kernel-ark/net/sched/act_sample.c

302 lines
7.6 KiB
C
Raw Normal View History

/*
* net/sched/act_sample.c - Packet sampling tc action
* Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/gfp.h>
#include <net/net_namespace.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <linux/tc_act/tc_sample.h>
#include <net/tc_act/tc_sample.h>
#include <net/psample.h>
net/sched: act_sample: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action sample rate 1024 group 4 pass index 90 # tc actions replace action sample \ > rate 1024 group 4 goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action sample 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: sample rate 1/1024 group 4 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 8000000079966067 P4D 8000000079966067 PUD 7987b067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 5 Comm: kworker/0:0 Not tainted 5.0.0-rc4.gotochain_crash+ #536 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work 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:ffffbee60033fad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff99d7ae6e3b00 RCX: 00000000e555df9b RDX: 0000000000000000 RSI: 00000000b0352718 RDI: ffff99d7fda1fcf0 RBP: ffffbee60033fb70 R08: 0000000070731ab1 R09: 0000000000000400 R10: 0000000000000000 R11: ffff99d7ac733838 R12: ffff99d7f3c2be00 R13: ffff99d7f3c2be08 R14: 0000000000000001 R15: ffff99d7f3c2b600 FS: 0000000000000000(0000) GS:ffff99d7fda00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 00000000797de006 CR4: 00000000001606f0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_sample psample veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel mbcache jbd2 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device aesni_intel crypto_simd snd_pcm cryptd glue_helper snd_timer joydev snd pcspkr virtio_balloon i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect virtio_net sysimgblt fb_sys_fops net_failover ttm failover virtio_blk virtio_console drm ata_piix serio_raw crc32c_intel libata virtio_pci virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_sample_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 14:00:09 +00:00
#include <net/pkt_cls.h>
#include <linux/if_arp.h>
static unsigned int sample_net_id;
static struct tc_action_ops act_sample_ops;
static const struct nla_policy sample_policy[TCA_SAMPLE_MAX + 1] = {
[TCA_SAMPLE_PARMS] = { .len = sizeof(struct tc_sample) },
[TCA_SAMPLE_RATE] = { .type = NLA_U32 },
[TCA_SAMPLE_TRUNC_SIZE] = { .type = NLA_U32 },
[TCA_SAMPLE_PSAMPLE_GROUP] = { .type = NLA_U32 },
};
static int tcf_sample_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a, int ovr,
net/sched: prepare TC actions to properly validate the control action - pass a pointer to struct tcf_proto in each actions's init() handler, to allow validating the control action, checking whether the chain exists and (eventually) refcounting it. - remove code that validates the control action after a successful call to the action's init() handler, and replace it with a test that forbids addition of actions having 'goto_chain' and NULL goto_chain pointer at the same time. - add tcf_action_check_ctrlact(), that will validate the control action and eventually allocate the action 'goto_chain' within the init() handler. - add tcf_action_set_ctrlact(), that will assign the control action and swap the current 'goto_chain' pointer with the new given one. This disallows 'goto_chain' on actions that don't initialize it properly in their init() handler, i.e. calling tcf_action_check_ctrlact() after successful IDR reservation and then calling tcf_action_set_ctrlact() to assign 'goto_chain' and 'tcf_action' consistently. By doing this, the kernel does not leak anymore refcounts when a valid 'goto chain' handle is replaced in TC actions, causing kmemleak splats like the following one: # tc chain add dev dd0 chain 42 ingress protocol ip flower \ > ip_proto tcp action drop # tc chain add dev dd0 chain 43 ingress protocol ip flower \ > ip_proto udp action drop # tc filter add dev dd0 ingress matchall \ > action gact goto chain 42 index 66 # tc filter replace dev dd0 ingress matchall \ > action gact goto chain 43 index 66 # echo scan >/sys/kernel/debug/kmemleak <...> unreferenced object 0xffff93c0ee09f000 (size 1024): comm "tc", pid 2565, jiffies 4295339808 (age 65.426s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 08 00 06 00 00 00 00 00 00 00 00 00 ................ backtrace: [<000000009b63f92d>] tc_ctl_chain+0x3d2/0x4c0 [<00000000683a8d72>] rtnetlink_rcv_msg+0x263/0x2d0 [<00000000ddd88f8e>] netlink_rcv_skb+0x4a/0x110 [<000000006126a348>] netlink_unicast+0x1a0/0x250 [<00000000b3340877>] netlink_sendmsg+0x2c1/0x3c0 [<00000000a25a2171>] sock_sendmsg+0x36/0x40 [<00000000f19ee1ec>] ___sys_sendmsg+0x280/0x2f0 [<00000000d0422042>] __sys_sendmsg+0x5e/0xa0 [<000000007a6c61f9>] do_syscall_64+0x5b/0x180 [<00000000ccd07542>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [<0000000013eaa334>] 0xffffffffffffffff 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 13:59:59 +00:00
int bind, bool rtnl_held, struct tcf_proto *tp,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, sample_net_id);
struct nlattr *tb[TCA_SAMPLE_MAX + 1];
struct psample_group *psample_group;
net/sched: act_sample: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action sample rate 1024 group 4 pass index 90 # tc actions replace action sample \ > rate 1024 group 4 goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action sample 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: sample rate 1/1024 group 4 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 8000000079966067 P4D 8000000079966067 PUD 7987b067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 5 Comm: kworker/0:0 Not tainted 5.0.0-rc4.gotochain_crash+ #536 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work 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:ffffbee60033fad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff99d7ae6e3b00 RCX: 00000000e555df9b RDX: 0000000000000000 RSI: 00000000b0352718 RDI: ffff99d7fda1fcf0 RBP: ffffbee60033fb70 R08: 0000000070731ab1 R09: 0000000000000400 R10: 0000000000000000 R11: ffff99d7ac733838 R12: ffff99d7f3c2be00 R13: ffff99d7f3c2be08 R14: 0000000000000001 R15: ffff99d7f3c2b600 FS: 0000000000000000(0000) GS:ffff99d7fda00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 00000000797de006 CR4: 00000000001606f0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_sample psample veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel mbcache jbd2 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device aesni_intel crypto_simd snd_pcm cryptd glue_helper snd_timer joydev snd pcspkr virtio_balloon i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect virtio_net sysimgblt fb_sys_fops net_failover ttm failover virtio_blk virtio_console drm ata_piix serio_raw crc32c_intel libata virtio_pci virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_sample_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 14:00:09 +00:00
struct tcf_chain *goto_ch = NULL;
net/sched: act_sample: fix divide by zero in the traffic path the control path of 'sample' action does not validate the value of 'rate' provided by the user, but then it uses it as divisor in the traffic path. Validate it in tcf_sample_init(), and return -EINVAL with a proper extack message in case that value is zero, to fix a splat with the script below: # tc f a dev test0 egress matchall action sample rate 0 group 1 index 2 # tc -s a s action sample total acts 1 action order 0: sample rate 1/0 group 1 pipe index 2 ref 1 bind 1 installed 19 sec used 19 sec Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 # ping 192.0.2.1 -I test0 -c1 -q divide error: 0000 [#1] SMP PTI CPU: 1 PID: 6192 Comm: ping Not tainted 5.1.0-rc2.diag2+ #591 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_sample_act+0x9e/0x1e0 [act_sample] Code: 6a f1 85 c0 74 0d 80 3d 83 1a 00 00 00 0f 84 9c 00 00 00 4d 85 e4 0f 84 85 00 00 00 e8 9b d7 9c f1 44 8b 8b e0 00 00 00 31 d2 <41> f7 f1 85 d2 75 70 f6 85 83 00 00 00 10 48 8b 45 10 8b 88 08 01 RSP: 0018:ffffae320190ba30 EFLAGS: 00010246 RAX: 00000000b0677d21 RBX: ffff8af1ed9ec000 RCX: 0000000059a9fe49 RDX: 0000000000000000 RSI: 000000000c7e33b7 RDI: ffff8af23daa0af0 RBP: ffff8af1ee11b200 R08: 0000000074fcaf7e R09: 0000000000000000 R10: 0000000000000050 R11: ffffffffb3088680 R12: ffff8af232307f80 R13: 0000000000000003 R14: ffff8af1ed9ec000 R15: 0000000000000000 FS: 00007fe9c6d2f740(0000) GS:ffff8af23da80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fff6772f000 CR3: 00000000746a2004 CR4: 00000000001606e0 Call Trace: tcf_action_exec+0x7c/0x1c0 tcf_classify+0x57/0x160 __dev_queue_xmit+0x3dc/0xd10 ip_finish_output2+0x257/0x6d0 ip_output+0x75/0x280 ip_send_skb+0x15/0x40 raw_sendmsg+0xae3/0x1410 sock_sendmsg+0x36/0x40 __sys_sendto+0x10e/0x140 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x60/0x210 entry_SYSCALL_64_after_hwframe+0x49/0xbe [...] Kernel panic - not syncing: Fatal exception in interrupt Add a TDC selftest to document that 'rate' is now being validated. Reported-by: Matteo Croce <mcroce@redhat.com> Fixes: 5c5670fae430 ("net/sched: Introduce sample tc action") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Yotam Gigi <yotam.gi@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-04 10:31:35 +00:00
u32 psample_group_num, rate;
struct tc_sample *parm;
struct tcf_sample *s;
bool exists = false;
int ret, err;
if (!nla)
return -EINVAL;
netlink: make validation more configurable for future strictness We currently have two levels of strict validation: 1) liberal (default) - undefined (type >= max) & NLA_UNSPEC attributes accepted - attribute length >= expected accepted - garbage at end of message accepted 2) strict (opt-in) - NLA_UNSPEC attributes accepted - attribute length >= expected accepted Split out parsing strictness into four different options: * TRAILING - check that there's no trailing data after parsing attributes (in message or nested) * MAXTYPE - reject attrs > max known type * UNSPEC - reject attributes with NLA_UNSPEC policy entries * STRICT_ATTRS - strictly validate attribute size The default for future things should be *everything*. The current *_strict() is a combination of TRAILING and MAXTYPE, and is renamed to _deprecated_strict(). The current regular parsing has none of this, and is renamed to *_parse_deprecated(). Additionally it allows us to selectively set one of the new flags even on old policies. Notably, the UNSPEC flag could be useful in this case, since it can be arranged (by filling in the policy) to not be an incompatible userspace ABI change, but would then going forward prevent forgetting attribute entries. Similar can apply to the POLICY flag. We end up with the following renames: * nla_parse -> nla_parse_deprecated * nla_parse_strict -> nla_parse_deprecated_strict * nlmsg_parse -> nlmsg_parse_deprecated * nlmsg_parse_strict -> nlmsg_parse_deprecated_strict * nla_parse_nested -> nla_parse_nested_deprecated * nla_validate_nested -> nla_validate_nested_deprecated Using spatch, of course: @@ expression TB, MAX, HEAD, LEN, POL, EXT; @@ -nla_parse(TB, MAX, HEAD, LEN, POL, EXT) +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression TB, MAX, NLA, POL, EXT; @@ -nla_parse_nested(TB, MAX, NLA, POL, EXT) +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT) @@ expression START, MAX, POL, EXT; @@ -nla_validate_nested(START, MAX, POL, EXT) +nla_validate_nested_deprecated(START, MAX, POL, EXT) @@ expression NLH, HDRLEN, MAX, POL, EXT; @@ -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT) +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT) For this patch, don't actually add the strict, non-renamed versions yet so that it breaks compile if I get it wrong. Also, while at it, make nla_validate and nla_parse go down to a common __nla_validate_parse() function to avoid code duplication. Ultimately, this allows us to have very strict validation for every new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the next patch, while existing things will continue to work as is. In effect then, this adds fully strict validation for any new command. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 12:07:28 +00:00
ret = nla_parse_nested_deprecated(tb, TCA_SAMPLE_MAX, nla,
sample_policy, NULL);
if (ret < 0)
return ret;
if (!tb[TCA_SAMPLE_PARMS] || !tb[TCA_SAMPLE_RATE] ||
!tb[TCA_SAMPLE_PSAMPLE_GROUP])
return -EINVAL;
parm = nla_data(tb[TCA_SAMPLE_PARMS]);
err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
if (err < 0)
return err;
exists = err;
if (exists && bind)
return 0;
if (!exists) {
ret = tcf_idr_create(tn, parm->index, est, a,
net/sched: act_sample: fix NULL dereference in the data path Matteo reported the following splat, testing the datapath of TC 'sample': BUG: KASAN: null-ptr-deref in tcf_sample_act+0xc4/0x310 Read of size 8 at addr 0000000000000000 by task nc/433 CPU: 0 PID: 433 Comm: nc Not tainted 4.19.0-rc3-kvm #17 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS ?-20180531_142017-buildhw-08.phx2.fedoraproject.org-1.fc28 04/01/2014 Call Trace: kasan_report.cold.6+0x6c/0x2fa tcf_sample_act+0xc4/0x310 ? dev_hard_start_xmit+0x117/0x180 tcf_action_exec+0xa3/0x160 tcf_classify+0xdd/0x1d0 htb_enqueue+0x18e/0x6b0 ? deref_stack_reg+0x7a/0xb0 ? htb_delete+0x4b0/0x4b0 ? unwind_next_frame+0x819/0x8f0 ? entry_SYSCALL_64_after_hwframe+0x44/0xa9 __dev_queue_xmit+0x722/0xca0 ? unwind_get_return_address_ptr+0x50/0x50 ? netdev_pick_tx+0xe0/0xe0 ? save_stack+0x8c/0xb0 ? kasan_kmalloc+0xbe/0xd0 ? __kmalloc_track_caller+0xe4/0x1c0 ? __kmalloc_reserve.isra.45+0x24/0x70 ? __alloc_skb+0xdd/0x2e0 ? sk_stream_alloc_skb+0x91/0x3b0 ? tcp_sendmsg_locked+0x71b/0x15a0 ? tcp_sendmsg+0x22/0x40 ? __sys_sendto+0x1b0/0x250 ? __x64_sys_sendto+0x6f/0x80 ? do_syscall_64+0x5d/0x150 ? entry_SYSCALL_64_after_hwframe+0x44/0xa9 ? __sys_sendto+0x1b0/0x250 ? __x64_sys_sendto+0x6f/0x80 ? do_syscall_64+0x5d/0x150 ? entry_SYSCALL_64_after_hwframe+0x44/0xa9 ip_finish_output2+0x495/0x590 ? ip_copy_metadata+0x2e0/0x2e0 ? skb_gso_validate_network_len+0x6f/0x110 ? ip_finish_output+0x174/0x280 __tcp_transmit_skb+0xb17/0x12b0 ? __tcp_select_window+0x380/0x380 tcp_write_xmit+0x913/0x1de0 ? __sk_mem_schedule+0x50/0x80 tcp_sendmsg_locked+0x49d/0x15a0 ? tcp_rcv_established+0x8da/0xa30 ? tcp_set_state+0x220/0x220 ? clear_user+0x1f/0x50 ? iov_iter_zero+0x1ae/0x590 ? __fget_light+0xa0/0xe0 tcp_sendmsg+0x22/0x40 __sys_sendto+0x1b0/0x250 ? __ia32_sys_getpeername+0x40/0x40 ? _copy_to_user+0x58/0x70 ? poll_select_copy_remaining+0x176/0x200 ? __pollwait+0x1c0/0x1c0 ? ktime_get_ts64+0x11f/0x140 ? kern_select+0x108/0x150 ? core_sys_select+0x360/0x360 ? vfs_read+0x127/0x150 ? kernel_write+0x90/0x90 __x64_sys_sendto+0x6f/0x80 do_syscall_64+0x5d/0x150 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7fefef2b129d Code: ff ff ff ff eb b6 0f 1f 80 00 00 00 00 48 8d 05 51 37 0c 00 41 89 ca 8b 00 85 c0 75 20 45 31 c9 45 31 c0 b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 6b f3 c3 66 0f 1f 84 00 00 00 00 00 41 56 41 RSP: 002b:00007fff2f5350c8 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 000056118d60c120 RCX: 00007fefef2b129d RDX: 0000000000002000 RSI: 000056118d629320 RDI: 0000000000000003 RBP: 000056118d530370 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000002000 R13: 000056118d5c2a10 R14: 000056118d5c2a10 R15: 000056118d5303b8 tcf_sample_act() tried to update its per-cpu stats, but tcf_sample_init() forgot to allocate them, because tcf_idr_create() was called with a wrong value of 'cpustats'. Setting it to true proved to fix the reported crash. Reported-by: Matteo Croce <mcroce@redhat.com> Fixes: 65a206c01e8e ("net/sched: Change act_api and act_xxx modules to use IDR") Fixes: 5c5670fae430 ("net/sched: Introduce sample tc action") Tested-by: Matteo Croce <mcroce@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-09-14 10:03:18 +00:00
&act_sample_ops, bind, true);
if (ret) {
tcf_idr_cleanup(tn, parm->index);
return ret;
}
ret = ACT_P_CREATED;
} else if (!ovr) {
tcf_idr_release(*a, bind);
return -EEXIST;
}
net/sched: act_sample: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action sample rate 1024 group 4 pass index 90 # tc actions replace action sample \ > rate 1024 group 4 goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action sample 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: sample rate 1/1024 group 4 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 8000000079966067 P4D 8000000079966067 PUD 7987b067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 5 Comm: kworker/0:0 Not tainted 5.0.0-rc4.gotochain_crash+ #536 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work 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:ffffbee60033fad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff99d7ae6e3b00 RCX: 00000000e555df9b RDX: 0000000000000000 RSI: 00000000b0352718 RDI: ffff99d7fda1fcf0 RBP: ffffbee60033fb70 R08: 0000000070731ab1 R09: 0000000000000400 R10: 0000000000000000 R11: ffff99d7ac733838 R12: ffff99d7f3c2be00 R13: ffff99d7f3c2be08 R14: 0000000000000001 R15: ffff99d7f3c2b600 FS: 0000000000000000(0000) GS:ffff99d7fda00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 00000000797de006 CR4: 00000000001606f0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_sample psample veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel mbcache jbd2 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device aesni_intel crypto_simd snd_pcm cryptd glue_helper snd_timer joydev snd pcspkr virtio_balloon i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect virtio_net sysimgblt fb_sys_fops net_failover ttm failover virtio_blk virtio_console drm ata_piix serio_raw crc32c_intel libata virtio_pci virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_sample_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 14:00:09 +00:00
err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
if (err < 0)
goto release_idr;
net/sched: act_sample: fix divide by zero in the traffic path the control path of 'sample' action does not validate the value of 'rate' provided by the user, but then it uses it as divisor in the traffic path. Validate it in tcf_sample_init(), and return -EINVAL with a proper extack message in case that value is zero, to fix a splat with the script below: # tc f a dev test0 egress matchall action sample rate 0 group 1 index 2 # tc -s a s action sample total acts 1 action order 0: sample rate 1/0 group 1 pipe index 2 ref 1 bind 1 installed 19 sec used 19 sec Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 # ping 192.0.2.1 -I test0 -c1 -q divide error: 0000 [#1] SMP PTI CPU: 1 PID: 6192 Comm: ping Not tainted 5.1.0-rc2.diag2+ #591 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_sample_act+0x9e/0x1e0 [act_sample] Code: 6a f1 85 c0 74 0d 80 3d 83 1a 00 00 00 0f 84 9c 00 00 00 4d 85 e4 0f 84 85 00 00 00 e8 9b d7 9c f1 44 8b 8b e0 00 00 00 31 d2 <41> f7 f1 85 d2 75 70 f6 85 83 00 00 00 10 48 8b 45 10 8b 88 08 01 RSP: 0018:ffffae320190ba30 EFLAGS: 00010246 RAX: 00000000b0677d21 RBX: ffff8af1ed9ec000 RCX: 0000000059a9fe49 RDX: 0000000000000000 RSI: 000000000c7e33b7 RDI: ffff8af23daa0af0 RBP: ffff8af1ee11b200 R08: 0000000074fcaf7e R09: 0000000000000000 R10: 0000000000000050 R11: ffffffffb3088680 R12: ffff8af232307f80 R13: 0000000000000003 R14: ffff8af1ed9ec000 R15: 0000000000000000 FS: 00007fe9c6d2f740(0000) GS:ffff8af23da80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fff6772f000 CR3: 00000000746a2004 CR4: 00000000001606e0 Call Trace: tcf_action_exec+0x7c/0x1c0 tcf_classify+0x57/0x160 __dev_queue_xmit+0x3dc/0xd10 ip_finish_output2+0x257/0x6d0 ip_output+0x75/0x280 ip_send_skb+0x15/0x40 raw_sendmsg+0xae3/0x1410 sock_sendmsg+0x36/0x40 __sys_sendto+0x10e/0x140 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x60/0x210 entry_SYSCALL_64_after_hwframe+0x49/0xbe [...] Kernel panic - not syncing: Fatal exception in interrupt Add a TDC selftest to document that 'rate' is now being validated. Reported-by: Matteo Croce <mcroce@redhat.com> Fixes: 5c5670fae430 ("net/sched: Introduce sample tc action") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Yotam Gigi <yotam.gi@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-04 10:31:35 +00:00
rate = nla_get_u32(tb[TCA_SAMPLE_RATE]);
if (!rate) {
NL_SET_ERR_MSG(extack, "invalid sample rate");
err = -EINVAL;
goto put_chain;
}
net: sched: always disable bh when taking tcf_lock Recently, ops->init() and ops->dump() of all actions were modified to always obtain tcf_lock when accessing private action state. Actions that don't depend on tcf_lock for synchronization with their data path use non-bh locking API. However, tcf_lock is also used to protect rate estimator stats in softirq context by timer callback. Change ops->init() and ops->dump() of all actions to disable bh when using tcf_lock to prevent deadlock reported by following lockdep warning: [ 105.470398] ================================ [ 105.475014] WARNING: inconsistent lock state [ 105.479628] 4.18.0-rc8+ #664 Not tainted [ 105.483897] -------------------------------- [ 105.488511] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. [ 105.494871] swapper/16/0 [HC0[0]:SC1[1]:HE1:SE0] takes: [ 105.500449] 00000000f86c012e (&(&p->tcfa_lock)->rlock){+.?.}, at: est_fetch_counters+0x3c/0xa0 [ 105.509696] {SOFTIRQ-ON-W} state was registered at: [ 105.514925] _raw_spin_lock+0x2c/0x40 [ 105.519022] tcf_bpf_init+0x579/0x820 [act_bpf] [ 105.523990] tcf_action_init_1+0x4e4/0x660 [ 105.528518] tcf_action_init+0x1ce/0x2d0 [ 105.532880] tcf_exts_validate+0x1d8/0x200 [ 105.537416] fl_change+0x55a/0x268b [cls_flower] [ 105.542469] tc_new_tfilter+0x748/0xa20 [ 105.546738] rtnetlink_rcv_msg+0x56a/0x6d0 [ 105.551268] netlink_rcv_skb+0x18d/0x200 [ 105.555628] netlink_unicast+0x2d0/0x370 [ 105.559990] netlink_sendmsg+0x3b9/0x6a0 [ 105.564349] sock_sendmsg+0x6b/0x80 [ 105.568271] ___sys_sendmsg+0x4a1/0x520 [ 105.572547] __sys_sendmsg+0xd7/0x150 [ 105.576655] do_syscall_64+0x72/0x2c0 [ 105.580757] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 105.586243] irq event stamp: 489296 [ 105.590084] hardirqs last enabled at (489296): [<ffffffffb507e639>] _raw_spin_unlock_irq+0x29/0x40 [ 105.599765] hardirqs last disabled at (489295): [<ffffffffb507e745>] _raw_spin_lock_irq+0x15/0x50 [ 105.609277] softirqs last enabled at (489292): [<ffffffffb413a6a3>] irq_enter+0x83/0xa0 [ 105.618001] softirqs last disabled at (489293): [<ffffffffb413a800>] irq_exit+0x140/0x190 [ 105.626813] other info that might help us debug this: [ 105.633976] Possible unsafe locking scenario: [ 105.640526] CPU0 [ 105.643325] ---- [ 105.646125] lock(&(&p->tcfa_lock)->rlock); [ 105.650747] <Interrupt> [ 105.653717] lock(&(&p->tcfa_lock)->rlock); [ 105.658514] *** DEADLOCK *** [ 105.665349] 1 lock held by swapper/16/0: [ 105.669629] #0: 00000000a640ad99 ((&est->timer)){+.-.}, at: call_timer_fn+0x10b/0x550 [ 105.678200] stack backtrace: [ 105.683194] CPU: 16 PID: 0 Comm: swapper/16 Not tainted 4.18.0-rc8+ #664 [ 105.690249] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 105.698626] Call Trace: [ 105.701421] <IRQ> [ 105.703791] dump_stack+0x92/0xeb [ 105.707461] print_usage_bug+0x336/0x34c [ 105.711744] mark_lock+0x7c9/0x980 [ 105.715500] ? print_shortest_lock_dependencies+0x2e0/0x2e0 [ 105.721424] ? check_usage_forwards+0x230/0x230 [ 105.726315] __lock_acquire+0x923/0x26f0 [ 105.730597] ? debug_show_all_locks+0x240/0x240 [ 105.735478] ? mark_lock+0x493/0x980 [ 105.739412] ? check_chain_key+0x140/0x1f0 [ 105.743861] ? __lock_acquire+0x836/0x26f0 [ 105.748323] ? lock_acquire+0x12e/0x290 [ 105.752516] lock_acquire+0x12e/0x290 [ 105.756539] ? est_fetch_counters+0x3c/0xa0 [ 105.761084] _raw_spin_lock+0x2c/0x40 [ 105.765099] ? est_fetch_counters+0x3c/0xa0 [ 105.769633] est_fetch_counters+0x3c/0xa0 [ 105.773995] est_timer+0x87/0x390 [ 105.777670] ? est_fetch_counters+0xa0/0xa0 [ 105.782210] ? lock_acquire+0x12e/0x290 [ 105.786410] call_timer_fn+0x161/0x550 [ 105.790512] ? est_fetch_counters+0xa0/0xa0 [ 105.795055] ? del_timer_sync+0xd0/0xd0 [ 105.799249] ? __lock_is_held+0x93/0x110 [ 105.803531] ? mark_held_locks+0x20/0xe0 [ 105.807813] ? _raw_spin_unlock_irq+0x29/0x40 [ 105.812525] ? est_fetch_counters+0xa0/0xa0 [ 105.817069] ? est_fetch_counters+0xa0/0xa0 [ 105.821610] run_timer_softirq+0x3c4/0x9f0 [ 105.826064] ? lock_acquire+0x12e/0x290 [ 105.830257] ? __bpf_trace_timer_class+0x10/0x10 [ 105.835237] ? __lock_is_held+0x25/0x110 [ 105.839517] __do_softirq+0x11d/0x7bf [ 105.843542] irq_exit+0x140/0x190 [ 105.847208] smp_apic_timer_interrupt+0xac/0x3b0 [ 105.852182] apic_timer_interrupt+0xf/0x20 [ 105.856628] </IRQ> [ 105.859081] RIP: 0010:cpuidle_enter_state+0xd8/0x4d0 [ 105.864395] Code: 46 ff 48 89 44 24 08 0f 1f 44 00 00 31 ff e8 cf ec 46 ff 80 7c 24 07 00 0f 85 1d 02 00 00 e8 9f 90 4b ff fb 66 0f 1f 44 00 00 <4c> 8b 6c 24 08 4d 29 fd 0f 80 36 03 00 00 4c 89 e8 48 ba cf f7 53 [ 105.884288] RSP: 0018:ffff8803ad94fd20 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 [ 105.892494] RAX: 0000000000000000 RBX: ffffe8fb300829c0 RCX: ffffffffb41e19e1 [ 105.899988] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8803ad9358ac [ 105.907503] RBP: ffffffffb6636300 R08: 0000000000000004 R09: 0000000000000000 [ 105.914997] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000004 [ 105.922487] R13: ffffffffb6636140 R14: ffffffffb66362d8 R15: 000000188d36091b [ 105.929988] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.935232] do_idle+0x28e/0x320 [ 105.938817] ? arch_cpu_idle_exit+0x40/0x40 [ 105.943361] ? mark_lock+0x8c1/0x980 [ 105.947295] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.952619] cpu_startup_entry+0xc2/0xd0 [ 105.956900] ? cpu_in_idle+0x20/0x20 [ 105.960830] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.966146] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.971391] start_secondary+0x2b5/0x360 [ 105.975669] ? set_cpu_sibling_map+0x1330/0x1330 [ 105.980654] secondary_startup_64+0xa5/0xb0 Taking tcf_lock in sample action with bh disabled causes lockdep to issue a warning regarding possible irq lock inversion dependency between tcf_lock, and psample_groups_lock that is taken when holding tcf_lock in sample init: [ 162.108959] Possible interrupt unsafe locking scenario: [ 162.116386] CPU0 CPU1 [ 162.121277] ---- ---- [ 162.126162] lock(psample_groups_lock); [ 162.130447] local_irq_disable(); [ 162.136772] lock(&(&p->tcfa_lock)->rlock); [ 162.143957] lock(psample_groups_lock); [ 162.150813] <Interrupt> [ 162.153808] lock(&(&p->tcfa_lock)->rlock); [ 162.158608] *** DEADLOCK *** In order to prevent potential lock inversion dependency between tcf_lock and psample_groups_lock, extract call to psample_group_get() from tcf_lock protected section in sample action init function. Fixes: 4e232818bd32 ("net: sched: act_mirred: remove dependency on rtnl lock") Fixes: 764e9a24480f ("net: sched: act_vlan: remove dependency on rtnl lock") Fixes: 729e01260989 ("net: sched: act_tunnel_key: remove dependency on rtnl lock") Fixes: d77284956656 ("net: sched: act_sample: remove dependency on rtnl lock") Fixes: e8917f437006 ("net: sched: act_gact: remove dependency on rtnl lock") Fixes: b6a2b971c0b0 ("net: sched: act_csum: remove dependency on rtnl lock") Fixes: 2142236b4584 ("net: sched: act_bpf: remove dependency on rtnl lock") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-14 18:46:16 +00:00
psample_group_num = nla_get_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]);
psample_group = psample_group_get(net, psample_group_num);
if (!psample_group) {
net/sched: act_sample: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action sample rate 1024 group 4 pass index 90 # tc actions replace action sample \ > rate 1024 group 4 goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action sample 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: sample rate 1/1024 group 4 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 8000000079966067 P4D 8000000079966067 PUD 7987b067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 5 Comm: kworker/0:0 Not tainted 5.0.0-rc4.gotochain_crash+ #536 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work 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:ffffbee60033fad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff99d7ae6e3b00 RCX: 00000000e555df9b RDX: 0000000000000000 RSI: 00000000b0352718 RDI: ffff99d7fda1fcf0 RBP: ffffbee60033fb70 R08: 0000000070731ab1 R09: 0000000000000400 R10: 0000000000000000 R11: ffff99d7ac733838 R12: ffff99d7f3c2be00 R13: ffff99d7f3c2be08 R14: 0000000000000001 R15: ffff99d7f3c2b600 FS: 0000000000000000(0000) GS:ffff99d7fda00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 00000000797de006 CR4: 00000000001606f0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_sample psample veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel mbcache jbd2 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device aesni_intel crypto_simd snd_pcm cryptd glue_helper snd_timer joydev snd pcspkr virtio_balloon i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect virtio_net sysimgblt fb_sys_fops net_failover ttm failover virtio_blk virtio_console drm ata_piix serio_raw crc32c_intel libata virtio_pci virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_sample_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 14:00:09 +00:00
err = -ENOMEM;
goto put_chain;
}
net: sched: always disable bh when taking tcf_lock Recently, ops->init() and ops->dump() of all actions were modified to always obtain tcf_lock when accessing private action state. Actions that don't depend on tcf_lock for synchronization with their data path use non-bh locking API. However, tcf_lock is also used to protect rate estimator stats in softirq context by timer callback. Change ops->init() and ops->dump() of all actions to disable bh when using tcf_lock to prevent deadlock reported by following lockdep warning: [ 105.470398] ================================ [ 105.475014] WARNING: inconsistent lock state [ 105.479628] 4.18.0-rc8+ #664 Not tainted [ 105.483897] -------------------------------- [ 105.488511] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. [ 105.494871] swapper/16/0 [HC0[0]:SC1[1]:HE1:SE0] takes: [ 105.500449] 00000000f86c012e (&(&p->tcfa_lock)->rlock){+.?.}, at: est_fetch_counters+0x3c/0xa0 [ 105.509696] {SOFTIRQ-ON-W} state was registered at: [ 105.514925] _raw_spin_lock+0x2c/0x40 [ 105.519022] tcf_bpf_init+0x579/0x820 [act_bpf] [ 105.523990] tcf_action_init_1+0x4e4/0x660 [ 105.528518] tcf_action_init+0x1ce/0x2d0 [ 105.532880] tcf_exts_validate+0x1d8/0x200 [ 105.537416] fl_change+0x55a/0x268b [cls_flower] [ 105.542469] tc_new_tfilter+0x748/0xa20 [ 105.546738] rtnetlink_rcv_msg+0x56a/0x6d0 [ 105.551268] netlink_rcv_skb+0x18d/0x200 [ 105.555628] netlink_unicast+0x2d0/0x370 [ 105.559990] netlink_sendmsg+0x3b9/0x6a0 [ 105.564349] sock_sendmsg+0x6b/0x80 [ 105.568271] ___sys_sendmsg+0x4a1/0x520 [ 105.572547] __sys_sendmsg+0xd7/0x150 [ 105.576655] do_syscall_64+0x72/0x2c0 [ 105.580757] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 105.586243] irq event stamp: 489296 [ 105.590084] hardirqs last enabled at (489296): [<ffffffffb507e639>] _raw_spin_unlock_irq+0x29/0x40 [ 105.599765] hardirqs last disabled at (489295): [<ffffffffb507e745>] _raw_spin_lock_irq+0x15/0x50 [ 105.609277] softirqs last enabled at (489292): [<ffffffffb413a6a3>] irq_enter+0x83/0xa0 [ 105.618001] softirqs last disabled at (489293): [<ffffffffb413a800>] irq_exit+0x140/0x190 [ 105.626813] other info that might help us debug this: [ 105.633976] Possible unsafe locking scenario: [ 105.640526] CPU0 [ 105.643325] ---- [ 105.646125] lock(&(&p->tcfa_lock)->rlock); [ 105.650747] <Interrupt> [ 105.653717] lock(&(&p->tcfa_lock)->rlock); [ 105.658514] *** DEADLOCK *** [ 105.665349] 1 lock held by swapper/16/0: [ 105.669629] #0: 00000000a640ad99 ((&est->timer)){+.-.}, at: call_timer_fn+0x10b/0x550 [ 105.678200] stack backtrace: [ 105.683194] CPU: 16 PID: 0 Comm: swapper/16 Not tainted 4.18.0-rc8+ #664 [ 105.690249] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 105.698626] Call Trace: [ 105.701421] <IRQ> [ 105.703791] dump_stack+0x92/0xeb [ 105.707461] print_usage_bug+0x336/0x34c [ 105.711744] mark_lock+0x7c9/0x980 [ 105.715500] ? print_shortest_lock_dependencies+0x2e0/0x2e0 [ 105.721424] ? check_usage_forwards+0x230/0x230 [ 105.726315] __lock_acquire+0x923/0x26f0 [ 105.730597] ? debug_show_all_locks+0x240/0x240 [ 105.735478] ? mark_lock+0x493/0x980 [ 105.739412] ? check_chain_key+0x140/0x1f0 [ 105.743861] ? __lock_acquire+0x836/0x26f0 [ 105.748323] ? lock_acquire+0x12e/0x290 [ 105.752516] lock_acquire+0x12e/0x290 [ 105.756539] ? est_fetch_counters+0x3c/0xa0 [ 105.761084] _raw_spin_lock+0x2c/0x40 [ 105.765099] ? est_fetch_counters+0x3c/0xa0 [ 105.769633] est_fetch_counters+0x3c/0xa0 [ 105.773995] est_timer+0x87/0x390 [ 105.777670] ? est_fetch_counters+0xa0/0xa0 [ 105.782210] ? lock_acquire+0x12e/0x290 [ 105.786410] call_timer_fn+0x161/0x550 [ 105.790512] ? est_fetch_counters+0xa0/0xa0 [ 105.795055] ? del_timer_sync+0xd0/0xd0 [ 105.799249] ? __lock_is_held+0x93/0x110 [ 105.803531] ? mark_held_locks+0x20/0xe0 [ 105.807813] ? _raw_spin_unlock_irq+0x29/0x40 [ 105.812525] ? est_fetch_counters+0xa0/0xa0 [ 105.817069] ? est_fetch_counters+0xa0/0xa0 [ 105.821610] run_timer_softirq+0x3c4/0x9f0 [ 105.826064] ? lock_acquire+0x12e/0x290 [ 105.830257] ? __bpf_trace_timer_class+0x10/0x10 [ 105.835237] ? __lock_is_held+0x25/0x110 [ 105.839517] __do_softirq+0x11d/0x7bf [ 105.843542] irq_exit+0x140/0x190 [ 105.847208] smp_apic_timer_interrupt+0xac/0x3b0 [ 105.852182] apic_timer_interrupt+0xf/0x20 [ 105.856628] </IRQ> [ 105.859081] RIP: 0010:cpuidle_enter_state+0xd8/0x4d0 [ 105.864395] Code: 46 ff 48 89 44 24 08 0f 1f 44 00 00 31 ff e8 cf ec 46 ff 80 7c 24 07 00 0f 85 1d 02 00 00 e8 9f 90 4b ff fb 66 0f 1f 44 00 00 <4c> 8b 6c 24 08 4d 29 fd 0f 80 36 03 00 00 4c 89 e8 48 ba cf f7 53 [ 105.884288] RSP: 0018:ffff8803ad94fd20 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 [ 105.892494] RAX: 0000000000000000 RBX: ffffe8fb300829c0 RCX: ffffffffb41e19e1 [ 105.899988] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8803ad9358ac [ 105.907503] RBP: ffffffffb6636300 R08: 0000000000000004 R09: 0000000000000000 [ 105.914997] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000004 [ 105.922487] R13: ffffffffb6636140 R14: ffffffffb66362d8 R15: 000000188d36091b [ 105.929988] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.935232] do_idle+0x28e/0x320 [ 105.938817] ? arch_cpu_idle_exit+0x40/0x40 [ 105.943361] ? mark_lock+0x8c1/0x980 [ 105.947295] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.952619] cpu_startup_entry+0xc2/0xd0 [ 105.956900] ? cpu_in_idle+0x20/0x20 [ 105.960830] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.966146] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.971391] start_secondary+0x2b5/0x360 [ 105.975669] ? set_cpu_sibling_map+0x1330/0x1330 [ 105.980654] secondary_startup_64+0xa5/0xb0 Taking tcf_lock in sample action with bh disabled causes lockdep to issue a warning regarding possible irq lock inversion dependency between tcf_lock, and psample_groups_lock that is taken when holding tcf_lock in sample init: [ 162.108959] Possible interrupt unsafe locking scenario: [ 162.116386] CPU0 CPU1 [ 162.121277] ---- ---- [ 162.126162] lock(psample_groups_lock); [ 162.130447] local_irq_disable(); [ 162.136772] lock(&(&p->tcfa_lock)->rlock); [ 162.143957] lock(psample_groups_lock); [ 162.150813] <Interrupt> [ 162.153808] lock(&(&p->tcfa_lock)->rlock); [ 162.158608] *** DEADLOCK *** In order to prevent potential lock inversion dependency between tcf_lock and psample_groups_lock, extract call to psample_group_get() from tcf_lock protected section in sample action init function. Fixes: 4e232818bd32 ("net: sched: act_mirred: remove dependency on rtnl lock") Fixes: 764e9a24480f ("net: sched: act_vlan: remove dependency on rtnl lock") Fixes: 729e01260989 ("net: sched: act_tunnel_key: remove dependency on rtnl lock") Fixes: d77284956656 ("net: sched: act_sample: remove dependency on rtnl lock") Fixes: e8917f437006 ("net: sched: act_gact: remove dependency on rtnl lock") Fixes: b6a2b971c0b0 ("net: sched: act_csum: remove dependency on rtnl lock") Fixes: 2142236b4584 ("net: sched: act_bpf: remove dependency on rtnl lock") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-14 18:46:16 +00:00
s = to_sample(*a);
spin_lock_bh(&s->tcf_lock);
net/sched: act_sample: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action sample rate 1024 group 4 pass index 90 # tc actions replace action sample \ > rate 1024 group 4 goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action sample 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: sample rate 1/1024 group 4 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 8000000079966067 P4D 8000000079966067 PUD 7987b067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 5 Comm: kworker/0:0 Not tainted 5.0.0-rc4.gotochain_crash+ #536 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work 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:ffffbee60033fad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff99d7ae6e3b00 RCX: 00000000e555df9b RDX: 0000000000000000 RSI: 00000000b0352718 RDI: ffff99d7fda1fcf0 RBP: ffffbee60033fb70 R08: 0000000070731ab1 R09: 0000000000000400 R10: 0000000000000000 R11: ffff99d7ac733838 R12: ffff99d7f3c2be00 R13: ffff99d7f3c2be08 R14: 0000000000000001 R15: ffff99d7f3c2b600 FS: 0000000000000000(0000) GS:ffff99d7fda00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 00000000797de006 CR4: 00000000001606f0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_sample psample veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel mbcache jbd2 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device aesni_intel crypto_simd snd_pcm cryptd glue_helper snd_timer joydev snd pcspkr virtio_balloon i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect virtio_net sysimgblt fb_sys_fops net_failover ttm failover virtio_blk virtio_console drm ata_piix serio_raw crc32c_intel libata virtio_pci virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_sample_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 14:00:09 +00:00
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
net/sched: act_sample: fix divide by zero in the traffic path the control path of 'sample' action does not validate the value of 'rate' provided by the user, but then it uses it as divisor in the traffic path. Validate it in tcf_sample_init(), and return -EINVAL with a proper extack message in case that value is zero, to fix a splat with the script below: # tc f a dev test0 egress matchall action sample rate 0 group 1 index 2 # tc -s a s action sample total acts 1 action order 0: sample rate 1/0 group 1 pipe index 2 ref 1 bind 1 installed 19 sec used 19 sec Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 # ping 192.0.2.1 -I test0 -c1 -q divide error: 0000 [#1] SMP PTI CPU: 1 PID: 6192 Comm: ping Not tainted 5.1.0-rc2.diag2+ #591 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_sample_act+0x9e/0x1e0 [act_sample] Code: 6a f1 85 c0 74 0d 80 3d 83 1a 00 00 00 0f 84 9c 00 00 00 4d 85 e4 0f 84 85 00 00 00 e8 9b d7 9c f1 44 8b 8b e0 00 00 00 31 d2 <41> f7 f1 85 d2 75 70 f6 85 83 00 00 00 10 48 8b 45 10 8b 88 08 01 RSP: 0018:ffffae320190ba30 EFLAGS: 00010246 RAX: 00000000b0677d21 RBX: ffff8af1ed9ec000 RCX: 0000000059a9fe49 RDX: 0000000000000000 RSI: 000000000c7e33b7 RDI: ffff8af23daa0af0 RBP: ffff8af1ee11b200 R08: 0000000074fcaf7e R09: 0000000000000000 R10: 0000000000000050 R11: ffffffffb3088680 R12: ffff8af232307f80 R13: 0000000000000003 R14: ffff8af1ed9ec000 R15: 0000000000000000 FS: 00007fe9c6d2f740(0000) GS:ffff8af23da80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fff6772f000 CR3: 00000000746a2004 CR4: 00000000001606e0 Call Trace: tcf_action_exec+0x7c/0x1c0 tcf_classify+0x57/0x160 __dev_queue_xmit+0x3dc/0xd10 ip_finish_output2+0x257/0x6d0 ip_output+0x75/0x280 ip_send_skb+0x15/0x40 raw_sendmsg+0xae3/0x1410 sock_sendmsg+0x36/0x40 __sys_sendto+0x10e/0x140 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x60/0x210 entry_SYSCALL_64_after_hwframe+0x49/0xbe [...] Kernel panic - not syncing: Fatal exception in interrupt Add a TDC selftest to document that 'rate' is now being validated. Reported-by: Matteo Croce <mcroce@redhat.com> Fixes: 5c5670fae430 ("net/sched: Introduce sample tc action") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Yotam Gigi <yotam.gi@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-04 10:31:35 +00:00
s->rate = rate;
net: sched: always disable bh when taking tcf_lock Recently, ops->init() and ops->dump() of all actions were modified to always obtain tcf_lock when accessing private action state. Actions that don't depend on tcf_lock for synchronization with their data path use non-bh locking API. However, tcf_lock is also used to protect rate estimator stats in softirq context by timer callback. Change ops->init() and ops->dump() of all actions to disable bh when using tcf_lock to prevent deadlock reported by following lockdep warning: [ 105.470398] ================================ [ 105.475014] WARNING: inconsistent lock state [ 105.479628] 4.18.0-rc8+ #664 Not tainted [ 105.483897] -------------------------------- [ 105.488511] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. [ 105.494871] swapper/16/0 [HC0[0]:SC1[1]:HE1:SE0] takes: [ 105.500449] 00000000f86c012e (&(&p->tcfa_lock)->rlock){+.?.}, at: est_fetch_counters+0x3c/0xa0 [ 105.509696] {SOFTIRQ-ON-W} state was registered at: [ 105.514925] _raw_spin_lock+0x2c/0x40 [ 105.519022] tcf_bpf_init+0x579/0x820 [act_bpf] [ 105.523990] tcf_action_init_1+0x4e4/0x660 [ 105.528518] tcf_action_init+0x1ce/0x2d0 [ 105.532880] tcf_exts_validate+0x1d8/0x200 [ 105.537416] fl_change+0x55a/0x268b [cls_flower] [ 105.542469] tc_new_tfilter+0x748/0xa20 [ 105.546738] rtnetlink_rcv_msg+0x56a/0x6d0 [ 105.551268] netlink_rcv_skb+0x18d/0x200 [ 105.555628] netlink_unicast+0x2d0/0x370 [ 105.559990] netlink_sendmsg+0x3b9/0x6a0 [ 105.564349] sock_sendmsg+0x6b/0x80 [ 105.568271] ___sys_sendmsg+0x4a1/0x520 [ 105.572547] __sys_sendmsg+0xd7/0x150 [ 105.576655] do_syscall_64+0x72/0x2c0 [ 105.580757] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 105.586243] irq event stamp: 489296 [ 105.590084] hardirqs last enabled at (489296): [<ffffffffb507e639>] _raw_spin_unlock_irq+0x29/0x40 [ 105.599765] hardirqs last disabled at (489295): [<ffffffffb507e745>] _raw_spin_lock_irq+0x15/0x50 [ 105.609277] softirqs last enabled at (489292): [<ffffffffb413a6a3>] irq_enter+0x83/0xa0 [ 105.618001] softirqs last disabled at (489293): [<ffffffffb413a800>] irq_exit+0x140/0x190 [ 105.626813] other info that might help us debug this: [ 105.633976] Possible unsafe locking scenario: [ 105.640526] CPU0 [ 105.643325] ---- [ 105.646125] lock(&(&p->tcfa_lock)->rlock); [ 105.650747] <Interrupt> [ 105.653717] lock(&(&p->tcfa_lock)->rlock); [ 105.658514] *** DEADLOCK *** [ 105.665349] 1 lock held by swapper/16/0: [ 105.669629] #0: 00000000a640ad99 ((&est->timer)){+.-.}, at: call_timer_fn+0x10b/0x550 [ 105.678200] stack backtrace: [ 105.683194] CPU: 16 PID: 0 Comm: swapper/16 Not tainted 4.18.0-rc8+ #664 [ 105.690249] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 105.698626] Call Trace: [ 105.701421] <IRQ> [ 105.703791] dump_stack+0x92/0xeb [ 105.707461] print_usage_bug+0x336/0x34c [ 105.711744] mark_lock+0x7c9/0x980 [ 105.715500] ? print_shortest_lock_dependencies+0x2e0/0x2e0 [ 105.721424] ? check_usage_forwards+0x230/0x230 [ 105.726315] __lock_acquire+0x923/0x26f0 [ 105.730597] ? debug_show_all_locks+0x240/0x240 [ 105.735478] ? mark_lock+0x493/0x980 [ 105.739412] ? check_chain_key+0x140/0x1f0 [ 105.743861] ? __lock_acquire+0x836/0x26f0 [ 105.748323] ? lock_acquire+0x12e/0x290 [ 105.752516] lock_acquire+0x12e/0x290 [ 105.756539] ? est_fetch_counters+0x3c/0xa0 [ 105.761084] _raw_spin_lock+0x2c/0x40 [ 105.765099] ? est_fetch_counters+0x3c/0xa0 [ 105.769633] est_fetch_counters+0x3c/0xa0 [ 105.773995] est_timer+0x87/0x390 [ 105.777670] ? est_fetch_counters+0xa0/0xa0 [ 105.782210] ? lock_acquire+0x12e/0x290 [ 105.786410] call_timer_fn+0x161/0x550 [ 105.790512] ? est_fetch_counters+0xa0/0xa0 [ 105.795055] ? del_timer_sync+0xd0/0xd0 [ 105.799249] ? __lock_is_held+0x93/0x110 [ 105.803531] ? mark_held_locks+0x20/0xe0 [ 105.807813] ? _raw_spin_unlock_irq+0x29/0x40 [ 105.812525] ? est_fetch_counters+0xa0/0xa0 [ 105.817069] ? est_fetch_counters+0xa0/0xa0 [ 105.821610] run_timer_softirq+0x3c4/0x9f0 [ 105.826064] ? lock_acquire+0x12e/0x290 [ 105.830257] ? __bpf_trace_timer_class+0x10/0x10 [ 105.835237] ? __lock_is_held+0x25/0x110 [ 105.839517] __do_softirq+0x11d/0x7bf [ 105.843542] irq_exit+0x140/0x190 [ 105.847208] smp_apic_timer_interrupt+0xac/0x3b0 [ 105.852182] apic_timer_interrupt+0xf/0x20 [ 105.856628] </IRQ> [ 105.859081] RIP: 0010:cpuidle_enter_state+0xd8/0x4d0 [ 105.864395] Code: 46 ff 48 89 44 24 08 0f 1f 44 00 00 31 ff e8 cf ec 46 ff 80 7c 24 07 00 0f 85 1d 02 00 00 e8 9f 90 4b ff fb 66 0f 1f 44 00 00 <4c> 8b 6c 24 08 4d 29 fd 0f 80 36 03 00 00 4c 89 e8 48 ba cf f7 53 [ 105.884288] RSP: 0018:ffff8803ad94fd20 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 [ 105.892494] RAX: 0000000000000000 RBX: ffffe8fb300829c0 RCX: ffffffffb41e19e1 [ 105.899988] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8803ad9358ac [ 105.907503] RBP: ffffffffb6636300 R08: 0000000000000004 R09: 0000000000000000 [ 105.914997] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000004 [ 105.922487] R13: ffffffffb6636140 R14: ffffffffb66362d8 R15: 000000188d36091b [ 105.929988] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.935232] do_idle+0x28e/0x320 [ 105.938817] ? arch_cpu_idle_exit+0x40/0x40 [ 105.943361] ? mark_lock+0x8c1/0x980 [ 105.947295] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.952619] cpu_startup_entry+0xc2/0xd0 [ 105.956900] ? cpu_in_idle+0x20/0x20 [ 105.960830] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.966146] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.971391] start_secondary+0x2b5/0x360 [ 105.975669] ? set_cpu_sibling_map+0x1330/0x1330 [ 105.980654] secondary_startup_64+0xa5/0xb0 Taking tcf_lock in sample action with bh disabled causes lockdep to issue a warning regarding possible irq lock inversion dependency between tcf_lock, and psample_groups_lock that is taken when holding tcf_lock in sample init: [ 162.108959] Possible interrupt unsafe locking scenario: [ 162.116386] CPU0 CPU1 [ 162.121277] ---- ---- [ 162.126162] lock(psample_groups_lock); [ 162.130447] local_irq_disable(); [ 162.136772] lock(&(&p->tcfa_lock)->rlock); [ 162.143957] lock(psample_groups_lock); [ 162.150813] <Interrupt> [ 162.153808] lock(&(&p->tcfa_lock)->rlock); [ 162.158608] *** DEADLOCK *** In order to prevent potential lock inversion dependency between tcf_lock and psample_groups_lock, extract call to psample_group_get() from tcf_lock protected section in sample action init function. Fixes: 4e232818bd32 ("net: sched: act_mirred: remove dependency on rtnl lock") Fixes: 764e9a24480f ("net: sched: act_vlan: remove dependency on rtnl lock") Fixes: 729e01260989 ("net: sched: act_tunnel_key: remove dependency on rtnl lock") Fixes: d77284956656 ("net: sched: act_sample: remove dependency on rtnl lock") Fixes: e8917f437006 ("net: sched: act_gact: remove dependency on rtnl lock") Fixes: b6a2b971c0b0 ("net: sched: act_csum: remove dependency on rtnl lock") Fixes: 2142236b4584 ("net: sched: act_bpf: remove dependency on rtnl lock") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-14 18:46:16 +00:00
s->psample_group_num = psample_group_num;
RCU_INIT_POINTER(s->psample_group, psample_group);
if (tb[TCA_SAMPLE_TRUNC_SIZE]) {
s->truncate = true;
s->trunc_size = nla_get_u32(tb[TCA_SAMPLE_TRUNC_SIZE]);
}
net: sched: always disable bh when taking tcf_lock Recently, ops->init() and ops->dump() of all actions were modified to always obtain tcf_lock when accessing private action state. Actions that don't depend on tcf_lock for synchronization with their data path use non-bh locking API. However, tcf_lock is also used to protect rate estimator stats in softirq context by timer callback. Change ops->init() and ops->dump() of all actions to disable bh when using tcf_lock to prevent deadlock reported by following lockdep warning: [ 105.470398] ================================ [ 105.475014] WARNING: inconsistent lock state [ 105.479628] 4.18.0-rc8+ #664 Not tainted [ 105.483897] -------------------------------- [ 105.488511] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. [ 105.494871] swapper/16/0 [HC0[0]:SC1[1]:HE1:SE0] takes: [ 105.500449] 00000000f86c012e (&(&p->tcfa_lock)->rlock){+.?.}, at: est_fetch_counters+0x3c/0xa0 [ 105.509696] {SOFTIRQ-ON-W} state was registered at: [ 105.514925] _raw_spin_lock+0x2c/0x40 [ 105.519022] tcf_bpf_init+0x579/0x820 [act_bpf] [ 105.523990] tcf_action_init_1+0x4e4/0x660 [ 105.528518] tcf_action_init+0x1ce/0x2d0 [ 105.532880] tcf_exts_validate+0x1d8/0x200 [ 105.537416] fl_change+0x55a/0x268b [cls_flower] [ 105.542469] tc_new_tfilter+0x748/0xa20 [ 105.546738] rtnetlink_rcv_msg+0x56a/0x6d0 [ 105.551268] netlink_rcv_skb+0x18d/0x200 [ 105.555628] netlink_unicast+0x2d0/0x370 [ 105.559990] netlink_sendmsg+0x3b9/0x6a0 [ 105.564349] sock_sendmsg+0x6b/0x80 [ 105.568271] ___sys_sendmsg+0x4a1/0x520 [ 105.572547] __sys_sendmsg+0xd7/0x150 [ 105.576655] do_syscall_64+0x72/0x2c0 [ 105.580757] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 105.586243] irq event stamp: 489296 [ 105.590084] hardirqs last enabled at (489296): [<ffffffffb507e639>] _raw_spin_unlock_irq+0x29/0x40 [ 105.599765] hardirqs last disabled at (489295): [<ffffffffb507e745>] _raw_spin_lock_irq+0x15/0x50 [ 105.609277] softirqs last enabled at (489292): [<ffffffffb413a6a3>] irq_enter+0x83/0xa0 [ 105.618001] softirqs last disabled at (489293): [<ffffffffb413a800>] irq_exit+0x140/0x190 [ 105.626813] other info that might help us debug this: [ 105.633976] Possible unsafe locking scenario: [ 105.640526] CPU0 [ 105.643325] ---- [ 105.646125] lock(&(&p->tcfa_lock)->rlock); [ 105.650747] <Interrupt> [ 105.653717] lock(&(&p->tcfa_lock)->rlock); [ 105.658514] *** DEADLOCK *** [ 105.665349] 1 lock held by swapper/16/0: [ 105.669629] #0: 00000000a640ad99 ((&est->timer)){+.-.}, at: call_timer_fn+0x10b/0x550 [ 105.678200] stack backtrace: [ 105.683194] CPU: 16 PID: 0 Comm: swapper/16 Not tainted 4.18.0-rc8+ #664 [ 105.690249] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 105.698626] Call Trace: [ 105.701421] <IRQ> [ 105.703791] dump_stack+0x92/0xeb [ 105.707461] print_usage_bug+0x336/0x34c [ 105.711744] mark_lock+0x7c9/0x980 [ 105.715500] ? print_shortest_lock_dependencies+0x2e0/0x2e0 [ 105.721424] ? check_usage_forwards+0x230/0x230 [ 105.726315] __lock_acquire+0x923/0x26f0 [ 105.730597] ? debug_show_all_locks+0x240/0x240 [ 105.735478] ? mark_lock+0x493/0x980 [ 105.739412] ? check_chain_key+0x140/0x1f0 [ 105.743861] ? __lock_acquire+0x836/0x26f0 [ 105.748323] ? lock_acquire+0x12e/0x290 [ 105.752516] lock_acquire+0x12e/0x290 [ 105.756539] ? est_fetch_counters+0x3c/0xa0 [ 105.761084] _raw_spin_lock+0x2c/0x40 [ 105.765099] ? est_fetch_counters+0x3c/0xa0 [ 105.769633] est_fetch_counters+0x3c/0xa0 [ 105.773995] est_timer+0x87/0x390 [ 105.777670] ? est_fetch_counters+0xa0/0xa0 [ 105.782210] ? lock_acquire+0x12e/0x290 [ 105.786410] call_timer_fn+0x161/0x550 [ 105.790512] ? est_fetch_counters+0xa0/0xa0 [ 105.795055] ? del_timer_sync+0xd0/0xd0 [ 105.799249] ? __lock_is_held+0x93/0x110 [ 105.803531] ? mark_held_locks+0x20/0xe0 [ 105.807813] ? _raw_spin_unlock_irq+0x29/0x40 [ 105.812525] ? est_fetch_counters+0xa0/0xa0 [ 105.817069] ? est_fetch_counters+0xa0/0xa0 [ 105.821610] run_timer_softirq+0x3c4/0x9f0 [ 105.826064] ? lock_acquire+0x12e/0x290 [ 105.830257] ? __bpf_trace_timer_class+0x10/0x10 [ 105.835237] ? __lock_is_held+0x25/0x110 [ 105.839517] __do_softirq+0x11d/0x7bf [ 105.843542] irq_exit+0x140/0x190 [ 105.847208] smp_apic_timer_interrupt+0xac/0x3b0 [ 105.852182] apic_timer_interrupt+0xf/0x20 [ 105.856628] </IRQ> [ 105.859081] RIP: 0010:cpuidle_enter_state+0xd8/0x4d0 [ 105.864395] Code: 46 ff 48 89 44 24 08 0f 1f 44 00 00 31 ff e8 cf ec 46 ff 80 7c 24 07 00 0f 85 1d 02 00 00 e8 9f 90 4b ff fb 66 0f 1f 44 00 00 <4c> 8b 6c 24 08 4d 29 fd 0f 80 36 03 00 00 4c 89 e8 48 ba cf f7 53 [ 105.884288] RSP: 0018:ffff8803ad94fd20 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 [ 105.892494] RAX: 0000000000000000 RBX: ffffe8fb300829c0 RCX: ffffffffb41e19e1 [ 105.899988] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8803ad9358ac [ 105.907503] RBP: ffffffffb6636300 R08: 0000000000000004 R09: 0000000000000000 [ 105.914997] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000004 [ 105.922487] R13: ffffffffb6636140 R14: ffffffffb66362d8 R15: 000000188d36091b [ 105.929988] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.935232] do_idle+0x28e/0x320 [ 105.938817] ? arch_cpu_idle_exit+0x40/0x40 [ 105.943361] ? mark_lock+0x8c1/0x980 [ 105.947295] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.952619] cpu_startup_entry+0xc2/0xd0 [ 105.956900] ? cpu_in_idle+0x20/0x20 [ 105.960830] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.966146] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.971391] start_secondary+0x2b5/0x360 [ 105.975669] ? set_cpu_sibling_map+0x1330/0x1330 [ 105.980654] secondary_startup_64+0xa5/0xb0 Taking tcf_lock in sample action with bh disabled causes lockdep to issue a warning regarding possible irq lock inversion dependency between tcf_lock, and psample_groups_lock that is taken when holding tcf_lock in sample init: [ 162.108959] Possible interrupt unsafe locking scenario: [ 162.116386] CPU0 CPU1 [ 162.121277] ---- ---- [ 162.126162] lock(psample_groups_lock); [ 162.130447] local_irq_disable(); [ 162.136772] lock(&(&p->tcfa_lock)->rlock); [ 162.143957] lock(psample_groups_lock); [ 162.150813] <Interrupt> [ 162.153808] lock(&(&p->tcfa_lock)->rlock); [ 162.158608] *** DEADLOCK *** In order to prevent potential lock inversion dependency between tcf_lock and psample_groups_lock, extract call to psample_group_get() from tcf_lock protected section in sample action init function. Fixes: 4e232818bd32 ("net: sched: act_mirred: remove dependency on rtnl lock") Fixes: 764e9a24480f ("net: sched: act_vlan: remove dependency on rtnl lock") Fixes: 729e01260989 ("net: sched: act_tunnel_key: remove dependency on rtnl lock") Fixes: d77284956656 ("net: sched: act_sample: remove dependency on rtnl lock") Fixes: e8917f437006 ("net: sched: act_gact: remove dependency on rtnl lock") Fixes: b6a2b971c0b0 ("net: sched: act_csum: remove dependency on rtnl lock") Fixes: 2142236b4584 ("net: sched: act_bpf: remove dependency on rtnl lock") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-14 18:46:16 +00:00
spin_unlock_bh(&s->tcf_lock);
net/sched: act_sample: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action sample rate 1024 group 4 pass index 90 # tc actions replace action sample \ > rate 1024 group 4 goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action sample 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: sample rate 1/1024 group 4 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 8000000079966067 P4D 8000000079966067 PUD 7987b067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 5 Comm: kworker/0:0 Not tainted 5.0.0-rc4.gotochain_crash+ #536 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work 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:ffffbee60033fad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff99d7ae6e3b00 RCX: 00000000e555df9b RDX: 0000000000000000 RSI: 00000000b0352718 RDI: ffff99d7fda1fcf0 RBP: ffffbee60033fb70 R08: 0000000070731ab1 R09: 0000000000000400 R10: 0000000000000000 R11: ffff99d7ac733838 R12: ffff99d7f3c2be00 R13: ffff99d7f3c2be08 R14: 0000000000000001 R15: ffff99d7f3c2b600 FS: 0000000000000000(0000) GS:ffff99d7fda00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 00000000797de006 CR4: 00000000001606f0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_sample psample veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel mbcache jbd2 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device aesni_intel crypto_simd snd_pcm cryptd glue_helper snd_timer joydev snd pcspkr virtio_balloon i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect virtio_net sysimgblt fb_sys_fops net_failover ttm failover virtio_blk virtio_console drm ata_piix serio_raw crc32c_intel libata virtio_pci virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_sample_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 14:00:09 +00:00
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_sample: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action sample rate 1024 group 4 pass index 90 # tc actions replace action sample \ > rate 1024 group 4 goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action sample 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: sample rate 1/1024 group 4 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 8000000079966067 P4D 8000000079966067 PUD 7987b067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 5 Comm: kworker/0:0 Not tainted 5.0.0-rc4.gotochain_crash+ #536 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work 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:ffffbee60033fad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff99d7ae6e3b00 RCX: 00000000e555df9b RDX: 0000000000000000 RSI: 00000000b0352718 RDI: ffff99d7fda1fcf0 RBP: ffffbee60033fb70 R08: 0000000070731ab1 R09: 0000000000000400 R10: 0000000000000000 R11: ffff99d7ac733838 R12: ffff99d7f3c2be00 R13: ffff99d7f3c2be08 R14: 0000000000000001 R15: ffff99d7f3c2b600 FS: 0000000000000000(0000) GS:ffff99d7fda00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 00000000797de006 CR4: 00000000001606f0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_sample psample veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel mbcache jbd2 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device aesni_intel crypto_simd snd_pcm cryptd glue_helper snd_timer joydev snd pcspkr virtio_balloon i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect virtio_net sysimgblt fb_sys_fops net_failover ttm failover virtio_blk virtio_console drm ata_piix serio_raw crc32c_intel libata virtio_pci virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_sample_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 14:00:09 +00:00
put_chain:
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
release_idr:
tcf_idr_release(*a, bind);
return err;
}
static void tcf_sample_cleanup(struct tc_action *a)
{
struct tcf_sample *s = to_sample(a);
struct psample_group *psample_group;
/* last reference to action, no need to lock */
psample_group = rcu_dereference_protected(s->psample_group, 1);
RCU_INIT_POINTER(s->psample_group, NULL);
net/sched: fix NULL dereference in the error path of tcf_sample_init() when the following command # tc action add action sample rate 100 group 100 index 100 is run for the first time, and psample_group_get(100) fails to create a new group, tcf_sample_cleanup() calls psample_group_put(NULL), thus causing the following error: BUG: unable to handle kernel NULL pointer dereference at 000000000000001c IP: psample_group_put+0x15/0x71 [psample] PGD 8000000075775067 P4D 8000000075775067 PUD 7453c067 PMD 0 Oops: 0002 [#1] SMP PTI Modules linked in: act_sample(E) psample ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hda_core mbcache jbd2 crct10dif_pclmul snd_hwdep crc32_pclmul snd_seq ghash_clmulni_intel pcbc snd_seq_device snd_pcm aesni_intel crypto_simd snd_timer glue_helper snd cryptd joydev pcspkr i2c_piix4 soundcore virtio_balloon nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm drm virtio_net ata_piix virtio_console virtio_blk libata serio_raw crc32c_intel virtio_pci i2c_core virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_tunnel_key] CPU: 2 PID: 5740 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:psample_group_put+0x15/0x71 [psample] RSP: 0018:ffffb8a80032f7d0 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000024 RDX: 0000000000000001 RSI: 0000000000000000 RDI: ffffffffc06d93c0 RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000044 R10: 00000000bd003000 R11: ffff979fba04aa59 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: ffff979fbba3f22c FS: 00007f7638112740(0000) GS:ffff979fbfd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000000001c CR3: 00000000734ea001 CR4: 00000000001606e0 Call Trace: __tcf_idr_release+0x79/0xf0 tcf_sample_init+0x125/0x1d0 [act_sample] tcf_action_init_1+0x2cc/0x430 tcf_action_init+0xd3/0x1b0 tc_ctl_action+0x18b/0x240 rtnetlink_rcv_msg+0x29c/0x310 ? _cond_resched+0x15/0x30 ? __kmalloc_node_track_caller+0x1b9/0x270 ? rtnl_calcit.isra.28+0x100/0x100 netlink_rcv_skb+0xd2/0x110 netlink_unicast+0x17c/0x230 netlink_sendmsg+0x2cd/0x3c0 sock_sendmsg+0x30/0x40 ___sys_sendmsg+0x27a/0x290 ? filemap_map_pages+0x34a/0x3a0 ? __handle_mm_fault+0xbfd/0xe20 __sys_sendmsg+0x51/0x90 do_syscall_64+0x6e/0x1a0 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 RIP: 0033:0x7f7637523ba0 RSP: 002b:00007fff0473ef58 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007fff0473f080 RCX: 00007f7637523ba0 RDX: 0000000000000000 RSI: 00007fff0473efd0 RDI: 0000000000000003 RBP: 000000005aaaac80 R08: 0000000000000002 R09: 0000000000000000 R10: 00007fff0473e9e0 R11: 0000000000000246 R12: 0000000000000000 R13: 00007fff0473f094 R14: 0000000000000001 R15: 0000000000669f60 Code: be 02 00 00 00 48 89 df e8 a9 fe ff ff e9 7c ff ff ff 0f 1f 40 00 0f 1f 44 00 00 53 48 89 fb 48 c7 c7 c0 93 6d c0 e8 db 20 8c ef <83> 6b 1c 01 74 10 48 c7 c7 c0 93 6d c0 ff 14 25 e8 83 83 b0 5b RIP: psample_group_put+0x15/0x71 [psample] RSP: ffffb8a80032f7d0 CR2: 000000000000001c Fix it in tcf_sample_cleanup(), ensuring that calls to psample_group_put(p) are done only when p is not NULL. Fixes: cadb9c9fdbc6 ("net/sched: act_sample: Fix error path in init") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-15 23:00:56 +00:00
if (psample_group)
psample_group_put(psample_group);
}
static bool tcf_sample_dev_ok_push(struct net_device *dev)
{
switch (dev->type) {
case ARPHRD_TUNNEL:
case ARPHRD_TUNNEL6:
case ARPHRD_SIT:
case ARPHRD_IPGRE:
case ARPHRD_VOID:
case ARPHRD_NONE:
return false;
default:
return true;
}
}
static int tcf_sample_act(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
struct tcf_sample *s = to_sample(a);
struct psample_group *psample_group;
int retval;
int size;
int iif;
int oif;
tcf_lastuse_update(&s->tcf_tm);
bstats_cpu_update(this_cpu_ptr(s->common.cpu_bstats), skb);
retval = READ_ONCE(s->tcf_action);
psample_group = rcu_dereference_bh(s->psample_group);
/* randomly sample packets according to rate */
if (psample_group && (prandom_u32() % s->rate == 0)) {
if (!skb_at_tc_ingress(skb)) {
iif = skb->skb_iif;
oif = skb->dev->ifindex;
} else {
iif = skb->dev->ifindex;
oif = 0;
}
/* on ingress, the mac header gets popped, so push it back */
if (skb_at_tc_ingress(skb) && tcf_sample_dev_ok_push(skb->dev))
skb_push(skb, skb->mac_len);
size = s->truncate ? s->trunc_size : skb->len;
psample_sample_packet(psample_group, skb, size, iif, oif,
s->rate);
if (skb_at_tc_ingress(skb) && tcf_sample_dev_ok_push(skb->dev))
skb_pull(skb, skb->mac_len);
}
return retval;
}
static int tcf_sample_dump(struct sk_buff *skb, struct tc_action *a,
int bind, int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_sample *s = to_sample(a);
struct tc_sample opt = {
.index = s->tcf_index,
.refcnt = refcount_read(&s->tcf_refcnt) - ref,
.bindcnt = atomic_read(&s->tcf_bindcnt) - bind,
};
struct tcf_t t;
net: sched: always disable bh when taking tcf_lock Recently, ops->init() and ops->dump() of all actions were modified to always obtain tcf_lock when accessing private action state. Actions that don't depend on tcf_lock for synchronization with their data path use non-bh locking API. However, tcf_lock is also used to protect rate estimator stats in softirq context by timer callback. Change ops->init() and ops->dump() of all actions to disable bh when using tcf_lock to prevent deadlock reported by following lockdep warning: [ 105.470398] ================================ [ 105.475014] WARNING: inconsistent lock state [ 105.479628] 4.18.0-rc8+ #664 Not tainted [ 105.483897] -------------------------------- [ 105.488511] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. [ 105.494871] swapper/16/0 [HC0[0]:SC1[1]:HE1:SE0] takes: [ 105.500449] 00000000f86c012e (&(&p->tcfa_lock)->rlock){+.?.}, at: est_fetch_counters+0x3c/0xa0 [ 105.509696] {SOFTIRQ-ON-W} state was registered at: [ 105.514925] _raw_spin_lock+0x2c/0x40 [ 105.519022] tcf_bpf_init+0x579/0x820 [act_bpf] [ 105.523990] tcf_action_init_1+0x4e4/0x660 [ 105.528518] tcf_action_init+0x1ce/0x2d0 [ 105.532880] tcf_exts_validate+0x1d8/0x200 [ 105.537416] fl_change+0x55a/0x268b [cls_flower] [ 105.542469] tc_new_tfilter+0x748/0xa20 [ 105.546738] rtnetlink_rcv_msg+0x56a/0x6d0 [ 105.551268] netlink_rcv_skb+0x18d/0x200 [ 105.555628] netlink_unicast+0x2d0/0x370 [ 105.559990] netlink_sendmsg+0x3b9/0x6a0 [ 105.564349] sock_sendmsg+0x6b/0x80 [ 105.568271] ___sys_sendmsg+0x4a1/0x520 [ 105.572547] __sys_sendmsg+0xd7/0x150 [ 105.576655] do_syscall_64+0x72/0x2c0 [ 105.580757] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 105.586243] irq event stamp: 489296 [ 105.590084] hardirqs last enabled at (489296): [<ffffffffb507e639>] _raw_spin_unlock_irq+0x29/0x40 [ 105.599765] hardirqs last disabled at (489295): [<ffffffffb507e745>] _raw_spin_lock_irq+0x15/0x50 [ 105.609277] softirqs last enabled at (489292): [<ffffffffb413a6a3>] irq_enter+0x83/0xa0 [ 105.618001] softirqs last disabled at (489293): [<ffffffffb413a800>] irq_exit+0x140/0x190 [ 105.626813] other info that might help us debug this: [ 105.633976] Possible unsafe locking scenario: [ 105.640526] CPU0 [ 105.643325] ---- [ 105.646125] lock(&(&p->tcfa_lock)->rlock); [ 105.650747] <Interrupt> [ 105.653717] lock(&(&p->tcfa_lock)->rlock); [ 105.658514] *** DEADLOCK *** [ 105.665349] 1 lock held by swapper/16/0: [ 105.669629] #0: 00000000a640ad99 ((&est->timer)){+.-.}, at: call_timer_fn+0x10b/0x550 [ 105.678200] stack backtrace: [ 105.683194] CPU: 16 PID: 0 Comm: swapper/16 Not tainted 4.18.0-rc8+ #664 [ 105.690249] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 105.698626] Call Trace: [ 105.701421] <IRQ> [ 105.703791] dump_stack+0x92/0xeb [ 105.707461] print_usage_bug+0x336/0x34c [ 105.711744] mark_lock+0x7c9/0x980 [ 105.715500] ? print_shortest_lock_dependencies+0x2e0/0x2e0 [ 105.721424] ? check_usage_forwards+0x230/0x230 [ 105.726315] __lock_acquire+0x923/0x26f0 [ 105.730597] ? debug_show_all_locks+0x240/0x240 [ 105.735478] ? mark_lock+0x493/0x980 [ 105.739412] ? check_chain_key+0x140/0x1f0 [ 105.743861] ? __lock_acquire+0x836/0x26f0 [ 105.748323] ? lock_acquire+0x12e/0x290 [ 105.752516] lock_acquire+0x12e/0x290 [ 105.756539] ? est_fetch_counters+0x3c/0xa0 [ 105.761084] _raw_spin_lock+0x2c/0x40 [ 105.765099] ? est_fetch_counters+0x3c/0xa0 [ 105.769633] est_fetch_counters+0x3c/0xa0 [ 105.773995] est_timer+0x87/0x390 [ 105.777670] ? est_fetch_counters+0xa0/0xa0 [ 105.782210] ? lock_acquire+0x12e/0x290 [ 105.786410] call_timer_fn+0x161/0x550 [ 105.790512] ? est_fetch_counters+0xa0/0xa0 [ 105.795055] ? del_timer_sync+0xd0/0xd0 [ 105.799249] ? __lock_is_held+0x93/0x110 [ 105.803531] ? mark_held_locks+0x20/0xe0 [ 105.807813] ? _raw_spin_unlock_irq+0x29/0x40 [ 105.812525] ? est_fetch_counters+0xa0/0xa0 [ 105.817069] ? est_fetch_counters+0xa0/0xa0 [ 105.821610] run_timer_softirq+0x3c4/0x9f0 [ 105.826064] ? lock_acquire+0x12e/0x290 [ 105.830257] ? __bpf_trace_timer_class+0x10/0x10 [ 105.835237] ? __lock_is_held+0x25/0x110 [ 105.839517] __do_softirq+0x11d/0x7bf [ 105.843542] irq_exit+0x140/0x190 [ 105.847208] smp_apic_timer_interrupt+0xac/0x3b0 [ 105.852182] apic_timer_interrupt+0xf/0x20 [ 105.856628] </IRQ> [ 105.859081] RIP: 0010:cpuidle_enter_state+0xd8/0x4d0 [ 105.864395] Code: 46 ff 48 89 44 24 08 0f 1f 44 00 00 31 ff e8 cf ec 46 ff 80 7c 24 07 00 0f 85 1d 02 00 00 e8 9f 90 4b ff fb 66 0f 1f 44 00 00 <4c> 8b 6c 24 08 4d 29 fd 0f 80 36 03 00 00 4c 89 e8 48 ba cf f7 53 [ 105.884288] RSP: 0018:ffff8803ad94fd20 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 [ 105.892494] RAX: 0000000000000000 RBX: ffffe8fb300829c0 RCX: ffffffffb41e19e1 [ 105.899988] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8803ad9358ac [ 105.907503] RBP: ffffffffb6636300 R08: 0000000000000004 R09: 0000000000000000 [ 105.914997] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000004 [ 105.922487] R13: ffffffffb6636140 R14: ffffffffb66362d8 R15: 000000188d36091b [ 105.929988] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.935232] do_idle+0x28e/0x320 [ 105.938817] ? arch_cpu_idle_exit+0x40/0x40 [ 105.943361] ? mark_lock+0x8c1/0x980 [ 105.947295] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.952619] cpu_startup_entry+0xc2/0xd0 [ 105.956900] ? cpu_in_idle+0x20/0x20 [ 105.960830] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.966146] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.971391] start_secondary+0x2b5/0x360 [ 105.975669] ? set_cpu_sibling_map+0x1330/0x1330 [ 105.980654] secondary_startup_64+0xa5/0xb0 Taking tcf_lock in sample action with bh disabled causes lockdep to issue a warning regarding possible irq lock inversion dependency between tcf_lock, and psample_groups_lock that is taken when holding tcf_lock in sample init: [ 162.108959] Possible interrupt unsafe locking scenario: [ 162.116386] CPU0 CPU1 [ 162.121277] ---- ---- [ 162.126162] lock(psample_groups_lock); [ 162.130447] local_irq_disable(); [ 162.136772] lock(&(&p->tcfa_lock)->rlock); [ 162.143957] lock(psample_groups_lock); [ 162.150813] <Interrupt> [ 162.153808] lock(&(&p->tcfa_lock)->rlock); [ 162.158608] *** DEADLOCK *** In order to prevent potential lock inversion dependency between tcf_lock and psample_groups_lock, extract call to psample_group_get() from tcf_lock protected section in sample action init function. Fixes: 4e232818bd32 ("net: sched: act_mirred: remove dependency on rtnl lock") Fixes: 764e9a24480f ("net: sched: act_vlan: remove dependency on rtnl lock") Fixes: 729e01260989 ("net: sched: act_tunnel_key: remove dependency on rtnl lock") Fixes: d77284956656 ("net: sched: act_sample: remove dependency on rtnl lock") Fixes: e8917f437006 ("net: sched: act_gact: remove dependency on rtnl lock") Fixes: b6a2b971c0b0 ("net: sched: act_csum: remove dependency on rtnl lock") Fixes: 2142236b4584 ("net: sched: act_bpf: remove dependency on rtnl lock") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-14 18:46:16 +00:00
spin_lock_bh(&s->tcf_lock);
opt.action = s->tcf_action;
if (nla_put(skb, TCA_SAMPLE_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
tcf_tm_dump(&t, &s->tcf_tm);
if (nla_put_64bit(skb, TCA_SAMPLE_TM, sizeof(t), &t, TCA_SAMPLE_PAD))
goto nla_put_failure;
if (nla_put_u32(skb, TCA_SAMPLE_RATE, s->rate))
goto nla_put_failure;
if (s->truncate)
if (nla_put_u32(skb, TCA_SAMPLE_TRUNC_SIZE, s->trunc_size))
goto nla_put_failure;
if (nla_put_u32(skb, TCA_SAMPLE_PSAMPLE_GROUP, s->psample_group_num))
goto nla_put_failure;
net: sched: always disable bh when taking tcf_lock Recently, ops->init() and ops->dump() of all actions were modified to always obtain tcf_lock when accessing private action state. Actions that don't depend on tcf_lock for synchronization with their data path use non-bh locking API. However, tcf_lock is also used to protect rate estimator stats in softirq context by timer callback. Change ops->init() and ops->dump() of all actions to disable bh when using tcf_lock to prevent deadlock reported by following lockdep warning: [ 105.470398] ================================ [ 105.475014] WARNING: inconsistent lock state [ 105.479628] 4.18.0-rc8+ #664 Not tainted [ 105.483897] -------------------------------- [ 105.488511] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. [ 105.494871] swapper/16/0 [HC0[0]:SC1[1]:HE1:SE0] takes: [ 105.500449] 00000000f86c012e (&(&p->tcfa_lock)->rlock){+.?.}, at: est_fetch_counters+0x3c/0xa0 [ 105.509696] {SOFTIRQ-ON-W} state was registered at: [ 105.514925] _raw_spin_lock+0x2c/0x40 [ 105.519022] tcf_bpf_init+0x579/0x820 [act_bpf] [ 105.523990] tcf_action_init_1+0x4e4/0x660 [ 105.528518] tcf_action_init+0x1ce/0x2d0 [ 105.532880] tcf_exts_validate+0x1d8/0x200 [ 105.537416] fl_change+0x55a/0x268b [cls_flower] [ 105.542469] tc_new_tfilter+0x748/0xa20 [ 105.546738] rtnetlink_rcv_msg+0x56a/0x6d0 [ 105.551268] netlink_rcv_skb+0x18d/0x200 [ 105.555628] netlink_unicast+0x2d0/0x370 [ 105.559990] netlink_sendmsg+0x3b9/0x6a0 [ 105.564349] sock_sendmsg+0x6b/0x80 [ 105.568271] ___sys_sendmsg+0x4a1/0x520 [ 105.572547] __sys_sendmsg+0xd7/0x150 [ 105.576655] do_syscall_64+0x72/0x2c0 [ 105.580757] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 105.586243] irq event stamp: 489296 [ 105.590084] hardirqs last enabled at (489296): [<ffffffffb507e639>] _raw_spin_unlock_irq+0x29/0x40 [ 105.599765] hardirqs last disabled at (489295): [<ffffffffb507e745>] _raw_spin_lock_irq+0x15/0x50 [ 105.609277] softirqs last enabled at (489292): [<ffffffffb413a6a3>] irq_enter+0x83/0xa0 [ 105.618001] softirqs last disabled at (489293): [<ffffffffb413a800>] irq_exit+0x140/0x190 [ 105.626813] other info that might help us debug this: [ 105.633976] Possible unsafe locking scenario: [ 105.640526] CPU0 [ 105.643325] ---- [ 105.646125] lock(&(&p->tcfa_lock)->rlock); [ 105.650747] <Interrupt> [ 105.653717] lock(&(&p->tcfa_lock)->rlock); [ 105.658514] *** DEADLOCK *** [ 105.665349] 1 lock held by swapper/16/0: [ 105.669629] #0: 00000000a640ad99 ((&est->timer)){+.-.}, at: call_timer_fn+0x10b/0x550 [ 105.678200] stack backtrace: [ 105.683194] CPU: 16 PID: 0 Comm: swapper/16 Not tainted 4.18.0-rc8+ #664 [ 105.690249] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 105.698626] Call Trace: [ 105.701421] <IRQ> [ 105.703791] dump_stack+0x92/0xeb [ 105.707461] print_usage_bug+0x336/0x34c [ 105.711744] mark_lock+0x7c9/0x980 [ 105.715500] ? print_shortest_lock_dependencies+0x2e0/0x2e0 [ 105.721424] ? check_usage_forwards+0x230/0x230 [ 105.726315] __lock_acquire+0x923/0x26f0 [ 105.730597] ? debug_show_all_locks+0x240/0x240 [ 105.735478] ? mark_lock+0x493/0x980 [ 105.739412] ? check_chain_key+0x140/0x1f0 [ 105.743861] ? __lock_acquire+0x836/0x26f0 [ 105.748323] ? lock_acquire+0x12e/0x290 [ 105.752516] lock_acquire+0x12e/0x290 [ 105.756539] ? est_fetch_counters+0x3c/0xa0 [ 105.761084] _raw_spin_lock+0x2c/0x40 [ 105.765099] ? est_fetch_counters+0x3c/0xa0 [ 105.769633] est_fetch_counters+0x3c/0xa0 [ 105.773995] est_timer+0x87/0x390 [ 105.777670] ? est_fetch_counters+0xa0/0xa0 [ 105.782210] ? lock_acquire+0x12e/0x290 [ 105.786410] call_timer_fn+0x161/0x550 [ 105.790512] ? est_fetch_counters+0xa0/0xa0 [ 105.795055] ? del_timer_sync+0xd0/0xd0 [ 105.799249] ? __lock_is_held+0x93/0x110 [ 105.803531] ? mark_held_locks+0x20/0xe0 [ 105.807813] ? _raw_spin_unlock_irq+0x29/0x40 [ 105.812525] ? est_fetch_counters+0xa0/0xa0 [ 105.817069] ? est_fetch_counters+0xa0/0xa0 [ 105.821610] run_timer_softirq+0x3c4/0x9f0 [ 105.826064] ? lock_acquire+0x12e/0x290 [ 105.830257] ? __bpf_trace_timer_class+0x10/0x10 [ 105.835237] ? __lock_is_held+0x25/0x110 [ 105.839517] __do_softirq+0x11d/0x7bf [ 105.843542] irq_exit+0x140/0x190 [ 105.847208] smp_apic_timer_interrupt+0xac/0x3b0 [ 105.852182] apic_timer_interrupt+0xf/0x20 [ 105.856628] </IRQ> [ 105.859081] RIP: 0010:cpuidle_enter_state+0xd8/0x4d0 [ 105.864395] Code: 46 ff 48 89 44 24 08 0f 1f 44 00 00 31 ff e8 cf ec 46 ff 80 7c 24 07 00 0f 85 1d 02 00 00 e8 9f 90 4b ff fb 66 0f 1f 44 00 00 <4c> 8b 6c 24 08 4d 29 fd 0f 80 36 03 00 00 4c 89 e8 48 ba cf f7 53 [ 105.884288] RSP: 0018:ffff8803ad94fd20 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 [ 105.892494] RAX: 0000000000000000 RBX: ffffe8fb300829c0 RCX: ffffffffb41e19e1 [ 105.899988] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8803ad9358ac [ 105.907503] RBP: ffffffffb6636300 R08: 0000000000000004 R09: 0000000000000000 [ 105.914997] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000004 [ 105.922487] R13: ffffffffb6636140 R14: ffffffffb66362d8 R15: 000000188d36091b [ 105.929988] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.935232] do_idle+0x28e/0x320 [ 105.938817] ? arch_cpu_idle_exit+0x40/0x40 [ 105.943361] ? mark_lock+0x8c1/0x980 [ 105.947295] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.952619] cpu_startup_entry+0xc2/0xd0 [ 105.956900] ? cpu_in_idle+0x20/0x20 [ 105.960830] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.966146] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.971391] start_secondary+0x2b5/0x360 [ 105.975669] ? set_cpu_sibling_map+0x1330/0x1330 [ 105.980654] secondary_startup_64+0xa5/0xb0 Taking tcf_lock in sample action with bh disabled causes lockdep to issue a warning regarding possible irq lock inversion dependency between tcf_lock, and psample_groups_lock that is taken when holding tcf_lock in sample init: [ 162.108959] Possible interrupt unsafe locking scenario: [ 162.116386] CPU0 CPU1 [ 162.121277] ---- ---- [ 162.126162] lock(psample_groups_lock); [ 162.130447] local_irq_disable(); [ 162.136772] lock(&(&p->tcfa_lock)->rlock); [ 162.143957] lock(psample_groups_lock); [ 162.150813] <Interrupt> [ 162.153808] lock(&(&p->tcfa_lock)->rlock); [ 162.158608] *** DEADLOCK *** In order to prevent potential lock inversion dependency between tcf_lock and psample_groups_lock, extract call to psample_group_get() from tcf_lock protected section in sample action init function. Fixes: 4e232818bd32 ("net: sched: act_mirred: remove dependency on rtnl lock") Fixes: 764e9a24480f ("net: sched: act_vlan: remove dependency on rtnl lock") Fixes: 729e01260989 ("net: sched: act_tunnel_key: remove dependency on rtnl lock") Fixes: d77284956656 ("net: sched: act_sample: remove dependency on rtnl lock") Fixes: e8917f437006 ("net: sched: act_gact: remove dependency on rtnl lock") Fixes: b6a2b971c0b0 ("net: sched: act_csum: remove dependency on rtnl lock") Fixes: 2142236b4584 ("net: sched: act_bpf: remove dependency on rtnl lock") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-14 18:46:16 +00:00
spin_unlock_bh(&s->tcf_lock);
return skb->len;
nla_put_failure:
net: sched: always disable bh when taking tcf_lock Recently, ops->init() and ops->dump() of all actions were modified to always obtain tcf_lock when accessing private action state. Actions that don't depend on tcf_lock for synchronization with their data path use non-bh locking API. However, tcf_lock is also used to protect rate estimator stats in softirq context by timer callback. Change ops->init() and ops->dump() of all actions to disable bh when using tcf_lock to prevent deadlock reported by following lockdep warning: [ 105.470398] ================================ [ 105.475014] WARNING: inconsistent lock state [ 105.479628] 4.18.0-rc8+ #664 Not tainted [ 105.483897] -------------------------------- [ 105.488511] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. [ 105.494871] swapper/16/0 [HC0[0]:SC1[1]:HE1:SE0] takes: [ 105.500449] 00000000f86c012e (&(&p->tcfa_lock)->rlock){+.?.}, at: est_fetch_counters+0x3c/0xa0 [ 105.509696] {SOFTIRQ-ON-W} state was registered at: [ 105.514925] _raw_spin_lock+0x2c/0x40 [ 105.519022] tcf_bpf_init+0x579/0x820 [act_bpf] [ 105.523990] tcf_action_init_1+0x4e4/0x660 [ 105.528518] tcf_action_init+0x1ce/0x2d0 [ 105.532880] tcf_exts_validate+0x1d8/0x200 [ 105.537416] fl_change+0x55a/0x268b [cls_flower] [ 105.542469] tc_new_tfilter+0x748/0xa20 [ 105.546738] rtnetlink_rcv_msg+0x56a/0x6d0 [ 105.551268] netlink_rcv_skb+0x18d/0x200 [ 105.555628] netlink_unicast+0x2d0/0x370 [ 105.559990] netlink_sendmsg+0x3b9/0x6a0 [ 105.564349] sock_sendmsg+0x6b/0x80 [ 105.568271] ___sys_sendmsg+0x4a1/0x520 [ 105.572547] __sys_sendmsg+0xd7/0x150 [ 105.576655] do_syscall_64+0x72/0x2c0 [ 105.580757] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 105.586243] irq event stamp: 489296 [ 105.590084] hardirqs last enabled at (489296): [<ffffffffb507e639>] _raw_spin_unlock_irq+0x29/0x40 [ 105.599765] hardirqs last disabled at (489295): [<ffffffffb507e745>] _raw_spin_lock_irq+0x15/0x50 [ 105.609277] softirqs last enabled at (489292): [<ffffffffb413a6a3>] irq_enter+0x83/0xa0 [ 105.618001] softirqs last disabled at (489293): [<ffffffffb413a800>] irq_exit+0x140/0x190 [ 105.626813] other info that might help us debug this: [ 105.633976] Possible unsafe locking scenario: [ 105.640526] CPU0 [ 105.643325] ---- [ 105.646125] lock(&(&p->tcfa_lock)->rlock); [ 105.650747] <Interrupt> [ 105.653717] lock(&(&p->tcfa_lock)->rlock); [ 105.658514] *** DEADLOCK *** [ 105.665349] 1 lock held by swapper/16/0: [ 105.669629] #0: 00000000a640ad99 ((&est->timer)){+.-.}, at: call_timer_fn+0x10b/0x550 [ 105.678200] stack backtrace: [ 105.683194] CPU: 16 PID: 0 Comm: swapper/16 Not tainted 4.18.0-rc8+ #664 [ 105.690249] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 105.698626] Call Trace: [ 105.701421] <IRQ> [ 105.703791] dump_stack+0x92/0xeb [ 105.707461] print_usage_bug+0x336/0x34c [ 105.711744] mark_lock+0x7c9/0x980 [ 105.715500] ? print_shortest_lock_dependencies+0x2e0/0x2e0 [ 105.721424] ? check_usage_forwards+0x230/0x230 [ 105.726315] __lock_acquire+0x923/0x26f0 [ 105.730597] ? debug_show_all_locks+0x240/0x240 [ 105.735478] ? mark_lock+0x493/0x980 [ 105.739412] ? check_chain_key+0x140/0x1f0 [ 105.743861] ? __lock_acquire+0x836/0x26f0 [ 105.748323] ? lock_acquire+0x12e/0x290 [ 105.752516] lock_acquire+0x12e/0x290 [ 105.756539] ? est_fetch_counters+0x3c/0xa0 [ 105.761084] _raw_spin_lock+0x2c/0x40 [ 105.765099] ? est_fetch_counters+0x3c/0xa0 [ 105.769633] est_fetch_counters+0x3c/0xa0 [ 105.773995] est_timer+0x87/0x390 [ 105.777670] ? est_fetch_counters+0xa0/0xa0 [ 105.782210] ? lock_acquire+0x12e/0x290 [ 105.786410] call_timer_fn+0x161/0x550 [ 105.790512] ? est_fetch_counters+0xa0/0xa0 [ 105.795055] ? del_timer_sync+0xd0/0xd0 [ 105.799249] ? __lock_is_held+0x93/0x110 [ 105.803531] ? mark_held_locks+0x20/0xe0 [ 105.807813] ? _raw_spin_unlock_irq+0x29/0x40 [ 105.812525] ? est_fetch_counters+0xa0/0xa0 [ 105.817069] ? est_fetch_counters+0xa0/0xa0 [ 105.821610] run_timer_softirq+0x3c4/0x9f0 [ 105.826064] ? lock_acquire+0x12e/0x290 [ 105.830257] ? __bpf_trace_timer_class+0x10/0x10 [ 105.835237] ? __lock_is_held+0x25/0x110 [ 105.839517] __do_softirq+0x11d/0x7bf [ 105.843542] irq_exit+0x140/0x190 [ 105.847208] smp_apic_timer_interrupt+0xac/0x3b0 [ 105.852182] apic_timer_interrupt+0xf/0x20 [ 105.856628] </IRQ> [ 105.859081] RIP: 0010:cpuidle_enter_state+0xd8/0x4d0 [ 105.864395] Code: 46 ff 48 89 44 24 08 0f 1f 44 00 00 31 ff e8 cf ec 46 ff 80 7c 24 07 00 0f 85 1d 02 00 00 e8 9f 90 4b ff fb 66 0f 1f 44 00 00 <4c> 8b 6c 24 08 4d 29 fd 0f 80 36 03 00 00 4c 89 e8 48 ba cf f7 53 [ 105.884288] RSP: 0018:ffff8803ad94fd20 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 [ 105.892494] RAX: 0000000000000000 RBX: ffffe8fb300829c0 RCX: ffffffffb41e19e1 [ 105.899988] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8803ad9358ac [ 105.907503] RBP: ffffffffb6636300 R08: 0000000000000004 R09: 0000000000000000 [ 105.914997] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000004 [ 105.922487] R13: ffffffffb6636140 R14: ffffffffb66362d8 R15: 000000188d36091b [ 105.929988] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.935232] do_idle+0x28e/0x320 [ 105.938817] ? arch_cpu_idle_exit+0x40/0x40 [ 105.943361] ? mark_lock+0x8c1/0x980 [ 105.947295] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.952619] cpu_startup_entry+0xc2/0xd0 [ 105.956900] ? cpu_in_idle+0x20/0x20 [ 105.960830] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.966146] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.971391] start_secondary+0x2b5/0x360 [ 105.975669] ? set_cpu_sibling_map+0x1330/0x1330 [ 105.980654] secondary_startup_64+0xa5/0xb0 Taking tcf_lock in sample action with bh disabled causes lockdep to issue a warning regarding possible irq lock inversion dependency between tcf_lock, and psample_groups_lock that is taken when holding tcf_lock in sample init: [ 162.108959] Possible interrupt unsafe locking scenario: [ 162.116386] CPU0 CPU1 [ 162.121277] ---- ---- [ 162.126162] lock(psample_groups_lock); [ 162.130447] local_irq_disable(); [ 162.136772] lock(&(&p->tcfa_lock)->rlock); [ 162.143957] lock(psample_groups_lock); [ 162.150813] <Interrupt> [ 162.153808] lock(&(&p->tcfa_lock)->rlock); [ 162.158608] *** DEADLOCK *** In order to prevent potential lock inversion dependency between tcf_lock and psample_groups_lock, extract call to psample_group_get() from tcf_lock protected section in sample action init function. Fixes: 4e232818bd32 ("net: sched: act_mirred: remove dependency on rtnl lock") Fixes: 764e9a24480f ("net: sched: act_vlan: remove dependency on rtnl lock") Fixes: 729e01260989 ("net: sched: act_tunnel_key: remove dependency on rtnl lock") Fixes: d77284956656 ("net: sched: act_sample: remove dependency on rtnl lock") Fixes: e8917f437006 ("net: sched: act_gact: remove dependency on rtnl lock") Fixes: b6a2b971c0b0 ("net: sched: act_csum: remove dependency on rtnl lock") Fixes: 2142236b4584 ("net: sched: act_bpf: remove dependency on rtnl lock") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-14 18:46:16 +00:00
spin_unlock_bh(&s->tcf_lock);
nlmsg_trim(skb, b);
return -1;
}
static int tcf_sample_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, sample_net_id);
return tcf_generic_walker(tn, skb, cb, type, ops, extack);
}
static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index)
{
struct tc_action_net *tn = net_generic(net, sample_net_id);
return tcf_idr_search(tn, a, index);
}
static struct tc_action_ops act_sample_ops = {
.kind = "sample",
.id = TCA_ID_SAMPLE,
.owner = THIS_MODULE,
.act = tcf_sample_act,
.dump = tcf_sample_dump,
.init = tcf_sample_init,
.cleanup = tcf_sample_cleanup,
.walk = tcf_sample_walker,
.lookup = tcf_sample_search,
.size = sizeof(struct tcf_sample),
};
static __net_init int sample_init_net(struct net *net)
{
struct tc_action_net *tn = net_generic(net, sample_net_id);
return tc_action_net_init(tn, &act_sample_ops);
}
static void __net_exit sample_exit_net(struct list_head *net_list)
{
tc_action_net_exit(net_list, sample_net_id);
}
static struct pernet_operations sample_net_ops = {
.init = sample_init_net,
.exit_batch = sample_exit_net,
.id = &sample_net_id,
.size = sizeof(struct tc_action_net),
};
static int __init sample_init_module(void)
{
return tcf_register_action(&act_sample_ops, &sample_net_ops);
}
static void __exit sample_cleanup_module(void)
{
tcf_unregister_action(&act_sample_ops, &sample_net_ops);
}
module_init(sample_init_module);
module_exit(sample_cleanup_module);
MODULE_AUTHOR("Yotam Gigi <yotam.gi@gmail.com>");
MODULE_DESCRIPTION("Packet sampling action");
MODULE_LICENSE("GPL v2");