From cc8e58f8325cdf14b9516b61c384cdfd02a4f408 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 3 Sep 2020 19:10:11 -0700 Subject: act_ife: load meta modules before tcf_idr_check_alloc() The following deadlock scenario is triggered by syzbot: Thread A: Thread B: tcf_idr_check_alloc() ... populate_metalist() rtnl_unlock() rtnl_lock() ... request_module() tcf_idr_check_alloc() rtnl_lock() At this point, thread A is waiting for thread B to release RTNL lock, while thread B is waiting for thread A to commit the IDR change with tcf_idr_insert() later. Break this deadlock situation by preloading ife modules earlier, before tcf_idr_check_alloc(), this is fine because we only need to load modules we need potentially. Reported-and-tested-by: syzbot+80e32b5d1f9923f8ace6@syzkaller.appspotmail.com Fixes: 0190c1d452a9 ("net: sched: atomically check-allocate action") Cc: Jamal Hadi Salim Cc: Vlad Buslov Cc: Jiri Pirko Signed-off-by: Cong Wang Signed-off-by: Jakub Kicinski --- net/sched/act_ife.c | 44 ++++++++++++++++++++++++++++++++++---------- 1 file changed, 34 insertions(+), 10 deletions(-) (limited to 'net/sched') diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index c1fcd85719d6..5c568757643b 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -436,6 +436,25 @@ static void tcf_ife_cleanup(struct tc_action *a) kfree_rcu(p, rcu); } +static int load_metalist(struct nlattr **tb, bool rtnl_held) +{ + int i; + + for (i = 1; i < max_metacnt; i++) { + if (tb[i]) { + void *val = nla_data(tb[i]); + int len = nla_len(tb[i]); + int rc; + + rc = load_metaops_and_vet(i, val, len, rtnl_held); + if (rc != 0) + return rc; + } + } + + return 0; +} + static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, bool exists, bool rtnl_held) { @@ -449,10 +468,6 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, val = nla_data(tb[i]); len = nla_len(tb[i]); - rc = load_metaops_and_vet(i, val, len, rtnl_held); - if (rc != 0) - return rc; - rc = add_metainfo(ife, i, val, len, exists); if (rc) return rc; @@ -509,6 +524,21 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, if (!p) return -ENOMEM; + if (tb[TCA_IFE_METALST]) { + err = nla_parse_nested_deprecated(tb2, IFE_META_MAX, + tb[TCA_IFE_METALST], NULL, + NULL); + if (err) { + kfree(p); + return err; + } + err = load_metalist(tb2, rtnl_held); + if (err) { + kfree(p); + return err; + } + } + index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) { @@ -570,15 +600,9 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, } if (tb[TCA_IFE_METALST]) { - err = nla_parse_nested_deprecated(tb2, IFE_META_MAX, - tb[TCA_IFE_METALST], NULL, - NULL); - if (err) - goto metadata_parse_err; err = populate_metalist(ife, tb2, exists, rtnl_held); if (err) goto metadata_parse_err; - } else { /* if no passed metadata allow list or passed allow-all * then here we process by adding as many supported metadatum -- cgit v1.2.3-70-g09d2 From 2fb541c862c987d02dfdf28f1545016deecfa0d5 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Tue, 8 Sep 2020 19:02:34 +0800 Subject: net: sch_generic: aviod concurrent reset and enqueue op for lockless qdisc Currently there is concurrent reset and enqueue operation for the same lockless qdisc when there is no lock to synchronize the q->enqueue() in __dev_xmit_skb() with the qdisc reset operation in qdisc_deactivate() called by dev_deactivate_queue(), which may cause out-of-bounds access for priv->ring[] in hns3 driver if user has requested a smaller queue num when __dev_xmit_skb() still enqueue a skb with a larger queue_mapping after the corresponding qdisc is reset, and call hns3_nic_net_xmit() with that skb later. Reused the existing synchronize_net() in dev_deactivate_many() to make sure skb with larger queue_mapping enqueued to old qdisc(which is saved in dev_queue->qdisc_sleeping) will always be reset when dev_reset_queue() is called. Fixes: 6b3ba9146fe6 ("net: sched: allow qdiscs to handle locking") Signed-off-by: Yunsheng Lin Signed-off-by: David S. Miller --- net/sched/sch_generic.c | 48 +++++++++++++++++++++++++++++++++--------------- 1 file changed, 33 insertions(+), 15 deletions(-) (limited to 'net/sched') diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 265a61d011df..54c417244642 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -1131,24 +1131,10 @@ EXPORT_SYMBOL(dev_activate); static void qdisc_deactivate(struct Qdisc *qdisc) { - bool nolock = qdisc->flags & TCQ_F_NOLOCK; - if (qdisc->flags & TCQ_F_BUILTIN) return; - if (test_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state)) - return; - - if (nolock) - spin_lock_bh(&qdisc->seqlock); - spin_lock_bh(qdisc_lock(qdisc)); set_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state); - - qdisc_reset(qdisc); - - spin_unlock_bh(qdisc_lock(qdisc)); - if (nolock) - spin_unlock_bh(&qdisc->seqlock); } static void dev_deactivate_queue(struct net_device *dev, @@ -1165,6 +1151,30 @@ static void dev_deactivate_queue(struct net_device *dev, } } +static void dev_reset_queue(struct net_device *dev, + struct netdev_queue *dev_queue, + void *_unused) +{ + struct Qdisc *qdisc; + bool nolock; + + qdisc = dev_queue->qdisc_sleeping; + if (!qdisc) + return; + + nolock = qdisc->flags & TCQ_F_NOLOCK; + + if (nolock) + spin_lock_bh(&qdisc->seqlock); + spin_lock_bh(qdisc_lock(qdisc)); + + qdisc_reset(qdisc); + + spin_unlock_bh(qdisc_lock(qdisc)); + if (nolock) + spin_unlock_bh(&qdisc->seqlock); +} + static bool some_qdisc_is_busy(struct net_device *dev) { unsigned int i; @@ -1213,12 +1223,20 @@ void dev_deactivate_many(struct list_head *head) dev_watchdog_down(dev); } - /* Wait for outstanding qdisc-less dev_queue_xmit calls. + /* Wait for outstanding qdisc-less dev_queue_xmit calls or + * outstanding qdisc enqueuing calls. * This is avoided if all devices are in dismantle phase : * Caller will call synchronize_net() for us */ synchronize_net(); + list_for_each_entry(dev, head, close_list) { + netdev_for_each_tx_queue(dev, dev_reset_queue, NULL); + + if (dev_ingress_queue(dev)) + dev_reset_queue(dev, dev_ingress_queue(dev), NULL); + } + /* Wait for outstanding qdisc_run calls. */ list_for_each_entry(dev, head, close_list) { while (some_qdisc_is_busy(dev)) { -- cgit v1.2.3-70-g09d2 From b5b73b26b3ca34574124ed7ae9c5ba8391a7f176 Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Wed, 9 Sep 2020 17:03:11 -0700 Subject: taprio: Fix allowing too small intervals It's possible that the user specifies an interval that couldn't allow any packet to be transmitted. This also avoids the issue of the hrtimer handler starving the other threads because it's running too often. The solution is to reject interval sizes that according to the current link speed wouldn't allow any packet to be transmitted. Reported-by: syzbot+8267241609ae8c23b248@syzkaller.appspotmail.com Fixes: 5a781ccbd19e ("tc: Add support for configuring the taprio scheduler") Signed-off-by: Vinicius Costa Gomes Signed-off-by: David S. Miller --- net/sched/sch_taprio.c | 28 +++++++++++++++++----------- 1 file changed, 17 insertions(+), 11 deletions(-) (limited to 'net/sched') diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index fe53c1e38c7d..b0ad7687ee2c 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -777,9 +777,11 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { [TCA_TAPRIO_ATTR_TXTIME_DELAY] = { .type = NLA_U32 }, }; -static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry, +static int fill_sched_entry(struct taprio_sched *q, struct nlattr **tb, + struct sched_entry *entry, struct netlink_ext_ack *extack) { + int min_duration = length_to_duration(q, ETH_ZLEN); u32 interval = 0; if (tb[TCA_TAPRIO_SCHED_ENTRY_CMD]) @@ -794,7 +796,10 @@ static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry, interval = nla_get_u32( tb[TCA_TAPRIO_SCHED_ENTRY_INTERVAL]); - if (interval == 0) { + /* The interval should allow at least the minimum ethernet + * frame to go out. + */ + if (interval < min_duration) { NL_SET_ERR_MSG(extack, "Invalid interval for schedule entry"); return -EINVAL; } @@ -804,8 +809,9 @@ static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry, return 0; } -static int parse_sched_entry(struct nlattr *n, struct sched_entry *entry, - int index, struct netlink_ext_ack *extack) +static int parse_sched_entry(struct taprio_sched *q, struct nlattr *n, + struct sched_entry *entry, int index, + struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { }; int err; @@ -819,10 +825,10 @@ static int parse_sched_entry(struct nlattr *n, struct sched_entry *entry, entry->index = index; - return fill_sched_entry(tb, entry, extack); + return fill_sched_entry(q, tb, entry, extack); } -static int parse_sched_list(struct nlattr *list, +static int parse_sched_list(struct taprio_sched *q, struct nlattr *list, struct sched_gate_list *sched, struct netlink_ext_ack *extack) { @@ -847,7 +853,7 @@ static int parse_sched_list(struct nlattr *list, return -ENOMEM; } - err = parse_sched_entry(n, entry, i, extack); + err = parse_sched_entry(q, n, entry, i, extack); if (err < 0) { kfree(entry); return err; @@ -862,7 +868,7 @@ static int parse_sched_list(struct nlattr *list, return i; } -static int parse_taprio_schedule(struct nlattr **tb, +static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb, struct sched_gate_list *new, struct netlink_ext_ack *extack) { @@ -883,8 +889,8 @@ static int parse_taprio_schedule(struct nlattr **tb, new->cycle_time = nla_get_s64(tb[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME]); if (tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST]) - err = parse_sched_list( - tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST], new, extack); + err = parse_sched_list(q, tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST], + new, extack); if (err < 0) return err; @@ -1473,7 +1479,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, goto free_sched; } - err = parse_taprio_schedule(tb, new_admin, extack); + err = parse_taprio_schedule(q, tb, new_admin, extack); if (err < 0) goto free_sched; -- cgit v1.2.3-70-g09d2 From 13e6ce98aa65ab5ce19351c020419360dfe8af29 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 13 Sep 2020 19:51:50 +0800 Subject: net: sched: only keep the available bits when setting vxlan md->gbp As we can see from vxlan_build/parse_gbp_hdr(), when processing metadata on vxlan rx/tx path, only dont_learn/policy_applied/policy_id fields can be set to or parse from the packet for vxlan gbp option. So we'd better do the mask when set it in act_tunnel_key and cls_flower. Otherwise, when users don't know these bits, they may configure with a value which can never be matched. Reported-by: Shuang Li Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/vxlan.h | 3 +++ net/sched/act_tunnel_key.c | 1 + net/sched/cls_flower.c | 4 +++- 3 files changed, 7 insertions(+), 1 deletion(-) (limited to 'net/sched') diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 3a41627cbdfe..08537aa14f7c 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -121,6 +121,9 @@ struct vxlanhdr_gbp { #define VXLAN_GBP_POLICY_APPLIED (BIT(3) << 16) #define VXLAN_GBP_ID_MASK (0xFFFF) +#define VXLAN_GBP_MASK (VXLAN_GBP_DONT_LEARN | VXLAN_GBP_POLICY_APPLIED | \ + VXLAN_GBP_ID_MASK) + /* * VXLAN Generic Protocol Extension (VXLAN_F_GPE): * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 536c4bc31be6..37f1e10f35e0 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -156,6 +156,7 @@ tunnel_key_copy_vxlan_opt(const struct nlattr *nla, void *dst, int dst_len, struct vxlan_metadata *md = dst; md->gbp = nla_get_u32(tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP]); + md->gbp &= VXLAN_GBP_MASK; } return sizeof(struct vxlan_metadata); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index a4f7ef1de7e7..e8fda1bd4d9d 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1175,8 +1175,10 @@ static int fl_set_vxlan_opt(const struct nlattr *nla, struct fl_flow_key *key, return -EINVAL; } - if (tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]) + if (tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]) { md->gbp = nla_get_u32(tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]); + md->gbp &= VXLAN_GBP_MASK; + } return sizeof(*md); } -- cgit v1.2.3-70-g09d2 From 8e1b3ac4786680c2d2b5a24e38a2d714c3bcd1ef Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 13 Sep 2020 19:43:03 +0800 Subject: net: sched: initialize with 0 before setting erspan md->u In fl_set_erspan_opt(), all bits of erspan md was set 1, as this function is also used to set opt MASK. However, when setting for md->u.index for opt VALUE, the rest bits of the union md->u will be left 1. It would cause to fail the match of the whole md when version is 1 and only index is set. This patch is to fix by initializing with 0 before setting erspan md->u. Reported-by: Shuang Li Fixes: 79b1011cb33d ("net: sched: allow flower to match erspan options") Signed-off-by: Xin Long Signed-off-by: David S. Miller --- net/sched/cls_flower.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/sched') diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index e8fda1bd4d9d..fed18fd2c50b 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1223,6 +1223,7 @@ static int fl_set_erspan_opt(const struct nlattr *nla, struct fl_flow_key *key, } if (tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX]) { nla = tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX]; + memset(&md->u, 0x00, sizeof(md->u)); md->u.index = nla_get_be32(nla); } } else if (md->version == 2) { -- cgit v1.2.3-70-g09d2