From 153e9cdb7e9277d63cf5eed5fb5c3694310f6ca9 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 17 Apr 2018 12:07:06 -0700 Subject: KEYS: DNS: limit the length of option strings [ Upstream commit 9c438d7a3a52dcc2b9ed095cb87d3a5e83cf7e60 ] Adding a dns_resolver key whose payload contains a very long option name resulted in that string being printed in full. This hit the WARN_ONCE() in set_precision() during the printk(), because printk() only supports a precision of up to 32767 bytes: precision 1000000 too large WARNING: CPU: 0 PID: 752 at lib/vsprintf.c:2189 vsnprintf+0x4bc/0x5b0 Fix it by limiting option strings (combined name + value) to a much more reasonable 128 bytes. The exact limit is arbitrary, but currently the only recognized option is formatted as "dnserror=%lu" which fits well within this limit. Also ratelimit the printks. Reproducer: perl -e 'print "#", "A" x 1000000, "\x00"' | keyctl padd dns_resolver desc @s This bug was found using syzkaller. Reported-by: Mark Rutland Fixes: 4a2d789267e0 ("DNS: If the DNS server returns an error, allow that to be cached [ver #2]") Signed-off-by: Eric Biggers Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/dns_resolver/dns_key.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'net') diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c index 6abc5012200b..e26df2764e83 100644 --- a/net/dns_resolver/dns_key.c +++ b/net/dns_resolver/dns_key.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -91,9 +92,9 @@ dns_resolver_preparse(struct key_preparsed_payload *prep) next_opt = memchr(opt, '#', end - opt) ?: end; opt_len = next_opt - opt; - if (!opt_len) { - printk(KERN_WARNING - "Empty option to dns_resolver key\n"); + if (opt_len <= 0 || opt_len > 128) { + pr_warn_ratelimited("Invalid option length (%d) for dns_resolver key\n", + opt_len); return -EINVAL; } @@ -127,10 +128,8 @@ dns_resolver_preparse(struct key_preparsed_payload *prep) } bad_option_value: - printk(KERN_WARNING - "Option '%*.*s' to dns_resolver key:" - " bad/missing value\n", - opt_nlen, opt_nlen, opt); + pr_warn_ratelimited("Option '%*.*s' to dns_resolver key: bad/missing value\n", + opt_nlen, opt_nlen, opt); return -EINVAL; } while (opt = next_opt + 1, opt < end); } -- cgit v1.2.3 From ddecae8696b96cf56154692298fa4511bc7f70d5 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Mon, 23 Apr 2018 16:15:14 +0200 Subject: l2tp: check sockaddr length in pppol2tp_connect() [ Upstream commit eb1c28c05894a4b1f6b56c5bf072205e64cfa280 ] Check sockaddr_len before dereferencing sp->sa_protocol, to ensure that it actually points to valid data. Fixes: fd558d186df2 ("l2tp: Split pppol2tp patch into separate l2tp and ppp parts") Reported-by: syzbot+a70ac890b23b1bf29f5c@syzkaller.appspotmail.com Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/l2tp/l2tp_ppp.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'net') diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 67f2e72723b2..2764c4bd072c 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -606,6 +606,13 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, lock_sock(sk); error = -EINVAL; + + if (sockaddr_len != sizeof(struct sockaddr_pppol2tp) && + sockaddr_len != sizeof(struct sockaddr_pppol2tpv3) && + sockaddr_len != sizeof(struct sockaddr_pppol2tpin6) && + sockaddr_len != sizeof(struct sockaddr_pppol2tpv3in6)) + goto end; + if (sp->sa_protocol != PX_PROTO_OL2TP) goto end; -- cgit v1.2.3 From d6e78baf1df18ec01f7fea0c389600e2f5faad75 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 11 Apr 2018 14:46:00 -0700 Subject: net: validate attribute sizes in neigh_dump_table() [ Upstream commit 7dd07c143a4b54d050e748bee4b4b9e94a7b1744 ] Since neigh_dump_table() calls nlmsg_parse() without giving policy constraints, attributes can have arbirary size that we must validate Reported by syzbot/KMSAN : BUG: KMSAN: uninit-value in neigh_master_filtered net/core/neighbour.c:2292 [inline] BUG: KMSAN: uninit-value in neigh_dump_table net/core/neighbour.c:2348 [inline] BUG: KMSAN: uninit-value in neigh_dump_info+0x1af0/0x2250 net/core/neighbour.c:2438 CPU: 1 PID: 3575 Comm: syzkaller268891 Not tainted 4.16.0+ #83 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x185/0x1d0 lib/dump_stack.c:53 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676 neigh_master_filtered net/core/neighbour.c:2292 [inline] neigh_dump_table net/core/neighbour.c:2348 [inline] neigh_dump_info+0x1af0/0x2250 net/core/neighbour.c:2438 netlink_dump+0x9ad/0x1540 net/netlink/af_netlink.c:2225 __netlink_dump_start+0x1167/0x12a0 net/netlink/af_netlink.c:2322 netlink_dump_start include/linux/netlink.h:214 [inline] rtnetlink_rcv_msg+0x1435/0x1560 net/core/rtnetlink.c:4598 netlink_rcv_skb+0x355/0x5f0 net/netlink/af_netlink.c:2447 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:4653 netlink_unicast_kernel net/netlink/af_netlink.c:1311 [inline] netlink_unicast+0x1672/0x1750 net/netlink/af_netlink.c:1337 netlink_sendmsg+0x1048/0x1310 net/netlink/af_netlink.c:1900 sock_sendmsg_nosec net/socket.c:630 [inline] sock_sendmsg net/socket.c:640 [inline] ___sys_sendmsg+0xec0/0x1310 net/socket.c:2046 __sys_sendmsg net/socket.c:2080 [inline] SYSC_sendmsg+0x2a3/0x3d0 net/socket.c:2091 SyS_sendmsg+0x54/0x80 net/socket.c:2087 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 RIP: 0033:0x43fed9 RSP: 002b:00007ffddbee2798 EFLAGS: 00000213 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 000000000043fed9 RDX: 0000000000000000 RSI: 0000000020005000 RDI: 0000000000000003 RBP: 00000000006ca018 R08: 00000000004002c8 R09: 00000000004002c8 R10: 00000000004002c8 R11: 0000000000000213 R12: 0000000000401800 R13: 0000000000401890 R14: 0000000000000000 R15: 0000000000000000 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline] kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188 kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314 kmsan_slab_alloc+0x11/0x20 mm/kmsan/kmsan.c:321 slab_post_alloc_hook mm/slab.h:445 [inline] slab_alloc_node mm/slub.c:2737 [inline] __kmalloc_node_track_caller+0xaed/0x11c0 mm/slub.c:4369 __kmalloc_reserve net/core/skbuff.c:138 [inline] __alloc_skb+0x2cf/0x9f0 net/core/skbuff.c:206 alloc_skb include/linux/skbuff.h:984 [inline] netlink_alloc_large_skb net/netlink/af_netlink.c:1183 [inline] netlink_sendmsg+0x9a6/0x1310 net/netlink/af_netlink.c:1875 sock_sendmsg_nosec net/socket.c:630 [inline] sock_sendmsg net/socket.c:640 [inline] ___sys_sendmsg+0xec0/0x1310 net/socket.c:2046 __sys_sendmsg net/socket.c:2080 [inline] SYSC_sendmsg+0x2a3/0x3d0 net/socket.c:2091 SyS_sendmsg+0x54/0x80 net/socket.c:2087 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 Fixes: 21fdd092acc7 ("net: Add support for filtering neigh dump by master device") Signed-off-by: Eric Dumazet Cc: David Ahern Reported-by: syzbot Acked-by: David Ahern Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/core/neighbour.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 33432e64804c..8723cb845919 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2280,12 +2280,16 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL); if (!err) { - if (tb[NDA_IFINDEX]) + if (tb[NDA_IFINDEX]) { + if (nla_len(tb[NDA_IFINDEX]) != sizeof(u32)) + return -EINVAL; filter_idx = nla_get_u32(tb[NDA_IFINDEX]); - - if (tb[NDA_MASTER]) + } + if (tb[NDA_MASTER]) { + if (nla_len(tb[NDA_MASTER]) != sizeof(u32)) + return -EINVAL; filter_master_idx = nla_get_u32(tb[NDA_MASTER]); - + } if (filter_idx || filter_master_idx) flags |= NLM_F_DUMP_FILTERED; } -- cgit v1.2.3 From 6ebd6a11b297191078aa86b6f563f65d7cb53993 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 19 Apr 2018 12:25:38 -0700 Subject: llc: delete timers synchronously in llc_sk_free() [ Upstream commit b905ef9ab90115d001c1658259af4b1c65088779 ] The connection timers of an llc sock could be still flying after we delete them in llc_sk_free(), and even possibly after we free the sock. We could just wait synchronously here in case of troubles. Note, I leave other call paths as they are, since they may not have to wait, at least we can change them to synchronously when needed. Also, move the code to net/llc/llc_conn.c, which is apparently a better place. Reported-by: Signed-off-by: Cong Wang Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/llc/llc_c_ac.c | 9 +-------- net/llc/llc_conn.c | 22 +++++++++++++++++++++- 2 files changed, 22 insertions(+), 9 deletions(-) (limited to 'net') diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c index ea225bd2672c..f8d4ab8ca1a5 100644 --- a/net/llc/llc_c_ac.c +++ b/net/llc/llc_c_ac.c @@ -1096,14 +1096,7 @@ int llc_conn_ac_inc_tx_win_size(struct sock *sk, struct sk_buff *skb) int llc_conn_ac_stop_all_timers(struct sock *sk, struct sk_buff *skb) { - struct llc_sock *llc = llc_sk(sk); - - del_timer(&llc->pf_cycle_timer.timer); - del_timer(&llc->ack_timer.timer); - del_timer(&llc->rej_sent_timer.timer); - del_timer(&llc->busy_state_timer.timer); - llc->ack_must_be_send = 0; - llc->ack_pf = 0; + llc_sk_stop_all_timers(sk, false); return 0; } diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 8bc5a1bd2d45..d861b74ad068 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -951,6 +951,26 @@ out: return sk; } +void llc_sk_stop_all_timers(struct sock *sk, bool sync) +{ + struct llc_sock *llc = llc_sk(sk); + + if (sync) { + del_timer_sync(&llc->pf_cycle_timer.timer); + del_timer_sync(&llc->ack_timer.timer); + del_timer_sync(&llc->rej_sent_timer.timer); + del_timer_sync(&llc->busy_state_timer.timer); + } else { + del_timer(&llc->pf_cycle_timer.timer); + del_timer(&llc->ack_timer.timer); + del_timer(&llc->rej_sent_timer.timer); + del_timer(&llc->busy_state_timer.timer); + } + + llc->ack_must_be_send = 0; + llc->ack_pf = 0; +} + /** * llc_sk_free - Frees a LLC socket * @sk - socket to free @@ -963,7 +983,7 @@ void llc_sk_free(struct sock *sk) llc->state = LLC_CONN_OUT_OF_SVC; /* Stop all (possibly) running timers */ - llc_conn_ac_stop_all_timers(sk, NULL); + llc_sk_stop_all_timers(sk, true); #ifdef DEBUG_LLC_CONN_ALLOC printk(KERN_INFO "%s: unackq=%d, txq=%d\n", __func__, skb_queue_len(&llc->pdu_unack_q), -- cgit v1.2.3 From 09a37b3661f6d3cf701950dd6944f24d559449f7 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Fri, 20 Apr 2018 15:57:30 +0200 Subject: tcp: don't read out-of-bounds opsize [ Upstream commit 7e5a206ab686f098367b61aca989f5cdfa8114a3 ] The old code reads the "opsize" variable from out-of-bounds memory (first byte behind the segment) if a broken TCP segment ends directly after an opcode that is neither EOL nor NOP. The result of the read isn't used for anything, so the worst thing that could theoretically happen is a pagefault; and since the physmap is usually mostly contiguous, even that seems pretty unlikely. The following C reproducer triggers the uninitialized read - however, you can't actually see anything happen unless you put something like a pr_warn() in tcp_parse_md5sig_option() to print the opsize. ==================================== #define _GNU_SOURCE #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include void systemf(const char *command, ...) { char *full_command; va_list ap; va_start(ap, command); if (vasprintf(&full_command, command, ap) == -1) err(1, "vasprintf"); va_end(ap); printf("systemf: <<<%s>>>\n", full_command); system(full_command); } char *devname; int tun_alloc(char *name) { int fd = open("/dev/net/tun", O_RDWR); if (fd == -1) err(1, "open tun dev"); static struct ifreq req = { .ifr_flags = IFF_TUN|IFF_NO_PI }; strcpy(req.ifr_name, name); if (ioctl(fd, TUNSETIFF, &req)) err(1, "TUNSETIFF"); devname = req.ifr_name; printf("device name: %s\n", devname); return fd; } #define IPADDR(a,b,c,d) (((a)<<0)+((b)<<8)+((c)<<16)+((d)<<24)) void sum_accumulate(unsigned int *sum, void *data, int len) { assert((len&2)==0); for (int i=0; i> 16) + (sum & 0xffff); sum = (sum >> 16) + (sum & 0xffff); return htons(~sum); } void fix_ip_sum(struct iphdr *ip) { unsigned int sum = 0; sum_accumulate(&sum, ip, sizeof(*ip)); ip->check = sum_final(sum); } void fix_tcp_sum(struct iphdr *ip, struct tcphdr *tcp) { unsigned int sum = 0; struct { unsigned int saddr; unsigned int daddr; unsigned char pad; unsigned char proto_num; unsigned short tcp_len; } fakehdr = { .saddr = ip->saddr, .daddr = ip->daddr, .proto_num = ip->protocol, .tcp_len = htons(ntohs(ip->tot_len) - ip->ihl*4) }; sum_accumulate(&sum, &fakehdr, sizeof(fakehdr)); sum_accumulate(&sum, tcp, tcp->doff*4); tcp->check = sum_final(sum); } int main(void) { int tun_fd = tun_alloc("inject_dev%d"); systemf("ip link set %s up", devname); systemf("ip addr add 192.168.42.1/24 dev %s", devname); struct { struct iphdr ip; struct tcphdr tcp; unsigned char tcp_opts[20]; } __attribute__((packed)) syn_packet = { .ip = { .ihl = sizeof(struct iphdr)/4, .version = 4, .tot_len = htons(sizeof(syn_packet)), .ttl = 30, .protocol = IPPROTO_TCP, /* FIXUP check */ .saddr = IPADDR(192,168,42,2), .daddr = IPADDR(192,168,42,1) }, .tcp = { .source = htons(1), .dest = htons(1337), .seq = 0x12345678, .doff = (sizeof(syn_packet.tcp)+sizeof(syn_packet.tcp_opts))/4, .syn = 1, .window = htons(64), .check = 0 /*FIXUP*/ }, .tcp_opts = { /* INVALID: trailing MD5SIG opcode after NOPs */ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 19 } }; fix_ip_sum(&syn_packet.ip); fix_tcp_sum(&syn_packet.ip, &syn_packet.tcp); while (1) { int write_res = write(tun_fd, &syn_packet, sizeof(syn_packet)); if (write_res != sizeof(syn_packet)) err(1, "packet write failed"); } } ==================================== Fixes: cfb6eeb4c860 ("[TCP]: MD5 Signature Option (RFC2385) support.") Signed-off-by: Jann Horn Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_input.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 96115d1e0d90..ed018760502e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3869,11 +3869,8 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th) int length = (th->doff << 2) - sizeof(*th); const u8 *ptr = (const u8 *)(th + 1); - /* If the TCP option is too short, we can short cut */ - if (length < TCPOLEN_MD5SIG) - return NULL; - - while (length > 0) { + /* If not enough data remaining, we can short cut */ + while (length >= TCPOLEN_MD5SIG) { int opcode = *ptr++; int opsize; -- cgit v1.2.3 From 183f20fb01dcbc1e4b1d821c83e37d3fff144893 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Mon, 23 Apr 2018 17:37:03 -0400 Subject: packet: fix bitfield update race [ Upstream commit a6361f0ca4b25460f2cdf3235ebe8115f622901e ] Updates to the bitfields in struct packet_sock are not atomic. Serialize these read-modify-write cycles. Move po->running into a separate variable. Its writes are protected by po->bind_lock (except for one startup case at packet_create). Also replace a textual precondition warning with lockdep annotation. All others are set only in packet_setsockopt. Serialize these updates by holding the socket lock. Analogous to other field updates, also hold the lock when testing whether a ring is active (pg_vec). Fixes: 8dc419447415 ("[PACKET]: Add optional checksum computation for recvmsg") Reported-by: DaeRyong Jeong Reported-by: Byoungyoung Lee Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/packet/af_packet.c | 60 ++++++++++++++++++++++++++++++++++++-------------- net/packet/internal.h | 10 ++++----- 2 files changed, 49 insertions(+), 21 deletions(-) (limited to 'net') diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 92ca3e106c2b..ad3cd675efd5 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -332,11 +332,11 @@ static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb) skb_set_queue_mapping(skb, queue_index); } -/* register_prot_hook must be invoked with the po->bind_lock held, +/* __register_prot_hook must be invoked through register_prot_hook * or from a context in which asynchronous accesses to the packet * socket is not possible (packet_create()). */ -static void register_prot_hook(struct sock *sk) +static void __register_prot_hook(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); @@ -351,8 +351,13 @@ static void register_prot_hook(struct sock *sk) } } -/* {,__}unregister_prot_hook() must be invoked with the po->bind_lock - * held. If the sync parameter is true, we will temporarily drop +static void register_prot_hook(struct sock *sk) +{ + lockdep_assert_held_once(&pkt_sk(sk)->bind_lock); + __register_prot_hook(sk); +} + +/* If the sync parameter is true, we will temporarily drop * the po->bind_lock and do a synchronize_net to make sure no * asynchronous packet processing paths still refer to the elements * of po->prot_hook. If the sync parameter is false, it is the @@ -362,6 +367,8 @@ static void __unregister_prot_hook(struct sock *sk, bool sync) { struct packet_sock *po = pkt_sk(sk); + lockdep_assert_held_once(&po->bind_lock); + po->running = 0; if (po->fanout) @@ -3134,7 +3141,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, if (proto) { po->prot_hook.type = proto; - register_prot_hook(sk); + __register_prot_hook(sk); } mutex_lock(&net->packet.sklist_lock); @@ -3653,12 +3660,18 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) - return -EBUSY; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; - po->tp_loss = !!val; - return 0; + + lock_sock(sk); + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { + ret = -EBUSY; + } else { + po->tp_loss = !!val; + ret = 0; + } + release_sock(sk); + return ret; } case PACKET_AUXDATA: { @@ -3669,7 +3682,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; + lock_sock(sk); po->auxdata = !!val; + release_sock(sk); return 0; } case PACKET_ORIGDEV: @@ -3681,7 +3696,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; + lock_sock(sk); po->origdev = !!val; + release_sock(sk); return 0; } case PACKET_VNET_HDR: @@ -3690,15 +3707,20 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (sock->type != SOCK_RAW) return -EINVAL; - if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) - return -EBUSY; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; - po->has_vnet_hdr = !!val; - return 0; + lock_sock(sk); + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { + ret = -EBUSY; + } else { + po->has_vnet_hdr = !!val; + ret = 0; + } + release_sock(sk); + return ret; } case PACKET_TIMESTAMP: { @@ -3736,11 +3758,17 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) - return -EBUSY; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; - po->tp_tx_has_off = !!val; + + lock_sock(sk); + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { + ret = -EBUSY; + } else { + po->tp_tx_has_off = !!val; + ret = 0; + } + release_sock(sk); return 0; } case PACKET_QDISC_BYPASS: diff --git a/net/packet/internal.h b/net/packet/internal.h index d55bfc34d6b3..1309e2a7baad 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -109,10 +109,12 @@ struct packet_sock { int copy_thresh; spinlock_t bind_lock; struct mutex pg_vec_lock; - unsigned int running:1, /* prot_hook is attached*/ - auxdata:1, + unsigned int running; /* bind_lock must be held */ + unsigned int auxdata:1, /* writer must hold sock lock */ origdev:1, - has_vnet_hdr:1; + has_vnet_hdr:1, + tp_loss:1, + tp_tx_has_off:1; int pressure; int ifindex; /* bound device */ __be16 num; @@ -122,8 +124,6 @@ struct packet_sock { enum tpacket_versions tp_version; unsigned int tp_hdrlen; unsigned int tp_reserve; - unsigned int tp_loss:1; - unsigned int tp_tx_has_off:1; unsigned int tp_tstamp; struct net_device __rcu *cached_dev; int (*xmit)(struct sk_buff *skb); -- cgit v1.2.3 From 3f74460e5b3333e49bc175ef3eab175cb42c0ce0 Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Tue, 17 Apr 2018 18:46:14 +0900 Subject: vlan: Fix reading memory beyond skb->tail in skb_vlan_tagged_multi [ Upstream commit 7ce2367254e84753bceb07327aaf5c953cfce117 ] Syzkaller spotted an old bug which leads to reading skb beyond tail by 4 bytes on vlan tagged packets. This is caused because skb_vlan_tagged_multi() did not check skb_headlen. BUG: KMSAN: uninit-value in eth_type_vlan include/linux/if_vlan.h:283 [inline] BUG: KMSAN: uninit-value in skb_vlan_tagged_multi include/linux/if_vlan.h:656 [inline] BUG: KMSAN: uninit-value in vlan_features_check include/linux/if_vlan.h:672 [inline] BUG: KMSAN: uninit-value in dflt_features_check net/core/dev.c:2949 [inline] BUG: KMSAN: uninit-value in netif_skb_features+0xd1b/0xdc0 net/core/dev.c:3009 CPU: 1 PID: 3582 Comm: syzkaller435149 Not tainted 4.16.0+ #82 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x185/0x1d0 lib/dump_stack.c:53 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676 eth_type_vlan include/linux/if_vlan.h:283 [inline] skb_vlan_tagged_multi include/linux/if_vlan.h:656 [inline] vlan_features_check include/linux/if_vlan.h:672 [inline] dflt_features_check net/core/dev.c:2949 [inline] netif_skb_features+0xd1b/0xdc0 net/core/dev.c:3009 validate_xmit_skb+0x89/0x1320 net/core/dev.c:3084 __dev_queue_xmit+0x1cb2/0x2b60 net/core/dev.c:3549 dev_queue_xmit+0x4b/0x60 net/core/dev.c:3590 packet_snd net/packet/af_packet.c:2944 [inline] packet_sendmsg+0x7c57/0x8a10 net/packet/af_packet.c:2969 sock_sendmsg_nosec net/socket.c:630 [inline] sock_sendmsg net/socket.c:640 [inline] sock_write_iter+0x3b9/0x470 net/socket.c:909 do_iter_readv_writev+0x7bb/0x970 include/linux/fs.h:1776 do_iter_write+0x30d/0xd40 fs/read_write.c:932 vfs_writev fs/read_write.c:977 [inline] do_writev+0x3c9/0x830 fs/read_write.c:1012 SYSC_writev+0x9b/0xb0 fs/read_write.c:1085 SyS_writev+0x56/0x80 fs/read_write.c:1082 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 RIP: 0033:0x43ffa9 RSP: 002b:00007fff2cff3948 EFLAGS: 00000217 ORIG_RAX: 0000000000000014 RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 000000000043ffa9 RDX: 0000000000000001 RSI: 0000000020000080 RDI: 0000000000000003 RBP: 00000000006cb018 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000217 R12: 00000000004018d0 R13: 0000000000401960 R14: 0000000000000000 R15: 0000000000000000 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline] kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188 kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314 kmsan_slab_alloc+0x11/0x20 mm/kmsan/kmsan.c:321 slab_post_alloc_hook mm/slab.h:445 [inline] slab_alloc_node mm/slub.c:2737 [inline] __kmalloc_node_track_caller+0xaed/0x11c0 mm/slub.c:4369 __kmalloc_reserve net/core/skbuff.c:138 [inline] __alloc_skb+0x2cf/0x9f0 net/core/skbuff.c:206 alloc_skb include/linux/skbuff.h:984 [inline] alloc_skb_with_frags+0x1d4/0xb20 net/core/skbuff.c:5234 sock_alloc_send_pskb+0xb56/0x1190 net/core/sock.c:2085 packet_alloc_skb net/packet/af_packet.c:2803 [inline] packet_snd net/packet/af_packet.c:2894 [inline] packet_sendmsg+0x6444/0x8a10 net/packet/af_packet.c:2969 sock_sendmsg_nosec net/socket.c:630 [inline] sock_sendmsg net/socket.c:640 [inline] sock_write_iter+0x3b9/0x470 net/socket.c:909 do_iter_readv_writev+0x7bb/0x970 include/linux/fs.h:1776 do_iter_write+0x30d/0xd40 fs/read_write.c:932 vfs_writev fs/read_write.c:977 [inline] do_writev+0x3c9/0x830 fs/read_write.c:1012 SYSC_writev+0x9b/0xb0 fs/read_write.c:1085 SyS_writev+0x56/0x80 fs/read_write.c:1082 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 Fixes: 58e998c6d239 ("offloading: Force software GSO for multiple vlan tags.") Reported-and-tested-by: syzbot+0bbe42c764feafa82c5a@syzkaller.appspotmail.com Signed-off-by: Toshiaki Makita Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/core/dev.c b/net/core/dev.c index dc63c37d5301..3bcbf931a910 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2706,7 +2706,7 @@ netdev_features_t passthru_features_check(struct sk_buff *skb, } EXPORT_SYMBOL(passthru_features_check); -static netdev_features_t dflt_features_check(const struct sk_buff *skb, +static netdev_features_t dflt_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { -- cgit v1.2.3 From 14c81b811aae69641253ae86b83b8eba7677509c Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 12 Apr 2018 14:24:31 +0800 Subject: sctp: do not check port in sctp_inet6_cmp_addr [ Upstream commit 1071ec9d453a38023579714b64a951a2fb982071 ] pf->cmp_addr() is called before binding a v6 address to the sock. It should not check ports, like in sctp_inet_cmp_addr. But sctp_inet6_cmp_addr checks the addr by invoking af(6)->cmp_addr, sctp_v6_cmp_addr where it also compares the ports. This would cause that setsockopt(SCTP_SOCKOPT_BINDX_ADD) could bind multiple duplicated IPv6 addresses after Commit 40b4f0fd74e4 ("sctp: lack the check for ports in sctp_v6_cmp_addr"). This patch is to remove af->cmp_addr called in sctp_inet6_cmp_addr, but do the proper check for both v6 addrs and v4mapped addrs. v1->v2: - define __sctp_v6_cmp_addr to do the common address comparison used for both pf and af v6 cmp_addr. Fixes: 40b4f0fd74e4 ("sctp: lack the check for ports in sctp_v6_cmp_addr") Reported-by: Jianwen Ji Signed-off-by: Xin Long Acked-by: Neil Horman Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/sctp/ipv6.c | 60 ++++++++++++++++++++++++++++----------------------------- 1 file changed, 30 insertions(+), 30 deletions(-) (limited to 'net') diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index edb8514b4e00..1cd7b7e33fa3 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -519,46 +519,49 @@ static void sctp_v6_to_addr(union sctp_addr *addr, struct in6_addr *saddr, addr->v6.sin6_scope_id = 0; } -/* Compare addresses exactly. - * v4-mapped-v6 is also in consideration. - */ -static int sctp_v6_cmp_addr(const union sctp_addr *addr1, - const union sctp_addr *addr2) +static int __sctp_v6_cmp_addr(const union sctp_addr *addr1, + const union sctp_addr *addr2) { if (addr1->sa.sa_family != addr2->sa.sa_family) { if (addr1->sa.sa_family == AF_INET && addr2->sa.sa_family == AF_INET6 && - ipv6_addr_v4mapped(&addr2->v6.sin6_addr)) { - if (addr2->v6.sin6_port == addr1->v4.sin_port && - addr2->v6.sin6_addr.s6_addr32[3] == - addr1->v4.sin_addr.s_addr) - return 1; - } + ipv6_addr_v4mapped(&addr2->v6.sin6_addr) && + addr2->v6.sin6_addr.s6_addr32[3] == + addr1->v4.sin_addr.s_addr) + return 1; + if (addr2->sa.sa_family == AF_INET && addr1->sa.sa_family == AF_INET6 && - ipv6_addr_v4mapped(&addr1->v6.sin6_addr)) { - if (addr1->v6.sin6_port == addr2->v4.sin_port && - addr1->v6.sin6_addr.s6_addr32[3] == - addr2->v4.sin_addr.s_addr) - return 1; - } + ipv6_addr_v4mapped(&addr1->v6.sin6_addr) && + addr1->v6.sin6_addr.s6_addr32[3] == + addr2->v4.sin_addr.s_addr) + return 1; + return 0; } - if (addr1->v6.sin6_port != addr2->v6.sin6_port) - return 0; + if (!ipv6_addr_equal(&addr1->v6.sin6_addr, &addr2->v6.sin6_addr)) return 0; + /* If this is a linklocal address, compare the scope_id. */ - if (ipv6_addr_type(&addr1->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) { - if (addr1->v6.sin6_scope_id && addr2->v6.sin6_scope_id && - (addr1->v6.sin6_scope_id != addr2->v6.sin6_scope_id)) { - return 0; - } - } + if ((ipv6_addr_type(&addr1->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) && + addr1->v6.sin6_scope_id && addr2->v6.sin6_scope_id && + addr1->v6.sin6_scope_id != addr2->v6.sin6_scope_id) + return 0; return 1; } +/* Compare addresses exactly. + * v4-mapped-v6 is also in consideration. + */ +static int sctp_v6_cmp_addr(const union sctp_addr *addr1, + const union sctp_addr *addr2) +{ + return __sctp_v6_cmp_addr(addr1, addr2) && + addr1->v6.sin6_port == addr2->v6.sin6_port; +} + /* Initialize addr struct to INADDR_ANY. */ static void sctp_v6_inaddr_any(union sctp_addr *addr, __be16 port) { @@ -843,8 +846,8 @@ static int sctp_inet6_cmp_addr(const union sctp_addr *addr1, const union sctp_addr *addr2, struct sctp_sock *opt) { - struct sctp_af *af1, *af2; struct sock *sk = sctp_opt2sk(opt); + struct sctp_af *af1, *af2; af1 = sctp_get_af_specific(addr1->sa.sa_family); af2 = sctp_get_af_specific(addr2->sa.sa_family); @@ -860,10 +863,7 @@ static int sctp_inet6_cmp_addr(const union sctp_addr *addr1, if (sctp_is_any(sk, addr1) || sctp_is_any(sk, addr2)) return 1; - if (addr1->sa.sa_family != addr2->sa.sa_family) - return 0; - - return af1->cmp_addr(addr1, addr2); + return __sctp_v6_cmp_addr(addr1, addr2); } /* Verify that the provided sockaddr looks bindable. Common verification, -- cgit v1.2.3 From ddebd5d78238a78aac4051317f456e672308ce9f Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Wed, 18 Apr 2018 11:51:56 -0700 Subject: llc: hold llc_sap before release_sock() [ Upstream commit f7e43672683b097bb074a8fe7af9bc600a23f231 ] syzbot reported we still access llc->sap in llc_backlog_rcv() after it is freed in llc_sap_remove_socket(): 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 llc_conn_ac_send_sabme_cmd_p_set_x+0x3a8/0x460 net/llc/llc_c_ac.c:785 llc_exec_conn_trans_actions net/llc/llc_conn.c:475 [inline] llc_conn_service net/llc/llc_conn.c:400 [inline] llc_conn_state_process+0x4e1/0x13a0 net/llc/llc_conn.c:75 llc_backlog_rcv+0x195/0x1e0 net/llc/llc_conn.c:891 sk_backlog_rcv include/net/sock.h:909 [inline] __release_sock+0x12f/0x3a0 net/core/sock.c:2335 release_sock+0xa4/0x2b0 net/core/sock.c:2850 llc_ui_release+0xc8/0x220 net/llc/af_llc.c:204 llc->sap is refcount'ed and llc_sap_remove_socket() is paired with llc_sap_add_socket(). This can be amended by holding its refcount before llc_sap_remove_socket() and releasing it after release_sock(). Reported-by: Signed-off-by: Cong Wang Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/llc/af_llc.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'net') diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 1e698768aca8..149dd1abdc74 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -187,6 +187,7 @@ static int llc_ui_release(struct socket *sock) { struct sock *sk = sock->sk; struct llc_sock *llc; + struct llc_sap *sap; if (unlikely(sk == NULL)) goto out; @@ -197,9 +198,15 @@ static int llc_ui_release(struct socket *sock) llc->laddr.lsap, llc->daddr.lsap); if (!llc_send_disc(sk)) llc_ui_wait_for_disc(sk, sk->sk_rcvtimeo); + sap = llc->sap; + /* Hold this for release_sock(), so that llc_backlog_rcv() could still + * use it. + */ + llc_sap_hold(sap); if (!sock_flag(sk, SOCK_ZAPPED)) llc_sap_remove_socket(llc->sap, sk); release_sock(sk); + llc_sap_put(sap); if (llc->dev) dev_put(llc->dev); sock_put(sk); -- cgit v1.2.3 From 50083b76de998479d45d3bd0f117a8d27d7b17af Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 19 Apr 2018 21:54:34 -0700 Subject: llc: fix NULL pointer deref for SOCK_ZAPPED [ Upstream commit 3a04ce7130a7e5dad4e78d45d50313747f8c830f ] For SOCK_ZAPPED socket, we don't need to care about llc->sap, so we should just skip these refcount functions in this case. Fixes: f7e43672683b ("llc: hold llc_sap before release_sock()") Reported-by: kernel test robot Signed-off-by: Cong Wang Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/llc/af_llc.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) (limited to 'net') diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 149dd1abdc74..09f2f3471ad6 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -187,7 +187,6 @@ static int llc_ui_release(struct socket *sock) { struct sock *sk = sock->sk; struct llc_sock *llc; - struct llc_sap *sap; if (unlikely(sk == NULL)) goto out; @@ -198,15 +197,19 @@ static int llc_ui_release(struct socket *sock) llc->laddr.lsap, llc->daddr.lsap); if (!llc_send_disc(sk)) llc_ui_wait_for_disc(sk, sk->sk_rcvtimeo); - sap = llc->sap; - /* Hold this for release_sock(), so that llc_backlog_rcv() could still - * use it. - */ - llc_sap_hold(sap); - if (!sock_flag(sk, SOCK_ZAPPED)) + if (!sock_flag(sk, SOCK_ZAPPED)) { + struct llc_sap *sap = llc->sap; + + /* Hold this for release_sock(), so that llc_backlog_rcv() + * could still use it. + */ + llc_sap_hold(sap); llc_sap_remove_socket(llc->sap, sk); - release_sock(sk); - llc_sap_put(sap); + release_sock(sk); + llc_sap_put(sap); + } else { + release_sock(sk); + } if (llc->dev) dev_put(llc->dev); sock_put(sk); -- cgit v1.2.3 From 761b54e09947ac15b0d688ab3ecf430c890b6bfe Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 16 Apr 2018 08:29:42 -0700 Subject: tipc: add policy for TIPC_NLA_NET_ADDR [ Upstream commit ec518f21cb1a1b1f8a516499ea05c60299e04963 ] Before syzbot/KMSAN bites, add the missing policy for TIPC_NLA_NET_ADDR Fixes: 27c21416727a ("tipc: add net set to new netlink api") Signed-off-by: Eric Dumazet Cc: Jon Maloy Cc: Ying Xue Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/tipc/net.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/tipc/net.c b/net/tipc/net.c index 77bf9113c7a7..2763bd369b79 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -44,7 +44,8 @@ static const struct nla_policy tipc_nl_net_policy[TIPC_NLA_NET_MAX + 1] = { [TIPC_NLA_NET_UNSPEC] = { .type = NLA_UNSPEC }, - [TIPC_NLA_NET_ID] = { .type = NLA_U32 } + [TIPC_NLA_NET_ID] = { .type = NLA_U32 }, + [TIPC_NLA_NET_ADDR] = { .type = NLA_U32 }, }; /* -- cgit v1.2.3 From 0eb338b22c800e27af7dc60812d82b76a27d1514 Mon Sep 17 00:00:00 2001 From: Wolfgang Bumiller Date: Thu, 12 Apr 2018 10:46:55 +0200 Subject: net: fix deadlock while clearing neighbor proxy table [ Upstream commit 53b76cdf7e8fecec1d09e38aad2f8579882591a8 ] When coming from ndisc_netdev_event() in net/ipv6/ndisc.c, neigh_ifdown() is called with &nd_tbl, locking this while clearing the proxy neighbor entries when eg. deleting an interface. Calling the table's pndisc_destructor() with the lock still held, however, can cause a deadlock: When a multicast listener is available an IGMP packet of type ICMPV6_MGM_REDUCTION may be sent out. When reaching ip6_finish_output2(), if no neighbor entry for the target address is found, __neigh_create() is called with &nd_tbl, which it'll want to lock. Move the elements into their own list, then unlock the table and perform the destruction. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=199289 Fixes: 6fd6ce2056de ("ipv6: Do not depend on rt->n in ip6_finish_output2().") Signed-off-by: Wolfgang Bumiller Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/core/neighbour.c | 28 ++++++++++++++++++---------- 1 file changed, 18 insertions(+), 10 deletions(-) (limited to 'net') diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 8723cb845919..f60b93627876 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -54,7 +54,8 @@ do { \ static void neigh_timer_handler(unsigned long arg); static void __neigh_notify(struct neighbour *n, int type, int flags); static void neigh_update_notify(struct neighbour *neigh); -static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev); +static int pneigh_ifdown_and_unlock(struct neigh_table *tbl, + struct net_device *dev); #ifdef CONFIG_PROC_FS static const struct file_operations neigh_stat_seq_fops; @@ -254,8 +255,7 @@ int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev) { write_lock_bh(&tbl->lock); neigh_flush_dev(tbl, dev); - pneigh_ifdown(tbl, dev); - write_unlock_bh(&tbl->lock); + pneigh_ifdown_and_unlock(tbl, dev); del_timer_sync(&tbl->proxy_timer); pneigh_queue_purge(&tbl->proxy_queue); @@ -645,9 +645,10 @@ int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey, return -ENOENT; } -static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev) +static int pneigh_ifdown_and_unlock(struct neigh_table *tbl, + struct net_device *dev) { - struct pneigh_entry *n, **np; + struct pneigh_entry *n, **np, *freelist = NULL; u32 h; for (h = 0; h <= PNEIGH_HASHMASK; h++) { @@ -655,16 +656,23 @@ static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev) while ((n = *np) != NULL) { if (!dev || n->dev == dev) { *np = n->next; - if (tbl->pdestructor) - tbl->pdestructor(n); - if (n->dev) - dev_put(n->dev); - kfree(n); + n->next = freelist; + freelist = n; continue; } np = &n->next; } } + write_unlock_bh(&tbl->lock); + while ((n = freelist)) { + freelist = n->next; + n->next = NULL; + if (tbl->pdestructor) + tbl->pdestructor(n); + if (n->dev) + dev_put(n->dev); + kfree(n); + } return -ENOENT; } -- cgit v1.2.3 From 8be2d38bb3579b3da34ff326e6c87e4cb0b740f4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 11 Apr 2018 14:36:28 -0700 Subject: tcp: md5: reject TCP_MD5SIG or TCP_MD5SIG_EXT on established sockets [ Upstream commit 7212303268918b9a203aebeacfdbd83b5e87b20d ] syzbot/KMSAN reported an uninit-value in tcp_parse_options() [1] I believe this was caused by a TCP_MD5SIG being set on live flow. This is highly unexpected, since TCP option space is limited. For instance, presence of TCP MD5 option automatically disables TCP TimeStamp option at SYN/SYNACK time, which we can not do once flow has been established. Really, adding/deleting an MD5 key only makes sense on sockets in CLOSE or LISTEN state. [1] BUG: KMSAN: uninit-value in tcp_parse_options+0xd74/0x1a30 net/ipv4/tcp_input.c:3720 CPU: 1 PID: 6177 Comm: syzkaller192004 Not tainted 4.16.0+ #83 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x185/0x1d0 lib/dump_stack.c:53 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676 tcp_parse_options+0xd74/0x1a30 net/ipv4/tcp_input.c:3720 tcp_fast_parse_options net/ipv4/tcp_input.c:3858 [inline] tcp_validate_incoming+0x4f1/0x2790 net/ipv4/tcp_input.c:5184 tcp_rcv_established+0xf60/0x2bb0 net/ipv4/tcp_input.c:5453 tcp_v4_do_rcv+0x6cd/0xd90 net/ipv4/tcp_ipv4.c:1469 sk_backlog_rcv include/net/sock.h:908 [inline] __release_sock+0x2d6/0x680 net/core/sock.c:2271 release_sock+0x97/0x2a0 net/core/sock.c:2786 tcp_sendmsg+0xd6/0x100 net/ipv4/tcp.c:1464 inet_sendmsg+0x48d/0x740 net/ipv4/af_inet.c:764 sock_sendmsg_nosec net/socket.c:630 [inline] sock_sendmsg net/socket.c:640 [inline] SYSC_sendto+0x6c3/0x7e0 net/socket.c:1747 SyS_sendto+0x8a/0xb0 net/socket.c:1715 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 RIP: 0033:0x448fe9 RSP: 002b:00007fd472c64d38 EFLAGS: 00000216 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 00000000006e5a30 RCX: 0000000000448fe9 RDX: 000000000000029f RSI: 0000000020a88f88 RDI: 0000000000000004 RBP: 00000000006e5a34 R08: 0000000020e68000 R09: 0000000000000010 R10: 00000000200007fd R11: 0000000000000216 R12: 0000000000000000 R13: 00007fff074899ef R14: 00007fd472c659c0 R15: 0000000000000009 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline] kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188 kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314 kmsan_slab_alloc+0x11/0x20 mm/kmsan/kmsan.c:321 slab_post_alloc_hook mm/slab.h:445 [inline] slab_alloc_node mm/slub.c:2737 [inline] __kmalloc_node_track_caller+0xaed/0x11c0 mm/slub.c:4369 __kmalloc_reserve net/core/skbuff.c:138 [inline] __alloc_skb+0x2cf/0x9f0 net/core/skbuff.c:206 alloc_skb include/linux/skbuff.h:984 [inline] tcp_send_ack+0x18c/0x910 net/ipv4/tcp_output.c:3624 __tcp_ack_snd_check net/ipv4/tcp_input.c:5040 [inline] tcp_ack_snd_check net/ipv4/tcp_input.c:5053 [inline] tcp_rcv_established+0x2103/0x2bb0 net/ipv4/tcp_input.c:5469 tcp_v4_do_rcv+0x6cd/0xd90 net/ipv4/tcp_ipv4.c:1469 sk_backlog_rcv include/net/sock.h:908 [inline] __release_sock+0x2d6/0x680 net/core/sock.c:2271 release_sock+0x97/0x2a0 net/core/sock.c:2786 tcp_sendmsg+0xd6/0x100 net/ipv4/tcp.c:1464 inet_sendmsg+0x48d/0x740 net/ipv4/af_inet.c:764 sock_sendmsg_nosec net/socket.c:630 [inline] sock_sendmsg net/socket.c:640 [inline] SYSC_sendto+0x6c3/0x7e0 net/socket.c:1747 SyS_sendto+0x8a/0xb0 net/socket.c:1715 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 Fixes: cfb6eeb4c860 ("[TCP]: MD5 Signature Option (RFC2385) support.") Signed-off-by: Eric Dumazet Reported-by: syzbot Acked-by: Yuchung Cheng Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 23d77ff1da59..82d2b55c953a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2589,8 +2589,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level, #ifdef CONFIG_TCP_MD5SIG case TCP_MD5SIG: - /* Read the IP->Key mappings from userspace */ - err = tp->af_specific->md5_parse(sk, optval, optlen); + if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) + err = tp->af_specific->md5_parse(sk, optval, optlen); + else + err = -EINVAL; break; #endif case TCP_USER_TIMEOUT: -- cgit v1.2.3 From ab3828313863194e445d439ce7eae65563b774bd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 15 Apr 2018 17:52:04 -0700 Subject: net: af_packet: fix race in PACKET_{R|T}X_RING [ Upstream commit 5171b37d959641bbc619781caf62e61f7b940871 ] In order to remove the race caught by syzbot [1], we need to lock the socket before using po->tp_version as this could change under us otherwise. This means lock_sock() and release_sock() must be done by packet_set_ring() callers. [1] : BUG: KMSAN: uninit-value in packet_set_ring+0x1254/0x3870 net/packet/af_packet.c:4249 CPU: 0 PID: 20195 Comm: syzkaller707632 Not tainted 4.16.0+ #83 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x185/0x1d0 lib/dump_stack.c:53 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676 packet_set_ring+0x1254/0x3870 net/packet/af_packet.c:4249 packet_setsockopt+0x12c6/0x5a90 net/packet/af_packet.c:3662 SYSC_setsockopt+0x4b8/0x570 net/socket.c:1849 SyS_setsockopt+0x76/0xa0 net/socket.c:1828 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 RIP: 0033:0x449099 RSP: 002b:00007f42b5307ce8 EFLAGS: 00000246 ORIG_RAX: 0000000000000036 RAX: ffffffffffffffda RBX: 000000000070003c RCX: 0000000000449099 RDX: 0000000000000005 RSI: 0000000000000107 RDI: 0000000000000003 RBP: 0000000000700038 R08: 000000000000001c R09: 0000000000000000 R10: 00000000200000c0 R11: 0000000000000246 R12: 0000000000000000 R13: 000000000080eecf R14: 00007f42b53089c0 R15: 0000000000000001 Local variable description: ----req_u@packet_setsockopt Variable was created at: packet_setsockopt+0x13f/0x5a90 net/packet/af_packet.c:3612 SYSC_setsockopt+0x4b8/0x570 net/socket.c:1849 Fixes: f6fb8f100b80 ("af-packet: TPACKET_V3 flexible buffer implementation.") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/packet/af_packet.c | 28 ++++++++++++++++++---------- 1 file changed, 18 insertions(+), 10 deletions(-) (limited to 'net') diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index ad3cd675efd5..f165514a4db5 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2899,6 +2899,7 @@ static int packet_release(struct socket *sock) packet_flush_mclist(sk); + lock_sock(sk); if (po->rx_ring.pg_vec) { memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 0); @@ -2908,6 +2909,7 @@ static int packet_release(struct socket *sock) memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 1); } + release_sock(sk); f = fanout_release(sk); @@ -3577,6 +3579,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv union tpacket_req_u req_u; int len; + lock_sock(sk); switch (po->tp_version) { case TPACKET_V1: case TPACKET_V2: @@ -3587,14 +3590,21 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv len = sizeof(req_u.req3); break; } - if (optlen < len) - return -EINVAL; - if (pkt_sk(sk)->has_vnet_hdr) - return -EINVAL; - if (copy_from_user(&req_u.req, optval, len)) - return -EFAULT; - return packet_set_ring(sk, &req_u, 0, - optname == PACKET_TX_RING); + if (optlen < len) { + ret = -EINVAL; + } else { + if (pkt_sk(sk)->has_vnet_hdr) { + ret = -EINVAL; + } else { + if (copy_from_user(&req_u.req, optval, len)) + ret = -EFAULT; + else + ret = packet_set_ring(sk, &req_u, 0, + optname == PACKET_TX_RING); + } + } + release_sock(sk); + return ret; } case PACKET_COPY_THRESH: { @@ -4144,7 +4154,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, /* Added to avoid minimal code churn */ struct tpacket_req *req = &req_u->req; - lock_sock(sk); /* Opening a Tx-ring is NOT supported in TPACKET_V3 */ if (!closing && tx_ring && (po->tp_version > TPACKET_V2)) { WARN(1, "Tx-ring is not supported.\n"); @@ -4280,7 +4289,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, if (pg_vec) free_pg_vec(pg_vec, order, req->tp_block_nr); out: - release_sock(sk); return err; } -- cgit v1.2.3 From b1785e844a02e770d3cb7458a6f15d2e7c1f927b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 22 Apr 2018 18:29:23 -0700 Subject: ipv6: add RTA_TABLE and RTA_PREFSRC to rtm_ipv6_policy [ Upstream commit aa8f8778493c85fff480cdf8b349b1e1dcb5f243 ] KMSAN reported use of uninit-value that I tracked to lack of proper size check on RTA_TABLE attribute. I also believe RTA_PREFSRC lacks a similar check. Fixes: 86872cb57925 ("[IPv6] route: FIB6 configuration using struct fib6_config") Fixes: c3968a857a6b ("ipv6: RTA_PREFSRC support for ipv6 route source address selection") Signed-off-by: Eric Dumazet Reported-by: syzbot Acked-by: David Ahern Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv6/route.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net') diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 99920fcea97c..2f6d8f57fdd4 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2711,6 +2711,7 @@ void rt6_mtu_change(struct net_device *dev, unsigned int mtu) static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_GATEWAY] = { .len = sizeof(struct in6_addr) }, + [RTA_PREFSRC] = { .len = sizeof(struct in6_addr) }, [RTA_OIF] = { .type = NLA_U32 }, [RTA_IIF] = { .type = NLA_U32 }, [RTA_PRIORITY] = { .type = NLA_U32 }, @@ -2719,6 +2720,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_PREF] = { .type = NLA_U8 }, [RTA_ENCAP_TYPE] = { .type = NLA_U16 }, [RTA_ENCAP] = { .type = NLA_NESTED }, + [RTA_TABLE] = { .type = NLA_U32 }, }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, -- cgit v1.2.3