linux/net/sched/act_tunnel_key.c

607 lines
16 KiB
C
Raw Normal View History

/*
* Copyright (c) 2016, Amir Vadai <amir@vadai.me>
* Copyright (c) 2016, Mellanox Technologies. All rights reserved.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*/
#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/netlink.h>
#include <net/pkt_sched.h>
#include <net/dst.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);
bstats_cpu_update(this_cpu_ptr(t->common.cpu_bstats), 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_GENEVE] = { .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 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;
err = nla_parse_nested(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_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;
const struct nlattr *attr, *head = nla_data(nla);
err = nla_validate(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:
opt_len = tunnel_key_copy_geneve_opt(attr, dst,
dst_len, extack);
if (opt_len < 0)
return opt_len;
opts_len += opt_len;
if (dst) {
dst_len -= opt_len;
dst += opt_len;
}
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
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 },
};
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 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;
struct tc_tunnel_key *parm;
struct tcf_tunnel_key *t;
bool exists = false;
__be16 dst_port = 0;
int opts_len = 0;
__be64 key_id;
__be16 flags;
u8 tos, ttl;
int ret = 0;
int err;
if (!nla) {
NL_SET_ERR_MSG(extack, "Tunnel requires attributes to be passed");
return -EINVAL;
}
err = nla_parse_nested(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]);
err = tcf_idr_check_alloc(tn, &parm->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]) {
NL_SET_ERR_MSG(extack, "Missing tunnel key id");
ret = -EINVAL;
goto err_out;
}
key_id = key32_to_tunnel_id(nla_get_be32(tb[TCA_TUNNEL_KEY_ENC_KEY_ID]));
flags = TUNNEL_KEY | 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;
}
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 err_out;
}
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(tn, parm->index, est, a,
&act_tunnel_key_ops, bind, true);
if (ret) {
NL_SET_ERR_MSG(extack, "Cannot create TC IDR");
goto err_out;
}
ret = ACT_P_CREATED;
} else if (!ovr) {
tcf_idr_release(*a, bind);
NL_SET_ERR_MSG(extack, "TC IDR already exists");
return -EEXIST;
}
t = to_tunnel_key(*a);
params_new = kzalloc(sizeof(*params_new), GFP_KERNEL);
if (unlikely(!params_new)) {
tcf_idr_release(*a, bind);
NL_SET_ERR_MSG(extack, "Cannot allocate tunnel key parameters");
return -ENOMEM;
}
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);
t->tcf_action = parm->action;
rcu_swap_protected(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);
if (params_new)
kfree_rcu(params_new, rcu);
if (ret == ACT_P_CREATED)
tcf_idr_insert(tn, *a);
return ret;
err_out:
if (exists)
tcf_idr_release(*a, bind);
else
tcf_idr_cleanup(tn, parm->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: fix NULL dereference in the error path of tunnel_key_init() when the following command # tc action add action tunnel_key unset index 100 is run for the first time, and tunnel_key_init() fails to allocate struct tcf_tunnel_key_params, tunnel_key_release() dereferences NULL pointers. This causes the following error: BUG: unable to handle kernel NULL pointer dereference at 0000000000000010 IP: tunnel_key_release+0xd/0x40 [act_tunnel_key] PGD 8000000033787067 P4D 8000000033787067 PUD 74646067 PMD 0 Oops: 0000 [#1] SMP PTI Modules linked in: act_tunnel_key(E) act_csum ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 mbcache jbd2 crct10dif_pclmul crc32_pclmul snd_hda_codec_generic ghash_clmulni_intel snd_hda_intel pcbc snd_hda_codec snd_hda_core snd_hwdep snd_seq aesni_intel snd_seq_device crypto_simd glue_helper snd_pcm cryptd joydev snd_timer pcspkr virtio_balloon snd i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm virtio_net virtio_blk drm virtio_console crc32c_intel ata_piix serio_raw i2c_core virtio_pci libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CPU: 2 PID: 3101 Comm: tc Tainted: G E 4.16.0-rc4.act_vlan.orig+ #403 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tunnel_key_release+0xd/0x40 [act_tunnel_key] RSP: 0018:ffffba46803b7768 EFLAGS: 00010286 RAX: ffffffffc09010a0 RBX: 0000000000000000 RCX: 0000000000000024 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff99ee336d7480 RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000044 R10: 0000000000000220 R11: ffff99ee79d73131 R12: 0000000000000000 R13: ffff99ee32d67610 R14: ffff99ee7671dc38 R15: 00000000fffffff4 FS: 00007febcb2cd740(0000) GS:ffff99ee7fd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000010 CR3: 000000007c8e4005 CR4: 00000000001606e0 Call Trace: __tcf_idr_release+0x79/0xf0 tunnel_key_init+0xd9/0x460 [act_tunnel_key] tcf_action_init_1+0x2cc/0x430 tcf_action_init+0xd3/0x1b0 tc_ctl_action+0x18b/0x240 rtnetlink_rcv_msg+0x29c/0x310 ? _cond_resched+0x15/0x30 ? __kmalloc_node_track_caller+0x1b9/0x270 ? rtnl_calcit.isra.28+0x100/0x100 netlink_rcv_skb+0xd2/0x110 netlink_unicast+0x17c/0x230 netlink_sendmsg+0x2cd/0x3c0 sock_sendmsg+0x30/0x40 ___sys_sendmsg+0x27a/0x290 __sys_sendmsg+0x51/0x90 do_syscall_64+0x6e/0x1a0 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 RIP: 0033:0x7febca6deba0 RSP: 002b:00007ffe7b0dd128 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007ffe7b0dd250 RCX: 00007febca6deba0 RDX: 0000000000000000 RSI: 00007ffe7b0dd1a0 RDI: 0000000000000003 RBP: 000000005aaa90cb R08: 0000000000000002 R09: 0000000000000000 R10: 00007ffe7b0dcba0 R11: 0000000000000246 R12: 0000000000000000 R13: 00007ffe7b0dd264 R14: 0000000000000001 R15: 0000000000669f60 Code: 44 00 00 8b 0d b5 23 00 00 48 8b 87 48 10 00 00 48 8b 3c c8 e9 a5 e5 d8 c3 0f 1f 44 00 00 0f 1f 44 00 00 53 48 8b 9f b0 00 00 00 <83> 7b 10 01 74 0b 48 89 df 31 f6 5b e9 f2 fa 7f c3 48 8b 7b 18 RIP: tunnel_key_release+0xd/0x40 [act_tunnel_key] RSP: ffffba46803b7768 CR2: 0000000000000010 Fix this in tunnel_key_release(), ensuring 'param' is not NULL before dereferencing it. Fixes: d0f6dd8a914f ("net/sched: Introduce act_tunnel_key") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-16 07:00:55 +08:00
if (params) {
if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET)
dst_release(&params->tcft_enc_metadata->dst);
net/sched: fix NULL dereference in the error path of tunnel_key_init() when the following command # tc action add action tunnel_key unset index 100 is run for the first time, and tunnel_key_init() fails to allocate struct tcf_tunnel_key_params, tunnel_key_release() dereferences NULL pointers. This causes the following error: BUG: unable to handle kernel NULL pointer dereference at 0000000000000010 IP: tunnel_key_release+0xd/0x40 [act_tunnel_key] PGD 8000000033787067 P4D 8000000033787067 PUD 74646067 PMD 0 Oops: 0000 [#1] SMP PTI Modules linked in: act_tunnel_key(E) act_csum ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 mbcache jbd2 crct10dif_pclmul crc32_pclmul snd_hda_codec_generic ghash_clmulni_intel snd_hda_intel pcbc snd_hda_codec snd_hda_core snd_hwdep snd_seq aesni_intel snd_seq_device crypto_simd glue_helper snd_pcm cryptd joydev snd_timer pcspkr virtio_balloon snd i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm virtio_net virtio_blk drm virtio_console crc32c_intel ata_piix serio_raw i2c_core virtio_pci libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CPU: 2 PID: 3101 Comm: tc Tainted: G E 4.16.0-rc4.act_vlan.orig+ #403 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tunnel_key_release+0xd/0x40 [act_tunnel_key] RSP: 0018:ffffba46803b7768 EFLAGS: 00010286 RAX: ffffffffc09010a0 RBX: 0000000000000000 RCX: 0000000000000024 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff99ee336d7480 RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000044 R10: 0000000000000220 R11: ffff99ee79d73131 R12: 0000000000000000 R13: ffff99ee32d67610 R14: ffff99ee7671dc38 R15: 00000000fffffff4 FS: 00007febcb2cd740(0000) GS:ffff99ee7fd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000010 CR3: 000000007c8e4005 CR4: 00000000001606e0 Call Trace: __tcf_idr_release+0x79/0xf0 tunnel_key_init+0xd9/0x460 [act_tunnel_key] tcf_action_init_1+0x2cc/0x430 tcf_action_init+0xd3/0x1b0 tc_ctl_action+0x18b/0x240 rtnetlink_rcv_msg+0x29c/0x310 ? _cond_resched+0x15/0x30 ? __kmalloc_node_track_caller+0x1b9/0x270 ? rtnl_calcit.isra.28+0x100/0x100 netlink_rcv_skb+0xd2/0x110 netlink_unicast+0x17c/0x230 netlink_sendmsg+0x2cd/0x3c0 sock_sendmsg+0x30/0x40 ___sys_sendmsg+0x27a/0x290 __sys_sendmsg+0x51/0x90 do_syscall_64+0x6e/0x1a0 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 RIP: 0033:0x7febca6deba0 RSP: 002b:00007ffe7b0dd128 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007ffe7b0dd250 RCX: 00007febca6deba0 RDX: 0000000000000000 RSI: 00007ffe7b0dd1a0 RDI: 0000000000000003 RBP: 000000005aaa90cb R08: 0000000000000002 R09: 0000000000000000 R10: 00007ffe7b0dcba0 R11: 0000000000000246 R12: 0000000000000000 R13: 00007ffe7b0dd264 R14: 0000000000000001 R15: 0000000000669f60 Code: 44 00 00 8b 0d b5 23 00 00 48 8b 87 48 10 00 00 48 8b 3c c8 e9 a5 e5 d8 c3 0f 1f 44 00 00 0f 1f 44 00 00 53 48 8b 9f b0 00 00 00 <83> 7b 10 01 74 0b 48 89 df 31 f6 5b e9 f2 fa 7f c3 48 8b 7b 18 RIP: tunnel_key_release+0xd/0x40 [act_tunnel_key] RSP: ffffba46803b7768 CR2: 0000000000000010 Fix this in tunnel_key_release(), ensuring 'param' is not NULL before dereferencing it. Fixes: d0f6dd8a914f ("net/sched: Introduce act_tunnel_key") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-16 07:00:55 +08:00
kfree_rcu(params, rcu);
}
}
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(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))
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_opts_dump(struct sk_buff *skb,
const struct ip_tunnel_info *info)
{
struct nlattr *start;
int err;
if (!info->options_len)
return 0;
start = nla_nest_start(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)
return err;
} else {
return -EINVAL;
}
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 (nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_KEY_ID, key_id) ||
tunnel_key_dump_addresses(skb,
&params->tcft_enc_metadata->u.tun_info) ||
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 netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
return tcf_idr_search(tn, a, index);
}
static int tunnel_key_delete(struct net *net, u32 index)
{
struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
return tcf_idr_delete_index(tn, index);
}
static struct tc_action_ops act_tunnel_key_ops = {
.kind = "tunnel_key",
.type = TCA_ACT_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,
.delete = tunnel_key_delete,
.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(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");