From d9f92772e8ec388d070752ee8f187ef8fa18621f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 12 May 2018 02:49:30 -0700 Subject: xfrm6: avoid potential infinite loop in _decode_session6() syzbot found a way to trigger an infinitie loop by overflowing @offset variable that has been forced to use u16 for some very obscure reason in the past. We probably want to look at NEXTHDR_FRAGMENT handling which looks wrong, in a separate patch. In net-next, we shall try to use skb_header_pointer() instead of pskb_may_pull(). watchdog: BUG: soft lockup - CPU#1 stuck for 134s! [syz-executor738:4553] Modules linked in: irq event stamp: 13885653 hardirqs last enabled at (13885652): [] restore_regs_and_return_to_kernel+0x0/0x2b hardirqs last disabled at (13885653): [] interrupt_entry+0xb5/0xf0 arch/x86/entry/entry_64.S:625 softirqs last enabled at (13614028): [] tun_napi_alloc_frags drivers/net/tun.c:1478 [inline] softirqs last enabled at (13614028): [] tun_get_user+0x1dd9/0x4290 drivers/net/tun.c:1825 softirqs last disabled at (13614032): [] tun_get_user+0x313f/0x4290 drivers/net/tun.c:1942 CPU: 1 PID: 4553 Comm: syz-executor738 Not tainted 4.17.0-rc3+ #40 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:check_kcov_mode kernel/kcov.c:67 [inline] RIP: 0010:__sanitizer_cov_trace_pc+0x20/0x50 kernel/kcov.c:101 RSP: 0018:ffff8801d8cfe250 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffff8801d88a8080 RBX: ffff8801d7389e40 RCX: 0000000000000006 RDX: 0000000000000000 RSI: ffffffff868da4ad RDI: ffff8801c8a53277 RBP: ffff8801d8cfe250 R08: ffff8801d88a8080 R09: ffff8801d8cfe3e8 R10: ffffed003b19fc87 R11: ffff8801d8cfe43f R12: ffff8801c8a5327f R13: 0000000000000000 R14: ffff8801c8a4e5fe R15: ffff8801d8cfe3e8 FS: 0000000000d88940(0000) GS:ffff8801daf00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffff600400 CR3: 00000001acab3000 CR4: 00000000001406e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: _decode_session6+0xc1d/0x14f0 net/ipv6/xfrm6_policy.c:150 __xfrm_decode_session+0x71/0x140 net/xfrm/xfrm_policy.c:2368 xfrm_decode_session_reverse include/net/xfrm.h:1213 [inline] icmpv6_route_lookup+0x395/0x6e0 net/ipv6/icmp.c:372 icmp6_send+0x1982/0x2da0 net/ipv6/icmp.c:551 icmpv6_send+0x17a/0x300 net/ipv6/ip6_icmp.c:43 ip6_input_finish+0x14e1/0x1a30 net/ipv6/ip6_input.c:305 NF_HOOK include/linux/netfilter.h:288 [inline] ip6_input+0xe1/0x5e0 net/ipv6/ip6_input.c:327 dst_input include/net/dst.h:450 [inline] ip6_rcv_finish+0x29c/0xa10 net/ipv6/ip6_input.c:71 NF_HOOK include/linux/netfilter.h:288 [inline] ipv6_rcv+0xeb8/0x2040 net/ipv6/ip6_input.c:208 __netif_receive_skb_core+0x2468/0x3650 net/core/dev.c:4646 __netif_receive_skb+0x2c/0x1e0 net/core/dev.c:4711 netif_receive_skb_internal+0x126/0x7b0 net/core/dev.c:4785 napi_frags_finish net/core/dev.c:5226 [inline] napi_gro_frags+0x631/0xc40 net/core/dev.c:5299 tun_get_user+0x3168/0x4290 drivers/net/tun.c:1951 tun_chr_write_iter+0xb9/0x154 drivers/net/tun.c:1996 call_write_iter include/linux/fs.h:1784 [inline] do_iter_readv_writev+0x859/0xa50 fs/read_write.c:680 do_iter_write+0x185/0x5f0 fs/read_write.c:959 vfs_writev+0x1c7/0x330 fs/read_write.c:1004 do_writev+0x112/0x2f0 fs/read_write.c:1039 __do_sys_writev fs/read_write.c:1112 [inline] __se_sys_writev fs/read_write.c:1109 [inline] __x64_sys_writev+0x75/0xb0 fs/read_write.c:1109 do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x49/0xbe Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Cc: Steffen Klassert Cc: Nicolas Dichtel Reported-by: syzbot+0053c8...@syzkaller.appspotmail.com Signed-off-by: Steffen Klassert --- net/ipv6/xfrm6_policy.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 416fe67271a9..86dba282a147 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -126,7 +126,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) struct flowi6 *fl6 = &fl->u.ip6; int onlyproto = 0; const struct ipv6hdr *hdr = ipv6_hdr(skb); - u16 offset = sizeof(*hdr); + u32 offset = sizeof(*hdr); struct ipv6_opt_hdr *exthdr; const unsigned char *nh = skb_network_header(skb); u16 nhoff = IP6CB(skb)->nhoff; -- cgit v1.2.3-58-ga151 From b71534583f22d08c3e3563bf5100aeb5f5c9fbe5 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Wed, 16 May 2018 22:10:37 +0900 Subject: netfilter: nf_tables: fix NULL pointer dereference on nft_ct_helper_obj_dump() In the nft_ct_helper_obj_dump(), always priv->helper4 is dereferenced. But if family is ipv6, priv->helper6 should be dereferenced. Steps to reproduces: #test.nft table ip6 filter { ct helper ftp { type "ftp" protocol tcp } chain input { type filter hook input priority 4; ct helper set "ftp" } } %nft -f test.nft %nft list ruleset we can see the below messages: [ 916.286233] kasan: GPF could be caused by NULL-ptr deref or user memory access [ 916.294777] general protection fault: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI [ 916.302613] Modules linked in: nft_objref nf_conntrack_sip nf_conntrack_snmp nf_conntrack_broadcast nf_conntrack_ftp nft_ct nf_conntrack nf_tables nfnetlink [last unloaded: nfnetlink] [ 916.318758] CPU: 1 PID: 2093 Comm: nft Not tainted 4.17.0-rc4+ #181 [ 916.326772] Hardware name: To be filled by O.E.M. To be filled by O.E.M./Aptio CRB, BIOS 5.6.5 07/08/2015 [ 916.338773] RIP: 0010:strlen+0x1a/0x90 [ 916.342781] RSP: 0018:ffff88010ff0f2f8 EFLAGS: 00010292 [ 916.346773] RAX: dffffc0000000000 RBX: ffff880119b26ee8 RCX: ffff88010c150038 [ 916.354777] RDX: 0000000000000002 RSI: ffff880119b26ee8 RDI: 0000000000000010 [ 916.362773] RBP: 0000000000000010 R08: 0000000000007e88 R09: ffff88010c15003c [ 916.370773] R10: ffff88010c150037 R11: ffffed002182a007 R12: ffff88010ff04040 [ 916.378779] R13: 0000000000000010 R14: ffff880119b26f30 R15: ffff88010ff04110 [ 916.387265] FS: 00007f57a1997700(0000) GS:ffff88011b800000(0000) knlGS:0000000000000000 [ 916.394785] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 916.402778] CR2: 00007f57a0ac80f0 CR3: 000000010ff02000 CR4: 00000000001006e0 [ 916.410772] Call Trace: [ 916.414787] nft_ct_helper_obj_dump+0x94/0x200 [nft_ct] [ 916.418779] ? nft_ct_set_eval+0x560/0x560 [nft_ct] [ 916.426771] ? memset+0x1f/0x40 [ 916.426771] ? __nla_reserve+0x92/0xb0 [ 916.434774] ? memcpy+0x34/0x50 [ 916.434774] nf_tables_fill_obj_info+0x484/0x860 [nf_tables] [ 916.442773] ? __nft_release_basechain+0x600/0x600 [nf_tables] [ 916.450779] ? lock_acquire+0x193/0x380 [ 916.454771] ? lock_acquire+0x193/0x380 [ 916.458789] ? nf_tables_dump_obj+0x148/0xcb0 [nf_tables] [ 916.462777] nf_tables_dump_obj+0x5f0/0xcb0 [nf_tables] [ 916.470769] ? __alloc_skb+0x30b/0x500 [ 916.474779] netlink_dump+0x752/0xb50 [ 916.478775] __netlink_dump_start+0x4d3/0x750 [ 916.482784] nf_tables_getobj+0x27a/0x930 [nf_tables] [ 916.490774] ? nft_obj_notify+0x100/0x100 [nf_tables] [ 916.494772] ? nf_tables_getobj+0x930/0x930 [nf_tables] [ 916.502579] ? nf_tables_dump_flowtable_done+0x70/0x70 [nf_tables] [ 916.506774] ? nft_obj_notify+0x100/0x100 [nf_tables] [ 916.514808] nfnetlink_rcv_msg+0x8ab/0xa86 [nfnetlink] [ 916.518771] ? nfnetlink_rcv_msg+0x550/0xa86 [nfnetlink] [ 916.526782] netlink_rcv_skb+0x23e/0x360 [ 916.530773] ? nfnetlink_bind+0x200/0x200 [nfnetlink] [ 916.534778] ? debug_check_no_locks_freed+0x280/0x280 [ 916.542770] ? netlink_ack+0x870/0x870 [ 916.546786] ? ns_capable_common+0xf4/0x130 [ 916.550765] nfnetlink_rcv+0x172/0x16c0 [nfnetlink] [ 916.554771] ? sched_clock_local+0xe2/0x150 [ 916.558774] ? sched_clock_cpu+0x144/0x180 [ 916.566575] ? lock_acquire+0x380/0x380 [ 916.570775] ? sched_clock_local+0xe2/0x150 [ 916.574765] ? nfnetlink_net_init+0x130/0x130 [nfnetlink] [ 916.578763] ? sched_clock_cpu+0x144/0x180 [ 916.582770] ? lock_acquire+0x193/0x380 [ 916.590771] ? lock_acquire+0x193/0x380 [ 916.594766] ? lock_acquire+0x380/0x380 [ 916.598760] ? netlink_deliver_tap+0x262/0xa60 [ 916.602766] ? lock_acquire+0x193/0x380 [ 916.606766] netlink_unicast+0x3ef/0x5a0 [ 916.610771] ? netlink_attachskb+0x630/0x630 [ 916.614763] netlink_sendmsg+0x72a/0xb00 [ 916.618769] ? netlink_unicast+0x5a0/0x5a0 [ 916.626766] ? _copy_from_user+0x92/0xc0 [ 916.630773] __sys_sendto+0x202/0x300 [ 916.634772] ? __ia32_sys_getpeername+0xb0/0xb0 [ 916.638759] ? lock_acquire+0x380/0x380 [ 916.642769] ? lock_acquire+0x193/0x380 [ 916.646761] ? finish_task_switch+0xf4/0x560 [ 916.650763] ? __schedule+0x582/0x19a0 [ 916.655301] ? __sched_text_start+0x8/0x8 [ 916.655301] ? up_read+0x1c/0x110 [ 916.655301] ? __do_page_fault+0x48b/0xaa0 [ 916.655301] ? entry_SYSCALL_64_after_hwframe+0x59/0xbe [ 916.655301] __x64_sys_sendto+0xdd/0x1b0 [ 916.655301] do_syscall_64+0x96/0x3d0 [ 916.655301] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 916.655301] RIP: 0033:0x7f57a0ff5e03 [ 916.655301] RSP: 002b:00007fff6367e0a8 EFLAGS: 00000246 ORIG_RAX: 000000000000002c [ 916.655301] RAX: ffffffffffffffda RBX: 00007fff6367f1e0 RCX: 00007f57a0ff5e03 [ 916.655301] RDX: 0000000000000020 RSI: 00007fff6367e110 RDI: 0000000000000003 [ 916.655301] RBP: 00007fff6367e100 R08: 00007f57a0ce9160 R09: 000000000000000c [ 916.655301] R10: 0000000000000000 R11: 0000000000000246 R12: 00007fff6367e110 [ 916.655301] R13: 0000000000000020 R14: 00007f57a153c610 R15: 0000562417258de0 [ 916.655301] Code: ff ff ff 0f 1f 40 00 66 2e 0f 1f 84 00 00 00 00 00 55 48 89 fa 53 48 c1 ea 03 48 b8 00 00 00 00 00 fc ff df 48 89 fd 48 83 ec 08 <0f> b6 04 02 48 89 fa 83 e2 07 38 d0 7f [ 916.655301] RIP: strlen+0x1a/0x90 RSP: ffff88010ff0f2f8 [ 916.771929] ---[ end trace 1065e048e72479fe ]--- [ 916.777204] Kernel panic - not syncing: Fatal exception [ 916.778158] Kernel Offset: 0x14000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) Signed-off-by: Taehee Yoo Acked-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_ct.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) (limited to 'net') diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index ea737fd789e8..5c0de704bad5 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -880,22 +880,26 @@ static int nft_ct_helper_obj_dump(struct sk_buff *skb, struct nft_object *obj, bool reset) { const struct nft_ct_helper_obj *priv = nft_obj_data(obj); - const struct nf_conntrack_helper *helper = priv->helper4; + const struct nf_conntrack_helper *helper; u16 family; + if (priv->helper4 && priv->helper6) { + family = NFPROTO_INET; + helper = priv->helper4; + } else if (priv->helper6) { + family = NFPROTO_IPV6; + helper = priv->helper6; + } else { + family = NFPROTO_IPV4; + helper = priv->helper4; + } + if (nla_put_string(skb, NFTA_CT_HELPER_NAME, helper->name)) return -1; if (nla_put_u8(skb, NFTA_CT_HELPER_L4PROTO, priv->l4proto)) return -1; - if (priv->helper4 && priv->helper6) - family = NFPROTO_INET; - else if (priv->helper6) - family = NFPROTO_IPV6; - else - family = NFPROTO_IPV4; - if (nla_put_be16(skb, NFTA_CT_HELPER_L3PROTO, htons(family))) return -1; -- cgit v1.2.3-58-ga151 From 94c752f99954797da583a84c4907ff19e92550a4 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 27 Apr 2018 10:45:31 +0200 Subject: netfilter: ebtables: handle string from userspace with care strlcpy() can't be safely used on a user-space provided string, as it can try to read beyond the buffer's end, if the latter is not NULL terminated. Leveraging the above, syzbot has been able to trigger the following splat: BUG: KASAN: stack-out-of-bounds in strlcpy include/linux/string.h:300 [inline] BUG: KASAN: stack-out-of-bounds in compat_mtw_from_user net/bridge/netfilter/ebtables.c:1957 [inline] BUG: KASAN: stack-out-of-bounds in ebt_size_mwt net/bridge/netfilter/ebtables.c:2059 [inline] BUG: KASAN: stack-out-of-bounds in size_entry_mwt net/bridge/netfilter/ebtables.c:2155 [inline] BUG: KASAN: stack-out-of-bounds in compat_copy_entries+0x96c/0x14a0 net/bridge/netfilter/ebtables.c:2194 Write of size 33 at addr ffff8801b0abf888 by task syz-executor0/4504 CPU: 0 PID: 4504 Comm: syz-executor0 Not tainted 4.17.0-rc2+ #40 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+0x1b9/0x294 lib/dump_stack.c:113 print_address_description+0x6c/0x20b mm/kasan/report.c:256 kasan_report_error mm/kasan/report.c:354 [inline] kasan_report.cold.7+0x242/0x2fe mm/kasan/report.c:412 check_memory_region_inline mm/kasan/kasan.c:260 [inline] check_memory_region+0x13e/0x1b0 mm/kasan/kasan.c:267 memcpy+0x37/0x50 mm/kasan/kasan.c:303 strlcpy include/linux/string.h:300 [inline] compat_mtw_from_user net/bridge/netfilter/ebtables.c:1957 [inline] ebt_size_mwt net/bridge/netfilter/ebtables.c:2059 [inline] size_entry_mwt net/bridge/netfilter/ebtables.c:2155 [inline] compat_copy_entries+0x96c/0x14a0 net/bridge/netfilter/ebtables.c:2194 compat_do_replace+0x483/0x900 net/bridge/netfilter/ebtables.c:2285 compat_do_ebt_set_ctl+0x2ac/0x324 net/bridge/netfilter/ebtables.c:2367 compat_nf_sockopt net/netfilter/nf_sockopt.c:144 [inline] compat_nf_setsockopt+0x9b/0x140 net/netfilter/nf_sockopt.c:156 compat_ip_setsockopt+0xff/0x140 net/ipv4/ip_sockglue.c:1279 inet_csk_compat_setsockopt+0x97/0x120 net/ipv4/inet_connection_sock.c:1041 compat_tcp_setsockopt+0x49/0x80 net/ipv4/tcp.c:2901 compat_sock_common_setsockopt+0xb4/0x150 net/core/sock.c:3050 __compat_sys_setsockopt+0x1ab/0x7c0 net/compat.c:403 __do_compat_sys_setsockopt net/compat.c:416 [inline] __se_compat_sys_setsockopt net/compat.c:413 [inline] __ia32_compat_sys_setsockopt+0xbd/0x150 net/compat.c:413 do_syscall_32_irqs_on arch/x86/entry/common.c:323 [inline] do_fast_syscall_32+0x345/0xf9b arch/x86/entry/common.c:394 entry_SYSENTER_compat+0x70/0x7f arch/x86/entry/entry_64_compat.S:139 RIP: 0023:0xf7fb3cb9 RSP: 002b:00000000fff0c26c EFLAGS: 00000282 ORIG_RAX: 000000000000016e RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000000000 RDX: 0000000000000080 RSI: 0000000020000300 RDI: 00000000000005f4 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 The buggy address belongs to the page: page:ffffea0006c2afc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0 flags: 0x2fffc0000000000() raw: 02fffc0000000000 0000000000000000 0000000000000000 00000000ffffffff raw: 0000000000000000 ffffea0006c20101 0000000000000000 0000000000000000 page dumped because: kasan: bad access detected Fix the issue replacing the unsafe function with strscpy() and taking care of possible errors. Fixes: 81e675c227ec ("netfilter: ebtables: add CONFIG_COMPAT support") Reported-and-tested-by: syzbot+4e42a04e0bc33cb6c087@syzkaller.appspotmail.com Signed-off-by: Paolo Abeni Signed-off-by: Pablo Neira Ayuso --- net/bridge/netfilter/ebtables.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 28a4c3490359..6ba639f6c51d 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1954,7 +1954,8 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, int off, pad = 0; unsigned int size_kern, match_size = mwt->match_size; - strlcpy(name, mwt->u.name, sizeof(name)); + if (strscpy(name, mwt->u.name, sizeof(name)) < 0) + return -EINVAL; if (state->buf_kern_start) dst = state->buf_kern_start + state->buf_kern_offset; -- cgit v1.2.3-58-ga151 From 97a0549b15a0b466c47f6a0143a490a082c64b4e Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Thu, 17 May 2018 22:49:49 +0900 Subject: netfilter: nft_meta: fix wrong value dereference in nft_meta_set_eval In the nft_meta_set_eval, nftrace value is dereferenced as u32 from sreg. But correct type is u8. so that sometimes incorrect value is dereferenced. Steps to reproduce: %nft add table ip filter %nft add chain ip filter input { type filter hook input priority 4\; } %nft add rule ip filter input nftrace set 0 %nft monitor Sometimes, we can see trace messages. trace id 16767227 ip filter input packet: iif "enp2s0" ether saddr xx:xx:xx:xx:xx:xx ether daddr xx:xx:xx:xx:xx:xx ip saddr 192.168.0.1 ip daddr 255.255.255.255 ip dscp cs0 ip ecn not-ect ip trace id 16767227 ip filter input rule nftrace set 0 (verdict continue) trace id 16767227 ip filter input verdict continue trace id 16767227 ip filter input Signed-off-by: Taehee Yoo Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_meta.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'net') diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 8fb91940e2e7..204af9899482 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -234,7 +234,7 @@ void nft_meta_set_eval(const struct nft_expr *expr, struct sk_buff *skb = pkt->skb; u32 *sreg = ®s->data[meta->sreg]; u32 value = *sreg; - u8 pkt_type; + u8 value8; switch (meta->key) { case NFT_META_MARK: @@ -244,15 +244,17 @@ void nft_meta_set_eval(const struct nft_expr *expr, skb->priority = value; break; case NFT_META_PKTTYPE: - pkt_type = nft_reg_load8(sreg); + value8 = nft_reg_load8(sreg); - if (skb->pkt_type != pkt_type && - skb_pkt_type_ok(pkt_type) && + if (skb->pkt_type != value8 && + skb_pkt_type_ok(value8) && skb_pkt_type_ok(skb->pkt_type)) - skb->pkt_type = pkt_type; + skb->pkt_type = value8; break; case NFT_META_NFTRACE: - skb->nf_trace = !!value; + value8 = nft_reg_load8(sreg); + + skb->nf_trace = !!value8; break; default: WARN_ON(1); -- cgit v1.2.3-58-ga151 From 3e0f64b7dd3149f75e8652ff1df56cffeedc8fc1 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 16 May 2018 22:58:33 +0200 Subject: netfilter: nft_limit: fix packet ratelimiting Credit calculations for the packet ratelimiting are not correct, as per the applied ratelimit of 25/second and burst 8, a total of 33 packets should have been accepted. This is true in iptables(33) but not in nftables (~65). For packet ratelimiting, use: div_u64(limit->nsecs, limit->rate) * limit->burst; to calculate credit, just like in iptables' xt_limit does. Moreover, use default burst in iptables, users are expecting similar behaviour. Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_limit.c | 38 ++++++++++++++++++++++++-------------- 1 file changed, 24 insertions(+), 14 deletions(-) (limited to 'net') diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index a9fc298ef4c3..72f13a1144dd 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -51,10 +51,13 @@ static inline bool nft_limit_eval(struct nft_limit *limit, u64 cost) return !limit->invert; } +/* Use same default as in iptables. */ +#define NFT_LIMIT_PKT_BURST_DEFAULT 5 + static int nft_limit_init(struct nft_limit *limit, - const struct nlattr * const tb[]) + const struct nlattr * const tb[], bool pkts) { - u64 unit; + u64 unit, tokens; if (tb[NFTA_LIMIT_RATE] == NULL || tb[NFTA_LIMIT_UNIT] == NULL) @@ -68,18 +71,25 @@ static int nft_limit_init(struct nft_limit *limit, if (tb[NFTA_LIMIT_BURST]) limit->burst = ntohl(nla_get_be32(tb[NFTA_LIMIT_BURST])); - else - limit->burst = 0; + + if (pkts && limit->burst == 0) + limit->burst = NFT_LIMIT_PKT_BURST_DEFAULT; if (limit->rate + limit->burst < limit->rate) return -EOVERFLOW; - /* The token bucket size limits the number of tokens can be - * accumulated. tokens_max specifies the bucket size. - * tokens_max = unit * (rate + burst) / rate. - */ - limit->tokens = div_u64(limit->nsecs * (limit->rate + limit->burst), - limit->rate); + if (pkts) { + tokens = div_u64(limit->nsecs, limit->rate) * limit->burst; + } else { + /* The token bucket size limits the number of tokens can be + * accumulated. tokens_max specifies the bucket size. + * tokens_max = unit * (rate + burst) / rate. + */ + tokens = div_u64(limit->nsecs * (limit->rate + limit->burst), + limit->rate); + } + + limit->tokens = tokens; limit->tokens_max = limit->tokens; if (tb[NFTA_LIMIT_FLAGS]) { @@ -144,7 +154,7 @@ static int nft_limit_pkts_init(const struct nft_ctx *ctx, struct nft_limit_pkts *priv = nft_expr_priv(expr); int err; - err = nft_limit_init(&priv->limit, tb); + err = nft_limit_init(&priv->limit, tb, true); if (err < 0) return err; @@ -185,7 +195,7 @@ static int nft_limit_bytes_init(const struct nft_ctx *ctx, { struct nft_limit *priv = nft_expr_priv(expr); - return nft_limit_init(priv, tb); + return nft_limit_init(priv, tb, false); } static int nft_limit_bytes_dump(struct sk_buff *skb, @@ -246,7 +256,7 @@ static int nft_limit_obj_pkts_init(const struct nft_ctx *ctx, struct nft_limit_pkts *priv = nft_obj_data(obj); int err; - err = nft_limit_init(&priv->limit, tb); + err = nft_limit_init(&priv->limit, tb, true); if (err < 0) return err; @@ -289,7 +299,7 @@ static int nft_limit_obj_bytes_init(const struct nft_ctx *ctx, { struct nft_limit *priv = nft_obj_data(obj); - return nft_limit_init(priv, tb); + return nft_limit_init(priv, tb, false); } static int nft_limit_obj_bytes_dump(struct sk_buff *skb, -- cgit v1.2.3-58-ga151 From 52f96757905bbf0edef47f3ee6c7c784e7f8ff8a Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sat, 19 May 2018 18:22:35 +0300 Subject: ipvs: fix buffer overflow with sync daemon and service syzkaller reports for buffer overflow for interface name when starting sync daemons [1] What we do is that we copy user structure into larger stack buffer but later we search NUL past the stack buffer. The same happens for sched_name when adding/editing virtual server. We are restricted by IP_VS_SCHEDNAME_MAXLEN and IP_VS_IFNAME_MAXLEN being used as size in include/uapi/linux/ip_vs.h, so they include the space for NUL. As using strlcpy is wrong for unsafe source, replace it with strscpy and add checks to return EINVAL if source string is not NUL-terminated. The incomplete strlcpy fix comes from 2.6.13. For the netlink interface reduce the len parameter for IPVS_DAEMON_ATTR_MCAST_IFN and IPVS_SVC_ATTR_SCHED_NAME, so that we get proper EINVAL. [1] kernel BUG at lib/string.c:1052! invalid opcode: 0000 [#1] SMP KASAN Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 1 PID: 373 Comm: syz-executor936 Not tainted 4.17.0-rc4+ #45 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:fortify_panic+0x13/0x20 lib/string.c:1051 RSP: 0018:ffff8801c976f800 EFLAGS: 00010282 RAX: 0000000000000022 RBX: 0000000000000040 RCX: 0000000000000000 RDX: 0000000000000022 RSI: ffffffff8160f6f1 RDI: ffffed00392edef6 RBP: ffff8801c976f800 R08: ffff8801cf4c62c0 R09: ffffed003b5e4fb0 R10: ffffed003b5e4fb0 R11: ffff8801daf27d87 R12: ffff8801c976fa20 R13: ffff8801c976fae4 R14: ffff8801c976fae0 R15: 000000000000048b FS: 00007fd99f75e700(0000) GS:ffff8801daf00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000200001c0 CR3: 00000001d6843000 CR4: 00000000001406e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: strlen include/linux/string.h:270 [inline] strlcpy include/linux/string.h:293 [inline] do_ip_vs_set_ctl+0x31c/0x1d00 net/netfilter/ipvs/ip_vs_ctl.c:2388 nf_sockopt net/netfilter/nf_sockopt.c:106 [inline] nf_setsockopt+0x7d/0xd0 net/netfilter/nf_sockopt.c:115 ip_setsockopt+0xd8/0xf0 net/ipv4/ip_sockglue.c:1253 udp_setsockopt+0x62/0xa0 net/ipv4/udp.c:2487 ipv6_setsockopt+0x149/0x170 net/ipv6/ipv6_sockglue.c:917 tcp_setsockopt+0x93/0xe0 net/ipv4/tcp.c:3057 sock_common_setsockopt+0x9a/0xe0 net/core/sock.c:3046 __sys_setsockopt+0x1bd/0x390 net/socket.c:1903 __do_sys_setsockopt net/socket.c:1914 [inline] __se_sys_setsockopt net/socket.c:1911 [inline] __x64_sys_setsockopt+0xbe/0x150 net/socket.c:1911 do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x447369 RSP: 002b:00007fd99f75dda8 EFLAGS: 00000246 ORIG_RAX: 0000000000000036 RAX: ffffffffffffffda RBX: 00000000006e39e4 RCX: 0000000000447369 RDX: 000000000000048b RSI: 0000000000000000 RDI: 0000000000000003 RBP: 0000000000000000 R08: 0000000000000018 R09: 0000000000000000 R10: 00000000200001c0 R11: 0000000000000246 R12: 00000000006e39e0 R13: 75a1ff93f0896195 R14: 6f745f3168746576 R15: 0000000000000001 Code: 08 5b 41 5c 41 5d 41 5e 41 5f 5d c3 0f 0b 48 89 df e8 d2 8f 48 fa eb de 55 48 89 fe 48 c7 c7 60 65 64 88 48 89 e5 e8 91 dd f3 f9 <0f> 0b 90 90 90 90 90 90 90 90 90 90 90 55 48 89 e5 41 57 41 56 RIP: fortify_panic+0x13/0x20 lib/string.c:1051 RSP: ffff8801c976f800 Reported-and-tested-by: syzbot+aac887f77319868646df@syzkaller.appspotmail.com Fixes: e4ff67513096 ("ipvs: add sync_maxlen parameter for the sync daemon") Fixes: 4da62fc70d7c ("[IPVS]: Fix for overflows") Signed-off-by: Julian Anastasov Acked-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipvs/ip_vs_ctl.c | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) (limited to 'net') diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index f36098887ad0..3ecca0616d8c 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2381,8 +2381,10 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) struct ipvs_sync_daemon_cfg cfg; memset(&cfg, 0, sizeof(cfg)); - strlcpy(cfg.mcast_ifn, dm->mcast_ifn, - sizeof(cfg.mcast_ifn)); + ret = -EINVAL; + if (strscpy(cfg.mcast_ifn, dm->mcast_ifn, + sizeof(cfg.mcast_ifn)) <= 0) + goto out_dec; cfg.syncid = dm->syncid; ret = start_sync_thread(ipvs, &cfg, dm->state); } else { @@ -2420,12 +2422,19 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) } } + if ((cmd == IP_VS_SO_SET_ADD || cmd == IP_VS_SO_SET_EDIT) && + strnlen(usvc.sched_name, IP_VS_SCHEDNAME_MAXLEN) == + IP_VS_SCHEDNAME_MAXLEN) { + ret = -EINVAL; + goto out_unlock; + } + /* Check for valid protocol: TCP or UDP or SCTP, even for fwmark!=0 */ if (usvc.protocol != IPPROTO_TCP && usvc.protocol != IPPROTO_UDP && usvc.protocol != IPPROTO_SCTP) { - pr_err("set_ctl: invalid protocol: %d %pI4:%d %s\n", + pr_err("set_ctl: invalid protocol: %d %pI4:%d\n", usvc.protocol, &usvc.addr.ip, - ntohs(usvc.port), usvc.sched_name); + ntohs(usvc.port)); ret = -EFAULT; goto out_unlock; } @@ -2847,7 +2856,7 @@ static const struct nla_policy ip_vs_cmd_policy[IPVS_CMD_ATTR_MAX + 1] = { static const struct nla_policy ip_vs_daemon_policy[IPVS_DAEMON_ATTR_MAX + 1] = { [IPVS_DAEMON_ATTR_STATE] = { .type = NLA_U32 }, [IPVS_DAEMON_ATTR_MCAST_IFN] = { .type = NLA_NUL_STRING, - .len = IP_VS_IFNAME_MAXLEN }, + .len = IP_VS_IFNAME_MAXLEN - 1 }, [IPVS_DAEMON_ATTR_SYNC_ID] = { .type = NLA_U32 }, [IPVS_DAEMON_ATTR_SYNC_MAXLEN] = { .type = NLA_U16 }, [IPVS_DAEMON_ATTR_MCAST_GROUP] = { .type = NLA_U32 }, @@ -2865,7 +2874,7 @@ static const struct nla_policy ip_vs_svc_policy[IPVS_SVC_ATTR_MAX + 1] = { [IPVS_SVC_ATTR_PORT] = { .type = NLA_U16 }, [IPVS_SVC_ATTR_FWMARK] = { .type = NLA_U32 }, [IPVS_SVC_ATTR_SCHED_NAME] = { .type = NLA_NUL_STRING, - .len = IP_VS_SCHEDNAME_MAXLEN }, + .len = IP_VS_SCHEDNAME_MAXLEN - 1 }, [IPVS_SVC_ATTR_PE_NAME] = { .type = NLA_NUL_STRING, .len = IP_VS_PENAME_MAXLEN }, [IPVS_SVC_ATTR_FLAGS] = { .type = NLA_BINARY, -- cgit v1.2.3-58-ga151 From 4b83a9049a983b20b1ec2757727c5e39f5847ad2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 21 May 2018 16:35:24 -0700 Subject: netfilter: provide correct argument to nla_strlcpy() Recent patch forgot to remove nla_data(), upsetting syzkaller a bit. BUG: KASAN: slab-out-of-bounds in nla_strlcpy+0x13d/0x150 lib/nlattr.c:314 Read of size 1 at addr ffff8801ad1f4fdd by task syz-executor189/4509 CPU: 1 PID: 4509 Comm: syz-executor189 Not tainted 4.17.0-rc6+ #62 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+0x1b9/0x294 lib/dump_stack.c:113 print_address_description+0x6c/0x20b mm/kasan/report.c:256 kasan_report_error mm/kasan/report.c:354 [inline] kasan_report.cold.7+0x242/0x2fe mm/kasan/report.c:412 __asan_report_load1_noabort+0x14/0x20 mm/kasan/report.c:430 nla_strlcpy+0x13d/0x150 lib/nlattr.c:314 nfnl_acct_new+0x574/0xc50 net/netfilter/nfnetlink_acct.c:118 nfnetlink_rcv_msg+0xdb5/0xff0 net/netfilter/nfnetlink.c:212 netlink_rcv_skb+0x172/0x440 net/netlink/af_netlink.c:2448 nfnetlink_rcv+0x1fe/0x1ba0 net/netfilter/nfnetlink.c:513 netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline] netlink_unicast+0x58b/0x740 net/netlink/af_netlink.c:1336 netlink_sendmsg+0x9f0/0xfa0 net/netlink/af_netlink.c:1901 sock_sendmsg_nosec net/socket.c:629 [inline] sock_sendmsg+0xd5/0x120 net/socket.c:639 sock_write_iter+0x35a/0x5a0 net/socket.c:908 call_write_iter include/linux/fs.h:1784 [inline] new_sync_write fs/read_write.c:474 [inline] __vfs_write+0x64d/0x960 fs/read_write.c:487 vfs_write+0x1f8/0x560 fs/read_write.c:549 ksys_write+0xf9/0x250 fs/read_write.c:598 __do_sys_write fs/read_write.c:610 [inline] __se_sys_write fs/read_write.c:607 [inline] __x64_sys_write+0x73/0xb0 fs/read_write.c:607 Fixes: 4e09fc873d92 ("netfilter: prefer nla_strlcpy for dealing with NLA_STRING attributes") Signed-off-by: Eric Dumazet Acked-by: Florian Westphal Reported-by: syzbot Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_acct.c | 2 +- net/netfilter/nfnetlink_cthelper.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index 6ddf89183e7b..a0e5adf0b3b6 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -115,7 +115,7 @@ static int nfnl_acct_new(struct net *net, struct sock *nfnl, nfacct->flags = flags; } - nla_strlcpy(nfacct->name, nla_data(tb[NFACCT_NAME]), NFACCT_NAME_MAX); + nla_strlcpy(nfacct->name, tb[NFACCT_NAME], NFACCT_NAME_MAX); if (tb[NFACCT_BYTES]) { atomic64_set(&nfacct->bytes, diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index fa026b269b36..cb5b5f207777 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -150,7 +150,7 @@ nfnl_cthelper_expect_policy(struct nf_conntrack_expect_policy *expect_policy, return -EINVAL; nla_strlcpy(expect_policy->name, - nla_data(tb[NFCTH_POLICY_NAME]), NF_CT_HELPER_NAME_LEN); + tb[NFCTH_POLICY_NAME], NF_CT_HELPER_NAME_LEN); expect_policy->max_expected = ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_MAX])); if (expect_policy->max_expected > NF_CT_EXPECT_MAX_CNT) @@ -235,7 +235,7 @@ nfnl_cthelper_create(const struct nlattr * const tb[], goto err1; nla_strlcpy(helper->name, - nla_data(tb[NFCTH_NAME]), NF_CT_HELPER_NAME_LEN); + tb[NFCTH_NAME], NF_CT_HELPER_NAME_LEN); size = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN])); if (size > FIELD_SIZEOF(struct nf_conn_help, data)) { ret = -ENOMEM; -- cgit v1.2.3-58-ga151 From 533d1daea8d8a389b37207ad7b50c4e750969231 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 25 May 2018 23:29:59 +0200 Subject: IB: Revert "remove redundant INFINIBAND kconfig dependencies" Several subsystems depend on INFINIBAND_ADDR_TRANS, which in turn depends on INFINIBAND. However, when with CONFIG_INIFIBAND=m, this leads to a link error when another driver using it is built-in. The INFINIBAND_ADDR_TRANS dependency is insufficient here as this is a 'bool' symbol that does not force anything to be a module in turn. fs/cifs/smbdirect.o: In function `smbd_disconnect_rdma_work': smbdirect.c:(.text+0x1e4): undefined reference to `rdma_disconnect' net/9p/trans_rdma.o: In function `rdma_request': trans_rdma.c:(.text+0x7bc): undefined reference to `rdma_disconnect' net/9p/trans_rdma.o: In function `rdma_destroy_trans': trans_rdma.c:(.text+0x830): undefined reference to `ib_destroy_qp' trans_rdma.c:(.text+0x858): undefined reference to `ib_dealloc_pd' Fixes: 9533b292a7ac ("IB: remove redundant INFINIBAND kconfig dependencies") Signed-off-by: Arnd Bergmann Acked-by: Greg Thelen Signed-off-by: Jason Gunthorpe --- drivers/infiniband/ulp/srpt/Kconfig | 2 +- drivers/nvme/host/Kconfig | 2 +- drivers/nvme/target/Kconfig | 2 +- drivers/staging/lustre/lnet/Kconfig | 2 +- fs/cifs/Kconfig | 2 +- net/9p/Kconfig | 2 +- net/rds/Kconfig | 2 +- net/sunrpc/Kconfig | 2 +- 8 files changed, 8 insertions(+), 8 deletions(-) (limited to 'net') diff --git a/drivers/infiniband/ulp/srpt/Kconfig b/drivers/infiniband/ulp/srpt/Kconfig index 25bf6955b6d0..fb8b7182f05e 100644 --- a/drivers/infiniband/ulp/srpt/Kconfig +++ b/drivers/infiniband/ulp/srpt/Kconfig @@ -1,6 +1,6 @@ config INFINIBAND_SRPT tristate "InfiniBand SCSI RDMA Protocol target support" - depends on INFINIBAND_ADDR_TRANS && TARGET_CORE + depends on INFINIBAND && INFINIBAND_ADDR_TRANS && TARGET_CORE ---help--- Support for the SCSI RDMA Protocol (SRP) Target driver. The diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig index dbb7464c018c..88a8b5916624 100644 --- a/drivers/nvme/host/Kconfig +++ b/drivers/nvme/host/Kconfig @@ -27,7 +27,7 @@ config NVME_FABRICS config NVME_RDMA tristate "NVM Express over Fabrics RDMA host driver" - depends on INFINIBAND_ADDR_TRANS && BLOCK + depends on INFINIBAND && INFINIBAND_ADDR_TRANS && BLOCK select NVME_CORE select NVME_FABRICS select SG_POOL diff --git a/drivers/nvme/target/Kconfig b/drivers/nvme/target/Kconfig index 7595664ee753..3c7b61ddb0d1 100644 --- a/drivers/nvme/target/Kconfig +++ b/drivers/nvme/target/Kconfig @@ -27,7 +27,7 @@ config NVME_TARGET_LOOP config NVME_TARGET_RDMA tristate "NVMe over Fabrics RDMA target support" - depends on INFINIBAND_ADDR_TRANS + depends on INFINIBAND && INFINIBAND_ADDR_TRANS depends on NVME_TARGET select SGL_ALLOC help diff --git a/drivers/staging/lustre/lnet/Kconfig b/drivers/staging/lustre/lnet/Kconfig index f3b1ad4bd3dc..ad049e6f24e4 100644 --- a/drivers/staging/lustre/lnet/Kconfig +++ b/drivers/staging/lustre/lnet/Kconfig @@ -34,7 +34,7 @@ config LNET_SELFTEST config LNET_XPRT_IB tristate "LNET infiniband support" - depends on LNET && PCI && INFINIBAND_ADDR_TRANS + depends on LNET && PCI && INFINIBAND && INFINIBAND_ADDR_TRANS default LNET && INFINIBAND help This option allows the LNET users to use infiniband as an diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig index d61e2de8d0eb..5f132d59dfc2 100644 --- a/fs/cifs/Kconfig +++ b/fs/cifs/Kconfig @@ -197,7 +197,7 @@ config CIFS_SMB311 config CIFS_SMB_DIRECT bool "SMB Direct support (Experimental)" - depends on CIFS=m && INFINIBAND_ADDR_TRANS || CIFS=y && INFINIBAND_ADDR_TRANS=y + depends on CIFS=m && INFINIBAND && INFINIBAND_ADDR_TRANS || CIFS=y && INFINIBAND=y && INFINIBAND_ADDR_TRANS=y help Enables SMB Direct experimental support for SMB 3.0, 3.02 and 3.1.1. SMB Direct allows transferring SMB packets over RDMA. If unsure, diff --git a/net/9p/Kconfig b/net/9p/Kconfig index 46c39f7da444..e6014e0e51f7 100644 --- a/net/9p/Kconfig +++ b/net/9p/Kconfig @@ -32,7 +32,7 @@ config NET_9P_XEN config NET_9P_RDMA - depends on INET && INFINIBAND_ADDR_TRANS + depends on INET && INFINIBAND && INFINIBAND_ADDR_TRANS tristate "9P RDMA Transport (Experimental)" help This builds support for an RDMA transport. diff --git a/net/rds/Kconfig b/net/rds/Kconfig index 1a31502ee7db..bffde4b46c5d 100644 --- a/net/rds/Kconfig +++ b/net/rds/Kconfig @@ -8,7 +8,7 @@ config RDS config RDS_RDMA tristate "RDS over Infiniband" - depends on RDS && INFINIBAND_ADDR_TRANS + depends on RDS && INFINIBAND && INFINIBAND_ADDR_TRANS ---help--- Allow RDS to use Infiniband as a transport. This transport supports RDMA operations. diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig index 6358e5271070..ac09ca803296 100644 --- a/net/sunrpc/Kconfig +++ b/net/sunrpc/Kconfig @@ -50,7 +50,7 @@ config SUNRPC_DEBUG config SUNRPC_XPRT_RDMA tristate "RPC-over-RDMA transport" - depends on SUNRPC && INFINIBAND_ADDR_TRANS + depends on SUNRPC && INFINIBAND && INFINIBAND_ADDR_TRANS default SUNRPC && INFINIBAND select SG_POOL help -- cgit v1.2.3-58-ga151 From ad9d9e85072b668731f356be0a3750a3ba22a607 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sun, 27 May 2018 21:08:13 +0200 Subject: netfilter: nf_tables: disable preemption in nft_update_chain_stats() This patch fixes the following splat. [118709.054937] BUG: using smp_processor_id() in preemptible [00000000] code: test/1571 [118709.054970] caller is nft_update_chain_stats.isra.4+0x53/0x97 [nf_tables] [118709.054980] CPU: 2 PID: 1571 Comm: test Not tainted 4.17.0-rc6+ #335 [...] [118709.054992] Call Trace: [118709.055011] dump_stack+0x5f/0x86 [118709.055026] check_preemption_disabled+0xd4/0xe4 Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 942702a2776f..40e744572283 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -126,15 +126,15 @@ static noinline void nft_update_chain_stats(const struct nft_chain *chain, if (!base_chain->stats) return; + local_bh_disable(); stats = this_cpu_ptr(rcu_dereference(base_chain->stats)); if (stats) { - local_bh_disable(); u64_stats_update_begin(&stats->syncp); stats->pkts++; stats->bytes += pkt->skb->len; u64_stats_update_end(&stats->syncp); - local_bh_enable(); } + local_bh_enable(); } struct nft_jumpstack { -- cgit v1.2.3-58-ga151 From 360cc79d9d299ce297b205508276285ceffc5fa8 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Tue, 29 May 2018 01:13:45 +0900 Subject: netfilter: nf_tables: fix NULL-ptr in nf_tables_dump_obj() The table field in nft_obj_filter is not an array. In order to check tablename, we should check if the pointer is set. Test commands: %nft add table ip filter %nft add counter ip filter ct1 %nft reset counters Splat looks like: [ 306.510504] kasan: CONFIG_KASAN_INLINE enabled [ 306.516184] kasan: GPF could be caused by NULL-ptr deref or user memory access [ 306.524775] general protection fault: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI [ 306.528284] Modules linked in: nft_objref nft_counter nf_tables nfnetlink ip_tables x_tables [ 306.528284] CPU: 0 PID: 1488 Comm: nft Not tainted 4.17.0-rc4+ #17 [ 306.528284] Hardware name: To be filled by O.E.M. To be filled by O.E.M./Aptio CRB, BIOS 5.6.5 07/08/2015 [ 306.528284] RIP: 0010:nf_tables_dump_obj+0x52c/0xa70 [nf_tables] [ 306.528284] RSP: 0018:ffff8800b6cb7520 EFLAGS: 00010246 [ 306.528284] RAX: 0000000000000000 RBX: ffff8800b6c49820 RCX: 0000000000000000 [ 306.528284] RDX: 0000000000000000 RSI: dffffc0000000000 RDI: ffffed0016d96e9a [ 306.528284] RBP: ffff8800b6cb75c0 R08: ffffed00236fce7c R09: ffffed00236fce7b [ 306.528284] R10: ffffffff9f6241e8 R11: ffffed00236fce7c R12: ffff880111365108 [ 306.528284] R13: 0000000000000000 R14: ffff8800b6c49860 R15: ffff8800b6c49860 [ 306.528284] FS: 00007f838b007700(0000) GS:ffff88011b600000(0000) knlGS:0000000000000000 [ 306.528284] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 306.528284] CR2: 00007ffeafabcf78 CR3: 00000000b6cbe000 CR4: 00000000001006f0 [ 306.528284] Call Trace: [ 306.528284] netlink_dump+0x470/0xa20 [ 306.528284] __netlink_dump_start+0x5ae/0x690 [ 306.528284] ? nf_tables_getobj+0x1b3/0x740 [nf_tables] [ 306.528284] nf_tables_getobj+0x2f5/0x740 [nf_tables] [ 306.528284] ? nft_obj_notify+0x100/0x100 [nf_tables] [ 306.528284] ? nf_tables_getobj+0x740/0x740 [nf_tables] [ 306.528284] ? nf_tables_dump_flowtable_done+0x70/0x70 [nf_tables] [ 306.528284] ? nft_obj_notify+0x100/0x100 [nf_tables] [ 306.528284] nfnetlink_rcv_msg+0x8ff/0x932 [nfnetlink] [ 306.528284] ? nfnetlink_rcv_msg+0x216/0x932 [nfnetlink] [ 306.528284] netlink_rcv_skb+0x1c9/0x2f0 [ 306.528284] ? nfnetlink_bind+0x1d0/0x1d0 [nfnetlink] [ 306.528284] ? debug_check_no_locks_freed+0x270/0x270 [ 306.528284] ? netlink_ack+0x7a0/0x7a0 [ 306.528284] ? ns_capable_common+0x6e/0x110 [ ... ] Fixes: e46abbcc05aa8 ("netfilter: nf_tables: Allow table names of up to 255 chars") Signed-off-by: Taehee Yoo Acked-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 91e80aa852d6..2bdc8767aa40 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4706,7 +4706,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) if (idx > s_idx) memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); - if (filter && filter->table[0] && + if (filter && filter->table && strcmp(filter->table, table->name)) goto cont; if (filter && @@ -5380,7 +5380,7 @@ static int nf_tables_dump_flowtable(struct sk_buff *skb, if (idx > s_idx) memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); - if (filter && filter->table[0] && + if (filter && filter->table && strcmp(filter->table, table->name)) goto cont; -- cgit v1.2.3-58-ga151 From bbb8c61f97e3a2dd91b30d3e57b7964a67569d11 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Tue, 29 May 2018 01:14:12 +0900 Subject: netfilter: nf_tables: increase nft_counters_enabled in nft_chain_stats_replace() When a chain is updated, a counter can be attached. if so, the nft_counters_enabled should be increased. test commands: %nft add table ip filter %nft add chain ip filter input { type filter hook input priority 4\; } %iptables-compat -Z input %nft delete chain ip filter input we can see below messages. [ 286.443720] jump label: negative count! [ 286.448278] WARNING: CPU: 0 PID: 1459 at kernel/jump_label.c:197 __static_key_slow_dec_cpuslocked+0x6f/0xf0 [ 286.449144] Modules linked in: nf_tables nfnetlink ip_tables x_tables [ 286.449144] CPU: 0 PID: 1459 Comm: nft Tainted: G W 4.17.0-rc2+ #12 [ 286.449144] RIP: 0010:__static_key_slow_dec_cpuslocked+0x6f/0xf0 [ 286.449144] RSP: 0018:ffff88010e5176f0 EFLAGS: 00010286 [ 286.449144] RAX: 000000000000001b RBX: ffffffffc0179500 RCX: ffffffffb8a82522 [ 286.449144] RDX: 0000000000000001 RSI: 0000000000000008 RDI: ffff88011b7e5eac [ 286.449144] RBP: 0000000000000000 R08: ffffed00236fce5c R09: ffffed00236fce5b [ 286.449144] R10: ffffffffc0179503 R11: ffffed00236fce5c R12: 0000000000000000 [ 286.449144] R13: ffff88011a28e448 R14: ffff88011a28e470 R15: dffffc0000000000 [ 286.449144] FS: 00007f0384328700(0000) GS:ffff88011b600000(0000) knlGS:0000000000000000 [ 286.449144] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 286.449144] CR2: 00007f038394bf10 CR3: 0000000104a86000 CR4: 00000000001006f0 [ 286.449144] Call Trace: [ 286.449144] static_key_slow_dec+0x6a/0x70 [ 286.449144] nf_tables_chain_destroy+0x19d/0x210 [nf_tables] [ 286.449144] nf_tables_commit+0x1891/0x1c50 [nf_tables] [ 286.449144] nfnetlink_rcv+0x1148/0x13d0 [nfnetlink] [ ... ] Signed-off-by: Taehee Yoo 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 2bdc8767aa40..501e48a7965b 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1298,8 +1298,10 @@ static void nft_chain_stats_replace(struct nft_base_chain *chain, rcu_assign_pointer(chain->stats, newstats); synchronize_rcu(); free_percpu(oldstats); - } else + } else { rcu_assign_pointer(chain->stats, newstats); + static_branch_inc(&nft_counters_enabled); + } } static void nf_tables_chain_destroy(struct nft_ctx *ctx) -- cgit v1.2.3-58-ga151 From bbb40a0b75209734ff9286f3326171638c9f6569 Mon Sep 17 00:00:00 2001 From: Mathieu Xhonneux Date: Fri, 25 May 2018 13:29:41 +0100 Subject: ipv6: sr: fix memory OOB access in seg6_do_srh_encap/inline seg6_do_srh_encap and seg6_do_srh_inline can possibly do an out-of-bounds access when adding the SRH to the packet. This no longer happen when expanding the skb not only by the size of the SRH (+ outer IPv6 header), but also by skb->mac_len. [ 53.793056] BUG: KASAN: use-after-free in seg6_do_srh_encap+0x284/0x620 [ 53.794564] Write of size 14 at addr ffff88011975ecfa by task ping/674 [ 53.796665] CPU: 0 PID: 674 Comm: ping Not tainted 4.17.0-rc3-ARCH+ #90 [ 53.796670] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-20171110_100015-anatol 04/01/2014 [ 53.796673] Call Trace: [ 53.796679] [ 53.796689] dump_stack+0x71/0xab [ 53.796700] print_address_description+0x6a/0x270 [ 53.796707] kasan_report+0x258/0x380 [ 53.796715] ? seg6_do_srh_encap+0x284/0x620 [ 53.796722] memmove+0x34/0x50 [ 53.796730] seg6_do_srh_encap+0x284/0x620 [ 53.796741] ? seg6_do_srh+0x29b/0x360 [ 53.796747] seg6_do_srh+0x29b/0x360 [ 53.796756] seg6_input+0x2e/0x2e0 [ 53.796765] lwtunnel_input+0x93/0xd0 [ 53.796774] ipv6_rcv+0x690/0x920 [ 53.796783] ? ip6_input+0x170/0x170 [ 53.796791] ? eth_gro_receive+0x2d0/0x2d0 [ 53.796800] ? ip6_input+0x170/0x170 [ 53.796809] __netif_receive_skb_core+0xcc0/0x13f0 [ 53.796820] ? netdev_info+0x110/0x110 [ 53.796827] ? napi_complete_done+0xb6/0x170 [ 53.796834] ? e1000_clean+0x6da/0xf70 [ 53.796845] ? process_backlog+0x129/0x2a0 [ 53.796853] process_backlog+0x129/0x2a0 [ 53.796862] net_rx_action+0x211/0x5c0 [ 53.796870] ? napi_complete_done+0x170/0x170 [ 53.796887] ? run_rebalance_domains+0x11f/0x150 [ 53.796891] __do_softirq+0x10e/0x39e [ 53.796894] do_softirq_own_stack+0x2a/0x40 [ 53.796895] [ 53.796898] do_softirq.part.16+0x54/0x60 [ 53.796900] __local_bh_enable_ip+0x5b/0x60 [ 53.796903] ip6_finish_output2+0x416/0x9f0 [ 53.796906] ? ip6_dst_lookup_flow+0x110/0x110 [ 53.796909] ? ip6_sk_dst_lookup_flow+0x390/0x390 [ 53.796911] ? __rcu_read_unlock+0x66/0x80 [ 53.796913] ? ip6_mtu+0x44/0xf0 [ 53.796916] ? ip6_output+0xfc/0x220 [ 53.796918] ip6_output+0xfc/0x220 [ 53.796921] ? ip6_finish_output+0x2b0/0x2b0 [ 53.796923] ? memcpy+0x34/0x50 [ 53.796926] ip6_send_skb+0x43/0xc0 [ 53.796929] rawv6_sendmsg+0x1216/0x1530 [ 53.796932] ? __orc_find+0x6b/0xc0 [ 53.796934] ? rawv6_rcv_skb+0x160/0x160 [ 53.796937] ? __rcu_read_unlock+0x66/0x80 [ 53.796939] ? __rcu_read_unlock+0x66/0x80 [ 53.796942] ? is_bpf_text_address+0x1e/0x30 [ 53.796944] ? kernel_text_address+0xec/0x100 [ 53.796946] ? __kernel_text_address+0xe/0x30 [ 53.796948] ? unwind_get_return_address+0x2f/0x50 [ 53.796950] ? __save_stack_trace+0x92/0x100 [ 53.796954] ? save_stack+0x89/0xb0 [ 53.796956] ? kasan_kmalloc+0xa0/0xd0 [ 53.796958] ? kmem_cache_alloc+0xd2/0x1f0 [ 53.796961] ? prepare_creds+0x23/0x160 [ 53.796963] ? __x64_sys_capset+0x252/0x3e0 [ 53.796966] ? do_syscall_64+0x69/0x160 [ 53.796968] ? entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 53.796971] ? __alloc_pages_nodemask+0x170/0x380 [ 53.796973] ? __alloc_pages_slowpath+0x12c0/0x12c0 [ 53.796977] ? tty_vhangup+0x20/0x20 [ 53.796979] ? policy_nodemask+0x1a/0x90 [ 53.796982] ? __mod_node_page_state+0x8d/0xa0 [ 53.796986] ? __check_object_size+0xe7/0x240 [ 53.796989] ? __sys_sendto+0x229/0x290 [ 53.796991] ? rawv6_rcv_skb+0x160/0x160 [ 53.796993] __sys_sendto+0x229/0x290 [ 53.796996] ? __ia32_sys_getpeername+0x50/0x50 [ 53.796999] ? commit_creds+0x2de/0x520 [ 53.797002] ? security_capset+0x57/0x70 [ 53.797004] ? __x64_sys_capset+0x29f/0x3e0 [ 53.797007] ? __x64_sys_rt_sigsuspend+0xe0/0xe0 [ 53.797011] ? __do_page_fault+0x664/0x770 [ 53.797014] __x64_sys_sendto+0x74/0x90 [ 53.797017] do_syscall_64+0x69/0x160 [ 53.797019] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 53.797022] RIP: 0033:0x7f43b7a6714a [ 53.797023] RSP: 002b:00007ffd891bd368 EFLAGS: 00000246 ORIG_RAX: 000000000000002c [ 53.797026] RAX: ffffffffffffffda RBX: 00000000006129c0 RCX: 00007f43b7a6714a [ 53.797028] RDX: 0000000000000040 RSI: 00000000006129c0 RDI: 0000000000000004 [ 53.797029] RBP: 00007ffd891be640 R08: 0000000000610940 R09: 000000000000001c [ 53.797030] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000040 [ 53.797032] R13: 000000000060e6a0 R14: 0000000000008004 R15: 000000000040b661 [ 53.797171] Allocated by task 642: [ 53.797460] kasan_kmalloc+0xa0/0xd0 [ 53.797463] kmem_cache_alloc+0xd2/0x1f0 [ 53.797465] getname_flags+0x40/0x210 [ 53.797467] user_path_at_empty+0x1d/0x40 [ 53.797469] do_faccessat+0x12a/0x320 [ 53.797471] do_syscall_64+0x69/0x160 [ 53.797473] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 53.797607] Freed by task 642: [ 53.797869] __kasan_slab_free+0x130/0x180 [ 53.797871] kmem_cache_free+0xa8/0x230 [ 53.797872] filename_lookup+0x15b/0x230 [ 53.797874] do_faccessat+0x12a/0x320 [ 53.797876] do_syscall_64+0x69/0x160 [ 53.797878] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 53.798014] The buggy address belongs to the object at ffff88011975e600 which belongs to the cache names_cache of size 4096 [ 53.799043] The buggy address is located 1786 bytes inside of 4096-byte region [ffff88011975e600, ffff88011975f600) [ 53.800013] The buggy address belongs to the page: [ 53.800414] page:ffffea000465d600 count:1 mapcount:0 mapping:0000000000000000 index:0x0 compound_mapcount: 0 [ 53.801259] flags: 0x17fff0000008100(slab|head) [ 53.801640] raw: 017fff0000008100 0000000000000000 0000000000000000 0000000100070007 [ 53.803147] raw: dead000000000100 dead000000000200 ffff88011b185a40 0000000000000000 [ 53.803787] page dumped because: kasan: bad access detected [ 53.804384] Memory state around the buggy address: [ 53.804788] ffff88011975eb80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 53.805384] ffff88011975ec00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 53.805979] >ffff88011975ec80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 53.806577] ^ [ 53.807165] ffff88011975ed00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 53.807762] ffff88011975ed80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 53.808356] ================================================================== [ 53.808949] Disabling lock debugging due to kernel taint Fixes: 6c8702c60b88 ("ipv6: sr: add support for SRH encapsulation and injection with lwtunnels") Signed-off-by: David Lebrun Signed-off-by: Mathieu Xhonneux Signed-off-by: David S. Miller --- net/ipv6/seg6_iptunnel.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 5fe139484919..bf4763fd68c2 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -103,7 +103,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) hdrlen = (osrh->hdrlen + 1) << 3; tot_len = hdrlen + sizeof(*hdr); - err = skb_cow_head(skb, tot_len); + err = skb_cow_head(skb, tot_len + skb->mac_len); if (unlikely(err)) return err; @@ -161,7 +161,7 @@ int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh) hdrlen = (osrh->hdrlen + 1) << 3; - err = skb_cow_head(skb, hdrlen); + err = skb_cow_head(skb, hdrlen + skb->mac_len); if (unlikely(err)) return err; -- cgit v1.2.3-58-ga151 From 38369f54d97dd7dc50c73a2797bfeb53c2e87d2d Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Thu, 31 May 2018 09:45:18 +0200 Subject: xfrm Fix potential error pointer dereference in xfrm_bundle_create. We may derference an invalid pointer in the error path of xfrm_bundle_create(). Fix this by returning this error pointer directly instead of assigning it to xdst0. Fixes: 45b018beddb6 ("ipsec: Create and use new helpers for dst child access.") Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 40b54cc64243..5f48251c1319 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1658,7 +1658,6 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, trailer_len -= xdst_prev->u.dst.xfrm->props.trailer_len; } -out: return &xdst0->u.dst; put_states: @@ -1667,8 +1666,8 @@ put_states: free_dst: if (xdst0) dst_release_immediate(&xdst0->u.dst); - xdst0 = ERR_PTR(err); - goto out; + + return ERR_PTR(err); } static int xfrm_expand_policies(const struct flowi *fl, u16 family, -- cgit v1.2.3-58-ga151 From 8258d2da9f9f521dce7019e018360c28d116354e Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Wed, 30 May 2018 11:29:15 +0300 Subject: cls_flower: Fix incorrect idr release when failing to modify rule When we fail to modify a rule, we incorrectly release the idr handle of the unmodified old rule. Fix that by checking if we need to release it. Fixes: fe2502e49b58 ("net_sched: remove cls_flower idr on failure") Reported-by: Vlad Buslov Reviewed-by: Roi Dayan Acked-by: Jiri Pirko Signed-off-by: Paul Blakey Signed-off-by: David S. Miller --- net/sched/cls_flower.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index d964e60c730e..c79f6e71512e 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -977,7 +977,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, return 0; errout_idr: - if (fnew->handle) + if (!fold) idr_remove(&head->handle_idr, fnew->handle); errout: tcf_exts_destroy(&fnew->exts); -- cgit v1.2.3-58-ga151 From 0f51f3582f22e543b78c4e113220ed1c35acbd97 Mon Sep 17 00:00:00 2001 From: Samuel Mendoza-Jonas Date: Thu, 31 May 2018 14:10:04 +1000 Subject: net/ncsi: Fix array size in dumpit handler With CONFIG_CC_STACKPROTECTOR enabled the kernel panics as below when parsing a NCSI_CMD_PKG_INFO command: [ 150.149711] Kernel panic - not syncing: stack-protector: Kernel stack is corrupted in: 805cff08 [ 150.149711] [ 150.159919] CPU: 0 PID: 1301 Comm: ncsi-netlink Not tainted 4.13.16-468cbec6d2c91239332cb91b1f0a73aafcb6f0c6 #1 [ 150.170004] Hardware name: Generic DT based system [ 150.174852] [<80109930>] (unwind_backtrace) from [<80106bc4>] (show_stack+0x20/0x24) [ 150.182641] [<80106bc4>] (show_stack) from [<805d36e4>] (dump_stack+0x20/0x28) [ 150.189888] [<805d36e4>] (dump_stack) from [<801163ac>] (panic+0xdc/0x278) [ 150.196780] [<801163ac>] (panic) from [<801162cc>] (__stack_chk_fail+0x20/0x24) [ 150.204111] [<801162cc>] (__stack_chk_fail) from [<805cff08>] (ncsi_pkg_info_all_nl+0x244/0x258) [ 150.212912] [<805cff08>] (ncsi_pkg_info_all_nl) from [<804f939c>] (genl_lock_dumpit+0x3c/0x54) [ 150.221535] [<804f939c>] (genl_lock_dumpit) from [<804f873c>] (netlink_dump+0xf8/0x284) [ 150.229550] [<804f873c>] (netlink_dump) from [<804f8d44>] (__netlink_dump_start+0x124/0x17c) [ 150.237992] [<804f8d44>] (__netlink_dump_start) from [<804f9880>] (genl_rcv_msg+0x1c8/0x3d4) [ 150.246440] [<804f9880>] (genl_rcv_msg) from [<804f9174>] (netlink_rcv_skb+0xd8/0x134) [ 150.254361] [<804f9174>] (netlink_rcv_skb) from [<804f96a4>] (genl_rcv+0x30/0x44) [ 150.261850] [<804f96a4>] (genl_rcv) from [<804f7790>] (netlink_unicast+0x198/0x234) [ 150.269511] [<804f7790>] (netlink_unicast) from [<804f7ffc>] (netlink_sendmsg+0x368/0x3b0) [ 150.277783] [<804f7ffc>] (netlink_sendmsg) from [<804abea4>] (sock_sendmsg+0x24/0x34) [ 150.285625] [<804abea4>] (sock_sendmsg) from [<804ac1dc>] (___sys_sendmsg+0x244/0x260) [ 150.293556] [<804ac1dc>] (___sys_sendmsg) from [<804ad98c>] (__sys_sendmsg+0x5c/0x9c) [ 150.301400] [<804ad98c>] (__sys_sendmsg) from [<804ad9e4>] (SyS_sendmsg+0x18/0x1c) [ 150.308984] [<804ad9e4>] (SyS_sendmsg) from [<80102640>] (ret_fast_syscall+0x0/0x3c) [ 150.316743] ---[ end Kernel panic - not syncing: stack-protector: Kernel stack is corrupted in: 805cff08 This turns out to be because the attrs array in ncsi_pkg_info_all_nl() is initialised to a length of NCSI_ATTR_MAX which is the maximum attribute number, not the number of attributes. Fixes: 955dc68cb9b2 ("net/ncsi: Add generic netlink family") Signed-off-by: Samuel Mendoza-Jonas Signed-off-by: David S. Miller --- net/ncsi/ncsi-netlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c index 8d7e849d4825..41cede4041d3 100644 --- a/net/ncsi/ncsi-netlink.c +++ b/net/ncsi/ncsi-netlink.c @@ -215,7 +215,7 @@ err: static int ncsi_pkg_info_all_nl(struct sk_buff *skb, struct netlink_callback *cb) { - struct nlattr *attrs[NCSI_ATTR_MAX]; + struct nlattr *attrs[NCSI_ATTR_MAX + 1]; struct ncsi_package *np, *package; struct ncsi_dev_priv *ndp; unsigned int package_id; -- cgit v1.2.3-58-ga151 From 664088f8d68178809b848ca450f2797efb34e8e7 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 31 May 2018 15:59:46 -0400 Subject: net-sysfs: Fix memory leak in XPS configuration This patch reorders the error cases in showing the XPS configuration so that we hold off on memory allocation until after we have verified that we can support XPS on a given ring. Fixes: 184c449f91fe ("net: Add support for XPS with QoS via traffic classes") Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- net/core/net-sysfs.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index c476f0794132..bb7e80f4ced3 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1214,9 +1214,6 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue, cpumask_var_t mask; unsigned long index; - if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) - return -ENOMEM; - index = get_netdev_queue_index(queue); if (dev->num_tc) { @@ -1226,6 +1223,9 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue, return -EINVAL; } + if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + rcu_read_lock(); dev_maps = rcu_dereference(dev->xps_maps); if (dev_maps) { -- cgit v1.2.3-58-ga151 From eb7f54b90bd8f469834c5e86dcf72ebf9a629811 Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Fri, 1 Jun 2018 14:30:38 +0300 Subject: kcm: Fix use-after-free caused by clonned sockets (resend for properly queueing in patchwork) kcm_clone() creates kernel socket, which does not take net counter. Thus, the net may die before the socket is completely destructed, i.e. kcm_exit_net() is executed before kcm_done(). Reported-by: syzbot+5f1a04e374a635efc426@syzkaller.appspotmail.com Signed-off-by: Kirill Tkhai Signed-off-by: David S. Miller --- net/kcm/kcmsock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index dc76bc346829..d3601d421571 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1671,7 +1671,7 @@ static struct file *kcm_clone(struct socket *osock) __module_get(newsock->ops->owner); newsk = sk_alloc(sock_net(osock->sk), PF_KCM, GFP_KERNEL, - &kcm_proto, true); + &kcm_proto, false); if (!newsk) { sock_release(newsock); return ERR_PTR(-ENOMEM); -- cgit v1.2.3-58-ga151 From 82612de1c98e610d194e34178bde3cca7dedce41 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 31 May 2018 10:59:32 +0200 Subject: ip_tunnel: restore binding to ifaces with a large mtu After commit f6cc9c054e77, the following conf is broken (note that the default loopback mtu is 65536, ie IP_MAX_MTU + 1): $ ip tunnel add gre1 mode gre local 10.125.0.1 remote 10.125.0.2 dev lo add tunnel "gre0" failed: Invalid argument $ ip l a type dummy $ ip l s dummy1 up $ ip l s dummy1 mtu 65535 $ ip tunnel add gre1 mode gre local 10.125.0.1 remote 10.125.0.2 dev dummy1 add tunnel "gre0" failed: Invalid argument dev_set_mtu() doesn't allow to set a mtu which is too large. First, let's cap the mtu returned by ip_tunnel_bind_dev(). Second, remove the magic value 0xFFF8 and use IP_MAX_MTU instead. 0xFFF8 seems to be there for ages, I don't know why this value was used. With a recent kernel, it's also possible to set a mtu > IP_MAX_MTU: $ ip l s dummy1 mtu 66000 After that patch, it's also possible to bind an ip tunnel on that kind of interface. CC: Petr Machata CC: Ido Schimmel Link: https://git.kernel.org/pub/scm/linux/kernel/git/davem/netdev-vger-cvs.git/commit/?id=e5afd356a411a Fixes: f6cc9c054e77 ("ip_tunnel: Emit events for post-register MTU changes") Signed-off-by: Nicolas Dichtel Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- net/ipv4/ip_tunnel.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 6b0e362cc99b..38d906baf1df 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -328,7 +328,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev) if (tdev) { hlen = tdev->hard_header_len + tdev->needed_headroom; - mtu = tdev->mtu; + mtu = min(tdev->mtu, IP_MAX_MTU); } dev->needed_headroom = t_hlen + hlen; @@ -362,7 +362,7 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net, nt = netdev_priv(dev); t_hlen = nt->hlen + sizeof(struct iphdr); dev->min_mtu = ETH_MIN_MTU; - dev->max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen; + dev->max_mtu = IP_MAX_MTU - dev->hard_header_len - t_hlen; ip_tunnel_add(itn, nt); return nt; @@ -930,7 +930,7 @@ int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict) { struct ip_tunnel *tunnel = netdev_priv(dev); int t_hlen = tunnel->hlen + sizeof(struct iphdr); - int max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen; + int max_mtu = IP_MAX_MTU - dev->hard_header_len - t_hlen; if (new_mtu < ETH_MIN_MTU) return -EINVAL; @@ -1107,7 +1107,7 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], mtu = ip_tunnel_bind_dev(dev); if (tb[IFLA_MTU]) { - unsigned int max = 0xfff8 - dev->hard_header_len - nt->hlen; + unsigned int max = IP_MAX_MTU - dev->hard_header_len - nt->hlen; mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU, (unsigned int)(max - sizeof(struct iphdr))); -- cgit v1.2.3-58-ga151 From f7ff1fde9441b4fcc8ffb6e66e6e5a00d008937e Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 31 May 2018 10:59:33 +0200 Subject: ip6_tunnel: remove magic mtu value 0xFFF8 I don't know where this value comes from (probably a copy and paste and paste and paste ...). Let's use standard values which are a bit greater. Link: https://git.kernel.org/pub/scm/linux/kernel/git/davem/netdev-vger-cvs.git/commit/?id=e5afd356a411a Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- net/ipv6/ip6_tunnel.c | 11 ++++++++--- net/ipv6/sit.c | 5 +++-- 2 files changed, 11 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index da66aaac51ce..00e138a44cbb 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1692,8 +1692,13 @@ int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) if (new_mtu < ETH_MIN_MTU) return -EINVAL; } - if (new_mtu > 0xFFF8 - dev->hard_header_len) - return -EINVAL; + if (tnl->parms.proto == IPPROTO_IPV6 || tnl->parms.proto == 0) { + if (new_mtu > IP6_MAX_MTU - dev->hard_header_len) + return -EINVAL; + } else { + if (new_mtu > IP_MAX_MTU - dev->hard_header_len) + return -EINVAL; + } dev->mtu = new_mtu; return 0; } @@ -1841,7 +1846,7 @@ ip6_tnl_dev_init_gen(struct net_device *dev) if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) dev->mtu -= 8; dev->min_mtu = ETH_MIN_MTU; - dev->max_mtu = 0xFFF8 - dev->hard_header_len; + dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len; return 0; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 2afce37a7177..e9400ffa7875 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1371,7 +1371,7 @@ static void ipip6_tunnel_setup(struct net_device *dev) dev->hard_header_len = LL_MAX_HEADER + t_hlen; dev->mtu = ETH_DATA_LEN - t_hlen; dev->min_mtu = IPV6_MIN_MTU; - dev->max_mtu = 0xFFF8 - t_hlen; + dev->max_mtu = IP6_MAX_MTU - t_hlen; dev->flags = IFF_NOARP; netif_keep_dst(dev); dev->addr_len = 4; @@ -1583,7 +1583,8 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev, if (tb[IFLA_MTU]) { u32 mtu = nla_get_u32(tb[IFLA_MTU]); - if (mtu >= IPV6_MIN_MTU && mtu <= 0xFFF8 - dev->hard_header_len) + if (mtu >= IPV6_MIN_MTU && + mtu <= IP6_MAX_MTU - dev->hard_header_len) dev->mtu = mtu; } -- cgit v1.2.3-58-ga151