From 96ff6ba50ab22c4004cb485f6cbabc75281ba5df Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sun, 6 Oct 2019 14:24:25 -0700 Subject: llc: fix sk_buff leak in llc_conn_service() commit b74555de21acd791f12c4a1aeaf653dd7ac21133 upstream. syzbot reported: BUG: memory leak unreferenced object 0xffff88811eb3de00 (size 224): comm "syz-executor559", pid 7315, jiffies 4294943019 (age 10.300s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 a0 38 24 81 88 ff ff 00 c0 f2 15 81 88 ff ff ..8$............ backtrace: [<000000008d1c66a1>] kmemleak_alloc_recursive include/linux/kmemleak.h:55 [inline] [<000000008d1c66a1>] slab_post_alloc_hook mm/slab.h:439 [inline] [<000000008d1c66a1>] slab_alloc_node mm/slab.c:3269 [inline] [<000000008d1c66a1>] kmem_cache_alloc_node+0x153/0x2a0 mm/slab.c:3579 [<00000000447d9496>] __alloc_skb+0x6e/0x210 net/core/skbuff.c:198 [<000000000cdbf82f>] alloc_skb include/linux/skbuff.h:1058 [inline] [<000000000cdbf82f>] llc_alloc_frame+0x66/0x110 net/llc/llc_sap.c:54 [<000000002418b52e>] llc_conn_ac_send_sabme_cmd_p_set_x+0x2f/0x140 net/llc/llc_c_ac.c:777 [<000000001372ae17>] llc_exec_conn_trans_actions net/llc/llc_conn.c:475 [inline] [<000000001372ae17>] llc_conn_service net/llc/llc_conn.c:400 [inline] [<000000001372ae17>] llc_conn_state_process+0x1ac/0x640 net/llc/llc_conn.c:75 [<00000000f27e53c1>] llc_establish_connection+0x110/0x170 net/llc/llc_if.c:109 [<00000000291b2ca0>] llc_ui_connect+0x10e/0x370 net/llc/af_llc.c:477 [<000000000f9c740b>] __sys_connect+0x11d/0x170 net/socket.c:1840 [...] The bug is that most callers of llc_conn_send_pdu() assume it consumes a reference to the skb, when actually due to commit b85ab56c3f81 ("llc: properly handle dev_queue_xmit() return value") it doesn't. Revert most of that commit, and instead make the few places that need llc_conn_send_pdu() to *not* consume a reference call skb_get() before. Fixes: b85ab56c3f81 ("llc: properly handle dev_queue_xmit() return value") Reported-by: syzbot+6b825a6494a04cc0e3f7@syzkaller.appspotmail.com Signed-off-by: Eric Biggers Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- include/net/llc_conn.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/llc_conn.h b/include/net/llc_conn.h index df528a623548..ea985aa7a6c5 100644 --- a/include/net/llc_conn.h +++ b/include/net/llc_conn.h @@ -104,7 +104,7 @@ void llc_sk_reset(struct sock *sk); /* Access to a connection */ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb); -int llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb); +void llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb); void llc_conn_rtn_pdu(struct sock *sk, struct sk_buff *skb); void llc_conn_resend_i_pdu_as_cmd(struct sock *sk, u8 nr, u8 first_p_bit); void llc_conn_resend_i_pdu_as_rsp(struct sock *sk, u8 nr, u8 first_f_bit); -- cgit v1.2.3 From 09ee754c623344d6a94caf115e77ed74b4b2a702 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 24 Sep 2019 13:11:26 -0700 Subject: sch_netem: fix rcu splat in netem_enqueue() commit 159d2c7d8106177bd9a986fd005a311fe0d11285 upstream. qdisc_root() use from netem_enqueue() triggers a lockdep warning. __dev_queue_xmit() uses rcu_read_lock_bh() which is not equivalent to rcu_read_lock() + local_bh_disable_bh as far as lockdep is concerned. WARNING: suspicious RCU usage 5.3.0-rc7+ #0 Not tainted ----------------------------- include/net/sch_generic.h:492 suspicious rcu_dereference_check() usage! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 1 3 locks held by syz-executor427/8855: #0: 00000000b5525c01 (rcu_read_lock_bh){....}, at: lwtunnel_xmit_redirect include/net/lwtunnel.h:92 [inline] #0: 00000000b5525c01 (rcu_read_lock_bh){....}, at: ip_finish_output2+0x2dc/0x2570 net/ipv4/ip_output.c:214 #1: 00000000b5525c01 (rcu_read_lock_bh){....}, at: __dev_queue_xmit+0x20a/0x3650 net/core/dev.c:3804 #2: 00000000364bae92 (&(&sch->q.lock)->rlock){+.-.}, at: spin_lock include/linux/spinlock.h:338 [inline] #2: 00000000364bae92 (&(&sch->q.lock)->rlock){+.-.}, at: __dev_xmit_skb net/core/dev.c:3502 [inline] #2: 00000000364bae92 (&(&sch->q.lock)->rlock){+.-.}, at: __dev_queue_xmit+0x14b8/0x3650 net/core/dev.c:3838 stack backtrace: CPU: 0 PID: 8855 Comm: syz-executor427 Not tainted 5.3.0-rc7+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x172/0x1f0 lib/dump_stack.c:113 lockdep_rcu_suspicious+0x153/0x15d kernel/locking/lockdep.c:5357 qdisc_root include/net/sch_generic.h:492 [inline] netem_enqueue+0x1cfb/0x2d80 net/sched/sch_netem.c:479 __dev_xmit_skb net/core/dev.c:3527 [inline] __dev_queue_xmit+0x15d2/0x3650 net/core/dev.c:3838 dev_queue_xmit+0x18/0x20 net/core/dev.c:3902 neigh_hh_output include/net/neighbour.h:500 [inline] neigh_output include/net/neighbour.h:509 [inline] ip_finish_output2+0x1726/0x2570 net/ipv4/ip_output.c:228 __ip_finish_output net/ipv4/ip_output.c:308 [inline] __ip_finish_output+0x5fc/0xb90 net/ipv4/ip_output.c:290 ip_finish_output+0x38/0x1f0 net/ipv4/ip_output.c:318 NF_HOOK_COND include/linux/netfilter.h:294 [inline] ip_mc_output+0x292/0xf40 net/ipv4/ip_output.c:417 dst_output include/net/dst.h:436 [inline] ip_local_out+0xbb/0x190 net/ipv4/ip_output.c:125 ip_send_skb+0x42/0xf0 net/ipv4/ip_output.c:1555 udp_send_skb.isra.0+0x6b2/0x1160 net/ipv4/udp.c:887 udp_sendmsg+0x1e96/0x2820 net/ipv4/udp.c:1174 inet_sendmsg+0x9e/0xe0 net/ipv4/af_inet.c:807 sock_sendmsg_nosec net/socket.c:637 [inline] sock_sendmsg+0xd7/0x130 net/socket.c:657 ___sys_sendmsg+0x3e2/0x920 net/socket.c:2311 __sys_sendmmsg+0x1bf/0x4d0 net/socket.c:2413 __do_sys_sendmmsg net/socket.c:2442 [inline] __se_sys_sendmmsg net/socket.c:2439 [inline] __x64_sys_sendmmsg+0x9d/0x100 net/socket.c:2439 do_syscall_64+0xfd/0x6a0 arch/x86/entry/common.c:296 entry_SYSCALL_64_after_hwframe+0x49/0xbe Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/net/sch_generic.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/net') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 7a5d6a073165..ccd2a964dad7 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -289,6 +289,11 @@ static inline struct Qdisc *qdisc_root(const struct Qdisc *qdisc) return q; } +static inline struct Qdisc *qdisc_root_bh(const struct Qdisc *qdisc) +{ + return rcu_dereference_bh(qdisc->dev_queue->qdisc); +} + static inline struct Qdisc *qdisc_root_sleeping(const struct Qdisc *qdisc) { return qdisc->dev_queue->qdisc_sleeping; -- cgit v1.2.3 From 157fdfe11eeb063e30c2965ce98845e3ab1af43b Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 20 May 2018 16:39:10 +0800 Subject: sctp: fix the issue that flags are ignored when using kernel_connect commit 644fbdeacf1d3edd366e44b8ba214de9d1dd66a9 upstream. Now sctp uses inet_dgram_connect as its proto_ops .connect, and the flags param can't be passed into its proto .connect where this flags is really needed. sctp works around it by getting flags from socket file in __sctp_connect. It works for connecting from userspace, as inherently the user sock has socket file and it passes f_flags as the flags param into the proto_ops .connect. However, the sock created by sock_create_kern doesn't have a socket file, and it passes the flags (like O_NONBLOCK) by using the flags param in kernel_connect, which calls proto_ops .connect later. So to fix it, this patch defines a new proto_ops .connect for sctp, sctp_inet_connect, which calls __sctp_connect() directly with this flags param. After this, the sctp's proto .connect can be removed. Note that sctp_inet_connect doesn't need to do some checks that are not needed for sctp, which makes thing better than with inet_dgram_connect. Suggested-by: Marcelo Ricardo Leitner Signed-off-by: Xin Long Acked-by: Neil Horman Acked-by: Marcelo Ricardo Leitner Reviewed-by: Michal Kubecek Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/net/sctp/sctp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index d33b17ba51d2..8a71f4d42c62 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -98,6 +98,8 @@ void sctp_addr_wq_mgmt(struct net *, struct sctp_sockaddr_entry *, int); /* * sctp/socket.c */ +int sctp_inet_connect(struct socket *sock, struct sockaddr *uaddr, + int addr_len, int flags); int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb); int sctp_inet_listen(struct socket *sock, int backlog); void sctp_write_space(struct sock *sk); -- cgit v1.2.3 From 2f036ae97f3ddac74d40cdf6306473dc28200138 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 24 Oct 2019 13:50:27 -0700 Subject: net: fix sk_page_frag() recursion from memory reclaim [ Upstream commit 20eb4f29b60286e0d6dc01d9c260b4bd383c58fb ] sk_page_frag() optimizes skb_frag allocations by using per-task skb_frag cache when it knows it's the only user. The condition is determined by seeing whether the socket allocation mask allows blocking - if the allocation may block, it obviously owns the task's context and ergo exclusively owns current->task_frag. Unfortunately, this misses recursion through memory reclaim path. Please take a look at the following backtrace. [2] RIP: 0010:tcp_sendmsg_locked+0xccf/0xe10 ... tcp_sendmsg+0x27/0x40 sock_sendmsg+0x30/0x40 sock_xmit.isra.24+0xa1/0x170 [nbd] nbd_send_cmd+0x1d2/0x690 [nbd] nbd_queue_rq+0x1b5/0x3b0 [nbd] __blk_mq_try_issue_directly+0x108/0x1b0 blk_mq_request_issue_directly+0xbd/0xe0 blk_mq_try_issue_list_directly+0x41/0xb0 blk_mq_sched_insert_requests+0xa2/0xe0 blk_mq_flush_plug_list+0x205/0x2a0 blk_flush_plug_list+0xc3/0xf0 [1] blk_finish_plug+0x21/0x2e _xfs_buf_ioapply+0x313/0x460 __xfs_buf_submit+0x67/0x220 xfs_buf_read_map+0x113/0x1a0 xfs_trans_read_buf_map+0xbf/0x330 xfs_btree_read_buf_block.constprop.42+0x95/0xd0 xfs_btree_lookup_get_block+0x95/0x170 xfs_btree_lookup+0xcc/0x470 xfs_bmap_del_extent_real+0x254/0x9a0 __xfs_bunmapi+0x45c/0xab0 xfs_bunmapi+0x15/0x30 xfs_itruncate_extents_flags+0xca/0x250 xfs_free_eofblocks+0x181/0x1e0 xfs_fs_destroy_inode+0xa8/0x1b0 destroy_inode+0x38/0x70 dispose_list+0x35/0x50 prune_icache_sb+0x52/0x70 super_cache_scan+0x120/0x1a0 do_shrink_slab+0x120/0x290 shrink_slab+0x216/0x2b0 shrink_node+0x1b6/0x4a0 do_try_to_free_pages+0xc6/0x370 try_to_free_mem_cgroup_pages+0xe3/0x1e0 try_charge+0x29e/0x790 mem_cgroup_charge_skmem+0x6a/0x100 __sk_mem_raise_allocated+0x18e/0x390 __sk_mem_schedule+0x2a/0x40 [0] tcp_sendmsg_locked+0x8eb/0xe10 tcp_sendmsg+0x27/0x40 sock_sendmsg+0x30/0x40 ___sys_sendmsg+0x26d/0x2b0 __sys_sendmsg+0x57/0xa0 do_syscall_64+0x42/0x100 entry_SYSCALL_64_after_hwframe+0x44/0xa9 In [0], tcp_send_msg_locked() was using current->page_frag when it called sk_wmem_schedule(). It already calculated how many bytes can be fit into current->page_frag. Due to memory pressure, sk_wmem_schedule() called into memory reclaim path which called into xfs and then IO issue path. Because the filesystem in question is backed by nbd, the control goes back into the tcp layer - back into tcp_sendmsg_locked(). nbd sets sk_allocation to (GFP_NOIO | __GFP_MEMALLOC) which makes sense - it's in the process of freeing memory and wants to be able to, e.g., drop clean pages to make forward progress. However, this confused sk_page_frag() called from [2]. Because it only tests whether the allocation allows blocking which it does, it now thinks current->page_frag can be used again although it already was being used in [0]. After [2] used current->page_frag, the offset would be increased by the used amount. When the control returns to [0], current->page_frag's offset is increased and the previously calculated number of bytes now may overrun the end of allocated memory leading to silent memory corruptions. Fix it by adding gfpflags_normal_context() which tests sleepable && !reclaim and use it to determine whether to use current->task_frag. v2: Eric didn't like gfp flags being tested twice. Introduce a new helper gfpflags_normal_context() and combine the two tests. Signed-off-by: Tejun Heo Cc: Josef Bacik Cc: Eric Dumazet Cc: stable@vger.kernel.org Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/net/sock.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index 0aadd3b03ced..1571ab68de16 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2077,12 +2077,17 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, * sk_page_frag - return an appropriate page_frag * @sk: socket * - * If socket allocation mode allows current thread to sleep, it means its - * safe to use the per task page_frag instead of the per socket one. + * Use the per task page_frag instead of the per socket one for + * optimization when we know that we're in the normal context and owns + * everything that's associated with %current. + * + * gfpflags_allow_blocking() isn't enough here as direct reclaim may nest + * inside other socket operations and end up recursing into sk_page_frag() + * while it's already in use. */ static inline struct page_frag *sk_page_frag(struct sock *sk) { - if (gfpflags_allow_blocking(sk->sk_allocation)) + if (gfpflags_normal_context(sk->sk_allocation)) return ¤t->task_frag; return &sk->sk_frag; -- cgit v1.2.3 From 491cd03f3b44f58f346ec15e2fc958d0def7b5a7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 22 Oct 2019 07:57:46 -0700 Subject: net/flow_dissector: switch to siphash commit 55667441c84fa5e0911a0aac44fb059c15ba6da2 upstream. UDP IPv6 packets auto flowlabels are using a 32bit secret (static u32 hashrnd in net/core/flow_dissector.c) and apply jhash() over fields known by the receivers. Attackers can easily infer the 32bit secret and use this information to identify a device and/or user, since this 32bit secret is only set at boot time. Really, using jhash() to generate cookies sent on the wire is a serious security concern. Trying to change the rol32(hash, 16) in ip6_make_flowlabel() would be a dead end. Trying to periodically change the secret (like in sch_sfq.c) could change paths taken in the network for long lived flows. Let's switch to siphash, as we did in commit df453700e8d8 ("inet: switch IP ID generator to siphash") Using a cryptographically strong pseudo random function will solve this privacy issue and more generally remove other weak points in the stack. Packet schedulers using skb_get_hash_perturb() benefit from this change. Fixes: b56774163f99 ("ipv6: Enable auto flow labels by default") Fixes: 42240901f7c4 ("ipv6: Implement different admin modes for automatic flow labels") Fixes: 67800f9b1f4e ("ipv6: Call skb_get_hash_flowi6 to get skb->hash in ip6_make_flowlabel") Fixes: cb1ce2ef387b ("ipv6: Implement automatic flow label generation on transmit") Signed-off-by: Eric Dumazet Reported-by: Jonathan Berger Reported-by: Amit Klein Reported-by: Benny Pinkas Cc: Tom Herbert Signed-off-by: David S. Miller Signed-off-by: Mahesh Bandewar Signed-off-by: Greg Kroah-Hartman --- include/net/flow_dissector.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 8c8548cf5888..62a462413081 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -3,6 +3,7 @@ #include #include +#include #include /** @@ -146,7 +147,7 @@ struct flow_dissector { struct flow_keys { struct flow_dissector_key_control control; #define FLOW_KEYS_HASH_START_FIELD basic - struct flow_dissector_key_basic basic; + struct flow_dissector_key_basic basic __aligned(SIPHASH_ALIGNMENT); struct flow_dissector_key_tags tags; struct flow_dissector_key_keyid keyid; struct flow_dissector_key_ports ports; -- cgit v1.2.3 From 817e5140ed12cfb67f8d33de75dccce03895230d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 Nov 2019 20:08:19 -0800 Subject: net: fix data-race in neigh_event_send() [ Upstream commit 1b53d64435d56902fc234ff2507142d971a09687 ] KCSAN reported the following data-race [1] The fix will also prevent the compiler from optimizing out the condition. [1] BUG: KCSAN: data-race in neigh_resolve_output / neigh_resolve_output write to 0xffff8880a41dba78 of 8 bytes by interrupt on cpu 1: neigh_event_send include/net/neighbour.h:443 [inline] neigh_resolve_output+0x78/0x480 net/core/neighbour.c:1474 neigh_output include/net/neighbour.h:511 [inline] ip_finish_output2+0x4af/0xe40 net/ipv4/ip_output.c:228 __ip_finish_output net/ipv4/ip_output.c:308 [inline] __ip_finish_output+0x23a/0x490 net/ipv4/ip_output.c:290 ip_finish_output+0x41/0x160 net/ipv4/ip_output.c:318 NF_HOOK_COND include/linux/netfilter.h:294 [inline] ip_output+0xdf/0x210 net/ipv4/ip_output.c:432 dst_output include/net/dst.h:436 [inline] ip_local_out+0x74/0x90 net/ipv4/ip_output.c:125 __ip_queue_xmit+0x3a8/0xa40 net/ipv4/ip_output.c:532 ip_queue_xmit+0x45/0x60 include/net/ip.h:237 __tcp_transmit_skb+0xe81/0x1d60 net/ipv4/tcp_output.c:1169 tcp_transmit_skb net/ipv4/tcp_output.c:1185 [inline] __tcp_retransmit_skb+0x4bd/0x15f0 net/ipv4/tcp_output.c:2976 tcp_retransmit_skb+0x36/0x1a0 net/ipv4/tcp_output.c:2999 tcp_retransmit_timer+0x719/0x16d0 net/ipv4/tcp_timer.c:515 tcp_write_timer_handler+0x42d/0x510 net/ipv4/tcp_timer.c:598 tcp_write_timer+0xd1/0xf0 net/ipv4/tcp_timer.c:618 read to 0xffff8880a41dba78 of 8 bytes by interrupt on cpu 0: neigh_event_send include/net/neighbour.h:442 [inline] neigh_resolve_output+0x57/0x480 net/core/neighbour.c:1474 neigh_output include/net/neighbour.h:511 [inline] ip_finish_output2+0x4af/0xe40 net/ipv4/ip_output.c:228 __ip_finish_output net/ipv4/ip_output.c:308 [inline] __ip_finish_output+0x23a/0x490 net/ipv4/ip_output.c:290 ip_finish_output+0x41/0x160 net/ipv4/ip_output.c:318 NF_HOOK_COND include/linux/netfilter.h:294 [inline] ip_output+0xdf/0x210 net/ipv4/ip_output.c:432 dst_output include/net/dst.h:436 [inline] ip_local_out+0x74/0x90 net/ipv4/ip_output.c:125 __ip_queue_xmit+0x3a8/0xa40 net/ipv4/ip_output.c:532 ip_queue_xmit+0x45/0x60 include/net/ip.h:237 __tcp_transmit_skb+0xe81/0x1d60 net/ipv4/tcp_output.c:1169 tcp_transmit_skb net/ipv4/tcp_output.c:1185 [inline] __tcp_retransmit_skb+0x4bd/0x15f0 net/ipv4/tcp_output.c:2976 tcp_retransmit_skb+0x36/0x1a0 net/ipv4/tcp_output.c:2999 tcp_retransmit_timer+0x719/0x16d0 net/ipv4/tcp_timer.c:515 tcp_write_timer_handler+0x42d/0x510 net/ipv4/tcp_timer.c:598 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.4.0-rc3+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/net/neighbour.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/neighbour.h b/include/net/neighbour.h index f6017ddc4ded..1c0d07376125 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -425,8 +425,8 @@ static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) { unsigned long now = jiffies; - if (neigh->used != now) - neigh->used = now; + if (READ_ONCE(neigh->used) != now) + WRITE_ONCE(neigh->used, now); if (!(neigh->nud_state&(NUD_CONNECTED|NUD_DELAY|NUD_PROBE))) return __neigh_event_send(neigh, skb); return 0; -- cgit v1.2.3 From b10f57eb8982c4601d7e830c5490d98ebe3c775f Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Thu, 31 Oct 2019 11:06:24 +0100 Subject: netfilter: nf_tables: Align nft_expr private data to 64-bit commit 250367c59e6ba0d79d702a059712d66edacd4a1a upstream. Invoking the following commands on a 32-bit architecture with strict alignment requirements (such as an ARMv7-based Raspberry Pi) results in an alignment exception: # nft add table ip test-ip4 # nft add chain ip test-ip4 output { type filter hook output priority 0; } # nft add rule ip test-ip4 output quota 1025 bytes Alignment trap: not handling instruction e1b26f9f at [<7f4473f8>] Unhandled fault: alignment exception (0x001) at 0xb832e824 Internal error: : 1 [#1] PREEMPT SMP ARM Hardware name: BCM2835 [<7f4473fc>] (nft_quota_do_init [nft_quota]) [<7f447448>] (nft_quota_init [nft_quota]) [<7f4260d0>] (nf_tables_newrule [nf_tables]) [<7f4168dc>] (nfnetlink_rcv_batch [nfnetlink]) [<7f416bd0>] (nfnetlink_rcv [nfnetlink]) [<8078b334>] (netlink_unicast) [<8078b664>] (netlink_sendmsg) [<8071b47c>] (sock_sendmsg) [<8071bd18>] (___sys_sendmsg) [<8071ce3c>] (__sys_sendmsg) [<8071ce94>] (sys_sendmsg) The reason is that nft_quota_do_init() calls atomic64_set() on an atomic64_t which is only aligned to 32-bit, not 64-bit, because it succeeds struct nft_expr in memory which only contains a 32-bit pointer. Fix by aligning the nft_expr private data to 64-bit. Fixes: 96518518cc41 ("netfilter: add nftables") Signed-off-by: Lukas Wunner Cc: stable@vger.kernel.org # v3.13+ Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- include/net/netfilter/nf_tables.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 4bd7508bedc9..b96df7499600 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -648,7 +648,8 @@ struct nft_expr_ops { */ struct nft_expr { const struct nft_expr_ops *ops; - unsigned char data[]; + unsigned char data[] + __attribute__((aligned(__alignof__(u64)))); }; static inline void *nft_expr_priv(const struct nft_expr *expr) -- cgit v1.2.3 From f00565130bde6f2e2906b6a961f095b5589d7393 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 23 Oct 2019 09:53:03 -0700 Subject: ipvs: move old_secure_tcp into struct netns_ipvs [ Upstream commit c24b75e0f9239e78105f81c5f03a751641eb07ef ] syzbot reported the following issue : BUG: KCSAN: data-race in update_defense_level / update_defense_level read to 0xffffffff861a6260 of 4 bytes by task 3006 on cpu 1: update_defense_level+0x621/0xb30 net/netfilter/ipvs/ip_vs_ctl.c:177 defense_work_handler+0x3d/0xd0 net/netfilter/ipvs/ip_vs_ctl.c:225 process_one_work+0x3d4/0x890 kernel/workqueue.c:2269 worker_thread+0xa0/0x800 kernel/workqueue.c:2415 kthread+0x1d4/0x200 drivers/block/aoe/aoecmd.c:1253 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:352 write to 0xffffffff861a6260 of 4 bytes by task 7333 on cpu 0: update_defense_level+0xa62/0xb30 net/netfilter/ipvs/ip_vs_ctl.c:205 defense_work_handler+0x3d/0xd0 net/netfilter/ipvs/ip_vs_ctl.c:225 process_one_work+0x3d4/0x890 kernel/workqueue.c:2269 worker_thread+0xa0/0x800 kernel/workqueue.c:2415 kthread+0x1d4/0x200 drivers/block/aoe/aoecmd.c:1253 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:352 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 7333 Comm: kworker/0:5 Not tainted 5.4.0-rc3+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: events defense_work_handler Indeed, old_secure_tcp is currently a static variable, while it needs to be a per netns variable. Fixes: a0840e2e165a ("IPVS: netns, ip_vs_ctl local vars moved to ipvs struct.") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: Simon Horman Signed-off-by: Sasha Levin --- include/net/ip_vs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index a6cc576fd467..b0156f8a9ab7 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -880,6 +880,7 @@ struct netns_ipvs { struct delayed_work defense_work; /* Work handler */ int drop_rate; int drop_counter; + int old_secure_tcp; atomic_t dropentry; /* locks in ctl.c */ spinlock_t dropentry_lock; /* drop entry handling */ -- cgit v1.2.3 From b575bf8be32348bb1053141d7afb4b7a7336e7f6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 4 Nov 2019 21:38:43 -0800 Subject: net: prevent load/store tearing on sk->sk_stamp [ Upstream commit f75359f3ac855940c5718af10ba089b8977bf339 ] Add a couple of READ_ONCE() and WRITE_ONCE() to prevent load-tearing and store-tearing in sock_read_timestamp() and sock_write_timestamp() This might prevent another KCSAN report. Fixes: 3a0ed3e96197 ("sock: Make sock->sk_stamp thread-safe") Signed-off-by: Eric Dumazet Cc: Deepa Dinamani Acked-by: Deepa Dinamani Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/net/sock.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index 1571ab68de16..5ed4786a2058 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2174,7 +2174,7 @@ static inline ktime_t sock_read_timestamp(struct sock *sk) return kt; #else - return sk->sk_stamp; + return READ_ONCE(sk->sk_stamp); #endif } @@ -2185,7 +2185,7 @@ static inline void sock_write_timestamp(struct sock *sk, ktime_t kt) sk->sk_stamp = kt; write_sequnlock(&sk->sk_stamp_seq); #else - sk->sk_stamp = kt; + WRITE_ONCE(sk->sk_stamp, kt); #endif } -- cgit v1.2.3 From db70320a71fbd38a560335a47613ac33d61eb5a7 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 11 Sep 2018 11:42:06 -0700 Subject: llc: avoid blocking in llc_sap_close() [ Upstream commit 9708d2b5b7c648e8e0a40d11e8cea12f6277f33c ] llc_sap_close() is called by llc_sap_put() which could be called in BH context in llc_rcv(). We can't block in BH. There is no reason to block it here, kfree_rcu() should be sufficient. Signed-off-by: Cong Wang Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/net/llc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/llc.h b/include/net/llc.h index 82d989995d18..95e5ced4c133 100644 --- a/include/net/llc.h +++ b/include/net/llc.h @@ -66,6 +66,7 @@ struct llc_sap { int sk_count; struct hlist_nulls_head sk_laddr_hash[LLC_SK_LADDR_HASH_ENTRIES]; struct hlist_head sk_dev_hash[LLC_SK_DEV_HASH_ENTRIES]; + struct rcu_head rcu; }; static inline -- cgit v1.2.3