From e38910c0072b541a91954682c8b074a93e57c09b Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Wed, 7 Jun 2023 09:27:08 +0200 Subject: can: isotp: isotp_sendmsg(): fix return error fix on TX path With commit d674a8f123b4 ("can: isotp: isotp_sendmsg(): fix return error on FC timeout on TX path") the missing correct return value in the case of a protocol error was introduced. But the way the error value has been read and sent to the user space does not follow the common scheme to clear the error after reading which is provided by the sock_error() function. This leads to an error report at the following write() attempt although everything should be working. Fixes: d674a8f123b4 ("can: isotp: isotp_sendmsg(): fix return error on FC timeout on TX path") Reported-by: Carsten Schmidt Signed-off-by: Oliver Hartkopp Link: https://lore.kernel.org/all/20230607072708.38809-1-socketcan@hartkopp.net Cc: stable@vger.kernel.org Signed-off-by: Marc Kleine-Budde --- net/can/isotp.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/can/isotp.c b/net/can/isotp.c index 84f9aba02901..ca9d728d6d72 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -1112,8 +1112,9 @@ wait_free_buffer: if (err) goto err_event_drop; - if (sk->sk_err) - return -sk->sk_err; + err = sock_error(sk); + if (err) + return err; } return size; -- cgit From 8d61f926d42045961e6b65191c09e3678d86a9cf Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 21 Jun 2023 15:43:37 +0000 Subject: netlink: fix potential deadlock in netlink_set_err() syzbot reported a possible deadlock in netlink_set_err() [1] A similar issue was fixed in commit 1d482e666b8e ("netlink: disable IRQs for netlink_lock_table()") in netlink_lock_table() This patch adds IRQ safety to netlink_set_err() and __netlink_diag_dump() which were not covered by cited commit. [1] WARNING: possible irq lock inversion dependency detected 6.4.0-rc6-syzkaller-00240-g4e9f0ec38852 #0 Not tainted syz-executor.2/23011 just changed the state of lock: ffffffff8e1a7a58 (nl_table_lock){.+.?}-{2:2}, at: netlink_set_err+0x2e/0x3a0 net/netlink/af_netlink.c:1612 but this lock was taken by another, SOFTIRQ-safe lock in the past: (&local->queue_stop_reason_lock){..-.}-{2:2} and interrupts could create inverse lock ordering between them. other info that might help us debug this: Possible interrupt unsafe locking scenario: CPU0 CPU1 ---- ---- lock(nl_table_lock); local_irq_disable(); lock(&local->queue_stop_reason_lock); lock(nl_table_lock); lock(&local->queue_stop_reason_lock); *** DEADLOCK *** Fixes: 1d482e666b8e ("netlink: disable IRQs for netlink_lock_table()") Reported-by: syzbot+a7d200a347f912723e5c@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=a7d200a347f912723e5c Link: https://lore.kernel.org/netdev/000000000000e38d1605fea5747e@google.com/T/#u Signed-off-by: Eric Dumazet Cc: Johannes Berg Link: https://lore.kernel.org/r/20230621154337.1668594-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/netlink/af_netlink.c | 5 +++-- net/netlink/diag.c | 5 +++-- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 3a1e0fd5bf14..5968b6450d82 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1600,6 +1600,7 @@ out: int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code) { struct netlink_set_err_data info; + unsigned long flags; struct sock *sk; int ret = 0; @@ -1609,12 +1610,12 @@ int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code) /* sk->sk_err wants a positive error value */ info.code = -code; - read_lock(&nl_table_lock); + read_lock_irqsave(&nl_table_lock, flags); sk_for_each_bound(sk, &nl_table[ssk->sk_protocol].mc_list) ret += do_one_set_err(sk, &info); - read_unlock(&nl_table_lock); + read_unlock_irqrestore(&nl_table_lock, flags); return ret; } EXPORT_SYMBOL(netlink_set_err); diff --git a/net/netlink/diag.c b/net/netlink/diag.c index c6255eac305c..4143b2ea4195 100644 --- a/net/netlink/diag.c +++ b/net/netlink/diag.c @@ -94,6 +94,7 @@ static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net *net = sock_net(skb->sk); struct netlink_diag_req *req; struct netlink_sock *nlsk; + unsigned long flags; struct sock *sk; int num = 2; int ret = 0; @@ -152,7 +153,7 @@ static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, num++; mc_list: - read_lock(&nl_table_lock); + read_lock_irqsave(&nl_table_lock, flags); sk_for_each_bound(sk, &tbl->mc_list) { if (sk_hashed(sk)) continue; @@ -173,7 +174,7 @@ mc_list: } num++; } - read_unlock(&nl_table_lock); + read_unlock_irqrestore(&nl_table_lock, flags); done: cb->args[0] = num; -- cgit From aa5406950726e336c5c9585b09799a734b6e77bf Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 21 Jun 2023 17:47:20 +0000 Subject: netlink: do not hard code device address lenth in fdb dumps syzbot reports that some netdev devices do not have a six bytes address [1] Replace ETH_ALEN by dev->addr_len. [1] (Case of a device where dev->addr_len = 4) BUG: KMSAN: kernel-infoleak in instrument_copy_to_user include/linux/instrumented.h:114 [inline] BUG: KMSAN: kernel-infoleak in copyout+0xb8/0x100 lib/iov_iter.c:169 instrument_copy_to_user include/linux/instrumented.h:114 [inline] copyout+0xb8/0x100 lib/iov_iter.c:169 _copy_to_iter+0x6d8/0x1d00 lib/iov_iter.c:536 copy_to_iter include/linux/uio.h:206 [inline] simple_copy_to_iter+0x68/0xa0 net/core/datagram.c:513 __skb_datagram_iter+0x123/0xdc0 net/core/datagram.c:419 skb_copy_datagram_iter+0x5c/0x200 net/core/datagram.c:527 skb_copy_datagram_msg include/linux/skbuff.h:3960 [inline] netlink_recvmsg+0x4ae/0x15a0 net/netlink/af_netlink.c:1970 sock_recvmsg_nosec net/socket.c:1019 [inline] sock_recvmsg net/socket.c:1040 [inline] ____sys_recvmsg+0x283/0x7f0 net/socket.c:2722 ___sys_recvmsg+0x223/0x840 net/socket.c:2764 do_recvmmsg+0x4f9/0xfd0 net/socket.c:2858 __sys_recvmmsg net/socket.c:2937 [inline] __do_sys_recvmmsg net/socket.c:2960 [inline] __se_sys_recvmmsg net/socket.c:2953 [inline] __x64_sys_recvmmsg+0x397/0x490 net/socket.c:2953 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Uninit was stored to memory at: __nla_put lib/nlattr.c:1009 [inline] nla_put+0x1c6/0x230 lib/nlattr.c:1067 nlmsg_populate_fdb_fill+0x2b8/0x600 net/core/rtnetlink.c:4071 nlmsg_populate_fdb net/core/rtnetlink.c:4418 [inline] ndo_dflt_fdb_dump+0x616/0x840 net/core/rtnetlink.c:4456 rtnl_fdb_dump+0x14ff/0x1fc0 net/core/rtnetlink.c:4629 netlink_dump+0x9d1/0x1310 net/netlink/af_netlink.c:2268 netlink_recvmsg+0xc5c/0x15a0 net/netlink/af_netlink.c:1995 sock_recvmsg_nosec+0x7a/0x120 net/socket.c:1019 ____sys_recvmsg+0x664/0x7f0 net/socket.c:2720 ___sys_recvmsg+0x223/0x840 net/socket.c:2764 do_recvmmsg+0x4f9/0xfd0 net/socket.c:2858 __sys_recvmmsg net/socket.c:2937 [inline] __do_sys_recvmmsg net/socket.c:2960 [inline] __se_sys_recvmmsg net/socket.c:2953 [inline] __x64_sys_recvmmsg+0x397/0x490 net/socket.c:2953 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Uninit was created at: slab_post_alloc_hook+0x12d/0xb60 mm/slab.h:716 slab_alloc_node mm/slub.c:3451 [inline] __kmem_cache_alloc_node+0x4ff/0x8b0 mm/slub.c:3490 kmalloc_trace+0x51/0x200 mm/slab_common.c:1057 kmalloc include/linux/slab.h:559 [inline] __hw_addr_create net/core/dev_addr_lists.c:60 [inline] __hw_addr_add_ex+0x2e5/0x9e0 net/core/dev_addr_lists.c:118 __dev_mc_add net/core/dev_addr_lists.c:867 [inline] dev_mc_add+0x9a/0x130 net/core/dev_addr_lists.c:885 igmp6_group_added+0x267/0xbc0 net/ipv6/mcast.c:680 ipv6_mc_up+0x296/0x3b0 net/ipv6/mcast.c:2754 ipv6_mc_remap+0x1e/0x30 net/ipv6/mcast.c:2708 addrconf_type_change net/ipv6/addrconf.c:3731 [inline] addrconf_notify+0x4d3/0x1d90 net/ipv6/addrconf.c:3699 notifier_call_chain kernel/notifier.c:93 [inline] raw_notifier_call_chain+0xe4/0x430 kernel/notifier.c:461 call_netdevice_notifiers_info net/core/dev.c:1935 [inline] call_netdevice_notifiers_extack net/core/dev.c:1973 [inline] call_netdevice_notifiers+0x1ee/0x2d0 net/core/dev.c:1987 bond_enslave+0xccd/0x53f0 drivers/net/bonding/bond_main.c:1906 do_set_master net/core/rtnetlink.c:2626 [inline] rtnl_newlink_create net/core/rtnetlink.c:3460 [inline] __rtnl_newlink net/core/rtnetlink.c:3660 [inline] rtnl_newlink+0x378c/0x40e0 net/core/rtnetlink.c:3673 rtnetlink_rcv_msg+0x16a6/0x1840 net/core/rtnetlink.c:6395 netlink_rcv_skb+0x371/0x650 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x34/0x40 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0xf28/0x1230 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x122f/0x13d0 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x999/0xd50 net/socket.c:2503 ___sys_sendmsg+0x28d/0x3c0 net/socket.c:2557 __sys_sendmsg net/socket.c:2586 [inline] __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x304/0x490 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Bytes 2856-2857 of 3500 are uninitialized Memory access of size 3500 starts at ffff888018d99104 Data copied to user address 0000000020000480 Fixes: d83b06036048 ("net: add fdb generic dump routine") Reported-by: syzbot Signed-off-by: Eric Dumazet Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/20230621174720.1845040-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/core/rtnetlink.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 41de3a2f29e1..7776611a14ae 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -4090,7 +4090,7 @@ static int nlmsg_populate_fdb_fill(struct sk_buff *skb, ndm->ndm_ifindex = dev->ifindex; ndm->ndm_state = ndm_state; - if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr)) + if (nla_put(skb, NDA_LLADDR, dev->addr_len, addr)) goto nla_put_failure; if (vid) if (nla_put(skb, NDA_VLAN, sizeof(u16), &vid)) @@ -4104,10 +4104,10 @@ nla_put_failure: return -EMSGSIZE; } -static inline size_t rtnl_fdb_nlmsg_size(void) +static inline size_t rtnl_fdb_nlmsg_size(const struct net_device *dev) { return NLMSG_ALIGN(sizeof(struct ndmsg)) + - nla_total_size(ETH_ALEN) + /* NDA_LLADDR */ + nla_total_size(dev->addr_len) + /* NDA_LLADDR */ nla_total_size(sizeof(u16)) + /* NDA_VLAN */ 0; } @@ -4119,7 +4119,7 @@ static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, u16 vid, int type, struct sk_buff *skb; int err = -ENOBUFS; - skb = nlmsg_new(rtnl_fdb_nlmsg_size(), GFP_ATOMIC); + skb = nlmsg_new(rtnl_fdb_nlmsg_size(dev), GFP_ATOMIC); if (!skb) goto errout; -- cgit From 11b73313c12403f617b47752db0ab3deef201af7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 22 Jun 2023 18:15:03 +0000 Subject: sch_netem: fix issues in netem_change() vs get_dist_table() In blamed commit, I missed that get_dist_table() was allocating memory using GFP_KERNEL, and acquiring qdisc lock to perform the swap of newly allocated table with current one. In this patch, get_dist_table() is allocating memory and copy user data before we acquire the qdisc lock. Then we perform swap operations while being protected by the lock. Note that after this patch netem_change() no longer can do partial changes. If an error is returned, qdisc conf is left unchanged. Fixes: 2174a08db80d ("sch_netem: acquire qdisc lock in netem_change()") Reported-by: syzbot Signed-off-by: Eric Dumazet Cc: Stephen Hemminger Acked-by: Jamal Hadi Salim Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230622181503.2327695-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/sched/sch_netem.c | 59 ++++++++++++++++++++++----------------------------- 1 file changed, 25 insertions(+), 34 deletions(-) (limited to 'net') diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index e79be1b3e74d..b93ec2a3454e 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -773,12 +773,10 @@ static void dist_free(struct disttable *d) * signed 16 bit values. */ -static int get_dist_table(struct Qdisc *sch, struct disttable **tbl, - const struct nlattr *attr) +static int get_dist_table(struct disttable **tbl, const struct nlattr *attr) { size_t n = nla_len(attr)/sizeof(__s16); const __s16 *data = nla_data(attr); - spinlock_t *root_lock; struct disttable *d; int i; @@ -793,13 +791,7 @@ static int get_dist_table(struct Qdisc *sch, struct disttable **tbl, for (i = 0; i < n; i++) d->table[i] = data[i]; - root_lock = qdisc_root_sleeping_lock(sch); - - spin_lock_bh(root_lock); - swap(*tbl, d); - spin_unlock_bh(root_lock); - - dist_free(d); + *tbl = d; return 0; } @@ -956,6 +948,8 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, { struct netem_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_NETEM_MAX + 1]; + struct disttable *delay_dist = NULL; + struct disttable *slot_dist = NULL; struct tc_netem_qopt *qopt; struct clgstate old_clg; int old_loss_model = CLG_RANDOM; @@ -966,6 +960,18 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, if (ret < 0) return ret; + if (tb[TCA_NETEM_DELAY_DIST]) { + ret = get_dist_table(&delay_dist, tb[TCA_NETEM_DELAY_DIST]); + if (ret) + goto table_free; + } + + if (tb[TCA_NETEM_SLOT_DIST]) { + ret = get_dist_table(&slot_dist, tb[TCA_NETEM_SLOT_DIST]); + if (ret) + goto table_free; + } + sch_tree_lock(sch); /* backup q->clg and q->loss_model */ old_clg = q->clg; @@ -975,26 +981,17 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, ret = get_loss_clg(q, tb[TCA_NETEM_LOSS]); if (ret) { q->loss_model = old_loss_model; + q->clg = old_clg; goto unlock; } } else { q->loss_model = CLG_RANDOM; } - if (tb[TCA_NETEM_DELAY_DIST]) { - ret = get_dist_table(sch, &q->delay_dist, - tb[TCA_NETEM_DELAY_DIST]); - if (ret) - goto get_table_failure; - } - - if (tb[TCA_NETEM_SLOT_DIST]) { - ret = get_dist_table(sch, &q->slot_dist, - tb[TCA_NETEM_SLOT_DIST]); - if (ret) - goto get_table_failure; - } - + if (delay_dist) + swap(q->delay_dist, delay_dist); + if (slot_dist) + swap(q->slot_dist, slot_dist); sch->limit = qopt->limit; q->latency = PSCHED_TICKS2NS(qopt->latency); @@ -1044,17 +1041,11 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, unlock: sch_tree_unlock(sch); - return ret; -get_table_failure: - /* recover clg and loss_model, in case of - * q->clg and q->loss_model were modified - * in get_loss_clg() - */ - q->clg = old_clg; - q->loss_model = old_loss_model; - - goto unlock; +table_free: + dist_free(delay_dist); + dist_free(slot_dist); + return ret; } static int netem_init(struct Qdisc *sch, struct nlattr *opt, -- cgit From 6709d4b7bc2e079241fdef15d1160581c5261c10 Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Sun, 25 Jun 2023 17:10:07 +0800 Subject: net: nfc: Fix use-after-free caused by nfc_llcp_find_local This commit fixes several use-after-free that caused by function nfc_llcp_find_local(). For example, one UAF can happen when below buggy time window occurs. // nfc_genl_llc_get_params | // nfc_unregister_device | dev = nfc_get_device(idx); | device_lock(...) if (!dev) | dev->shutting_down = true; return -ENODEV; | device_unlock(...); | device_lock(...); | // nfc_llcp_unregister_device | nfc_llcp_find_local() nfc_llcp_find_local(...); | | local_cleanup() if (!local) { | rc = -ENODEV; | // nfc_llcp_local_put goto exit; | kref_put(.., local_release) } | | // local_release | list_del(&local->list) // nfc_genl_send_params | kfree() local->dev->idx !!!UAF!!! | | and the crash trace for the one of the discussed UAF like: BUG: KASAN: slab-use-after-free in nfc_genl_llc_get_params+0x72f/0x780 net/nfc/netlink.c:1045 Read of size 8 at addr ffff888105b0e410 by task 20114 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x72/0xa0 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:319 [inline] print_report+0xcc/0x620 mm/kasan/report.c:430 kasan_report+0xb2/0xe0 mm/kasan/report.c:536 nfc_genl_send_params net/nfc/netlink.c:999 [inline] nfc_genl_llc_get_params+0x72f/0x780 net/nfc/netlink.c:1045 genl_family_rcv_msg_doit.isra.0+0x1ee/0x2e0 net/netlink/genetlink.c:968 genl_family_rcv_msg net/netlink/genetlink.c:1048 [inline] genl_rcv_msg+0x503/0x7d0 net/netlink/genetlink.c:1065 netlink_rcv_skb+0x161/0x430 net/netlink/af_netlink.c:2548 genl_rcv+0x28/0x40 net/netlink/genetlink.c:1076 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x644/0x900 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x934/0xe70 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg+0x1b6/0x200 net/socket.c:747 ____sys_sendmsg+0x6e9/0x890 net/socket.c:2501 ___sys_sendmsg+0x110/0x1b0 net/socket.c:2555 __sys_sendmsg+0xf7/0x1d0 net/socket.c:2584 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3f/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc RIP: 0033:0x7f34640a2389 RSP: 002b:00007f3463415168 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007f34641c1f80 RCX: 00007f34640a2389 RDX: 0000000000000000 RSI: 0000000020000240 RDI: 0000000000000006 RBP: 00007f34640ed493 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007ffe38449ecf R14: 00007f3463415300 R15: 0000000000022000 Allocated by task 20116: kasan_save_stack+0x22/0x50 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 ____kasan_kmalloc mm/kasan/common.c:374 [inline] __kasan_kmalloc+0x7f/0x90 mm/kasan/common.c:383 kmalloc include/linux/slab.h:580 [inline] kzalloc include/linux/slab.h:720 [inline] nfc_llcp_register_device+0x49/0xa40 net/nfc/llcp_core.c:1567 nfc_register_device+0x61/0x260 net/nfc/core.c:1124 nci_register_device+0x776/0xb20 net/nfc/nci/core.c:1257 virtual_ncidev_open+0x147/0x230 drivers/nfc/virtual_ncidev.c:148 misc_open+0x379/0x4a0 drivers/char/misc.c:165 chrdev_open+0x26c/0x780 fs/char_dev.c:414 do_dentry_open+0x6c4/0x12a0 fs/open.c:920 do_open fs/namei.c:3560 [inline] path_openat+0x24fe/0x37e0 fs/namei.c:3715 do_filp_open+0x1ba/0x410 fs/namei.c:3742 do_sys_openat2+0x171/0x4c0 fs/open.c:1356 do_sys_open fs/open.c:1372 [inline] __do_sys_openat fs/open.c:1388 [inline] __se_sys_openat fs/open.c:1383 [inline] __x64_sys_openat+0x143/0x200 fs/open.c:1383 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3f/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc Freed by task 20115: kasan_save_stack+0x22/0x50 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 kasan_save_free_info+0x2e/0x50 mm/kasan/generic.c:521 ____kasan_slab_free mm/kasan/common.c:236 [inline] ____kasan_slab_free mm/kasan/common.c:200 [inline] __kasan_slab_free+0x10a/0x190 mm/kasan/common.c:244 kasan_slab_free include/linux/kasan.h:162 [inline] slab_free_hook mm/slub.c:1781 [inline] slab_free_freelist_hook mm/slub.c:1807 [inline] slab_free mm/slub.c:3787 [inline] __kmem_cache_free+0x7a/0x190 mm/slub.c:3800 local_release net/nfc/llcp_core.c:174 [inline] kref_put include/linux/kref.h:65 [inline] nfc_llcp_local_put net/nfc/llcp_core.c:182 [inline] nfc_llcp_local_put net/nfc/llcp_core.c:177 [inline] nfc_llcp_unregister_device+0x206/0x290 net/nfc/llcp_core.c:1620 nfc_unregister_device+0x160/0x1d0 net/nfc/core.c:1179 virtual_ncidev_close+0x52/0xa0 drivers/nfc/virtual_ncidev.c:163 __fput+0x252/0xa20 fs/file_table.c:321 task_work_run+0x174/0x270 kernel/task_work.c:179 resume_user_mode_work include/linux/resume_user_mode.h:49 [inline] exit_to_user_mode_loop kernel/entry/common.c:171 [inline] exit_to_user_mode_prepare+0x108/0x110 kernel/entry/common.c:204 __syscall_exit_to_user_mode_work kernel/entry/common.c:286 [inline] syscall_exit_to_user_mode+0x21/0x50 kernel/entry/common.c:297 do_syscall_64+0x4c/0x90 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x72/0xdc Last potentially related work creation: kasan_save_stack+0x22/0x50 mm/kasan/common.c:45 __kasan_record_aux_stack+0x95/0xb0 mm/kasan/generic.c:491 kvfree_call_rcu+0x29/0xa80 kernel/rcu/tree.c:3328 drop_sysctl_table+0x3be/0x4e0 fs/proc/proc_sysctl.c:1735 unregister_sysctl_table.part.0+0x9c/0x190 fs/proc/proc_sysctl.c:1773 unregister_sysctl_table+0x24/0x30 fs/proc/proc_sysctl.c:1753 neigh_sysctl_unregister+0x5f/0x80 net/core/neighbour.c:3895 addrconf_notify+0x140/0x17b0 net/ipv6/addrconf.c:3684 notifier_call_chain+0xbe/0x210 kernel/notifier.c:87 call_netdevice_notifiers_info+0xb5/0x150 net/core/dev.c:1937 call_netdevice_notifiers_extack net/core/dev.c:1975 [inline] call_netdevice_notifiers net/core/dev.c:1989 [inline] dev_change_name+0x3c3/0x870 net/core/dev.c:1211 dev_ifsioc+0x800/0xf70 net/core/dev_ioctl.c:376 dev_ioctl+0x3d9/0xf80 net/core/dev_ioctl.c:542 sock_do_ioctl+0x160/0x260 net/socket.c:1213 sock_ioctl+0x3f9/0x670 net/socket.c:1316 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl fs/ioctl.c:856 [inline] __x64_sys_ioctl+0x19e/0x210 fs/ioctl.c:856 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3f/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc The buggy address belongs to the object at ffff888105b0e400 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 16 bytes inside of freed 1024-byte region [ffff888105b0e400, ffff888105b0e800) The buggy address belongs to the physical page: head:ffffea000416c200 order:3 entire_mapcount:0 nr_pages_mapped:0 pincount:0 flags: 0x200000000010200(slab|head|node=0|zone=2) raw: 0200000000010200 ffff8881000430c0 ffffea00044c7010 ffffea0004510e10 raw: 0000000000000000 00000000000a000a 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888105b0e300: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff888105b0e380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffff888105b0e400: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff888105b0e480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888105b0e500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb In summary, this patch solves those use-after-free by 1. Re-implement the nfc_llcp_find_local(). The current version does not grab the reference when getting the local from the linked list. For example, the llcp_sock_bind() gets the reference like below: // llcp_sock_bind() local = nfc_llcp_find_local(dev); // A ..... \ | raceable ..... / llcp_sock->local = nfc_llcp_local_get(local); // B There is an apparent race window that one can drop the reference and free the local object fetched in (A) before (B) gets the reference. 2. Some callers of the nfc_llcp_find_local() do not grab the reference at all. For example, the nfc_genl_llc_{{get/set}_params/sdreq} functions. We add the nfc_llcp_local_put() for them. Moreover, we add the necessary error handling function to put the reference. 3. Add the nfc_llcp_remove_local() helper. The local object is removed from the linked list in local_release() when all reference is gone. This patch removes it when nfc_llcp_unregister_device() is called. Therefore, every caller of nfc_llcp_find_local() will get a reference even when the nfc_llcp_unregister_device() is called. This promises no use-after-free for the local object is ever possible. Fixes: 52feb444a903 ("NFC: Extend netlink interface for LTO, RW, and MIUX parameters support") Fixes: c7aa12252f51 ("NFC: Take a reference on the LLCP local pointer when creating a socket") Signed-off-by: Lin Ma Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- net/nfc/llcp.h | 1 - net/nfc/llcp_commands.c | 12 +++++++++--- net/nfc/llcp_core.c | 49 ++++++++++++++++++++++++++++++++++++++++++------- net/nfc/llcp_sock.c | 18 ++++++++++-------- net/nfc/netlink.c | 20 +++++++++++++++----- net/nfc/nfc.h | 1 + 6 files changed, 77 insertions(+), 24 deletions(-) (limited to 'net') diff --git a/net/nfc/llcp.h b/net/nfc/llcp.h index c1d9be636933..d8345ed57c95 100644 --- a/net/nfc/llcp.h +++ b/net/nfc/llcp.h @@ -201,7 +201,6 @@ void nfc_llcp_sock_link(struct llcp_sock_list *l, struct sock *s); void nfc_llcp_sock_unlink(struct llcp_sock_list *l, struct sock *s); void nfc_llcp_socket_remote_param_init(struct nfc_llcp_sock *sock); struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev); -struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local); int nfc_llcp_local_put(struct nfc_llcp_local *local); u8 nfc_llcp_get_sdp_ssap(struct nfc_llcp_local *local, struct nfc_llcp_sock *sock); diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index 41e3a20c8935..5d2d4bc26ef9 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -359,6 +359,7 @@ int nfc_llcp_send_symm(struct nfc_dev *dev) struct sk_buff *skb; struct nfc_llcp_local *local; u16 size = 0; + int err; local = nfc_llcp_find_local(dev); if (local == NULL) @@ -368,8 +369,10 @@ int nfc_llcp_send_symm(struct nfc_dev *dev) size += dev->tx_headroom + dev->tx_tailroom + NFC_HEADER_SIZE; skb = alloc_skb(size, GFP_KERNEL); - if (skb == NULL) - return -ENOMEM; + if (skb == NULL) { + err = -ENOMEM; + goto out; + } skb_reserve(skb, dev->tx_headroom + NFC_HEADER_SIZE); @@ -379,8 +382,11 @@ int nfc_llcp_send_symm(struct nfc_dev *dev) nfc_llcp_send_to_raw_sock(local, skb, NFC_DIRECTION_TX); - return nfc_data_exchange(dev, local->target_idx, skb, + err = nfc_data_exchange(dev, local->target_idx, skb, nfc_llcp_recv, local); +out: + nfc_llcp_local_put(local); + return err; } int nfc_llcp_send_connect(struct nfc_llcp_sock *sock) diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index a27e1842b2a0..f60e424e0607 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -17,6 +17,8 @@ static u8 llcp_magic[3] = {0x46, 0x66, 0x6d}; static LIST_HEAD(llcp_devices); +/* Protects llcp_devices list */ +static DEFINE_SPINLOCK(llcp_devices_lock); static void nfc_llcp_rx_skb(struct nfc_llcp_local *local, struct sk_buff *skb); @@ -141,7 +143,7 @@ static void nfc_llcp_socket_release(struct nfc_llcp_local *local, bool device, write_unlock(&local->raw_sockets.lock); } -struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local) +static struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local) { kref_get(&local->ref); @@ -169,7 +171,6 @@ static void local_release(struct kref *ref) local = container_of(ref, struct nfc_llcp_local, ref); - list_del(&local->list); local_cleanup(local); kfree(local); } @@ -282,12 +283,33 @@ static void nfc_llcp_sdreq_timer(struct timer_list *t) struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev) { struct nfc_llcp_local *local; + struct nfc_llcp_local *res = NULL; + spin_lock(&llcp_devices_lock); list_for_each_entry(local, &llcp_devices, list) - if (local->dev == dev) + if (local->dev == dev) { + res = nfc_llcp_local_get(local); + break; + } + spin_unlock(&llcp_devices_lock); + + return res; +} + +static struct nfc_llcp_local *nfc_llcp_remove_local(struct nfc_dev *dev) +{ + struct nfc_llcp_local *local, *tmp; + + spin_lock(&llcp_devices_lock); + list_for_each_entry_safe(local, tmp, &llcp_devices, list) + if (local->dev == dev) { + list_del(&local->list); + spin_unlock(&llcp_devices_lock); return local; + } + spin_unlock(&llcp_devices_lock); - pr_debug("No device found\n"); + pr_warn("Shutting down device not found\n"); return NULL; } @@ -608,12 +630,15 @@ u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len) *general_bytes_len = local->gb_len; + nfc_llcp_local_put(local); + return local->gb; } int nfc_llcp_set_remote_gb(struct nfc_dev *dev, const u8 *gb, u8 gb_len) { struct nfc_llcp_local *local; + int err; if (gb_len < 3 || gb_len > NFC_MAX_GT_LEN) return -EINVAL; @@ -630,12 +655,16 @@ int nfc_llcp_set_remote_gb(struct nfc_dev *dev, const u8 *gb, u8 gb_len) if (memcmp(local->remote_gb, llcp_magic, 3)) { pr_err("MAC does not support LLCP\n"); - return -EINVAL; + err = -EINVAL; + goto out; } - return nfc_llcp_parse_gb_tlv(local, + err = nfc_llcp_parse_gb_tlv(local, &local->remote_gb[3], local->remote_gb_len - 3); +out: + nfc_llcp_local_put(local); + return err; } static u8 nfc_llcp_dsap(const struct sk_buff *pdu) @@ -1517,6 +1546,8 @@ int nfc_llcp_data_received(struct nfc_dev *dev, struct sk_buff *skb) __nfc_llcp_recv(local, skb); + nfc_llcp_local_put(local); + return 0; } @@ -1533,6 +1564,8 @@ void nfc_llcp_mac_is_down(struct nfc_dev *dev) /* Close and purge all existing sockets */ nfc_llcp_socket_release(local, true, 0); + + nfc_llcp_local_put(local); } void nfc_llcp_mac_is_up(struct nfc_dev *dev, u32 target_idx, @@ -1558,6 +1591,8 @@ void nfc_llcp_mac_is_up(struct nfc_dev *dev, u32 target_idx, mod_timer(&local->link_timer, jiffies + msecs_to_jiffies(local->remote_lto)); } + + nfc_llcp_local_put(local); } int nfc_llcp_register_device(struct nfc_dev *ndev) @@ -1608,7 +1643,7 @@ int nfc_llcp_register_device(struct nfc_dev *ndev) void nfc_llcp_unregister_device(struct nfc_dev *dev) { - struct nfc_llcp_local *local = nfc_llcp_find_local(dev); + struct nfc_llcp_local *local = nfc_llcp_remove_local(dev); if (local == NULL) { pr_debug("No such device\n"); diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index 77642d18a3b4..645677f84dba 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -99,7 +99,7 @@ static int llcp_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) } llcp_sock->dev = dev; - llcp_sock->local = nfc_llcp_local_get(local); + llcp_sock->local = local; llcp_sock->nfc_protocol = llcp_addr.nfc_protocol; llcp_sock->service_name_len = min_t(unsigned int, llcp_addr.service_name_len, @@ -186,7 +186,7 @@ static int llcp_raw_sock_bind(struct socket *sock, struct sockaddr *addr, } llcp_sock->dev = dev; - llcp_sock->local = nfc_llcp_local_get(local); + llcp_sock->local = local; llcp_sock->nfc_protocol = llcp_addr.nfc_protocol; nfc_llcp_sock_link(&local->raw_sockets, sk); @@ -696,22 +696,22 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr, if (dev->dep_link_up == false) { ret = -ENOLINK; device_unlock(&dev->dev); - goto put_dev; + goto sock_llcp_put_local; } device_unlock(&dev->dev); if (local->rf_mode == NFC_RF_INITIATOR && addr->target_idx != local->target_idx) { ret = -ENOLINK; - goto put_dev; + goto sock_llcp_put_local; } llcp_sock->dev = dev; - llcp_sock->local = nfc_llcp_local_get(local); + llcp_sock->local = local; llcp_sock->ssap = nfc_llcp_get_local_ssap(local); if (llcp_sock->ssap == LLCP_SAP_MAX) { ret = -ENOMEM; - goto sock_llcp_put_local; + goto sock_llcp_nullify; } llcp_sock->reserved_ssap = llcp_sock->ssap; @@ -757,11 +757,13 @@ sock_unlink: sock_llcp_release: nfc_llcp_put_ssap(local, llcp_sock->ssap); -sock_llcp_put_local: - nfc_llcp_local_put(llcp_sock->local); +sock_llcp_nullify: llcp_sock->local = NULL; llcp_sock->dev = NULL; +sock_llcp_put_local: + nfc_llcp_local_put(local); + put_dev: nfc_put_device(dev); diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index b9264e730fd9..e9ac6a6f934e 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -1039,11 +1039,14 @@ static int nfc_genl_llc_get_params(struct sk_buff *skb, struct genl_info *info) msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { rc = -ENOMEM; - goto exit; + goto put_local; } rc = nfc_genl_send_params(msg, local, info->snd_portid, info->snd_seq); +put_local: + nfc_llcp_local_put(local); + exit: device_unlock(&dev->dev); @@ -1105,7 +1108,7 @@ static int nfc_genl_llc_set_params(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NFC_ATTR_LLC_PARAM_LTO]) { if (dev->dep_link_up) { rc = -EINPROGRESS; - goto exit; + goto put_local; } local->lto = nla_get_u8(info->attrs[NFC_ATTR_LLC_PARAM_LTO]); @@ -1117,6 +1120,9 @@ static int nfc_genl_llc_set_params(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NFC_ATTR_LLC_PARAM_MIUX]) local->miux = cpu_to_be16(miux); +put_local: + nfc_llcp_local_put(local); + exit: device_unlock(&dev->dev); @@ -1172,7 +1178,7 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info) if (rc != 0) { rc = -EINVAL; - goto exit; + goto put_local; } if (!sdp_attrs[NFC_SDP_ATTR_URI]) @@ -1191,7 +1197,7 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info) sdreq = nfc_llcp_build_sdreq_tlv(tid, uri, uri_len); if (sdreq == NULL) { rc = -ENOMEM; - goto exit; + goto put_local; } tlvs_len += sdreq->tlv_len; @@ -1201,10 +1207,14 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info) if (hlist_empty(&sdreq_list)) { rc = -EINVAL; - goto exit; + goto put_local; } rc = nfc_llcp_send_snl_sdreq(local, &sdreq_list, tlvs_len); + +put_local: + nfc_llcp_local_put(local); + exit: device_unlock(&dev->dev); diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h index de2ec66d7e83..0b1e6466f4fb 100644 --- a/net/nfc/nfc.h +++ b/net/nfc/nfc.h @@ -52,6 +52,7 @@ int nfc_llcp_set_remote_gb(struct nfc_dev *dev, const u8 *gb, u8 gb_len); u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len); int nfc_llcp_data_received(struct nfc_dev *dev, struct sk_buff *skb); struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev); +int nfc_llcp_local_put(struct nfc_llcp_local *local); int __init nfc_llcp_init(void); void nfc_llcp_exit(void); void nfc_llcp_free_sdp_tlv(struct nfc_llcp_sdp_tlv *sdp); -- cgit From ff0a3a7d52ff7282dbd183e7fc29a1fe386b0c30 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 21 Jun 2023 17:56:53 +0200 Subject: netfilter: conntrack: dccp: copy entire header to stack buffer, not just basic one Eric Dumazet says: nf_conntrack_dccp_packet() has an unique: dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh); And nothing more is 'pulled' from the packet, depending on the content. dh->dccph_doff, and/or dh->dccph_x ...) So dccp_ack_seq() is happily reading stuff past the _dh buffer. BUG: KASAN: stack-out-of-bounds in nf_conntrack_dccp_packet+0x1134/0x11c0 Read of size 4 at addr ffff000128f66e0c by task syz-executor.2/29371 [..] Fix this by increasing the stack buffer to also include room for the extra sequence numbers and all the known dccp packet type headers, then pull again after the initial validation of the basic header. While at it, mark packets invalid that lack 48bit sequence bit but where RFC says the type MUST use them. Compile tested only. v2: first skb_header_pointer() now needs to adjust the size to only pull the generic header. (Eric) Heads-up: I intend to remove dccp conntrack support later this year. Fixes: 2bc780499aa3 ("[NETFILTER]: nf_conntrack: add DCCP protocol support") Reported-by: Eric Dumazet Signed-off-by: Florian Westphal Reviewed-by: Eric Dumazet Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_proto_dccp.c | 52 +++++++++++++++++++++++++++++++-- 1 file changed, 49 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index c1557d47ccd1..d4fd626d2b8c 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -432,9 +432,19 @@ static bool dccp_error(const struct dccp_hdr *dh, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state) { + static const unsigned long require_seq48 = 1 << DCCP_PKT_REQUEST | + 1 << DCCP_PKT_RESPONSE | + 1 << DCCP_PKT_CLOSEREQ | + 1 << DCCP_PKT_CLOSE | + 1 << DCCP_PKT_RESET | + 1 << DCCP_PKT_SYNC | + 1 << DCCP_PKT_SYNCACK; unsigned int dccp_len = skb->len - dataoff; unsigned int cscov; const char *msg; + u8 type; + + BUILD_BUG_ON(DCCP_PKT_INVALID >= BITS_PER_LONG); if (dh->dccph_doff * 4 < sizeof(struct dccp_hdr) || dh->dccph_doff * 4 > dccp_len) { @@ -459,34 +469,70 @@ static bool dccp_error(const struct dccp_hdr *dh, goto out_invalid; } - if (dh->dccph_type >= DCCP_PKT_INVALID) { + type = dh->dccph_type; + if (type >= DCCP_PKT_INVALID) { msg = "nf_ct_dccp: reserved packet type "; goto out_invalid; } + + if (test_bit(type, &require_seq48) && !dh->dccph_x) { + msg = "nf_ct_dccp: type lacks 48bit sequence numbers"; + goto out_invalid; + } + return false; out_invalid: nf_l4proto_log_invalid(skb, state, IPPROTO_DCCP, "%s", msg); return true; } +struct nf_conntrack_dccp_buf { + struct dccp_hdr dh; /* generic header part */ + struct dccp_hdr_ext ext; /* optional depending dh->dccph_x */ + union { /* depends on header type */ + struct dccp_hdr_ack_bits ack; + struct dccp_hdr_request req; + struct dccp_hdr_response response; + struct dccp_hdr_reset rst; + } u; +}; + +static struct dccp_hdr * +dccp_header_pointer(const struct sk_buff *skb, int offset, const struct dccp_hdr *dh, + struct nf_conntrack_dccp_buf *buf) +{ + unsigned int hdrlen = __dccp_hdr_len(dh); + + if (hdrlen > sizeof(*buf)) + return NULL; + + return skb_header_pointer(skb, offset, hdrlen, buf); +} + int nf_conntrack_dccp_packet(struct nf_conn *ct, struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - struct dccp_hdr _dh, *dh; + struct nf_conntrack_dccp_buf _dh; u_int8_t type, old_state, new_state; enum ct_dccp_roles role; unsigned int *timeouts; + struct dccp_hdr *dh; - dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh); + dh = skb_header_pointer(skb, dataoff, sizeof(*dh), &_dh.dh); if (!dh) return NF_DROP; if (dccp_error(dh, skb, dataoff, state)) return -NF_ACCEPT; + /* pull again, including possible 48 bit sequences and subtype header */ + dh = dccp_header_pointer(skb, dataoff, dh, &_dh); + if (!dh) + return NF_DROP; + type = dh->dccph_type; if (!nf_ct_is_confirmed(ct) && !dccp_new(ct, skb, dh, state)) return -NF_ACCEPT; -- cgit From f188d30087480eab421cd8ca552fb15f55d57f4d Mon Sep 17 00:00:00 2001 From: "Ilia.Gavrilov" Date: Fri, 23 Jun 2023 11:23:46 +0000 Subject: netfilter: nf_conntrack_sip: fix the ct_sip_parse_numerical_param() return value. ct_sip_parse_numerical_param() returns only 0 or 1 now. But process_register_request() and process_register_response() imply checking for a negative value if parsing of a numerical header parameter failed. The invocation in nf_nat_sip() looks correct: if (ct_sip_parse_numerical_param(...) > 0 && ...) { ... } Make the return value of the function ct_sip_parse_numerical_param() a tristate to fix all the cases a) return 1 if value is found; *val is set b) return 0 if value is not found; *val is unchanged c) return -1 on error; *val is undefined Found by InfoTeCS on behalf of Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 0f32a40fc91a ("[NETFILTER]: nf_conntrack_sip: create signalling expectations") Signed-off-by: Ilia.Gavrilov Reviewed-by: Simon Horman Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_sip.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 77f5e82d8e3f..d0eac27f6ba0 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -611,7 +611,7 @@ int ct_sip_parse_numerical_param(const struct nf_conn *ct, const char *dptr, start += strlen(name); *val = simple_strtoul(start, &end, 0); if (start == end) - return 0; + return -1; if (matchoff && matchlen) { *matchoff = start - dptr; *matchlen = end - start; -- cgit From 3e70489721b6c870252c9082c496703677240f53 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 26 Jun 2023 00:42:18 +0200 Subject: netfilter: nf_tables: unbind non-anonymous set if rule construction fails Otherwise a dangling reference to a rule object that is gone remains in the set binding list. Fixes: 26b5a5712eb8 ("netfilter: nf_tables: add NFT_TRANS_PREPARE_ERROR to deal with bound set/chain") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net') diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 4c7937fd803f..1d64c163076a 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5343,6 +5343,8 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, nft_set_trans_unbind(ctx, set); if (nft_set_is_anonymous(set)) nft_deactivate_next(ctx->net, set); + else + list_del_rcu(&binding->list); set->use--; break; -- cgit From b389139f12f287b8ed2e2628b72df89a081f0b59 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 26 Jun 2023 00:42:19 +0200 Subject: netfilter: nf_tables: fix underflow in chain reference counter Set element addition error path decrements reference counter on chains twice: once on element release and again via nft_data_release(). Then, d6b478666ffa ("netfilter: nf_tables: fix underflow in object reference counter") incorrectly fixed this by removing the stateful object reference count decrement. Restore the stateful object decrement as in b91d90368837 ("netfilter: nf_tables: fix leaking object reference count") and let nft_data_release() decrement the chain reference counter, so this is done only once. Fixes: d6b478666ffa ("netfilter: nf_tables: fix underflow in object reference counter") Fixes: 628bd3e49cba ("netfilter: nf_tables: drop map element references from preparation phase") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 1d64c163076a..c742918f22a4 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -6771,7 +6771,9 @@ err_set_full: err_element_clash: kfree(trans); err_elem_free: - nft_set_elem_destroy(set, elem.priv, true); + nf_tables_set_elem_destroy(ctx, set, elem.priv); + if (obj) + obj->use--; err_parse_data: if (nla[NFTA_SET_ELEM_DATA] != NULL) nft_data_release(&elem.data.val, desc.type); -- cgit From d06f925f13976ab82167c93467c70a337a0a3cda Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 26 Jun 2023 18:44:02 +0300 Subject: net: dsa: avoid suspicious RCU usage for synced VLAN-aware MAC addresses When using the felix driver (the only one which supports UC filtering and MC filtering) as a DSA master for a random other DSA switch, one can see the following stack trace when the downstream switch ports join a VLAN-aware bridge: ============================= WARNING: suspicious RCU usage ----------------------------- net/8021q/vlan_core.c:238 suspicious rcu_dereference_protected() usage! stack backtrace: Workqueue: dsa_ordered dsa_slave_switchdev_event_work Call trace: lockdep_rcu_suspicious+0x170/0x210 vlan_for_each+0x8c/0x188 dsa_slave_sync_uc+0x128/0x178 __hw_addr_sync_dev+0x138/0x158 dsa_slave_set_rx_mode+0x58/0x70 __dev_set_rx_mode+0x88/0xa8 dev_uc_add+0x74/0xa0 dsa_port_bridge_host_fdb_add+0xec/0x180 dsa_slave_switchdev_event_work+0x7c/0x1c8 process_one_work+0x290/0x568 What it's saying is that vlan_for_each() expects rtnl_lock() context and it's not getting it, when it's called from the DSA master's ndo_set_rx_mode(). The caller of that - dsa_slave_set_rx_mode() - is the slave DSA interface's dsa_port_bridge_host_fdb_add() which comes from the deferred dsa_slave_switchdev_event_work(). We went to great lengths to avoid the rtnl_lock() context in that call path in commit 0faf890fc519 ("net: dsa: drop rtnl_lock from dsa_slave_switchdev_event_work"), and calling rtnl_lock() is simply not an option due to the possibility of deadlocking when calling dsa_flush_workqueue() from the call paths that do hold rtnl_lock() - basically all of them. So, when the DSA master calls vlan_for_each() from its ndo_set_rx_mode(), the state of the 8021q driver on this device is really not protected from concurrent access by anything. Looking at net/8021q/, I don't think that vlan_info->vid_list was particularly designed with RCU traversal in mind, so introducing an RCU read-side form of vlan_for_each() - vlan_for_each_rcu() - won't be so easy, and it also wouldn't be exactly what we need anyway. In general I believe that the solution isn't in net/8021q/ anyway; vlan_for_each() is not cut out for this task. DSA doesn't need rtnl_lock() to be held per se - since it's not a netdev state change that we're blocking, but rather, just concurrent additions/removals to a VLAN list. We don't even need sleepable context - the callback of vlan_for_each() just schedules deferred work. The proposed escape is to remove the dependency on vlan_for_each() and to open-code a non-sleepable, rtnl-free alternative to that, based on copies of the VLAN list modified from .ndo_vlan_rx_add_vid() and .ndo_vlan_rx_kill_vid(). Fixes: 64fdc5f341db ("net: dsa: sync unicast and multicast addresses for VLAN filters too") Signed-off-by: Vladimir Oltean Link: https://lore.kernel.org/r/20230626154402.3154454-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- net/dsa/dsa.c | 2 +- net/dsa/slave.c | 84 ++++++++++++++++++++++++++++++++++++++------------------ net/dsa/switch.c | 4 +-- net/dsa/switch.h | 3 ++ 4 files changed, 64 insertions(+), 29 deletions(-) (limited to 'net') diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 1afed89e03c0..ccbdb98109f8 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -1106,7 +1106,7 @@ static struct dsa_port *dsa_port_touch(struct dsa_switch *ds, int index) mutex_init(&dp->vlans_lock); INIT_LIST_HEAD(&dp->fdbs); INIT_LIST_HEAD(&dp->mdbs); - INIT_LIST_HEAD(&dp->vlans); + INIT_LIST_HEAD(&dp->vlans); /* also initializes &dp->user_vlans */ INIT_LIST_HEAD(&dp->list); list_add_tail(&dp->list, &dst->ports); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 165bb2cb8431..527b1d576460 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -27,6 +27,7 @@ #include "master.h" #include "netlink.h" #include "slave.h" +#include "switch.h" #include "tag.h" struct dsa_switchdev_event_work { @@ -161,8 +162,7 @@ static int dsa_slave_schedule_standalone_work(struct net_device *dev, return 0; } -static int dsa_slave_host_vlan_rx_filtering(struct net_device *vdev, int vid, - void *arg) +static int dsa_slave_host_vlan_rx_filtering(void *arg, int vid) { struct dsa_host_vlan_rx_filtering_ctx *ctx = arg; @@ -170,6 +170,28 @@ static int dsa_slave_host_vlan_rx_filtering(struct net_device *vdev, int vid, ctx->addr, vid); } +static int dsa_slave_vlan_for_each(struct net_device *dev, + int (*cb)(void *arg, int vid), void *arg) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_vlan *v; + int err; + + lockdep_assert_held(&dev->addr_list_lock); + + err = cb(arg, 0); + if (err) + return err; + + list_for_each_entry(v, &dp->user_vlans, list) { + err = cb(arg, v->vid); + if (err) + return err; + } + + return 0; +} + static int dsa_slave_sync_uc(struct net_device *dev, const unsigned char *addr) { @@ -180,18 +202,14 @@ static int dsa_slave_sync_uc(struct net_device *dev, .addr = addr, .event = DSA_UC_ADD, }; - int err; dev_uc_add(master, addr); if (!dsa_switch_supports_uc_filtering(dp->ds)) return 0; - err = dsa_slave_schedule_standalone_work(dev, DSA_UC_ADD, addr, 0); - if (err) - return err; - - return vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, &ctx); + return dsa_slave_vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, + &ctx); } static int dsa_slave_unsync_uc(struct net_device *dev, @@ -204,18 +222,14 @@ static int dsa_slave_unsync_uc(struct net_device *dev, .addr = addr, .event = DSA_UC_DEL, }; - int err; dev_uc_del(master, addr); if (!dsa_switch_supports_uc_filtering(dp->ds)) return 0; - err = dsa_slave_schedule_standalone_work(dev, DSA_UC_DEL, addr, 0); - if (err) - return err; - - return vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, &ctx); + return dsa_slave_vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, + &ctx); } static int dsa_slave_sync_mc(struct net_device *dev, @@ -228,18 +242,14 @@ static int dsa_slave_sync_mc(struct net_device *dev, .addr = addr, .event = DSA_MC_ADD, }; - int err; dev_mc_add(master, addr); if (!dsa_switch_supports_mc_filtering(dp->ds)) return 0; - err = dsa_slave_schedule_standalone_work(dev, DSA_MC_ADD, addr, 0); - if (err) - return err; - - return vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, &ctx); + return dsa_slave_vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, + &ctx); } static int dsa_slave_unsync_mc(struct net_device *dev, @@ -252,18 +262,14 @@ static int dsa_slave_unsync_mc(struct net_device *dev, .addr = addr, .event = DSA_MC_DEL, }; - int err; dev_mc_del(master, addr); if (!dsa_switch_supports_mc_filtering(dp->ds)) return 0; - err = dsa_slave_schedule_standalone_work(dev, DSA_MC_DEL, addr, 0); - if (err) - return err; - - return vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, &ctx); + return dsa_slave_vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, + &ctx); } void dsa_slave_sync_ha(struct net_device *dev) @@ -1759,6 +1765,7 @@ static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto, struct netlink_ext_ack extack = {0}; struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; + struct dsa_vlan *v; int ret; /* User port... */ @@ -1782,8 +1789,17 @@ static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto, !dsa_switch_supports_mc_filtering(ds)) return 0; + v = kzalloc(sizeof(*v), GFP_KERNEL); + if (!v) { + ret = -ENOMEM; + goto rollback; + } + netif_addr_lock_bh(dev); + v->vid = vid; + list_add_tail(&v->list, &dp->user_vlans); + if (dsa_switch_supports_mc_filtering(ds)) { netdev_for_each_synced_mc_addr(ha, dev) { dsa_slave_schedule_standalone_work(dev, DSA_MC_ADD, @@ -1803,6 +1819,12 @@ static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto, dsa_flush_workqueue(); return 0; + +rollback: + dsa_port_host_vlan_del(dp, &vlan); + dsa_port_vlan_del(dp, &vlan); + + return ret; } static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, @@ -1816,6 +1838,7 @@ static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, }; struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; + struct dsa_vlan *v; int err; err = dsa_port_vlan_del(dp, &vlan); @@ -1832,6 +1855,15 @@ static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, netif_addr_lock_bh(dev); + v = dsa_vlan_find(&dp->user_vlans, &vlan); + if (!v) { + netif_addr_unlock_bh(dev); + return -ENOENT; + } + + list_del(&v->list); + kfree(v); + if (dsa_switch_supports_mc_filtering(ds)) { netdev_for_each_synced_mc_addr(ha, dev) { dsa_slave_schedule_standalone_work(dev, DSA_MC_DEL, diff --git a/net/dsa/switch.c b/net/dsa/switch.c index 8c9a9f94b756..1a42f9317334 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -673,8 +673,8 @@ static bool dsa_port_host_vlan_match(struct dsa_port *dp, return false; } -static struct dsa_vlan *dsa_vlan_find(struct list_head *vlan_list, - const struct switchdev_obj_port_vlan *vlan) +struct dsa_vlan *dsa_vlan_find(struct list_head *vlan_list, + const struct switchdev_obj_port_vlan *vlan) { struct dsa_vlan *v; diff --git a/net/dsa/switch.h b/net/dsa/switch.h index 15e67b95eb6e..ea034677da15 100644 --- a/net/dsa/switch.h +++ b/net/dsa/switch.h @@ -111,6 +111,9 @@ struct dsa_notifier_master_state_info { bool operational; }; +struct dsa_vlan *dsa_vlan_find(struct list_head *vlan_list, + const struct switchdev_obj_port_vlan *vlan); + int dsa_tree_notify(struct dsa_switch_tree *dst, unsigned long e, void *v); int dsa_broadcast(unsigned long e, void *v); -- cgit From 25a9c8a4431c364f97f75558cb346d2ad3f53fbb Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 26 Jun 2023 09:43:13 -0700 Subject: netlink: Add __sock_i_ino() for __netlink_diag_dump(). syzbot reported a warning in __local_bh_enable_ip(). [0] Commit 8d61f926d420 ("netlink: fix potential deadlock in netlink_set_err()") converted read_lock(&nl_table_lock) to read_lock_irqsave() in __netlink_diag_dump() to prevent a deadlock. However, __netlink_diag_dump() calls sock_i_ino() that uses read_lock_bh() and read_unlock_bh(). If CONFIG_TRACE_IRQFLAGS=y, read_unlock_bh() finally enables IRQ even though it should stay disabled until the following read_unlock_irqrestore(). Using read_lock() in sock_i_ino() would trigger a lockdep splat in another place that was fixed in commit f064af1e500a ("net: fix a lockdep splat"), so let's add __sock_i_ino() that would be safe to use under BH disabled. [0]: WARNING: CPU: 0 PID: 5012 at kernel/softirq.c:376 __local_bh_enable_ip+0xbe/0x130 kernel/softirq.c:376 Modules linked in: CPU: 0 PID: 5012 Comm: syz-executor487 Not tainted 6.4.0-rc7-syzkaller-00202-g6f68fc395f49 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/27/2023 RIP: 0010:__local_bh_enable_ip+0xbe/0x130 kernel/softirq.c:376 Code: 45 bf 01 00 00 00 e8 91 5b 0a 00 e8 3c 15 3d 00 fb 65 8b 05 ec e9 b5 7e 85 c0 74 58 5b 5d c3 65 8b 05 b2 b6 b4 7e 85 c0 75 a2 <0f> 0b eb 9e e8 89 15 3d 00 eb 9f 48 89 ef e8 6f 49 18 00 eb a8 0f RSP: 0018:ffffc90003a1f3d0 EFLAGS: 00010046 RAX: 0000000000000000 RBX: 0000000000000201 RCX: 1ffffffff1cf5996 RDX: 0000000000000000 RSI: 0000000000000201 RDI: ffffffff8805c6f3 RBP: ffffffff8805c6f3 R08: 0000000000000001 R09: ffff8880152b03a3 R10: ffffed1002a56074 R11: 0000000000000005 R12: 00000000000073e4 R13: dffffc0000000000 R14: 0000000000000002 R15: 0000000000000000 FS: 0000555556726300(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000045ad50 CR3: 000000007c646000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: sock_i_ino+0x83/0xa0 net/core/sock.c:2559 __netlink_diag_dump+0x45c/0x790 net/netlink/diag.c:171 netlink_diag_dump+0xd6/0x230 net/netlink/diag.c:207 netlink_dump+0x570/0xc50 net/netlink/af_netlink.c:2269 __netlink_dump_start+0x64b/0x910 net/netlink/af_netlink.c:2374 netlink_dump_start include/linux/netlink.h:329 [inline] netlink_diag_handler_dump+0x1ae/0x250 net/netlink/diag.c:238 __sock_diag_cmd net/core/sock_diag.c:238 [inline] sock_diag_rcv_msg+0x31e/0x440 net/core/sock_diag.c:269 netlink_rcv_skb+0x165/0x440 net/netlink/af_netlink.c:2547 sock_diag_rcv+0x2a/0x40 net/core/sock_diag.c:280 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x547/0x7f0 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x925/0xe30 net/netlink/af_netlink.c:1914 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg+0xde/0x190 net/socket.c:747 ____sys_sendmsg+0x71c/0x900 net/socket.c:2503 ___sys_sendmsg+0x110/0x1b0 net/socket.c:2557 __sys_sendmsg+0xf7/0x1c0 net/socket.c:2586 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f5303aaabb9 Code: 28 c3 e8 2a 14 00 00 66 2e 0f 1f 84 00 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffc7506e548 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f5303aaabb9 RDX: 0000000000000000 RSI: 0000000020000180 RDI: 0000000000000003 RBP: 00007f5303a6ed60 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f5303a6edf0 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 Fixes: 8d61f926d420 ("netlink: fix potential deadlock in netlink_set_err()") Reported-by: syzbot+5da61cf6a9bc1902d422@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=5da61cf6a9bc1902d422 Suggested-by: Eric Dumazet Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20230626164313.52528-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- net/core/sock.c | 17 ++++++++++++++--- net/netlink/diag.c | 2 +- 2 files changed, 15 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/core/sock.c b/net/core/sock.c index 6e5662ca00fe..4a0edccf8606 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2550,13 +2550,24 @@ kuid_t sock_i_uid(struct sock *sk) } EXPORT_SYMBOL(sock_i_uid); -unsigned long sock_i_ino(struct sock *sk) +unsigned long __sock_i_ino(struct sock *sk) { unsigned long ino; - read_lock_bh(&sk->sk_callback_lock); + read_lock(&sk->sk_callback_lock); ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0; - read_unlock_bh(&sk->sk_callback_lock); + read_unlock(&sk->sk_callback_lock); + return ino; +} +EXPORT_SYMBOL(__sock_i_ino); + +unsigned long sock_i_ino(struct sock *sk) +{ + unsigned long ino; + + local_bh_disable(); + ino = __sock_i_ino(sk); + local_bh_enable(); return ino; } EXPORT_SYMBOL(sock_i_ino); diff --git a/net/netlink/diag.c b/net/netlink/diag.c index 4143b2ea4195..e4f21b1067bc 100644 --- a/net/netlink/diag.c +++ b/net/netlink/diag.c @@ -168,7 +168,7 @@ mc_list: NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - sock_i_ino(sk)) < 0) { + __sock_i_ino(sk)) < 0) { ret = 1; break; } -- cgit