kernel_optimize_test/net/dccp/minisocks.c
Eric Dumazet 62f8f4d906 dccp: fix use-after-free in dccp_feat_activate_values
Dmitry reported crashes in DCCP stack [1]

Problem here is that when I got rid of listener spinlock, I missed the
fact that DCCP stores a complex state in struct dccp_request_sock,
while TCP does not.

Since multiple cpus could access it at the same time, we need to add
protection.

[1]
BUG: KASAN: use-after-free in dccp_feat_activate_values+0x967/0xab0
net/dccp/feat.c:1541 at addr ffff88003713be68
Read of size 8 by task syz-executor2/8457
CPU: 2 PID: 8457 Comm: syz-executor2 Not tainted 4.10.0-rc7+ #127
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:15 [inline]
 dump_stack+0x292/0x398 lib/dump_stack.c:51
 kasan_object_err+0x1c/0x70 mm/kasan/report.c:162
 print_address_description mm/kasan/report.c:200 [inline]
 kasan_report_error mm/kasan/report.c:289 [inline]
 kasan_report.part.1+0x20e/0x4e0 mm/kasan/report.c:311
 kasan_report mm/kasan/report.c:332 [inline]
 __asan_report_load8_noabort+0x29/0x30 mm/kasan/report.c:332
 dccp_feat_activate_values+0x967/0xab0 net/dccp/feat.c:1541
 dccp_create_openreq_child+0x464/0x610 net/dccp/minisocks.c:121
 dccp_v6_request_recv_sock+0x1f6/0x1960 net/dccp/ipv6.c:457
 dccp_check_req+0x335/0x5a0 net/dccp/minisocks.c:186
 dccp_v6_rcv+0x69e/0x1d00 net/dccp/ipv6.c:711
 ip6_input_finish+0x46d/0x17a0 net/ipv6/ip6_input.c:279
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ip6_input+0xdb/0x590 net/ipv6/ip6_input.c:322
 dst_input include/net/dst.h:507 [inline]
 ip6_rcv_finish+0x289/0x890 net/ipv6/ip6_input.c:69
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ipv6_rcv+0x12ec/0x23d0 net/ipv6/ip6_input.c:203
 __netif_receive_skb_core+0x1ae5/0x3400 net/core/dev.c:4190
 __netif_receive_skb+0x2a/0x170 net/core/dev.c:4228
 process_backlog+0xe5/0x6c0 net/core/dev.c:4839
 napi_poll net/core/dev.c:5202 [inline]
 net_rx_action+0xe70/0x1900 net/core/dev.c:5267
 __do_softirq+0x2fb/0xb7d kernel/softirq.c:284
 do_softirq_own_stack+0x1c/0x30 arch/x86/entry/entry_64.S:902
 </IRQ>
 do_softirq.part.17+0x1e8/0x230 kernel/softirq.c:328
 do_softirq kernel/softirq.c:176 [inline]
 __local_bh_enable_ip+0x1f2/0x200 kernel/softirq.c:181
 local_bh_enable include/linux/bottom_half.h:31 [inline]
 rcu_read_unlock_bh include/linux/rcupdate.h:971 [inline]
 ip6_finish_output2+0xbb0/0x23d0 net/ipv6/ip6_output.c:123
 ip6_finish_output+0x302/0x960 net/ipv6/ip6_output.c:148
 NF_HOOK_COND include/linux/netfilter.h:246 [inline]
 ip6_output+0x1cb/0x8d0 net/ipv6/ip6_output.c:162
 ip6_xmit+0xcdf/0x20d0 include/net/dst.h:501
 inet6_csk_xmit+0x320/0x5f0 net/ipv6/inet6_connection_sock.c:179
 dccp_transmit_skb+0xb09/0x1120 net/dccp/output.c:141
 dccp_xmit_packet+0x215/0x760 net/dccp/output.c:280
 dccp_write_xmit+0x168/0x1d0 net/dccp/output.c:362
 dccp_sendmsg+0x79c/0xb10 net/dccp/proto.c:796
 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:744
 sock_sendmsg_nosec net/socket.c:635 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:645
 SYSC_sendto+0x660/0x810 net/socket.c:1687
 SyS_sendto+0x40/0x50 net/socket.c:1655
 entry_SYSCALL_64_fastpath+0x1f/0xc2
RIP: 0033:0x4458b9
RSP: 002b:00007f8ceb77bb58 EFLAGS: 00000282 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 0000000000000017 RCX: 00000000004458b9
RDX: 0000000000000023 RSI: 0000000020e60000 RDI: 0000000000000017
RBP: 00000000006e1b90 R08: 00000000200f9fe1 R09: 0000000000000020
R10: 0000000000008010 R11: 0000000000000282 R12: 00000000007080a8
R13: 0000000000000000 R14: 00007f8ceb77c9c0 R15: 00007f8ceb77c700
Object at ffff88003713be50, in cache kmalloc-64 size: 64
Allocated:
PID = 8446
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
 save_stack+0x43/0xd0 mm/kasan/kasan.c:502
 set_track mm/kasan/kasan.c:514 [inline]
 kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:605
 kmem_cache_alloc_trace+0x82/0x270 mm/slub.c:2738
 kmalloc include/linux/slab.h:490 [inline]
 dccp_feat_entry_new+0x214/0x410 net/dccp/feat.c:467
 dccp_feat_push_change+0x38/0x220 net/dccp/feat.c:487
 __feat_register_sp+0x223/0x2f0 net/dccp/feat.c:741
 dccp_feat_propagate_ccid+0x22b/0x2b0 net/dccp/feat.c:949
 dccp_feat_server_ccid_dependencies+0x1b3/0x250 net/dccp/feat.c:1012
 dccp_make_response+0x1f1/0xc90 net/dccp/output.c:423
 dccp_v6_send_response+0x4ec/0xc20 net/dccp/ipv6.c:217
 dccp_v6_conn_request+0xaba/0x11b0 net/dccp/ipv6.c:377
 dccp_rcv_state_process+0x51e/0x1650 net/dccp/input.c:606
 dccp_v6_do_rcv+0x213/0x350 net/dccp/ipv6.c:632
 sk_backlog_rcv include/net/sock.h:893 [inline]
 __sk_receive_skb+0x36f/0xcc0 net/core/sock.c:479
 dccp_v6_rcv+0xba5/0x1d00 net/dccp/ipv6.c:742
 ip6_input_finish+0x46d/0x17a0 net/ipv6/ip6_input.c:279
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ip6_input+0xdb/0x590 net/ipv6/ip6_input.c:322
 dst_input include/net/dst.h:507 [inline]
 ip6_rcv_finish+0x289/0x890 net/ipv6/ip6_input.c:69
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ipv6_rcv+0x12ec/0x23d0 net/ipv6/ip6_input.c:203
 __netif_receive_skb_core+0x1ae5/0x3400 net/core/dev.c:4190
 __netif_receive_skb+0x2a/0x170 net/core/dev.c:4228
 process_backlog+0xe5/0x6c0 net/core/dev.c:4839
 napi_poll net/core/dev.c:5202 [inline]
 net_rx_action+0xe70/0x1900 net/core/dev.c:5267
 __do_softirq+0x2fb/0xb7d kernel/softirq.c:284
Freed:
PID = 15
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
 save_stack+0x43/0xd0 mm/kasan/kasan.c:502
 set_track mm/kasan/kasan.c:514 [inline]
 kasan_slab_free+0x73/0xc0 mm/kasan/kasan.c:578
 slab_free_hook mm/slub.c:1355 [inline]
 slab_free_freelist_hook mm/slub.c:1377 [inline]
 slab_free mm/slub.c:2954 [inline]
 kfree+0xe8/0x2b0 mm/slub.c:3874
 dccp_feat_entry_destructor.part.4+0x48/0x60 net/dccp/feat.c:418
 dccp_feat_entry_destructor net/dccp/feat.c:416 [inline]
 dccp_feat_list_pop net/dccp/feat.c:541 [inline]
 dccp_feat_activate_values+0x57f/0xab0 net/dccp/feat.c:1543
 dccp_create_openreq_child+0x464/0x610 net/dccp/minisocks.c:121
 dccp_v6_request_recv_sock+0x1f6/0x1960 net/dccp/ipv6.c:457
 dccp_check_req+0x335/0x5a0 net/dccp/minisocks.c:186
 dccp_v6_rcv+0x69e/0x1d00 net/dccp/ipv6.c:711
 ip6_input_finish+0x46d/0x17a0 net/ipv6/ip6_input.c:279
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ip6_input+0xdb/0x590 net/ipv6/ip6_input.c:322
 dst_input include/net/dst.h:507 [inline]
 ip6_rcv_finish+0x289/0x890 net/ipv6/ip6_input.c:69
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ipv6_rcv+0x12ec/0x23d0 net/ipv6/ip6_input.c:203
 __netif_receive_skb_core+0x1ae5/0x3400 net/core/dev.c:4190
 __netif_receive_skb+0x2a/0x170 net/core/dev.c:4228
 process_backlog+0xe5/0x6c0 net/core/dev.c:4839
 napi_poll net/core/dev.c:5202 [inline]
 net_rx_action+0xe70/0x1900 net/core/dev.c:5267
 __do_softirq+0x2fb/0xb7d kernel/softirq.c:284
Memory state around the buggy address:
 ffff88003713bd00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff88003713bd80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff88003713be00: fc fc fc fc fc fc fc fc fc fc fb fb fb fb fb fb
                                                          ^

Fixes: 079096f103 ("tcp/dccp: install syn_recv requests into ehash table")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Tested-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-07 14:15:27 -08:00

267 lines
7.2 KiB
C

/*
* net/dccp/minisocks.c
*
* An implementation of the DCCP protocol
* Arnaldo Carvalho de Melo <acme@conectiva.com.br>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/dccp.h>
#include <linux/gfp.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/timer.h>
#include <net/sock.h>
#include <net/xfrm.h>
#include <net/inet_timewait_sock.h>
#include "ackvec.h"
#include "ccid.h"
#include "dccp.h"
#include "feat.h"
struct inet_timewait_death_row dccp_death_row = {
.sysctl_max_tw_buckets = NR_FILE * 2,
.hashinfo = &dccp_hashinfo,
};
EXPORT_SYMBOL_GPL(dccp_death_row);
void dccp_time_wait(struct sock *sk, int state, int timeo)
{
struct inet_timewait_sock *tw;
tw = inet_twsk_alloc(sk, &dccp_death_row, state);
if (tw != NULL) {
const struct inet_connection_sock *icsk = inet_csk(sk);
const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1);
#if IS_ENABLED(CONFIG_IPV6)
if (tw->tw_family == PF_INET6) {
tw->tw_v6_daddr = sk->sk_v6_daddr;
tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
tw->tw_ipv6only = sk->sk_ipv6only;
}
#endif
/* Get the TIME_WAIT timeout firing. */
if (timeo < rto)
timeo = rto;
tw->tw_timeout = DCCP_TIMEWAIT_LEN;
if (state == DCCP_TIME_WAIT)
timeo = DCCP_TIMEWAIT_LEN;
inet_twsk_schedule(tw, timeo);
/* Linkage updates. */
__inet_twsk_hashdance(tw, sk, &dccp_hashinfo);
inet_twsk_put(tw);
} else {
/* Sorry, if we're out of memory, just CLOSE this
* socket up. We've got bigger problems than
* non-graceful socket closings.
*/
DCCP_WARN("time wait bucket table overflow\n");
}
dccp_done(sk);
}
struct sock *dccp_create_openreq_child(const struct sock *sk,
const struct request_sock *req,
const struct sk_buff *skb)
{
/*
* Step 3: Process LISTEN state
*
* (* Generate a new socket and switch to that socket *)
* Set S := new socket for this port pair
*/
struct sock *newsk = inet_csk_clone_lock(sk, req, GFP_ATOMIC);
if (newsk != NULL) {
struct dccp_request_sock *dreq = dccp_rsk(req);
struct inet_connection_sock *newicsk = inet_csk(newsk);
struct dccp_sock *newdp = dccp_sk(newsk);
newdp->dccps_role = DCCP_ROLE_SERVER;
newdp->dccps_hc_rx_ackvec = NULL;
newdp->dccps_service_list = NULL;
newdp->dccps_service = dreq->dreq_service;
newdp->dccps_timestamp_echo = dreq->dreq_timestamp_echo;
newdp->dccps_timestamp_time = dreq->dreq_timestamp_time;
newicsk->icsk_rto = DCCP_TIMEOUT_INIT;
INIT_LIST_HEAD(&newdp->dccps_featneg);
/*
* Step 3: Process LISTEN state
*
* Choose S.ISS (initial seqno) or set from Init Cookies
* Initialize S.GAR := S.ISS
* Set S.ISR, S.GSR from packet (or Init Cookies)
*
* Setting AWL/AWH and SWL/SWH happens as part of the feature
* activation below, as these windows all depend on the local
* and remote Sequence Window feature values (7.5.2).
*/
newdp->dccps_iss = dreq->dreq_iss;
newdp->dccps_gss = dreq->dreq_gss;
newdp->dccps_gar = newdp->dccps_iss;
newdp->dccps_isr = dreq->dreq_isr;
newdp->dccps_gsr = dreq->dreq_gsr;
/*
* Activate features: initialise CCIDs, sequence windows etc.
*/
if (dccp_feat_activate_values(newsk, &dreq->dreq_featneg)) {
sk_free_unlock_clone(newsk);
return NULL;
}
dccp_init_xmit_timers(newsk);
__DCCP_INC_STATS(DCCP_MIB_PASSIVEOPENS);
}
return newsk;
}
EXPORT_SYMBOL_GPL(dccp_create_openreq_child);
/*
* Process an incoming packet for RESPOND sockets represented
* as an request_sock.
*/
struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
struct request_sock *req)
{
struct sock *child = NULL;
struct dccp_request_sock *dreq = dccp_rsk(req);
bool own_req;
/* TCP/DCCP listeners became lockless.
* DCCP stores complex state in its request_sock, so we need
* a protection for them, now this code runs without being protected
* by the parent (listener) lock.
*/
spin_lock_bh(&dreq->dreq_lock);
/* Check for retransmitted REQUEST */
if (dccp_hdr(skb)->dccph_type == DCCP_PKT_REQUEST) {
if (after48(DCCP_SKB_CB(skb)->dccpd_seq, dreq->dreq_gsr)) {
dccp_pr_debug("Retransmitted REQUEST\n");
dreq->dreq_gsr = DCCP_SKB_CB(skb)->dccpd_seq;
/*
* Send another RESPONSE packet
* To protect against Request floods, increment retrans
* counter (backoff, monitored by dccp_response_timer).
*/
inet_rtx_syn_ack(sk, req);
}
/* Network Duplicate, discard packet */
goto out;
}
DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_PACKET_ERROR;
if (dccp_hdr(skb)->dccph_type != DCCP_PKT_ACK &&
dccp_hdr(skb)->dccph_type != DCCP_PKT_DATAACK)
goto drop;
/* Invalid ACK */
if (!between48(DCCP_SKB_CB(skb)->dccpd_ack_seq,
dreq->dreq_iss, dreq->dreq_gss)) {
dccp_pr_debug("Invalid ACK number: ack_seq=%llu, "
"dreq_iss=%llu, dreq_gss=%llu\n",
(unsigned long long)
DCCP_SKB_CB(skb)->dccpd_ack_seq,
(unsigned long long) dreq->dreq_iss,
(unsigned long long) dreq->dreq_gss);
goto drop;
}
if (dccp_parse_options(sk, dreq, skb))
goto drop;
child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL,
req, &own_req);
if (child) {
child = inet_csk_complete_hashdance(sk, child, req, own_req);
goto out;
}
DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY;
drop:
if (dccp_hdr(skb)->dccph_type != DCCP_PKT_RESET)
req->rsk_ops->send_reset(sk, skb);
inet_csk_reqsk_queue_drop(sk, req);
out:
spin_unlock_bh(&dreq->dreq_lock);
return child;
}
EXPORT_SYMBOL_GPL(dccp_check_req);
/*
* Queue segment on the new socket if the new socket is active,
* otherwise we just shortcircuit this and continue with
* the new socket.
*/
int dccp_child_process(struct sock *parent, struct sock *child,
struct sk_buff *skb)
{
int ret = 0;
const int state = child->sk_state;
if (!sock_owned_by_user(child)) {
ret = dccp_rcv_state_process(child, skb, dccp_hdr(skb),
skb->len);
/* Wakeup parent, send SIGIO */
if (state == DCCP_RESPOND && child->sk_state != state)
parent->sk_data_ready(parent);
} else {
/* Alas, it is possible again, because we do lookup
* in main socket hash table and lock on listening
* socket does not protect us more.
*/
__sk_add_backlog(child, skb);
}
bh_unlock_sock(child);
sock_put(child);
return ret;
}
EXPORT_SYMBOL_GPL(dccp_child_process);
void dccp_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
struct request_sock *rsk)
{
DCCP_BUG("DCCP-ACK packets are never sent in LISTEN/RESPOND state");
}
EXPORT_SYMBOL_GPL(dccp_reqsk_send_ack);
int dccp_reqsk_init(struct request_sock *req,
struct dccp_sock const *dp, struct sk_buff const *skb)
{
struct dccp_request_sock *dreq = dccp_rsk(req);
spin_lock_init(&dreq->dreq_lock);
inet_rsk(req)->ir_rmt_port = dccp_hdr(skb)->dccph_sport;
inet_rsk(req)->ir_num = ntohs(dccp_hdr(skb)->dccph_dport);
inet_rsk(req)->acked = 0;
dreq->dreq_timestamp_echo = 0;
/* inherit feature negotiation options from listening socket */
return dccp_feat_clone_list(&dp->dccps_featneg, &dreq->dreq_featneg);
}
EXPORT_SYMBOL_GPL(dccp_reqsk_init);