointers via array indexing or offsets added or subtracted to pointers are preffered to signed 32-bit data. "int" being used as an array index needs to be sign-extended to 64-bit before being used. void f(long *p, int i) { g(p[i]); } roughly translates to movsx rsi, esi mov rdi, [rsi+...] call g MOVSX is 3 byte instruction which isn't necessary if the variable is unsigned because x86_64 is zero extending by default. Now, there is net_generic() function which, you guessed it right, uses "int" as an array index: static inline void *net_generic(const struct net *net, int id) { ... ptr = ng->ptr[id - 1]; ... } And this function is used a lot, so those sign extensions add up. Patch snipes ~1730 bytes on allyesconfig kernel (without all junk messing with code generation): add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730) Unfortunately some functions actually grow bigger. This is a semmingly random artefact of code generation with register allocator being used differently. gcc decides that some variable needs to live in new r8+ registers and every access now requires REX prefix. Or it is shifted into r12, so [r12+0] addressing mode has to be used which is longer than [r8] However, overall balance is in negative direction: add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730) function old new delta nfsd4_lock 3886 3959 +73 tipc_link_build_proto_msg 1096 1140 +44 mac80211_hwsim_new_radio 2776 2808 +32 tipc_mon_rcv 1032 1058 +26 svcauth_gss_legacy_init 1413 1429 +16 tipc_bcbase_select_primary 379 392 +13 nfsd4_exchange_id 1247 1260 +13 nfsd4_setclientid_confirm 782 793 +11 ... put_client_renew_locked 494 480 -14 ip_set_sockfn_get 730 716 -14 geneve_sock_add 829 813 -16 nfsd4_sequence_done 721 703 -18 nlmclnt_lookup_host 708 686 -22 nfsd4_lockt 1085 1063 -22 nfs_get_client 1077 1050 -27 tcf_bpf_init 1106 1076 -30 nfsd4_encode_fattr 5997 5930 -67 Total: Before=154856051, After=154854321, chg -0.00% Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-17 04:58:21 +03:00
static unsigned int connmark_net_id;
static struct tc_action_ops act_connmark_ops;
static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
const struct nf_conntrack_tuple_hash *thash;
struct nf_conntrack_tuple tuple;
enum ip_conntrack_info ctinfo;
struct tcf_connmark_info *ca = to_connmark(a);
struct nf_conntrack_zone zone;
struct nf_conn *c;
int proto;
spin_lock(&ca->tcf_lock);
tcf_lastuse_update(&ca->tcf_tm);
bstats_update(&ca->tcf_bstats, skb);
sched: consistently handle layer3 header accesses in the presence of VLANs There are a couple of places in net/sched/ that check skb->protocol and act on the value there. However, in the presence of VLAN tags, the value stored in skb->protocol can be inconsistent based on whether VLAN acceleration is enabled. The commit quoted in the Fixes tag below fixed the users of skb->protocol to use a helper that will always see the VLAN ethertype. However, most of the callers don't actually handle the VLAN ethertype, but expect to find the IP header type in the protocol field. This means that things like changing the ECN field, or parsing diffserv values, stops working if there's a VLAN tag, or if there are multiple nested VLAN tags (QinQ). To fix this, change the helper to take an argument that indicates whether the caller wants to skip the VLAN tags or not. When skipping VLAN tags, we make sure to skip all of them, so behaviour is consistent even in QinQ mode. To make the helper usable from the ECN code, move it to if_vlan.h instead of pkt_sched.h. v3: - Remove empty lines - Move vlan variable definitions inside loop in skb_protocol() - Also use skb_protocol() helper in IP{,6}_ECN_decapsulate() and bpf_skb_ecn_set_ce() v2: - Use eth_type_vlan() helper in skb_protocol() - Also fix code that reads skb->protocol directly - Change a couple of 'if/else if' statements to switch constructs to avoid calling the helper twice Reported-by: Ilya Ponetayev <i.ponetaev@ndmsystems.com> Fixes: d8b9605d2697 ("net: sched: fix skb->protocol use in case of accelerated vlan path") Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-07-03 23:26:43 +03:00
switch (skb_protocol(skb, true)) {
case htons(ETH_P_IP):
if (skb->len < sizeof(struct iphdr))
goto out;
proto = NFPROTO_IPV4;
sched: consistently handle layer3 header accesses in the presence of VLANs There are a couple of places in net/sched/ that check skb->protocol and act on the value there. However, in the presence of VLAN tags, the value stored in skb->protocol can be inconsistent based on whether VLAN acceleration is enabled. The commit quoted in the Fixes tag below fixed the users of skb->protocol to use a helper that will always see the VLAN ethertype. However, most of the callers don't actually handle the VLAN ethertype, but expect to find the IP header type in the protocol field. This means that things like changing the ECN field, or parsing diffserv values, stops working if there's a VLAN tag, or if there are multiple nested VLAN tags (QinQ). To fix this, change the helper to take an argument that indicates whether the caller wants to skip the VLAN tags or not. When skipping VLAN tags, we make sure to skip all of them, so behaviour is consistent even in QinQ mode. To make the helper usable from the ECN code, move it to if_vlan.h instead of pkt_sched.h. v3: - Remove empty lines - Move vlan variable definitions inside loop in skb_protocol() - Also use skb_protocol() helper in IP{,6}_ECN_decapsulate() and bpf_skb_ecn_set_ce() v2: - Use eth_type_vlan() helper in skb_protocol() - Also fix code that reads skb->protocol directly - Change a couple of 'if/else if' statements to switch constructs to avoid calling the helper twice Reported-by: Ilya Ponetayev <i.ponetaev@ndmsystems.com> Fixes: d8b9605d2697 ("net: sched: fix skb->protocol use in case of accelerated vlan path") Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-07-03 23:26:43 +03:00
break;
case htons(ETH_P_IPV6):
if (skb->len < sizeof(struct ipv6hdr))
goto out;
proto = NFPROTO_IPV6;
sched: consistently handle layer3 header accesses in the presence of VLANs There are a couple of places in net/sched/ that check skb->protocol and act on the value there. However, in the presence of VLAN tags, the value stored in skb->protocol can be inconsistent based on whether VLAN acceleration is enabled. The commit quoted in the Fixes tag below fixed the users of skb->protocol to use a helper that will always see the VLAN ethertype. However, most of the callers don't actually handle the VLAN ethertype, but expect to find the IP header type in the protocol field. This means that things like changing the ECN field, or parsing diffserv values, stops working if there's a VLAN tag, or if there are multiple nested VLAN tags (QinQ). To fix this, change the helper to take an argument that indicates whether the caller wants to skip the VLAN tags or not. When skipping VLAN tags, we make sure to skip all of them, so behaviour is consistent even in QinQ mode. To make the helper usable from the ECN code, move it to if_vlan.h instead of pkt_sched.h. v3: - Remove empty lines - Move vlan variable definitions inside loop in skb_protocol() - Also use skb_protocol() helper in IP{,6}_ECN_decapsulate() and bpf_skb_ecn_set_ce() v2: - Use eth_type_vlan() helper in skb_protocol() - Also fix code that reads skb->protocol directly - Change a couple of 'if/else if' statements to switch constructs to avoid calling the helper twice Reported-by: Ilya Ponetayev <i.ponetaev@ndmsystems.com> Fixes: d8b9605d2697 ("net: sched: fix skb->protocol use in case of accelerated vlan path") Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-07-03 23:26:43 +03:00
break;
default:
goto out;
}
c = nf_ct_get(skb, &ctinfo);
if (c) {
skb->mark = c->mark;
/* using overlimits stats to count how many packets marked */
ca->tcf_qstats.overlimits++;
goto out;
}
if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb),
proto, ca->net, &tuple))
goto out;
zone.id = ca->zone;
netfilter: nf_conntrack: add direction support for zones This work adds a direction parameter to netfilter zones, so identity separation can be performed only in original/reply or both directions (default). This basically opens up the possibility of doing NAT with conflicting IP address/port tuples from multiple, isolated tenants on a host (e.g. from a netns) without requiring each tenant to NAT twice resp. to use its own dedicated IP address to SNAT to, meaning overlapping tuples can be made unique with the zone identifier in original direction, where the NAT engine will then allocate a unique tuple in the commonly shared default zone for the reply direction. In some restricted, local DNAT cases, also port redirection could be used for making the reply traffic unique w/o requiring SNAT. The consensus we've reached and discussed at NFWS and since the initial implementation [1] was to directly integrate the direction meta data into the existing zones infrastructure, as opposed to the ct->mark approach we proposed initially. As we pass the nf_conntrack_zone object directly around, we don't have to touch all call-sites, but only those, that contain equality checks of zones. Thus, based on the current direction (original or reply), we either return the actual id, or the default NF_CT_DEFAULT_ZONE_ID. CT expectations are direction-agnostic entities when expectations are being compared among themselves, so we can only use the identifier in this case. Note that zone identifiers can not be included into the hash mix anymore as they don't contain a "stable" value that would be equal for both directions at all times, f.e. if only zone->id would unconditionally be xor'ed into the table slot hash, then replies won't find the corresponding conntracking entry anymore. If no particular direction is specified when configuring zones, the behaviour is exactly as we expect currently (both directions). Support has been added for the CT netlink interface as well as the x_tables raw CT target, which both already offer existing interfaces to user space for the configuration of zones. Below a minimal, simplified collision example (script in [2]) with netperf sessions: +--- tenant-1 ---+ mark := 1 | netperf |--+ +----------------+ | CT zone := mark [ORIGINAL] [ip,sport] := X +--------------+ +--- gateway ---+ | mark routing |--| SNAT |-- ... + +--------------+ +---------------+ | +--- tenant-2 ---+ | ~~~|~~~ | netperf |--+ +-----------+ | +----------------+ mark := 2 | netserver |------ ... + [ip,sport] := X +-----------+ [ip,port] := Y On the gateway netns, example: iptables -t raw -A PREROUTING -j CT --zone mark --zone-dir ORIGINAL iptables -t nat -A POSTROUTING -o <dev> -j SNAT --to-source <ip> --random-fully iptables -t mangle -A PREROUTING -m conntrack --ctdir ORIGINAL -j CONNMARK --save-mark iptables -t mangle -A POSTROUTING -m conntrack --ctdir REPLY -j CONNMARK --restore-mark conntrack dump from gateway netns: netperf -H 10.1.1.2 -t TCP_STREAM -l60 -p12865,5555 from each tenant netns tcp 6 431995 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=5555 dport=12865 zone-orig=1 src=10.1.1.2 dst=10.1.1.1 sport=12865 dport=1024 [ASSURED] mark=1 secctx=system_u:object_r:unlabeled_t:s0 use=1 tcp 6 431994 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=5555 dport=12865 zone-orig=2 src=10.1.1.2 dst=10.1.1.1 sport=12865 dport=5555 [ASSURED] mark=2 secctx=system_u:object_r:unlabeled_t:s0 use=1 tcp 6 299 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=39438 dport=33768 zone-orig=1 src=10.1.1.2 dst=10.1.1.1 sport=33768 dport=39438 [ASSURED] mark=1 secctx=system_u:object_r:unlabeled_t:s0 use=1 tcp 6 300 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=32889 dport=40206 zone-orig=2 src=10.1.1.2 dst=10.1.1.1 sport=40206 dport=32889 [ASSURED] mark=2 secctx=system_u:object_r:unlabeled_t:s0 use=2 Taking this further, test script in [2] creates 200 tenants and runs original-tuple colliding netperf sessions each. A conntrack -L dump in the gateway netns also confirms 200 overlapping entries, all in ESTABLISHED state as expected. I also did run various other tests with some permutations of the script, to mention some: SNAT in random/random-fully/persistent mode, no zones (no overlaps), static zones (original, reply, both directions), etc. [1] http://thread.gmane.org/gmane.comp.security.firewalls.netfilter.devel/57412/ [2] https://paste.fedoraproject.org/242835/65657871/ Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2015-08-14 17:03:39 +03:00
zone.dir = NF_CT_DEFAULT_ZONE_DIR;
thash = nf_conntrack_find_get(ca->net, &zone, &tuple);
if (!thash)
goto out;
c = nf_ct_tuplehash_to_ctrack(thash);
/* using overlimits stats to count how many packets marked */
ca->tcf_qstats.overlimits++;
skb->mark = c->mark;
nf_ct_put(c);
out:
spin_unlock(&ca->tcf_lock);
return ca->tcf_action;
}
static const struct nla_policy connmark_policy[TCA_CONNMARK_MAX + 1] = {
[TCA_CONNMARK_PARMS] = { .len = sizeof(struct tc_connmark) },
};
static int tcf_connmark_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
int ovr, int bind, bool rtnl_held,
struct tcf_proto *tp, u32 flags,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, connmark_net_id);
struct nlattr *tb[TCA_CONNMARK_MAX + 1];
net/sched: act_connmark: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action connmark pass index 90 # tc actions replace action connmark \ > goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action connmark had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: connmark zone 0 goto chain 42 index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 302 Comm: kworker/0:2 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff9bea406c3ad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff8c5dfc009f00 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff9bea406c3a80 RDI: ffff8c5dfb9d6ec0 RBP: ffff9bea406c3b70 R08: ffff8c5dfda222a0 R09: ffffffff90933c3c R10: 0000000000000000 R11: 0000000092793f7d R12: ffff8c5df48b3c00 R13: ffff8c5df48b3c08 R14: 0000000000000001 R15: ffff8c5dfb9d6e40 FS: 0000000000000000(0000) GS:ffff8c5dfda00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000062e0e006 CR4: 00000000001606f0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_connmark nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul mbcache crc32_pclmul jbd2 snd_hda_codec_generic ghash_clmulni_intel snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel snd_timer crypto_simd cryptd snd glue_helper joydev virtio_balloon pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper virtio_net net_failover syscopyarea virtio_blk failover virtio_console sysfillrect sysimgblt fb_sys_fops ttm drm ata_piix crc32c_intel serio_raw libata virtio_pci virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_connmark_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 17:00:05 +03:00
struct tcf_chain *goto_ch = NULL;
struct tcf_connmark_info *ci;
struct tc_connmark *parm;
net/sched: act_connmark: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action connmark pass index 90 # tc actions replace action connmark \ > goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action connmark had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: connmark zone 0 goto chain 42 index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 302 Comm: kworker/0:2 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff9bea406c3ad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff8c5dfc009f00 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff9bea406c3a80 RDI: ffff8c5dfb9d6ec0 RBP: ffff9bea406c3b70 R08: ffff8c5dfda222a0 R09: ffffffff90933c3c R10: 0000000000000000 R11: 0000000092793f7d R12: ffff8c5df48b3c00 R13: ffff8c5df48b3c08 R14: 0000000000000001 R15: ffff8c5dfb9d6e40 FS: 0000000000000000(0000) GS:ffff8c5dfda00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000062e0e006 CR4: 00000000001606f0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_connmark nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul mbcache crc32_pclmul jbd2 snd_hda_codec_generic ghash_clmulni_intel snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel snd_timer crypto_simd cryptd snd glue_helper joydev virtio_balloon pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper virtio_net net_failover syscopyarea virtio_blk failover virtio_console sysfillrect sysimgblt fb_sys_fops ttm drm ata_piix crc32c_intel serio_raw libata virtio_pci virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_connmark_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 17:00:05 +03:00
int ret = 0, err;
u32 index;
if (!nla)
return -EINVAL;
netlink: make validation more configurable for future strictness We currently have two levels of strict validation: 1) liberal (default) - undefined (type >= max) & NLA_UNSPEC attributes accepted - attribute length >= expected accepted - garbage at end of message accepted 2) strict (opt-in) - NLA_UNSPEC attributes accepted - attribute length >= expected accepted Split out parsing strictness into four different options: * TRAILING - check that there's no trailing data after parsing attributes (in message or nested) * MAXTYPE - reject attrs > max known type * UNSPEC - reject attributes with NLA_UNSPEC policy entries * STRICT_ATTRS - strictly validate attribute size The default for future things should be *everything*. The current *_strict() is a combination of TRAILING and MAXTYPE, and is renamed to _deprecated_strict(). The current regular parsing has none of this, and is renamed to *_parse_deprecated(). Additionally it allows us to selectively set one of the new flags even on old policies. Notably, the UNSPEC flag could be useful in this case, since it can be arranged (by filling in the policy) to not be an incompatible userspace ABI change, but would then going forward prevent forgetting attribute entries. Similar can apply to the POLICY flag. We end up with the following renames: * nla_parse -> nla_parse_deprecated * nla_parse_strict -> nla_parse_deprecated_strict * nlmsg_parse -> nlmsg_parse_deprecated * nlmsg_parse_strict -> nlmsg_parse_deprecated_strict * nla_parse_nested -> nla_parse_nested_deprecated * nla_validate_nested -> nla_validate_nested_deprecated Using spatch, of course: @@ expression TB, MAX, HEAD, LEN, POL, EXT; @@ -nla_parse(TB, MAX, HEAD, LEN, POL, EXT) +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression TB, MAX, NLA, POL, EXT; @@ -nla_parse_nested(TB, MAX, NLA, POL, EXT) +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT) @@ expression START, MAX, POL, EXT; @@ -nla_validate_nested(START, MAX, POL, EXT) +nla_validate_nested_deprecated(START, MAX, POL, EXT) @@ expression NLH, HDRLEN, MAX, POL, EXT; @@ -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT) +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT) For this patch, don't actually add the strict, non-renamed versions yet so that it breaks compile if I get it wrong. Also, while at it, make nla_validate and nla_parse go down to a common __nla_validate_parse() function to avoid code duplication. Ultimately, this allows us to have very strict validation for every new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the next patch, while existing things will continue to work as is. In effect then, this adds fully strict validation for any new command. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 15:07:28 +03:00
ret = nla_parse_nested_deprecated(tb, TCA_CONNMARK_MAX, nla,
connmark_policy, NULL);
if (ret < 0)
return ret;
act_connmark: avoid crashing on malformed nlattrs with null parms tcf_connmark_init does not check in its configuration if TCA_CONNMARK_PARMS is set, resulting in a null pointer dereference when trying to access it. [501099.043007] BUG: unable to handle kernel NULL pointer dereference at 0000000000000004 [501099.043039] IP: [<ffffffffc10c60fb>] tcf_connmark_init+0x8b/0x180 [act_connmark] ... [501099.044334] Call Trace: [501099.044345] [<ffffffffa47270e8>] ? tcf_action_init_1+0x198/0x1b0 [501099.044363] [<ffffffffa47271b0>] ? tcf_action_init+0xb0/0x120 [501099.044380] [<ffffffffa47250a4>] ? tcf_exts_validate+0xc4/0x110 [501099.044398] [<ffffffffc0f5fa97>] ? u32_set_parms+0xa7/0x270 [cls_u32] [501099.044417] [<ffffffffc0f60bf0>] ? u32_change+0x680/0x87b [cls_u32] [501099.044436] [<ffffffffa4725d1d>] ? tc_ctl_tfilter+0x4dd/0x8a0 [501099.044454] [<ffffffffa44a23a1>] ? security_capable+0x41/0x60 [501099.044471] [<ffffffffa470ca01>] ? rtnetlink_rcv_msg+0xe1/0x220 [501099.044490] [<ffffffffa470c920>] ? rtnl_newlink+0x870/0x870 [501099.044507] [<ffffffffa472cc61>] ? netlink_rcv_skb+0xa1/0xc0 [501099.044524] [<ffffffffa47073f4>] ? rtnetlink_rcv+0x24/0x30 [501099.044541] [<ffffffffa472c634>] ? netlink_unicast+0x184/0x230 [501099.044558] [<ffffffffa472c9d8>] ? netlink_sendmsg+0x2f8/0x3b0 [501099.044576] [<ffffffffa46d8880>] ? sock_sendmsg+0x30/0x40 [501099.044592] [<ffffffffa46d8e03>] ? SYSC_sendto+0xd3/0x150 [501099.044608] [<ffffffffa425fda1>] ? __do_page_fault+0x2d1/0x510 [501099.044626] [<ffffffffa47fbd7b>] ? system_call_fast_compare_end+0xc/0x9b Fixes: 22a5dc0e5e3e ("net: sched: Introduce connmark action") Signed-off-by: Étienne Noss <etienne.noss@wifirst.fr> Signed-off-by: Victorien Molle <victorien.molle@wifirst.fr> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-10 18:55:32 +03:00
if (!tb[TCA_CONNMARK_PARMS])
return -EINVAL;
parm = nla_data(tb[TCA_CONNMARK_PARMS]);
index = parm->index;
ret = tcf_idr_check_alloc(tn, &index, a, bind);
if (!ret) {
ret = tcf_idr_create(tn, index, est, a,
&act_connmark_ops, bind, false, 0);
if (ret) {
tcf_idr_cleanup(tn, index);
return ret;
}
ci = to_connmark(*a);
net/sched: act_connmark: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action connmark pass index 90 # tc actions replace action connmark \ > goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action connmark had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: connmark zone 0 goto chain 42 index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 302 Comm: kworker/0:2 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff9bea406c3ad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff8c5dfc009f00 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff9bea406c3a80 RDI: ffff8c5dfb9d6ec0 RBP: ffff9bea406c3b70 R08: ffff8c5dfda222a0 R09: ffffffff90933c3c R10: 0000000000000000 R11: 0000000092793f7d R12: ffff8c5df48b3c00 R13: ffff8c5df48b3c08 R14: 0000000000000001 R15: ffff8c5dfb9d6e40 FS: 0000000000000000(0000) GS:ffff8c5dfda00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000062e0e006 CR4: 00000000001606f0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_connmark nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul mbcache crc32_pclmul jbd2 snd_hda_codec_generic ghash_clmulni_intel snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel snd_timer crypto_simd cryptd snd glue_helper joydev virtio_balloon pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper virtio_net net_failover syscopyarea virtio_blk failover virtio_console sysfillrect sysimgblt fb_sys_fops ttm drm ata_piix crc32c_intel serio_raw libata virtio_pci virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_connmark_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 17:00:05 +03:00
err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch,
extack);
if (err < 0)
goto release_idr;
tcf_action_set_ctrlact(*a, parm->action, goto_ch);
ci->net = net;
ci->zone = parm->zone;
ret = ACT_P_CREATED;
} else if (ret > 0) {
ci = to_connmark(*a);
if (bind)
return 0;
if (!ovr) {
tcf_idr_release(*a, bind);
return -EEXIST;
}
net/sched: act_connmark: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action connmark pass index 90 # tc actions replace action connmark \ > goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action connmark had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: connmark zone 0 goto chain 42 index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 302 Comm: kworker/0:2 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff9bea406c3ad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff8c5dfc009f00 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff9bea406c3a80 RDI: ffff8c5dfb9d6ec0 RBP: ffff9bea406c3b70 R08: ffff8c5dfda222a0 R09: ffffffff90933c3c R10: 0000000000000000 R11: 0000000092793f7d R12: ffff8c5df48b3c00 R13: ffff8c5df48b3c08 R14: 0000000000000001 R15: ffff8c5dfb9d6e40 FS: 0000000000000000(0000) GS:ffff8c5dfda00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000062e0e006 CR4: 00000000001606f0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_connmark nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul mbcache crc32_pclmul jbd2 snd_hda_codec_generic ghash_clmulni_intel snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel snd_timer crypto_simd cryptd snd glue_helper joydev virtio_balloon pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper virtio_net net_failover syscopyarea virtio_blk failover virtio_console sysfillrect sysimgblt fb_sys_fops ttm drm ata_piix crc32c_intel serio_raw libata virtio_pci virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_connmark_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 17:00:05 +03:00
err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch,
extack);
if (err < 0)
goto release_idr;
/* replacing action and zone */
spin_lock_bh(&ci->tcf_lock);
net/sched: act_connmark: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action connmark pass index 90 # tc actions replace action connmark \ > goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action connmark had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: connmark zone 0 goto chain 42 index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 302 Comm: kworker/0:2 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff9bea406c3ad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff8c5dfc009f00 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff9bea406c3a80 RDI: ffff8c5dfb9d6ec0 RBP: ffff9bea406c3b70 R08: ffff8c5dfda222a0 R09: ffffffff90933c3c R10: 0000000000000000 R11: 0000000092793f7d R12: ffff8c5df48b3c00 R13: ffff8c5df48b3c08 R14: 0000000000000001 R15: ffff8c5dfb9d6e40 FS: 0000000000000000(0000) GS:ffff8c5dfda00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000062e0e006 CR4: 00000000001606f0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_connmark nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul mbcache crc32_pclmul jbd2 snd_hda_codec_generic ghash_clmulni_intel snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel snd_timer crypto_simd cryptd snd glue_helper joydev virtio_balloon pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper virtio_net net_failover syscopyarea virtio_blk failover virtio_console sysfillrect sysimgblt fb_sys_fops ttm drm ata_piix crc32c_intel serio_raw libata virtio_pci virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_connmark_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 17:00:05 +03:00
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
ci->zone = parm->zone;
spin_unlock_bh(&ci->tcf_lock);
net/sched: act_connmark: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action connmark pass index 90 # tc actions replace action connmark \ > goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action connmark had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: connmark zone 0 goto chain 42 index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 302 Comm: kworker/0:2 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff9bea406c3ad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff8c5dfc009f00 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff9bea406c3a80 RDI: ffff8c5dfb9d6ec0 RBP: ffff9bea406c3b70 R08: ffff8c5dfda222a0 R09: ffffffff90933c3c R10: 0000000000000000 R11: 0000000092793f7d R12: ffff8c5df48b3c00 R13: ffff8c5df48b3c08 R14: 0000000000000001 R15: ffff8c5dfb9d6e40 FS: 0000000000000000(0000) GS:ffff8c5dfda00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000062e0e006 CR4: 00000000001606f0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_connmark nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul mbcache crc32_pclmul jbd2 snd_hda_codec_generic ghash_clmulni_intel snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel snd_timer crypto_simd cryptd snd glue_helper joydev virtio_balloon pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper virtio_net net_failover syscopyarea virtio_blk failover virtio_console sysfillrect sysimgblt fb_sys_fops ttm drm ata_piix crc32c_intel serio_raw libata virtio_pci virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_connmark_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 17:00:05 +03:00
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
ret = 0;
}
return ret;
net/sched: act_connmark: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action connmark pass index 90 # tc actions replace action connmark \ > goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action connmark had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: connmark zone 0 goto chain 42 index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 302 Comm: kworker/0:2 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff9bea406c3ad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff8c5dfc009f00 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff9bea406c3a80 RDI: ffff8c5dfb9d6ec0 RBP: ffff9bea406c3b70 R08: ffff8c5dfda222a0 R09: ffffffff90933c3c R10: 0000000000000000 R11: 0000000092793f7d R12: ffff8c5df48b3c00 R13: ffff8c5df48b3c08 R14: 0000000000000001 R15: ffff8c5dfb9d6e40 FS: 0000000000000000(0000) GS:ffff8c5dfda00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000062e0e006 CR4: 00000000001606f0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_connmark nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul mbcache crc32_pclmul jbd2 snd_hda_codec_generic ghash_clmulni_intel snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel snd_timer crypto_simd cryptd snd glue_helper joydev virtio_balloon pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper virtio_net net_failover syscopyarea virtio_blk failover virtio_console sysfillrect sysimgblt fb_sys_fops ttm drm ata_piix crc32c_intel serio_raw libata virtio_pci virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_connmark_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 17:00:05 +03:00
release_idr:
tcf_idr_release(*a, bind);
return err;
}
static inline int tcf_connmark_dump(struct sk_buff *skb, struct tc_action *a,
int bind, int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_connmark_info *ci = to_connmark(a);
struct tc_connmark opt = {
.index = ci->tcf_index,
.refcnt = refcount_read(&ci->tcf_refcnt) - ref,
.bindcnt = atomic_read(&ci->tcf_bindcnt) - bind,
};
struct tcf_t t;
spin_lock_bh(&ci->tcf_lock);
opt.action = ci->tcf_action;
opt.zone = ci->zone;
if (nla_put(skb, TCA_CONNMARK_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
tcf_tm_dump(&t, &ci->tcf_tm);
if (nla_put_64bit(skb, TCA_CONNMARK_TM, sizeof(t), &t,
TCA_CONNMARK_PAD))
goto nla_put_failure;
spin_unlock_bh(&ci->tcf_lock);
return skb->len;
nla_put_failure:
spin_unlock_bh(&ci->tcf_lock);
nlmsg_trim(skb, b);
return -1;
}
static int tcf_connmark_walker(struct net *net, struct sk_buff *skb,
struct netlink_callback *cb, int type,
const struct tc_action_ops *ops,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, connmark_net_id);
return tcf_generic_walker(tn, skb, cb, type, ops, extack);
}
static int tcf_connmark_search(struct net *net, struct tc_action **a, u32 index)
{
struct tc_action_net *tn = net_generic(net, connmark_net_id);
return tcf_idr_search(tn, a, index);
}
static struct tc_action_ops act_connmark_ops = {
.kind = "connmark",
.id = TCA_ID_CONNMARK,
.owner = THIS_MODULE,
.act = tcf_connmark_act,
.dump = tcf_connmark_dump,
.init = tcf_connmark_init,
.walk = tcf_connmark_walker,
.lookup = tcf_connmark_search,
.size = sizeof(struct tcf_connmark_info),
};
static __net_init int connmark_init_net(struct net *net)
{
struct tc_action_net *tn = net_generic(net, connmark_net_id);
return tc_action_net_init(net, tn, &act_connmark_ops);
}
static void __net_exit connmark_exit_net(struct list_head *net_list)
{
tc_action_net_exit(net_list, connmark_net_id);
}
static struct pernet_operations connmark_net_ops = {
.init = connmark_init_net,
.exit_batch = connmark_exit_net,
.id = &connmark_net_id,
.size = sizeof(struct tc_action_net),
};
static int __init connmark_init_module(void)
{
return tcf_register_action(&act_connmark_ops, &connmark_net_ops);
}
static void __exit connmark_cleanup_module(void)
{
tcf_unregister_action(&act_connmark_ops, &connmark_net_ops);
}
module_init(connmark_init_module);
module_exit(connmark_cleanup_module);
MODULE_AUTHOR("Felix Fietkau <nbd@openwrt.org>");
MODULE_DESCRIPTION("Connection tracking mark restoring");
MODULE_LICENSE("GPL");