1
linux/net/sched/act_skbmod.c

327 lines
8.1 KiB
C
Raw Permalink Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* net/sched/act_skbmod.c skb data modifier
*
* Copyright (c) 2016 Jamal Hadi Salim <jhs@mojatatu.com>
*/
#include <linux/module.h>
#include <linux/if_arp.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
net/sched: act_skbmod: Add SKBMOD_F_ECN option support Currently, when doing rate limiting using the tc-police(8) action, the easiest way is to simply drop the packets which exceed or conform the configured bandwidth limit. Add a new option to tc-skbmod(8), so that users may use the ECN [1] extension to explicitly inform the receiver about the congestion instead of dropping packets "on the floor". The 2 least significant bits of the Traffic Class field in IPv4 and IPv6 headers are used to represent different ECN states [2]: 0b00: "Non ECN-Capable Transport", Non-ECT 0b10: "ECN Capable Transport", ECT(0) 0b01: "ECN Capable Transport", ECT(1) 0b11: "Congestion Encountered", CE As an example: $ tc filter add dev eth0 parent 1: protocol ip prio 10 \ matchall action skbmod ecn Doing the above marks all ECT(0) and ECT(1) packets as CE. It does NOT affect Non-ECT or non-IP packets. In the tc-police scenario mentioned above, users may pipe a tc-police action and a tc-skbmod "ecn" action together to achieve ECN-based rate limiting. For TCP connections, upon receiving a CE packet, the receiver will respond with an ECE packet, asking the sender to reduce their congestion window. However ECN also works with other L4 protocols e.g. DCCP and SCTP [2], and our implementation does not touch or care about L4 headers. The updated tc-skbmod SYNOPSIS looks like the following: tc ... action skbmod { set SETTABLE | swap SWAPPABLE | ecn } ... Only one of "set", "swap" or "ecn" shall be used in a single tc-skbmod command. Trying to use more than one of them at a time is considered undefined behavior; pipe multiple tc-skbmod commands together instead. "set" and "swap" only affect Ethernet packets, while "ecn" only affects IPv{4,6} packets. It is also worth mentioning that, in theory, the same effect could be achieved by piping a "police" action and a "bpf" action using the bpf_skb_ecn_set_ce() helper, but this requires eBPF programming from the user, thus impractical. Depends on patch "net/sched: act_skbmod: Skip non-Ethernet packets". [1] https://datatracker.ietf.org/doc/html/rfc3168 [2] https://en.wikipedia.org/wiki/Explicit_Congestion_Notification Reviewed-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Peilin Ye <peilin.ye@bytedance.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-07-27 18:33:15 -07:00
#include <net/inet_ecn.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
net/sched: act_skbmod: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action skbmod set smac 00:c1:a0:c1:a0:00 pass index 90 # tc actions replace action skbmod \ > set smac 00:c1:a0:c1:a0:00 goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action skbmod had the following output: src MAC address <00:c1:a0:c1:a0:00> src MAC address <00:c1:a0:c1:a0:00> Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: skbmod goto chain 42 set smac 00:c1:a0:c1:a0:00 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 800000002d5c7067 P4D 800000002d5c7067 PUD 77e16067 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:ffff8987ffd83be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff8987aeb68800 RCX: ffff8987fa263640 RDX: 0000000000000000 RSI: ffff8987f51c8802 RDI: 00000000000000a0 RBP: ffff8987ffd83c80 R08: ffff8987f939bac8 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8987f5c77d00 R13: ffff8987f5c77d08 R14: 0000000000000001 R15: ffff8987f0c29f00 FS: 0000000000000000(0000) GS:ffff8987ffd80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007832c004 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 ? tick_sched_timer+0x37/0x70 __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: 56 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:ffffa2a1c038feb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffffa94184f0 RBX: 0000000000000003 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000003 RBP: 0000000000000003 R08: 001123cfc2ba71ac R09: 0000000000000000 R10: 0000000000000000 R11: 00000000000f4240 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_skbmod veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel mbcache jbd2 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device aesni_intel crypto_simd cryptd glue_helper snd_pcm joydev pcspkr virtio_balloon snd_timer snd i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect virtio_net sysimgblt fb_sys_fops net_failover virtio_console ttm virtio_blk failover drm crc32c_intel serio_raw ata_piix virtio_pci libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_skbmod_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 07:00:12 -07:00
#include <net/pkt_cls.h>
#include <net/tc_wrapper.h>
#include <linux/tc_act/tc_skbmod.h>
#include <net/tc_act/tc_skbmod.h>
static struct tc_action_ops act_skbmod_ops;
TC_INDIRECT_SCOPE int tcf_skbmod_act(struct sk_buff *skb,
const struct tc_action *a,
struct tcf_result *res)
{
struct tcf_skbmod *d = to_skbmod(a);
net/sched: act_skbmod: Add SKBMOD_F_ECN option support Currently, when doing rate limiting using the tc-police(8) action, the easiest way is to simply drop the packets which exceed or conform the configured bandwidth limit. Add a new option to tc-skbmod(8), so that users may use the ECN [1] extension to explicitly inform the receiver about the congestion instead of dropping packets "on the floor". The 2 least significant bits of the Traffic Class field in IPv4 and IPv6 headers are used to represent different ECN states [2]: 0b00: "Non ECN-Capable Transport", Non-ECT 0b10: "ECN Capable Transport", ECT(0) 0b01: "ECN Capable Transport", ECT(1) 0b11: "Congestion Encountered", CE As an example: $ tc filter add dev eth0 parent 1: protocol ip prio 10 \ matchall action skbmod ecn Doing the above marks all ECT(0) and ECT(1) packets as CE. It does NOT affect Non-ECT or non-IP packets. In the tc-police scenario mentioned above, users may pipe a tc-police action and a tc-skbmod "ecn" action together to achieve ECN-based rate limiting. For TCP connections, upon receiving a CE packet, the receiver will respond with an ECE packet, asking the sender to reduce their congestion window. However ECN also works with other L4 protocols e.g. DCCP and SCTP [2], and our implementation does not touch or care about L4 headers. The updated tc-skbmod SYNOPSIS looks like the following: tc ... action skbmod { set SETTABLE | swap SWAPPABLE | ecn } ... Only one of "set", "swap" or "ecn" shall be used in a single tc-skbmod command. Trying to use more than one of them at a time is considered undefined behavior; pipe multiple tc-skbmod commands together instead. "set" and "swap" only affect Ethernet packets, while "ecn" only affects IPv{4,6} packets. It is also worth mentioning that, in theory, the same effect could be achieved by piping a "police" action and a "bpf" action using the bpf_skb_ecn_set_ce() helper, but this requires eBPF programming from the user, thus impractical. Depends on patch "net/sched: act_skbmod: Skip non-Ethernet packets". [1] https://datatracker.ietf.org/doc/html/rfc3168 [2] https://en.wikipedia.org/wiki/Explicit_Congestion_Notification Reviewed-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Peilin Ye <peilin.ye@bytedance.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-07-27 18:33:15 -07:00
int action, max_edit_len, err;
struct tcf_skbmod_params *p;
u64 flags;
tcf_lastuse_update(&d->tcf_tm);
bstats_update(this_cpu_ptr(d->common.cpu_bstats), skb);
action = READ_ONCE(d->tcf_action);
if (unlikely(action == TC_ACT_SHOT))
goto drop;
net/sched: act_skbmod: Add SKBMOD_F_ECN option support Currently, when doing rate limiting using the tc-police(8) action, the easiest way is to simply drop the packets which exceed or conform the configured bandwidth limit. Add a new option to tc-skbmod(8), so that users may use the ECN [1] extension to explicitly inform the receiver about the congestion instead of dropping packets "on the floor". The 2 least significant bits of the Traffic Class field in IPv4 and IPv6 headers are used to represent different ECN states [2]: 0b00: "Non ECN-Capable Transport", Non-ECT 0b10: "ECN Capable Transport", ECT(0) 0b01: "ECN Capable Transport", ECT(1) 0b11: "Congestion Encountered", CE As an example: $ tc filter add dev eth0 parent 1: protocol ip prio 10 \ matchall action skbmod ecn Doing the above marks all ECT(0) and ECT(1) packets as CE. It does NOT affect Non-ECT or non-IP packets. In the tc-police scenario mentioned above, users may pipe a tc-police action and a tc-skbmod "ecn" action together to achieve ECN-based rate limiting. For TCP connections, upon receiving a CE packet, the receiver will respond with an ECE packet, asking the sender to reduce their congestion window. However ECN also works with other L4 protocols e.g. DCCP and SCTP [2], and our implementation does not touch or care about L4 headers. The updated tc-skbmod SYNOPSIS looks like the following: tc ... action skbmod { set SETTABLE | swap SWAPPABLE | ecn } ... Only one of "set", "swap" or "ecn" shall be used in a single tc-skbmod command. Trying to use more than one of them at a time is considered undefined behavior; pipe multiple tc-skbmod commands together instead. "set" and "swap" only affect Ethernet packets, while "ecn" only affects IPv{4,6} packets. It is also worth mentioning that, in theory, the same effect could be achieved by piping a "police" action and a "bpf" action using the bpf_skb_ecn_set_ce() helper, but this requires eBPF programming from the user, thus impractical. Depends on patch "net/sched: act_skbmod: Skip non-Ethernet packets". [1] https://datatracker.ietf.org/doc/html/rfc3168 [2] https://en.wikipedia.org/wiki/Explicit_Congestion_Notification Reviewed-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Peilin Ye <peilin.ye@bytedance.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-07-27 18:33:15 -07:00
max_edit_len = skb_mac_header_len(skb);
p = rcu_dereference_bh(d->skbmod_p);
flags = p->flags;
/* tcf_skbmod_init() guarantees "flags" to be one of the following:
* 1. a combination of SKBMOD_F_{DMAC,SMAC,ETYPE}
* 2. SKBMOD_F_SWAPMAC
* 3. SKBMOD_F_ECN
* SKBMOD_F_ECN only works with IP packets; all other flags only work with Ethernet
* packets.
*/
if (flags == SKBMOD_F_ECN) {
switch (skb_protocol(skb, true)) {
case cpu_to_be16(ETH_P_IP):
case cpu_to_be16(ETH_P_IPV6):
max_edit_len += skb_network_header_len(skb);
break;
default:
goto out;
}
} else if (!skb->dev || skb->dev->type != ARPHRD_ETHER) {
goto out;
}
net/sched: act_skbmod: Add SKBMOD_F_ECN option support Currently, when doing rate limiting using the tc-police(8) action, the easiest way is to simply drop the packets which exceed or conform the configured bandwidth limit. Add a new option to tc-skbmod(8), so that users may use the ECN [1] extension to explicitly inform the receiver about the congestion instead of dropping packets "on the floor". The 2 least significant bits of the Traffic Class field in IPv4 and IPv6 headers are used to represent different ECN states [2]: 0b00: "Non ECN-Capable Transport", Non-ECT 0b10: "ECN Capable Transport", ECT(0) 0b01: "ECN Capable Transport", ECT(1) 0b11: "Congestion Encountered", CE As an example: $ tc filter add dev eth0 parent 1: protocol ip prio 10 \ matchall action skbmod ecn Doing the above marks all ECT(0) and ECT(1) packets as CE. It does NOT affect Non-ECT or non-IP packets. In the tc-police scenario mentioned above, users may pipe a tc-police action and a tc-skbmod "ecn" action together to achieve ECN-based rate limiting. For TCP connections, upon receiving a CE packet, the receiver will respond with an ECE packet, asking the sender to reduce their congestion window. However ECN also works with other L4 protocols e.g. DCCP and SCTP [2], and our implementation does not touch or care about L4 headers. The updated tc-skbmod SYNOPSIS looks like the following: tc ... action skbmod { set SETTABLE | swap SWAPPABLE | ecn } ... Only one of "set", "swap" or "ecn" shall be used in a single tc-skbmod command. Trying to use more than one of them at a time is considered undefined behavior; pipe multiple tc-skbmod commands together instead. "set" and "swap" only affect Ethernet packets, while "ecn" only affects IPv{4,6} packets. It is also worth mentioning that, in theory, the same effect could be achieved by piping a "police" action and a "bpf" action using the bpf_skb_ecn_set_ce() helper, but this requires eBPF programming from the user, thus impractical. Depends on patch "net/sched: act_skbmod: Skip non-Ethernet packets". [1] https://datatracker.ietf.org/doc/html/rfc3168 [2] https://en.wikipedia.org/wiki/Explicit_Congestion_Notification Reviewed-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Peilin Ye <peilin.ye@bytedance.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-07-27 18:33:15 -07:00
err = skb_ensure_writable(skb, max_edit_len);
if (unlikely(err)) /* best policy is to drop on the floor */
goto drop;
if (flags & SKBMOD_F_DMAC)
ether_addr_copy(eth_hdr(skb)->h_dest, p->eth_dst);
if (flags & SKBMOD_F_SMAC)
ether_addr_copy(eth_hdr(skb)->h_source, p->eth_src);
if (flags & SKBMOD_F_ETYPE)
eth_hdr(skb)->h_proto = p->eth_type;
if (flags & SKBMOD_F_SWAPMAC) {
u16 tmpaddr[ETH_ALEN / 2]; /* ether_addr_copy() requirement */
/*XXX: I am sure we can come up with more efficient swapping*/
ether_addr_copy((u8 *)tmpaddr, eth_hdr(skb)->h_dest);
ether_addr_copy(eth_hdr(skb)->h_dest, eth_hdr(skb)->h_source);
ether_addr_copy(eth_hdr(skb)->h_source, (u8 *)tmpaddr);
}
net/sched: act_skbmod: Add SKBMOD_F_ECN option support Currently, when doing rate limiting using the tc-police(8) action, the easiest way is to simply drop the packets which exceed or conform the configured bandwidth limit. Add a new option to tc-skbmod(8), so that users may use the ECN [1] extension to explicitly inform the receiver about the congestion instead of dropping packets "on the floor". The 2 least significant bits of the Traffic Class field in IPv4 and IPv6 headers are used to represent different ECN states [2]: 0b00: "Non ECN-Capable Transport", Non-ECT 0b10: "ECN Capable Transport", ECT(0) 0b01: "ECN Capable Transport", ECT(1) 0b11: "Congestion Encountered", CE As an example: $ tc filter add dev eth0 parent 1: protocol ip prio 10 \ matchall action skbmod ecn Doing the above marks all ECT(0) and ECT(1) packets as CE. It does NOT affect Non-ECT or non-IP packets. In the tc-police scenario mentioned above, users may pipe a tc-police action and a tc-skbmod "ecn" action together to achieve ECN-based rate limiting. For TCP connections, upon receiving a CE packet, the receiver will respond with an ECE packet, asking the sender to reduce their congestion window. However ECN also works with other L4 protocols e.g. DCCP and SCTP [2], and our implementation does not touch or care about L4 headers. The updated tc-skbmod SYNOPSIS looks like the following: tc ... action skbmod { set SETTABLE | swap SWAPPABLE | ecn } ... Only one of "set", "swap" or "ecn" shall be used in a single tc-skbmod command. Trying to use more than one of them at a time is considered undefined behavior; pipe multiple tc-skbmod commands together instead. "set" and "swap" only affect Ethernet packets, while "ecn" only affects IPv{4,6} packets. It is also worth mentioning that, in theory, the same effect could be achieved by piping a "police" action and a "bpf" action using the bpf_skb_ecn_set_ce() helper, but this requires eBPF programming from the user, thus impractical. Depends on patch "net/sched: act_skbmod: Skip non-Ethernet packets". [1] https://datatracker.ietf.org/doc/html/rfc3168 [2] https://en.wikipedia.org/wiki/Explicit_Congestion_Notification Reviewed-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Peilin Ye <peilin.ye@bytedance.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-07-27 18:33:15 -07:00
if (flags & SKBMOD_F_ECN)
INET_ECN_set_ce(skb);
out:
return action;
drop:
qstats_overlimit_inc(this_cpu_ptr(d->common.cpu_qstats));
return TC_ACT_SHOT;
}
static const struct nla_policy skbmod_policy[TCA_SKBMOD_MAX + 1] = {
[TCA_SKBMOD_PARMS] = { .len = sizeof(struct tc_skbmod) },
[TCA_SKBMOD_DMAC] = { .len = ETH_ALEN },
[TCA_SKBMOD_SMAC] = { .len = ETH_ALEN },
[TCA_SKBMOD_ETYPE] = { .type = NLA_U16 },
};
static int tcf_skbmod_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_skbmod_ops.net_id);
bool ovr = flags & TCA_ACT_FLAGS_REPLACE;
bool bind = flags & TCA_ACT_FLAGS_BIND;
struct nlattr *tb[TCA_SKBMOD_MAX + 1];
struct tcf_skbmod_params *p, *p_old;
net/sched: act_skbmod: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action skbmod set smac 00:c1:a0:c1:a0:00 pass index 90 # tc actions replace action skbmod \ > set smac 00:c1:a0:c1:a0:00 goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action skbmod had the following output: src MAC address <00:c1:a0:c1:a0:00> src MAC address <00:c1:a0:c1:a0:00> Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: skbmod goto chain 42 set smac 00:c1:a0:c1:a0:00 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 800000002d5c7067 P4D 800000002d5c7067 PUD 77e16067 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:ffff8987ffd83be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff8987aeb68800 RCX: ffff8987fa263640 RDX: 0000000000000000 RSI: ffff8987f51c8802 RDI: 00000000000000a0 RBP: ffff8987ffd83c80 R08: ffff8987f939bac8 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8987f5c77d00 R13: ffff8987f5c77d08 R14: 0000000000000001 R15: ffff8987f0c29f00 FS: 0000000000000000(0000) GS:ffff8987ffd80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007832c004 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 ? tick_sched_timer+0x37/0x70 __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: 56 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:ffffa2a1c038feb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffffa94184f0 RBX: 0000000000000003 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000003 RBP: 0000000000000003 R08: 001123cfc2ba71ac R09: 0000000000000000 R10: 0000000000000000 R11: 00000000000f4240 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_skbmod veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel mbcache jbd2 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device aesni_intel crypto_simd cryptd glue_helper snd_pcm joydev pcspkr virtio_balloon snd_timer snd i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect virtio_net sysimgblt fb_sys_fops net_failover virtio_console ttm virtio_blk failover drm crc32c_intel serio_raw ata_piix virtio_pci libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_skbmod_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 07:00:12 -07:00
struct tcf_chain *goto_ch = NULL;
struct tc_skbmod *parm;
u32 lflags = 0, index;
struct tcf_skbmod *d;
bool exists = false;
u8 *daddr = NULL;
u8 *saddr = NULL;
u16 eth_type = 0;
int ret = 0, err;
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 05:07:28 -07:00
err = nla_parse_nested_deprecated(tb, TCA_SKBMOD_MAX, nla,
skbmod_policy, NULL);
if (err < 0)
return err;
if (!tb[TCA_SKBMOD_PARMS])
return -EINVAL;
if (tb[TCA_SKBMOD_DMAC]) {
daddr = nla_data(tb[TCA_SKBMOD_DMAC]);
lflags |= SKBMOD_F_DMAC;
}
if (tb[TCA_SKBMOD_SMAC]) {
saddr = nla_data(tb[TCA_SKBMOD_SMAC]);
lflags |= SKBMOD_F_SMAC;
}
if (tb[TCA_SKBMOD_ETYPE]) {
eth_type = nla_get_u16(tb[TCA_SKBMOD_ETYPE]);
lflags |= SKBMOD_F_ETYPE;
}
parm = nla_data(tb[TCA_SKBMOD_PARMS]);
index = parm->index;
if (parm->flags & SKBMOD_F_SWAPMAC)
lflags = SKBMOD_F_SWAPMAC;
net/sched: act_skbmod: Add SKBMOD_F_ECN option support Currently, when doing rate limiting using the tc-police(8) action, the easiest way is to simply drop the packets which exceed or conform the configured bandwidth limit. Add a new option to tc-skbmod(8), so that users may use the ECN [1] extension to explicitly inform the receiver about the congestion instead of dropping packets "on the floor". The 2 least significant bits of the Traffic Class field in IPv4 and IPv6 headers are used to represent different ECN states [2]: 0b00: "Non ECN-Capable Transport", Non-ECT 0b10: "ECN Capable Transport", ECT(0) 0b01: "ECN Capable Transport", ECT(1) 0b11: "Congestion Encountered", CE As an example: $ tc filter add dev eth0 parent 1: protocol ip prio 10 \ matchall action skbmod ecn Doing the above marks all ECT(0) and ECT(1) packets as CE. It does NOT affect Non-ECT or non-IP packets. In the tc-police scenario mentioned above, users may pipe a tc-police action and a tc-skbmod "ecn" action together to achieve ECN-based rate limiting. For TCP connections, upon receiving a CE packet, the receiver will respond with an ECE packet, asking the sender to reduce their congestion window. However ECN also works with other L4 protocols e.g. DCCP and SCTP [2], and our implementation does not touch or care about L4 headers. The updated tc-skbmod SYNOPSIS looks like the following: tc ... action skbmod { set SETTABLE | swap SWAPPABLE | ecn } ... Only one of "set", "swap" or "ecn" shall be used in a single tc-skbmod command. Trying to use more than one of them at a time is considered undefined behavior; pipe multiple tc-skbmod commands together instead. "set" and "swap" only affect Ethernet packets, while "ecn" only affects IPv{4,6} packets. It is also worth mentioning that, in theory, the same effect could be achieved by piping a "police" action and a "bpf" action using the bpf_skb_ecn_set_ce() helper, but this requires eBPF programming from the user, thus impractical. Depends on patch "net/sched: act_skbmod: Skip non-Ethernet packets". [1] https://datatracker.ietf.org/doc/html/rfc3168 [2] https://en.wikipedia.org/wiki/Explicit_Congestion_Notification Reviewed-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Peilin Ye <peilin.ye@bytedance.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-07-27 18:33:15 -07:00
if (parm->flags & SKBMOD_F_ECN)
lflags = SKBMOD_F_ECN;
err = tcf_idr_check_alloc(tn, &index, a, bind);
if (err < 0)
return err;
exists = err;
if (exists && bind)
return ACT_P_BOUND;
if (!lflags) {
if (exists)
tcf_idr_release(*a, bind);
else
tcf_idr_cleanup(tn, index);
return -EINVAL;
}
if (!exists) {
ret = tcf_idr_create(tn, index, est, a,
&act_skbmod_ops, bind, true, flags);
if (ret) {
tcf_idr_cleanup(tn, index);
return ret;
}
ret = ACT_P_CREATED;
} else if (!ovr) {
tcf_idr_release(*a, bind);
return -EEXIST;
}
net/sched: act_skbmod: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action skbmod set smac 00:c1:a0:c1:a0:00 pass index 90 # tc actions replace action skbmod \ > set smac 00:c1:a0:c1:a0:00 goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action skbmod had the following output: src MAC address <00:c1:a0:c1:a0:00> src MAC address <00:c1:a0:c1:a0:00> Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: skbmod goto chain 42 set smac 00:c1:a0:c1:a0:00 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 800000002d5c7067 P4D 800000002d5c7067 PUD 77e16067 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:ffff8987ffd83be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff8987aeb68800 RCX: ffff8987fa263640 RDX: 0000000000000000 RSI: ffff8987f51c8802 RDI: 00000000000000a0 RBP: ffff8987ffd83c80 R08: ffff8987f939bac8 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8987f5c77d00 R13: ffff8987f5c77d08 R14: 0000000000000001 R15: ffff8987f0c29f00 FS: 0000000000000000(0000) GS:ffff8987ffd80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007832c004 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 ? tick_sched_timer+0x37/0x70 __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: 56 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:ffffa2a1c038feb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffffa94184f0 RBX: 0000000000000003 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000003 RBP: 0000000000000003 R08: 001123cfc2ba71ac R09: 0000000000000000 R10: 0000000000000000 R11: 00000000000f4240 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_skbmod veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel mbcache jbd2 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device aesni_intel crypto_simd cryptd glue_helper snd_pcm joydev pcspkr virtio_balloon snd_timer snd i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect virtio_net sysimgblt fb_sys_fops net_failover virtio_console ttm virtio_blk failover drm crc32c_intel serio_raw ata_piix virtio_pci libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_skbmod_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 07:00:12 -07:00
err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
if (err < 0)
goto release_idr;
d = to_skbmod(*a);
p = kzalloc(sizeof(struct tcf_skbmod_params), GFP_KERNEL);
if (unlikely(!p)) {
net/sched: act_skbmod: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action skbmod set smac 00:c1:a0:c1:a0:00 pass index 90 # tc actions replace action skbmod \ > set smac 00:c1:a0:c1:a0:00 goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action skbmod had the following output: src MAC address <00:c1:a0:c1:a0:00> src MAC address <00:c1:a0:c1:a0:00> Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: skbmod goto chain 42 set smac 00:c1:a0:c1:a0:00 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 800000002d5c7067 P4D 800000002d5c7067 PUD 77e16067 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:ffff8987ffd83be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff8987aeb68800 RCX: ffff8987fa263640 RDX: 0000000000000000 RSI: ffff8987f51c8802 RDI: 00000000000000a0 RBP: ffff8987ffd83c80 R08: ffff8987f939bac8 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8987f5c77d00 R13: ffff8987f5c77d08 R14: 0000000000000001 R15: ffff8987f0c29f00 FS: 0000000000000000(0000) GS:ffff8987ffd80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007832c004 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 ? tick_sched_timer+0x37/0x70 __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: 56 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:ffffa2a1c038feb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffffa94184f0 RBX: 0000000000000003 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000003 RBP: 0000000000000003 R08: 001123cfc2ba71ac R09: 0000000000000000 R10: 0000000000000000 R11: 00000000000f4240 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_skbmod veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel mbcache jbd2 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device aesni_intel crypto_simd cryptd glue_helper snd_pcm joydev pcspkr virtio_balloon snd_timer snd i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect virtio_net sysimgblt fb_sys_fops net_failover virtio_console ttm virtio_blk failover drm crc32c_intel serio_raw ata_piix virtio_pci libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_skbmod_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 07:00:12 -07:00
err = -ENOMEM;
goto put_chain;
}
p->flags = lflags;
if (ovr)
spin_lock_bh(&d->tcf_lock);
/* Protected by tcf_lock if overwriting existing action. */
net/sched: act_skbmod: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action skbmod set smac 00:c1:a0:c1:a0:00 pass index 90 # tc actions replace action skbmod \ > set smac 00:c1:a0:c1:a0:00 goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action skbmod had the following output: src MAC address <00:c1:a0:c1:a0:00> src MAC address <00:c1:a0:c1:a0:00> Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: skbmod goto chain 42 set smac 00:c1:a0:c1:a0:00 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 800000002d5c7067 P4D 800000002d5c7067 PUD 77e16067 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:ffff8987ffd83be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff8987aeb68800 RCX: ffff8987fa263640 RDX: 0000000000000000 RSI: ffff8987f51c8802 RDI: 00000000000000a0 RBP: ffff8987ffd83c80 R08: ffff8987f939bac8 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8987f5c77d00 R13: ffff8987f5c77d08 R14: 0000000000000001 R15: ffff8987f0c29f00 FS: 0000000000000000(0000) GS:ffff8987ffd80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007832c004 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 ? tick_sched_timer+0x37/0x70 __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: 56 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:ffffa2a1c038feb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffffa94184f0 RBX: 0000000000000003 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000003 RBP: 0000000000000003 R08: 001123cfc2ba71ac R09: 0000000000000000 R10: 0000000000000000 R11: 00000000000f4240 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_skbmod veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel mbcache jbd2 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device aesni_intel crypto_simd cryptd glue_helper snd_pcm joydev pcspkr virtio_balloon snd_timer snd i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect virtio_net sysimgblt fb_sys_fops net_failover virtio_console ttm virtio_blk failover drm crc32c_intel serio_raw ata_piix virtio_pci libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_skbmod_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 07:00:12 -07:00
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
p_old = rcu_dereference_protected(d->skbmod_p, 1);
if (lflags & SKBMOD_F_DMAC)
ether_addr_copy(p->eth_dst, daddr);
if (lflags & SKBMOD_F_SMAC)
ether_addr_copy(p->eth_src, saddr);
if (lflags & SKBMOD_F_ETYPE)
p->eth_type = htons(eth_type);
rcu_assign_pointer(d->skbmod_p, p);
if (ovr)
spin_unlock_bh(&d->tcf_lock);
if (p_old)
kfree_rcu(p_old, rcu);
net/sched: act_skbmod: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action skbmod set smac 00:c1:a0:c1:a0:00 pass index 90 # tc actions replace action skbmod \ > set smac 00:c1:a0:c1:a0:00 goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action skbmod had the following output: src MAC address <00:c1:a0:c1:a0:00> src MAC address <00:c1:a0:c1:a0:00> Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: skbmod goto chain 42 set smac 00:c1:a0:c1:a0:00 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 800000002d5c7067 P4D 800000002d5c7067 PUD 77e16067 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:ffff8987ffd83be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff8987aeb68800 RCX: ffff8987fa263640 RDX: 0000000000000000 RSI: ffff8987f51c8802 RDI: 00000000000000a0 RBP: ffff8987ffd83c80 R08: ffff8987f939bac8 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8987f5c77d00 R13: ffff8987f5c77d08 R14: 0000000000000001 R15: ffff8987f0c29f00 FS: 0000000000000000(0000) GS:ffff8987ffd80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007832c004 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 ? tick_sched_timer+0x37/0x70 __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: 56 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:ffffa2a1c038feb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffffa94184f0 RBX: 0000000000000003 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000003 RBP: 0000000000000003 R08: 001123cfc2ba71ac R09: 0000000000000000 R10: 0000000000000000 R11: 00000000000f4240 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_skbmod veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel mbcache jbd2 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device aesni_intel crypto_simd cryptd glue_helper snd_pcm joydev pcspkr virtio_balloon snd_timer snd i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect virtio_net sysimgblt fb_sys_fops net_failover virtio_console ttm virtio_blk failover drm crc32c_intel serio_raw ata_piix virtio_pci libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_skbmod_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 07:00:12 -07:00
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
return ret;
net/sched: act_skbmod: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action skbmod set smac 00:c1:a0:c1:a0:00 pass index 90 # tc actions replace action skbmod \ > set smac 00:c1:a0:c1:a0:00 goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action skbmod had the following output: src MAC address <00:c1:a0:c1:a0:00> src MAC address <00:c1:a0:c1:a0:00> Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: skbmod goto chain 42 set smac 00:c1:a0:c1:a0:00 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 800000002d5c7067 P4D 800000002d5c7067 PUD 77e16067 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:ffff8987ffd83be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff8987aeb68800 RCX: ffff8987fa263640 RDX: 0000000000000000 RSI: ffff8987f51c8802 RDI: 00000000000000a0 RBP: ffff8987ffd83c80 R08: ffff8987f939bac8 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8987f5c77d00 R13: ffff8987f5c77d08 R14: 0000000000000001 R15: ffff8987f0c29f00 FS: 0000000000000000(0000) GS:ffff8987ffd80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007832c004 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 ? tick_sched_timer+0x37/0x70 __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: 56 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:ffffa2a1c038feb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffffa94184f0 RBX: 0000000000000003 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000003 RBP: 0000000000000003 R08: 001123cfc2ba71ac R09: 0000000000000000 R10: 0000000000000000 R11: 00000000000f4240 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_skbmod veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel mbcache jbd2 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device aesni_intel crypto_simd cryptd glue_helper snd_pcm joydev pcspkr virtio_balloon snd_timer snd i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect virtio_net sysimgblt fb_sys_fops net_failover virtio_console ttm virtio_blk failover drm crc32c_intel serio_raw ata_piix virtio_pci libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_skbmod_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 07:00:12 -07:00
put_chain:
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
release_idr:
tcf_idr_release(*a, bind);
return err;
}
static void tcf_skbmod_cleanup(struct tc_action *a)
{
struct tcf_skbmod *d = to_skbmod(a);
struct tcf_skbmod_params *p;
p = rcu_dereference_protected(d->skbmod_p, 1);
net/sched: fix NULL dereference on the error path of tcf_skbmod_init() when the following command # tc action replace action skbmod swap mac index 100 is run for the first time, and tcf_skbmod_init() fails to allocate struct tcf_skbmod_params, tcf_skbmod_cleanup() calls kfree_rcu(NULL), thus causing the following error: BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 IP: __call_rcu+0x23/0x2b0 PGD 8000000034057067 P4D 8000000034057067 PUD 74937067 PMD 0 Oops: 0002 [#1] SMP PTI Modules linked in: act_skbmod(E) psample ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 snd_hda_codec_generic snd_hda_intel snd_hda_codec crct10dif_pclmul mbcache jbd2 crc32_pclmul snd_hda_core ghash_clmulni_intel snd_hwdep pcbc snd_seq snd_seq_device snd_pcm aesni_intel snd_timer crypto_simd glue_helper snd cryptd virtio_balloon joydev soundcore 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_net virtio_blk ata_piix libata crc32c_intel virtio_pci serio_raw virtio_ring virtio i2c_core floppy dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_skbmod] CPU: 3 PID: 3144 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:ffffbd2e403e7798 EFLAGS: 00010246 RAX: ffffffffc0872080 RBX: ffff981d34bff780 RCX: 00000000ffffffff RDX: ffffffff922a5f00 RSI: 0000000000000000 RDI: 0000000000000000 RBP: 0000000000000000 R08: 0000000000000001 R09: 000000000000021f R10: 000000003d003000 R11: 0000000000aaaaaa R12: 0000000000000000 R13: ffffffff922a5f00 R14: 0000000000000001 R15: ffff981d3b698c2c FS: 00007f3678292740(0000) GS:ffff981d3fd80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000008 CR3: 000000007c57a006 CR4: 00000000001606e0 Call Trace: __tcf_idr_release+0x79/0xf0 tcf_skbmod_init+0x1d1/0x210 [act_skbmod] 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: 0033:0x7f36776a3ba0 RSP: 002b:00007fff4703b618 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007fff4703b740 RCX: 00007f36776a3ba0 RDX: 0000000000000000 RSI: 00007fff4703b690 RDI: 0000000000000003 RBP: 000000005aaaba36 R08: 0000000000000002 R09: 0000000000000000 R10: 00007fff4703b0a0 R11: 0000000000000246 R12: 0000000000000000 R13: 00007fff4703b754 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: ffffbd2e403e7798 CR2: 0000000000000008 Fix it in tcf_skbmod_cleanup(), ensuring that kfree_rcu(p, ...) is called only when p is not NULL. Fixes: 86da71b57383 ("net_sched: Introduce skbmod action") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-15 16:00:57 -07:00
if (p)
kfree_rcu(p, rcu);
}
static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a,
int bind, int ref)
{
struct tcf_skbmod *d = to_skbmod(a);
unsigned char *b = skb_tail_pointer(skb);
struct tcf_skbmod_params *p;
net/sched: act_skbmod: prevent kernel-infoleak syzbot found that tcf_skbmod_dump() was copying four bytes from kernel stack to user space [1]. The issue here is that 'struct tc_skbmod' has a four bytes hole. We need to clear the structure before filling fields. [1] BUG: KMSAN: kernel-infoleak in instrument_copy_to_user include/linux/instrumented.h:114 [inline] BUG: KMSAN: kernel-infoleak in copy_to_user_iter lib/iov_iter.c:24 [inline] BUG: KMSAN: kernel-infoleak in iterate_ubuf include/linux/iov_iter.h:29 [inline] BUG: KMSAN: kernel-infoleak in iterate_and_advance2 include/linux/iov_iter.h:245 [inline] BUG: KMSAN: kernel-infoleak in iterate_and_advance include/linux/iov_iter.h:271 [inline] BUG: KMSAN: kernel-infoleak in _copy_to_iter+0x366/0x2520 lib/iov_iter.c:185 instrument_copy_to_user include/linux/instrumented.h:114 [inline] copy_to_user_iter lib/iov_iter.c:24 [inline] iterate_ubuf include/linux/iov_iter.h:29 [inline] iterate_and_advance2 include/linux/iov_iter.h:245 [inline] iterate_and_advance include/linux/iov_iter.h:271 [inline] _copy_to_iter+0x366/0x2520 lib/iov_iter.c:185 copy_to_iter include/linux/uio.h:196 [inline] simple_copy_to_iter net/core/datagram.c:532 [inline] __skb_datagram_iter+0x185/0x1000 net/core/datagram.c:420 skb_copy_datagram_iter+0x5c/0x200 net/core/datagram.c:546 skb_copy_datagram_msg include/linux/skbuff.h:4050 [inline] netlink_recvmsg+0x432/0x1610 net/netlink/af_netlink.c:1962 sock_recvmsg_nosec net/socket.c:1046 [inline] sock_recvmsg+0x2c4/0x340 net/socket.c:1068 __sys_recvfrom+0x35a/0x5f0 net/socket.c:2242 __do_sys_recvfrom net/socket.c:2260 [inline] __se_sys_recvfrom net/socket.c:2256 [inline] __x64_sys_recvfrom+0x126/0x1d0 net/socket.c:2256 do_syscall_64+0xd5/0x1f0 entry_SYSCALL_64_after_hwframe+0x6d/0x75 Uninit was stored to memory at: pskb_expand_head+0x30f/0x19d0 net/core/skbuff.c:2253 netlink_trim+0x2c2/0x330 net/netlink/af_netlink.c:1317 netlink_unicast+0x9f/0x1260 net/netlink/af_netlink.c:1351 nlmsg_unicast include/net/netlink.h:1144 [inline] nlmsg_notify+0x21d/0x2f0 net/netlink/af_netlink.c:2610 rtnetlink_send+0x73/0x90 net/core/rtnetlink.c:741 rtnetlink_maybe_send include/linux/rtnetlink.h:17 [inline] tcf_add_notify net/sched/act_api.c:2048 [inline] tcf_action_add net/sched/act_api.c:2071 [inline] tc_ctl_action+0x146e/0x19d0 net/sched/act_api.c:2119 rtnetlink_rcv_msg+0x1737/0x1900 net/core/rtnetlink.c:6595 netlink_rcv_skb+0x375/0x650 net/netlink/af_netlink.c:2559 rtnetlink_rcv+0x34/0x40 net/core/rtnetlink.c:6613 netlink_unicast_kernel net/netlink/af_netlink.c:1335 [inline] netlink_unicast+0xf4c/0x1260 net/netlink/af_netlink.c:1361 netlink_sendmsg+0x10df/0x11f0 net/netlink/af_netlink.c:1905 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x30f/0x380 net/socket.c:745 ____sys_sendmsg+0x877/0xb60 net/socket.c:2584 ___sys_sendmsg+0x28d/0x3c0 net/socket.c:2638 __sys_sendmsg net/socket.c:2667 [inline] __do_sys_sendmsg net/socket.c:2676 [inline] __se_sys_sendmsg net/socket.c:2674 [inline] __x64_sys_sendmsg+0x307/0x4a0 net/socket.c:2674 do_syscall_64+0xd5/0x1f0 entry_SYSCALL_64_after_hwframe+0x6d/0x75 Uninit was stored to memory at: __nla_put lib/nlattr.c:1041 [inline] nla_put+0x1c6/0x230 lib/nlattr.c:1099 tcf_skbmod_dump+0x23f/0xc20 net/sched/act_skbmod.c:256 tcf_action_dump_old net/sched/act_api.c:1191 [inline] tcf_action_dump_1+0x85e/0x970 net/sched/act_api.c:1227 tcf_action_dump+0x1fd/0x460 net/sched/act_api.c:1251 tca_get_fill+0x519/0x7a0 net/sched/act_api.c:1628 tcf_add_notify_msg net/sched/act_api.c:2023 [inline] tcf_add_notify net/sched/act_api.c:2042 [inline] tcf_action_add net/sched/act_api.c:2071 [inline] tc_ctl_action+0x1365/0x19d0 net/sched/act_api.c:2119 rtnetlink_rcv_msg+0x1737/0x1900 net/core/rtnetlink.c:6595 netlink_rcv_skb+0x375/0x650 net/netlink/af_netlink.c:2559 rtnetlink_rcv+0x34/0x40 net/core/rtnetlink.c:6613 netlink_unicast_kernel net/netlink/af_netlink.c:1335 [inline] netlink_unicast+0xf4c/0x1260 net/netlink/af_netlink.c:1361 netlink_sendmsg+0x10df/0x11f0 net/netlink/af_netlink.c:1905 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x30f/0x380 net/socket.c:745 ____sys_sendmsg+0x877/0xb60 net/socket.c:2584 ___sys_sendmsg+0x28d/0x3c0 net/socket.c:2638 __sys_sendmsg net/socket.c:2667 [inline] __do_sys_sendmsg net/socket.c:2676 [inline] __se_sys_sendmsg net/socket.c:2674 [inline] __x64_sys_sendmsg+0x307/0x4a0 net/socket.c:2674 do_syscall_64+0xd5/0x1f0 entry_SYSCALL_64_after_hwframe+0x6d/0x75 Local variable opt created at: tcf_skbmod_dump+0x9d/0xc20 net/sched/act_skbmod.c:244 tcf_action_dump_old net/sched/act_api.c:1191 [inline] tcf_action_dump_1+0x85e/0x970 net/sched/act_api.c:1227 Bytes 188-191 of 248 are uninitialized Memory access of size 248 starts at ffff888117697680 Data copied to user address 00007ffe56d855f0 Fixes: 86da71b57383 ("net_sched: Introduce skbmod action") Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Link: https://lore.kernel.org/r/20240403130908.93421-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-04-03 06:09:08 -07:00
struct tc_skbmod opt;
struct tcf_t t;
net/sched: act_skbmod: prevent kernel-infoleak syzbot found that tcf_skbmod_dump() was copying four bytes from kernel stack to user space [1]. The issue here is that 'struct tc_skbmod' has a four bytes hole. We need to clear the structure before filling fields. [1] BUG: KMSAN: kernel-infoleak in instrument_copy_to_user include/linux/instrumented.h:114 [inline] BUG: KMSAN: kernel-infoleak in copy_to_user_iter lib/iov_iter.c:24 [inline] BUG: KMSAN: kernel-infoleak in iterate_ubuf include/linux/iov_iter.h:29 [inline] BUG: KMSAN: kernel-infoleak in iterate_and_advance2 include/linux/iov_iter.h:245 [inline] BUG: KMSAN: kernel-infoleak in iterate_and_advance include/linux/iov_iter.h:271 [inline] BUG: KMSAN: kernel-infoleak in _copy_to_iter+0x366/0x2520 lib/iov_iter.c:185 instrument_copy_to_user include/linux/instrumented.h:114 [inline] copy_to_user_iter lib/iov_iter.c:24 [inline] iterate_ubuf include/linux/iov_iter.h:29 [inline] iterate_and_advance2 include/linux/iov_iter.h:245 [inline] iterate_and_advance include/linux/iov_iter.h:271 [inline] _copy_to_iter+0x366/0x2520 lib/iov_iter.c:185 copy_to_iter include/linux/uio.h:196 [inline] simple_copy_to_iter net/core/datagram.c:532 [inline] __skb_datagram_iter+0x185/0x1000 net/core/datagram.c:420 skb_copy_datagram_iter+0x5c/0x200 net/core/datagram.c:546 skb_copy_datagram_msg include/linux/skbuff.h:4050 [inline] netlink_recvmsg+0x432/0x1610 net/netlink/af_netlink.c:1962 sock_recvmsg_nosec net/socket.c:1046 [inline] sock_recvmsg+0x2c4/0x340 net/socket.c:1068 __sys_recvfrom+0x35a/0x5f0 net/socket.c:2242 __do_sys_recvfrom net/socket.c:2260 [inline] __se_sys_recvfrom net/socket.c:2256 [inline] __x64_sys_recvfrom+0x126/0x1d0 net/socket.c:2256 do_syscall_64+0xd5/0x1f0 entry_SYSCALL_64_after_hwframe+0x6d/0x75 Uninit was stored to memory at: pskb_expand_head+0x30f/0x19d0 net/core/skbuff.c:2253 netlink_trim+0x2c2/0x330 net/netlink/af_netlink.c:1317 netlink_unicast+0x9f/0x1260 net/netlink/af_netlink.c:1351 nlmsg_unicast include/net/netlink.h:1144 [inline] nlmsg_notify+0x21d/0x2f0 net/netlink/af_netlink.c:2610 rtnetlink_send+0x73/0x90 net/core/rtnetlink.c:741 rtnetlink_maybe_send include/linux/rtnetlink.h:17 [inline] tcf_add_notify net/sched/act_api.c:2048 [inline] tcf_action_add net/sched/act_api.c:2071 [inline] tc_ctl_action+0x146e/0x19d0 net/sched/act_api.c:2119 rtnetlink_rcv_msg+0x1737/0x1900 net/core/rtnetlink.c:6595 netlink_rcv_skb+0x375/0x650 net/netlink/af_netlink.c:2559 rtnetlink_rcv+0x34/0x40 net/core/rtnetlink.c:6613 netlink_unicast_kernel net/netlink/af_netlink.c:1335 [inline] netlink_unicast+0xf4c/0x1260 net/netlink/af_netlink.c:1361 netlink_sendmsg+0x10df/0x11f0 net/netlink/af_netlink.c:1905 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x30f/0x380 net/socket.c:745 ____sys_sendmsg+0x877/0xb60 net/socket.c:2584 ___sys_sendmsg+0x28d/0x3c0 net/socket.c:2638 __sys_sendmsg net/socket.c:2667 [inline] __do_sys_sendmsg net/socket.c:2676 [inline] __se_sys_sendmsg net/socket.c:2674 [inline] __x64_sys_sendmsg+0x307/0x4a0 net/socket.c:2674 do_syscall_64+0xd5/0x1f0 entry_SYSCALL_64_after_hwframe+0x6d/0x75 Uninit was stored to memory at: __nla_put lib/nlattr.c:1041 [inline] nla_put+0x1c6/0x230 lib/nlattr.c:1099 tcf_skbmod_dump+0x23f/0xc20 net/sched/act_skbmod.c:256 tcf_action_dump_old net/sched/act_api.c:1191 [inline] tcf_action_dump_1+0x85e/0x970 net/sched/act_api.c:1227 tcf_action_dump+0x1fd/0x460 net/sched/act_api.c:1251 tca_get_fill+0x519/0x7a0 net/sched/act_api.c:1628 tcf_add_notify_msg net/sched/act_api.c:2023 [inline] tcf_add_notify net/sched/act_api.c:2042 [inline] tcf_action_add net/sched/act_api.c:2071 [inline] tc_ctl_action+0x1365/0x19d0 net/sched/act_api.c:2119 rtnetlink_rcv_msg+0x1737/0x1900 net/core/rtnetlink.c:6595 netlink_rcv_skb+0x375/0x650 net/netlink/af_netlink.c:2559 rtnetlink_rcv+0x34/0x40 net/core/rtnetlink.c:6613 netlink_unicast_kernel net/netlink/af_netlink.c:1335 [inline] netlink_unicast+0xf4c/0x1260 net/netlink/af_netlink.c:1361 netlink_sendmsg+0x10df/0x11f0 net/netlink/af_netlink.c:1905 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x30f/0x380 net/socket.c:745 ____sys_sendmsg+0x877/0xb60 net/socket.c:2584 ___sys_sendmsg+0x28d/0x3c0 net/socket.c:2638 __sys_sendmsg net/socket.c:2667 [inline] __do_sys_sendmsg net/socket.c:2676 [inline] __se_sys_sendmsg net/socket.c:2674 [inline] __x64_sys_sendmsg+0x307/0x4a0 net/socket.c:2674 do_syscall_64+0xd5/0x1f0 entry_SYSCALL_64_after_hwframe+0x6d/0x75 Local variable opt created at: tcf_skbmod_dump+0x9d/0xc20 net/sched/act_skbmod.c:244 tcf_action_dump_old net/sched/act_api.c:1191 [inline] tcf_action_dump_1+0x85e/0x970 net/sched/act_api.c:1227 Bytes 188-191 of 248 are uninitialized Memory access of size 248 starts at ffff888117697680 Data copied to user address 00007ffe56d855f0 Fixes: 86da71b57383 ("net_sched: Introduce skbmod action") Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Link: https://lore.kernel.org/r/20240403130908.93421-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-04-03 06:09:08 -07:00
memset(&opt, 0, sizeof(opt));
opt.index = d->tcf_index;
opt.refcnt = refcount_read(&d->tcf_refcnt) - ref;
net/sched: act_skbmod: prevent kernel-infoleak syzbot found that tcf_skbmod_dump() was copying four bytes from kernel stack to user space [1]. The issue here is that 'struct tc_skbmod' has a four bytes hole. We need to clear the structure before filling fields. [1] BUG: KMSAN: kernel-infoleak in instrument_copy_to_user include/linux/instrumented.h:114 [inline] BUG: KMSAN: kernel-infoleak in copy_to_user_iter lib/iov_iter.c:24 [inline] BUG: KMSAN: kernel-infoleak in iterate_ubuf include/linux/iov_iter.h:29 [inline] BUG: KMSAN: kernel-infoleak in iterate_and_advance2 include/linux/iov_iter.h:245 [inline] BUG: KMSAN: kernel-infoleak in iterate_and_advance include/linux/iov_iter.h:271 [inline] BUG: KMSAN: kernel-infoleak in _copy_to_iter+0x366/0x2520 lib/iov_iter.c:185 instrument_copy_to_user include/linux/instrumented.h:114 [inline] copy_to_user_iter lib/iov_iter.c:24 [inline] iterate_ubuf include/linux/iov_iter.h:29 [inline] iterate_and_advance2 include/linux/iov_iter.h:245 [inline] iterate_and_advance include/linux/iov_iter.h:271 [inline] _copy_to_iter+0x366/0x2520 lib/iov_iter.c:185 copy_to_iter include/linux/uio.h:196 [inline] simple_copy_to_iter net/core/datagram.c:532 [inline] __skb_datagram_iter+0x185/0x1000 net/core/datagram.c:420 skb_copy_datagram_iter+0x5c/0x200 net/core/datagram.c:546 skb_copy_datagram_msg include/linux/skbuff.h:4050 [inline] netlink_recvmsg+0x432/0x1610 net/netlink/af_netlink.c:1962 sock_recvmsg_nosec net/socket.c:1046 [inline] sock_recvmsg+0x2c4/0x340 net/socket.c:1068 __sys_recvfrom+0x35a/0x5f0 net/socket.c:2242 __do_sys_recvfrom net/socket.c:2260 [inline] __se_sys_recvfrom net/socket.c:2256 [inline] __x64_sys_recvfrom+0x126/0x1d0 net/socket.c:2256 do_syscall_64+0xd5/0x1f0 entry_SYSCALL_64_after_hwframe+0x6d/0x75 Uninit was stored to memory at: pskb_expand_head+0x30f/0x19d0 net/core/skbuff.c:2253 netlink_trim+0x2c2/0x330 net/netlink/af_netlink.c:1317 netlink_unicast+0x9f/0x1260 net/netlink/af_netlink.c:1351 nlmsg_unicast include/net/netlink.h:1144 [inline] nlmsg_notify+0x21d/0x2f0 net/netlink/af_netlink.c:2610 rtnetlink_send+0x73/0x90 net/core/rtnetlink.c:741 rtnetlink_maybe_send include/linux/rtnetlink.h:17 [inline] tcf_add_notify net/sched/act_api.c:2048 [inline] tcf_action_add net/sched/act_api.c:2071 [inline] tc_ctl_action+0x146e/0x19d0 net/sched/act_api.c:2119 rtnetlink_rcv_msg+0x1737/0x1900 net/core/rtnetlink.c:6595 netlink_rcv_skb+0x375/0x650 net/netlink/af_netlink.c:2559 rtnetlink_rcv+0x34/0x40 net/core/rtnetlink.c:6613 netlink_unicast_kernel net/netlink/af_netlink.c:1335 [inline] netlink_unicast+0xf4c/0x1260 net/netlink/af_netlink.c:1361 netlink_sendmsg+0x10df/0x11f0 net/netlink/af_netlink.c:1905 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x30f/0x380 net/socket.c:745 ____sys_sendmsg+0x877/0xb60 net/socket.c:2584 ___sys_sendmsg+0x28d/0x3c0 net/socket.c:2638 __sys_sendmsg net/socket.c:2667 [inline] __do_sys_sendmsg net/socket.c:2676 [inline] __se_sys_sendmsg net/socket.c:2674 [inline] __x64_sys_sendmsg+0x307/0x4a0 net/socket.c:2674 do_syscall_64+0xd5/0x1f0 entry_SYSCALL_64_after_hwframe+0x6d/0x75 Uninit was stored to memory at: __nla_put lib/nlattr.c:1041 [inline] nla_put+0x1c6/0x230 lib/nlattr.c:1099 tcf_skbmod_dump+0x23f/0xc20 net/sched/act_skbmod.c:256 tcf_action_dump_old net/sched/act_api.c:1191 [inline] tcf_action_dump_1+0x85e/0x970 net/sched/act_api.c:1227 tcf_action_dump+0x1fd/0x460 net/sched/act_api.c:1251 tca_get_fill+0x519/0x7a0 net/sched/act_api.c:1628 tcf_add_notify_msg net/sched/act_api.c:2023 [inline] tcf_add_notify net/sched/act_api.c:2042 [inline] tcf_action_add net/sched/act_api.c:2071 [inline] tc_ctl_action+0x1365/0x19d0 net/sched/act_api.c:2119 rtnetlink_rcv_msg+0x1737/0x1900 net/core/rtnetlink.c:6595 netlink_rcv_skb+0x375/0x650 net/netlink/af_netlink.c:2559 rtnetlink_rcv+0x34/0x40 net/core/rtnetlink.c:6613 netlink_unicast_kernel net/netlink/af_netlink.c:1335 [inline] netlink_unicast+0xf4c/0x1260 net/netlink/af_netlink.c:1361 netlink_sendmsg+0x10df/0x11f0 net/netlink/af_netlink.c:1905 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x30f/0x380 net/socket.c:745 ____sys_sendmsg+0x877/0xb60 net/socket.c:2584 ___sys_sendmsg+0x28d/0x3c0 net/socket.c:2638 __sys_sendmsg net/socket.c:2667 [inline] __do_sys_sendmsg net/socket.c:2676 [inline] __se_sys_sendmsg net/socket.c:2674 [inline] __x64_sys_sendmsg+0x307/0x4a0 net/socket.c:2674 do_syscall_64+0xd5/0x1f0 entry_SYSCALL_64_after_hwframe+0x6d/0x75 Local variable opt created at: tcf_skbmod_dump+0x9d/0xc20 net/sched/act_skbmod.c:244 tcf_action_dump_old net/sched/act_api.c:1191 [inline] tcf_action_dump_1+0x85e/0x970 net/sched/act_api.c:1227 Bytes 188-191 of 248 are uninitialized Memory access of size 248 starts at ffff888117697680 Data copied to user address 00007ffe56d855f0 Fixes: 86da71b57383 ("net_sched: Introduce skbmod action") Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Link: https://lore.kernel.org/r/20240403130908.93421-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-04-03 06:09:08 -07:00
opt.bindcnt = atomic_read(&d->tcf_bindcnt) - bind;
spin_lock_bh(&d->tcf_lock);
opt.action = d->tcf_action;
p = rcu_dereference_protected(d->skbmod_p,
lockdep_is_held(&d->tcf_lock));
opt.flags = p->flags;
if (nla_put(skb, TCA_SKBMOD_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
if ((p->flags & SKBMOD_F_DMAC) &&
nla_put(skb, TCA_SKBMOD_DMAC, ETH_ALEN, p->eth_dst))
goto nla_put_failure;
if ((p->flags & SKBMOD_F_SMAC) &&
nla_put(skb, TCA_SKBMOD_SMAC, ETH_ALEN, p->eth_src))
goto nla_put_failure;
if ((p->flags & SKBMOD_F_ETYPE) &&
nla_put_u16(skb, TCA_SKBMOD_ETYPE, ntohs(p->eth_type)))
goto nla_put_failure;
tcf_tm_dump(&t, &d->tcf_tm);
if (nla_put_64bit(skb, TCA_SKBMOD_TM, sizeof(t), &t, TCA_SKBMOD_PAD))
goto nla_put_failure;
spin_unlock_bh(&d->tcf_lock);
return skb->len;
nla_put_failure:
spin_unlock_bh(&d->tcf_lock);
nlmsg_trim(skb, b);
return -1;
}
static struct tc_action_ops act_skbmod_ops = {
.kind = "skbmod",
.id = TCA_ACT_SKBMOD,
.owner = THIS_MODULE,
.act = tcf_skbmod_act,
.dump = tcf_skbmod_dump,
.init = tcf_skbmod_init,
.cleanup = tcf_skbmod_cleanup,
.size = sizeof(struct tcf_skbmod),
};
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 06:09:41 -07:00
MODULE_ALIAS_NET_ACT("skbmod");
static __net_init int skbmod_init_net(struct net *net)
{
struct tc_action_net *tn = net_generic(net, act_skbmod_ops.net_id);
return tc_action_net_init(net, tn, &act_skbmod_ops);
}
static void __net_exit skbmod_exit_net(struct list_head *net_list)
{
tc_action_net_exit(net_list, act_skbmod_ops.net_id);
}
static struct pernet_operations skbmod_net_ops = {
.init = skbmod_init_net,
.exit_batch = skbmod_exit_net,
.id = &act_skbmod_ops.net_id,
.size = sizeof(struct tc_action_net),
};
MODULE_AUTHOR("Jamal Hadi Salim, <jhs@mojatatu.com>");
MODULE_DESCRIPTION("SKB data mod-ing");
MODULE_LICENSE("GPL");
static int __init skbmod_init_module(void)
{
return tcf_register_action(&act_skbmod_ops, &skbmod_net_ops);
}
static void __exit skbmod_cleanup_module(void)
{
tcf_unregister_action(&act_skbmod_ops, &skbmod_net_ops);
}
module_init(skbmod_init_module);
module_exit(skbmod_cleanup_module);