linux/net/sched/act_csum.c

747 lines
17 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Checksum updating actions
*
* Copyright (c) 2010 Gregoire Baron <baronchon@n7mm.org>
*/
#include <linux/types.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/netlink.h>
#include <net/netlink.h>
#include <linux/rtnetlink.h>
#include <linux/skbuff.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/icmp.h>
#include <linux/icmpv6.h>
#include <linux/igmp.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <net/ip6_checksum.h>
#include <net/sctp/checksum.h>
#include <net/act_api.h>
net/sched: act_csum: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall action csum icmp pass index 90 # tc actions replace action csum icmp goto chain 42 index 90 \ > cookie c1a0c1a0 # tc actions show action csum 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: csum (icmp) action 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 8000000074692067 P4D 8000000074692067 PUD 2e210067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 0 Comm: swapper/0 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:ffff93153da03be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9314ee40f700 RCX: 0000000000003a00 RDX: 0000000000000000 RSI: ffff931537c87828 RDI: ffff931537c87818 RBP: ffff93153da03c80 R08: 00000000527cffff R09: 0000000000000003 R10: 000000000000003f R11: 0000000000000028 R12: ffff9314edf68400 R13: ffff9314edf68408 R14: 0000000000000001 R15: ffff9314ed67b600 FS: 0000000000000000(0000) GS:ffff93153da00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000073e32003 CR4: 00000000001606f0 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: 66 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:ffffffff9a803e98 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffff99e184f0 RBX: 0000000000000000 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000000 RBP: 0000000000000000 R08: 000eb5c4572376b3 R09: 0000000000000000 R10: ffffa53e806a3ca0 R11: 00000000000f4240 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x1/0x1 default_idle+0x1c/0x140 do_idle+0x1c4/0x280 cpu_startup_entry+0x19/0x20 start_kernel+0x49e/0x4be secondary_startup_64+0xa4/0xb0 Modules linked in: act_csum veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul snd_hda_codec_generic ghash_clmulni_intel snd_hda_intel mbcache snd_hda_codec jbd2 snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd snd_timer glue_helper snd joydev virtio_balloon pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect virtio_net sysimgblt net_failover fb_sys_fops virtio_console virtio_blk ttm failover drm ata_piix crc32c_intel floppy virtio_pci serio_raw libata virtio_ring virtio dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_csum_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 14:00:01 +00:00
#include <net/pkt_cls.h>
#include <linux/tc_act/tc_csum.h>
#include <net/tc_act/tc_csum.h>
static const struct nla_policy csum_policy[TCA_CSUM_MAX + 1] = {
[TCA_CSUM_PARMS] = { .len = sizeof(struct tc_csum), },
};
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 01:58:21 +00:00
static unsigned int csum_net_id;
static struct tc_action_ops act_csum_ops;
static int tcf_csum_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,
u32 flags, struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, csum_net_id);
struct tcf_csum_params *params_new;
struct nlattr *tb[TCA_CSUM_MAX + 1];
net/sched: act_csum: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall action csum icmp pass index 90 # tc actions replace action csum icmp goto chain 42 index 90 \ > cookie c1a0c1a0 # tc actions show action csum 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: csum (icmp) action 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 8000000074692067 P4D 8000000074692067 PUD 2e210067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 0 Comm: swapper/0 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:ffff93153da03be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9314ee40f700 RCX: 0000000000003a00 RDX: 0000000000000000 RSI: ffff931537c87828 RDI: ffff931537c87818 RBP: ffff93153da03c80 R08: 00000000527cffff R09: 0000000000000003 R10: 000000000000003f R11: 0000000000000028 R12: ffff9314edf68400 R13: ffff9314edf68408 R14: 0000000000000001 R15: ffff9314ed67b600 FS: 0000000000000000(0000) GS:ffff93153da00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000073e32003 CR4: 00000000001606f0 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: 66 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:ffffffff9a803e98 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffff99e184f0 RBX: 0000000000000000 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000000 RBP: 0000000000000000 R08: 000eb5c4572376b3 R09: 0000000000000000 R10: ffffa53e806a3ca0 R11: 00000000000f4240 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x1/0x1 default_idle+0x1c/0x140 do_idle+0x1c4/0x280 cpu_startup_entry+0x19/0x20 start_kernel+0x49e/0x4be secondary_startup_64+0xa4/0xb0 Modules linked in: act_csum veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul snd_hda_codec_generic ghash_clmulni_intel snd_hda_intel mbcache snd_hda_codec jbd2 snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd snd_timer glue_helper snd joydev virtio_balloon pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect virtio_net sysimgblt net_failover fb_sys_fops virtio_console virtio_blk ttm failover drm ata_piix crc32c_intel floppy virtio_pci serio_raw libata virtio_ring virtio dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_csum_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 14:00:01 +00:00
struct tcf_chain *goto_ch = NULL;
struct tc_csum *parm;
struct tcf_csum *p;
int ret = 0, err;
u32 index;
if (nla == NULL)
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
err = nla_parse_nested_deprecated(tb, TCA_CSUM_MAX, nla, csum_policy,
NULL);
if (err < 0)
return err;
if (tb[TCA_CSUM_PARMS] == NULL)
return -EINVAL;
parm = nla_data(tb[TCA_CSUM_PARMS]);
index = parm->index;
err = tcf_idr_check_alloc(tn, &index, a, bind);
if (!err) {
ret = tcf_idr_create_from_flags(tn, index, est, a,
&act_csum_ops, bind, flags);
if (ret) {
tcf_idr_cleanup(tn, 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_csum: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall action csum icmp pass index 90 # tc actions replace action csum icmp goto chain 42 index 90 \ > cookie c1a0c1a0 # tc actions show action csum 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: csum (icmp) action 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 8000000074692067 P4D 8000000074692067 PUD 2e210067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 0 Comm: swapper/0 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:ffff93153da03be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9314ee40f700 RCX: 0000000000003a00 RDX: 0000000000000000 RSI: ffff931537c87828 RDI: ffff931537c87818 RBP: ffff93153da03c80 R08: 00000000527cffff R09: 0000000000000003 R10: 000000000000003f R11: 0000000000000028 R12: ffff9314edf68400 R13: ffff9314edf68408 R14: 0000000000000001 R15: ffff9314ed67b600 FS: 0000000000000000(0000) GS:ffff93153da00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000073e32003 CR4: 00000000001606f0 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: 66 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:ffffffff9a803e98 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffff99e184f0 RBX: 0000000000000000 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000000 RBP: 0000000000000000 R08: 000eb5c4572376b3 R09: 0000000000000000 R10: ffffa53e806a3ca0 R11: 00000000000f4240 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x1/0x1 default_idle+0x1c/0x140 do_idle+0x1c4/0x280 cpu_startup_entry+0x19/0x20 start_kernel+0x49e/0x4be secondary_startup_64+0xa4/0xb0 Modules linked in: act_csum veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul snd_hda_codec_generic ghash_clmulni_intel snd_hda_intel mbcache snd_hda_codec jbd2 snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd snd_timer glue_helper snd joydev virtio_balloon pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect virtio_net sysimgblt net_failover fb_sys_fops virtio_console virtio_blk ttm failover drm ata_piix crc32c_intel floppy virtio_pci serio_raw libata virtio_ring virtio dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_csum_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 14:00:01 +00:00
err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
if (err < 0)
goto release_idr;
p = to_tcf_csum(*a);
params_new = kzalloc(sizeof(*params_new), GFP_KERNEL);
if (unlikely(!params_new)) {
net/sched: act_csum: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall action csum icmp pass index 90 # tc actions replace action csum icmp goto chain 42 index 90 \ > cookie c1a0c1a0 # tc actions show action csum 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: csum (icmp) action 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 8000000074692067 P4D 8000000074692067 PUD 2e210067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 0 Comm: swapper/0 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:ffff93153da03be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9314ee40f700 RCX: 0000000000003a00 RDX: 0000000000000000 RSI: ffff931537c87828 RDI: ffff931537c87818 RBP: ffff93153da03c80 R08: 00000000527cffff R09: 0000000000000003 R10: 000000000000003f R11: 0000000000000028 R12: ffff9314edf68400 R13: ffff9314edf68408 R14: 0000000000000001 R15: ffff9314ed67b600 FS: 0000000000000000(0000) GS:ffff93153da00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000073e32003 CR4: 00000000001606f0 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: 66 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:ffffffff9a803e98 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffff99e184f0 RBX: 0000000000000000 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000000 RBP: 0000000000000000 R08: 000eb5c4572376b3 R09: 0000000000000000 R10: ffffa53e806a3ca0 R11: 00000000000f4240 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x1/0x1 default_idle+0x1c/0x140 do_idle+0x1c4/0x280 cpu_startup_entry+0x19/0x20 start_kernel+0x49e/0x4be secondary_startup_64+0xa4/0xb0 Modules linked in: act_csum veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul snd_hda_codec_generic ghash_clmulni_intel snd_hda_intel mbcache snd_hda_codec jbd2 snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd snd_timer glue_helper snd joydev virtio_balloon pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect virtio_net sysimgblt net_failover fb_sys_fops virtio_console virtio_blk ttm failover drm ata_piix crc32c_intel floppy virtio_pci serio_raw libata virtio_ring virtio dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_csum_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 14:00:01 +00:00
err = -ENOMEM;
goto put_chain;
}
params_new->update_flags = parm->update_flags;
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(&p->tcf_lock);
net/sched: act_csum: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall action csum icmp pass index 90 # tc actions replace action csum icmp goto chain 42 index 90 \ > cookie c1a0c1a0 # tc actions show action csum 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: csum (icmp) action 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 8000000074692067 P4D 8000000074692067 PUD 2e210067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 0 Comm: swapper/0 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:ffff93153da03be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9314ee40f700 RCX: 0000000000003a00 RDX: 0000000000000000 RSI: ffff931537c87828 RDI: ffff931537c87818 RBP: ffff93153da03c80 R08: 00000000527cffff R09: 0000000000000003 R10: 000000000000003f R11: 0000000000000028 R12: ffff9314edf68400 R13: ffff9314edf68408 R14: 0000000000000001 R15: ffff9314ed67b600 FS: 0000000000000000(0000) GS:ffff93153da00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000073e32003 CR4: 00000000001606f0 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: 66 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:ffffffff9a803e98 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffff99e184f0 RBX: 0000000000000000 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000000 RBP: 0000000000000000 R08: 000eb5c4572376b3 R09: 0000000000000000 R10: ffffa53e806a3ca0 R11: 00000000000f4240 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x1/0x1 default_idle+0x1c/0x140 do_idle+0x1c4/0x280 cpu_startup_entry+0x19/0x20 start_kernel+0x49e/0x4be secondary_startup_64+0xa4/0xb0 Modules linked in: act_csum veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul snd_hda_codec_generic ghash_clmulni_intel snd_hda_intel mbcache snd_hda_codec jbd2 snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd snd_timer glue_helper snd joydev virtio_balloon pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect virtio_net sysimgblt net_failover fb_sys_fops virtio_console virtio_blk ttm failover drm ata_piix crc32c_intel floppy virtio_pci serio_raw libata virtio_ring virtio dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_csum_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 14:00:01 +00:00
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
params_new = rcu_replace_pointer(p->params, params_new,
lockdep_is_held(&p->tcf_lock));
net: sched: always disable bh when taking tcf_lock Recently, ops->init() and ops->dump() of all actions were modified to always obtain tcf_lock when accessing private action state. Actions that don't depend on tcf_lock for synchronization with their data path use non-bh locking API. However, tcf_lock is also used to protect rate estimator stats in softirq context by timer callback. Change ops->init() and ops->dump() of all actions to disable bh when using tcf_lock to prevent deadlock reported by following lockdep warning: [ 105.470398] ================================ [ 105.475014] WARNING: inconsistent lock state [ 105.479628] 4.18.0-rc8+ #664 Not tainted [ 105.483897] -------------------------------- [ 105.488511] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. [ 105.494871] swapper/16/0 [HC0[0]:SC1[1]:HE1:SE0] takes: [ 105.500449] 00000000f86c012e (&(&p->tcfa_lock)->rlock){+.?.}, at: est_fetch_counters+0x3c/0xa0 [ 105.509696] {SOFTIRQ-ON-W} state was registered at: [ 105.514925] _raw_spin_lock+0x2c/0x40 [ 105.519022] tcf_bpf_init+0x579/0x820 [act_bpf] [ 105.523990] tcf_action_init_1+0x4e4/0x660 [ 105.528518] tcf_action_init+0x1ce/0x2d0 [ 105.532880] tcf_exts_validate+0x1d8/0x200 [ 105.537416] fl_change+0x55a/0x268b [cls_flower] [ 105.542469] tc_new_tfilter+0x748/0xa20 [ 105.546738] rtnetlink_rcv_msg+0x56a/0x6d0 [ 105.551268] netlink_rcv_skb+0x18d/0x200 [ 105.555628] netlink_unicast+0x2d0/0x370 [ 105.559990] netlink_sendmsg+0x3b9/0x6a0 [ 105.564349] sock_sendmsg+0x6b/0x80 [ 105.568271] ___sys_sendmsg+0x4a1/0x520 [ 105.572547] __sys_sendmsg+0xd7/0x150 [ 105.576655] do_syscall_64+0x72/0x2c0 [ 105.580757] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 105.586243] irq event stamp: 489296 [ 105.590084] hardirqs last enabled at (489296): [<ffffffffb507e639>] _raw_spin_unlock_irq+0x29/0x40 [ 105.599765] hardirqs last disabled at (489295): [<ffffffffb507e745>] _raw_spin_lock_irq+0x15/0x50 [ 105.609277] softirqs last enabled at (489292): [<ffffffffb413a6a3>] irq_enter+0x83/0xa0 [ 105.618001] softirqs last disabled at (489293): [<ffffffffb413a800>] irq_exit+0x140/0x190 [ 105.626813] other info that might help us debug this: [ 105.633976] Possible unsafe locking scenario: [ 105.640526] CPU0 [ 105.643325] ---- [ 105.646125] lock(&(&p->tcfa_lock)->rlock); [ 105.650747] <Interrupt> [ 105.653717] lock(&(&p->tcfa_lock)->rlock); [ 105.658514] *** DEADLOCK *** [ 105.665349] 1 lock held by swapper/16/0: [ 105.669629] #0: 00000000a640ad99 ((&est->timer)){+.-.}, at: call_timer_fn+0x10b/0x550 [ 105.678200] stack backtrace: [ 105.683194] CPU: 16 PID: 0 Comm: swapper/16 Not tainted 4.18.0-rc8+ #664 [ 105.690249] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 105.698626] Call Trace: [ 105.701421] <IRQ> [ 105.703791] dump_stack+0x92/0xeb [ 105.707461] print_usage_bug+0x336/0x34c [ 105.711744] mark_lock+0x7c9/0x980 [ 105.715500] ? print_shortest_lock_dependencies+0x2e0/0x2e0 [ 105.721424] ? check_usage_forwards+0x230/0x230 [ 105.726315] __lock_acquire+0x923/0x26f0 [ 105.730597] ? debug_show_all_locks+0x240/0x240 [ 105.735478] ? mark_lock+0x493/0x980 [ 105.739412] ? check_chain_key+0x140/0x1f0 [ 105.743861] ? __lock_acquire+0x836/0x26f0 [ 105.748323] ? lock_acquire+0x12e/0x290 [ 105.752516] lock_acquire+0x12e/0x290 [ 105.756539] ? est_fetch_counters+0x3c/0xa0 [ 105.761084] _raw_spin_lock+0x2c/0x40 [ 105.765099] ? est_fetch_counters+0x3c/0xa0 [ 105.769633] est_fetch_counters+0x3c/0xa0 [ 105.773995] est_timer+0x87/0x390 [ 105.777670] ? est_fetch_counters+0xa0/0xa0 [ 105.782210] ? lock_acquire+0x12e/0x290 [ 105.786410] call_timer_fn+0x161/0x550 [ 105.790512] ? est_fetch_counters+0xa0/0xa0 [ 105.795055] ? del_timer_sync+0xd0/0xd0 [ 105.799249] ? __lock_is_held+0x93/0x110 [ 105.803531] ? mark_held_locks+0x20/0xe0 [ 105.807813] ? _raw_spin_unlock_irq+0x29/0x40 [ 105.812525] ? est_fetch_counters+0xa0/0xa0 [ 105.817069] ? est_fetch_counters+0xa0/0xa0 [ 105.821610] run_timer_softirq+0x3c4/0x9f0 [ 105.826064] ? lock_acquire+0x12e/0x290 [ 105.830257] ? __bpf_trace_timer_class+0x10/0x10 [ 105.835237] ? __lock_is_held+0x25/0x110 [ 105.839517] __do_softirq+0x11d/0x7bf [ 105.843542] irq_exit+0x140/0x190 [ 105.847208] smp_apic_timer_interrupt+0xac/0x3b0 [ 105.852182] apic_timer_interrupt+0xf/0x20 [ 105.856628] </IRQ> [ 105.859081] RIP: 0010:cpuidle_enter_state+0xd8/0x4d0 [ 105.864395] Code: 46 ff 48 89 44 24 08 0f 1f 44 00 00 31 ff e8 cf ec 46 ff 80 7c 24 07 00 0f 85 1d 02 00 00 e8 9f 90 4b ff fb 66 0f 1f 44 00 00 <4c> 8b 6c 24 08 4d 29 fd 0f 80 36 03 00 00 4c 89 e8 48 ba cf f7 53 [ 105.884288] RSP: 0018:ffff8803ad94fd20 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 [ 105.892494] RAX: 0000000000000000 RBX: ffffe8fb300829c0 RCX: ffffffffb41e19e1 [ 105.899988] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8803ad9358ac [ 105.907503] RBP: ffffffffb6636300 R08: 0000000000000004 R09: 0000000000000000 [ 105.914997] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000004 [ 105.922487] R13: ffffffffb6636140 R14: ffffffffb66362d8 R15: 000000188d36091b [ 105.929988] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.935232] do_idle+0x28e/0x320 [ 105.938817] ? arch_cpu_idle_exit+0x40/0x40 [ 105.943361] ? mark_lock+0x8c1/0x980 [ 105.947295] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.952619] cpu_startup_entry+0xc2/0xd0 [ 105.956900] ? cpu_in_idle+0x20/0x20 [ 105.960830] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.966146] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.971391] start_secondary+0x2b5/0x360 [ 105.975669] ? set_cpu_sibling_map+0x1330/0x1330 [ 105.980654] secondary_startup_64+0xa5/0xb0 Taking tcf_lock in sample action with bh disabled causes lockdep to issue a warning regarding possible irq lock inversion dependency between tcf_lock, and psample_groups_lock that is taken when holding tcf_lock in sample init: [ 162.108959] Possible interrupt unsafe locking scenario: [ 162.116386] CPU0 CPU1 [ 162.121277] ---- ---- [ 162.126162] lock(psample_groups_lock); [ 162.130447] local_irq_disable(); [ 162.136772] lock(&(&p->tcfa_lock)->rlock); [ 162.143957] lock(psample_groups_lock); [ 162.150813] <Interrupt> [ 162.153808] lock(&(&p->tcfa_lock)->rlock); [ 162.158608] *** DEADLOCK *** In order to prevent potential lock inversion dependency between tcf_lock and psample_groups_lock, extract call to psample_group_get() from tcf_lock protected section in sample action init function. Fixes: 4e232818bd32 ("net: sched: act_mirred: remove dependency on rtnl lock") Fixes: 764e9a24480f ("net: sched: act_vlan: remove dependency on rtnl lock") Fixes: 729e01260989 ("net: sched: act_tunnel_key: remove dependency on rtnl lock") Fixes: d77284956656 ("net: sched: act_sample: remove dependency on rtnl lock") Fixes: e8917f437006 ("net: sched: act_gact: remove dependency on rtnl lock") Fixes: b6a2b971c0b0 ("net: sched: act_csum: remove dependency on rtnl lock") Fixes: 2142236b4584 ("net: sched: act_bpf: remove dependency on rtnl lock") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-14 18:46:16 +00:00
spin_unlock_bh(&p->tcf_lock);
net/sched: act_csum: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall action csum icmp pass index 90 # tc actions replace action csum icmp goto chain 42 index 90 \ > cookie c1a0c1a0 # tc actions show action csum 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: csum (icmp) action 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 8000000074692067 P4D 8000000074692067 PUD 2e210067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 0 Comm: swapper/0 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:ffff93153da03be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9314ee40f700 RCX: 0000000000003a00 RDX: 0000000000000000 RSI: ffff931537c87828 RDI: ffff931537c87818 RBP: ffff93153da03c80 R08: 00000000527cffff R09: 0000000000000003 R10: 000000000000003f R11: 0000000000000028 R12: ffff9314edf68400 R13: ffff9314edf68408 R14: 0000000000000001 R15: ffff9314ed67b600 FS: 0000000000000000(0000) GS:ffff93153da00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000073e32003 CR4: 00000000001606f0 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: 66 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:ffffffff9a803e98 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffff99e184f0 RBX: 0000000000000000 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000000 RBP: 0000000000000000 R08: 000eb5c4572376b3 R09: 0000000000000000 R10: ffffa53e806a3ca0 R11: 00000000000f4240 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x1/0x1 default_idle+0x1c/0x140 do_idle+0x1c4/0x280 cpu_startup_entry+0x19/0x20 start_kernel+0x49e/0x4be secondary_startup_64+0xa4/0xb0 Modules linked in: act_csum veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul snd_hda_codec_generic ghash_clmulni_intel snd_hda_intel mbcache snd_hda_codec jbd2 snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd snd_timer glue_helper snd joydev virtio_balloon pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect virtio_net sysimgblt net_failover fb_sys_fops virtio_console virtio_blk ttm failover drm ata_piix crc32c_intel floppy virtio_pci serio_raw libata virtio_ring virtio dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_csum_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 14:00:01 +00:00
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
if (params_new)
kfree_rcu(params_new, rcu);
if (ret == ACT_P_CREATED)
tcf_idr_insert(tn, *a);
return ret;
net/sched: act_csum: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall action csum icmp pass index 90 # tc actions replace action csum icmp goto chain 42 index 90 \ > cookie c1a0c1a0 # tc actions show action csum 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: csum (icmp) action 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 8000000074692067 P4D 8000000074692067 PUD 2e210067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 0 Comm: swapper/0 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:ffff93153da03be0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9314ee40f700 RCX: 0000000000003a00 RDX: 0000000000000000 RSI: ffff931537c87828 RDI: ffff931537c87818 RBP: ffff93153da03c80 R08: 00000000527cffff R09: 0000000000000003 R10: 000000000000003f R11: 0000000000000028 R12: ffff9314edf68400 R13: ffff9314edf68408 R14: 0000000000000001 R15: ffff9314ed67b600 FS: 0000000000000000(0000) GS:ffff93153da00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000073e32003 CR4: 00000000001606f0 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: 66 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:ffffffff9a803e98 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffffffff99e184f0 RBX: 0000000000000000 RCX: 0000000000000001 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000000 RBP: 0000000000000000 R08: 000eb5c4572376b3 R09: 0000000000000000 R10: ffffa53e806a3ca0 R11: 00000000000f4240 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x1/0x1 default_idle+0x1c/0x140 do_idle+0x1c4/0x280 cpu_startup_entry+0x19/0x20 start_kernel+0x49e/0x4be secondary_startup_64+0xa4/0xb0 Modules linked in: act_csum veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul snd_hda_codec_generic ghash_clmulni_intel snd_hda_intel mbcache snd_hda_codec jbd2 snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd snd_timer glue_helper snd joydev virtio_balloon pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect virtio_net sysimgblt net_failover fb_sys_fops virtio_console virtio_blk ttm failover drm ata_piix crc32c_intel floppy virtio_pci serio_raw libata virtio_ring virtio dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_csum_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 14:00:01 +00:00
put_chain:
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
release_idr:
tcf_idr_release(*a, bind);
return err;
}
/**
* tcf_csum_skb_nextlayer - Get next layer pointer
* @skb: sk_buff to use
* @ihl: previous summed headers length
* @ipl: complete packet length
* @jhl: next header length
*
* Check the expected next layer availability in the specified sk_buff.
* Return the next layer pointer if pass, NULL otherwise.
*/
static void *tcf_csum_skb_nextlayer(struct sk_buff *skb,
unsigned int ihl, unsigned int ipl,
unsigned int jhl)
{
int ntkoff = skb_network_offset(skb);
int hl = ihl + jhl;
if (!pskb_may_pull(skb, ipl + ntkoff) || (ipl < hl) ||
skb_try_make_writable(skb, hl + ntkoff))
return NULL;
else
return (void *)(skb_network_header(skb) + ihl);
}
static int tcf_csum_ipv4_icmp(struct sk_buff *skb, unsigned int ihl,
unsigned int ipl)
{
struct icmphdr *icmph;
icmph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*icmph));
if (icmph == NULL)
return 0;
icmph->checksum = 0;
skb->csum = csum_partial(icmph, ipl - ihl, 0);
icmph->checksum = csum_fold(skb->csum);
skb->ip_summed = CHECKSUM_NONE;
return 1;
}
static int tcf_csum_ipv4_igmp(struct sk_buff *skb,
unsigned int ihl, unsigned int ipl)
{
struct igmphdr *igmph;
igmph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*igmph));
if (igmph == NULL)
return 0;
igmph->csum = 0;
skb->csum = csum_partial(igmph, ipl - ihl, 0);
igmph->csum = csum_fold(skb->csum);
skb->ip_summed = CHECKSUM_NONE;
return 1;
}
static int tcf_csum_ipv6_icmp(struct sk_buff *skb, unsigned int ihl,
unsigned int ipl)
{
struct icmp6hdr *icmp6h;
const struct ipv6hdr *ip6h;
icmp6h = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*icmp6h));
if (icmp6h == NULL)
return 0;
ip6h = ipv6_hdr(skb);
icmp6h->icmp6_cksum = 0;
skb->csum = csum_partial(icmp6h, ipl - ihl, 0);
icmp6h->icmp6_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
ipl - ihl, IPPROTO_ICMPV6,
skb->csum);
skb->ip_summed = CHECKSUM_NONE;
return 1;
}
static int tcf_csum_ipv4_tcp(struct sk_buff *skb, unsigned int ihl,
unsigned int ipl)
{
struct tcphdr *tcph;
const struct iphdr *iph;
if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
return 1;
tcph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*tcph));
if (tcph == NULL)
return 0;
iph = ip_hdr(skb);
tcph->check = 0;
skb->csum = csum_partial(tcph, ipl - ihl, 0);
tcph->check = tcp_v4_check(ipl - ihl,
iph->saddr, iph->daddr, skb->csum);
skb->ip_summed = CHECKSUM_NONE;
return 1;
}
static int tcf_csum_ipv6_tcp(struct sk_buff *skb, unsigned int ihl,
unsigned int ipl)
{
struct tcphdr *tcph;
const struct ipv6hdr *ip6h;
if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
return 1;
tcph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*tcph));
if (tcph == NULL)
return 0;
ip6h = ipv6_hdr(skb);
tcph->check = 0;
skb->csum = csum_partial(tcph, ipl - ihl, 0);
tcph->check = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
ipl - ihl, IPPROTO_TCP,
skb->csum);
skb->ip_summed = CHECKSUM_NONE;
return 1;
}
static int tcf_csum_ipv4_udp(struct sk_buff *skb, unsigned int ihl,
unsigned int ipl, int udplite)
{
struct udphdr *udph;
const struct iphdr *iph;
u16 ul;
net: accept UFO datagrams from tuntap and packet Tuntap and similar devices can inject GSO packets. Accept type VIRTIO_NET_HDR_GSO_UDP, even though not generating UFO natively. Processes are expected to use feature negotiation such as TUNSETOFFLOAD to detect supported offload types and refrain from injecting other packets. This process breaks down with live migration: guest kernels do not renegotiate flags, so destination hosts need to expose all features that the source host does. Partially revert the UFO removal from 182e0b6b5846~1..d9d30adf5677. This patch introduces nearly(*) no new code to simplify verification. It brings back verbatim tuntap UFO negotiation, VIRTIO_NET_HDR_GSO_UDP insertion and software UFO segmentation. It does not reinstate protocol stack support, hardware offload (NETIF_F_UFO), SKB_GSO_UDP tunneling in SKB_GSO_SOFTWARE or reception of VIRTIO_NET_HDR_GSO_UDP packets in tuntap. To support SKB_GSO_UDP reappearing in the stack, also reinstate logic in act_csum and openvswitch. Achieve equivalence with v4.13 HEAD by squashing in commit 939912216fa8 ("net: skb_needs_check() removes CHECKSUM_UNNECESSARY check for tx.") and reverting commit 8d63bee643f1 ("net: avoid skb_warn_bad_offload false positives on UFO"). (*) To avoid having to bring back skb_shinfo(skb)->ip6_frag_id, ipv6_proxy_select_ident is changed to return a __be32 and this is assigned directly to the frag_hdr. Also, SKB_GSO_UDP is inserted at the end of the enum to minimize code churn. Tested Booted a v4.13 guest kernel with QEMU. On a host kernel before this patch `ethtool -k eth0` shows UFO disabled. After the patch, it is enabled, same as on a v4.13 host kernel. A UFO packet sent from the guest appears on the tap device: host: nc -l -p -u 8000 & tcpdump -n -i tap0 guest: dd if=/dev/zero of=payload.txt bs=1 count=2000 nc -u 192.16.1.1 8000 < payload.txt Direct tap to tap transmission of VIRTIO_NET_HDR_GSO_UDP succeeds, packets arriving fragmented: ./with_tap_pair.sh ./tap_send_ufo tap0 tap1 (from https://github.com/wdebruij/kerneltools/tree/master/tests) Changes v1 -> v2 - simplified set_offload change (review comment) - documented test procedure Link: http://lkml.kernel.org/r/<CAF=yD-LuUeDuL9YWPJD9ykOZ0QCjNeznPDr6whqZ9NGMNF12Mw@mail.gmail.com> Fixes: fb652fdfe837 ("macvlan/macvtap: Remove NETIF_F_UFO advertisement.") Reported-by: Michal Kubecek <mkubecek@suse.cz> Signed-off-by: Willem de Bruijn <willemb@google.com> Acked-by: Jason Wang <jasowang@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-11-21 15:22:25 +00:00
if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
return 1;
/*
* Support both UDP and UDPLITE checksum algorithms, Don't use
* udph->len to get the real length without any protocol check,
* UDPLITE uses udph->len for another thing,
* Use iph->tot_len, or just ipl.
*/
udph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*udph));
if (udph == NULL)
return 0;
iph = ip_hdr(skb);
ul = ntohs(udph->len);
if (udplite || udph->check) {
udph->check = 0;
if (udplite) {
if (ul == 0)
skb->csum = csum_partial(udph, ipl - ihl, 0);
else if ((ul >= sizeof(*udph)) && (ul <= ipl - ihl))
skb->csum = csum_partial(udph, ul, 0);
else
goto ignore_obscure_skb;
} else {
if (ul != ipl - ihl)
goto ignore_obscure_skb;
skb->csum = csum_partial(udph, ul, 0);
}
udph->check = csum_tcpudp_magic(iph->saddr, iph->daddr,
ul, iph->protocol,
skb->csum);
if (!udph->check)
udph->check = CSUM_MANGLED_0;
}
skb->ip_summed = CHECKSUM_NONE;
ignore_obscure_skb:
return 1;
}
static int tcf_csum_ipv6_udp(struct sk_buff *skb, unsigned int ihl,
unsigned int ipl, int udplite)
{
struct udphdr *udph;
const struct ipv6hdr *ip6h;
u16 ul;
net: accept UFO datagrams from tuntap and packet Tuntap and similar devices can inject GSO packets. Accept type VIRTIO_NET_HDR_GSO_UDP, even though not generating UFO natively. Processes are expected to use feature negotiation such as TUNSETOFFLOAD to detect supported offload types and refrain from injecting other packets. This process breaks down with live migration: guest kernels do not renegotiate flags, so destination hosts need to expose all features that the source host does. Partially revert the UFO removal from 182e0b6b5846~1..d9d30adf5677. This patch introduces nearly(*) no new code to simplify verification. It brings back verbatim tuntap UFO negotiation, VIRTIO_NET_HDR_GSO_UDP insertion and software UFO segmentation. It does not reinstate protocol stack support, hardware offload (NETIF_F_UFO), SKB_GSO_UDP tunneling in SKB_GSO_SOFTWARE or reception of VIRTIO_NET_HDR_GSO_UDP packets in tuntap. To support SKB_GSO_UDP reappearing in the stack, also reinstate logic in act_csum and openvswitch. Achieve equivalence with v4.13 HEAD by squashing in commit 939912216fa8 ("net: skb_needs_check() removes CHECKSUM_UNNECESSARY check for tx.") and reverting commit 8d63bee643f1 ("net: avoid skb_warn_bad_offload false positives on UFO"). (*) To avoid having to bring back skb_shinfo(skb)->ip6_frag_id, ipv6_proxy_select_ident is changed to return a __be32 and this is assigned directly to the frag_hdr. Also, SKB_GSO_UDP is inserted at the end of the enum to minimize code churn. Tested Booted a v4.13 guest kernel with QEMU. On a host kernel before this patch `ethtool -k eth0` shows UFO disabled. After the patch, it is enabled, same as on a v4.13 host kernel. A UFO packet sent from the guest appears on the tap device: host: nc -l -p -u 8000 & tcpdump -n -i tap0 guest: dd if=/dev/zero of=payload.txt bs=1 count=2000 nc -u 192.16.1.1 8000 < payload.txt Direct tap to tap transmission of VIRTIO_NET_HDR_GSO_UDP succeeds, packets arriving fragmented: ./with_tap_pair.sh ./tap_send_ufo tap0 tap1 (from https://github.com/wdebruij/kerneltools/tree/master/tests) Changes v1 -> v2 - simplified set_offload change (review comment) - documented test procedure Link: http://lkml.kernel.org/r/<CAF=yD-LuUeDuL9YWPJD9ykOZ0QCjNeznPDr6whqZ9NGMNF12Mw@mail.gmail.com> Fixes: fb652fdfe837 ("macvlan/macvtap: Remove NETIF_F_UFO advertisement.") Reported-by: Michal Kubecek <mkubecek@suse.cz> Signed-off-by: Willem de Bruijn <willemb@google.com> Acked-by: Jason Wang <jasowang@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-11-21 15:22:25 +00:00
if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
return 1;
/*
* Support both UDP and UDPLITE checksum algorithms, Don't use
* udph->len to get the real length without any protocol check,
* UDPLITE uses udph->len for another thing,
* Use ip6h->payload_len + sizeof(*ip6h) ... , or just ipl.
*/
udph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*udph));
if (udph == NULL)
return 0;
ip6h = ipv6_hdr(skb);
ul = ntohs(udph->len);
udph->check = 0;
if (udplite) {
if (ul == 0)
skb->csum = csum_partial(udph, ipl - ihl, 0);
else if ((ul >= sizeof(*udph)) && (ul <= ipl - ihl))
skb->csum = csum_partial(udph, ul, 0);
else
goto ignore_obscure_skb;
} else {
if (ul != ipl - ihl)
goto ignore_obscure_skb;
skb->csum = csum_partial(udph, ul, 0);
}
udph->check = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, ul,
udplite ? IPPROTO_UDPLITE : IPPROTO_UDP,
skb->csum);
if (!udph->check)
udph->check = CSUM_MANGLED_0;
skb->ip_summed = CHECKSUM_NONE;
ignore_obscure_skb:
return 1;
}
static int tcf_csum_sctp(struct sk_buff *skb, unsigned int ihl,
unsigned int ipl)
{
struct sctphdr *sctph;
if (skb_is_gso(skb) && skb_is_gso_sctp(skb))
return 1;
sctph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*sctph));
if (!sctph)
return 0;
sctph->checksum = sctp_compute_cksum(skb,
skb_network_offset(skb) + ihl);
skb->ip_summed = CHECKSUM_NONE;
skb->csum_not_inet = 0;
return 1;
}
static int tcf_csum_ipv4(struct sk_buff *skb, u32 update_flags)
{
const struct iphdr *iph;
int ntkoff;
ntkoff = skb_network_offset(skb);
if (!pskb_may_pull(skb, sizeof(*iph) + ntkoff))
goto fail;
iph = ip_hdr(skb);
switch (iph->frag_off & htons(IP_OFFSET) ? 0 : iph->protocol) {
case IPPROTO_ICMP:
if (update_flags & TCA_CSUM_UPDATE_FLAG_ICMP)
if (!tcf_csum_ipv4_icmp(skb, iph->ihl * 4,
ntohs(iph->tot_len)))
goto fail;
break;
case IPPROTO_IGMP:
if (update_flags & TCA_CSUM_UPDATE_FLAG_IGMP)
if (!tcf_csum_ipv4_igmp(skb, iph->ihl * 4,
ntohs(iph->tot_len)))
goto fail;
break;
case IPPROTO_TCP:
if (update_flags & TCA_CSUM_UPDATE_FLAG_TCP)
if (!tcf_csum_ipv4_tcp(skb, iph->ihl * 4,
ntohs(iph->tot_len)))
goto fail;
break;
case IPPROTO_UDP:
if (update_flags & TCA_CSUM_UPDATE_FLAG_UDP)
if (!tcf_csum_ipv4_udp(skb, iph->ihl * 4,
ntohs(iph->tot_len), 0))
goto fail;
break;
case IPPROTO_UDPLITE:
if (update_flags & TCA_CSUM_UPDATE_FLAG_UDPLITE)
if (!tcf_csum_ipv4_udp(skb, iph->ihl * 4,
ntohs(iph->tot_len), 1))
goto fail;
break;
case IPPROTO_SCTP:
if ((update_flags & TCA_CSUM_UPDATE_FLAG_SCTP) &&
!tcf_csum_sctp(skb, iph->ihl * 4, ntohs(iph->tot_len)))
goto fail;
break;
}
if (update_flags & TCA_CSUM_UPDATE_FLAG_IPV4HDR) {
if (skb_try_make_writable(skb, sizeof(*iph) + ntkoff))
goto fail;
ip_send_check(ip_hdr(skb));
}
return 1;
fail:
return 0;
}
static int tcf_csum_ipv6_hopopts(struct ipv6_opt_hdr *ip6xh, unsigned int ixhl,
unsigned int *pl)
{
int off, len, optlen;
unsigned char *xh = (void *)ip6xh;
off = sizeof(*ip6xh);
len = ixhl - off;
while (len > 1) {
switch (xh[off]) {
case IPV6_TLV_PAD1:
optlen = 1;
break;
case IPV6_TLV_JUMBO:
optlen = xh[off + 1] + 2;
if (optlen != 6 || len < 6 || (off & 3) != 2)
/* wrong jumbo option length/alignment */
return 0;
*pl = ntohl(*(__be32 *)(xh + off + 2));
goto done;
default:
optlen = xh[off + 1] + 2;
if (optlen > len)
/* ignore obscure options */
goto done;
break;
}
off += optlen;
len -= optlen;
}
done:
return 1;
}
static int tcf_csum_ipv6(struct sk_buff *skb, u32 update_flags)
{
struct ipv6hdr *ip6h;
struct ipv6_opt_hdr *ip6xh;
unsigned int hl, ixhl;
unsigned int pl;
int ntkoff;
u8 nexthdr;
ntkoff = skb_network_offset(skb);
hl = sizeof(*ip6h);
if (!pskb_may_pull(skb, hl + ntkoff))
goto fail;
ip6h = ipv6_hdr(skb);
pl = ntohs(ip6h->payload_len);
nexthdr = ip6h->nexthdr;
do {
switch (nexthdr) {
case NEXTHDR_FRAGMENT:
goto ignore_skb;
case NEXTHDR_ROUTING:
case NEXTHDR_HOP:
case NEXTHDR_DEST:
if (!pskb_may_pull(skb, hl + sizeof(*ip6xh) + ntkoff))
goto fail;
ip6xh = (void *)(skb_network_header(skb) + hl);
ixhl = ipv6_optlen(ip6xh);
if (!pskb_may_pull(skb, hl + ixhl + ntkoff))
goto fail;
ip6xh = (void *)(skb_network_header(skb) + hl);
if ((nexthdr == NEXTHDR_HOP) &&
!(tcf_csum_ipv6_hopopts(ip6xh, ixhl, &pl)))
goto fail;
nexthdr = ip6xh->nexthdr;
hl += ixhl;
break;
case IPPROTO_ICMPV6:
if (update_flags & TCA_CSUM_UPDATE_FLAG_ICMP)
if (!tcf_csum_ipv6_icmp(skb,
hl, pl + sizeof(*ip6h)))
goto fail;
goto done;
case IPPROTO_TCP:
if (update_flags & TCA_CSUM_UPDATE_FLAG_TCP)
if (!tcf_csum_ipv6_tcp(skb,
hl, pl + sizeof(*ip6h)))
goto fail;
goto done;
case IPPROTO_UDP:
if (update_flags & TCA_CSUM_UPDATE_FLAG_UDP)
if (!tcf_csum_ipv6_udp(skb, hl,
pl + sizeof(*ip6h), 0))
goto fail;
goto done;
case IPPROTO_UDPLITE:
if (update_flags & TCA_CSUM_UPDATE_FLAG_UDPLITE)
if (!tcf_csum_ipv6_udp(skb, hl,
pl + sizeof(*ip6h), 1))
goto fail;
goto done;
case IPPROTO_SCTP:
if ((update_flags & TCA_CSUM_UPDATE_FLAG_SCTP) &&
!tcf_csum_sctp(skb, hl, pl + sizeof(*ip6h)))
goto fail;
goto done;
default:
goto ignore_skb;
}
} while (pskb_may_pull(skb, hl + 1 + ntkoff));
done:
ignore_skb:
return 1;
fail:
return 0;
}
static int tcf_csum_act(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
struct tcf_csum *p = to_tcf_csum(a);
bool orig_vlan_tag_present = false;
unsigned int vlan_hdr_count = 0;
struct tcf_csum_params *params;
u32 update_flags;
__be16 protocol;
int action;
params = rcu_dereference_bh(p->params);
tcf_lastuse_update(&p->tcf_tm);
tcf_action_update_bstats(&p->common, skb);
net/sched: act_csum: fix NULL dereference when 'goto chain' is used the control action in the common member of struct tcf_csum must be a valid value, as it can contain the chain index when 'goto chain' is used. Ensure that the control action can be read as x->tcfa_action, when x is a pointer to struct tc_action and x->ops->type is TCA_ACT_CSUM, to prevent the following command: # tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \ > $tcflags dst_mac $h2mac action csum ip or tcp or udp or sctp goto chain 1 from triggering a NULL pointer dereference when a matching packet is received. BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 PGD 800000010416b067 P4D 800000010416b067 PUD 1041be067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 3072 Comm: mausezahn Tainted: G E 4.18.0-rc2.auguri+ #421 Hardware name: Hewlett-Packard HP Z220 CMT Workstation/1790, BIOS K51 v01.58 02/07/2013 RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffffa020dea03c40 EFLAGS: 00010246 RAX: 0000000020000001 RBX: ffffa020d7ccef00 RCX: 0000000000000054 RDX: 0000000000000000 RSI: ffffa020ca5ae000 RDI: ffffa020d7ccef00 RBP: ffffa020dea03e60 R08: 0000000000000000 R09: ffffa020dea03c9c R10: ffffa020dea03c78 R11: 0000000000000008 R12: ffffa020d3fe4f00 R13: ffffa020d3fe4f08 R14: 0000000000000001 R15: ffffa020d53ca300 FS: 00007f5a46942740(0000) GS:ffffa020dea00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000104218002 CR4: 00000000001606f0 Call Trace: <IRQ> fl_classify+0x1ad/0x1c0 [cls_flower] ? arp_rcv+0x121/0x1b0 ? __x2apic_send_IPI_dest+0x40/0x40 ? smp_reschedule_interrupt+0x1c/0xd0 ? reschedule_interrupt+0xf/0x20 ? reschedule_interrupt+0xa/0x20 ? device_is_rmrr_locked+0xe/0x50 ? iommu_should_identity_map+0x49/0xd0 ? __intel_map_single+0x30/0x140 ? e1000e_update_rdt_wa.isra.52+0x22/0xb0 [e1000e] ? e1000_alloc_rx_buffers+0x233/0x250 [e1000e] ? kmem_cache_alloc+0x38/0x1c0 tcf_classify+0x89/0x140 __netif_receive_skb_core+0x5ea/0xb70 ? enqueue_task_fair+0xb6/0x7d0 ? process_backlog+0x97/0x150 process_backlog+0x97/0x150 net_rx_action+0x14b/0x3e0 __do_softirq+0xde/0x2b4 do_softirq_own_stack+0x2a/0x40 </IRQ> do_softirq.part.18+0x49/0x50 __local_bh_enable_ip+0x49/0x50 __dev_queue_xmit+0x4ab/0x8a0 ? wait_woken+0x80/0x80 ? packet_sendmsg+0x38f/0x810 ? __dev_queue_xmit+0x8a0/0x8a0 packet_sendmsg+0x38f/0x810 sock_sendmsg+0x36/0x40 __sys_sendto+0x10e/0x140 ? do_vfs_ioctl+0xa4/0x630 ? syscall_trace_enter+0x1df/0x2e0 ? __audit_syscall_exit+0x22a/0x290 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x5b/0x180 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f5a45cbec93 Code: 48 8b 0d 18 83 20 00 f7 d8 64 89 01 48 83 c8 ff c3 66 0f 1f 44 00 00 83 3d 59 c7 20 00 00 75 13 49 89 ca b8 2c 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 34 c3 48 83 ec 08 e8 2b f7 ff ff 48 89 04 24 RSP: 002b:00007ffd0ee6d748 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 0000000001161010 RCX: 00007f5a45cbec93 RDX: 0000000000000062 RSI: 0000000001161322 RDI: 0000000000000003 RBP: 00007ffd0ee6d780 R08: 00007ffd0ee6d760 R09: 0000000000000014 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000062 R13: 0000000001161322 R14: 00007ffd0ee6d760 R15: 0000000000000003 Modules linked in: act_csum act_gact cls_flower sch_ingress vrf veth act_tunnel_key(E) xt_CHECKSUM iptable_mangle ipt_MASQUERADE iptable_nat nf_nat_ipv4 nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack ipt_REJECT nf_reject_ipv4 tun bridge stp llc ebtable_filter ebtables ip6table_filter ip6_tables iptable_filter intel_rapl x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel snd_hda_codec_hdmi snd_hda_codec_realtek kvm snd_hda_codec_generic hp_wmi iTCO_wdt sparse_keymap rfkill mei_wdt iTCO_vendor_support wmi_bmof gpio_ich irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc aesni_intel snd_hda_intel crypto_simd cryptd snd_hda_codec glue_helper snd_hda_core snd_hwdep snd_seq snd_seq_device snd_pcm pcspkr i2c_i801 snd_timer snd sg lpc_ich soundcore wmi mei_me mei ie31200_edac nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c sr_mod cdrom sd_mod ahci libahci crc32c_intel i915 ixgbe serio_raw libata video dca i2c_algo_bit sfc drm_kms_helper syscopyarea mtd sysfillrect mdio sysimgblt fb_sys_fops drm e1000e i2c_core CR2: 0000000000000000 ---[ end trace 3c9e9d1a77df4026 ]--- 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:ffffa020dea03c40 EFLAGS: 00010246 RAX: 0000000020000001 RBX: ffffa020d7ccef00 RCX: 0000000000000054 RDX: 0000000000000000 RSI: ffffa020ca5ae000 RDI: ffffa020d7ccef00 RBP: ffffa020dea03e60 R08: 0000000000000000 R09: ffffa020dea03c9c R10: ffffa020dea03c78 R11: 0000000000000008 R12: ffffa020d3fe4f00 R13: ffffa020d3fe4f08 R14: 0000000000000001 R15: ffffa020d53ca300 FS: 00007f5a46942740(0000) GS:ffffa020dea00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000104218002 CR4: 00000000001606f0 Kernel panic - not syncing: Fatal exception in interrupt Kernel Offset: 0x26400000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]--- Fixes: 9c5f69bbd75a ("net/sched: act_csum: don't use spinlock in the fast path") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-06 19:01:05 +00:00
action = READ_ONCE(p->tcf_action);
if (unlikely(action == TC_ACT_SHOT))
goto drop;
update_flags = params->update_flags;
protocol = tc_skb_protocol(skb);
again:
switch (protocol) {
case cpu_to_be16(ETH_P_IP):
if (!tcf_csum_ipv4(skb, update_flags))
goto drop;
break;
case cpu_to_be16(ETH_P_IPV6):
if (!tcf_csum_ipv6(skb, update_flags))
goto drop;
break;
case cpu_to_be16(ETH_P_8021AD): /* fall through */
case cpu_to_be16(ETH_P_8021Q):
if (skb_vlan_tag_present(skb) && !orig_vlan_tag_present) {
protocol = skb->protocol;
orig_vlan_tag_present = true;
} else {
struct vlan_hdr *vlan = (struct vlan_hdr *)skb->data;
protocol = vlan->h_vlan_encapsulated_proto;
skb_pull(skb, VLAN_HLEN);
skb_reset_network_header(skb);
vlan_hdr_count++;
}
goto again;
}
out:
/* Restore the skb for the pulled VLAN tags */
while (vlan_hdr_count--) {
skb_push(skb, VLAN_HLEN);
skb_reset_network_header(skb);
}
return action;
drop:
tcf_action_inc_drop_qstats(&p->common);
action = TC_ACT_SHOT;
goto out;
}
static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind,
int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_csum *p = to_tcf_csum(a);
struct tcf_csum_params *params;
struct tc_csum opt = {
.index = p->tcf_index,
.refcnt = refcount_read(&p->tcf_refcnt) - ref,
.bindcnt = atomic_read(&p->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(&p->tcf_lock);
params = rcu_dereference_protected(p->params,
lockdep_is_held(&p->tcf_lock));
opt.action = p->tcf_action;
opt.update_flags = params->update_flags;
if (nla_put(skb, TCA_CSUM_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
tcf_tm_dump(&t, &p->tcf_tm);
if (nla_put_64bit(skb, TCA_CSUM_TM, sizeof(t), &t, TCA_CSUM_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>
2018-08-14 18:46:16 +00:00
spin_unlock_bh(&p->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(&p->tcf_lock);
nlmsg_trim(skb, b);
return -1;
}
static void tcf_csum_cleanup(struct tc_action *a)
{
struct tcf_csum *p = to_tcf_csum(a);
struct tcf_csum_params *params;
params = rcu_dereference_protected(p->params, 1);
net/sched: fix NULL dereference in the error path of tcf_csum_init() when the following command # tc action add action csum udp continue index 100 is run for the first time, and tcf_csum_init() fails allocating struct tcf_csum, tcf_csum_cleanup() calls kfree_rcu(NULL,...). This causes the following error: BUG: unable to handle kernel NULL pointer dereference at 0000000000000010 IP: __call_rcu+0x23/0x2b0 PGD 80000000740b4067 P4D 80000000740b4067 PUD 32e7f067 PMD 0 Oops: 0002 [#1] SMP PTI Modules linked in: act_csum(E) act_vlan ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 mbcache jbd2 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel snd_hda_codec_generic pcbc snd_hda_intel snd_hda_codec snd_hda_core snd_hwdep snd_seq snd_seq_device snd_pcm snd_timer aesni_intel crypto_simd glue_helper cryptd snd joydev pcspkr virtio_balloon i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm virtio_blk drm virtio_net virtio_console ata_piix crc32c_intel libata virtio_pci serio_raw i2c_core virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_vlan] CPU: 2 PID: 5763 Comm: tc Tainted: G E 4.16.0-rc4.act_vlan.orig+ #403 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:__call_rcu+0x23/0x2b0 RSP: 0018:ffffb275803e77c0 EFLAGS: 00010246 RAX: ffffffffc057b080 RBX: ffff9674bc6f5240 RCX: 00000000ffffffff RDX: ffffffff928a5f00 RSI: 0000000000000008 RDI: 0000000000000008 RBP: 0000000000000008 R08: 0000000000000001 R09: 0000000000000044 R10: 0000000000000220 R11: ffff9674b9ab4821 R12: 0000000000000000 R13: ffffffff928a5f00 R14: 0000000000000000 R15: 0000000000000001 FS: 00007fa6368d8740(0000) GS:ffff9674bfd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000010 CR3: 0000000073dec001 CR4: 00000000001606e0 Call Trace: __tcf_idr_release+0x79/0xf0 tcf_csum_init+0xfb/0x180 [act_csum] 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: 0033:0x7fa635ce9ba0 RSP: 002b:00007ffc185b0fc8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007ffc185b10f0 RCX: 00007fa635ce9ba0 RDX: 0000000000000000 RSI: 00007ffc185b1040 RDI: 0000000000000003 RBP: 000000005aaa85e0 R08: 0000000000000002 R09: 0000000000000000 R10: 00007ffc185b0a20 R11: 0000000000000246 R12: 0000000000000000 R13: 00007ffc185b1104 R14: 0000000000000001 R15: 0000000000669f60 Code: 5d e9 42 da ff ff 66 90 0f 1f 44 00 00 41 57 41 56 41 55 49 89 d5 41 54 55 48 89 fd 53 48 83 ec 08 40 f6 c7 07 0f 85 19 02 00 00 <48> 89 75 08 48 c7 45 00 00 00 00 00 9c 58 0f 1f 44 00 00 49 89 RIP: __call_rcu+0x23/0x2b0 RSP: ffffb275803e77c0 CR2: 0000000000000010 fix this in tcf_csum_cleanup(), ensuring that kfree_rcu(param, ...) is called only when param is not NULL. Fixes: 9c5f69bbd75a ("net/sched: act_csum: don't use spinlock in the fast path") 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 23:00:54 +00:00
if (params)
kfree_rcu(params, rcu);
}
static int tcf_csum_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, csum_net_id);
return tcf_generic_walker(tn, skb, cb, type, ops, extack);
}
static int tcf_csum_search(struct net *net, struct tc_action **a, u32 index)
{
struct tc_action_net *tn = net_generic(net, csum_net_id);
return tcf_idr_search(tn, a, index);
}
static size_t tcf_csum_get_fill_size(const struct tc_action *act)
{
return nla_total_size(sizeof(struct tc_csum));
}
static struct tc_action_ops act_csum_ops = {
.kind = "csum",
.id = TCA_ID_CSUM,
.owner = THIS_MODULE,
.act = tcf_csum_act,
.dump = tcf_csum_dump,
.init = tcf_csum_init,
.cleanup = tcf_csum_cleanup,
.walk = tcf_csum_walker,
.lookup = tcf_csum_search,
.get_fill_size = tcf_csum_get_fill_size,
.size = sizeof(struct tcf_csum),
};
static __net_init int csum_init_net(struct net *net)
{
struct tc_action_net *tn = net_generic(net, csum_net_id);
return tc_action_net_init(net, tn, &act_csum_ops);
}
static void __net_exit csum_exit_net(struct list_head *net_list)
{
tc_action_net_exit(net_list, csum_net_id);
}
static struct pernet_operations csum_net_ops = {
.init = csum_init_net,
.exit_batch = csum_exit_net,
.id = &csum_net_id,
.size = sizeof(struct tc_action_net),
};
MODULE_DESCRIPTION("Checksum updating actions");
MODULE_LICENSE("GPL");
static int __init csum_init_module(void)
{
return tcf_register_action(&act_csum_ops, &csum_net_ops);
}
static void __exit csum_cleanup_module(void)
{
tcf_unregister_action(&act_csum_ops, &csum_net_ops);
}
module_init(csum_init_module);
module_exit(csum_cleanup_module);