linux/net/sched/act_tunnel_key.c

840 lines
22 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Copyright (c) 2016, Amir Vadai <amir@vadai.me>
* Copyright (c) 2016, Mellanox Technologies. All rights reserved.
*/
#include <linux/module.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <net/geneve.h>
#include <net/vxlan.h>
#include <net/erspan.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/dst.h>
net/sched: act_tunnel_key: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.2 dst_port 3128 \ > nocsum id 1 pass index 90 # tc actions replace action tunnel_key \ > set src_ip 10.10.10.1 dst_ip 20.20.2 dst_port 3128 nocsum id 1 \ > goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action tunnel_key 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: tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.2.0 key_id 1 dst_port 3128 nocsum 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 800000002aba4067 P4D 800000002aba4067 PUD 795f9067 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:ffff9346bdb83be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9346bb795c00 RCX: 0000000000000002 RDX: 0000000000000000 RSI: ffff93466c881700 RDI: 0000000000000246 RBP: ffff9346bdb83c80 R08: ffff9346b3e1e0c8 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff9346b978f000 R13: ffff9346b978f008 R14: 0000000000000001 R15: ffff93466dceeb40 FS: 0000000000000000(0000) GS:ffff9346bdb80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007a6c2002 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: 55 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:ffffa48a8038feb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffffaa8184f0 RBX: 0000000000000003 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000003 RBP: 0000000000000003 R08: 0011251c6fcfac49 R09: ffff9346b995be00 R10: ffffa48a805e7ce8 R11: 00000000024c38dd 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_tunnel_key veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul snd_hda_codec_generic ghash_clmulni_intel mbcache snd_hda_intel jbd2 snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd glue_helper joydev snd_timer snd pcspkr virtio_balloon soundcore i2c_piix4 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 ttm net_failover virtio_console virtio_blk failover drm serio_raw crc32c_intel ata_piix virtio_pci floppy virtio_ring libata virtio dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_tunnel_key_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 22:00:13 +08:00
#include <net/pkt_cls.h>
#include <linux/tc_act/tc_tunnel_key.h>
#include <net/tc_act/tc_tunnel_key.h>
netns: make struct pernet_operations::id unsigned int Make struct pernet_operations::id unsigned. There are 2 reasons to do so: 1) This field is really an index into an zero based array and thus is unsigned entity. Using negative value is out-of-bound access by definition. 2) On x86_64 unsigned 32-bit data which are mixed with pointers via array indexing or offsets added or subtracted to pointers are preffered to signed 32-bit data. "int" being used as an array index needs to be sign-extended to 64-bit before being used. void f(long *p, int i) { g(p[i]); } roughly translates to movsx rsi, esi mov rdi, [rsi+...] call g MOVSX is 3 byte instruction which isn't necessary if the variable is unsigned because x86_64 is zero extending by default. Now, there is net_generic() function which, you guessed it right, uses "int" as an array index: static inline void *net_generic(const struct net *net, int id) { ... ptr = ng->ptr[id - 1]; ... } And this function is used a lot, so those sign extensions add up. Patch snipes ~1730 bytes on allyesconfig kernel (without all junk messing with code generation): add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730) Unfortunately some functions actually grow bigger. This is a semmingly random artefact of code generation with register allocator being used differently. gcc decides that some variable needs to live in new r8+ registers and every access now requires REX prefix. Or it is shifted into r12, so [r12+0] addressing mode has to be used which is longer than [r8] However, overall balance is in negative direction: add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730) function old new delta nfsd4_lock 3886 3959 +73 tipc_link_build_proto_msg 1096 1140 +44 mac80211_hwsim_new_radio 2776 2808 +32 tipc_mon_rcv 1032 1058 +26 svcauth_gss_legacy_init 1413 1429 +16 tipc_bcbase_select_primary 379 392 +13 nfsd4_exchange_id 1247 1260 +13 nfsd4_setclientid_confirm 782 793 +11 ... put_client_renew_locked 494 480 -14 ip_set_sockfn_get 730 716 -14 geneve_sock_add 829 813 -16 nfsd4_sequence_done 721 703 -18 nlmclnt_lookup_host 708 686 -22 nfsd4_lockt 1085 1063 -22 nfs_get_client 1077 1050 -27 tcf_bpf_init 1106 1076 -30 nfsd4_encode_fattr 5997 5930 -67 Total: Before=154856051, After=154854321, chg -0.00% Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-17 09:58:21 +08:00
static unsigned int tunnel_key_net_id;
static struct tc_action_ops act_tunnel_key_ops;
static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
struct tcf_tunnel_key *t = to_tunnel_key(a);
struct tcf_tunnel_key_params *params;
int action;
params = rcu_dereference_bh(t->params);
tcf_lastuse_update(&t->tcf_tm);
tcf_action_update_bstats(&t->common, skb);
net/sched: act_tunnel_key: fix NULL dereference when 'goto chain' is used the control action in the common member of struct tcf_tunnel_key must be a valid value, as it can contain the chain index when 'goto chain' is used. Ensure that the control action can be read as x->tcfa_action, when x is a pointer to struct tc_action and x->ops->type is TCA_ACT_TUNNEL_KEY, to prevent the following command: # tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \ > $tcflags dst_mac $h2mac action tunnel_key unset goto chain 1 from causing a NULL dereference when a matching packet is received: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 PGD 80000001097ac067 P4D 80000001097ac067 PUD 103b0a067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 3491 Comm: mausezahn Tainted: G E 4.18.0-rc2.auguri+ #421 Hardware name: Hewlett-Packard HP Z220 CMT Workstation/1790, BIOS K51 v01.58 02/07/2013 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:ffff95145ea03c40 EFLAGS: 00010246 RAX: 0000000020000001 RBX: ffff9514499e5800 RCX: 0000000000000001 RDX: 0000000000000000 RSI: 0000000000000002 RDI: 0000000000000000 RBP: ffff95145ea03e60 R08: 0000000000000000 R09: ffff95145ea03c9c R10: ffff95145ea03c78 R11: 0000000000000008 R12: ffff951456a69800 R13: ffff951456a69808 R14: 0000000000000001 R15: ffff95144965ee40 FS: 00007fd67ee11740(0000) GS:ffff95145ea00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 00000001038a2006 CR4: 00000000001606f0 Call Trace: <IRQ> fl_classify+0x1ad/0x1c0 [cls_flower] ? __update_load_avg_se.isra.47+0x1ca/0x1d0 ? __update_load_avg_se.isra.47+0x1ca/0x1d0 ? update_load_avg+0x665/0x690 ? update_load_avg+0x665/0x690 ? kmem_cache_alloc+0x38/0x1c0 tcf_classify+0x89/0x140 __netif_receive_skb_core+0x5ea/0xb70 ? enqueue_entity+0xd0/0x270 ? process_backlog+0x97/0x150 process_backlog+0x97/0x150 net_rx_action+0x14b/0x3e0 __do_softirq+0xde/0x2b4 do_softirq_own_stack+0x2a/0x40 </IRQ> do_softirq.part.18+0x49/0x50 __local_bh_enable_ip+0x49/0x50 __dev_queue_xmit+0x4ab/0x8a0 ? wait_woken+0x80/0x80 ? packet_sendmsg+0x38f/0x810 ? __dev_queue_xmit+0x8a0/0x8a0 packet_sendmsg+0x38f/0x810 sock_sendmsg+0x36/0x40 __sys_sendto+0x10e/0x140 ? do_vfs_ioctl+0xa4/0x630 ? syscall_trace_enter+0x1df/0x2e0 ? __audit_syscall_exit+0x22a/0x290 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x5b/0x180 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7fd67e18dc93 Code: 48 8b 0d 18 83 20 00 f7 d8 64 89 01 48 83 c8 ff c3 66 0f 1f 44 00 00 83 3d 59 c7 20 00 00 75 13 49 89 ca b8 2c 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 34 c3 48 83 ec 08 e8 2b f7 ff ff 48 89 04 24 RSP: 002b:00007ffe0189b748 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 00000000020ca010 RCX: 00007fd67e18dc93 RDX: 0000000000000062 RSI: 00000000020ca322 RDI: 0000000000000003 RBP: 00007ffe0189b780 R08: 00007ffe0189b760 R09: 0000000000000014 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000062 R13: 00000000020ca322 R14: 00007ffe0189b760 R15: 0000000000000003 Modules linked in: act_tunnel_key act_gact cls_flower sch_ingress vrf veth act_csum(E) xt_CHECKSUM iptable_mangle ipt_MASQUERADE iptable_nat nf_nat_ipv4 nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack ipt_REJECT nf_reject_ipv4 tun bridge stp llc ebtable_filter ebtables ip6table_filter ip6_tables iptable_filter intel_rapl snd_hda_codec_hdmi x86_pkg_temp_thermal intel_powerclamp snd_hda_codec_realtek coretemp snd_hda_codec_generic kvm_intel kvm irqbypass snd_hda_intel crct10dif_pclmul crc32_pclmul hp_wmi ghash_clmulni_intel pcbc snd_hda_codec aesni_intel sparse_keymap rfkill snd_hda_core snd_hwdep snd_seq crypto_simd iTCO_wdt gpio_ich iTCO_vendor_support wmi_bmof cryptd mei_wdt glue_helper snd_seq_device snd_pcm pcspkr snd_timer snd i2c_i801 lpc_ich sg soundcore wmi mei_me mei ie31200_edac nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c sd_mod sr_mod cdrom i915 video i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ahci crc32c_intel libahci serio_raw sfc libata mtd drm ixgbe mdio i2c_core e1000e dca CR2: 0000000000000000 ---[ end trace 1ab8b5b5d4639dfc ]--- 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:ffff95145ea03c40 EFLAGS: 00010246 RAX: 0000000020000001 RBX: ffff9514499e5800 RCX: 0000000000000001 RDX: 0000000000000000 RSI: 0000000000000002 RDI: 0000000000000000 RBP: ffff95145ea03e60 R08: 0000000000000000 R09: ffff95145ea03c9c R10: ffff95145ea03c78 R11: 0000000000000008 R12: ffff951456a69800 R13: ffff951456a69808 R14: 0000000000000001 R15: ffff95144965ee40 FS: 00007fd67ee11740(0000) GS:ffff95145ea00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 00000001038a2006 CR4: 00000000001606f0 Kernel panic - not syncing: Fatal exception in interrupt Kernel Offset: 0x11400000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]--- Fixes: d0f6dd8a914f ("net/sched: Introduce act_tunnel_key") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-07 03:01:06 +08:00
action = READ_ONCE(t->tcf_action);
switch (params->tcft_action) {
case TCA_TUNNEL_KEY_ACT_RELEASE:
skb_dst_drop(skb);
break;
case TCA_TUNNEL_KEY_ACT_SET:
skb_dst_drop(skb);
skb_dst_set(skb, dst_clone(&params->tcft_enc_metadata->dst));
break;
default:
WARN_ONCE(1, "Bad tunnel_key action %d.\n",
params->tcft_action);
break;
}
return action;
}
static const struct nla_policy
enc_opts_policy[TCA_TUNNEL_KEY_ENC_OPTS_MAX + 1] = {
[TCA_TUNNEL_KEY_ENC_OPTS_UNSPEC] = {
.strict_start_type = TCA_TUNNEL_KEY_ENC_OPTS_VXLAN },
[TCA_TUNNEL_KEY_ENC_OPTS_GENEVE] = { .type = NLA_NESTED },
[TCA_TUNNEL_KEY_ENC_OPTS_VXLAN] = { .type = NLA_NESTED },
[TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN] = { .type = NLA_NESTED },
};
static const struct nla_policy
geneve_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX + 1] = {
[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS] = { .type = NLA_U16 },
[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE] = { .type = NLA_U8 },
[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA] = { .type = NLA_BINARY,
.len = 128 },
};
static const struct nla_policy
vxlan_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX + 1] = {
[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP] = { .type = NLA_U32 },
};
static const struct nla_policy
erspan_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX + 1] = {
[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER] = { .type = NLA_U8 },
[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX] = { .type = NLA_U32 },
[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR] = { .type = NLA_U8 },
[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID] = { .type = NLA_U8 },
};
static int
tunnel_key_copy_geneve_opt(const struct nlattr *nla, void *dst, int dst_len,
struct netlink_ext_ack *extack)
{
struct nlattr *tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX + 1];
int err, data_len, opt_len;
u8 *data;
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 20:07:28 +08:00
err = nla_parse_nested_deprecated(tb,
TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX,
nla, geneve_opt_policy, extack);
if (err < 0)
return err;
if (!tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS] ||
!tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE] ||
!tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]) {
NL_SET_ERR_MSG(extack, "Missing tunnel key geneve option class, type or data");
return -EINVAL;
}
data = nla_data(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]);
data_len = nla_len(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]);
if (data_len < 4) {
NL_SET_ERR_MSG(extack, "Tunnel key geneve option data is less than 4 bytes long");
return -ERANGE;
}
if (data_len % 4) {
NL_SET_ERR_MSG(extack, "Tunnel key geneve option data is not a multiple of 4 bytes long");
return -ERANGE;
}
opt_len = sizeof(struct geneve_opt) + data_len;
if (dst) {
struct geneve_opt *opt = dst;
WARN_ON(dst_len < opt_len);
opt->opt_class =
nla_get_be16(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS]);
opt->type = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE]);
opt->length = data_len / 4; /* length is in units of 4 bytes */
opt->r1 = 0;
opt->r2 = 0;
opt->r3 = 0;
memcpy(opt + 1, data, data_len);
}
return opt_len;
}
static int
tunnel_key_copy_vxlan_opt(const struct nlattr *nla, void *dst, int dst_len,
struct netlink_ext_ack *extack)
{
struct nlattr *tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX + 1];
int err;
err = nla_parse_nested(tb, TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX, nla,
vxlan_opt_policy, extack);
if (err < 0)
return err;
if (!tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP]) {
NL_SET_ERR_MSG(extack, "Missing tunnel key vxlan option gbp");
return -EINVAL;
}
if (dst) {
struct vxlan_metadata *md = dst;
md->gbp = nla_get_u32(tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP]);
}
return sizeof(struct vxlan_metadata);
}
static int
tunnel_key_copy_erspan_opt(const struct nlattr *nla, void *dst, int dst_len,
struct netlink_ext_ack *extack)
{
struct nlattr *tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX + 1];
int err;
u8 ver;
err = nla_parse_nested(tb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX, nla,
erspan_opt_policy, extack);
if (err < 0)
return err;
if (!tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER]) {
NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option ver");
return -EINVAL;
}
ver = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER]);
if (ver == 1) {
if (!tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX]) {
NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option index");
return -EINVAL;
}
} else if (ver == 2) {
if (!tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR] ||
!tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID]) {
NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option dir or hwid");
return -EINVAL;
}
} else {
NL_SET_ERR_MSG(extack, "Tunnel key erspan option ver is incorrect");
return -EINVAL;
}
if (dst) {
struct erspan_metadata *md = dst;
md->version = ver;
if (ver == 1) {
nla = tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX];
md->u.index = nla_get_be32(nla);
} else {
nla = tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR];
md->u.md2.dir = nla_get_u8(nla);
nla = tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID];
set_hwid(&md->u.md2, nla_get_u8(nla));
}
}
return sizeof(struct erspan_metadata);
}
static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst,
int dst_len, struct netlink_ext_ack *extack)
{
int err, rem, opt_len, len = nla_len(nla), opts_len = 0, type = 0;
const struct nlattr *attr, *head = nla_data(nla);
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 20:07:28 +08:00
err = nla_validate_deprecated(head, len, TCA_TUNNEL_KEY_ENC_OPTS_MAX,
enc_opts_policy, extack);
if (err)
return err;
nla_for_each_attr(attr, head, len, rem) {
switch (nla_type(attr)) {
case TCA_TUNNEL_KEY_ENC_OPTS_GENEVE:
if (type && type != TUNNEL_GENEVE_OPT) {
NL_SET_ERR_MSG(extack, "Duplicate type for geneve options");
return -EINVAL;
}
opt_len = tunnel_key_copy_geneve_opt(attr, dst,
dst_len, extack);
if (opt_len < 0)
return opt_len;
opts_len += opt_len;
if (opts_len > IP_TUNNEL_OPTS_MAX) {
NL_SET_ERR_MSG(extack, "Tunnel options exceeds max size");
return -EINVAL;
}
if (dst) {
dst_len -= opt_len;
dst += opt_len;
}
type = TUNNEL_GENEVE_OPT;
break;
case TCA_TUNNEL_KEY_ENC_OPTS_VXLAN:
if (type) {
NL_SET_ERR_MSG(extack, "Duplicate type for vxlan options");
return -EINVAL;
}
opt_len = tunnel_key_copy_vxlan_opt(attr, dst,
dst_len, extack);
if (opt_len < 0)
return opt_len;
opts_len += opt_len;
type = TUNNEL_VXLAN_OPT;
break;
case TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN:
if (type) {
NL_SET_ERR_MSG(extack, "Duplicate type for erspan options");
return -EINVAL;
}
opt_len = tunnel_key_copy_erspan_opt(attr, dst,
dst_len, extack);
if (opt_len < 0)
return opt_len;
opts_len += opt_len;
type = TUNNEL_ERSPAN_OPT;
break;
}
}
if (!opts_len) {
NL_SET_ERR_MSG(extack, "Empty list of tunnel options");
return -EINVAL;
}
if (rem > 0) {
NL_SET_ERR_MSG(extack, "Trailing data after parsing tunnel key options attributes");
return -EINVAL;
}
return opts_len;
}
static int tunnel_key_get_opts_len(struct nlattr *nla,
struct netlink_ext_ack *extack)
{
return tunnel_key_copy_opts(nla, NULL, 0, extack);
}
static int tunnel_key_opts_set(struct nlattr *nla, struct ip_tunnel_info *info,
int opts_len, struct netlink_ext_ack *extack)
{
info->options_len = opts_len;
switch (nla_type(nla_data(nla))) {
case TCA_TUNNEL_KEY_ENC_OPTS_GENEVE:
#if IS_ENABLED(CONFIG_INET)
info->key.tun_flags |= TUNNEL_GENEVE_OPT;
return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info),
opts_len, extack);
#else
return -EAFNOSUPPORT;
#endif
case TCA_TUNNEL_KEY_ENC_OPTS_VXLAN:
#if IS_ENABLED(CONFIG_INET)
info->key.tun_flags |= TUNNEL_VXLAN_OPT;
return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info),
opts_len, extack);
#else
return -EAFNOSUPPORT;
#endif
case TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN:
#if IS_ENABLED(CONFIG_INET)
info->key.tun_flags |= TUNNEL_ERSPAN_OPT;
return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info),
opts_len, extack);
#else
return -EAFNOSUPPORT;
#endif
default:
NL_SET_ERR_MSG(extack, "Cannot set tunnel options for unknown tunnel type");
return -EINVAL;
}
}
static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = {
[TCA_TUNNEL_KEY_PARMS] = { .len = sizeof(struct tc_tunnel_key) },
[TCA_TUNNEL_KEY_ENC_IPV4_SRC] = { .type = NLA_U32 },
[TCA_TUNNEL_KEY_ENC_IPV4_DST] = { .type = NLA_U32 },
[TCA_TUNNEL_KEY_ENC_IPV6_SRC] = { .len = sizeof(struct in6_addr) },
[TCA_TUNNEL_KEY_ENC_IPV6_DST] = { .len = sizeof(struct in6_addr) },
[TCA_TUNNEL_KEY_ENC_KEY_ID] = { .type = NLA_U32 },
[TCA_TUNNEL_KEY_ENC_DST_PORT] = {.type = NLA_U16},
[TCA_TUNNEL_KEY_NO_CSUM] = { .type = NLA_U8 },
[TCA_TUNNEL_KEY_ENC_OPTS] = { .type = NLA_NESTED },
[TCA_TUNNEL_KEY_ENC_TOS] = { .type = NLA_U8 },
[TCA_TUNNEL_KEY_ENC_TTL] = { .type = NLA_U8 },
};
net/sched: act_tunnel_key: fix memory leak in case of action replace running the following TDC test cases: 7afc - Replace tunnel_key set action with all parameters 364d - Replace tunnel_key set action with all parameters and cookie it's possible to trigger kmemleak warnings like: unreferenced object 0xffff94797127ab40 (size 192): comm "tc", pid 3248, jiffies 4300565293 (age 1006.862s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 c0 93 f9 8a ff ff ff ff ................ 41 84 ee 89 ff ff ff ff 00 00 00 00 00 00 00 00 A............... backtrace: [<000000001e85b61c>] tunnel_key_init+0x31d/0x820 [act_tunnel_key] [<000000007f3f6ee7>] tcf_action_init_1+0x384/0x4c0 [<00000000e89e3ded>] tcf_action_init+0x12b/0x1a0 [<00000000c1c8c0f8>] tcf_action_add+0x73/0x170 [<0000000095a9fc28>] tc_ctl_action+0x122/0x160 [<000000004bebeac5>] rtnetlink_rcv_msg+0x263/0x2d0 [<000000009fd862dd>] netlink_rcv_skb+0x4a/0x110 [<00000000b55199e7>] netlink_unicast+0x1a0/0x250 [<000000004996cd21>] netlink_sendmsg+0x2c1/0x3c0 [<000000004d6a94b4>] sock_sendmsg+0x36/0x40 [<000000005d9f0208>] ___sys_sendmsg+0x280/0x2f0 [<00000000dec19023>] __sys_sendmsg+0x5e/0xa0 [<000000004b82ac81>] do_syscall_64+0x5b/0x180 [<00000000a0f1209a>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [<000000002926b2ab>] 0xffffffffffffffff when the tunnel_key action is replaced, the kernel forgets to release the dst metadata: ensure they are released by tunnel_key_init(), the same way it's done in tunnel_key_release(). Fixes: d0f6dd8a914f4 ("net/sched: Introduce act_tunnel_key") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-11 03:21:02 +08:00
static void tunnel_key_release_params(struct tcf_tunnel_key_params *p)
{
if (!p)
return;
if (p->tcft_action == TCA_TUNNEL_KEY_ACT_SET)
net/sched: act_tunnel_key: fix memory leak in case of action replace running the following TDC test cases: 7afc - Replace tunnel_key set action with all parameters 364d - Replace tunnel_key set action with all parameters and cookie it's possible to trigger kmemleak warnings like: unreferenced object 0xffff94797127ab40 (size 192): comm "tc", pid 3248, jiffies 4300565293 (age 1006.862s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 c0 93 f9 8a ff ff ff ff ................ 41 84 ee 89 ff ff ff ff 00 00 00 00 00 00 00 00 A............... backtrace: [<000000001e85b61c>] tunnel_key_init+0x31d/0x820 [act_tunnel_key] [<000000007f3f6ee7>] tcf_action_init_1+0x384/0x4c0 [<00000000e89e3ded>] tcf_action_init+0x12b/0x1a0 [<00000000c1c8c0f8>] tcf_action_add+0x73/0x170 [<0000000095a9fc28>] tc_ctl_action+0x122/0x160 [<000000004bebeac5>] rtnetlink_rcv_msg+0x263/0x2d0 [<000000009fd862dd>] netlink_rcv_skb+0x4a/0x110 [<00000000b55199e7>] netlink_unicast+0x1a0/0x250 [<000000004996cd21>] netlink_sendmsg+0x2c1/0x3c0 [<000000004d6a94b4>] sock_sendmsg+0x36/0x40 [<000000005d9f0208>] ___sys_sendmsg+0x280/0x2f0 [<00000000dec19023>] __sys_sendmsg+0x5e/0xa0 [<000000004b82ac81>] do_syscall_64+0x5b/0x180 [<00000000a0f1209a>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [<000000002926b2ab>] 0xffffffffffffffff when the tunnel_key action is replaced, the kernel forgets to release the dst metadata: ensure they are released by tunnel_key_init(), the same way it's done in tunnel_key_release(). Fixes: d0f6dd8a914f4 ("net/sched: Introduce act_tunnel_key") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-11 03:21:02 +08:00
dst_release(&p->tcft_enc_metadata->dst);
net/sched: act_tunnel_key: fix memory leak in case of action replace running the following TDC test cases: 7afc - Replace tunnel_key set action with all parameters 364d - Replace tunnel_key set action with all parameters and cookie it's possible to trigger kmemleak warnings like: unreferenced object 0xffff94797127ab40 (size 192): comm "tc", pid 3248, jiffies 4300565293 (age 1006.862s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 c0 93 f9 8a ff ff ff ff ................ 41 84 ee 89 ff ff ff ff 00 00 00 00 00 00 00 00 A............... backtrace: [<000000001e85b61c>] tunnel_key_init+0x31d/0x820 [act_tunnel_key] [<000000007f3f6ee7>] tcf_action_init_1+0x384/0x4c0 [<00000000e89e3ded>] tcf_action_init+0x12b/0x1a0 [<00000000c1c8c0f8>] tcf_action_add+0x73/0x170 [<0000000095a9fc28>] tc_ctl_action+0x122/0x160 [<000000004bebeac5>] rtnetlink_rcv_msg+0x263/0x2d0 [<000000009fd862dd>] netlink_rcv_skb+0x4a/0x110 [<00000000b55199e7>] netlink_unicast+0x1a0/0x250 [<000000004996cd21>] netlink_sendmsg+0x2c1/0x3c0 [<000000004d6a94b4>] sock_sendmsg+0x36/0x40 [<000000005d9f0208>] ___sys_sendmsg+0x280/0x2f0 [<00000000dec19023>] __sys_sendmsg+0x5e/0xa0 [<000000004b82ac81>] do_syscall_64+0x5b/0x180 [<00000000a0f1209a>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [<000000002926b2ab>] 0xffffffffffffffff when the tunnel_key action is replaced, the kernel forgets to release the dst metadata: ensure they are released by tunnel_key_init(), the same way it's done in tunnel_key_release(). Fixes: d0f6dd8a914f4 ("net/sched: Introduce act_tunnel_key") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-11 03:21:02 +08:00
kfree_rcu(p, rcu);
}
static int tunnel_key_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
int ovr, int bind, bool rtnl_held,
struct tcf_proto *tp, u32 act_flags,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
struct nlattr *tb[TCA_TUNNEL_KEY_MAX + 1];
struct tcf_tunnel_key_params *params_new;
struct metadata_dst *metadata = NULL;
net/sched: act_tunnel_key: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.2 dst_port 3128 \ > nocsum id 1 pass index 90 # tc actions replace action tunnel_key \ > set src_ip 10.10.10.1 dst_ip 20.20.2 dst_port 3128 nocsum id 1 \ > goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action tunnel_key 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: tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.2.0 key_id 1 dst_port 3128 nocsum 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 800000002aba4067 P4D 800000002aba4067 PUD 795f9067 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:ffff9346bdb83be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9346bb795c00 RCX: 0000000000000002 RDX: 0000000000000000 RSI: ffff93466c881700 RDI: 0000000000000246 RBP: ffff9346bdb83c80 R08: ffff9346b3e1e0c8 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff9346b978f000 R13: ffff9346b978f008 R14: 0000000000000001 R15: ffff93466dceeb40 FS: 0000000000000000(0000) GS:ffff9346bdb80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007a6c2002 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: 55 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:ffffa48a8038feb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffffaa8184f0 RBX: 0000000000000003 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000003 RBP: 0000000000000003 R08: 0011251c6fcfac49 R09: ffff9346b995be00 R10: ffffa48a805e7ce8 R11: 00000000024c38dd 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_tunnel_key veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul snd_hda_codec_generic ghash_clmulni_intel mbcache snd_hda_intel jbd2 snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd glue_helper joydev snd_timer snd pcspkr virtio_balloon soundcore i2c_piix4 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 ttm net_failover virtio_console virtio_blk failover drm serio_raw crc32c_intel ata_piix virtio_pci floppy virtio_ring libata virtio dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_tunnel_key_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 22:00:13 +08:00
struct tcf_chain *goto_ch = NULL;
struct tc_tunnel_key *parm;
struct tcf_tunnel_key *t;
bool exists = false;
__be16 dst_port = 0;
__be64 key_id = 0;
int opts_len = 0;
__be16 flags = 0;
u8 tos, ttl;
int ret = 0;
u32 index;
int err;
if (!nla) {
NL_SET_ERR_MSG(extack, "Tunnel requires attributes to be passed");
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 20:07:28 +08:00
err = nla_parse_nested_deprecated(tb, TCA_TUNNEL_KEY_MAX, nla,
tunnel_key_policy, extack);
if (err < 0) {
NL_SET_ERR_MSG(extack, "Failed to parse nested tunnel key attributes");
return err;
}
if (!tb[TCA_TUNNEL_KEY_PARMS]) {
NL_SET_ERR_MSG(extack, "Missing tunnel key parameters");
return -EINVAL;
}
parm = nla_data(tb[TCA_TUNNEL_KEY_PARMS]);
index = parm->index;
err = tcf_idr_check_alloc(tn, &index, a, bind);
if (err < 0)
return err;
exists = err;
if (exists && bind)
return 0;
switch (parm->t_action) {
case TCA_TUNNEL_KEY_ACT_RELEASE:
break;
case TCA_TUNNEL_KEY_ACT_SET:
if (tb[TCA_TUNNEL_KEY_ENC_KEY_ID]) {
__be32 key32;
key32 = nla_get_be32(tb[TCA_TUNNEL_KEY_ENC_KEY_ID]);
key_id = key32_to_tunnel_id(key32);
flags = TUNNEL_KEY;
}
flags |= TUNNEL_CSUM;
if (tb[TCA_TUNNEL_KEY_NO_CSUM] &&
nla_get_u8(tb[TCA_TUNNEL_KEY_NO_CSUM]))
flags &= ~TUNNEL_CSUM;
if (tb[TCA_TUNNEL_KEY_ENC_DST_PORT])
dst_port = nla_get_be16(tb[TCA_TUNNEL_KEY_ENC_DST_PORT]);
if (tb[TCA_TUNNEL_KEY_ENC_OPTS]) {
opts_len = tunnel_key_get_opts_len(tb[TCA_TUNNEL_KEY_ENC_OPTS],
extack);
if (opts_len < 0) {
ret = opts_len;
goto err_out;
}
}
tos = 0;
if (tb[TCA_TUNNEL_KEY_ENC_TOS])
tos = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_TOS]);
ttl = 0;
if (tb[TCA_TUNNEL_KEY_ENC_TTL])
ttl = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_TTL]);
if (tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC] &&
tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]) {
__be32 saddr;
__be32 daddr;
saddr = nla_get_in_addr(tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC]);
daddr = nla_get_in_addr(tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]);
metadata = __ip_tun_set_dst(saddr, daddr, tos, ttl,
dst_port, flags,
key_id, opts_len);
} else if (tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC] &&
tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]) {
struct in6_addr saddr;
struct in6_addr daddr;
saddr = nla_get_in6_addr(tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC]);
daddr = nla_get_in6_addr(tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]);
metadata = __ipv6_tun_set_dst(&saddr, &daddr, tos, ttl, dst_port,
0, flags,
key_id, 0);
} else {
NL_SET_ERR_MSG(extack, "Missing either ipv4 or ipv6 src and dst");
ret = -EINVAL;
goto err_out;
}
if (!metadata) {
NL_SET_ERR_MSG(extack, "Cannot allocate tunnel metadata dst");
ret = -ENOMEM;
goto err_out;
}
#ifdef CONFIG_DST_CACHE
ret = dst_cache_init(&metadata->u.tun_info.dst_cache, GFP_KERNEL);
if (ret)
goto release_tun_meta;
#endif
if (opts_len) {
ret = tunnel_key_opts_set(tb[TCA_TUNNEL_KEY_ENC_OPTS],
&metadata->u.tun_info,
opts_len, extack);
if (ret < 0)
goto release_tun_meta;
}
metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX;
break;
default:
NL_SET_ERR_MSG(extack, "Unknown tunnel key action");
net sched actions: return explicit error when tunnel_key mode is not specified If set/unset mode of the tunnel_key action is not provided, ->init() still returns 0, and the caller proceeds with bogus 'struct tc_action *' object, this results in crash: % tc actions add action tunnel_key src_ip 1.1.1.1 dst_ip 2.2.2.1 id 7 index 1 [ 35.805515] general protection fault: 0000 [#1] SMP PTI [ 35.806161] Modules linked in: act_tunnel_key kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc aesni_intel aes_x86_64 crypto_simd glue_helper cryptd serio_raw [ 35.808233] CPU: 1 PID: 428 Comm: tc Not tainted 4.16.0-rc4+ #286 [ 35.808929] RIP: 0010:tcf_action_init+0x90/0x190 [ 35.809457] RSP: 0018:ffffb8edc068b9a0 EFLAGS: 00010206 [ 35.810053] RAX: 1320c000000a0003 RBX: 0000000000000001 RCX: 0000000000000000 [ 35.810866] RDX: 0000000000000070 RSI: 0000000000007965 RDI: ffffb8edc068b910 [ 35.811660] RBP: ffffb8edc068b9d0 R08: 0000000000000000 R09: ffffb8edc068b808 [ 35.812463] R10: ffffffffc02bf040 R11: 0000000000000040 R12: ffffb8edc068bb38 [ 35.813235] R13: 0000000000000000 R14: 0000000000000000 R15: ffffb8edc068b910 [ 35.814006] FS: 00007f3d0d8556c0(0000) GS:ffff91d1dbc40000(0000) knlGS:0000000000000000 [ 35.814881] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 35.815540] CR2: 000000000043f720 CR3: 0000000019248001 CR4: 00000000001606a0 [ 35.816457] Call Trace: [ 35.817158] tc_ctl_action+0x11a/0x220 [ 35.817795] rtnetlink_rcv_msg+0x23d/0x2e0 [ 35.818457] ? __slab_alloc+0x1c/0x30 [ 35.819079] ? __kmalloc_node_track_caller+0xb1/0x2b0 [ 35.819544] ? rtnl_calcit.isra.30+0xe0/0xe0 [ 35.820231] netlink_rcv_skb+0xce/0x100 [ 35.820744] netlink_unicast+0x164/0x220 [ 35.821500] netlink_sendmsg+0x293/0x370 [ 35.822040] sock_sendmsg+0x30/0x40 [ 35.822508] ___sys_sendmsg+0x2c5/0x2e0 [ 35.823149] ? pagecache_get_page+0x27/0x220 [ 35.823714] ? filemap_fault+0xa2/0x640 [ 35.824423] ? page_add_file_rmap+0x108/0x200 [ 35.825065] ? alloc_set_pte+0x2aa/0x530 [ 35.825585] ? finish_fault+0x4e/0x70 [ 35.826140] ? __handle_mm_fault+0xbc1/0x10d0 [ 35.826723] ? __sys_sendmsg+0x41/0x70 [ 35.827230] __sys_sendmsg+0x41/0x70 [ 35.827710] do_syscall_64+0x68/0x120 [ 35.828195] entry_SYSCALL_64_after_hwframe+0x3d/0xa2 [ 35.828859] RIP: 0033:0x7f3d0ca4da67 [ 35.829331] RSP: 002b:00007ffc9f284338 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 35.830304] RAX: ffffffffffffffda RBX: 00007ffc9f284460 RCX: 00007f3d0ca4da67 [ 35.831247] RDX: 0000000000000000 RSI: 00007ffc9f2843b0 RDI: 0000000000000003 [ 35.832167] RBP: 000000005aa6a7a9 R08: 0000000000000001 R09: 0000000000000000 [ 35.833075] R10: 00000000000005f1 R11: 0000000000000246 R12: 0000000000000000 [ 35.833997] R13: 00007ffc9f2884c0 R14: 0000000000000001 R15: 0000000000674640 [ 35.834923] Code: 24 30 bb 01 00 00 00 45 31 f6 eb 5e 8b 50 08 83 c2 07 83 e2 fc 83 c2 70 49 8b 07 48 8b 40 70 48 85 c0 74 10 48 89 14 24 4c 89 ff <ff> d0 48 8b 14 24 48 01 c2 49 01 d6 45 85 ed 74 05 41 83 47 2c [ 35.837442] RIP: tcf_action_init+0x90/0x190 RSP: ffffb8edc068b9a0 [ 35.838291] ---[ end trace a095c06ee4b97a26 ]--- Fixes: d0f6dd8a914f ("net/sched: Introduce act_tunnel_key") Signed-off-by: Roman Mashak <mrv@mojatatu.com> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-13 04:20:58 +08:00
ret = -EINVAL;
goto err_out;
}
if (!exists) {
ret = tcf_idr_create_from_flags(tn, index, est, a,
&act_tunnel_key_ops, bind,
act_flags);
if (ret) {
NL_SET_ERR_MSG(extack, "Cannot create TC IDR");
goto release_tun_meta;
}
ret = ACT_P_CREATED;
} else if (!ovr) {
NL_SET_ERR_MSG(extack, "TC IDR already exists");
net/sched: fix memory leak in act_tunnel_key_init() If users try to install act_tunnel_key 'set' rules with duplicate values of 'index', the tunnel metadata are allocated, but never released. Then, kmemleak complains as follows: # tc a a a tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 index 111 # echo clear > /sys/kernel/debug/kmemleak # tc a a a tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 index 111 Error: TC IDR already exists. We have an error talking to the kernel # echo scan > /sys/kernel/debug/kmemleak # cat /sys/kernel/debug/kmemleak unreferenced object 0xffff8800574e6c80 (size 256): comm "tc", pid 5617, jiffies 4298118009 (age 57.990s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 1c e8 b0 ff ff ff ff ................ 81 24 c2 ad ff ff ff ff 00 00 00 00 00 00 00 00 .$.............. backtrace: [<00000000b7afbf4e>] tunnel_key_init+0x8a5/0x1800 [act_tunnel_key] [<000000007d98fccd>] tcf_action_init_1+0x698/0xac0 [<0000000099b8f7cc>] tcf_action_init+0x15c/0x590 [<00000000dc60eebe>] tc_ctl_action+0x336/0x5c2 [<000000002f5a2f7d>] rtnetlink_rcv_msg+0x357/0x8e0 [<000000000bfe7575>] netlink_rcv_skb+0x124/0x350 [<00000000edab656f>] netlink_unicast+0x40f/0x5d0 [<00000000b322cdcb>] netlink_sendmsg+0x6e8/0xba0 [<0000000063d9d490>] sock_sendmsg+0xb3/0xf0 [<00000000f0d3315a>] ___sys_sendmsg+0x654/0x960 [<00000000c06cbd42>] __sys_sendmsg+0xd3/0x170 [<00000000ce72e4b0>] do_syscall_64+0xa5/0x470 [<000000005caa2d97>] entry_SYSCALL_64_after_hwframe+0x49/0xbe [<00000000fac1b476>] 0xffffffffffffffff This problem theoretically happens also in case users attempt to setup a geneve rule having wrong configuration data, or when the kernel fails to allocate 'params_new'. Ensure that tunnel_key_init() releases the tunnel metadata also in the above conditions. Addresses-Coverity-ID: 1373974 ("Resource leak") Fixes: d0f6dd8a914f4 ("net/sched: Introduce act_tunnel_key") Fixes: 0ed5269f9e41f ("net/sched: add tunnel option support to act_tunnel_key") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-09-05 01:00:19 +08:00
ret = -EEXIST;
goto release_tun_meta;
}
net/sched: act_tunnel_key: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.2 dst_port 3128 \ > nocsum id 1 pass index 90 # tc actions replace action tunnel_key \ > set src_ip 10.10.10.1 dst_ip 20.20.2 dst_port 3128 nocsum id 1 \ > goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action tunnel_key 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: tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.2.0 key_id 1 dst_port 3128 nocsum 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 800000002aba4067 P4D 800000002aba4067 PUD 795f9067 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:ffff9346bdb83be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9346bb795c00 RCX: 0000000000000002 RDX: 0000000000000000 RSI: ffff93466c881700 RDI: 0000000000000246 RBP: ffff9346bdb83c80 R08: ffff9346b3e1e0c8 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff9346b978f000 R13: ffff9346b978f008 R14: 0000000000000001 R15: ffff93466dceeb40 FS: 0000000000000000(0000) GS:ffff9346bdb80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007a6c2002 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: 55 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:ffffa48a8038feb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffffaa8184f0 RBX: 0000000000000003 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000003 RBP: 0000000000000003 R08: 0011251c6fcfac49 R09: ffff9346b995be00 R10: ffffa48a805e7ce8 R11: 00000000024c38dd 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_tunnel_key veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul snd_hda_codec_generic ghash_clmulni_intel mbcache snd_hda_intel jbd2 snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd glue_helper joydev snd_timer snd pcspkr virtio_balloon soundcore i2c_piix4 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 ttm net_failover virtio_console virtio_blk failover drm serio_raw crc32c_intel ata_piix virtio_pci floppy virtio_ring libata virtio dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_tunnel_key_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 22:00:13 +08:00
err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
if (err < 0) {
ret = err;
exists = true;
goto release_tun_meta;
}
t = to_tunnel_key(*a);
params_new = kzalloc(sizeof(*params_new), GFP_KERNEL);
if (unlikely(!params_new)) {
NL_SET_ERR_MSG(extack, "Cannot allocate tunnel key parameters");
net/sched: fix memory leak in act_tunnel_key_init() If users try to install act_tunnel_key 'set' rules with duplicate values of 'index', the tunnel metadata are allocated, but never released. Then, kmemleak complains as follows: # tc a a a tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 index 111 # echo clear > /sys/kernel/debug/kmemleak # tc a a a tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 index 111 Error: TC IDR already exists. We have an error talking to the kernel # echo scan > /sys/kernel/debug/kmemleak # cat /sys/kernel/debug/kmemleak unreferenced object 0xffff8800574e6c80 (size 256): comm "tc", pid 5617, jiffies 4298118009 (age 57.990s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 1c e8 b0 ff ff ff ff ................ 81 24 c2 ad ff ff ff ff 00 00 00 00 00 00 00 00 .$.............. backtrace: [<00000000b7afbf4e>] tunnel_key_init+0x8a5/0x1800 [act_tunnel_key] [<000000007d98fccd>] tcf_action_init_1+0x698/0xac0 [<0000000099b8f7cc>] tcf_action_init+0x15c/0x590 [<00000000dc60eebe>] tc_ctl_action+0x336/0x5c2 [<000000002f5a2f7d>] rtnetlink_rcv_msg+0x357/0x8e0 [<000000000bfe7575>] netlink_rcv_skb+0x124/0x350 [<00000000edab656f>] netlink_unicast+0x40f/0x5d0 [<00000000b322cdcb>] netlink_sendmsg+0x6e8/0xba0 [<0000000063d9d490>] sock_sendmsg+0xb3/0xf0 [<00000000f0d3315a>] ___sys_sendmsg+0x654/0x960 [<00000000c06cbd42>] __sys_sendmsg+0xd3/0x170 [<00000000ce72e4b0>] do_syscall_64+0xa5/0x470 [<000000005caa2d97>] entry_SYSCALL_64_after_hwframe+0x49/0xbe [<00000000fac1b476>] 0xffffffffffffffff This problem theoretically happens also in case users attempt to setup a geneve rule having wrong configuration data, or when the kernel fails to allocate 'params_new'. Ensure that tunnel_key_init() releases the tunnel metadata also in the above conditions. Addresses-Coverity-ID: 1373974 ("Resource leak") Fixes: d0f6dd8a914f4 ("net/sched: Introduce act_tunnel_key") Fixes: 0ed5269f9e41f ("net/sched: add tunnel option support to act_tunnel_key") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-09-05 01:00:19 +08:00
ret = -ENOMEM;
exists = true;
net/sched: act_tunnel_key: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.2 dst_port 3128 \ > nocsum id 1 pass index 90 # tc actions replace action tunnel_key \ > set src_ip 10.10.10.1 dst_ip 20.20.2 dst_port 3128 nocsum id 1 \ > goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action tunnel_key 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: tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.2.0 key_id 1 dst_port 3128 nocsum 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 800000002aba4067 P4D 800000002aba4067 PUD 795f9067 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:ffff9346bdb83be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9346bb795c00 RCX: 0000000000000002 RDX: 0000000000000000 RSI: ffff93466c881700 RDI: 0000000000000246 RBP: ffff9346bdb83c80 R08: ffff9346b3e1e0c8 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff9346b978f000 R13: ffff9346b978f008 R14: 0000000000000001 R15: ffff93466dceeb40 FS: 0000000000000000(0000) GS:ffff9346bdb80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007a6c2002 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: 55 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:ffffa48a8038feb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffffaa8184f0 RBX: 0000000000000003 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000003 RBP: 0000000000000003 R08: 0011251c6fcfac49 R09: ffff9346b995be00 R10: ffffa48a805e7ce8 R11: 00000000024c38dd 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_tunnel_key veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul snd_hda_codec_generic ghash_clmulni_intel mbcache snd_hda_intel jbd2 snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd glue_helper joydev snd_timer snd pcspkr virtio_balloon soundcore i2c_piix4 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 ttm net_failover virtio_console virtio_blk failover drm serio_raw crc32c_intel ata_piix virtio_pci floppy virtio_ring libata virtio dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_tunnel_key_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 22:00:13 +08:00
goto put_chain;
}
params_new->tcft_action = parm->t_action;
params_new->tcft_enc_metadata = metadata;
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>
2018-08-15 02:46:16 +08:00
spin_lock_bh(&t->tcf_lock);
net/sched: act_tunnel_key: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.2 dst_port 3128 \ > nocsum id 1 pass index 90 # tc actions replace action tunnel_key \ > set src_ip 10.10.10.1 dst_ip 20.20.2 dst_port 3128 nocsum id 1 \ > goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action tunnel_key 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: tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.2.0 key_id 1 dst_port 3128 nocsum 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 800000002aba4067 P4D 800000002aba4067 PUD 795f9067 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:ffff9346bdb83be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9346bb795c00 RCX: 0000000000000002 RDX: 0000000000000000 RSI: ffff93466c881700 RDI: 0000000000000246 RBP: ffff9346bdb83c80 R08: ffff9346b3e1e0c8 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff9346b978f000 R13: ffff9346b978f008 R14: 0000000000000001 R15: ffff93466dceeb40 FS: 0000000000000000(0000) GS:ffff9346bdb80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007a6c2002 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: 55 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:ffffa48a8038feb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffffaa8184f0 RBX: 0000000000000003 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000003 RBP: 0000000000000003 R08: 0011251c6fcfac49 R09: ffff9346b995be00 R10: ffffa48a805e7ce8 R11: 00000000024c38dd 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_tunnel_key veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul snd_hda_codec_generic ghash_clmulni_intel mbcache snd_hda_intel jbd2 snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd glue_helper joydev snd_timer snd pcspkr virtio_balloon soundcore i2c_piix4 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 ttm net_failover virtio_console virtio_blk failover drm serio_raw crc32c_intel ata_piix virtio_pci floppy virtio_ring libata virtio dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_tunnel_key_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 22:00:13 +08:00
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
params_new = rcu_replace_pointer(t->params, params_new,
lockdep_is_held(&t->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>
2018-08-15 02:46:16 +08:00
spin_unlock_bh(&t->tcf_lock);
net/sched: act_tunnel_key: fix memory leak in case of action replace running the following TDC test cases: 7afc - Replace tunnel_key set action with all parameters 364d - Replace tunnel_key set action with all parameters and cookie it's possible to trigger kmemleak warnings like: unreferenced object 0xffff94797127ab40 (size 192): comm "tc", pid 3248, jiffies 4300565293 (age 1006.862s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 c0 93 f9 8a ff ff ff ff ................ 41 84 ee 89 ff ff ff ff 00 00 00 00 00 00 00 00 A............... backtrace: [<000000001e85b61c>] tunnel_key_init+0x31d/0x820 [act_tunnel_key] [<000000007f3f6ee7>] tcf_action_init_1+0x384/0x4c0 [<00000000e89e3ded>] tcf_action_init+0x12b/0x1a0 [<00000000c1c8c0f8>] tcf_action_add+0x73/0x170 [<0000000095a9fc28>] tc_ctl_action+0x122/0x160 [<000000004bebeac5>] rtnetlink_rcv_msg+0x263/0x2d0 [<000000009fd862dd>] netlink_rcv_skb+0x4a/0x110 [<00000000b55199e7>] netlink_unicast+0x1a0/0x250 [<000000004996cd21>] netlink_sendmsg+0x2c1/0x3c0 [<000000004d6a94b4>] sock_sendmsg+0x36/0x40 [<000000005d9f0208>] ___sys_sendmsg+0x280/0x2f0 [<00000000dec19023>] __sys_sendmsg+0x5e/0xa0 [<000000004b82ac81>] do_syscall_64+0x5b/0x180 [<00000000a0f1209a>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [<000000002926b2ab>] 0xffffffffffffffff when the tunnel_key action is replaced, the kernel forgets to release the dst metadata: ensure they are released by tunnel_key_init(), the same way it's done in tunnel_key_release(). Fixes: d0f6dd8a914f4 ("net/sched: Introduce act_tunnel_key") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-11 03:21:02 +08:00
tunnel_key_release_params(params_new);
net/sched: act_tunnel_key: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.2 dst_port 3128 \ > nocsum id 1 pass index 90 # tc actions replace action tunnel_key \ > set src_ip 10.10.10.1 dst_ip 20.20.2 dst_port 3128 nocsum id 1 \ > goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action tunnel_key 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: tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.2.0 key_id 1 dst_port 3128 nocsum 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 800000002aba4067 P4D 800000002aba4067 PUD 795f9067 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:ffff9346bdb83be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9346bb795c00 RCX: 0000000000000002 RDX: 0000000000000000 RSI: ffff93466c881700 RDI: 0000000000000246 RBP: ffff9346bdb83c80 R08: ffff9346b3e1e0c8 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff9346b978f000 R13: ffff9346b978f008 R14: 0000000000000001 R15: ffff93466dceeb40 FS: 0000000000000000(0000) GS:ffff9346bdb80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007a6c2002 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: 55 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:ffffa48a8038feb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffffaa8184f0 RBX: 0000000000000003 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000003 RBP: 0000000000000003 R08: 0011251c6fcfac49 R09: ffff9346b995be00 R10: ffffa48a805e7ce8 R11: 00000000024c38dd 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_tunnel_key veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul snd_hda_codec_generic ghash_clmulni_intel mbcache snd_hda_intel jbd2 snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd glue_helper joydev snd_timer snd pcspkr virtio_balloon soundcore i2c_piix4 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 ttm net_failover virtio_console virtio_blk failover drm serio_raw crc32c_intel ata_piix virtio_pci floppy virtio_ring libata virtio dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_tunnel_key_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 22:00:13 +08:00
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
if (ret == ACT_P_CREATED)
tcf_idr_insert(tn, *a);
return ret;
net/sched: act_tunnel_key: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.2 dst_port 3128 \ > nocsum id 1 pass index 90 # tc actions replace action tunnel_key \ > set src_ip 10.10.10.1 dst_ip 20.20.2 dst_port 3128 nocsum id 1 \ > goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action tunnel_key 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: tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.2.0 key_id 1 dst_port 3128 nocsum 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 800000002aba4067 P4D 800000002aba4067 PUD 795f9067 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:ffff9346bdb83be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9346bb795c00 RCX: 0000000000000002 RDX: 0000000000000000 RSI: ffff93466c881700 RDI: 0000000000000246 RBP: ffff9346bdb83c80 R08: ffff9346b3e1e0c8 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff9346b978f000 R13: ffff9346b978f008 R14: 0000000000000001 R15: ffff93466dceeb40 FS: 0000000000000000(0000) GS:ffff9346bdb80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007a6c2002 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: 55 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:ffffa48a8038feb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffffaa8184f0 RBX: 0000000000000003 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000003 RBP: 0000000000000003 R08: 0011251c6fcfac49 R09: ffff9346b995be00 R10: ffffa48a805e7ce8 R11: 00000000024c38dd 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_tunnel_key veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul snd_hda_codec_generic ghash_clmulni_intel mbcache snd_hda_intel jbd2 snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd glue_helper joydev snd_timer snd pcspkr virtio_balloon soundcore i2c_piix4 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 ttm net_failover virtio_console virtio_blk failover drm serio_raw crc32c_intel ata_piix virtio_pci floppy virtio_ring libata virtio dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_tunnel_key_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 22:00:13 +08:00
put_chain:
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
net/sched: fix memory leak in act_tunnel_key_init() If users try to install act_tunnel_key 'set' rules with duplicate values of 'index', the tunnel metadata are allocated, but never released. Then, kmemleak complains as follows: # tc a a a tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 index 111 # echo clear > /sys/kernel/debug/kmemleak # tc a a a tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 index 111 Error: TC IDR already exists. We have an error talking to the kernel # echo scan > /sys/kernel/debug/kmemleak # cat /sys/kernel/debug/kmemleak unreferenced object 0xffff8800574e6c80 (size 256): comm "tc", pid 5617, jiffies 4298118009 (age 57.990s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 1c e8 b0 ff ff ff ff ................ 81 24 c2 ad ff ff ff ff 00 00 00 00 00 00 00 00 .$.............. backtrace: [<00000000b7afbf4e>] tunnel_key_init+0x8a5/0x1800 [act_tunnel_key] [<000000007d98fccd>] tcf_action_init_1+0x698/0xac0 [<0000000099b8f7cc>] tcf_action_init+0x15c/0x590 [<00000000dc60eebe>] tc_ctl_action+0x336/0x5c2 [<000000002f5a2f7d>] rtnetlink_rcv_msg+0x357/0x8e0 [<000000000bfe7575>] netlink_rcv_skb+0x124/0x350 [<00000000edab656f>] netlink_unicast+0x40f/0x5d0 [<00000000b322cdcb>] netlink_sendmsg+0x6e8/0xba0 [<0000000063d9d490>] sock_sendmsg+0xb3/0xf0 [<00000000f0d3315a>] ___sys_sendmsg+0x654/0x960 [<00000000c06cbd42>] __sys_sendmsg+0xd3/0x170 [<00000000ce72e4b0>] do_syscall_64+0xa5/0x470 [<000000005caa2d97>] entry_SYSCALL_64_after_hwframe+0x49/0xbe [<00000000fac1b476>] 0xffffffffffffffff This problem theoretically happens also in case users attempt to setup a geneve rule having wrong configuration data, or when the kernel fails to allocate 'params_new'. Ensure that tunnel_key_init() releases the tunnel metadata also in the above conditions. Addresses-Coverity-ID: 1373974 ("Resource leak") Fixes: d0f6dd8a914f4 ("net/sched: Introduce act_tunnel_key") Fixes: 0ed5269f9e41f ("net/sched: add tunnel option support to act_tunnel_key") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-09-05 01:00:19 +08:00
release_tun_meta:
if (metadata)
dst_release(&metadata->dst);
net/sched: fix memory leak in act_tunnel_key_init() If users try to install act_tunnel_key 'set' rules with duplicate values of 'index', the tunnel metadata are allocated, but never released. Then, kmemleak complains as follows: # tc a a a tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 index 111 # echo clear > /sys/kernel/debug/kmemleak # tc a a a tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 index 111 Error: TC IDR already exists. We have an error talking to the kernel # echo scan > /sys/kernel/debug/kmemleak # cat /sys/kernel/debug/kmemleak unreferenced object 0xffff8800574e6c80 (size 256): comm "tc", pid 5617, jiffies 4298118009 (age 57.990s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 1c e8 b0 ff ff ff ff ................ 81 24 c2 ad ff ff ff ff 00 00 00 00 00 00 00 00 .$.............. backtrace: [<00000000b7afbf4e>] tunnel_key_init+0x8a5/0x1800 [act_tunnel_key] [<000000007d98fccd>] tcf_action_init_1+0x698/0xac0 [<0000000099b8f7cc>] tcf_action_init+0x15c/0x590 [<00000000dc60eebe>] tc_ctl_action+0x336/0x5c2 [<000000002f5a2f7d>] rtnetlink_rcv_msg+0x357/0x8e0 [<000000000bfe7575>] netlink_rcv_skb+0x124/0x350 [<00000000edab656f>] netlink_unicast+0x40f/0x5d0 [<00000000b322cdcb>] netlink_sendmsg+0x6e8/0xba0 [<0000000063d9d490>] sock_sendmsg+0xb3/0xf0 [<00000000f0d3315a>] ___sys_sendmsg+0x654/0x960 [<00000000c06cbd42>] __sys_sendmsg+0xd3/0x170 [<00000000ce72e4b0>] do_syscall_64+0xa5/0x470 [<000000005caa2d97>] entry_SYSCALL_64_after_hwframe+0x49/0xbe [<00000000fac1b476>] 0xffffffffffffffff This problem theoretically happens also in case users attempt to setup a geneve rule having wrong configuration data, or when the kernel fails to allocate 'params_new'. Ensure that tunnel_key_init() releases the tunnel metadata also in the above conditions. Addresses-Coverity-ID: 1373974 ("Resource leak") Fixes: d0f6dd8a914f4 ("net/sched: Introduce act_tunnel_key") Fixes: 0ed5269f9e41f ("net/sched: add tunnel option support to act_tunnel_key") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-09-05 01:00:19 +08:00
err_out:
if (exists)
tcf_idr_release(*a, bind);
else
tcf_idr_cleanup(tn, index);
return ret;
}
static void tunnel_key_release(struct tc_action *a)
{
struct tcf_tunnel_key *t = to_tunnel_key(a);
struct tcf_tunnel_key_params *params;
params = rcu_dereference_protected(t->params, 1);
net/sched: act_tunnel_key: fix memory leak in case of action replace running the following TDC test cases: 7afc - Replace tunnel_key set action with all parameters 364d - Replace tunnel_key set action with all parameters and cookie it's possible to trigger kmemleak warnings like: unreferenced object 0xffff94797127ab40 (size 192): comm "tc", pid 3248, jiffies 4300565293 (age 1006.862s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 c0 93 f9 8a ff ff ff ff ................ 41 84 ee 89 ff ff ff ff 00 00 00 00 00 00 00 00 A............... backtrace: [<000000001e85b61c>] tunnel_key_init+0x31d/0x820 [act_tunnel_key] [<000000007f3f6ee7>] tcf_action_init_1+0x384/0x4c0 [<00000000e89e3ded>] tcf_action_init+0x12b/0x1a0 [<00000000c1c8c0f8>] tcf_action_add+0x73/0x170 [<0000000095a9fc28>] tc_ctl_action+0x122/0x160 [<000000004bebeac5>] rtnetlink_rcv_msg+0x263/0x2d0 [<000000009fd862dd>] netlink_rcv_skb+0x4a/0x110 [<00000000b55199e7>] netlink_unicast+0x1a0/0x250 [<000000004996cd21>] netlink_sendmsg+0x2c1/0x3c0 [<000000004d6a94b4>] sock_sendmsg+0x36/0x40 [<000000005d9f0208>] ___sys_sendmsg+0x280/0x2f0 [<00000000dec19023>] __sys_sendmsg+0x5e/0xa0 [<000000004b82ac81>] do_syscall_64+0x5b/0x180 [<00000000a0f1209a>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [<000000002926b2ab>] 0xffffffffffffffff when the tunnel_key action is replaced, the kernel forgets to release the dst metadata: ensure they are released by tunnel_key_init(), the same way it's done in tunnel_key_release(). Fixes: d0f6dd8a914f4 ("net/sched: Introduce act_tunnel_key") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-11 03:21:02 +08:00
tunnel_key_release_params(params);
}
static int tunnel_key_geneve_opts_dump(struct sk_buff *skb,
const struct ip_tunnel_info *info)
{
int len = info->options_len;
u8 *src = (u8 *)(info + 1);
struct nlattr *start;
start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_GENEVE);
if (!start)
return -EMSGSIZE;
while (len > 0) {
struct geneve_opt *opt = (struct geneve_opt *)src;
if (nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS,
opt->opt_class) ||
nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE,
opt->type) ||
nla_put(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA,
opt->length * 4, opt + 1)) {
nla_nest_cancel(skb, start);
return -EMSGSIZE;
}
len -= sizeof(struct geneve_opt) + opt->length * 4;
src += sizeof(struct geneve_opt) + opt->length * 4;
}
nla_nest_end(skb, start);
return 0;
}
static int tunnel_key_vxlan_opts_dump(struct sk_buff *skb,
const struct ip_tunnel_info *info)
{
struct vxlan_metadata *md = (struct vxlan_metadata *)(info + 1);
struct nlattr *start;
start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_VXLAN);
if (!start)
return -EMSGSIZE;
if (nla_put_u32(skb, TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP, md->gbp)) {
nla_nest_cancel(skb, start);
return -EMSGSIZE;
}
nla_nest_end(skb, start);
return 0;
}
static int tunnel_key_erspan_opts_dump(struct sk_buff *skb,
const struct ip_tunnel_info *info)
{
struct erspan_metadata *md = (struct erspan_metadata *)(info + 1);
struct nlattr *start;
start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN);
if (!start)
return -EMSGSIZE;
if (nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER, md->version))
goto err;
if (md->version == 1 &&
nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX, md->u.index))
goto err;
if (md->version == 2 &&
(nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR,
md->u.md2.dir) ||
nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID,
get_hwid(&md->u.md2))))
goto err;
nla_nest_end(skb, start);
return 0;
err:
nla_nest_cancel(skb, start);
return -EMSGSIZE;
}
static int tunnel_key_opts_dump(struct sk_buff *skb,
const struct ip_tunnel_info *info)
{
struct nlattr *start;
int err = -EINVAL;
if (!info->options_len)
return 0;
start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS);
if (!start)
return -EMSGSIZE;
if (info->key.tun_flags & TUNNEL_GENEVE_OPT) {
err = tunnel_key_geneve_opts_dump(skb, info);
if (err)
goto err_out;
} else if (info->key.tun_flags & TUNNEL_VXLAN_OPT) {
err = tunnel_key_vxlan_opts_dump(skb, info);
if (err)
goto err_out;
} else if (info->key.tun_flags & TUNNEL_ERSPAN_OPT) {
err = tunnel_key_erspan_opts_dump(skb, info);
if (err)
goto err_out;
} else {
err_out:
nla_nest_cancel(skb, start);
return err;
}
nla_nest_end(skb, start);
return 0;
}
static int tunnel_key_dump_addresses(struct sk_buff *skb,
const struct ip_tunnel_info *info)
{
unsigned short family = ip_tunnel_info_af(info);
if (family == AF_INET) {
__be32 saddr = info->key.u.ipv4.src;
__be32 daddr = info->key.u.ipv4.dst;
if (!nla_put_in_addr(skb, TCA_TUNNEL_KEY_ENC_IPV4_SRC, saddr) &&
!nla_put_in_addr(skb, TCA_TUNNEL_KEY_ENC_IPV4_DST, daddr))
return 0;
}
if (family == AF_INET6) {
const struct in6_addr *saddr6 = &info->key.u.ipv6.src;
const struct in6_addr *daddr6 = &info->key.u.ipv6.dst;
if (!nla_put_in6_addr(skb,
TCA_TUNNEL_KEY_ENC_IPV6_SRC, saddr6) &&
!nla_put_in6_addr(skb,
TCA_TUNNEL_KEY_ENC_IPV6_DST, daddr6))
return 0;
}
return -EINVAL;
}
static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a,
int bind, int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_tunnel_key *t = to_tunnel_key(a);
struct tcf_tunnel_key_params *params;
struct tc_tunnel_key opt = {
.index = t->tcf_index,
.refcnt = refcount_read(&t->tcf_refcnt) - ref,
.bindcnt = atomic_read(&t->tcf_bindcnt) - bind,
};
struct tcf_t tm;
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>
2018-08-15 02:46:16 +08:00
spin_lock_bh(&t->tcf_lock);
params = rcu_dereference_protected(t->params,
lockdep_is_held(&t->tcf_lock));
opt.action = t->tcf_action;
opt.t_action = params->tcft_action;
if (nla_put(skb, TCA_TUNNEL_KEY_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET) {
struct ip_tunnel_info *info =
&params->tcft_enc_metadata->u.tun_info;
struct ip_tunnel_key *key = &info->key;
__be32 key_id = tunnel_id_to_key32(key->tun_id);
if (((key->tun_flags & TUNNEL_KEY) &&
nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_KEY_ID, key_id)) ||
tunnel_key_dump_addresses(skb,
&params->tcft_enc_metadata->u.tun_info) ||
(key->tp_dst &&
nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_DST_PORT,
key->tp_dst)) ||
nla_put_u8(skb, TCA_TUNNEL_KEY_NO_CSUM,
!(key->tun_flags & TUNNEL_CSUM)) ||
tunnel_key_opts_dump(skb, info))
goto nla_put_failure;
if (key->tos && nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_TOS, key->tos))
goto nla_put_failure;
if (key->ttl && nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_TTL, key->ttl))
goto nla_put_failure;
}
tcf_tm_dump(&tm, &t->tcf_tm);
if (nla_put_64bit(skb, TCA_TUNNEL_KEY_TM, sizeof(tm),
&tm, TCA_TUNNEL_KEY_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>
2018-08-15 02:46:16 +08:00
spin_unlock_bh(&t->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>
2018-08-15 02:46:16 +08:00
spin_unlock_bh(&t->tcf_lock);
nlmsg_trim(skb, b);
return -1;
}
static int tunnel_key_walker(struct net *net, struct sk_buff *skb,
struct netlink_callback *cb, int type,
const struct tc_action_ops *ops,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
return tcf_generic_walker(tn, skb, cb, type, ops, extack);
}
static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index)
{
struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
return tcf_idr_search(tn, a, index);
}
static struct tc_action_ops act_tunnel_key_ops = {
.kind = "tunnel_key",
.id = TCA_ID_TUNNEL_KEY,
.owner = THIS_MODULE,
.act = tunnel_key_act,
.dump = tunnel_key_dump,
.init = tunnel_key_init,
.cleanup = tunnel_key_release,
.walk = tunnel_key_walker,
.lookup = tunnel_key_search,
.size = sizeof(struct tcf_tunnel_key),
};
static __net_init int tunnel_key_init_net(struct net *net)
{
struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
return tc_action_net_init(net, tn, &act_tunnel_key_ops);
}
static void __net_exit tunnel_key_exit_net(struct list_head *net_list)
{
tc_action_net_exit(net_list, tunnel_key_net_id);
}
static struct pernet_operations tunnel_key_net_ops = {
.init = tunnel_key_init_net,
.exit_batch = tunnel_key_exit_net,
.id = &tunnel_key_net_id,
.size = sizeof(struct tc_action_net),
};
static int __init tunnel_key_init_module(void)
{
return tcf_register_action(&act_tunnel_key_ops, &tunnel_key_net_ops);
}
static void __exit tunnel_key_cleanup_module(void)
{
tcf_unregister_action(&act_tunnel_key_ops, &tunnel_key_net_ops);
}
module_init(tunnel_key_init_module);
module_exit(tunnel_key_cleanup_module);
MODULE_AUTHOR("Amir Vadai <amir@vadai.me>");
MODULE_DESCRIPTION("ip tunnel manipulation actions");
MODULE_LICENSE("GPL v2");