linux/net/sched/act_vlan.c

468 lines
12 KiB
C
Raw Permalink Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us>
*/
#include <linux/module.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <linux/if_vlan.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
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 <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 15:00:14 +01:00
#include <net/pkt_cls.h>
#include <net/tc_wrapper.h>
#include <linux/tc_act/tc_vlan.h>
#include <net/tc_act/tc_vlan.h>
static struct tc_action_ops act_vlan_ops;
TC_INDIRECT_SCOPE int tcf_vlan_act(struct sk_buff *skb,
const struct tc_action *a,
struct tcf_result *res)
{
struct tcf_vlan *v = to_vlan(a);
struct tcf_vlan_params *p;
int action;
int err;
u16 tci;
tcf_lastuse_update(&v->tcf_tm);
tcf_action_update_bstats(&v->common, skb);
/* Ensure 'data' points at mac_header prior calling vlan manipulating
* functions.
*/
if (skb_at_tc_ingress(skb))
skb_push_rcsum(skb, skb->mac_len);
action = READ_ONCE(v->tcf_action);
p = rcu_dereference_bh(v->vlan_p);
switch (p->tcfv_action) {
case TCA_VLAN_ACT_POP:
err = skb_vlan_pop(skb);
if (err)
goto drop;
break;
case TCA_VLAN_ACT_PUSH:
err = skb_vlan_push(skb, p->tcfv_push_proto, p->tcfv_push_vid |
(p->tcfv_push_prio << VLAN_PRIO_SHIFT));
if (err)
goto drop;
break;
case TCA_VLAN_ACT_MODIFY:
/* No-op if no vlan tag (either hw-accel or in-payload) */
if (!skb_vlan_tagged(skb))
goto out;
/* extract existing tag (and guarantee no hw-accel tag) */
if (skb_vlan_tag_present(skb)) {
tci = skb_vlan_tag_get(skb);
__vlan_hwaccel_clear_tag(skb);
} else {
/* in-payload vlan tag, pop it */
err = __skb_vlan_pop(skb, &tci);
if (err)
goto drop;
}
/* replace the vid */
tci = (tci & ~VLAN_VID_MASK) | p->tcfv_push_vid;
/* replace prio bits, if tcfv_push_prio specified */
if (p->tcfv_push_prio_exists) {
tci &= ~VLAN_PRIO_MASK;
tci |= p->tcfv_push_prio << VLAN_PRIO_SHIFT;
}
/* put updated tci as hwaccel tag */
__vlan_hwaccel_put_tag(skb, p->tcfv_push_proto, tci);
break;
case TCA_VLAN_ACT_POP_ETH:
err = skb_eth_pop(skb);
if (err)
goto drop;
break;
case TCA_VLAN_ACT_PUSH_ETH:
err = skb_eth_push(skb, p->tcfv_push_dst, p->tcfv_push_src);
if (err)
goto drop;
break;
default:
BUG();
}
out:
if (skb_at_tc_ingress(skb))
skb_pull_rcsum(skb, skb->mac_len);
tc: adjust network header after 2nd vlan push <tldr> skb network header of the single-tagged vlan packet continues to point the vlan payload (e.g. IP) after second vlan tag is pushed by tc act_vlan. This causes problem at the dissector which expects double-tagged packet network header to point to the inner vlan. The fix is to adjust network header in tcf_act_vlan.c but requires refactoring of skb_vlan_push function. </tldr> Consider the following shell script snippet configuring TC rules on the veth interface: ip link add veth0 type veth peer veth1 ip link set veth0 up ip link set veth1 up tc qdisc add dev veth0 clsact tc filter add dev veth0 ingress pref 10 chain 0 flower \ num_of_vlans 2 cvlan_ethtype 0x800 action goto chain 5 tc filter add dev veth0 ingress pref 20 chain 0 flower \ num_of_vlans 1 action vlan push id 100 \ protocol 0x8100 action goto chain 5 tc filter add dev veth0 ingress pref 30 chain 5 flower \ num_of_vlans 2 cvlan_ethtype 0x800 action simple sdata "success" Sending double-tagged vlan packet with the IP payload inside: cat <<ENDS | text2pcap - - | tcpreplay -i veth1 - 0000 00 00 00 00 00 11 00 00 00 00 00 22 81 00 00 64 ..........."...d 0010 81 00 00 14 08 00 45 04 00 26 04 d2 00 00 7f 11 ......E..&...... 0020 18 ef 0a 00 00 01 14 00 00 02 00 00 00 00 00 12 ................ 0030 e1 c7 00 00 00 00 00 00 00 00 00 00 ............ ENDS will match rule 10, goto rule 30 in chain 5 and correctly emit "success" to the dmesg. OTOH, sending single-tagged vlan packet: cat <<ENDS | text2pcap - - | tcpreplay -i veth1 - 0000 00 00 00 00 00 11 00 00 00 00 00 22 81 00 00 14 ...........".... 0010 08 00 45 04 00 2a 04 d2 00 00 7f 11 18 eb 0a 00 ..E..*.......... 0020 00 01 14 00 00 02 00 00 00 00 00 16 e1 bf 00 00 ................ 0030 00 00 00 00 00 00 00 00 00 00 00 00 ............ ENDS will match rule 20, will push the second vlan tag but will *not* match rule 30. IOW, the match at rule 30 fails if the second vlan was freshly pushed by the kernel. Lets look at __skb_flow_dissect working on the double-tagged vlan packet. Here is the relevant code from around net/core/flow_dissector.c:1277 copy-pasted here for convenience: if (dissector_vlan == FLOW_DISSECTOR_KEY_MAX && skb && skb_vlan_tag_present(skb)) { proto = skb->protocol; } else { vlan = __skb_header_pointer(skb, nhoff, sizeof(_vlan), data, hlen, &_vlan); if (!vlan) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } proto = vlan->h_vlan_encapsulated_proto; nhoff += sizeof(*vlan); } The "else" clause above gets the protocol of the encapsulated packet from the skb data at the network header location. printk debugging has showed that in the good double-tagged packet case proto is htons(0x800 == ETH_P_IP) as expected. However in the single-tagged packet case proto is garbage leading to the failure to match tc filter 30. proto is being set from the skb header pointed by nhoff parameter which is defined at the beginning of __skb_flow_dissect (net/core/flow_dissector.c:1055 in the current version): nhoff = skb_network_offset(skb); Therefore the culprit seems to be that the skb network offset is different between double-tagged packet received from the interface and single-tagged packet having its vlan tag pushed by TC. Lets look at the interesting points of the lifetime of the single/double tagged packets as they traverse our packet flow. Both of them will start at __netif_receive_skb_core where the first vlan tag will be stripped: if (eth_type_vlan(skb->protocol)) { skb = skb_vlan_untag(skb); if (unlikely(!skb)) goto out; } At this stage in double-tagged case skb->data points to the second vlan tag while in single-tagged case skb->data points to the network (eg. IP) header. Looking at TC vlan push action (net/sched/act_vlan.c) we have the following code at tcf_vlan_act (interesting points are in square brackets): if (skb_at_tc_ingress(skb)) [1] skb_push_rcsum(skb, skb->mac_len); .... case TCA_VLAN_ACT_PUSH: err = skb_vlan_push(skb, p->tcfv_push_proto, p->tcfv_push_vid | (p->tcfv_push_prio << VLAN_PRIO_SHIFT), 0); if (err) goto drop; break; .... out: if (skb_at_tc_ingress(skb)) [3] skb_pull_rcsum(skb, skb->mac_len); And skb_vlan_push (net/core/skbuff.c:6204) function does: err = __vlan_insert_tag(skb, skb->vlan_proto, skb_vlan_tag_get(skb)); if (err) return err; skb->protocol = skb->vlan_proto; [2] skb->mac_len += VLAN_HLEN; in the case of pushing the second tag. Lets look at what happens with skb->data of the single-tagged packet at each of the above points: 1. As a result of the skb_push_rcsum, skb->data is moved back to the start of the packet. 2. First VLAN tag is moved from the skb into packet buffer, skb->mac_len is incremented, skb->data still points to the start of the packet. 3. As a result of the skb_pull_rcsum, skb->data is moved forward by the modified skb->mac_len, thus pointing to the network header again. Then __skb_flow_dissect will get confused by having double-tagged vlan packet with the skb->data at the network header. The solution for the bug is to preserve "skb->data at second vlan header" semantics in the skb_vlan_push function. We do this by manipulating skb->network_header rather than skb->mac_len. skb_vlan_push callers are updated to do skb_reset_mac_len. Signed-off-by: Boris Sukholitko <boris.sukholitko@broadcom.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2024-08-22 13:35:08 +03:00
skb_reset_mac_len(skb);
return action;
drop:
tcf_action_inc_drop_qstats(&v->common);
return TC_ACT_SHOT;
}
static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = {
[TCA_VLAN_UNSPEC] = { .strict_start_type = TCA_VLAN_PUSH_ETH_DST },
[TCA_VLAN_PARMS] = { .len = sizeof(struct tc_vlan) },
[TCA_VLAN_PUSH_VLAN_ID] = { .type = NLA_U16 },
[TCA_VLAN_PUSH_VLAN_PROTOCOL] = { .type = NLA_U16 },
[TCA_VLAN_PUSH_VLAN_PRIORITY] = { .type = NLA_U8 },
[TCA_VLAN_PUSH_ETH_DST] = NLA_POLICY_ETH_ADDR,
[TCA_VLAN_PUSH_ETH_SRC] = NLA_POLICY_ETH_ADDR,
};
static int tcf_vlan_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
struct tcf_proto *tp, u32 flags,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, act_vlan_ops.net_id);
bool bind = flags & TCA_ACT_FLAGS_BIND;
struct nlattr *tb[TCA_VLAN_MAX + 1];
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 <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 15:00:14 +01:00
struct tcf_chain *goto_ch = NULL;
bool push_prio_exists = false;
struct tcf_vlan_params *p;
struct tc_vlan *parm;
struct tcf_vlan *v;
int action;
u16 push_vid = 0;
__be16 push_proto = 0;
u8 push_prio = 0;
bool exists = false;
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 14:07:28 +02:00
err = nla_parse_nested_deprecated(tb, TCA_VLAN_MAX, nla, vlan_policy,
NULL);
if (err < 0)
return err;
if (!tb[TCA_VLAN_PARMS])
return -EINVAL;
parm = nla_data(tb[TCA_VLAN_PARMS]);
index = parm->index;
err = tcf_idr_check_alloc(tn, &index, a, bind);
if (err < 0)
return err;
exists = err;
if (exists && bind)
return ACT_P_BOUND;
switch (parm->v_action) {
case TCA_VLAN_ACT_POP:
break;
case TCA_VLAN_ACT_PUSH:
case TCA_VLAN_ACT_MODIFY:
if (!tb[TCA_VLAN_PUSH_VLAN_ID]) {
if (exists)
tcf_idr_release(*a, bind);
else
tcf_idr_cleanup(tn, index);
return -EINVAL;
}
push_vid = nla_get_u16(tb[TCA_VLAN_PUSH_VLAN_ID]);
if (push_vid >= VLAN_VID_MASK) {
if (exists)
tcf_idr_release(*a, bind);
else
tcf_idr_cleanup(tn, index);
return -ERANGE;
}
if (tb[TCA_VLAN_PUSH_VLAN_PROTOCOL]) {
push_proto = nla_get_be16(tb[TCA_VLAN_PUSH_VLAN_PROTOCOL]);
switch (push_proto) {
case htons(ETH_P_8021Q):
case htons(ETH_P_8021AD):
break;
default:
if (exists)
tcf_idr_release(*a, bind);
else
tcf_idr_cleanup(tn, index);
return -EPROTONOSUPPORT;
}
} else {
push_proto = htons(ETH_P_8021Q);
}
push_prio_exists = !!tb[TCA_VLAN_PUSH_VLAN_PRIORITY];
if (push_prio_exists)
push_prio = nla_get_u8(tb[TCA_VLAN_PUSH_VLAN_PRIORITY]);
break;
case TCA_VLAN_ACT_POP_ETH:
break;
case TCA_VLAN_ACT_PUSH_ETH:
if (!tb[TCA_VLAN_PUSH_ETH_DST] || !tb[TCA_VLAN_PUSH_ETH_SRC]) {
if (exists)
tcf_idr_release(*a, bind);
else
tcf_idr_cleanup(tn, index);
return -EINVAL;
}
break;
default:
if (exists)
tcf_idr_release(*a, bind);
else
tcf_idr_cleanup(tn, index);
return -EINVAL;
}
action = parm->v_action;
if (!exists) {
ret = tcf_idr_create_from_flags(tn, index, est, a,
&act_vlan_ops, bind, flags);
if (ret) {
tcf_idr_cleanup(tn, index);
return ret;
}
ret = ACT_P_CREATED;
} else if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
tcf_idr_release(*a, bind);
return -EEXIST;
}
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 <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 15:00:14 +01:00
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) {
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 <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 15:00:14 +01:00
err = -ENOMEM;
goto put_chain;
}
p->tcfv_action = action;
p->tcfv_push_vid = push_vid;
p->tcfv_push_prio = push_prio;
p->tcfv_push_prio_exists = push_prio_exists || action == TCA_VLAN_ACT_PUSH;
p->tcfv_push_proto = push_proto;
if (action == TCA_VLAN_ACT_PUSH_ETH) {
nla_memcpy(&p->tcfv_push_dst, tb[TCA_VLAN_PUSH_ETH_DST],
ETH_ALEN);
nla_memcpy(&p->tcfv_push_src, tb[TCA_VLAN_PUSH_ETH_SRC],
ETH_ALEN);
}
net: sched: always disable bh when taking tcf_lock Recently, ops->init() and ops->dump() of all actions were modified to always obtain tcf_lock when accessing private action state. Actions that don't depend on tcf_lock for synchronization with their data path use non-bh locking API. However, tcf_lock is also used to protect rate estimator stats in softirq context by timer callback. Change ops->init() and ops->dump() of all actions to disable bh when using tcf_lock to prevent deadlock reported by following lockdep warning: [ 105.470398] ================================ [ 105.475014] WARNING: inconsistent lock state [ 105.479628] 4.18.0-rc8+ #664 Not tainted [ 105.483897] -------------------------------- [ 105.488511] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. [ 105.494871] swapper/16/0 [HC0[0]:SC1[1]:HE1:SE0] takes: [ 105.500449] 00000000f86c012e (&(&p->tcfa_lock)->rlock){+.?.}, at: est_fetch_counters+0x3c/0xa0 [ 105.509696] {SOFTIRQ-ON-W} state was registered at: [ 105.514925] _raw_spin_lock+0x2c/0x40 [ 105.519022] tcf_bpf_init+0x579/0x820 [act_bpf] [ 105.523990] tcf_action_init_1+0x4e4/0x660 [ 105.528518] tcf_action_init+0x1ce/0x2d0 [ 105.532880] tcf_exts_validate+0x1d8/0x200 [ 105.537416] fl_change+0x55a/0x268b [cls_flower] [ 105.542469] tc_new_tfilter+0x748/0xa20 [ 105.546738] rtnetlink_rcv_msg+0x56a/0x6d0 [ 105.551268] netlink_rcv_skb+0x18d/0x200 [ 105.555628] netlink_unicast+0x2d0/0x370 [ 105.559990] netlink_sendmsg+0x3b9/0x6a0 [ 105.564349] sock_sendmsg+0x6b/0x80 [ 105.568271] ___sys_sendmsg+0x4a1/0x520 [ 105.572547] __sys_sendmsg+0xd7/0x150 [ 105.576655] do_syscall_64+0x72/0x2c0 [ 105.580757] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 105.586243] irq event stamp: 489296 [ 105.590084] hardirqs last enabled at (489296): [<ffffffffb507e639>] _raw_spin_unlock_irq+0x29/0x40 [ 105.599765] hardirqs last disabled at (489295): [<ffffffffb507e745>] _raw_spin_lock_irq+0x15/0x50 [ 105.609277] softirqs last enabled at (489292): [<ffffffffb413a6a3>] irq_enter+0x83/0xa0 [ 105.618001] softirqs last disabled at (489293): [<ffffffffb413a800>] irq_exit+0x140/0x190 [ 105.626813] other info that might help us debug this: [ 105.633976] Possible unsafe locking scenario: [ 105.640526] CPU0 [ 105.643325] ---- [ 105.646125] lock(&(&p->tcfa_lock)->rlock); [ 105.650747] <Interrupt> [ 105.653717] lock(&(&p->tcfa_lock)->rlock); [ 105.658514] *** DEADLOCK *** [ 105.665349] 1 lock held by swapper/16/0: [ 105.669629] #0: 00000000a640ad99 ((&est->timer)){+.-.}, at: call_timer_fn+0x10b/0x550 [ 105.678200] stack backtrace: [ 105.683194] CPU: 16 PID: 0 Comm: swapper/16 Not tainted 4.18.0-rc8+ #664 [ 105.690249] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 105.698626] Call Trace: [ 105.701421] <IRQ> [ 105.703791] dump_stack+0x92/0xeb [ 105.707461] print_usage_bug+0x336/0x34c [ 105.711744] mark_lock+0x7c9/0x980 [ 105.715500] ? print_shortest_lock_dependencies+0x2e0/0x2e0 [ 105.721424] ? check_usage_forwards+0x230/0x230 [ 105.726315] __lock_acquire+0x923/0x26f0 [ 105.730597] ? debug_show_all_locks+0x240/0x240 [ 105.735478] ? mark_lock+0x493/0x980 [ 105.739412] ? check_chain_key+0x140/0x1f0 [ 105.743861] ? __lock_acquire+0x836/0x26f0 [ 105.748323] ? lock_acquire+0x12e/0x290 [ 105.752516] lock_acquire+0x12e/0x290 [ 105.756539] ? est_fetch_counters+0x3c/0xa0 [ 105.761084] _raw_spin_lock+0x2c/0x40 [ 105.765099] ? est_fetch_counters+0x3c/0xa0 [ 105.769633] est_fetch_counters+0x3c/0xa0 [ 105.773995] est_timer+0x87/0x390 [ 105.777670] ? est_fetch_counters+0xa0/0xa0 [ 105.782210] ? lock_acquire+0x12e/0x290 [ 105.786410] call_timer_fn+0x161/0x550 [ 105.790512] ? est_fetch_counters+0xa0/0xa0 [ 105.795055] ? del_timer_sync+0xd0/0xd0 [ 105.799249] ? __lock_is_held+0x93/0x110 [ 105.803531] ? mark_held_locks+0x20/0xe0 [ 105.807813] ? _raw_spin_unlock_irq+0x29/0x40 [ 105.812525] ? est_fetch_counters+0xa0/0xa0 [ 105.817069] ? est_fetch_counters+0xa0/0xa0 [ 105.821610] run_timer_softirq+0x3c4/0x9f0 [ 105.826064] ? lock_acquire+0x12e/0x290 [ 105.830257] ? __bpf_trace_timer_class+0x10/0x10 [ 105.835237] ? __lock_is_held+0x25/0x110 [ 105.839517] __do_softirq+0x11d/0x7bf [ 105.843542] irq_exit+0x140/0x190 [ 105.847208] smp_apic_timer_interrupt+0xac/0x3b0 [ 105.852182] apic_timer_interrupt+0xf/0x20 [ 105.856628] </IRQ> [ 105.859081] RIP: 0010:cpuidle_enter_state+0xd8/0x4d0 [ 105.864395] Code: 46 ff 48 89 44 24 08 0f 1f 44 00 00 31 ff e8 cf ec 46 ff 80 7c 24 07 00 0f 85 1d 02 00 00 e8 9f 90 4b ff fb 66 0f 1f 44 00 00 <4c> 8b 6c 24 08 4d 29 fd 0f 80 36 03 00 00 4c 89 e8 48 ba cf f7 53 [ 105.884288] RSP: 0018:ffff8803ad94fd20 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 [ 105.892494] RAX: 0000000000000000 RBX: ffffe8fb300829c0 RCX: ffffffffb41e19e1 [ 105.899988] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8803ad9358ac [ 105.907503] RBP: ffffffffb6636300 R08: 0000000000000004 R09: 0000000000000000 [ 105.914997] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000004 [ 105.922487] R13: ffffffffb6636140 R14: ffffffffb66362d8 R15: 000000188d36091b [ 105.929988] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.935232] do_idle+0x28e/0x320 [ 105.938817] ? arch_cpu_idle_exit+0x40/0x40 [ 105.943361] ? mark_lock+0x8c1/0x980 [ 105.947295] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.952619] cpu_startup_entry+0xc2/0xd0 [ 105.956900] ? cpu_in_idle+0x20/0x20 [ 105.960830] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.966146] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.971391] start_secondary+0x2b5/0x360 [ 105.975669] ? set_cpu_sibling_map+0x1330/0x1330 [ 105.980654] secondary_startup_64+0xa5/0xb0 Taking tcf_lock in sample action with bh disabled causes lockdep to issue a warning regarding possible irq lock inversion dependency between tcf_lock, and psample_groups_lock that is taken when holding tcf_lock in sample init: [ 162.108959] Possible interrupt unsafe locking scenario: [ 162.116386] CPU0 CPU1 [ 162.121277] ---- ---- [ 162.126162] lock(psample_groups_lock); [ 162.130447] local_irq_disable(); [ 162.136772] lock(&(&p->tcfa_lock)->rlock); [ 162.143957] lock(psample_groups_lock); [ 162.150813] <Interrupt> [ 162.153808] lock(&(&p->tcfa_lock)->rlock); [ 162.158608] *** DEADLOCK *** In order to prevent potential lock inversion dependency between tcf_lock and psample_groups_lock, extract call to psample_group_get() from tcf_lock protected section in sample action init function. Fixes: 4e232818bd32 ("net: sched: act_mirred: remove dependency on rtnl lock") Fixes: 764e9a24480f ("net: sched: act_vlan: remove dependency on rtnl lock") Fixes: 729e01260989 ("net: sched: act_tunnel_key: remove dependency on rtnl lock") Fixes: d77284956656 ("net: sched: act_sample: remove dependency on rtnl lock") Fixes: e8917f437006 ("net: sched: act_gact: remove dependency on rtnl lock") Fixes: b6a2b971c0b0 ("net: sched: act_csum: remove dependency on rtnl lock") Fixes: 2142236b4584 ("net: sched: act_bpf: remove dependency on rtnl lock") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-14 21:46:16 +03:00
spin_lock_bh(&v->tcf_lock);
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 <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 15:00:14 +01:00
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
p = rcu_replace_pointer(v->vlan_p, p, lockdep_is_held(&v->tcf_lock));
net: sched: always disable bh when taking tcf_lock Recently, ops->init() and ops->dump() of all actions were modified to always obtain tcf_lock when accessing private action state. Actions that don't depend on tcf_lock for synchronization with their data path use non-bh locking API. However, tcf_lock is also used to protect rate estimator stats in softirq context by timer callback. Change ops->init() and ops->dump() of all actions to disable bh when using tcf_lock to prevent deadlock reported by following lockdep warning: [ 105.470398] ================================ [ 105.475014] WARNING: inconsistent lock state [ 105.479628] 4.18.0-rc8+ #664 Not tainted [ 105.483897] -------------------------------- [ 105.488511] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. [ 105.494871] swapper/16/0 [HC0[0]:SC1[1]:HE1:SE0] takes: [ 105.500449] 00000000f86c012e (&(&p->tcfa_lock)->rlock){+.?.}, at: est_fetch_counters+0x3c/0xa0 [ 105.509696] {SOFTIRQ-ON-W} state was registered at: [ 105.514925] _raw_spin_lock+0x2c/0x40 [ 105.519022] tcf_bpf_init+0x579/0x820 [act_bpf] [ 105.523990] tcf_action_init_1+0x4e4/0x660 [ 105.528518] tcf_action_init+0x1ce/0x2d0 [ 105.532880] tcf_exts_validate+0x1d8/0x200 [ 105.537416] fl_change+0x55a/0x268b [cls_flower] [ 105.542469] tc_new_tfilter+0x748/0xa20 [ 105.546738] rtnetlink_rcv_msg+0x56a/0x6d0 [ 105.551268] netlink_rcv_skb+0x18d/0x200 [ 105.555628] netlink_unicast+0x2d0/0x370 [ 105.559990] netlink_sendmsg+0x3b9/0x6a0 [ 105.564349] sock_sendmsg+0x6b/0x80 [ 105.568271] ___sys_sendmsg+0x4a1/0x520 [ 105.572547] __sys_sendmsg+0xd7/0x150 [ 105.576655] do_syscall_64+0x72/0x2c0 [ 105.580757] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 105.586243] irq event stamp: 489296 [ 105.590084] hardirqs last enabled at (489296): [<ffffffffb507e639>] _raw_spin_unlock_irq+0x29/0x40 [ 105.599765] hardirqs last disabled at (489295): [<ffffffffb507e745>] _raw_spin_lock_irq+0x15/0x50 [ 105.609277] softirqs last enabled at (489292): [<ffffffffb413a6a3>] irq_enter+0x83/0xa0 [ 105.618001] softirqs last disabled at (489293): [<ffffffffb413a800>] irq_exit+0x140/0x190 [ 105.626813] other info that might help us debug this: [ 105.633976] Possible unsafe locking scenario: [ 105.640526] CPU0 [ 105.643325] ---- [ 105.646125] lock(&(&p->tcfa_lock)->rlock); [ 105.650747] <Interrupt> [ 105.653717] lock(&(&p->tcfa_lock)->rlock); [ 105.658514] *** DEADLOCK *** [ 105.665349] 1 lock held by swapper/16/0: [ 105.669629] #0: 00000000a640ad99 ((&est->timer)){+.-.}, at: call_timer_fn+0x10b/0x550 [ 105.678200] stack backtrace: [ 105.683194] CPU: 16 PID: 0 Comm: swapper/16 Not tainted 4.18.0-rc8+ #664 [ 105.690249] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 105.698626] Call Trace: [ 105.701421] <IRQ> [ 105.703791] dump_stack+0x92/0xeb [ 105.707461] print_usage_bug+0x336/0x34c [ 105.711744] mark_lock+0x7c9/0x980 [ 105.715500] ? print_shortest_lock_dependencies+0x2e0/0x2e0 [ 105.721424] ? check_usage_forwards+0x230/0x230 [ 105.726315] __lock_acquire+0x923/0x26f0 [ 105.730597] ? debug_show_all_locks+0x240/0x240 [ 105.735478] ? mark_lock+0x493/0x980 [ 105.739412] ? check_chain_key+0x140/0x1f0 [ 105.743861] ? __lock_acquire+0x836/0x26f0 [ 105.748323] ? lock_acquire+0x12e/0x290 [ 105.752516] lock_acquire+0x12e/0x290 [ 105.756539] ? est_fetch_counters+0x3c/0xa0 [ 105.761084] _raw_spin_lock+0x2c/0x40 [ 105.765099] ? est_fetch_counters+0x3c/0xa0 [ 105.769633] est_fetch_counters+0x3c/0xa0 [ 105.773995] est_timer+0x87/0x390 [ 105.777670] ? est_fetch_counters+0xa0/0xa0 [ 105.782210] ? lock_acquire+0x12e/0x290 [ 105.786410] call_timer_fn+0x161/0x550 [ 105.790512] ? est_fetch_counters+0xa0/0xa0 [ 105.795055] ? del_timer_sync+0xd0/0xd0 [ 105.799249] ? __lock_is_held+0x93/0x110 [ 105.803531] ? mark_held_locks+0x20/0xe0 [ 105.807813] ? _raw_spin_unlock_irq+0x29/0x40 [ 105.812525] ? est_fetch_counters+0xa0/0xa0 [ 105.817069] ? est_fetch_counters+0xa0/0xa0 [ 105.821610] run_timer_softirq+0x3c4/0x9f0 [ 105.826064] ? lock_acquire+0x12e/0x290 [ 105.830257] ? __bpf_trace_timer_class+0x10/0x10 [ 105.835237] ? __lock_is_held+0x25/0x110 [ 105.839517] __do_softirq+0x11d/0x7bf [ 105.843542] irq_exit+0x140/0x190 [ 105.847208] smp_apic_timer_interrupt+0xac/0x3b0 [ 105.852182] apic_timer_interrupt+0xf/0x20 [ 105.856628] </IRQ> [ 105.859081] RIP: 0010:cpuidle_enter_state+0xd8/0x4d0 [ 105.864395] Code: 46 ff 48 89 44 24 08 0f 1f 44 00 00 31 ff e8 cf ec 46 ff 80 7c 24 07 00 0f 85 1d 02 00 00 e8 9f 90 4b ff fb 66 0f 1f 44 00 00 <4c> 8b 6c 24 08 4d 29 fd 0f 80 36 03 00 00 4c 89 e8 48 ba cf f7 53 [ 105.884288] RSP: 0018:ffff8803ad94fd20 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 [ 105.892494] RAX: 0000000000000000 RBX: ffffe8fb300829c0 RCX: ffffffffb41e19e1 [ 105.899988] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8803ad9358ac [ 105.907503] RBP: ffffffffb6636300 R08: 0000000000000004 R09: 0000000000000000 [ 105.914997] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000004 [ 105.922487] R13: ffffffffb6636140 R14: ffffffffb66362d8 R15: 000000188d36091b [ 105.929988] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.935232] do_idle+0x28e/0x320 [ 105.938817] ? arch_cpu_idle_exit+0x40/0x40 [ 105.943361] ? mark_lock+0x8c1/0x980 [ 105.947295] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.952619] cpu_startup_entry+0xc2/0xd0 [ 105.956900] ? cpu_in_idle+0x20/0x20 [ 105.960830] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.966146] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.971391] start_secondary+0x2b5/0x360 [ 105.975669] ? set_cpu_sibling_map+0x1330/0x1330 [ 105.980654] secondary_startup_64+0xa5/0xb0 Taking tcf_lock in sample action with bh disabled causes lockdep to issue a warning regarding possible irq lock inversion dependency between tcf_lock, and psample_groups_lock that is taken when holding tcf_lock in sample init: [ 162.108959] Possible interrupt unsafe locking scenario: [ 162.116386] CPU0 CPU1 [ 162.121277] ---- ---- [ 162.126162] lock(psample_groups_lock); [ 162.130447] local_irq_disable(); [ 162.136772] lock(&(&p->tcfa_lock)->rlock); [ 162.143957] lock(psample_groups_lock); [ 162.150813] <Interrupt> [ 162.153808] lock(&(&p->tcfa_lock)->rlock); [ 162.158608] *** DEADLOCK *** In order to prevent potential lock inversion dependency between tcf_lock and psample_groups_lock, extract call to psample_group_get() from tcf_lock protected section in sample action init function. Fixes: 4e232818bd32 ("net: sched: act_mirred: remove dependency on rtnl lock") Fixes: 764e9a24480f ("net: sched: act_vlan: remove dependency on rtnl lock") Fixes: 729e01260989 ("net: sched: act_tunnel_key: remove dependency on rtnl lock") Fixes: d77284956656 ("net: sched: act_sample: remove dependency on rtnl lock") Fixes: e8917f437006 ("net: sched: act_gact: remove dependency on rtnl lock") Fixes: b6a2b971c0b0 ("net: sched: act_csum: remove dependency on rtnl lock") Fixes: 2142236b4584 ("net: sched: act_bpf: remove dependency on rtnl lock") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-14 21:46:16 +03:00
spin_unlock_bh(&v->tcf_lock);
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 <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 15:00:14 +01:00
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
if (p)
kfree_rcu(p, rcu);
return ret;
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 <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 15:00:14 +01:00
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)
{
struct tcf_vlan *v = to_vlan(a);
struct tcf_vlan_params *p;
p = rcu_dereference_protected(v->vlan_p, 1);
net/sched: fix NULL dereference in the error path of tcf_vlan_init() when the following command # tc actions replace action vlan pop index 100 is run for the first time, and tcf_vlan_init() fails allocating struct tcf_vlan_params, tcf_vlan_cleanup() calls kfree_rcu(NULL, ...). This causes the following error: BUG: unable to handle kernel NULL pointer dereference at 0000000000000018 IP: __call_rcu+0x23/0x2b0 PGD 80000000760a2067 P4D 80000000760a2067 PUD 742c1067 PMD 0 Oops: 0002 [#1] SMP PTI Modules linked in: act_vlan(E) ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 snd_hda_codec_generic snd_hda_intel mbcache snd_hda_codec jbd2 snd_hda_core crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc snd_hwdep snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd snd_timer glue_helper snd cryptd joydev soundcore virtio_balloon pcspkr i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm drm virtio_console virtio_blk virtio_net ata_piix crc32c_intel libata virtio_pci i2c_core virtio_ring serio_raw virtio floppy dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_vlan] CPU: 3 PID: 3119 Comm: tc Tainted: G E 4.16.0-rc4.act_vlan.orig+ #403 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:__call_rcu+0x23/0x2b0 RSP: 0018:ffffaac3005fb798 EFLAGS: 00010246 RAX: ffffffffc0704080 RBX: ffff97f2b4bbe900 RCX: 00000000ffffffff RDX: ffffffffabca5f00 RSI: 0000000000000010 RDI: 0000000000000010 RBP: 0000000000000010 R08: 0000000000000001 R09: 0000000000000044 R10: 00000000fd003000 R11: ffff97f2faab5b91 R12: 0000000000000000 R13: ffffffffabca5f00 R14: ffff97f2fb80202c R15: 00000000fffffff4 FS: 00007f68f75b4740(0000) GS:ffff97f2ffd80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000018 CR3: 0000000072b52001 CR4: 00000000001606e0 Call Trace: __tcf_idr_release+0x79/0xf0 tcf_vlan_init+0x168/0x270 [act_vlan] tcf_action_init_1+0x2cc/0x430 tcf_action_init+0xd3/0x1b0 tc_ctl_action+0x18b/0x240 rtnetlink_rcv_msg+0x29c/0x310 ? _cond_resched+0x15/0x30 ? __kmalloc_node_track_caller+0x1b9/0x270 ? rtnl_calcit.isra.28+0x100/0x100 netlink_rcv_skb+0xd2/0x110 netlink_unicast+0x17c/0x230 netlink_sendmsg+0x2cd/0x3c0 sock_sendmsg+0x30/0x40 ___sys_sendmsg+0x27a/0x290 ? filemap_map_pages+0x34a/0x3a0 ? __handle_mm_fault+0xbfd/0xe20 __sys_sendmsg+0x51/0x90 do_syscall_64+0x6e/0x1a0 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 RIP: 0033:0x7f68f69c5ba0 RSP: 002b:00007fffd79c1118 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007fffd79c1240 RCX: 00007f68f69c5ba0 RDX: 0000000000000000 RSI: 00007fffd79c1190 RDI: 0000000000000003 RBP: 000000005aaa708e R08: 0000000000000002 R09: 0000000000000000 R10: 00007fffd79c0ba0 R11: 0000000000000246 R12: 0000000000000000 R13: 00007fffd79c1254 R14: 0000000000000001 R15: 0000000000669f60 Code: 5d e9 42 da ff ff 66 90 0f 1f 44 00 00 41 57 41 56 41 55 49 89 d5 41 54 55 48 89 fd 53 48 83 ec 08 40 f6 c7 07 0f 85 19 02 00 00 <48> 89 75 08 48 c7 45 00 00 00 00 00 9c 58 0f 1f 44 00 00 49 89 RIP: __call_rcu+0x23/0x2b0 RSP: ffffaac3005fb798 CR2: 0000000000000018 fix this in tcf_vlan_cleanup(), ensuring that kfree_rcu(p, ...) is called only when p is not NULL. Fixes: 4c5b9d9642c8 ("act_vlan: VLAN action rewrite to use RCU lock/unlock and update") Acked-by: Jiri Pirko <jiri@mellanox.com> Acked-by: Manish Kurup <manish.kurup@verizon.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-16 00:00:53 +01:00
if (p)
kfree_rcu(p, rcu);
}
static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a,
int bind, int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_vlan *v = to_vlan(a);
struct tcf_vlan_params *p;
struct tc_vlan opt = {
.index = v->tcf_index,
.refcnt = refcount_read(&v->tcf_refcnt) - ref,
.bindcnt = atomic_read(&v->tcf_bindcnt) - bind,
};
struct tcf_t t;
net: sched: always disable bh when taking tcf_lock Recently, ops->init() and ops->dump() of all actions were modified to always obtain tcf_lock when accessing private action state. Actions that don't depend on tcf_lock for synchronization with their data path use non-bh locking API. However, tcf_lock is also used to protect rate estimator stats in softirq context by timer callback. Change ops->init() and ops->dump() of all actions to disable bh when using tcf_lock to prevent deadlock reported by following lockdep warning: [ 105.470398] ================================ [ 105.475014] WARNING: inconsistent lock state [ 105.479628] 4.18.0-rc8+ #664 Not tainted [ 105.483897] -------------------------------- [ 105.488511] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. [ 105.494871] swapper/16/0 [HC0[0]:SC1[1]:HE1:SE0] takes: [ 105.500449] 00000000f86c012e (&(&p->tcfa_lock)->rlock){+.?.}, at: est_fetch_counters+0x3c/0xa0 [ 105.509696] {SOFTIRQ-ON-W} state was registered at: [ 105.514925] _raw_spin_lock+0x2c/0x40 [ 105.519022] tcf_bpf_init+0x579/0x820 [act_bpf] [ 105.523990] tcf_action_init_1+0x4e4/0x660 [ 105.528518] tcf_action_init+0x1ce/0x2d0 [ 105.532880] tcf_exts_validate+0x1d8/0x200 [ 105.537416] fl_change+0x55a/0x268b [cls_flower] [ 105.542469] tc_new_tfilter+0x748/0xa20 [ 105.546738] rtnetlink_rcv_msg+0x56a/0x6d0 [ 105.551268] netlink_rcv_skb+0x18d/0x200 [ 105.555628] netlink_unicast+0x2d0/0x370 [ 105.559990] netlink_sendmsg+0x3b9/0x6a0 [ 105.564349] sock_sendmsg+0x6b/0x80 [ 105.568271] ___sys_sendmsg+0x4a1/0x520 [ 105.572547] __sys_sendmsg+0xd7/0x150 [ 105.576655] do_syscall_64+0x72/0x2c0 [ 105.580757] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 105.586243] irq event stamp: 489296 [ 105.590084] hardirqs last enabled at (489296): [<ffffffffb507e639>] _raw_spin_unlock_irq+0x29/0x40 [ 105.599765] hardirqs last disabled at (489295): [<ffffffffb507e745>] _raw_spin_lock_irq+0x15/0x50 [ 105.609277] softirqs last enabled at (489292): [<ffffffffb413a6a3>] irq_enter+0x83/0xa0 [ 105.618001] softirqs last disabled at (489293): [<ffffffffb413a800>] irq_exit+0x140/0x190 [ 105.626813] other info that might help us debug this: [ 105.633976] Possible unsafe locking scenario: [ 105.640526] CPU0 [ 105.643325] ---- [ 105.646125] lock(&(&p->tcfa_lock)->rlock); [ 105.650747] <Interrupt> [ 105.653717] lock(&(&p->tcfa_lock)->rlock); [ 105.658514] *** DEADLOCK *** [ 105.665349] 1 lock held by swapper/16/0: [ 105.669629] #0: 00000000a640ad99 ((&est->timer)){+.-.}, at: call_timer_fn+0x10b/0x550 [ 105.678200] stack backtrace: [ 105.683194] CPU: 16 PID: 0 Comm: swapper/16 Not tainted 4.18.0-rc8+ #664 [ 105.690249] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 105.698626] Call Trace: [ 105.701421] <IRQ> [ 105.703791] dump_stack+0x92/0xeb [ 105.707461] print_usage_bug+0x336/0x34c [ 105.711744] mark_lock+0x7c9/0x980 [ 105.715500] ? print_shortest_lock_dependencies+0x2e0/0x2e0 [ 105.721424] ? check_usage_forwards+0x230/0x230 [ 105.726315] __lock_acquire+0x923/0x26f0 [ 105.730597] ? debug_show_all_locks+0x240/0x240 [ 105.735478] ? mark_lock+0x493/0x980 [ 105.739412] ? check_chain_key+0x140/0x1f0 [ 105.743861] ? __lock_acquire+0x836/0x26f0 [ 105.748323] ? lock_acquire+0x12e/0x290 [ 105.752516] lock_acquire+0x12e/0x290 [ 105.756539] ? est_fetch_counters+0x3c/0xa0 [ 105.761084] _raw_spin_lock+0x2c/0x40 [ 105.765099] ? est_fetch_counters+0x3c/0xa0 [ 105.769633] est_fetch_counters+0x3c/0xa0 [ 105.773995] est_timer+0x87/0x390 [ 105.777670] ? est_fetch_counters+0xa0/0xa0 [ 105.782210] ? lock_acquire+0x12e/0x290 [ 105.786410] call_timer_fn+0x161/0x550 [ 105.790512] ? est_fetch_counters+0xa0/0xa0 [ 105.795055] ? del_timer_sync+0xd0/0xd0 [ 105.799249] ? __lock_is_held+0x93/0x110 [ 105.803531] ? mark_held_locks+0x20/0xe0 [ 105.807813] ? _raw_spin_unlock_irq+0x29/0x40 [ 105.812525] ? est_fetch_counters+0xa0/0xa0 [ 105.817069] ? est_fetch_counters+0xa0/0xa0 [ 105.821610] run_timer_softirq+0x3c4/0x9f0 [ 105.826064] ? lock_acquire+0x12e/0x290 [ 105.830257] ? __bpf_trace_timer_class+0x10/0x10 [ 105.835237] ? __lock_is_held+0x25/0x110 [ 105.839517] __do_softirq+0x11d/0x7bf [ 105.843542] irq_exit+0x140/0x190 [ 105.847208] smp_apic_timer_interrupt+0xac/0x3b0 [ 105.852182] apic_timer_interrupt+0xf/0x20 [ 105.856628] </IRQ> [ 105.859081] RIP: 0010:cpuidle_enter_state+0xd8/0x4d0 [ 105.864395] Code: 46 ff 48 89 44 24 08 0f 1f 44 00 00 31 ff e8 cf ec 46 ff 80 7c 24 07 00 0f 85 1d 02 00 00 e8 9f 90 4b ff fb 66 0f 1f 44 00 00 <4c> 8b 6c 24 08 4d 29 fd 0f 80 36 03 00 00 4c 89 e8 48 ba cf f7 53 [ 105.884288] RSP: 0018:ffff8803ad94fd20 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 [ 105.892494] RAX: 0000000000000000 RBX: ffffe8fb300829c0 RCX: ffffffffb41e19e1 [ 105.899988] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8803ad9358ac [ 105.907503] RBP: ffffffffb6636300 R08: 0000000000000004 R09: 0000000000000000 [ 105.914997] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000004 [ 105.922487] R13: ffffffffb6636140 R14: ffffffffb66362d8 R15: 000000188d36091b [ 105.929988] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.935232] do_idle+0x28e/0x320 [ 105.938817] ? arch_cpu_idle_exit+0x40/0x40 [ 105.943361] ? mark_lock+0x8c1/0x980 [ 105.947295] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.952619] cpu_startup_entry+0xc2/0xd0 [ 105.956900] ? cpu_in_idle+0x20/0x20 [ 105.960830] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.966146] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.971391] start_secondary+0x2b5/0x360 [ 105.975669] ? set_cpu_sibling_map+0x1330/0x1330 [ 105.980654] secondary_startup_64+0xa5/0xb0 Taking tcf_lock in sample action with bh disabled causes lockdep to issue a warning regarding possible irq lock inversion dependency between tcf_lock, and psample_groups_lock that is taken when holding tcf_lock in sample init: [ 162.108959] Possible interrupt unsafe locking scenario: [ 162.116386] CPU0 CPU1 [ 162.121277] ---- ---- [ 162.126162] lock(psample_groups_lock); [ 162.130447] local_irq_disable(); [ 162.136772] lock(&(&p->tcfa_lock)->rlock); [ 162.143957] lock(psample_groups_lock); [ 162.150813] <Interrupt> [ 162.153808] lock(&(&p->tcfa_lock)->rlock); [ 162.158608] *** DEADLOCK *** In order to prevent potential lock inversion dependency between tcf_lock and psample_groups_lock, extract call to psample_group_get() from tcf_lock protected section in sample action init function. Fixes: 4e232818bd32 ("net: sched: act_mirred: remove dependency on rtnl lock") Fixes: 764e9a24480f ("net: sched: act_vlan: remove dependency on rtnl lock") Fixes: 729e01260989 ("net: sched: act_tunnel_key: remove dependency on rtnl lock") Fixes: d77284956656 ("net: sched: act_sample: remove dependency on rtnl lock") Fixes: e8917f437006 ("net: sched: act_gact: remove dependency on rtnl lock") Fixes: b6a2b971c0b0 ("net: sched: act_csum: remove dependency on rtnl lock") Fixes: 2142236b4584 ("net: sched: act_bpf: remove dependency on rtnl lock") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-14 21:46:16 +03:00
spin_lock_bh(&v->tcf_lock);
opt.action = v->tcf_action;
p = rcu_dereference_protected(v->vlan_p, lockdep_is_held(&v->tcf_lock));
opt.v_action = p->tcfv_action;
if (nla_put(skb, TCA_VLAN_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
if ((p->tcfv_action == TCA_VLAN_ACT_PUSH ||
p->tcfv_action == TCA_VLAN_ACT_MODIFY) &&
(nla_put_u16(skb, TCA_VLAN_PUSH_VLAN_ID, p->tcfv_push_vid) ||
nla_put_be16(skb, TCA_VLAN_PUSH_VLAN_PROTOCOL,
p->tcfv_push_proto) ||
(p->tcfv_push_prio_exists &&
nla_put_u8(skb, TCA_VLAN_PUSH_VLAN_PRIORITY, p->tcfv_push_prio))))
goto nla_put_failure;
if (p->tcfv_action == TCA_VLAN_ACT_PUSH_ETH) {
if (nla_put(skb, TCA_VLAN_PUSH_ETH_DST, ETH_ALEN,
p->tcfv_push_dst))
goto nla_put_failure;
if (nla_put(skb, TCA_VLAN_PUSH_ETH_SRC, ETH_ALEN,
p->tcfv_push_src))
goto nla_put_failure;
}
tcf_tm_dump(&t, &v->tcf_tm);
if (nla_put_64bit(skb, TCA_VLAN_TM, sizeof(t), &t, TCA_VLAN_PAD))
goto nla_put_failure;
net: sched: always disable bh when taking tcf_lock Recently, ops->init() and ops->dump() of all actions were modified to always obtain tcf_lock when accessing private action state. Actions that don't depend on tcf_lock for synchronization with their data path use non-bh locking API. However, tcf_lock is also used to protect rate estimator stats in softirq context by timer callback. Change ops->init() and ops->dump() of all actions to disable bh when using tcf_lock to prevent deadlock reported by following lockdep warning: [ 105.470398] ================================ [ 105.475014] WARNING: inconsistent lock state [ 105.479628] 4.18.0-rc8+ #664 Not tainted [ 105.483897] -------------------------------- [ 105.488511] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. [ 105.494871] swapper/16/0 [HC0[0]:SC1[1]:HE1:SE0] takes: [ 105.500449] 00000000f86c012e (&(&p->tcfa_lock)->rlock){+.?.}, at: est_fetch_counters+0x3c/0xa0 [ 105.509696] {SOFTIRQ-ON-W} state was registered at: [ 105.514925] _raw_spin_lock+0x2c/0x40 [ 105.519022] tcf_bpf_init+0x579/0x820 [act_bpf] [ 105.523990] tcf_action_init_1+0x4e4/0x660 [ 105.528518] tcf_action_init+0x1ce/0x2d0 [ 105.532880] tcf_exts_validate+0x1d8/0x200 [ 105.537416] fl_change+0x55a/0x268b [cls_flower] [ 105.542469] tc_new_tfilter+0x748/0xa20 [ 105.546738] rtnetlink_rcv_msg+0x56a/0x6d0 [ 105.551268] netlink_rcv_skb+0x18d/0x200 [ 105.555628] netlink_unicast+0x2d0/0x370 [ 105.559990] netlink_sendmsg+0x3b9/0x6a0 [ 105.564349] sock_sendmsg+0x6b/0x80 [ 105.568271] ___sys_sendmsg+0x4a1/0x520 [ 105.572547] __sys_sendmsg+0xd7/0x150 [ 105.576655] do_syscall_64+0x72/0x2c0 [ 105.580757] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 105.586243] irq event stamp: 489296 [ 105.590084] hardirqs last enabled at (489296): [<ffffffffb507e639>] _raw_spin_unlock_irq+0x29/0x40 [ 105.599765] hardirqs last disabled at (489295): [<ffffffffb507e745>] _raw_spin_lock_irq+0x15/0x50 [ 105.609277] softirqs last enabled at (489292): [<ffffffffb413a6a3>] irq_enter+0x83/0xa0 [ 105.618001] softirqs last disabled at (489293): [<ffffffffb413a800>] irq_exit+0x140/0x190 [ 105.626813] other info that might help us debug this: [ 105.633976] Possible unsafe locking scenario: [ 105.640526] CPU0 [ 105.643325] ---- [ 105.646125] lock(&(&p->tcfa_lock)->rlock); [ 105.650747] <Interrupt> [ 105.653717] lock(&(&p->tcfa_lock)->rlock); [ 105.658514] *** DEADLOCK *** [ 105.665349] 1 lock held by swapper/16/0: [ 105.669629] #0: 00000000a640ad99 ((&est->timer)){+.-.}, at: call_timer_fn+0x10b/0x550 [ 105.678200] stack backtrace: [ 105.683194] CPU: 16 PID: 0 Comm: swapper/16 Not tainted 4.18.0-rc8+ #664 [ 105.690249] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 105.698626] Call Trace: [ 105.701421] <IRQ> [ 105.703791] dump_stack+0x92/0xeb [ 105.707461] print_usage_bug+0x336/0x34c [ 105.711744] mark_lock+0x7c9/0x980 [ 105.715500] ? print_shortest_lock_dependencies+0x2e0/0x2e0 [ 105.721424] ? check_usage_forwards+0x230/0x230 [ 105.726315] __lock_acquire+0x923/0x26f0 [ 105.730597] ? debug_show_all_locks+0x240/0x240 [ 105.735478] ? mark_lock+0x493/0x980 [ 105.739412] ? check_chain_key+0x140/0x1f0 [ 105.743861] ? __lock_acquire+0x836/0x26f0 [ 105.748323] ? lock_acquire+0x12e/0x290 [ 105.752516] lock_acquire+0x12e/0x290 [ 105.756539] ? est_fetch_counters+0x3c/0xa0 [ 105.761084] _raw_spin_lock+0x2c/0x40 [ 105.765099] ? est_fetch_counters+0x3c/0xa0 [ 105.769633] est_fetch_counters+0x3c/0xa0 [ 105.773995] est_timer+0x87/0x390 [ 105.777670] ? est_fetch_counters+0xa0/0xa0 [ 105.782210] ? lock_acquire+0x12e/0x290 [ 105.786410] call_timer_fn+0x161/0x550 [ 105.790512] ? est_fetch_counters+0xa0/0xa0 [ 105.795055] ? del_timer_sync+0xd0/0xd0 [ 105.799249] ? __lock_is_held+0x93/0x110 [ 105.803531] ? mark_held_locks+0x20/0xe0 [ 105.807813] ? _raw_spin_unlock_irq+0x29/0x40 [ 105.812525] ? est_fetch_counters+0xa0/0xa0 [ 105.817069] ? est_fetch_counters+0xa0/0xa0 [ 105.821610] run_timer_softirq+0x3c4/0x9f0 [ 105.826064] ? lock_acquire+0x12e/0x290 [ 105.830257] ? __bpf_trace_timer_class+0x10/0x10 [ 105.835237] ? __lock_is_held+0x25/0x110 [ 105.839517] __do_softirq+0x11d/0x7bf [ 105.843542] irq_exit+0x140/0x190 [ 105.847208] smp_apic_timer_interrupt+0xac/0x3b0 [ 105.852182] apic_timer_interrupt+0xf/0x20 [ 105.856628] </IRQ> [ 105.859081] RIP: 0010:cpuidle_enter_state+0xd8/0x4d0 [ 105.864395] Code: 46 ff 48 89 44 24 08 0f 1f 44 00 00 31 ff e8 cf ec 46 ff 80 7c 24 07 00 0f 85 1d 02 00 00 e8 9f 90 4b ff fb 66 0f 1f 44 00 00 <4c> 8b 6c 24 08 4d 29 fd 0f 80 36 03 00 00 4c 89 e8 48 ba cf f7 53 [ 105.884288] RSP: 0018:ffff8803ad94fd20 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 [ 105.892494] RAX: 0000000000000000 RBX: ffffe8fb300829c0 RCX: ffffffffb41e19e1 [ 105.899988] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8803ad9358ac [ 105.907503] RBP: ffffffffb6636300 R08: 0000000000000004 R09: 0000000000000000 [ 105.914997] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000004 [ 105.922487] R13: ffffffffb6636140 R14: ffffffffb66362d8 R15: 000000188d36091b [ 105.929988] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.935232] do_idle+0x28e/0x320 [ 105.938817] ? arch_cpu_idle_exit+0x40/0x40 [ 105.943361] ? mark_lock+0x8c1/0x980 [ 105.947295] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.952619] cpu_startup_entry+0xc2/0xd0 [ 105.956900] ? cpu_in_idle+0x20/0x20 [ 105.960830] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.966146] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.971391] start_secondary+0x2b5/0x360 [ 105.975669] ? set_cpu_sibling_map+0x1330/0x1330 [ 105.980654] secondary_startup_64+0xa5/0xb0 Taking tcf_lock in sample action with bh disabled causes lockdep to issue a warning regarding possible irq lock inversion dependency between tcf_lock, and psample_groups_lock that is taken when holding tcf_lock in sample init: [ 162.108959] Possible interrupt unsafe locking scenario: [ 162.116386] CPU0 CPU1 [ 162.121277] ---- ---- [ 162.126162] lock(psample_groups_lock); [ 162.130447] local_irq_disable(); [ 162.136772] lock(&(&p->tcfa_lock)->rlock); [ 162.143957] lock(psample_groups_lock); [ 162.150813] <Interrupt> [ 162.153808] lock(&(&p->tcfa_lock)->rlock); [ 162.158608] *** DEADLOCK *** In order to prevent potential lock inversion dependency between tcf_lock and psample_groups_lock, extract call to psample_group_get() from tcf_lock protected section in sample action init function. Fixes: 4e232818bd32 ("net: sched: act_mirred: remove dependency on rtnl lock") Fixes: 764e9a24480f ("net: sched: act_vlan: remove dependency on rtnl lock") Fixes: 729e01260989 ("net: sched: act_tunnel_key: remove dependency on rtnl lock") Fixes: d77284956656 ("net: sched: act_sample: remove dependency on rtnl lock") Fixes: e8917f437006 ("net: sched: act_gact: remove dependency on rtnl lock") Fixes: b6a2b971c0b0 ("net: sched: act_csum: remove dependency on rtnl lock") Fixes: 2142236b4584 ("net: sched: act_bpf: remove dependency on rtnl lock") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-14 21:46:16 +03:00
spin_unlock_bh(&v->tcf_lock);
return skb->len;
nla_put_failure:
net: sched: always disable bh when taking tcf_lock Recently, ops->init() and ops->dump() of all actions were modified to always obtain tcf_lock when accessing private action state. Actions that don't depend on tcf_lock for synchronization with their data path use non-bh locking API. However, tcf_lock is also used to protect rate estimator stats in softirq context by timer callback. Change ops->init() and ops->dump() of all actions to disable bh when using tcf_lock to prevent deadlock reported by following lockdep warning: [ 105.470398] ================================ [ 105.475014] WARNING: inconsistent lock state [ 105.479628] 4.18.0-rc8+ #664 Not tainted [ 105.483897] -------------------------------- [ 105.488511] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. [ 105.494871] swapper/16/0 [HC0[0]:SC1[1]:HE1:SE0] takes: [ 105.500449] 00000000f86c012e (&(&p->tcfa_lock)->rlock){+.?.}, at: est_fetch_counters+0x3c/0xa0 [ 105.509696] {SOFTIRQ-ON-W} state was registered at: [ 105.514925] _raw_spin_lock+0x2c/0x40 [ 105.519022] tcf_bpf_init+0x579/0x820 [act_bpf] [ 105.523990] tcf_action_init_1+0x4e4/0x660 [ 105.528518] tcf_action_init+0x1ce/0x2d0 [ 105.532880] tcf_exts_validate+0x1d8/0x200 [ 105.537416] fl_change+0x55a/0x268b [cls_flower] [ 105.542469] tc_new_tfilter+0x748/0xa20 [ 105.546738] rtnetlink_rcv_msg+0x56a/0x6d0 [ 105.551268] netlink_rcv_skb+0x18d/0x200 [ 105.555628] netlink_unicast+0x2d0/0x370 [ 105.559990] netlink_sendmsg+0x3b9/0x6a0 [ 105.564349] sock_sendmsg+0x6b/0x80 [ 105.568271] ___sys_sendmsg+0x4a1/0x520 [ 105.572547] __sys_sendmsg+0xd7/0x150 [ 105.576655] do_syscall_64+0x72/0x2c0 [ 105.580757] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 105.586243] irq event stamp: 489296 [ 105.590084] hardirqs last enabled at (489296): [<ffffffffb507e639>] _raw_spin_unlock_irq+0x29/0x40 [ 105.599765] hardirqs last disabled at (489295): [<ffffffffb507e745>] _raw_spin_lock_irq+0x15/0x50 [ 105.609277] softirqs last enabled at (489292): [<ffffffffb413a6a3>] irq_enter+0x83/0xa0 [ 105.618001] softirqs last disabled at (489293): [<ffffffffb413a800>] irq_exit+0x140/0x190 [ 105.626813] other info that might help us debug this: [ 105.633976] Possible unsafe locking scenario: [ 105.640526] CPU0 [ 105.643325] ---- [ 105.646125] lock(&(&p->tcfa_lock)->rlock); [ 105.650747] <Interrupt> [ 105.653717] lock(&(&p->tcfa_lock)->rlock); [ 105.658514] *** DEADLOCK *** [ 105.665349] 1 lock held by swapper/16/0: [ 105.669629] #0: 00000000a640ad99 ((&est->timer)){+.-.}, at: call_timer_fn+0x10b/0x550 [ 105.678200] stack backtrace: [ 105.683194] CPU: 16 PID: 0 Comm: swapper/16 Not tainted 4.18.0-rc8+ #664 [ 105.690249] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 105.698626] Call Trace: [ 105.701421] <IRQ> [ 105.703791] dump_stack+0x92/0xeb [ 105.707461] print_usage_bug+0x336/0x34c [ 105.711744] mark_lock+0x7c9/0x980 [ 105.715500] ? print_shortest_lock_dependencies+0x2e0/0x2e0 [ 105.721424] ? check_usage_forwards+0x230/0x230 [ 105.726315] __lock_acquire+0x923/0x26f0 [ 105.730597] ? debug_show_all_locks+0x240/0x240 [ 105.735478] ? mark_lock+0x493/0x980 [ 105.739412] ? check_chain_key+0x140/0x1f0 [ 105.743861] ? __lock_acquire+0x836/0x26f0 [ 105.748323] ? lock_acquire+0x12e/0x290 [ 105.752516] lock_acquire+0x12e/0x290 [ 105.756539] ? est_fetch_counters+0x3c/0xa0 [ 105.761084] _raw_spin_lock+0x2c/0x40 [ 105.765099] ? est_fetch_counters+0x3c/0xa0 [ 105.769633] est_fetch_counters+0x3c/0xa0 [ 105.773995] est_timer+0x87/0x390 [ 105.777670] ? est_fetch_counters+0xa0/0xa0 [ 105.782210] ? lock_acquire+0x12e/0x290 [ 105.786410] call_timer_fn+0x161/0x550 [ 105.790512] ? est_fetch_counters+0xa0/0xa0 [ 105.795055] ? del_timer_sync+0xd0/0xd0 [ 105.799249] ? __lock_is_held+0x93/0x110 [ 105.803531] ? mark_held_locks+0x20/0xe0 [ 105.807813] ? _raw_spin_unlock_irq+0x29/0x40 [ 105.812525] ? est_fetch_counters+0xa0/0xa0 [ 105.817069] ? est_fetch_counters+0xa0/0xa0 [ 105.821610] run_timer_softirq+0x3c4/0x9f0 [ 105.826064] ? lock_acquire+0x12e/0x290 [ 105.830257] ? __bpf_trace_timer_class+0x10/0x10 [ 105.835237] ? __lock_is_held+0x25/0x110 [ 105.839517] __do_softirq+0x11d/0x7bf [ 105.843542] irq_exit+0x140/0x190 [ 105.847208] smp_apic_timer_interrupt+0xac/0x3b0 [ 105.852182] apic_timer_interrupt+0xf/0x20 [ 105.856628] </IRQ> [ 105.859081] RIP: 0010:cpuidle_enter_state+0xd8/0x4d0 [ 105.864395] Code: 46 ff 48 89 44 24 08 0f 1f 44 00 00 31 ff e8 cf ec 46 ff 80 7c 24 07 00 0f 85 1d 02 00 00 e8 9f 90 4b ff fb 66 0f 1f 44 00 00 <4c> 8b 6c 24 08 4d 29 fd 0f 80 36 03 00 00 4c 89 e8 48 ba cf f7 53 [ 105.884288] RSP: 0018:ffff8803ad94fd20 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 [ 105.892494] RAX: 0000000000000000 RBX: ffffe8fb300829c0 RCX: ffffffffb41e19e1 [ 105.899988] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8803ad9358ac [ 105.907503] RBP: ffffffffb6636300 R08: 0000000000000004 R09: 0000000000000000 [ 105.914997] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000004 [ 105.922487] R13: ffffffffb6636140 R14: ffffffffb66362d8 R15: 000000188d36091b [ 105.929988] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.935232] do_idle+0x28e/0x320 [ 105.938817] ? arch_cpu_idle_exit+0x40/0x40 [ 105.943361] ? mark_lock+0x8c1/0x980 [ 105.947295] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.952619] cpu_startup_entry+0xc2/0xd0 [ 105.956900] ? cpu_in_idle+0x20/0x20 [ 105.960830] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.966146] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.971391] start_secondary+0x2b5/0x360 [ 105.975669] ? set_cpu_sibling_map+0x1330/0x1330 [ 105.980654] secondary_startup_64+0xa5/0xb0 Taking tcf_lock in sample action with bh disabled causes lockdep to issue a warning regarding possible irq lock inversion dependency between tcf_lock, and psample_groups_lock that is taken when holding tcf_lock in sample init: [ 162.108959] Possible interrupt unsafe locking scenario: [ 162.116386] CPU0 CPU1 [ 162.121277] ---- ---- [ 162.126162] lock(psample_groups_lock); [ 162.130447] local_irq_disable(); [ 162.136772] lock(&(&p->tcfa_lock)->rlock); [ 162.143957] lock(psample_groups_lock); [ 162.150813] <Interrupt> [ 162.153808] lock(&(&p->tcfa_lock)->rlock); [ 162.158608] *** DEADLOCK *** In order to prevent potential lock inversion dependency between tcf_lock and psample_groups_lock, extract call to psample_group_get() from tcf_lock protected section in sample action init function. Fixes: 4e232818bd32 ("net: sched: act_mirred: remove dependency on rtnl lock") Fixes: 764e9a24480f ("net: sched: act_vlan: remove dependency on rtnl lock") Fixes: 729e01260989 ("net: sched: act_tunnel_key: remove dependency on rtnl lock") Fixes: d77284956656 ("net: sched: act_sample: remove dependency on rtnl lock") Fixes: e8917f437006 ("net: sched: act_gact: remove dependency on rtnl lock") Fixes: b6a2b971c0b0 ("net: sched: act_csum: remove dependency on rtnl lock") Fixes: 2142236b4584 ("net: sched: act_bpf: remove dependency on rtnl lock") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-14 21:46:16 +03:00
spin_unlock_bh(&v->tcf_lock);
nlmsg_trim(skb, b);
return -1;
}
static void tcf_vlan_stats_update(struct tc_action *a, u64 bytes, u64 packets,
u64 drops, u64 lastuse, bool hw)
{
struct tcf_vlan *v = to_vlan(a);
struct tcf_t *tm = &v->tcf_tm;
tcf_action_update_stats(a, bytes, packets, drops, hw);
tm->lastuse = max_t(u64, tm->lastuse, lastuse);
}
static size_t tcf_vlan_get_fill_size(const struct tc_action *act)
{
return nla_total_size(sizeof(struct tc_vlan))
+ nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_ID */
+ nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_PROTOCOL */
+ nla_total_size(sizeof(u8)); /* TCA_VLAN_PUSH_VLAN_PRIORITY */
}
static int tcf_vlan_offload_act_setup(struct tc_action *act, void *entry_data,
u32 *index_inc, bool bind,
struct netlink_ext_ack *extack)
{
if (bind) {
struct flow_action_entry *entry = entry_data;
switch (tcf_vlan_action(act)) {
case TCA_VLAN_ACT_PUSH:
entry->id = FLOW_ACTION_VLAN_PUSH;
entry->vlan.vid = tcf_vlan_push_vid(act);
entry->vlan.proto = tcf_vlan_push_proto(act);
entry->vlan.prio = tcf_vlan_push_prio(act);
break;
case TCA_VLAN_ACT_POP:
entry->id = FLOW_ACTION_VLAN_POP;
break;
case TCA_VLAN_ACT_MODIFY:
entry->id = FLOW_ACTION_VLAN_MANGLE;
entry->vlan.vid = tcf_vlan_push_vid(act);
entry->vlan.proto = tcf_vlan_push_proto(act);
entry->vlan.prio = tcf_vlan_push_prio(act);
break;
case TCA_VLAN_ACT_POP_ETH:
entry->id = FLOW_ACTION_VLAN_POP_ETH;
break;
case TCA_VLAN_ACT_PUSH_ETH:
entry->id = FLOW_ACTION_VLAN_PUSH_ETH;
tcf_vlan_push_eth(entry->vlan_push_eth.src, entry->vlan_push_eth.dst, act);
break;
default:
NL_SET_ERR_MSG_MOD(extack, "Unsupported vlan action mode offload");
return -EOPNOTSUPP;
}
*index_inc = 1;
} else {
struct flow_offload_action *fl_action = entry_data;
switch (tcf_vlan_action(act)) {
case TCA_VLAN_ACT_PUSH:
fl_action->id = FLOW_ACTION_VLAN_PUSH;
break;
case TCA_VLAN_ACT_POP:
fl_action->id = FLOW_ACTION_VLAN_POP;
break;
case TCA_VLAN_ACT_MODIFY:
fl_action->id = FLOW_ACTION_VLAN_MANGLE;
break;
case TCA_VLAN_ACT_POP_ETH:
fl_action->id = FLOW_ACTION_VLAN_POP_ETH;
break;
case TCA_VLAN_ACT_PUSH_ETH:
fl_action->id = FLOW_ACTION_VLAN_PUSH_ETH;
break;
default:
return -EOPNOTSUPP;
}
}
return 0;
}
static struct tc_action_ops act_vlan_ops = {
.kind = "vlan",
.id = TCA_ID_VLAN,
.owner = THIS_MODULE,
.act = tcf_vlan_act,
.dump = tcf_vlan_dump,
.init = tcf_vlan_init,
.cleanup = tcf_vlan_cleanup,
.stats_update = tcf_vlan_stats_update,
.get_fill_size = tcf_vlan_get_fill_size,
.offload_act_setup = tcf_vlan_offload_act_setup,
.size = sizeof(struct tcf_vlan),
};
net/sched: Add module aliases for cls_,sch_,act_ modules No functional change intended, aliases will be used in followup commits. Note for backporters: you may need to add aliases also for modules that are already removed in mainline kernel but still in your version. Patches were generated with the help of Coccinelle scripts like: cat >scripts/coccinelle/misc/tcf_alias.cocci <<EOD virtual patch virtual report @ haskernel @ @@ @ tcf_has_kind depends on report && haskernel @ identifier ops; constant K; @@ static struct tcf_proto_ops ops = { .kind = K, ... }; +char module_alias = K; EOD /usr/bin/spatch -D report --cocci-file scripts/coccinelle/misc/tcf_alias.cocci \ --dir . \ -I ./arch/x86/include -I ./arch/x86/include/generated -I ./include \ -I ./arch/x86/include/uapi -I ./arch/x86/include/generated/uapi \ -I ./include/uapi -I ./include/generated/uapi \ --include ./include/linux/compiler-version.h --include ./include/linux/kconfig.h \ --jobs 8 --chunksize 1 2>/dev/null | \ sed 's/char module_alias = "\([^"]*\)";/MODULE_ALIAS_NET_CLS("\1");/' And analogously for: static struct tc_action_ops ops = { .kind = K, static struct Qdisc_ops ops = { .id = K, (Someone familiar would be able to fit those into one .cocci file without sed post processing.) Signed-off-by: Michal Koutný <mkoutny@suse.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@nvidia.com> Link: https://lore.kernel.org/r/20240201130943.19536-3-mkoutny@suse.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-02-01 14:09:41 +01:00
MODULE_ALIAS_NET_ACT("vlan");
static __net_init int vlan_init_net(struct net *net)
{
struct tc_action_net *tn = net_generic(net, act_vlan_ops.net_id);
return tc_action_net_init(net, tn, &act_vlan_ops);
}
static void __net_exit vlan_exit_net(struct list_head *net_list)
{
tc_action_net_exit(net_list, act_vlan_ops.net_id);
}
static struct pernet_operations vlan_net_ops = {
.init = vlan_init_net,
.exit_batch = vlan_exit_net,
.id = &act_vlan_ops.net_id,
.size = sizeof(struct tc_action_net),
};
static int __init vlan_init_module(void)
{
return tcf_register_action(&act_vlan_ops, &vlan_net_ops);
}
static void __exit vlan_cleanup_module(void)
{
tcf_unregister_action(&act_vlan_ops, &vlan_net_ops);
}
module_init(vlan_init_module);
module_exit(vlan_cleanup_module);
MODULE_AUTHOR("Jiri Pirko <jiri@resnulli.us>");
MODULE_DESCRIPTION("vlan manipulation actions");
MODULE_LICENSE("GPL v2");