OpenCloudOS-Kernel/net/sched/act_gact.c

320 lines
7.8 KiB
C
Raw Normal View History

/*
* net/sched/act_gact.c Generic actions
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
* copyright Jamal Hadi Salim (2002-4)
*
*/
#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 <net/netlink.h>
#include <net/pkt_sched.h>
net/sched: act_gact: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action gact pass index 90 # tc actions replace action gact \ > goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action gact 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: gact action goto chain 42 random type none pass val 0 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 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 2 PID: 0 Comm: swapper/2 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff8c2434703be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff8c23ed6d7e00 RCX: 000000000000005a RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8c23ed6d7e00 RBP: ffff8c2434703c80 R08: ffff8c243b639ac8 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8c2429e68b00 R13: ffff8c2429e68b08 R14: 0000000000000001 R15: ffff8c2429c5a480 FS: 0000000000000000(0000) GS:ffff8c2434700000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000002dc0e005 CR4: 00000000001606e0 Call Trace: <IRQ> tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ip6_finish_output2+0x369/0x590 ip6_finish_output2+0x369/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.35+0x79/0xc0 mld_sendpack+0x16f/0x220 mld_ifc_timer_expire+0x195/0x2c0 ? igmp6_timer_handler+0x70/0x70 call_timer_fn+0x2b/0x130 run_timer_softirq+0x3e8/0x440 ? tick_sched_timer+0x37/0x70 __do_softirq+0xe3/0x2f5 irq_exit+0xf0/0x100 smp_apic_timer_interrupt+0x6c/0x130 apic_timer_interrupt+0xf/0x20 </IRQ> RIP: 0010:native_safe_halt+0x2/0x10 Code: 74 ff ff ff 7f f3 c3 65 48 8b 04 25 00 5c 01 00 f0 80 48 02 20 48 8b 00 a8 08 74 8b eb c1 90 90 90 90 90 90 90 90 90 90 fb f4 <c3> 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f4 c3 90 90 90 90 90 90 RSP: 0018:ffff9c8640387eb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffff8b2184f0 RBX: 0000000000000002 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000002 RBP: 0000000000000002 R08: 000eb57882b36cc3 R09: 0000000000000020 R10: 0000000000000004 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x1/0x1 default_idle+0x1c/0x140 do_idle+0x1c4/0x280 cpu_startup_entry+0x19/0x20 start_secondary+0x1a7/0x200 secondary_startup_64+0xa4/0xb0 Modules linked in: act_gact act_bpf veth ip6table_filter ip6_tables iptable_filter binfmt_misc crct10dif_pclmul crc32_pclmul ghash_clmulni_intel snd_hda_codec_generic ext4 snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core mbcache jbd2 snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd glue_helper virtio_balloon joydev pcspkr snd_timer snd i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea virtio_net sysfillrect net_failover virtio_blk sysimgblt fb_sys_fops virtio_console ttm failover drm crc32c_intel serio_raw ata_piix libata floppy virtio_pci virtio_ring virtio dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_bpf] CR2: 0000000000000000 Validating the control action within tcf_gact_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 22:00:02 +08:00
#include <net/pkt_cls.h>
#include <linux/tc_act/tc_gact.h>
#include <net/tc_act/tc_gact.h>
netns: make struct pernet_operations::id unsigned int Make struct pernet_operations::id unsigned. There are 2 reasons to do so: 1) This field is really an index into an zero based array and thus is unsigned entity. Using negative value is out-of-bound access by definition. 2) On x86_64 unsigned 32-bit data which are mixed with pointers via array indexing or offsets added or subtracted to pointers are preffered to signed 32-bit data. "int" being used as an array index needs to be sign-extended to 64-bit before being used. void f(long *p, int i) { g(p[i]); } roughly translates to movsx rsi, esi mov rdi, [rsi+...] call g MOVSX is 3 byte instruction which isn't necessary if the variable is unsigned because x86_64 is zero extending by default. Now, there is net_generic() function which, you guessed it right, uses "int" as an array index: static inline void *net_generic(const struct net *net, int id) { ... ptr = ng->ptr[id - 1]; ... } And this function is used a lot, so those sign extensions add up. Patch snipes ~1730 bytes on allyesconfig kernel (without all junk messing with code generation): add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730) Unfortunately some functions actually grow bigger. This is a semmingly random artefact of code generation with register allocator being used differently. gcc decides that some variable needs to live in new r8+ registers and every access now requires REX prefix. Or it is shifted into r12, so [r12+0] addressing mode has to be used which is longer than [r8] However, overall balance is in negative direction: add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730) function old new delta nfsd4_lock 3886 3959 +73 tipc_link_build_proto_msg 1096 1140 +44 mac80211_hwsim_new_radio 2776 2808 +32 tipc_mon_rcv 1032 1058 +26 svcauth_gss_legacy_init 1413 1429 +16 tipc_bcbase_select_primary 379 392 +13 nfsd4_exchange_id 1247 1260 +13 nfsd4_setclientid_confirm 782 793 +11 ... put_client_renew_locked 494 480 -14 ip_set_sockfn_get 730 716 -14 geneve_sock_add 829 813 -16 nfsd4_sequence_done 721 703 -18 nlmclnt_lookup_host 708 686 -22 nfsd4_lockt 1085 1063 -22 nfs_get_client 1077 1050 -27 tcf_bpf_init 1106 1076 -30 nfsd4_encode_fattr 5997 5930 -67 Total: Before=154856051, After=154854321, chg -0.00% Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-17 09:58:21 +08:00
static unsigned int gact_net_id;
static struct tc_action_ops act_gact_ops;
#ifdef CONFIG_GACT_PROB
static int gact_net_rand(struct tcf_gact *gact)
{
smp_rmb(); /* coupled with smp_wmb() in tcf_gact_init() */
if (prandom_u32() % gact->tcfg_pval)
return gact->tcf_action;
return gact->tcfg_paction;
}
static int gact_determ(struct tcf_gact *gact)
{
u32 pack = atomic_inc_return(&gact->packets);
smp_rmb(); /* coupled with smp_wmb() in tcf_gact_init() */
if (pack % gact->tcfg_pval)
return gact->tcf_action;
return gact->tcfg_paction;
}
typedef int (*g_rand)(struct tcf_gact *gact);
static g_rand gact_rand[MAX_RAND] = { NULL, gact_net_rand, gact_determ };
#endif /* CONFIG_GACT_PROB */
static const struct nla_policy gact_policy[TCA_GACT_MAX + 1] = {
[TCA_GACT_PARMS] = { .len = sizeof(struct tc_gact) },
[TCA_GACT_PROB] = { .len = sizeof(struct tc_gact_p) },
};
static int tcf_gact_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
int ovr, int bind, bool rtnl_held,
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 21:59:59 +08:00
struct tcf_proto *tp, struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, gact_net_id);
struct nlattr *tb[TCA_GACT_MAX + 1];
net/sched: act_gact: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action gact pass index 90 # tc actions replace action gact \ > goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action gact 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: gact action goto chain 42 random type none pass val 0 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 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 2 PID: 0 Comm: swapper/2 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff8c2434703be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff8c23ed6d7e00 RCX: 000000000000005a RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8c23ed6d7e00 RBP: ffff8c2434703c80 R08: ffff8c243b639ac8 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8c2429e68b00 R13: ffff8c2429e68b08 R14: 0000000000000001 R15: ffff8c2429c5a480 FS: 0000000000000000(0000) GS:ffff8c2434700000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000002dc0e005 CR4: 00000000001606e0 Call Trace: <IRQ> tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ip6_finish_output2+0x369/0x590 ip6_finish_output2+0x369/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.35+0x79/0xc0 mld_sendpack+0x16f/0x220 mld_ifc_timer_expire+0x195/0x2c0 ? igmp6_timer_handler+0x70/0x70 call_timer_fn+0x2b/0x130 run_timer_softirq+0x3e8/0x440 ? tick_sched_timer+0x37/0x70 __do_softirq+0xe3/0x2f5 irq_exit+0xf0/0x100 smp_apic_timer_interrupt+0x6c/0x130 apic_timer_interrupt+0xf/0x20 </IRQ> RIP: 0010:native_safe_halt+0x2/0x10 Code: 74 ff ff ff 7f f3 c3 65 48 8b 04 25 00 5c 01 00 f0 80 48 02 20 48 8b 00 a8 08 74 8b eb c1 90 90 90 90 90 90 90 90 90 90 fb f4 <c3> 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f4 c3 90 90 90 90 90 90 RSP: 0018:ffff9c8640387eb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffff8b2184f0 RBX: 0000000000000002 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000002 RBP: 0000000000000002 R08: 000eb57882b36cc3 R09: 0000000000000020 R10: 0000000000000004 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x1/0x1 default_idle+0x1c/0x140 do_idle+0x1c4/0x280 cpu_startup_entry+0x19/0x20 start_secondary+0x1a7/0x200 secondary_startup_64+0xa4/0xb0 Modules linked in: act_gact act_bpf veth ip6table_filter ip6_tables iptable_filter binfmt_misc crct10dif_pclmul crc32_pclmul ghash_clmulni_intel snd_hda_codec_generic ext4 snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core mbcache jbd2 snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd glue_helper virtio_balloon joydev pcspkr snd_timer snd i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea virtio_net sysfillrect net_failover virtio_blk sysimgblt fb_sys_fops virtio_console ttm failover drm crc32c_intel serio_raw ata_piix libata floppy virtio_pci virtio_ring virtio dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_bpf] CR2: 0000000000000000 Validating the control action within tcf_gact_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 22:00:02 +08:00
struct tcf_chain *goto_ch = NULL;
struct tc_gact *parm;
struct tcf_gact *gact;
int ret = 0;
int err;
#ifdef CONFIG_GACT_PROB
struct tc_gact_p *p_parm = NULL;
#endif
if (nla == NULL)
return -EINVAL;
err = nla_parse_nested(tb, TCA_GACT_MAX, nla, gact_policy, NULL);
if (err < 0)
return err;
if (tb[TCA_GACT_PARMS] == NULL)
return -EINVAL;
parm = nla_data(tb[TCA_GACT_PARMS]);
#ifndef CONFIG_GACT_PROB
if (tb[TCA_GACT_PROB] != NULL)
return -EOPNOTSUPP;
#else
if (tb[TCA_GACT_PROB]) {
p_parm = nla_data(tb[TCA_GACT_PROB]);
if (p_parm->ptype >= MAX_RAND)
return -EINVAL;
if (TC_ACT_EXT_CMP(p_parm->paction, TC_ACT_GOTO_CHAIN)) {
NL_SET_ERR_MSG(extack,
"goto chain not allowed on fallback");
return -EINVAL;
}
}
#endif
err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
if (!err) {
ret = tcf_idr_create(tn, parm->index, est, a,
&act_gact_ops, bind, true);
if (ret) {
tcf_idr_cleanup(tn, parm->index);
return ret;
}
ret = ACT_P_CREATED;
} else if (err > 0) {
if (bind)/* dont override defaults */
return 0;
if (!ovr) {
tcf_idr_release(*a, bind);
return -EEXIST;
}
} else {
return err;
}
net/sched: act_gact: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action gact pass index 90 # tc actions replace action gact \ > goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action gact 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: gact action goto chain 42 random type none pass val 0 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 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 2 PID: 0 Comm: swapper/2 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff8c2434703be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff8c23ed6d7e00 RCX: 000000000000005a RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8c23ed6d7e00 RBP: ffff8c2434703c80 R08: ffff8c243b639ac8 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8c2429e68b00 R13: ffff8c2429e68b08 R14: 0000000000000001 R15: ffff8c2429c5a480 FS: 0000000000000000(0000) GS:ffff8c2434700000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000002dc0e005 CR4: 00000000001606e0 Call Trace: <IRQ> tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ip6_finish_output2+0x369/0x590 ip6_finish_output2+0x369/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.35+0x79/0xc0 mld_sendpack+0x16f/0x220 mld_ifc_timer_expire+0x195/0x2c0 ? igmp6_timer_handler+0x70/0x70 call_timer_fn+0x2b/0x130 run_timer_softirq+0x3e8/0x440 ? tick_sched_timer+0x37/0x70 __do_softirq+0xe3/0x2f5 irq_exit+0xf0/0x100 smp_apic_timer_interrupt+0x6c/0x130 apic_timer_interrupt+0xf/0x20 </IRQ> RIP: 0010:native_safe_halt+0x2/0x10 Code: 74 ff ff ff 7f f3 c3 65 48 8b 04 25 00 5c 01 00 f0 80 48 02 20 48 8b 00 a8 08 74 8b eb c1 90 90 90 90 90 90 90 90 90 90 fb f4 <c3> 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f4 c3 90 90 90 90 90 90 RSP: 0018:ffff9c8640387eb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffff8b2184f0 RBX: 0000000000000002 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000002 RBP: 0000000000000002 R08: 000eb57882b36cc3 R09: 0000000000000020 R10: 0000000000000004 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x1/0x1 default_idle+0x1c/0x140 do_idle+0x1c4/0x280 cpu_startup_entry+0x19/0x20 start_secondary+0x1a7/0x200 secondary_startup_64+0xa4/0xb0 Modules linked in: act_gact act_bpf veth ip6table_filter ip6_tables iptable_filter binfmt_misc crct10dif_pclmul crc32_pclmul ghash_clmulni_intel snd_hda_codec_generic ext4 snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core mbcache jbd2 snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd glue_helper virtio_balloon joydev pcspkr snd_timer snd i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea virtio_net sysfillrect net_failover virtio_blk sysimgblt fb_sys_fops virtio_console ttm failover drm crc32c_intel serio_raw ata_piix libata floppy virtio_pci virtio_ring virtio dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_bpf] CR2: 0000000000000000 Validating the control action within tcf_gact_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 22:00:02 +08:00
err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
if (err < 0)
goto release_idr;
gact = to_gact(*a);
net: sched: always disable bh when taking tcf_lock Recently, ops->init() and ops->dump() of all actions were modified to always obtain tcf_lock when accessing private action state. Actions that don't depend on tcf_lock for synchronization with their data path use non-bh locking API. However, tcf_lock is also used to protect rate estimator stats in softirq context by timer callback. Change ops->init() and ops->dump() of all actions to disable bh when using tcf_lock to prevent deadlock reported by following lockdep warning: [ 105.470398] ================================ [ 105.475014] WARNING: inconsistent lock state [ 105.479628] 4.18.0-rc8+ #664 Not tainted [ 105.483897] -------------------------------- [ 105.488511] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. [ 105.494871] swapper/16/0 [HC0[0]:SC1[1]:HE1:SE0] takes: [ 105.500449] 00000000f86c012e (&(&p->tcfa_lock)->rlock){+.?.}, at: est_fetch_counters+0x3c/0xa0 [ 105.509696] {SOFTIRQ-ON-W} state was registered at: [ 105.514925] _raw_spin_lock+0x2c/0x40 [ 105.519022] tcf_bpf_init+0x579/0x820 [act_bpf] [ 105.523990] tcf_action_init_1+0x4e4/0x660 [ 105.528518] tcf_action_init+0x1ce/0x2d0 [ 105.532880] tcf_exts_validate+0x1d8/0x200 [ 105.537416] fl_change+0x55a/0x268b [cls_flower] [ 105.542469] tc_new_tfilter+0x748/0xa20 [ 105.546738] rtnetlink_rcv_msg+0x56a/0x6d0 [ 105.551268] netlink_rcv_skb+0x18d/0x200 [ 105.555628] netlink_unicast+0x2d0/0x370 [ 105.559990] netlink_sendmsg+0x3b9/0x6a0 [ 105.564349] sock_sendmsg+0x6b/0x80 [ 105.568271] ___sys_sendmsg+0x4a1/0x520 [ 105.572547] __sys_sendmsg+0xd7/0x150 [ 105.576655] do_syscall_64+0x72/0x2c0 [ 105.580757] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 105.586243] irq event stamp: 489296 [ 105.590084] hardirqs last enabled at (489296): [<ffffffffb507e639>] _raw_spin_unlock_irq+0x29/0x40 [ 105.599765] hardirqs last disabled at (489295): [<ffffffffb507e745>] _raw_spin_lock_irq+0x15/0x50 [ 105.609277] softirqs last enabled at (489292): [<ffffffffb413a6a3>] irq_enter+0x83/0xa0 [ 105.618001] softirqs last disabled at (489293): [<ffffffffb413a800>] irq_exit+0x140/0x190 [ 105.626813] other info that might help us debug this: [ 105.633976] Possible unsafe locking scenario: [ 105.640526] CPU0 [ 105.643325] ---- [ 105.646125] lock(&(&p->tcfa_lock)->rlock); [ 105.650747] <Interrupt> [ 105.653717] lock(&(&p->tcfa_lock)->rlock); [ 105.658514] *** DEADLOCK *** [ 105.665349] 1 lock held by swapper/16/0: [ 105.669629] #0: 00000000a640ad99 ((&est->timer)){+.-.}, at: call_timer_fn+0x10b/0x550 [ 105.678200] stack backtrace: [ 105.683194] CPU: 16 PID: 0 Comm: swapper/16 Not tainted 4.18.0-rc8+ #664 [ 105.690249] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 105.698626] Call Trace: [ 105.701421] <IRQ> [ 105.703791] dump_stack+0x92/0xeb [ 105.707461] print_usage_bug+0x336/0x34c [ 105.711744] mark_lock+0x7c9/0x980 [ 105.715500] ? print_shortest_lock_dependencies+0x2e0/0x2e0 [ 105.721424] ? check_usage_forwards+0x230/0x230 [ 105.726315] __lock_acquire+0x923/0x26f0 [ 105.730597] ? debug_show_all_locks+0x240/0x240 [ 105.735478] ? mark_lock+0x493/0x980 [ 105.739412] ? check_chain_key+0x140/0x1f0 [ 105.743861] ? __lock_acquire+0x836/0x26f0 [ 105.748323] ? lock_acquire+0x12e/0x290 [ 105.752516] lock_acquire+0x12e/0x290 [ 105.756539] ? est_fetch_counters+0x3c/0xa0 [ 105.761084] _raw_spin_lock+0x2c/0x40 [ 105.765099] ? est_fetch_counters+0x3c/0xa0 [ 105.769633] est_fetch_counters+0x3c/0xa0 [ 105.773995] est_timer+0x87/0x390 [ 105.777670] ? est_fetch_counters+0xa0/0xa0 [ 105.782210] ? lock_acquire+0x12e/0x290 [ 105.786410] call_timer_fn+0x161/0x550 [ 105.790512] ? est_fetch_counters+0xa0/0xa0 [ 105.795055] ? del_timer_sync+0xd0/0xd0 [ 105.799249] ? __lock_is_held+0x93/0x110 [ 105.803531] ? mark_held_locks+0x20/0xe0 [ 105.807813] ? _raw_spin_unlock_irq+0x29/0x40 [ 105.812525] ? est_fetch_counters+0xa0/0xa0 [ 105.817069] ? est_fetch_counters+0xa0/0xa0 [ 105.821610] run_timer_softirq+0x3c4/0x9f0 [ 105.826064] ? lock_acquire+0x12e/0x290 [ 105.830257] ? __bpf_trace_timer_class+0x10/0x10 [ 105.835237] ? __lock_is_held+0x25/0x110 [ 105.839517] __do_softirq+0x11d/0x7bf [ 105.843542] irq_exit+0x140/0x190 [ 105.847208] smp_apic_timer_interrupt+0xac/0x3b0 [ 105.852182] apic_timer_interrupt+0xf/0x20 [ 105.856628] </IRQ> [ 105.859081] RIP: 0010:cpuidle_enter_state+0xd8/0x4d0 [ 105.864395] Code: 46 ff 48 89 44 24 08 0f 1f 44 00 00 31 ff e8 cf ec 46 ff 80 7c 24 07 00 0f 85 1d 02 00 00 e8 9f 90 4b ff fb 66 0f 1f 44 00 00 <4c> 8b 6c 24 08 4d 29 fd 0f 80 36 03 00 00 4c 89 e8 48 ba cf f7 53 [ 105.884288] RSP: 0018:ffff8803ad94fd20 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 [ 105.892494] RAX: 0000000000000000 RBX: ffffe8fb300829c0 RCX: ffffffffb41e19e1 [ 105.899988] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8803ad9358ac [ 105.907503] RBP: ffffffffb6636300 R08: 0000000000000004 R09: 0000000000000000 [ 105.914997] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000004 [ 105.922487] R13: ffffffffb6636140 R14: ffffffffb66362d8 R15: 000000188d36091b [ 105.929988] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.935232] do_idle+0x28e/0x320 [ 105.938817] ? arch_cpu_idle_exit+0x40/0x40 [ 105.943361] ? mark_lock+0x8c1/0x980 [ 105.947295] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.952619] cpu_startup_entry+0xc2/0xd0 [ 105.956900] ? cpu_in_idle+0x20/0x20 [ 105.960830] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.966146] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.971391] start_secondary+0x2b5/0x360 [ 105.975669] ? set_cpu_sibling_map+0x1330/0x1330 [ 105.980654] secondary_startup_64+0xa5/0xb0 Taking tcf_lock in sample action with bh disabled causes lockdep to issue a warning regarding possible irq lock inversion dependency between tcf_lock, and psample_groups_lock that is taken when holding tcf_lock in sample init: [ 162.108959] Possible interrupt unsafe locking scenario: [ 162.116386] CPU0 CPU1 [ 162.121277] ---- ---- [ 162.126162] lock(psample_groups_lock); [ 162.130447] local_irq_disable(); [ 162.136772] lock(&(&p->tcfa_lock)->rlock); [ 162.143957] lock(psample_groups_lock); [ 162.150813] <Interrupt> [ 162.153808] lock(&(&p->tcfa_lock)->rlock); [ 162.158608] *** DEADLOCK *** In order to prevent potential lock inversion dependency between tcf_lock and psample_groups_lock, extract call to psample_group_get() from tcf_lock protected section in sample action init function. Fixes: 4e232818bd32 ("net: sched: act_mirred: remove dependency on rtnl lock") Fixes: 764e9a24480f ("net: sched: act_vlan: remove dependency on rtnl lock") Fixes: 729e01260989 ("net: sched: act_tunnel_key: remove dependency on rtnl lock") Fixes: d77284956656 ("net: sched: act_sample: remove dependency on rtnl lock") Fixes: e8917f437006 ("net: sched: act_gact: remove dependency on rtnl lock") Fixes: b6a2b971c0b0 ("net: sched: act_csum: remove dependency on rtnl lock") Fixes: 2142236b4584 ("net: sched: act_bpf: remove dependency on rtnl lock") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-15 02:46:16 +08:00
spin_lock_bh(&gact->tcf_lock);
net/sched: act_gact: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action gact pass index 90 # tc actions replace action gact \ > goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action gact 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: gact action goto chain 42 random type none pass val 0 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 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 2 PID: 0 Comm: swapper/2 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff8c2434703be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff8c23ed6d7e00 RCX: 000000000000005a RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8c23ed6d7e00 RBP: ffff8c2434703c80 R08: ffff8c243b639ac8 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8c2429e68b00 R13: ffff8c2429e68b08 R14: 0000000000000001 R15: ffff8c2429c5a480 FS: 0000000000000000(0000) GS:ffff8c2434700000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000002dc0e005 CR4: 00000000001606e0 Call Trace: <IRQ> tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ip6_finish_output2+0x369/0x590 ip6_finish_output2+0x369/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.35+0x79/0xc0 mld_sendpack+0x16f/0x220 mld_ifc_timer_expire+0x195/0x2c0 ? igmp6_timer_handler+0x70/0x70 call_timer_fn+0x2b/0x130 run_timer_softirq+0x3e8/0x440 ? tick_sched_timer+0x37/0x70 __do_softirq+0xe3/0x2f5 irq_exit+0xf0/0x100 smp_apic_timer_interrupt+0x6c/0x130 apic_timer_interrupt+0xf/0x20 </IRQ> RIP: 0010:native_safe_halt+0x2/0x10 Code: 74 ff ff ff 7f f3 c3 65 48 8b 04 25 00 5c 01 00 f0 80 48 02 20 48 8b 00 a8 08 74 8b eb c1 90 90 90 90 90 90 90 90 90 90 fb f4 <c3> 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f4 c3 90 90 90 90 90 90 RSP: 0018:ffff9c8640387eb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffff8b2184f0 RBX: 0000000000000002 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000002 RBP: 0000000000000002 R08: 000eb57882b36cc3 R09: 0000000000000020 R10: 0000000000000004 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x1/0x1 default_idle+0x1c/0x140 do_idle+0x1c4/0x280 cpu_startup_entry+0x19/0x20 start_secondary+0x1a7/0x200 secondary_startup_64+0xa4/0xb0 Modules linked in: act_gact act_bpf veth ip6table_filter ip6_tables iptable_filter binfmt_misc crct10dif_pclmul crc32_pclmul ghash_clmulni_intel snd_hda_codec_generic ext4 snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core mbcache jbd2 snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd glue_helper virtio_balloon joydev pcspkr snd_timer snd i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea virtio_net sysfillrect net_failover virtio_blk sysimgblt fb_sys_fops virtio_console ttm failover drm crc32c_intel serio_raw ata_piix libata floppy virtio_pci virtio_ring virtio dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_bpf] CR2: 0000000000000000 Validating the control action within tcf_gact_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 22:00:02 +08:00
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
#ifdef CONFIG_GACT_PROB
if (p_parm) {
gact->tcfg_paction = p_parm->paction;
gact->tcfg_pval = max_t(u16, 1, p_parm->pval);
/* Make sure tcfg_pval is written before tcfg_ptype
* coupled with smp_rmb() in gact_net_rand() & gact_determ()
*/
smp_wmb();
gact->tcfg_ptype = p_parm->ptype;
}
#endif
net: sched: always disable bh when taking tcf_lock Recently, ops->init() and ops->dump() of all actions were modified to always obtain tcf_lock when accessing private action state. Actions that don't depend on tcf_lock for synchronization with their data path use non-bh locking API. However, tcf_lock is also used to protect rate estimator stats in softirq context by timer callback. Change ops->init() and ops->dump() of all actions to disable bh when using tcf_lock to prevent deadlock reported by following lockdep warning: [ 105.470398] ================================ [ 105.475014] WARNING: inconsistent lock state [ 105.479628] 4.18.0-rc8+ #664 Not tainted [ 105.483897] -------------------------------- [ 105.488511] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. [ 105.494871] swapper/16/0 [HC0[0]:SC1[1]:HE1:SE0] takes: [ 105.500449] 00000000f86c012e (&(&p->tcfa_lock)->rlock){+.?.}, at: est_fetch_counters+0x3c/0xa0 [ 105.509696] {SOFTIRQ-ON-W} state was registered at: [ 105.514925] _raw_spin_lock+0x2c/0x40 [ 105.519022] tcf_bpf_init+0x579/0x820 [act_bpf] [ 105.523990] tcf_action_init_1+0x4e4/0x660 [ 105.528518] tcf_action_init+0x1ce/0x2d0 [ 105.532880] tcf_exts_validate+0x1d8/0x200 [ 105.537416] fl_change+0x55a/0x268b [cls_flower] [ 105.542469] tc_new_tfilter+0x748/0xa20 [ 105.546738] rtnetlink_rcv_msg+0x56a/0x6d0 [ 105.551268] netlink_rcv_skb+0x18d/0x200 [ 105.555628] netlink_unicast+0x2d0/0x370 [ 105.559990] netlink_sendmsg+0x3b9/0x6a0 [ 105.564349] sock_sendmsg+0x6b/0x80 [ 105.568271] ___sys_sendmsg+0x4a1/0x520 [ 105.572547] __sys_sendmsg+0xd7/0x150 [ 105.576655] do_syscall_64+0x72/0x2c0 [ 105.580757] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 105.586243] irq event stamp: 489296 [ 105.590084] hardirqs last enabled at (489296): [<ffffffffb507e639>] _raw_spin_unlock_irq+0x29/0x40 [ 105.599765] hardirqs last disabled at (489295): [<ffffffffb507e745>] _raw_spin_lock_irq+0x15/0x50 [ 105.609277] softirqs last enabled at (489292): [<ffffffffb413a6a3>] irq_enter+0x83/0xa0 [ 105.618001] softirqs last disabled at (489293): [<ffffffffb413a800>] irq_exit+0x140/0x190 [ 105.626813] other info that might help us debug this: [ 105.633976] Possible unsafe locking scenario: [ 105.640526] CPU0 [ 105.643325] ---- [ 105.646125] lock(&(&p->tcfa_lock)->rlock); [ 105.650747] <Interrupt> [ 105.653717] lock(&(&p->tcfa_lock)->rlock); [ 105.658514] *** DEADLOCK *** [ 105.665349] 1 lock held by swapper/16/0: [ 105.669629] #0: 00000000a640ad99 ((&est->timer)){+.-.}, at: call_timer_fn+0x10b/0x550 [ 105.678200] stack backtrace: [ 105.683194] CPU: 16 PID: 0 Comm: swapper/16 Not tainted 4.18.0-rc8+ #664 [ 105.690249] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 105.698626] Call Trace: [ 105.701421] <IRQ> [ 105.703791] dump_stack+0x92/0xeb [ 105.707461] print_usage_bug+0x336/0x34c [ 105.711744] mark_lock+0x7c9/0x980 [ 105.715500] ? print_shortest_lock_dependencies+0x2e0/0x2e0 [ 105.721424] ? check_usage_forwards+0x230/0x230 [ 105.726315] __lock_acquire+0x923/0x26f0 [ 105.730597] ? debug_show_all_locks+0x240/0x240 [ 105.735478] ? mark_lock+0x493/0x980 [ 105.739412] ? check_chain_key+0x140/0x1f0 [ 105.743861] ? __lock_acquire+0x836/0x26f0 [ 105.748323] ? lock_acquire+0x12e/0x290 [ 105.752516] lock_acquire+0x12e/0x290 [ 105.756539] ? est_fetch_counters+0x3c/0xa0 [ 105.761084] _raw_spin_lock+0x2c/0x40 [ 105.765099] ? est_fetch_counters+0x3c/0xa0 [ 105.769633] est_fetch_counters+0x3c/0xa0 [ 105.773995] est_timer+0x87/0x390 [ 105.777670] ? est_fetch_counters+0xa0/0xa0 [ 105.782210] ? lock_acquire+0x12e/0x290 [ 105.786410] call_timer_fn+0x161/0x550 [ 105.790512] ? est_fetch_counters+0xa0/0xa0 [ 105.795055] ? del_timer_sync+0xd0/0xd0 [ 105.799249] ? __lock_is_held+0x93/0x110 [ 105.803531] ? mark_held_locks+0x20/0xe0 [ 105.807813] ? _raw_spin_unlock_irq+0x29/0x40 [ 105.812525] ? est_fetch_counters+0xa0/0xa0 [ 105.817069] ? est_fetch_counters+0xa0/0xa0 [ 105.821610] run_timer_softirq+0x3c4/0x9f0 [ 105.826064] ? lock_acquire+0x12e/0x290 [ 105.830257] ? __bpf_trace_timer_class+0x10/0x10 [ 105.835237] ? __lock_is_held+0x25/0x110 [ 105.839517] __do_softirq+0x11d/0x7bf [ 105.843542] irq_exit+0x140/0x190 [ 105.847208] smp_apic_timer_interrupt+0xac/0x3b0 [ 105.852182] apic_timer_interrupt+0xf/0x20 [ 105.856628] </IRQ> [ 105.859081] RIP: 0010:cpuidle_enter_state+0xd8/0x4d0 [ 105.864395] Code: 46 ff 48 89 44 24 08 0f 1f 44 00 00 31 ff e8 cf ec 46 ff 80 7c 24 07 00 0f 85 1d 02 00 00 e8 9f 90 4b ff fb 66 0f 1f 44 00 00 <4c> 8b 6c 24 08 4d 29 fd 0f 80 36 03 00 00 4c 89 e8 48 ba cf f7 53 [ 105.884288] RSP: 0018:ffff8803ad94fd20 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 [ 105.892494] RAX: 0000000000000000 RBX: ffffe8fb300829c0 RCX: ffffffffb41e19e1 [ 105.899988] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8803ad9358ac [ 105.907503] RBP: ffffffffb6636300 R08: 0000000000000004 R09: 0000000000000000 [ 105.914997] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000004 [ 105.922487] R13: ffffffffb6636140 R14: ffffffffb66362d8 R15: 000000188d36091b [ 105.929988] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.935232] do_idle+0x28e/0x320 [ 105.938817] ? arch_cpu_idle_exit+0x40/0x40 [ 105.943361] ? mark_lock+0x8c1/0x980 [ 105.947295] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.952619] cpu_startup_entry+0xc2/0xd0 [ 105.956900] ? cpu_in_idle+0x20/0x20 [ 105.960830] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.966146] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.971391] start_secondary+0x2b5/0x360 [ 105.975669] ? set_cpu_sibling_map+0x1330/0x1330 [ 105.980654] secondary_startup_64+0xa5/0xb0 Taking tcf_lock in sample action with bh disabled causes lockdep to issue a warning regarding possible irq lock inversion dependency between tcf_lock, and psample_groups_lock that is taken when holding tcf_lock in sample init: [ 162.108959] Possible interrupt unsafe locking scenario: [ 162.116386] CPU0 CPU1 [ 162.121277] ---- ---- [ 162.126162] lock(psample_groups_lock); [ 162.130447] local_irq_disable(); [ 162.136772] lock(&(&p->tcfa_lock)->rlock); [ 162.143957] lock(psample_groups_lock); [ 162.150813] <Interrupt> [ 162.153808] lock(&(&p->tcfa_lock)->rlock); [ 162.158608] *** DEADLOCK *** In order to prevent potential lock inversion dependency between tcf_lock and psample_groups_lock, extract call to psample_group_get() from tcf_lock protected section in sample action init function. Fixes: 4e232818bd32 ("net: sched: act_mirred: remove dependency on rtnl lock") Fixes: 764e9a24480f ("net: sched: act_vlan: remove dependency on rtnl lock") Fixes: 729e01260989 ("net: sched: act_tunnel_key: remove dependency on rtnl lock") Fixes: d77284956656 ("net: sched: act_sample: remove dependency on rtnl lock") Fixes: e8917f437006 ("net: sched: act_gact: remove dependency on rtnl lock") Fixes: b6a2b971c0b0 ("net: sched: act_csum: remove dependency on rtnl lock") Fixes: 2142236b4584 ("net: sched: act_bpf: remove dependency on rtnl lock") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-15 02:46:16 +08:00
spin_unlock_bh(&gact->tcf_lock);
net/sched: act_gact: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action gact pass index 90 # tc actions replace action gact \ > goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action gact 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: gact action goto chain 42 random type none pass val 0 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 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 2 PID: 0 Comm: swapper/2 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff8c2434703be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff8c23ed6d7e00 RCX: 000000000000005a RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8c23ed6d7e00 RBP: ffff8c2434703c80 R08: ffff8c243b639ac8 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8c2429e68b00 R13: ffff8c2429e68b08 R14: 0000000000000001 R15: ffff8c2429c5a480 FS: 0000000000000000(0000) GS:ffff8c2434700000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000002dc0e005 CR4: 00000000001606e0 Call Trace: <IRQ> tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ip6_finish_output2+0x369/0x590 ip6_finish_output2+0x369/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.35+0x79/0xc0 mld_sendpack+0x16f/0x220 mld_ifc_timer_expire+0x195/0x2c0 ? igmp6_timer_handler+0x70/0x70 call_timer_fn+0x2b/0x130 run_timer_softirq+0x3e8/0x440 ? tick_sched_timer+0x37/0x70 __do_softirq+0xe3/0x2f5 irq_exit+0xf0/0x100 smp_apic_timer_interrupt+0x6c/0x130 apic_timer_interrupt+0xf/0x20 </IRQ> RIP: 0010:native_safe_halt+0x2/0x10 Code: 74 ff ff ff 7f f3 c3 65 48 8b 04 25 00 5c 01 00 f0 80 48 02 20 48 8b 00 a8 08 74 8b eb c1 90 90 90 90 90 90 90 90 90 90 fb f4 <c3> 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f4 c3 90 90 90 90 90 90 RSP: 0018:ffff9c8640387eb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffff8b2184f0 RBX: 0000000000000002 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000002 RBP: 0000000000000002 R08: 000eb57882b36cc3 R09: 0000000000000020 R10: 0000000000000004 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x1/0x1 default_idle+0x1c/0x140 do_idle+0x1c4/0x280 cpu_startup_entry+0x19/0x20 start_secondary+0x1a7/0x200 secondary_startup_64+0xa4/0xb0 Modules linked in: act_gact act_bpf veth ip6table_filter ip6_tables iptable_filter binfmt_misc crct10dif_pclmul crc32_pclmul ghash_clmulni_intel snd_hda_codec_generic ext4 snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core mbcache jbd2 snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd glue_helper virtio_balloon joydev pcspkr snd_timer snd i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea virtio_net sysfillrect net_failover virtio_blk sysimgblt fb_sys_fops virtio_console ttm failover drm crc32c_intel serio_raw ata_piix libata floppy virtio_pci virtio_ring virtio dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_bpf] CR2: 0000000000000000 Validating the control action within tcf_gact_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 22:00:02 +08:00
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
if (ret == ACT_P_CREATED)
tcf_idr_insert(tn, *a);
return ret;
net/sched: act_gact: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action gact pass index 90 # tc actions replace action gact \ > goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action gact 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: gact action goto chain 42 random type none pass val 0 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 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 2 PID: 0 Comm: swapper/2 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffff8c2434703be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff8c23ed6d7e00 RCX: 000000000000005a RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8c23ed6d7e00 RBP: ffff8c2434703c80 R08: ffff8c243b639ac8 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8c2429e68b00 R13: ffff8c2429e68b08 R14: 0000000000000001 R15: ffff8c2429c5a480 FS: 0000000000000000(0000) GS:ffff8c2434700000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000002dc0e005 CR4: 00000000001606e0 Call Trace: <IRQ> tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ip6_finish_output2+0x369/0x590 ip6_finish_output2+0x369/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.35+0x79/0xc0 mld_sendpack+0x16f/0x220 mld_ifc_timer_expire+0x195/0x2c0 ? igmp6_timer_handler+0x70/0x70 call_timer_fn+0x2b/0x130 run_timer_softirq+0x3e8/0x440 ? tick_sched_timer+0x37/0x70 __do_softirq+0xe3/0x2f5 irq_exit+0xf0/0x100 smp_apic_timer_interrupt+0x6c/0x130 apic_timer_interrupt+0xf/0x20 </IRQ> RIP: 0010:native_safe_halt+0x2/0x10 Code: 74 ff ff ff 7f f3 c3 65 48 8b 04 25 00 5c 01 00 f0 80 48 02 20 48 8b 00 a8 08 74 8b eb c1 90 90 90 90 90 90 90 90 90 90 fb f4 <c3> 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f4 c3 90 90 90 90 90 90 RSP: 0018:ffff9c8640387eb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffff8b2184f0 RBX: 0000000000000002 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000002 RBP: 0000000000000002 R08: 000eb57882b36cc3 R09: 0000000000000020 R10: 0000000000000004 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x1/0x1 default_idle+0x1c/0x140 do_idle+0x1c4/0x280 cpu_startup_entry+0x19/0x20 start_secondary+0x1a7/0x200 secondary_startup_64+0xa4/0xb0 Modules linked in: act_gact act_bpf veth ip6table_filter ip6_tables iptable_filter binfmt_misc crct10dif_pclmul crc32_pclmul ghash_clmulni_intel snd_hda_codec_generic ext4 snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core mbcache jbd2 snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd glue_helper virtio_balloon joydev pcspkr snd_timer snd i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea virtio_net sysfillrect net_failover virtio_blk sysimgblt fb_sys_fops virtio_console ttm failover drm crc32c_intel serio_raw ata_piix libata floppy virtio_pci virtio_ring virtio dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_bpf] CR2: 0000000000000000 Validating the control action within tcf_gact_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 22:00:02 +08:00
release_idr:
tcf_idr_release(*a, bind);
return err;
}
static int tcf_gact_act(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
struct tcf_gact *gact = to_gact(a);
int action = READ_ONCE(gact->tcf_action);
#ifdef CONFIG_GACT_PROB
{
u32 ptype = READ_ONCE(gact->tcfg_ptype);
if (ptype)
action = gact_rand[ptype](gact);
}
#endif
bstats_cpu_update(this_cpu_ptr(gact->common.cpu_bstats), skb);
if (action == TC_ACT_SHOT)
qstats_drop_inc(this_cpu_ptr(gact->common.cpu_qstats));
tcf_lastuse_update(&gact->tcf_tm);
return action;
}
static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u32 packets,
u64 lastuse, bool hw)
{
struct tcf_gact *gact = to_gact(a);
int action = READ_ONCE(gact->tcf_action);
struct tcf_t *tm = &gact->tcf_tm;
_bstats_cpu_update(this_cpu_ptr(gact->common.cpu_bstats), bytes,
packets);
if (action == TC_ACT_SHOT)
this_cpu_ptr(gact->common.cpu_qstats)->drops += packets;
if (hw)
_bstats_cpu_update(this_cpu_ptr(gact->common.cpu_bstats_hw),
bytes, packets);
tm->lastuse = max_t(u64, tm->lastuse, lastuse);
}
static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a,
int bind, int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_gact *gact = to_gact(a);
struct tc_gact opt = {
.index = gact->tcf_index,
.refcnt = refcount_read(&gact->tcf_refcnt) - ref,
.bindcnt = atomic_read(&gact->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>
2018-08-15 02:46:16 +08:00
spin_lock_bh(&gact->tcf_lock);
opt.action = gact->tcf_action;
if (nla_put(skb, TCA_GACT_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
#ifdef CONFIG_GACT_PROB
if (gact->tcfg_ptype) {
struct tc_gact_p p_opt = {
.paction = gact->tcfg_paction,
.pval = gact->tcfg_pval,
.ptype = gact->tcfg_ptype,
};
if (nla_put(skb, TCA_GACT_PROB, sizeof(p_opt), &p_opt))
goto nla_put_failure;
}
#endif
tcf_tm_dump(&t, &gact->tcf_tm);
if (nla_put_64bit(skb, TCA_GACT_TM, sizeof(t), &t, TCA_GACT_PAD))
goto nla_put_failure;
net: sched: always disable bh when taking tcf_lock Recently, ops->init() and ops->dump() of all actions were modified to always obtain tcf_lock when accessing private action state. Actions that don't depend on tcf_lock for synchronization with their data path use non-bh locking API. However, tcf_lock is also used to protect rate estimator stats in softirq context by timer callback. Change ops->init() and ops->dump() of all actions to disable bh when using tcf_lock to prevent deadlock reported by following lockdep warning: [ 105.470398] ================================ [ 105.475014] WARNING: inconsistent lock state [ 105.479628] 4.18.0-rc8+ #664 Not tainted [ 105.483897] -------------------------------- [ 105.488511] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. [ 105.494871] swapper/16/0 [HC0[0]:SC1[1]:HE1:SE0] takes: [ 105.500449] 00000000f86c012e (&(&p->tcfa_lock)->rlock){+.?.}, at: est_fetch_counters+0x3c/0xa0 [ 105.509696] {SOFTIRQ-ON-W} state was registered at: [ 105.514925] _raw_spin_lock+0x2c/0x40 [ 105.519022] tcf_bpf_init+0x579/0x820 [act_bpf] [ 105.523990] tcf_action_init_1+0x4e4/0x660 [ 105.528518] tcf_action_init+0x1ce/0x2d0 [ 105.532880] tcf_exts_validate+0x1d8/0x200 [ 105.537416] fl_change+0x55a/0x268b [cls_flower] [ 105.542469] tc_new_tfilter+0x748/0xa20 [ 105.546738] rtnetlink_rcv_msg+0x56a/0x6d0 [ 105.551268] netlink_rcv_skb+0x18d/0x200 [ 105.555628] netlink_unicast+0x2d0/0x370 [ 105.559990] netlink_sendmsg+0x3b9/0x6a0 [ 105.564349] sock_sendmsg+0x6b/0x80 [ 105.568271] ___sys_sendmsg+0x4a1/0x520 [ 105.572547] __sys_sendmsg+0xd7/0x150 [ 105.576655] do_syscall_64+0x72/0x2c0 [ 105.580757] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 105.586243] irq event stamp: 489296 [ 105.590084] hardirqs last enabled at (489296): [<ffffffffb507e639>] _raw_spin_unlock_irq+0x29/0x40 [ 105.599765] hardirqs last disabled at (489295): [<ffffffffb507e745>] _raw_spin_lock_irq+0x15/0x50 [ 105.609277] softirqs last enabled at (489292): [<ffffffffb413a6a3>] irq_enter+0x83/0xa0 [ 105.618001] softirqs last disabled at (489293): [<ffffffffb413a800>] irq_exit+0x140/0x190 [ 105.626813] other info that might help us debug this: [ 105.633976] Possible unsafe locking scenario: [ 105.640526] CPU0 [ 105.643325] ---- [ 105.646125] lock(&(&p->tcfa_lock)->rlock); [ 105.650747] <Interrupt> [ 105.653717] lock(&(&p->tcfa_lock)->rlock); [ 105.658514] *** DEADLOCK *** [ 105.665349] 1 lock held by swapper/16/0: [ 105.669629] #0: 00000000a640ad99 ((&est->timer)){+.-.}, at: call_timer_fn+0x10b/0x550 [ 105.678200] stack backtrace: [ 105.683194] CPU: 16 PID: 0 Comm: swapper/16 Not tainted 4.18.0-rc8+ #664 [ 105.690249] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 105.698626] Call Trace: [ 105.701421] <IRQ> [ 105.703791] dump_stack+0x92/0xeb [ 105.707461] print_usage_bug+0x336/0x34c [ 105.711744] mark_lock+0x7c9/0x980 [ 105.715500] ? print_shortest_lock_dependencies+0x2e0/0x2e0 [ 105.721424] ? check_usage_forwards+0x230/0x230 [ 105.726315] __lock_acquire+0x923/0x26f0 [ 105.730597] ? debug_show_all_locks+0x240/0x240 [ 105.735478] ? mark_lock+0x493/0x980 [ 105.739412] ? check_chain_key+0x140/0x1f0 [ 105.743861] ? __lock_acquire+0x836/0x26f0 [ 105.748323] ? lock_acquire+0x12e/0x290 [ 105.752516] lock_acquire+0x12e/0x290 [ 105.756539] ? est_fetch_counters+0x3c/0xa0 [ 105.761084] _raw_spin_lock+0x2c/0x40 [ 105.765099] ? est_fetch_counters+0x3c/0xa0 [ 105.769633] est_fetch_counters+0x3c/0xa0 [ 105.773995] est_timer+0x87/0x390 [ 105.777670] ? est_fetch_counters+0xa0/0xa0 [ 105.782210] ? lock_acquire+0x12e/0x290 [ 105.786410] call_timer_fn+0x161/0x550 [ 105.790512] ? est_fetch_counters+0xa0/0xa0 [ 105.795055] ? del_timer_sync+0xd0/0xd0 [ 105.799249] ? __lock_is_held+0x93/0x110 [ 105.803531] ? mark_held_locks+0x20/0xe0 [ 105.807813] ? _raw_spin_unlock_irq+0x29/0x40 [ 105.812525] ? est_fetch_counters+0xa0/0xa0 [ 105.817069] ? est_fetch_counters+0xa0/0xa0 [ 105.821610] run_timer_softirq+0x3c4/0x9f0 [ 105.826064] ? lock_acquire+0x12e/0x290 [ 105.830257] ? __bpf_trace_timer_class+0x10/0x10 [ 105.835237] ? __lock_is_held+0x25/0x110 [ 105.839517] __do_softirq+0x11d/0x7bf [ 105.843542] irq_exit+0x140/0x190 [ 105.847208] smp_apic_timer_interrupt+0xac/0x3b0 [ 105.852182] apic_timer_interrupt+0xf/0x20 [ 105.856628] </IRQ> [ 105.859081] RIP: 0010:cpuidle_enter_state+0xd8/0x4d0 [ 105.864395] Code: 46 ff 48 89 44 24 08 0f 1f 44 00 00 31 ff e8 cf ec 46 ff 80 7c 24 07 00 0f 85 1d 02 00 00 e8 9f 90 4b ff fb 66 0f 1f 44 00 00 <4c> 8b 6c 24 08 4d 29 fd 0f 80 36 03 00 00 4c 89 e8 48 ba cf f7 53 [ 105.884288] RSP: 0018:ffff8803ad94fd20 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 [ 105.892494] RAX: 0000000000000000 RBX: ffffe8fb300829c0 RCX: ffffffffb41e19e1 [ 105.899988] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8803ad9358ac [ 105.907503] RBP: ffffffffb6636300 R08: 0000000000000004 R09: 0000000000000000 [ 105.914997] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000004 [ 105.922487] R13: ffffffffb6636140 R14: ffffffffb66362d8 R15: 000000188d36091b [ 105.929988] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.935232] do_idle+0x28e/0x320 [ 105.938817] ? arch_cpu_idle_exit+0x40/0x40 [ 105.943361] ? mark_lock+0x8c1/0x980 [ 105.947295] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.952619] cpu_startup_entry+0xc2/0xd0 [ 105.956900] ? cpu_in_idle+0x20/0x20 [ 105.960830] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.966146] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.971391] start_secondary+0x2b5/0x360 [ 105.975669] ? set_cpu_sibling_map+0x1330/0x1330 [ 105.980654] secondary_startup_64+0xa5/0xb0 Taking tcf_lock in sample action with bh disabled causes lockdep to issue a warning regarding possible irq lock inversion dependency between tcf_lock, and psample_groups_lock that is taken when holding tcf_lock in sample init: [ 162.108959] Possible interrupt unsafe locking scenario: [ 162.116386] CPU0 CPU1 [ 162.121277] ---- ---- [ 162.126162] lock(psample_groups_lock); [ 162.130447] local_irq_disable(); [ 162.136772] lock(&(&p->tcfa_lock)->rlock); [ 162.143957] lock(psample_groups_lock); [ 162.150813] <Interrupt> [ 162.153808] lock(&(&p->tcfa_lock)->rlock); [ 162.158608] *** DEADLOCK *** In order to prevent potential lock inversion dependency between tcf_lock and psample_groups_lock, extract call to psample_group_get() from tcf_lock protected section in sample action init function. Fixes: 4e232818bd32 ("net: sched: act_mirred: remove dependency on rtnl lock") Fixes: 764e9a24480f ("net: sched: act_vlan: remove dependency on rtnl lock") Fixes: 729e01260989 ("net: sched: act_tunnel_key: remove dependency on rtnl lock") Fixes: d77284956656 ("net: sched: act_sample: remove dependency on rtnl lock") Fixes: e8917f437006 ("net: sched: act_gact: remove dependency on rtnl lock") Fixes: b6a2b971c0b0 ("net: sched: act_csum: remove dependency on rtnl lock") Fixes: 2142236b4584 ("net: sched: act_bpf: remove dependency on rtnl lock") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-15 02:46:16 +08:00
spin_unlock_bh(&gact->tcf_lock);
return skb->len;
nla_put_failure:
net: sched: always disable bh when taking tcf_lock Recently, ops->init() and ops->dump() of all actions were modified to always obtain tcf_lock when accessing private action state. Actions that don't depend on tcf_lock for synchronization with their data path use non-bh locking API. However, tcf_lock is also used to protect rate estimator stats in softirq context by timer callback. Change ops->init() and ops->dump() of all actions to disable bh when using tcf_lock to prevent deadlock reported by following lockdep warning: [ 105.470398] ================================ [ 105.475014] WARNING: inconsistent lock state [ 105.479628] 4.18.0-rc8+ #664 Not tainted [ 105.483897] -------------------------------- [ 105.488511] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. [ 105.494871] swapper/16/0 [HC0[0]:SC1[1]:HE1:SE0] takes: [ 105.500449] 00000000f86c012e (&(&p->tcfa_lock)->rlock){+.?.}, at: est_fetch_counters+0x3c/0xa0 [ 105.509696] {SOFTIRQ-ON-W} state was registered at: [ 105.514925] _raw_spin_lock+0x2c/0x40 [ 105.519022] tcf_bpf_init+0x579/0x820 [act_bpf] [ 105.523990] tcf_action_init_1+0x4e4/0x660 [ 105.528518] tcf_action_init+0x1ce/0x2d0 [ 105.532880] tcf_exts_validate+0x1d8/0x200 [ 105.537416] fl_change+0x55a/0x268b [cls_flower] [ 105.542469] tc_new_tfilter+0x748/0xa20 [ 105.546738] rtnetlink_rcv_msg+0x56a/0x6d0 [ 105.551268] netlink_rcv_skb+0x18d/0x200 [ 105.555628] netlink_unicast+0x2d0/0x370 [ 105.559990] netlink_sendmsg+0x3b9/0x6a0 [ 105.564349] sock_sendmsg+0x6b/0x80 [ 105.568271] ___sys_sendmsg+0x4a1/0x520 [ 105.572547] __sys_sendmsg+0xd7/0x150 [ 105.576655] do_syscall_64+0x72/0x2c0 [ 105.580757] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 105.586243] irq event stamp: 489296 [ 105.590084] hardirqs last enabled at (489296): [<ffffffffb507e639>] _raw_spin_unlock_irq+0x29/0x40 [ 105.599765] hardirqs last disabled at (489295): [<ffffffffb507e745>] _raw_spin_lock_irq+0x15/0x50 [ 105.609277] softirqs last enabled at (489292): [<ffffffffb413a6a3>] irq_enter+0x83/0xa0 [ 105.618001] softirqs last disabled at (489293): [<ffffffffb413a800>] irq_exit+0x140/0x190 [ 105.626813] other info that might help us debug this: [ 105.633976] Possible unsafe locking scenario: [ 105.640526] CPU0 [ 105.643325] ---- [ 105.646125] lock(&(&p->tcfa_lock)->rlock); [ 105.650747] <Interrupt> [ 105.653717] lock(&(&p->tcfa_lock)->rlock); [ 105.658514] *** DEADLOCK *** [ 105.665349] 1 lock held by swapper/16/0: [ 105.669629] #0: 00000000a640ad99 ((&est->timer)){+.-.}, at: call_timer_fn+0x10b/0x550 [ 105.678200] stack backtrace: [ 105.683194] CPU: 16 PID: 0 Comm: swapper/16 Not tainted 4.18.0-rc8+ #664 [ 105.690249] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 105.698626] Call Trace: [ 105.701421] <IRQ> [ 105.703791] dump_stack+0x92/0xeb [ 105.707461] print_usage_bug+0x336/0x34c [ 105.711744] mark_lock+0x7c9/0x980 [ 105.715500] ? print_shortest_lock_dependencies+0x2e0/0x2e0 [ 105.721424] ? check_usage_forwards+0x230/0x230 [ 105.726315] __lock_acquire+0x923/0x26f0 [ 105.730597] ? debug_show_all_locks+0x240/0x240 [ 105.735478] ? mark_lock+0x493/0x980 [ 105.739412] ? check_chain_key+0x140/0x1f0 [ 105.743861] ? __lock_acquire+0x836/0x26f0 [ 105.748323] ? lock_acquire+0x12e/0x290 [ 105.752516] lock_acquire+0x12e/0x290 [ 105.756539] ? est_fetch_counters+0x3c/0xa0 [ 105.761084] _raw_spin_lock+0x2c/0x40 [ 105.765099] ? est_fetch_counters+0x3c/0xa0 [ 105.769633] est_fetch_counters+0x3c/0xa0 [ 105.773995] est_timer+0x87/0x390 [ 105.777670] ? est_fetch_counters+0xa0/0xa0 [ 105.782210] ? lock_acquire+0x12e/0x290 [ 105.786410] call_timer_fn+0x161/0x550 [ 105.790512] ? est_fetch_counters+0xa0/0xa0 [ 105.795055] ? del_timer_sync+0xd0/0xd0 [ 105.799249] ? __lock_is_held+0x93/0x110 [ 105.803531] ? mark_held_locks+0x20/0xe0 [ 105.807813] ? _raw_spin_unlock_irq+0x29/0x40 [ 105.812525] ? est_fetch_counters+0xa0/0xa0 [ 105.817069] ? est_fetch_counters+0xa0/0xa0 [ 105.821610] run_timer_softirq+0x3c4/0x9f0 [ 105.826064] ? lock_acquire+0x12e/0x290 [ 105.830257] ? __bpf_trace_timer_class+0x10/0x10 [ 105.835237] ? __lock_is_held+0x25/0x110 [ 105.839517] __do_softirq+0x11d/0x7bf [ 105.843542] irq_exit+0x140/0x190 [ 105.847208] smp_apic_timer_interrupt+0xac/0x3b0 [ 105.852182] apic_timer_interrupt+0xf/0x20 [ 105.856628] </IRQ> [ 105.859081] RIP: 0010:cpuidle_enter_state+0xd8/0x4d0 [ 105.864395] Code: 46 ff 48 89 44 24 08 0f 1f 44 00 00 31 ff e8 cf ec 46 ff 80 7c 24 07 00 0f 85 1d 02 00 00 e8 9f 90 4b ff fb 66 0f 1f 44 00 00 <4c> 8b 6c 24 08 4d 29 fd 0f 80 36 03 00 00 4c 89 e8 48 ba cf f7 53 [ 105.884288] RSP: 0018:ffff8803ad94fd20 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 [ 105.892494] RAX: 0000000000000000 RBX: ffffe8fb300829c0 RCX: ffffffffb41e19e1 [ 105.899988] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8803ad9358ac [ 105.907503] RBP: ffffffffb6636300 R08: 0000000000000004 R09: 0000000000000000 [ 105.914997] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000004 [ 105.922487] R13: ffffffffb6636140 R14: ffffffffb66362d8 R15: 000000188d36091b [ 105.929988] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.935232] do_idle+0x28e/0x320 [ 105.938817] ? arch_cpu_idle_exit+0x40/0x40 [ 105.943361] ? mark_lock+0x8c1/0x980 [ 105.947295] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.952619] cpu_startup_entry+0xc2/0xd0 [ 105.956900] ? cpu_in_idle+0x20/0x20 [ 105.960830] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.966146] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.971391] start_secondary+0x2b5/0x360 [ 105.975669] ? set_cpu_sibling_map+0x1330/0x1330 [ 105.980654] secondary_startup_64+0xa5/0xb0 Taking tcf_lock in sample action with bh disabled causes lockdep to issue a warning regarding possible irq lock inversion dependency between tcf_lock, and psample_groups_lock that is taken when holding tcf_lock in sample init: [ 162.108959] Possible interrupt unsafe locking scenario: [ 162.116386] CPU0 CPU1 [ 162.121277] ---- ---- [ 162.126162] lock(psample_groups_lock); [ 162.130447] local_irq_disable(); [ 162.136772] lock(&(&p->tcfa_lock)->rlock); [ 162.143957] lock(psample_groups_lock); [ 162.150813] <Interrupt> [ 162.153808] lock(&(&p->tcfa_lock)->rlock); [ 162.158608] *** DEADLOCK *** In order to prevent potential lock inversion dependency between tcf_lock and psample_groups_lock, extract call to psample_group_get() from tcf_lock protected section in sample action init function. Fixes: 4e232818bd32 ("net: sched: act_mirred: remove dependency on rtnl lock") Fixes: 764e9a24480f ("net: sched: act_vlan: remove dependency on rtnl lock") Fixes: 729e01260989 ("net: sched: act_tunnel_key: remove dependency on rtnl lock") Fixes: d77284956656 ("net: sched: act_sample: remove dependency on rtnl lock") Fixes: e8917f437006 ("net: sched: act_gact: remove dependency on rtnl lock") Fixes: b6a2b971c0b0 ("net: sched: act_csum: remove dependency on rtnl lock") Fixes: 2142236b4584 ("net: sched: act_bpf: remove dependency on rtnl lock") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-15 02:46:16 +08:00
spin_unlock_bh(&gact->tcf_lock);
nlmsg_trim(skb, b);
return -1;
}
static int tcf_gact_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, gact_net_id);
return tcf_generic_walker(tn, skb, cb, type, ops, extack);
}
static int tcf_gact_search(struct net *net, struct tc_action **a, u32 index)
{
struct tc_action_net *tn = net_generic(net, gact_net_id);
return tcf_idr_search(tn, a, index);
}
static size_t tcf_gact_get_fill_size(const struct tc_action *act)
{
size_t sz = nla_total_size(sizeof(struct tc_gact)); /* TCA_GACT_PARMS */
#ifdef CONFIG_GACT_PROB
if (to_gact(act)->tcfg_ptype)
/* TCA_GACT_PROB */
sz += nla_total_size(sizeof(struct tc_gact_p));
#endif
return sz;
}
static struct tc_action_ops act_gact_ops = {
.kind = "gact",
.id = TCA_ID_GACT,
.owner = THIS_MODULE,
.act = tcf_gact_act,
.stats_update = tcf_gact_stats_update,
.dump = tcf_gact_dump,
.init = tcf_gact_init,
.walk = tcf_gact_walker,
.lookup = tcf_gact_search,
.get_fill_size = tcf_gact_get_fill_size,
.size = sizeof(struct tcf_gact),
};
static __net_init int gact_init_net(struct net *net)
{
struct tc_action_net *tn = net_generic(net, gact_net_id);
return tc_action_net_init(tn, &act_gact_ops);
}
static void __net_exit gact_exit_net(struct list_head *net_list)
{
tc_action_net_exit(net_list, gact_net_id);
}
static struct pernet_operations gact_net_ops = {
.init = gact_init_net,
.exit_batch = gact_exit_net,
.id = &gact_net_id,
.size = sizeof(struct tc_action_net),
};
MODULE_AUTHOR("Jamal Hadi Salim(2002-4)");
MODULE_DESCRIPTION("Generic Classifier actions");
MODULE_LICENSE("GPL");
static int __init gact_init_module(void)
{
#ifdef CONFIG_GACT_PROB
pr_info("GACT probability on\n");
#else
pr_info("GACT probability NOT on\n");
#endif
return tcf_register_action(&act_gact_ops, &gact_net_ops);
}
static void __exit gact_cleanup_module(void)
{
tcf_unregister_action(&act_gact_ops, &gact_net_ops);
}
module_init(gact_init_module);
module_exit(gact_cleanup_module);