net/sched: act_vlan: validate the control action inside init()

the following script:

# tc qdisc add dev crash0 clsact
# tc filter add dev crash0 egress matchall \
> action vlan pop pass index 90
# tc actions replace action vlan \
> pop goto chain 42 index 90 cookie c1a0c1a0
# tc actions show action vlan

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: vlan pop 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 800000007974f067 P4D 800000007974f067 PUD 79638067 PMD 0
Oops: 0000 [#1] SMP PTI
CPU: 3 PID: 0 Comm: swapper/3 Not tainted 5.0.0-rc4.gotochain_crash+ #536
Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
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:ffff982dfdb83be0 EFLAGS: 00010246
RAX: 000000002000002a RBX: ffff982dfc55db00 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffff982df97099c0 RDI: ffff982dfc55db00
RBP: ffff982dfdb83c80 R08: ffff982df983fec8 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: ffff982df5aacd00
R13: ffff982df5aacd08 R14: 0000000000000001 R15: ffff982df97099c0
FS: 0000000000000000(0000) GS:ffff982dfdb80000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000000 CR3: 00000000796d0005 CR4: 00000000001606e0
Call Trace:
<IRQ>
tcf_classify+0x58/0x120
__dev_queue_xmit+0x40a/0x890
? ip6_finish_output2+0x369/0x590
ip6_finish_output2+0x369/0x590
? ip6_output+0x68/0x110
ip6_output+0x68/0x110
? nf_hook.constprop.35+0x79/0xc0
mld_sendpack+0x16f/0x220
mld_ifc_timer_expire+0x195/0x2c0
? igmp6_timer_handler+0x70/0x70
call_timer_fn+0x2b/0x130
run_timer_softirq+0x3e8/0x440
? enqueue_hrtimer+0x39/0x90
__do_softirq+0xe3/0x2f5
irq_exit+0xf0/0x100
smp_apic_timer_interrupt+0x6c/0x130
apic_timer_interrupt+0xf/0x20
</IRQ>
RIP: 0010:native_safe_halt+0x2/0x10
Code: 7b ff ff ff 7f f3 c3 65 48 8b 04 25 00 5c 01 00 f0 80 48 02 20 48 8b 00 a8 08 74 8b eb c1 90 90 90 90 90 90 90 90 90 90 fb f4 <c3> 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f4 c3 90 90 90 90 90 90
RSP: 0018:ffffa4714038feb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13
RAX: ffffffff840184f0 RBX: 0000000000000003 RCX: 0000000000000000
RDX: 0000000000000001 RSI: 0000000000000000 RDI: 0000001e57d3f387
RBP: 0000000000000003 R08: 001125d9ca39e1eb R09: 0000000000000000
R10: 000000000000027d R11: 000000000009f400 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
? __sched_text_end+0x1/0x1
default_idle+0x1c/0x140
do_idle+0x1c4/0x280
cpu_startup_entry+0x19/0x20
start_secondary+0x1a7/0x200
secondary_startup_64+0xa4/0xb0
Modules linked in: act_vlan veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 snd_hda_codec_generic mbcache crct10dif_pclmul jbd2 snd_hda_intel crc32_pclmul snd_hda_codec ghash_clmulni_intel snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd glue_helper joydev snd_timer virtio_balloon snd pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt virtio_net fb_sys_fops virtio_blk ttm net_failover virtio_console failover ata_piix drm libata crc32c_intel virtio_pci serio_raw virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod
CR2: 0000000000000000

Validating the control action within tcf_vlan_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 <[e-mail]>
Signed-off-by: David S. Miller <[e-mail]>

net/sched/act_vlan.c

···
 #include <linux/if_vlan.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
 
 #include <linux/tc_act/tc_vlan.h>
 #include <net/tc_act/tc_vlan.h>
···
 {
 	struct tc_action_net *tn = net_generic(net, vlan_net_id);
 	struct nlattr *tb[TCA_VLAN_MAX + 1];
+	struct tcf_chain *goto_ch = NULL;
 	struct tcf_vlan_params *p;
 	struct tc_vlan *parm;
 	struct tcf_vlan *v;
···
 		return -EEXIST;
 	}
 
+	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
+	if (err < 0)
+		goto release_idr;
+
 	v = to_vlan(*a);
 
 	p = kzalloc(sizeof(*p), GFP_KERNEL);
 	if (!p) {
-		tcf_idr_release(*a, bind);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto put_chain;
 	}
 
 	p->tcfv_action = action;
···
 	p->tcfv_push_proto = push_proto;
 
 	spin_lock_bh(&v->tcf_lock);
-	v->tcf_action = parm->action;
+	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
 	rcu_swap_protected(v->vlan_p, p, lockdep_is_held(&v->tcf_lock));
 	spin_unlock_bh(&v->tcf_lock);
 
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
 	if (p)
 		kfree_rcu(p, rcu);
 
 	if (ret == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
 	return ret;
+put_chain:
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
+release_idr:
+	tcf_idr_release(*a, bind);
+	return err;
 }
 
 static void tcf_vlan_cleanup(struct tc_action *a)

tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json

···
         "teardown": [
             "$TC actions flush action vlan"
         ]
+    },
+    {
+        "id": "e394",
+        "name": "Replace vlan push action with invalid goto chain control",
+        "category": [
+            "actions",
+            "vlan"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action vlan",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action vlan push id 500 pass index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action vlan push id 500 goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action vlan index 90",
+        "matchPattern": "action order [0-9]+: vlan.*push id 500 protocol 802.1Q priority 0 pass.*index 90 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action vlan"
+        ]
     }
 ]