From 26394fc118d6115390bd5b3a0fb17096271da227 Mon Sep 17 00:00:00 2001 From: Ignat Korchagin Date: Fri, 11 Feb 2022 17:30:42 +0000 Subject: ipv6: mcast: use rcu-safe version of ipv6_get_lladdr() Some time ago 8965779d2c0e ("ipv6,mcast: always hold idev->lock before mca_lock") switched ipv6_get_lladdr() to __ipv6_get_lladdr(), which is rcu-unsafe version. That was OK, because idev->lock was held for these codepaths. In 88e2ca308094 ("mld: convert ifmcaddr6 to RCU") these external locks were removed, so we probably need to restore the original rcu-safe call. Otherwise, we occasionally get a machine crashed/stalled with the following in dmesg: [ 3405.966610][T230589] general protection fault, probably for non-canonical address 0xdead00000000008c: 0000 [#1] SMP NOPTI [ 3405.982083][T230589] CPU: 44 PID: 230589 Comm: kworker/44:3 Tainted: G O 5.15.19-cloudflare-2022.2.1 #1 [ 3405.998061][T230589] Hardware name: SUPA-COOL-SERV [ 3406.009552][T230589] Workqueue: mld mld_ifc_work [ 3406.017224][T230589] RIP: 0010:__ipv6_get_lladdr+0x34/0x60 [ 3406.025780][T230589] Code: 57 10 48 83 c7 08 48 89 e5 48 39 d7 74 3e 48 8d 82 38 ff ff ff eb 13 48 8b 90 d0 00 00 00 48 8d 82 38 ff ff ff 48 39 d7 74 22 <66> 83 78 32 20 77 1b 75 e4 89 ca 23 50 2c 75 dd 48 8b 50 08 48 8b [ 3406.055748][T230589] RSP: 0018:ffff94e4b3fc3d10 EFLAGS: 00010202 [ 3406.065617][T230589] RAX: dead00000000005a RBX: ffff94e4b3fc3d30 RCX: 0000000000000040 [ 3406.077477][T230589] RDX: dead000000000122 RSI: ffff94e4b3fc3d30 RDI: ffff8c3a31431008 [ 3406.089389][T230589] RBP: ffff94e4b3fc3d10 R08: 0000000000000000 R09: 0000000000000000 [ 3406.101445][T230589] R10: ffff8c3a31430000 R11: 000000000000000b R12: ffff8c2c37887100 [ 3406.113553][T230589] R13: ffff8c3a39537000 R14: 00000000000005dc R15: ffff8c3a31431000 [ 3406.125730][T230589] FS: 0000000000000000(0000) GS:ffff8c3b9fc80000(0000) knlGS:0000000000000000 [ 3406.138992][T230589] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 3406.149895][T230589] CR2: 00007f0dfea1db60 CR3: 000000387b5f2000 CR4: 0000000000350ee0 [ 3406.162421][T230589] Call Trace: [ 3406.170235][T230589] [ 3406.177736][T230589] mld_newpack+0xfe/0x1a0 [ 3406.186686][T230589] add_grhead+0x87/0xa0 [ 3406.195498][T230589] add_grec+0x485/0x4e0 [ 3406.204310][T230589] ? newidle_balance+0x126/0x3f0 [ 3406.214024][T230589] mld_ifc_work+0x15d/0x450 [ 3406.223279][T230589] process_one_work+0x1e6/0x380 [ 3406.232982][T230589] worker_thread+0x50/0x3a0 [ 3406.242371][T230589] ? rescuer_thread+0x360/0x360 [ 3406.252175][T230589] kthread+0x127/0x150 [ 3406.261197][T230589] ? set_kthread_struct+0x40/0x40 [ 3406.271287][T230589] ret_from_fork+0x22/0x30 [ 3406.280812][T230589] [ 3406.288937][T230589] Modules linked in: ... [last unloaded: kheaders] [ 3406.476714][T230589] ---[ end trace 3525a7655f2f3b9e ]--- Fixes: 88e2ca308094 ("mld: convert ifmcaddr6 to RCU") Reported-by: David Pinilla Caparros Signed-off-by: Ignat Korchagin Signed-off-by: David S. Miller --- include/net/addrconf.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/addrconf.h b/include/net/addrconf.h index e7ce719838b5..59940e230b78 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -109,8 +109,6 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, int ipv6_dev_get_saddr(struct net *net, const struct net_device *dev, const struct in6_addr *daddr, unsigned int srcprefs, struct in6_addr *saddr); -int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr, - u32 banned_flags); int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, u32 banned_flags); bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, -- cgit v1.2.3 From a2614140dc0f467a83aa3bb4b6ee2d6480a76202 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 11 Feb 2022 19:45:06 +0200 Subject: net: dsa: mv88e6xxx: flush switchdev FDB workqueue before removing VLAN mv88e6xxx is special among DSA drivers in that it requires the VTU to contain the VID of the FDB entry it modifies in mv88e6xxx_port_db_load_purge(), otherwise it will return -EOPNOTSUPP. Sometimes due to races this is not always satisfied even if external code does everything right (first deletes the FDB entries, then the VLAN), because DSA commits to hardware FDB entries asynchronously since commit c9eb3e0f8701 ("net: dsa: Add support for learning FDB through notification"). Therefore, the mv88e6xxx driver must close this race condition by itself, by asking DSA to flush the switchdev workqueue of any FDB deletions in progress, prior to exiting a VLAN. Fixes: c9eb3e0f8701 ("net: dsa: Add support for learning FDB through notification") Reported-by: Rafael Richter Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 7 +++++++ include/net/dsa.h | 1 + net/dsa/dsa.c | 1 + net/dsa/dsa_priv.h | 1 - 4 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 8530dbe403f4..ab1676553714 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2284,6 +2284,13 @@ static int mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port, if (!mv88e6xxx_max_vid(chip)) return -EOPNOTSUPP; + /* The ATU removal procedure needs the FID to be mapped in the VTU, + * but FDB deletion runs concurrently with VLAN deletion. Flush the DSA + * switchdev workqueue to ensure that all FDB entries are deleted + * before we remove the VLAN. + */ + dsa_flush_workqueue(); + mv88e6xxx_reg_lock(chip); err = mv88e6xxx_port_get_pvid(chip, port, &pvid); diff --git a/include/net/dsa.h b/include/net/dsa.h index 57b3e4e7413b..85a5ba3772f5 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -1187,6 +1187,7 @@ void dsa_unregister_switch(struct dsa_switch *ds); int dsa_register_switch(struct dsa_switch *ds); void dsa_switch_shutdown(struct dsa_switch *ds); struct dsa_switch *dsa_switch_find(int tree_index, int sw_index); +void dsa_flush_workqueue(void); #ifdef CONFIG_PM_SLEEP int dsa_switch_suspend(struct dsa_switch *ds); int dsa_switch_resume(struct dsa_switch *ds); diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index d9d0d227092c..c43f7446a75d 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -349,6 +349,7 @@ void dsa_flush_workqueue(void) { flush_workqueue(dsa_owq); } +EXPORT_SYMBOL_GPL(dsa_flush_workqueue); int dsa_devlink_param_get(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx) diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 760306f0012f..23c79e91ac67 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -147,7 +147,6 @@ void dsa_tag_driver_put(const struct dsa_device_ops *ops); const struct dsa_device_ops *dsa_find_tagger_by_name(const char *buf); bool dsa_schedule_work(struct work_struct *work); -void dsa_flush_workqueue(void); const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops); static inline int dsa_tag_protocol_overhead(const struct dsa_device_ops *ops) -- cgit v1.2.3 From 5891cd5ec46c2c2eb6427cb54d214b149635dd0e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 11 Feb 2022 12:06:23 -0800 Subject: net_sched: add __rcu annotation to netdev->qdisc syzbot found a data-race [1] which lead me to add __rcu annotations to netdev->qdisc, and proper accessors to get LOCKDEP support. [1] BUG: KCSAN: data-race in dev_activate / qdisc_lookup_rcu write to 0xffff888168ad6410 of 8 bytes by task 13559 on cpu 1: attach_default_qdiscs net/sched/sch_generic.c:1167 [inline] dev_activate+0x2ed/0x8f0 net/sched/sch_generic.c:1221 __dev_open+0x2e9/0x3a0 net/core/dev.c:1416 __dev_change_flags+0x167/0x3f0 net/core/dev.c:8139 rtnl_configure_link+0xc2/0x150 net/core/rtnetlink.c:3150 __rtnl_newlink net/core/rtnetlink.c:3489 [inline] rtnl_newlink+0xf4d/0x13e0 net/core/rtnetlink.c:3529 rtnetlink_rcv_msg+0x745/0x7e0 net/core/rtnetlink.c:5594 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2496 __do_sys_sendmsg net/socket.c:2505 [inline] __se_sys_sendmsg net/socket.c:2503 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff888168ad6410 of 8 bytes by task 13560 on cpu 0: qdisc_lookup_rcu+0x30/0x2e0 net/sched/sch_api.c:323 __tcf_qdisc_find+0x74/0x3a0 net/sched/cls_api.c:1050 tc_del_tfilter+0x1c7/0x1350 net/sched/cls_api.c:2211 rtnetlink_rcv_msg+0x5ba/0x7e0 net/core/rtnetlink.c:5585 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2496 __do_sys_sendmsg net/socket.c:2505 [inline] __se_sys_sendmsg net/socket.c:2503 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0xffffffff85dee080 -> 0xffff88815d96ec00 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 13560 Comm: syz-executor.2 Not tainted 5.17.0-rc3-syzkaller-00116-gf1baf68e1383-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 470502de5bdb ("net: sched: unlock rules update API") Signed-off-by: Eric Dumazet Cc: Vlad Buslov Reported-by: syzbot Cc: Jamal Hadi Salim Cc: Cong Wang Cc: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- net/core/rtnetlink.c | 6 ++++-- net/sched/cls_api.c | 6 +++--- net/sched/sch_api.c | 22 ++++++++++++---------- net/sched/sch_generic.c | 29 ++++++++++++++++------------- 5 files changed, 36 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e490b84732d1..8b5a314db167 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2158,7 +2158,7 @@ struct net_device { struct netdev_queue *_tx ____cacheline_aligned_in_smp; unsigned int num_tx_queues; unsigned int real_num_tx_queues; - struct Qdisc *qdisc; + struct Qdisc __rcu *qdisc; unsigned int tx_queue_len; spinlock_t tx_global_lock; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 710da8a36729..2fb8eb6791e8 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1699,6 +1699,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, { struct ifinfomsg *ifm; struct nlmsghdr *nlh; + struct Qdisc *qdisc; ASSERT_RTNL(); nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags); @@ -1716,6 +1717,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, if (tgt_netnsid >= 0 && nla_put_s32(skb, IFLA_TARGET_NETNSID, tgt_netnsid)) goto nla_put_failure; + qdisc = rtnl_dereference(dev->qdisc); if (nla_put_string(skb, IFLA_IFNAME, dev->name) || nla_put_u32(skb, IFLA_TXQLEN, dev->tx_queue_len) || nla_put_u8(skb, IFLA_OPERSTATE, @@ -1735,8 +1737,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, #endif put_master_ifindex(skb, dev) || nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) || - (dev->qdisc && - nla_put_string(skb, IFLA_QDISC, dev->qdisc->ops->id)) || + (qdisc && + nla_put_string(skb, IFLA_QDISC, qdisc->ops->id)) || nla_put_ifalias(skb, dev) || nla_put_u32(skb, IFLA_CARRIER_CHANGES, atomic_read(&dev->carrier_up_count) + diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 5f0f346b576f..5ce1208a6ea3 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1044,7 +1044,7 @@ static int __tcf_qdisc_find(struct net *net, struct Qdisc **q, /* Find qdisc */ if (!*parent) { - *q = dev->qdisc; + *q = rcu_dereference(dev->qdisc); *parent = (*q)->handle; } else { *q = qdisc_lookup_rcu(dev, TC_H_MAJ(*parent)); @@ -2587,7 +2587,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) parent = tcm->tcm_parent; if (!parent) - q = dev->qdisc; + q = rtnl_dereference(dev->qdisc); else q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent)); if (!q) @@ -2962,7 +2962,7 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; if (!tcm->tcm_parent) - q = dev->qdisc; + q = rtnl_dereference(dev->qdisc); else q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent)); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 179825a3b2fd..e3c0e8ea2dbb 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -301,7 +301,7 @@ struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle) if (!handle) return NULL; - q = qdisc_match_from_root(dev->qdisc, handle); + q = qdisc_match_from_root(rtnl_dereference(dev->qdisc), handle); if (q) goto out; @@ -320,7 +320,7 @@ struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle) if (!handle) return NULL; - q = qdisc_match_from_root(dev->qdisc, handle); + q = qdisc_match_from_root(rcu_dereference(dev->qdisc), handle); if (q) goto out; @@ -1082,10 +1082,10 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, skip: if (!ingress) { notify_and_destroy(net, skb, n, classid, - dev->qdisc, new); + rtnl_dereference(dev->qdisc), new); if (new && !new->ops->attach) qdisc_refcount_inc(new); - dev->qdisc = new ? : &noop_qdisc; + rcu_assign_pointer(dev->qdisc, new ? : &noop_qdisc); if (new && new->ops->attach) new->ops->attach(new); @@ -1451,7 +1451,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, q = dev_ingress_queue(dev)->qdisc_sleeping; } } else { - q = dev->qdisc; + q = rtnl_dereference(dev->qdisc); } if (!q) { NL_SET_ERR_MSG(extack, "Cannot find specified qdisc on specified device"); @@ -1540,7 +1540,7 @@ replay: q = dev_ingress_queue(dev)->qdisc_sleeping; } } else { - q = dev->qdisc; + q = rtnl_dereference(dev->qdisc); } /* It may be default qdisc, ignore it */ @@ -1762,7 +1762,8 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) s_q_idx = 0; q_idx = 0; - if (tc_dump_qdisc_root(dev->qdisc, skb, cb, &q_idx, s_q_idx, + if (tc_dump_qdisc_root(rtnl_dereference(dev->qdisc), + skb, cb, &q_idx, s_q_idx, true, tca[TCA_DUMP_INVISIBLE]) < 0) goto done; @@ -2033,7 +2034,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, } else if (qid1) { qid = qid1; } else if (qid == 0) - qid = dev->qdisc->handle; + qid = rtnl_dereference(dev->qdisc)->handle; /* Now qid is genuine qdisc handle consistent * both with parent and child. @@ -2044,7 +2045,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, portid = TC_H_MAKE(qid, portid); } else { if (qid == 0) - qid = dev->qdisc->handle; + qid = rtnl_dereference(dev->qdisc)->handle; } /* OK. Locate qdisc */ @@ -2205,7 +2206,8 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) s_t = cb->args[0]; t = 0; - if (tc_dump_tclass_root(dev->qdisc, skb, tcm, cb, &t, s_t, true) < 0) + if (tc_dump_tclass_root(rtnl_dereference(dev->qdisc), + skb, tcm, cb, &t, s_t, true) < 0) goto done; dev_queue = dev_ingress_queue(dev); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index f893d9a81b01..5bab9f8b8f45 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -1164,30 +1164,33 @@ static void attach_default_qdiscs(struct net_device *dev) if (!netif_is_multiqueue(dev) || dev->priv_flags & IFF_NO_QUEUE) { netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL); - dev->qdisc = txq->qdisc_sleeping; - qdisc_refcount_inc(dev->qdisc); + qdisc = txq->qdisc_sleeping; + rcu_assign_pointer(dev->qdisc, qdisc); + qdisc_refcount_inc(qdisc); } else { qdisc = qdisc_create_dflt(txq, &mq_qdisc_ops, TC_H_ROOT, NULL); if (qdisc) { - dev->qdisc = qdisc; + rcu_assign_pointer(dev->qdisc, qdisc); qdisc->ops->attach(qdisc); } } + qdisc = rtnl_dereference(dev->qdisc); /* Detect default qdisc setup/init failed and fallback to "noqueue" */ - if (dev->qdisc == &noop_qdisc) { + if (qdisc == &noop_qdisc) { netdev_warn(dev, "default qdisc (%s) fail, fallback to %s\n", default_qdisc_ops->id, noqueue_qdisc_ops.id); dev->priv_flags |= IFF_NO_QUEUE; netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL); - dev->qdisc = txq->qdisc_sleeping; - qdisc_refcount_inc(dev->qdisc); + qdisc = txq->qdisc_sleeping; + rcu_assign_pointer(dev->qdisc, qdisc); + qdisc_refcount_inc(qdisc); dev->priv_flags ^= IFF_NO_QUEUE; } #ifdef CONFIG_NET_SCHED - if (dev->qdisc != &noop_qdisc) - qdisc_hash_add(dev->qdisc, false); + if (qdisc != &noop_qdisc) + qdisc_hash_add(qdisc, false); #endif } @@ -1217,7 +1220,7 @@ void dev_activate(struct net_device *dev) * and noqueue_qdisc for virtual interfaces */ - if (dev->qdisc == &noop_qdisc) + if (rtnl_dereference(dev->qdisc) == &noop_qdisc) attach_default_qdiscs(dev); if (!netif_carrier_ok(dev)) @@ -1383,7 +1386,7 @@ static int qdisc_change_tx_queue_len(struct net_device *dev, void dev_qdisc_change_real_num_tx(struct net_device *dev, unsigned int new_real_tx) { - struct Qdisc *qdisc = dev->qdisc; + struct Qdisc *qdisc = rtnl_dereference(dev->qdisc); if (qdisc->ops->change_real_num_tx) qdisc->ops->change_real_num_tx(qdisc, new_real_tx); @@ -1447,7 +1450,7 @@ static void dev_init_scheduler_queue(struct net_device *dev, void dev_init_scheduler(struct net_device *dev) { - dev->qdisc = &noop_qdisc; + rcu_assign_pointer(dev->qdisc, &noop_qdisc); netdev_for_each_tx_queue(dev, dev_init_scheduler_queue, &noop_qdisc); if (dev_ingress_queue(dev)) dev_init_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc); @@ -1475,8 +1478,8 @@ void dev_shutdown(struct net_device *dev) netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc); if (dev_ingress_queue(dev)) shutdown_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc); - qdisc_put(dev->qdisc); - dev->qdisc = &noop_qdisc; + qdisc_put(rtnl_dereference(dev->qdisc)); + rcu_assign_pointer(dev->qdisc, &noop_qdisc); WARN_ON(timer_pending(&dev->watchdog_timer)); } -- cgit v1.2.3 From 9ceaf6f76b203682bb6100e14b3d7da4c0bedde8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 14 Feb 2022 11:15:53 -0800 Subject: bonding: fix data-races around agg_select_timer syzbot reported that two threads might write over agg_select_timer at the same time. Make agg_select_timer atomic to fix the races. BUG: KCSAN: data-race in bond_3ad_initiate_agg_selection / bond_3ad_state_machine_handler read to 0xffff8881242aea90 of 4 bytes by task 1846 on cpu 1: bond_3ad_state_machine_handler+0x99/0x2810 drivers/net/bonding/bond_3ad.c:2317 process_one_work+0x3f6/0x960 kernel/workqueue.c:2307 worker_thread+0x616/0xa70 kernel/workqueue.c:2454 kthread+0x1bf/0x1e0 kernel/kthread.c:377 ret_from_fork+0x1f/0x30 write to 0xffff8881242aea90 of 4 bytes by task 25910 on cpu 0: bond_3ad_initiate_agg_selection+0x18/0x30 drivers/net/bonding/bond_3ad.c:1998 bond_open+0x658/0x6f0 drivers/net/bonding/bond_main.c:3967 __dev_open+0x274/0x3a0 net/core/dev.c:1407 dev_open+0x54/0x190 net/core/dev.c:1443 bond_enslave+0xcef/0x3000 drivers/net/bonding/bond_main.c:1937 do_set_master net/core/rtnetlink.c:2532 [inline] do_setlink+0x94f/0x2500 net/core/rtnetlink.c:2736 __rtnl_newlink net/core/rtnetlink.c:3414 [inline] rtnl_newlink+0xfeb/0x13e0 net/core/rtnetlink.c:3529 rtnetlink_rcv_msg+0x745/0x7e0 net/core/rtnetlink.c:5594 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2496 __do_sys_sendmsg net/socket.c:2505 [inline] __se_sys_sendmsg net/socket.c:2503 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0x00000050 -> 0x0000004f Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 25910 Comm: syz-executor.1 Tainted: G W 5.17.0-rc4-syzkaller-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Reported-by: syzbot Cc: Jay Vosburgh Cc: Veaceslav Falico Signed-off-by: David S. Miller --- drivers/net/bonding/bond_3ad.c | 30 +++++++++++++++++++++++++----- include/net/bond_3ad.h | 2 +- 2 files changed, 26 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 9fd1d6cba3cd..a86b1f71762e 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -225,7 +225,7 @@ static inline int __check_agg_selection_timer(struct port *port) if (bond == NULL) return 0; - return BOND_AD_INFO(bond).agg_select_timer ? 1 : 0; + return atomic_read(&BOND_AD_INFO(bond).agg_select_timer) ? 1 : 0; } /** @@ -1995,7 +1995,7 @@ static void ad_marker_response_received(struct bond_marker *marker, */ void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout) { - BOND_AD_INFO(bond).agg_select_timer = timeout; + atomic_set(&BOND_AD_INFO(bond).agg_select_timer, timeout); } /** @@ -2278,6 +2278,28 @@ void bond_3ad_update_ad_actor_settings(struct bonding *bond) spin_unlock_bh(&bond->mode_lock); } +/** + * bond_agg_timer_advance - advance agg_select_timer + * @bond: bonding structure + * + * Return true when agg_select_timer reaches 0. + */ +static bool bond_agg_timer_advance(struct bonding *bond) +{ + int val, nval; + + while (1) { + val = atomic_read(&BOND_AD_INFO(bond).agg_select_timer); + if (!val) + return false; + nval = val - 1; + if (atomic_cmpxchg(&BOND_AD_INFO(bond).agg_select_timer, + val, nval) == val) + break; + } + return nval == 0; +} + /** * bond_3ad_state_machine_handler - handle state machines timeout * @work: work context to fetch bonding struct to work on from @@ -2313,9 +2335,7 @@ void bond_3ad_state_machine_handler(struct work_struct *work) if (!bond_has_slaves(bond)) goto re_arm; - /* check if agg_select_timer timer after initialize is timed out */ - if (BOND_AD_INFO(bond).agg_select_timer && - !(--BOND_AD_INFO(bond).agg_select_timer)) { + if (bond_agg_timer_advance(bond)) { slave = bond_first_slave_rcu(bond); port = slave ? &(SLAVE_AD_INFO(slave)->port) : NULL; diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index 38785d48baff..184105d68294 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -262,7 +262,7 @@ struct ad_system { struct ad_bond_info { struct ad_system system; /* 802.3ad system structure */ struct bond_3ad_stats stats; - u32 agg_select_timer; /* Timer to select aggregator after all adapter's hand shakes */ + atomic_t agg_select_timer; /* Timer to select aggregator after all adapter's hand shakes */ u16 aggregator_identifier; }; -- cgit v1.2.3 From 0b0dff5b3b98c5c7ce848151df9da0b3cdf0cc8b Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Tue, 15 Feb 2022 11:00:37 -0500 Subject: ipv6: per-netns exclusive flowlabel checks Ipv6 flowlabels historically require a reservation before use. Optionally in exclusive mode (e.g., user-private). Commit 59c820b2317f ("ipv6: elide flowlabel check if no exclusive leases exist") introduced a fastpath that avoids this check when no exclusive leases exist in the system, and thus any flowlabel use will be granted. That allows skipping the control operation to reserve a flowlabel entirely. Though with a warning if the fast path fails: This is an optimization. Robust applications still have to revert to requesting leases if the fast path fails due to an exclusive lease. Still, this is subtle. Better isolate network namespaces from each other. Flowlabels are per-netns. Also record per-netns whether exclusive leases are in use. Then behavior does not change based on activity in other netns. Changes v2 - wrap in IS_ENABLED(CONFIG_IPV6) to avoid breakage if disabled Fixes: 59c820b2317f ("ipv6: elide flowlabel check if no exclusive leases exist") Link: https://lore.kernel.org/netdev/MWHPR2201MB1072BCCCFCE779E4094837ACD0329@MWHPR2201MB1072.namprd22.prod.outlook.com/ Reported-by: Congyu Liu Signed-off-by: Willem de Bruijn Tested-by: Congyu Liu Link: https://lore.kernel.org/r/20220215160037.1976072-1-willemdebruijn.kernel@gmail.com Signed-off-by: Jakub Kicinski --- include/net/ipv6.h | 5 ++++- include/net/netns/ipv6.h | 3 ++- net/ipv6/ip6_flowlabel.c | 4 +++- 3 files changed, 9 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 3afcb128e064..92eec13d1693 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -393,17 +393,20 @@ static inline void txopt_put(struct ipv6_txoptions *opt) kfree_rcu(opt, rcu); } +#if IS_ENABLED(CONFIG_IPV6) struct ip6_flowlabel *__fl6_sock_lookup(struct sock *sk, __be32 label); extern struct static_key_false_deferred ipv6_flowlabel_exclusive; static inline struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label) { - if (static_branch_unlikely(&ipv6_flowlabel_exclusive.key)) + if (static_branch_unlikely(&ipv6_flowlabel_exclusive.key) && + READ_ONCE(sock_net(sk)->ipv6.flowlabel_has_excl)) return __fl6_sock_lookup(sk, label) ? : ERR_PTR(-ENOENT); return NULL; } +#endif struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space, struct ip6_flowlabel *fl, diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index a4b550380316..6bd7e5a85ce7 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -77,9 +77,10 @@ struct netns_ipv6 { spinlock_t fib6_gc_lock; unsigned int ip6_rt_gc_expire; unsigned long ip6_rt_last_gc; + unsigned char flowlabel_has_excl; #ifdef CONFIG_IPV6_MULTIPLE_TABLES - unsigned int fib6_rules_require_fldissect; bool fib6_has_custom_rules; + unsigned int fib6_rules_require_fldissect; #ifdef CONFIG_IPV6_SUBTREES unsigned int fib6_routes_require_src; #endif diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index aa673a6a7e43..ceb85c67ce39 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -450,8 +450,10 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, err = -EINVAL; goto done; } - if (fl_shared_exclusive(fl) || fl->opt) + if (fl_shared_exclusive(fl) || fl->opt) { + WRITE_ONCE(sock_net(sk)->ipv6.flowlabel_has_excl, 1); static_branch_deferred_inc(&ipv6_flowlabel_exclusive); + } return fl; done: -- cgit v1.2.3 From d95d6320ba7a51d61c097ffc3bcafcf70283414e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 16 Feb 2022 09:32:17 -0800 Subject: ipv6: fix data-race in fib6_info_hw_flags_set / fib6_purge_rt Because fib6_info_hw_flags_set() is called without any synchronization, all accesses to gi6->offload, fi->trap and fi->offload_failed need some basic protection like READ_ONCE()/WRITE_ONCE(). BUG: KCSAN: data-race in fib6_info_hw_flags_set / fib6_purge_rt read to 0xffff8881087d5886 of 1 bytes by task 13953 on cpu 0: fib6_drop_pcpu_from net/ipv6/ip6_fib.c:1007 [inline] fib6_purge_rt+0x4f/0x580 net/ipv6/ip6_fib.c:1033 fib6_del_route net/ipv6/ip6_fib.c:1983 [inline] fib6_del+0x696/0x890 net/ipv6/ip6_fib.c:2028 __ip6_del_rt net/ipv6/route.c:3876 [inline] ip6_del_rt+0x83/0x140 net/ipv6/route.c:3891 __ipv6_dev_ac_dec+0x2b5/0x370 net/ipv6/anycast.c:374 ipv6_dev_ac_dec net/ipv6/anycast.c:387 [inline] __ipv6_sock_ac_close+0x141/0x200 net/ipv6/anycast.c:207 ipv6_sock_ac_close+0x79/0x90 net/ipv6/anycast.c:220 inet6_release+0x32/0x50 net/ipv6/af_inet6.c:476 __sock_release net/socket.c:650 [inline] sock_close+0x6c/0x150 net/socket.c:1318 __fput+0x295/0x520 fs/file_table.c:280 ____fput+0x11/0x20 fs/file_table.c:313 task_work_run+0x8e/0x110 kernel/task_work.c:164 tracehook_notify_resume include/linux/tracehook.h:189 [inline] exit_to_user_mode_loop kernel/entry/common.c:175 [inline] exit_to_user_mode_prepare+0x160/0x190 kernel/entry/common.c:207 __syscall_exit_to_user_mode_work kernel/entry/common.c:289 [inline] syscall_exit_to_user_mode+0x20/0x40 kernel/entry/common.c:300 do_syscall_64+0x50/0xd0 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x44/0xae write to 0xffff8881087d5886 of 1 bytes by task 1912 on cpu 1: fib6_info_hw_flags_set+0x155/0x3b0 net/ipv6/route.c:6230 nsim_fib6_rt_hw_flags_set drivers/net/netdevsim/fib.c:668 [inline] nsim_fib6_rt_add drivers/net/netdevsim/fib.c:691 [inline] nsim_fib6_rt_insert drivers/net/netdevsim/fib.c:756 [inline] nsim_fib6_event drivers/net/netdevsim/fib.c:853 [inline] nsim_fib_event drivers/net/netdevsim/fib.c:886 [inline] nsim_fib_event_work+0x284f/0x2cf0 drivers/net/netdevsim/fib.c:1477 process_one_work+0x3f6/0x960 kernel/workqueue.c:2307 worker_thread+0x616/0xa70 kernel/workqueue.c:2454 kthread+0x2c7/0x2e0 kernel/kthread.c:327 ret_from_fork+0x1f/0x30 value changed: 0x22 -> 0x2a Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 1912 Comm: kworker/1:3 Not tainted 5.16.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: events nsim_fib_event_work Fixes: 0c5fcf9e249e ("IPv6: Add "offload failed" indication to routes") Fixes: bb3c4ab93e44 ("ipv6: Add "offload" and "trap" indications to routes") Signed-off-by: Eric Dumazet Cc: Amit Cohen Cc: Ido Schimmel Reported-by: syzbot Link: https://lore.kernel.org/r/20220216173217.3792411-2-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/netdevsim/fib.c | 4 ++-- include/net/ip6_fib.h | 10 ++++++---- net/ipv6/route.c | 19 ++++++++++--------- 3 files changed, 18 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c index 4300261e2f9e..378ee779061c 100644 --- a/drivers/net/netdevsim/fib.c +++ b/drivers/net/netdevsim/fib.c @@ -623,14 +623,14 @@ static int nsim_fib6_rt_append(struct nsim_fib_data *data, if (err) goto err_fib6_rt_nh_del; - fib6_event->rt_arr[i]->trap = true; + WRITE_ONCE(fib6_event->rt_arr[i]->trap, true); } return 0; err_fib6_rt_nh_del: for (i--; i >= 0; i--) { - fib6_event->rt_arr[i]->trap = false; + WRITE_ONCE(fib6_event->rt_arr[i]->trap, false); nsim_fib6_rt_nh_del(fib6_rt, fib6_event->rt_arr[i]); } return err; diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 40ae8f1b18e5..2048bc8748cb 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -190,14 +190,16 @@ struct fib6_info { u32 fib6_metric; u8 fib6_protocol; u8 fib6_type; + + u8 offload; + u8 trap; + u8 offload_failed; + u8 should_flush:1, dst_nocount:1, dst_nopolicy:1, fib6_destroying:1, - offload:1, - trap:1, - offload_failed:1, - unused:1; + unused:4; struct rcu_head rcu; struct nexthop *nh; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index f4884cda13b9..ea1cf414a92e 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5753,11 +5753,11 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, } if (!dst) { - if (rt->offload) + if (READ_ONCE(rt->offload)) rtm->rtm_flags |= RTM_F_OFFLOAD; - if (rt->trap) + if (READ_ONCE(rt->trap)) rtm->rtm_flags |= RTM_F_TRAP; - if (rt->offload_failed) + if (READ_ONCE(rt->offload_failed)) rtm->rtm_flags |= RTM_F_OFFLOAD_FAILED; } @@ -6215,19 +6215,20 @@ void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i, struct sk_buff *skb; int err; - if (f6i->offload == offload && f6i->trap == trap && - f6i->offload_failed == offload_failed) + if (READ_ONCE(f6i->offload) == offload && + READ_ONCE(f6i->trap) == trap && + READ_ONCE(f6i->offload_failed) == offload_failed) return; - f6i->offload = offload; - f6i->trap = trap; + WRITE_ONCE(f6i->offload, offload); + WRITE_ONCE(f6i->trap, trap); /* 2 means send notifications only if offload_failed was changed. */ if (net->ipv6.sysctl.fib_notify_on_flag_change == 2 && - f6i->offload_failed == offload_failed) + READ_ONCE(f6i->offload_failed) == offload_failed) return; - f6i->offload_failed = offload_failed; + WRITE_ONCE(f6i->offload_failed, offload_failed); if (!rcu_access_pointer(f6i->fib6_node)) /* The route was removed from the tree, do not send -- cgit v1.2.3