From e323d865b36134e8c5c82c834df89109a5c60dab Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 10 Mar 2021 08:26:41 -0800 Subject: net: sched: validate stab values iproute2 package is well behaved, but malicious user space can provide illegal shift values and trigger UBSAN reports. Add stab parameter to red_check_params() to validate user input. syzbot reported: UBSAN: shift-out-of-bounds in ./include/net/red.h:312:18 shift exponent 111 is too large for 64-bit type 'long unsigned int' CPU: 1 PID: 14662 Comm: syz-executor.3 Not tainted 5.12.0-rc2-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:79 [inline] dump_stack+0x141/0x1d7 lib/dump_stack.c:120 ubsan_epilogue+0xb/0x5a lib/ubsan.c:148 __ubsan_handle_shift_out_of_bounds.cold+0xb1/0x181 lib/ubsan.c:327 red_calc_qavg_from_idle_time include/net/red.h:312 [inline] red_calc_qavg include/net/red.h:353 [inline] choke_enqueue.cold+0x18/0x3dd net/sched/sch_choke.c:221 __dev_xmit_skb net/core/dev.c:3837 [inline] __dev_queue_xmit+0x1943/0x2e00 net/core/dev.c:4150 neigh_hh_output include/net/neighbour.h:499 [inline] neigh_output include/net/neighbour.h:508 [inline] ip6_finish_output2+0x911/0x1700 net/ipv6/ip6_output.c:117 __ip6_finish_output net/ipv6/ip6_output.c:182 [inline] __ip6_finish_output+0x4c1/0xe10 net/ipv6/ip6_output.c:161 ip6_finish_output+0x35/0x200 net/ipv6/ip6_output.c:192 NF_HOOK_COND include/linux/netfilter.h:290 [inline] ip6_output+0x1e4/0x530 net/ipv6/ip6_output.c:215 dst_output include/net/dst.h:448 [inline] NF_HOOK include/linux/netfilter.h:301 [inline] NF_HOOK include/linux/netfilter.h:295 [inline] ip6_xmit+0x127e/0x1eb0 net/ipv6/ip6_output.c:320 inet6_csk_xmit+0x358/0x630 net/ipv6/inet6_connection_sock.c:135 dccp_transmit_skb+0x973/0x12c0 net/dccp/output.c:138 dccp_send_reset+0x21b/0x2b0 net/dccp/output.c:535 dccp_finish_passive_close net/dccp/proto.c:123 [inline] dccp_finish_passive_close+0xed/0x140 net/dccp/proto.c:118 dccp_terminate_connection net/dccp/proto.c:958 [inline] dccp_close+0xb3c/0xe60 net/dccp/proto.c:1028 inet_release+0x12e/0x280 net/ipv4/af_inet.c:431 inet6_release+0x4c/0x70 net/ipv6/af_inet6.c:478 __sock_release+0xcd/0x280 net/socket.c:599 sock_close+0x18/0x20 net/socket.c:1258 __fput+0x288/0x920 fs/file_table.c:280 task_work_run+0xdd/0x1a0 kernel/task_work.c:140 tracehook_notify_resume include/linux/tracehook.h:189 [inline] Fixes: 8afa10cbe281 ("net_sched: red: Avoid illegal values") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- net/sched/sch_choke.c | 7 ++++--- net/sched/sch_gred.c | 2 +- net/sched/sch_red.c | 7 +++++-- net/sched/sch_sfq.c | 2 +- 4 files changed, 11 insertions(+), 7 deletions(-) (limited to 'net/sched') diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index 50f680f03a54..2adbd945bf15 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -345,6 +345,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt, struct sk_buff **old = NULL; unsigned int mask; u32 max_P; + u8 *stab; if (opt == NULL) return -EINVAL; @@ -361,8 +362,8 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt, max_P = tb[TCA_CHOKE_MAX_P] ? nla_get_u32(tb[TCA_CHOKE_MAX_P]) : 0; ctl = nla_data(tb[TCA_CHOKE_PARMS]); - - if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log)) + stab = nla_data(tb[TCA_CHOKE_STAB]); + if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log, stab)) return -EINVAL; if (ctl->limit > CHOKE_MAX_QUEUE) @@ -412,7 +413,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt, red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Plog, ctl->Scell_log, - nla_data(tb[TCA_CHOKE_STAB]), + stab, max_P); red_set_vars(&q->vars); diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index e0bc77533acc..f4132dc25ac0 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -480,7 +480,7 @@ static inline int gred_change_vq(struct Qdisc *sch, int dp, struct gred_sched *table = qdisc_priv(sch); struct gred_sched_data *q = table->tab[dp]; - if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log)) { + if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log, stab)) { NL_SET_ERR_MSG_MOD(extack, "invalid RED parameters"); return -EINVAL; } diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index b4ae34d7aa96..40adf1f07a82 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -242,6 +242,7 @@ static int __red_change(struct Qdisc *sch, struct nlattr **tb, unsigned char flags; int err; u32 max_P; + u8 *stab; if (tb[TCA_RED_PARMS] == NULL || tb[TCA_RED_STAB] == NULL) @@ -250,7 +251,9 @@ static int __red_change(struct Qdisc *sch, struct nlattr **tb, max_P = tb[TCA_RED_MAX_P] ? nla_get_u32(tb[TCA_RED_MAX_P]) : 0; ctl = nla_data(tb[TCA_RED_PARMS]); - if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log)) + stab = nla_data(tb[TCA_RED_STAB]); + if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, + ctl->Scell_log, stab)) return -EINVAL; err = red_get_flags(ctl->flags, TC_RED_HISTORIC_FLAGS, @@ -288,7 +291,7 @@ static int __red_change(struct Qdisc *sch, struct nlattr **tb, red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Plog, ctl->Scell_log, - nla_data(tb[TCA_RED_STAB]), + stab, max_P); red_set_vars(&q->vars); diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index b25e51440623..066754a18569 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -647,7 +647,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) } if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max, - ctl_v1->Wlog, ctl_v1->Scell_log)) + ctl_v1->Wlog, ctl_v1->Scell_log, NULL)) return -EINVAL; if (ctl_v1 && ctl_v1->qth_min) { p = kmalloc(sizeof(*p), GFP_KERNEL); -- cgit From 93bde210c4341e79f0cd9cb160d889f4577e40b1 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Thu, 11 Mar 2021 16:42:05 +0200 Subject: sch_htb: Fix select_queue for non-offload mode htb_select_queue assumes it's always the offload mode, and it ends up in calling ndo_setup_tc without any checks. It may lead to a NULL pointer dereference if ndo_setup_tc is not implemented, or to an error returned from the driver, which will prevent attaching qdiscs to HTB classes in the non-offload mode. This commit fixes the bug by adding the missing check to htb_select_queue. In the non-offload mode it will return sch->dev_queue, mimicking tc_modify_qdisc's behavior for the case where select_queue is not implemented. Reported-by: syzbot+b53a709f04722ca12a3c@syzkaller.appspotmail.com Fixes: d03b195b5aa0 ("sch_htb: Hierarchical QoS hardware offload") Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Signed-off-by: David S. Miller --- net/sched/sch_htb.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net/sched') diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index dff3adf5a915..b23203159996 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1340,8 +1340,12 @@ htb_select_queue(struct Qdisc *sch, struct tcmsg *tcm) { struct net_device *dev = qdisc_dev(sch); struct tc_htb_qopt_offload offload_opt; + struct htb_sched *q = qdisc_priv(sch); int err; + if (!q->offload) + return sch->dev_queue; + offload_opt = (struct tc_htb_qopt_offload) { .command = TC_HTB_LEAF_QUERY_QUEUE, .classid = TC_H_MIN(tcm->tcm_parent), -- cgit From fb3a3e37de337ec2941c71ff0bcb83e701f3c9f4 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Thu, 11 Mar 2021 16:42:06 +0200 Subject: sch_htb: Fix offload cleanup in htb_destroy on htb_init failure htb_init may fail to do the offload if it's not supported or if a runtime error happens when allocating direct qdiscs. In those cases TC_HTB_CREATE command is not sent to the driver, however, htb_destroy gets called anyway and attempts to send TC_HTB_DESTROY. It shouldn't happen, because the driver didn't receive TC_HTB_CREATE, and also because the driver may not support ndo_setup_tc at all, while q->offload is true, and htb_destroy mistakenly thinks the offload is supported. Trying to call ndo_setup_tc in the latter case will lead to a NULL pointer dereference. This commit fixes the issues with htb_destroy by deferring assignment of q->offload until after the TC_HTB_CREATE command. The necessary cleanup of the offload entities is already done in htb_init. Reported-by: syzbot+b53a709f04722ca12a3c@syzkaller.appspotmail.com Fixes: d03b195b5aa0 ("sch_htb: Hierarchical QoS hardware offload") Suggested-by: Eric Dumazet Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Signed-off-by: David S. Miller --- net/sched/sch_htb.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'net/sched') diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index b23203159996..62e12cb41a3e 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1020,6 +1020,7 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt, struct nlattr *tb[TCA_HTB_MAX + 1]; struct tc_htb_glob *gopt; unsigned int ntx; + bool offload; int err; qdisc_watchdog_init(&q->watchdog, sch); @@ -1044,9 +1045,9 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt, if (gopt->version != HTB_VER >> 16) return -EINVAL; - q->offload = nla_get_flag(tb[TCA_HTB_OFFLOAD]); + offload = nla_get_flag(tb[TCA_HTB_OFFLOAD]); - if (q->offload) { + if (offload) { if (sch->parent != TC_H_ROOT) return -EOPNOTSUPP; @@ -1076,7 +1077,7 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt, q->rate2quantum = 1; q->defcls = gopt->defcls; - if (!q->offload) + if (!offload) return 0; for (ntx = 0; ntx < q->num_direct_qdiscs; ntx++) { @@ -1107,12 +1108,14 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt, if (err) goto err_free_qdiscs; + /* Defer this assignment, so that htb_destroy skips offload-related + * parts (especially calling ndo_setup_tc) on errors. + */ + q->offload = true; + return 0; err_free_qdiscs: - /* TC_HTB_CREATE call failed, avoid any further calls to the driver. */ - q->offload = false; - for (ntx = 0; ntx < q->num_direct_qdiscs && q->direct_qdiscs[ntx]; ntx++) qdisc_put(q->direct_qdiscs[ntx]); -- cgit From d29334c15d33a6a92d2043ca88f84cd5ad026c57 Mon Sep 17 00:00:00 2001 From: wenxu Date: Tue, 16 Mar 2021 16:33:54 +0800 Subject: net/sched: act_api: fix miss set post_ct for ovs after do conntrack in act_ct When openvswitch conntrack offload with act_ct action. The first rule do conntrack in the act_ct in tc subsystem. And miss the next rule in the tc and fallback to the ovs datapath but miss set post_ct flag which will lead the ct_state_key with -trk flag. Fixes: 7baf2429a1a9 ("net/sched: cls_flower add CT_FLAGS_INVALID flag support") Signed-off-by: wenxu Reviewed-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- net/sched/cls_api.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/sched') diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index e37556cc37ab..13341e7fb077 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1629,6 +1629,7 @@ int tcf_classify_ingress(struct sk_buff *skb, return TC_ACT_SHOT; ext->chain = last_executed_chain; ext->mru = qdisc_skb_cb(skb)->mru; + ext->post_ct = qdisc_skb_cb(skb)->post_ct; } return ret; -- cgit From afa536d8405a9ca36e45ba035554afbb8da27b82 Mon Sep 17 00:00:00 2001 From: wenxu Date: Wed, 17 Mar 2021 12:02:43 +0800 Subject: net/sched: cls_flower: fix only mask bit check in the validate_ct_state The ct_state validate should not only check the mask bit and also check mask_bit & key_bit.. For the +new+est case example, The 'new' and 'est' bits should be set in both state_mask and state flags. Or the -new-est case also will be reject by kernel. When Openvswitch with two flows ct_state=+trk+new,action=commit,forward ct_state=+trk+est,action=forward A packet go through the kernel and the contrack state is invalid, The ct_state will be +trk-inv. Upcall to the ovs-vswitchd, the finally dp action will be drop with -new-est+trk. Fixes: 1bcc51ac0731 ("net/sched: cls_flower: Reject invalid ct_state flags rules") Fixes: 3aed8b63336c ("net/sched: cls_flower: validate ct_state for invalid and reply flags") Signed-off-by: wenxu Reviewed-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- net/sched/cls_flower.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/sched') diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index d097b5c15faa..c69a4ba9c33f 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1451,7 +1451,7 @@ static int fl_set_key_ct(struct nlattr **tb, &mask->ct_state, TCA_FLOWER_KEY_CT_STATE_MASK, sizeof(key->ct_state)); - err = fl_validate_ct_state(mask->ct_state, + err = fl_validate_ct_state(key->ct_state & mask->ct_state, tb[TCA_FLOWER_KEY_CT_STATE_MASK], extack); if (err) -- cgit From 8ca1b090e5c9a71abeea1dda8757f4ec3811f06e Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Mon, 22 Mar 2021 15:13:22 -0300 Subject: net/sched: act_ct: clear post_ct if doing ct_clear Invalid detection works with two distinct moments: act_ct tries to find a conntrack entry and set post_ct true, indicating that that was attempted. Then, when flow dissector tries to dissect CT info and no entry is there, it knows that it was tried and no entry was found, and synthesizes/sets key->ct_state = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | TCA_FLOWER_KEY_CT_FLAGS_INVALID; mimicing what OVS does. OVS has this a bit more streamlined, as it recomputes the key after trying to find a conntrack entry for it. Issue here is, when we have 'tc action ct clear', it didn't clear post_ct, causing a subsequent match on 'ct_state -trk' to fail, due to the above. The fix, thus, is to clear it. Reproducer rules: tc filter add dev enp130s0f0np0_0 ingress prio 1 chain 0 \ protocol ip flower ip_proto tcp ct_state -trk \ action ct zone 1 pipe \ action goto chain 2 tc filter add dev enp130s0f0np0_0 ingress prio 1 chain 2 \ protocol ip flower \ action ct clear pipe \ action goto chain 4 tc filter add dev enp130s0f0np0_0 ingress prio 1 chain 4 \ protocol ip flower ct_state -trk \ action mirred egress redirect dev enp130s0f1np1_0 With the fix, the 3rd rule matches, like it does with OVS kernel datapath. Fixes: 7baf2429a1a9 ("net/sched: cls_flower add CT_FLAGS_INVALID flag support") Signed-off-by: Marcelo Ricardo Leitner Reviewed-by: wenxu Signed-off-by: David S. Miller --- net/sched/act_ct.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'net/sched') diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index f0a0aa125b00..16e888a9601d 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -945,13 +945,14 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, tcf_lastuse_update(&c->tcf_tm); if (clear) { + qdisc_skb_cb(skb)->post_ct = false; ct = nf_ct_get(skb, &ctinfo); if (ct) { nf_conntrack_put(&ct->ct_general); nf_ct_set(skb, NULL, IP_CT_UNTRACKED); } - goto out; + goto out_clear; } family = tcf_ct_skb_nf_family(skb); @@ -1030,8 +1031,9 @@ out_push: skb_push_rcsum(skb, nh_ofs); out: - tcf_action_update_bstats(&c->common, skb); qdisc_skb_cb(skb)->post_ct = true; +out_clear: + tcf_action_update_bstats(&c->common, skb); if (defrag) qdisc_skb_cb(skb)->pkt_len = skb->len; return retval; -- cgit