From 8d975c15c0cd744000ca386247432d57b21f9df0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 25 Jan 2024 17:05:57 +0000 Subject: ip6_tunnel: make sure to pull inner header in __ip6_tnl_rcv() syzbot found __ip6_tnl_rcv() could access unitiliazed data [1]. Call pskb_inet_may_pull() to fix this, and initialize ipv6h variable after this call as it can change skb->head. [1] BUG: KMSAN: uninit-value in __INET_ECN_decapsulate include/net/inet_ecn.h:253 [inline] BUG: KMSAN: uninit-value in INET_ECN_decapsulate include/net/inet_ecn.h:275 [inline] BUG: KMSAN: uninit-value in IP6_ECN_decapsulate+0x7df/0x1e50 include/net/inet_ecn.h:321 __INET_ECN_decapsulate include/net/inet_ecn.h:253 [inline] INET_ECN_decapsulate include/net/inet_ecn.h:275 [inline] IP6_ECN_decapsulate+0x7df/0x1e50 include/net/inet_ecn.h:321 ip6ip6_dscp_ecn_decapsulate+0x178/0x1b0 net/ipv6/ip6_tunnel.c:727 __ip6_tnl_rcv+0xd4e/0x1590 net/ipv6/ip6_tunnel.c:845 ip6_tnl_rcv+0xce/0x100 net/ipv6/ip6_tunnel.c:888 gre_rcv+0x143f/0x1870 ip6_protocol_deliver_rcu+0xda6/0x2a60 net/ipv6/ip6_input.c:438 ip6_input_finish net/ipv6/ip6_input.c:483 [inline] NF_HOOK include/linux/netfilter.h:314 [inline] ip6_input+0x15d/0x430 net/ipv6/ip6_input.c:492 ip6_mc_input+0xa7e/0xc80 net/ipv6/ip6_input.c:586 dst_input include/net/dst.h:461 [inline] ip6_rcv_finish+0x5db/0x870 net/ipv6/ip6_input.c:79 NF_HOOK include/linux/netfilter.h:314 [inline] ipv6_rcv+0xda/0x390 net/ipv6/ip6_input.c:310 __netif_receive_skb_one_core net/core/dev.c:5532 [inline] __netif_receive_skb+0x1a6/0x5a0 net/core/dev.c:5646 netif_receive_skb_internal net/core/dev.c:5732 [inline] netif_receive_skb+0x58/0x660 net/core/dev.c:5791 tun_rx_batched+0x3ee/0x980 drivers/net/tun.c:1555 tun_get_user+0x53af/0x66d0 drivers/net/tun.c:2002 tun_chr_write_iter+0x3af/0x5d0 drivers/net/tun.c:2048 call_write_iter include/linux/fs.h:2084 [inline] new_sync_write fs/read_write.c:497 [inline] vfs_write+0x786/0x1200 fs/read_write.c:590 ksys_write+0x20f/0x4c0 fs/read_write.c:643 __do_sys_write fs/read_write.c:655 [inline] __se_sys_write fs/read_write.c:652 [inline] __x64_sys_write+0x93/0xd0 fs/read_write.c:652 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0x6d/0x140 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x63/0x6b Uninit was created at: slab_post_alloc_hook+0x129/0xa70 mm/slab.h:768 slab_alloc_node mm/slub.c:3478 [inline] kmem_cache_alloc_node+0x5e9/0xb10 mm/slub.c:3523 kmalloc_reserve+0x13d/0x4a0 net/core/skbuff.c:560 __alloc_skb+0x318/0x740 net/core/skbuff.c:651 alloc_skb include/linux/skbuff.h:1286 [inline] alloc_skb_with_frags+0xc8/0xbd0 net/core/skbuff.c:6334 sock_alloc_send_pskb+0xa80/0xbf0 net/core/sock.c:2787 tun_alloc_skb drivers/net/tun.c:1531 [inline] tun_get_user+0x1e8a/0x66d0 drivers/net/tun.c:1846 tun_chr_write_iter+0x3af/0x5d0 drivers/net/tun.c:2048 call_write_iter include/linux/fs.h:2084 [inline] new_sync_write fs/read_write.c:497 [inline] vfs_write+0x786/0x1200 fs/read_write.c:590 ksys_write+0x20f/0x4c0 fs/read_write.c:643 __do_sys_write fs/read_write.c:655 [inline] __se_sys_write fs/read_write.c:652 [inline] __x64_sys_write+0x93/0xd0 fs/read_write.c:652 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0x6d/0x140 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x63/0x6b CPU: 0 PID: 5034 Comm: syz-executor331 Not tainted 6.7.0-syzkaller-00562-g9f8413c4a66f #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/17/2023 Fixes: 0d3c703a9d17 ("ipv6: Cleanup IPv6 tunnel receive path") Reported-by: syzbot Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240125170557.2663942-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv6/ip6_tunnel.c | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 46c19bd48990..9bbabf750a21 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -796,8 +796,8 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, struct sk_buff *skb), bool log_ecn_err) { - const struct ipv6hdr *ipv6h = ipv6_hdr(skb); - int err; + const struct ipv6hdr *ipv6h; + int nh, err; if ((!(tpi->flags & TUNNEL_CSUM) && (tunnel->parms.i_flags & TUNNEL_CSUM)) || @@ -829,7 +829,6 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, goto drop; } - ipv6h = ipv6_hdr(skb); skb->protocol = eth_type_trans(skb, tunnel->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } else { @@ -837,7 +836,23 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, skb_reset_mac_header(skb); } + /* Save offset of outer header relative to skb->head, + * because we are going to reset the network header to the inner header + * and might change skb->head. + */ + nh = skb_network_header(skb) - skb->head; + skb_reset_network_header(skb); + + if (!pskb_inet_may_pull(skb)) { + DEV_STATS_INC(tunnel->dev, rx_length_errors); + DEV_STATS_INC(tunnel->dev, rx_errors); + goto drop; + } + + /* Get the outer header. */ + ipv6h = (struct ipv6hdr *)(skb->head + nh); + memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); __skb_tunnel_rx(skb, tunnel->dev, tunnel->net); -- cgit v1.2.3 From 60365049ccbacd101654a66ddcb299abfabd4fc5 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Fri, 26 Jan 2024 09:32:20 +0100 Subject: ipv6: Ensure natural alignment of const ipv6 loopback and router addresses On a parisc64 kernel I sometimes notice this kernel warning: Kernel unaligned access to 0x40ff8814 at ndisc_send_skb+0xc0/0x4d8 The address 0x40ff8814 points to the in6addr_linklocal_allrouters variable and the warning simply means that some ipv6 function tries to read a 64-bit word directly from the not-64-bit aligned in6addr_linklocal_allrouters variable. Unaligned accesses are non-critical as the architecture or exception handlers usually will fix it up at runtime. Nevertheless it may trigger a performance penality for some architectures. For details read the "unaligned-memory-access" kernel documentation. The patch below ensures that the ipv6 loopback and router addresses will always be naturally aligned. This prevents the unaligned accesses for all architectures. Signed-off-by: Helge Deller Fixes: 034dfc5df99eb ("ipv6: export in6addr_loopback to modules") Acked-by: Paolo Abeni Link: https://lore.kernel.org/r/ZbNuFM1bFqoH-UoY@p100 Signed-off-by: Paolo Abeni --- net/ipv6/addrconf_core.c | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 507a8353a6bd..c008d21925d7 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -220,19 +220,26 @@ const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { EXPORT_SYMBOL_GPL(ipv6_stub); /* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */ -const struct in6_addr in6addr_loopback = IN6ADDR_LOOPBACK_INIT; +const struct in6_addr in6addr_loopback __aligned(BITS_PER_LONG/8) + = IN6ADDR_LOOPBACK_INIT; EXPORT_SYMBOL(in6addr_loopback); -const struct in6_addr in6addr_any = IN6ADDR_ANY_INIT; +const struct in6_addr in6addr_any __aligned(BITS_PER_LONG/8) + = IN6ADDR_ANY_INIT; EXPORT_SYMBOL(in6addr_any); -const struct in6_addr in6addr_linklocal_allnodes = IN6ADDR_LINKLOCAL_ALLNODES_INIT; +const struct in6_addr in6addr_linklocal_allnodes __aligned(BITS_PER_LONG/8) + = IN6ADDR_LINKLOCAL_ALLNODES_INIT; EXPORT_SYMBOL(in6addr_linklocal_allnodes); -const struct in6_addr in6addr_linklocal_allrouters = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT; +const struct in6_addr in6addr_linklocal_allrouters __aligned(BITS_PER_LONG/8) + = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_linklocal_allrouters); -const struct in6_addr in6addr_interfacelocal_allnodes = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT; +const struct in6_addr in6addr_interfacelocal_allnodes __aligned(BITS_PER_LONG/8) + = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT; EXPORT_SYMBOL(in6addr_interfacelocal_allnodes); -const struct in6_addr in6addr_interfacelocal_allrouters = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT; +const struct in6_addr in6addr_interfacelocal_allrouters __aligned(BITS_PER_LONG/8) + = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_interfacelocal_allrouters); -const struct in6_addr in6addr_sitelocal_allrouters = IN6ADDR_SITELOCAL_ALLROUTERS_INIT; +const struct in6_addr in6addr_sitelocal_allrouters __aligned(BITS_PER_LONG/8) + = IN6ADDR_SITELOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_sitelocal_allrouters); static void snmp6_free_dev(struct inet6_dev *idev) -- cgit v1.2.3 From 92ab08eb63bbf54caebb425ed8908758c98ae8f2 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 8 Feb 2024 08:42:40 -0800 Subject: net: fill in MODULE_DESCRIPTION()s for ipv6 modules W=1 builds now warn if module is built without a MODULE_DESCRIPTION(). Add descriptions to the IPv6 modules. Signed-off-by: Breno Leitao Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240208164244.3818498-6-leitao@debian.org Signed-off-by: Jakub Kicinski --- net/ipv6/ah6.c | 1 + net/ipv6/esp6.c | 1 + net/ipv6/ip6_udp_tunnel.c | 1 + net/ipv6/mip6.c | 1 + net/ipv6/sit.c | 1 + net/ipv6/tunnel6.c | 1 + net/ipv6/xfrm6_tunnel.c | 1 + 7 files changed, 7 insertions(+) (limited to 'net/ipv6') diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 2016e90e6e1d..eb474f0987ae 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -800,5 +800,6 @@ static void __exit ah6_fini(void) module_init(ah6_init); module_exit(ah6_fini); +MODULE_DESCRIPTION("IPv6 AH transformation helpers"); MODULE_LICENSE("GPL"); MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_AH); diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 2cc1a45742d8..6e6efe026cdc 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -1301,5 +1301,6 @@ static void __exit esp6_fini(void) module_init(esp6_init); module_exit(esp6_fini); +MODULE_DESCRIPTION("IPv6 ESP transformation helpers"); MODULE_LICENSE("GPL"); MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_ESP); diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c index a7bf0327b380..c99053189ea8 100644 --- a/net/ipv6/ip6_udp_tunnel.c +++ b/net/ipv6/ip6_udp_tunnel.c @@ -182,4 +182,5 @@ struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb, } EXPORT_SYMBOL_GPL(udp_tunnel6_dst_lookup); +MODULE_DESCRIPTION("IPv6 Foo over UDP tunnel driver"); MODULE_LICENSE("GPL"); diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index 83d2a8be263f..6a16a5bd0d91 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -405,6 +405,7 @@ static void __exit mip6_fini(void) module_init(mip6_init); module_exit(mip6_fini); +MODULE_DESCRIPTION("IPv6 Mobility driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_DSTOPTS); MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_ROUTING); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index cc24cefdb85c..5e9f625b76e3 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1956,6 +1956,7 @@ xfrm_tunnel_failed: module_init(sit_init); module_exit(sit_cleanup); +MODULE_DESCRIPTION("IPv6-in-IPv4 tunnel SIT driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("sit"); MODULE_ALIAS_NETDEV("sit0"); diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c index 00e8d8b1c9a7..dc4ea9b11794 100644 --- a/net/ipv6/tunnel6.c +++ b/net/ipv6/tunnel6.c @@ -302,4 +302,5 @@ static void __exit tunnel6_fini(void) module_init(tunnel6_init); module_exit(tunnel6_fini); +MODULE_DESCRIPTION("IP-in-IPv6 tunnel driver"); MODULE_LICENSE("GPL"); diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 1323f2f6928e..f6cb94f82cc3 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -401,5 +401,6 @@ static void __exit xfrm6_tunnel_fini(void) module_init(xfrm6_tunnel_init); module_exit(xfrm6_tunnel_fini); +MODULE_DESCRIPTION("IPv6 XFRM tunnel driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_IPV6); -- cgit v1.2.3 From 488b6d91b07112eaaaa4454332c1480894d4e06e Mon Sep 17 00:00:00 2001 From: Vadim Fedorenko Date: Tue, 13 Feb 2024 03:04:28 -0800 Subject: net-timestamp: make sk_tskey more predictable in error path When SOF_TIMESTAMPING_OPT_ID is used to ambiguate timestamped datagrams, the sk_tskey can become unpredictable in case of any error happened during sendmsg(). Move increment later in the code and make decrement of sk_tskey in error path. This solution is still racy in case of multiple threads doing snedmsg() over the very same socket in parallel, but still makes error path much more predictable. Fixes: 09c2d251b707 ("net-timestamp: add key to disambiguate concurrent datagrams") Reported-by: Andy Lutomirski Signed-off-by: Vadim Fedorenko Reviewed-by: Willem de Bruijn Link: https://lore.kernel.org/r/20240213110428.1681540-1-vadfed@meta.com Signed-off-by: Paolo Abeni --- net/ipv4/ip_output.c | 13 ++++++++----- net/ipv6/ip6_output.c | 13 ++++++++----- 2 files changed, 16 insertions(+), 10 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 41537d18eecf..67d846622365 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -972,8 +972,8 @@ static int __ip_append_data(struct sock *sk, unsigned int maxfraglen, fragheaderlen, maxnonfragsize; int csummode = CHECKSUM_NONE; struct rtable *rt = (struct rtable *)cork->dst; + bool paged, hold_tskey, extra_uref = false; unsigned int wmem_alloc_delta = 0; - bool paged, extra_uref = false; u32 tskey = 0; skb = skb_peek_tail(queue); @@ -982,10 +982,6 @@ static int __ip_append_data(struct sock *sk, mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize; paged = !!cork->gso_size; - if (cork->tx_flags & SKBTX_ANY_TSTAMP && - READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) - tskey = atomic_inc_return(&sk->sk_tskey) - 1; - hh_len = LL_RESERVED_SPACE(rt->dst.dev); fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); @@ -1052,6 +1048,11 @@ static int __ip_append_data(struct sock *sk, cork->length += length; + hold_tskey = cork->tx_flags & SKBTX_ANY_TSTAMP && + READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID; + if (hold_tskey) + tskey = atomic_inc_return(&sk->sk_tskey) - 1; + /* So, what's going on in the loop below? * * We use calculated fragment length to generate chained skb, @@ -1274,6 +1275,8 @@ error: cork->length -= length; IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS); refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); + if (hold_tskey) + atomic_dec(&sk->sk_tskey); return err; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index a722a43dd668..31b86fe661aa 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1424,11 +1424,11 @@ static int __ip6_append_data(struct sock *sk, bool zc = false; u32 tskey = 0; struct rt6_info *rt = (struct rt6_info *)cork->dst; + bool paged, hold_tskey, extra_uref = false; struct ipv6_txoptions *opt = v6_cork->opt; int csummode = CHECKSUM_NONE; unsigned int maxnonfragsize, headersize; unsigned int wmem_alloc_delta = 0; - bool paged, extra_uref = false; skb = skb_peek_tail(queue); if (!skb) { @@ -1440,10 +1440,6 @@ static int __ip6_append_data(struct sock *sk, mtu = cork->gso_size ? IP6_MAX_MTU : cork->fragsize; orig_mtu = mtu; - if (cork->tx_flags & SKBTX_ANY_TSTAMP && - READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) - tskey = atomic_inc_return(&sk->sk_tskey) - 1; - hh_len = LL_RESERVED_SPACE(rt->dst.dev); fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len + @@ -1538,6 +1534,11 @@ emsgsize: flags &= ~MSG_SPLICE_PAGES; } + hold_tskey = cork->tx_flags & SKBTX_ANY_TSTAMP && + READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID; + if (hold_tskey) + tskey = atomic_inc_return(&sk->sk_tskey) - 1; + /* * Let's try using as much space as possible. * Use MTU if total length of the message fits into the MTU. @@ -1794,6 +1795,8 @@ error: cork->length -= length; IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); + if (hold_tskey) + atomic_dec(&sk->sk_tskey); return err; } -- cgit v1.2.3