linux-brain/net/sctp/endpointola.c

411 lines
10 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/* SCTP kernel implementation
* Copyright (c) 1999-2000 Cisco, Inc.
* Copyright (c) 1999-2001 Motorola, Inc.
* Copyright (c) 2001-2002 International Business Machines, Corp.
* Copyright (c) 2001 Intel Corp.
* Copyright (c) 2001 Nokia, Inc.
* Copyright (c) 2001 La Monte H.P. Yarroll
*
* This file is part of the SCTP kernel implementation
*
* This abstraction represents an SCTP endpoint.
*
* Please send any bug reports or fixes you make to the
* email address(es):
* lksctp developers <linux-sctp@vger.kernel.org>
*
* Written or modified by:
* La Monte H.P. Yarroll <piggy@acm.org>
* Karl Knutson <karl@athena.chicago.il.us>
* Jon Grimm <jgrimm@austin.ibm.com>
* Daisy Chang <daisyc@us.ibm.com>
* Dajiang Zhang <dajiang.zhang@nokia.com>
*/
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/in.h>
#include <linux/random.h> /* get_random_bytes() */
#include <net/sock.h>
#include <net/ipv6.h>
#include <net/sctp/sctp.h>
#include <net/sctp/sm.h>
/* Forward declarations for internal helpers. */
static void sctp_endpoint_bh_rcv(struct work_struct *work);
/*
* Initialize the base fields of the endpoint structure.
*/
static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
struct sock *sk,
gfp_t gfp)
{
struct net *net = sock_net(sk);
struct sctp_shared_key *null_key;
ep->digest = kzalloc(SCTP_SIGNATURE_SIZE, gfp);
if (!ep->digest)
return NULL;
ep->asconf_enable = net->sctp.addip_enable;
net: sctp: cache auth_enable per endpoint Currently, it is possible to create an SCTP socket, then switch auth_enable via sysctl setting to 1 and crash the system on connect: Oops[#1]: CPU: 0 PID: 0 Comm: swapper Not tainted 3.14.1-mipsgit-20140415 #1 task: ffffffff8056ce80 ti: ffffffff8055c000 task.ti: ffffffff8055c000 [...] Call Trace: [<ffffffff8043c4e8>] sctp_auth_asoc_set_default_hmac+0x68/0x80 [<ffffffff8042b300>] sctp_process_init+0x5e0/0x8a4 [<ffffffff8042188c>] sctp_sf_do_5_1B_init+0x234/0x34c [<ffffffff804228c8>] sctp_do_sm+0xb4/0x1e8 [<ffffffff80425a08>] sctp_endpoint_bh_rcv+0x1c4/0x214 [<ffffffff8043af68>] sctp_rcv+0x588/0x630 [<ffffffff8043e8e8>] sctp6_rcv+0x10/0x24 [<ffffffff803acb50>] ip6_input+0x2c0/0x440 [<ffffffff8030fc00>] __netif_receive_skb_core+0x4a8/0x564 [<ffffffff80310650>] process_backlog+0xb4/0x18c [<ffffffff80313cbc>] net_rx_action+0x12c/0x210 [<ffffffff80034254>] __do_softirq+0x17c/0x2ac [<ffffffff800345e0>] irq_exit+0x54/0xb0 [<ffffffff800075a4>] ret_from_irq+0x0/0x4 [<ffffffff800090ec>] rm7k_wait_irqoff+0x24/0x48 [<ffffffff8005e388>] cpu_startup_entry+0xc0/0x148 [<ffffffff805a88b0>] start_kernel+0x37c/0x398 Code: dd0900b8 000330f8 0126302d <dcc60000> 50c0fff1 0047182a a48306a0 03e00008 00000000 ---[ end trace b530b0551467f2fd ]--- Kernel panic - not syncing: Fatal exception in interrupt What happens while auth_enable=0 in that case is, that ep->auth_hmacs is initialized to NULL in sctp_auth_init_hmacs() when endpoint is being created. After that point, if an admin switches over to auth_enable=1, the machine can crash due to NULL pointer dereference during reception of an INIT chunk. When we enter sctp_process_init() via sctp_sf_do_5_1B_init() in order to respond to an INIT chunk, the INIT verification succeeds and while we walk and process all INIT params via sctp_process_param() we find that net->sctp.auth_enable is set, therefore do not fall through, but invoke sctp_auth_asoc_set_default_hmac() instead, and thus, dereference what we have set to NULL during endpoint initialization phase. The fix is to make auth_enable immutable by caching its value during endpoint initialization, so that its original value is being carried along until destruction. The bug seems to originate from the very first days. Fix in joint work with Daniel Borkmann. Reported-by: Joshua Kinard <kumba@gentoo.org> Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Acked-by: Neil Horman <nhorman@tuxdriver.com> Tested-by: Joshua Kinard <kumba@gentoo.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-04-18 00:26:50 +09:00
ep->auth_enable = net->sctp.auth_enable;
if (ep->auth_enable) {
if (sctp_auth_init(ep, gfp))
goto nomem;
if (ep->asconf_enable) {
sctp_auth_ep_add_chunkid(ep, SCTP_CID_ASCONF);
sctp_auth_ep_add_chunkid(ep, SCTP_CID_ASCONF_ACK);
}
}
/* Initialize the base structure. */
/* What type of endpoint are we? */
ep->base.type = SCTP_EP_TYPE_SOCKET;
/* Initialize the basic object fields. */
refcount_set(&ep->base.refcnt, 1);
ep->base.dead = false;
/* Create an input queue. */
sctp_inq_init(&ep->base.inqueue);
/* Set its top-half handler */
sctp_inq_set_th_handler(&ep->base.inqueue, sctp_endpoint_bh_rcv);
/* Initialize the bind addr area */
sctp_bind_addr_init(&ep->base.bind_addr, 0);
/* Create the lists of associations. */
INIT_LIST_HEAD(&ep->asocs);
/* Use SCTP specific send buffer space queues. */
ep->sndbuf_policy = net->sctp.sndbuf_policy;
sk->sk_data_ready = sctp_data_ready;
sk->sk_write_space = sctp_write_space;
sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
/* Get the receive buffer policy for this endpoint */
ep->rcvbuf_policy = net->sctp.rcvbuf_policy;
/* Initialize the secret key used with cookie. */
get_random_bytes(ep->secret_key, sizeof(ep->secret_key));
/* SCTP-AUTH extensions*/
INIT_LIST_HEAD(&ep->endpoint_shared_keys);
null_key = sctp_auth_shkey_create(0, gfp);
if (!null_key)
goto nomem_shkey;
list_add(&null_key->key_list, &ep->endpoint_shared_keys);
/* Add the null key to the endpoint shared keys list and
* set the hmcas and chunks pointers.
*/
ep->prsctp_enable = net->sctp.prsctp_enable;
ep->reconf_enable = net->sctp.reconf_enable;
ep->ecn_enable = net->sctp.ecn_enable;
/* Remember who we are attached to. */
ep->base.sk = sk;
sctp: cache netns in sctp_ep_common [ Upstream commit 312434617cb16be5166316cf9d08ba760b1042a1 ] This patch is to fix a data-race reported by syzbot: BUG: KCSAN: data-race in sctp_assoc_migrate / sctp_hash_obj write to 0xffff8880b67c0020 of 8 bytes by task 18908 on cpu 1: sctp_assoc_migrate+0x1a6/0x290 net/sctp/associola.c:1091 sctp_sock_migrate+0x8aa/0x9b0 net/sctp/socket.c:9465 sctp_accept+0x3c8/0x470 net/sctp/socket.c:4916 inet_accept+0x7f/0x360 net/ipv4/af_inet.c:734 __sys_accept4+0x224/0x430 net/socket.c:1754 __do_sys_accept net/socket.c:1795 [inline] __se_sys_accept net/socket.c:1792 [inline] __x64_sys_accept+0x4e/0x60 net/socket.c:1792 do_syscall_64+0xcc/0x370 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x44/0xa9 read to 0xffff8880b67c0020 of 8 bytes by task 12003 on cpu 0: sctp_hash_obj+0x4f/0x2d0 net/sctp/input.c:894 rht_key_get_hash include/linux/rhashtable.h:133 [inline] rht_key_hashfn include/linux/rhashtable.h:159 [inline] rht_head_hashfn include/linux/rhashtable.h:174 [inline] head_hashfn lib/rhashtable.c:41 [inline] rhashtable_rehash_one lib/rhashtable.c:245 [inline] rhashtable_rehash_chain lib/rhashtable.c:276 [inline] rhashtable_rehash_table lib/rhashtable.c:316 [inline] rht_deferred_worker+0x468/0xab0 lib/rhashtable.c:420 process_one_work+0x3d4/0x890 kernel/workqueue.c:2269 worker_thread+0xa0/0x800 kernel/workqueue.c:2415 kthread+0x1d4/0x200 drivers/block/aoe/aoecmd.c:1253 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:352 It was caused by rhashtable access asoc->base.sk when sctp_assoc_migrate is changing its value. However, what rhashtable wants is netns from asoc base.sk, and for an asoc, its netns won't change once set. So we can simply fix it by caching netns since created. Fixes: d6c0256a60e6 ("sctp: add the rhashtable apis for sctp global transport hashtable") Reported-by: syzbot+e3b35fe7918ff0ee474e@syzkaller.appspotmail.com Signed-off-by: Xin Long <lucien.xin@gmail.com> Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-11-23 12:56:49 +09:00
ep->base.net = sock_net(sk);
sock_hold(ep->base.sk);
return ep;
nomem_shkey:
sctp_auth_free(ep);
nomem:
kfree(ep->digest);
return NULL;
}
/* Create a sctp_endpoint with all that boring stuff initialized.
* Returns NULL if there isn't enough memory.
*/
struct sctp_endpoint *sctp_endpoint_new(struct sock *sk, gfp_t gfp)
{
struct sctp_endpoint *ep;
/* Build a local endpoint. */
ep = kzalloc(sizeof(*ep), gfp);
if (!ep)
goto fail;
if (!sctp_endpoint_init(ep, sk, gfp))
goto fail_init;
SCTP_DBG_OBJCNT_INC(ep);
return ep;
fail_init:
kfree(ep);
fail:
return NULL;
}
/* Add an association to an endpoint. */
void sctp_endpoint_add_asoc(struct sctp_endpoint *ep,
struct sctp_association *asoc)
{
struct sock *sk = ep->base.sk;
/* If this is a temporary association, don't bother
* since we'll be removing it shortly and don't
* want anyone to find it anyway.
*/
if (asoc->temp)
return;
/* Now just add it to our list of asocs */
list_add_tail(&asoc->asocs, &ep->asocs);
/* Increment the backlog value for a TCP-style listening socket. */
if (sctp_style(sk, TCP) && sctp_sstate(sk, LISTENING))
sk->sk_ack_backlog++;
}
/* Free the endpoint structure. Delay cleanup until
* all users have released their reference count on this structure.
*/
void sctp_endpoint_free(struct sctp_endpoint *ep)
{
ep->base.dead = true;
inet_sk_set_state(ep->base.sk, SCTP_SS_CLOSED);
/* Unlink this endpoint, so we can't find it again! */
sctp_unhash_endpoint(ep);
sctp_endpoint_put(ep);
}
/* Final destructor for endpoint. */
static void sctp_endpoint_destroy(struct sctp_endpoint *ep)
{
struct sock *sk;
net: sctp: rework debugging framework to use pr_debug and friends We should get rid of all own SCTP debug printk macros and use the ones that the kernel offers anyway instead. This makes the code more readable and conform to the kernel code, and offers all the features of dynamic debbuging that pr_debug() et al has, such as only turning on/off portions of debug messages at runtime through debugfs. The runtime cost of having CONFIG_DYNAMIC_DEBUG enabled, but none of the debug statements printing, is negligible [1]. If kernel debugging is completly turned off, then these statements will also compile into "empty" functions. While we're at it, we also need to change the Kconfig option as it /now/ only refers to the ifdef'ed code portions in outqueue.c that enable further debugging/tracing of SCTP transaction fields. Also, since SCTP_ASSERT code was enabled with this Kconfig option and has now been removed, we transform those code parts into WARNs resp. where appropriate BUG_ONs so that those bugs can be more easily detected as probably not many people have SCTP debugging permanently turned on. To turn on all SCTP debugging, the following steps are needed: # mount -t debugfs none /sys/kernel/debug # echo -n 'module sctp +p' > /sys/kernel/debug/dynamic_debug/control This can be done more fine-grained on a per file, per line basis and others as described in [2]. [1] https://www.kernel.org/doc/ols/2009/ols2009-pages-39-46.pdf [2] Documentation/dynamic-debug-howto.txt Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-06-29 02:49:40 +09:00
if (unlikely(!ep->base.dead)) {
WARN(1, "Attempt to destroy undead endpoint %p!\n", ep);
return;
}
/* Free the digest buffer */
kfree(ep->digest);
/* SCTP-AUTH: Free up AUTH releated data such as shared keys
* chunks and hmacs arrays that were allocated
*/
sctp_auth_destroy_keys(&ep->endpoint_shared_keys);
sctp_auth_free(ep);
/* Cleanup. */
sctp_inq_free(&ep->base.inqueue);
sctp_bind_addr_free(&ep->base.bind_addr);
memset(ep->secret_key, 0, sizeof(ep->secret_key));
sk = ep->base.sk;
/* Remove and free the port */
if (sctp_sk(sk)->bind_hash)
sctp_put_port(sk);
sctp_sk(sk)->ep = NULL;
/* Give up our hold on the sock */
sock_put(sk);
kfree(ep);
SCTP_DBG_OBJCNT_DEC(ep);
}
/* Hold a reference to an endpoint. */
void sctp_endpoint_hold(struct sctp_endpoint *ep)
{
refcount_inc(&ep->base.refcnt);
}
/* Release a reference to an endpoint and clean up if there are
* no more references.
*/
void sctp_endpoint_put(struct sctp_endpoint *ep)
{
if (refcount_dec_and_test(&ep->base.refcnt))
sctp_endpoint_destroy(ep);
}
/* Is this the endpoint we are looking for? */
struct sctp_endpoint *sctp_endpoint_is_match(struct sctp_endpoint *ep,
struct net *net,
const union sctp_addr *laddr)
{
struct sctp_endpoint *retval = NULL;
if ((htons(ep->base.bind_addr.port) == laddr->v4.sin_port) &&
net_eq(sock_net(ep->base.sk), net)) {
if (sctp_bind_addr_match(&ep->base.bind_addr, laddr,
sctp_sk(ep->base.sk)))
retval = ep;
}
return retval;
}
/* Find the association that goes with this chunk.
* We lookup the transport from hashtable at first, then get association
* through t->assoc.
*/
struct sctp_association *sctp_endpoint_lookup_assoc(
const struct sctp_endpoint *ep,
const union sctp_addr *paddr,
struct sctp_transport **transport)
{
struct sctp_association *asoc = NULL;
struct sctp_transport *t;
*transport = NULL;
/* If the local port is not set, there can't be any associations
* on this endpoint.
*/
if (!ep->base.bind_addr.port)
return NULL;
rcu_read_lock();
t = sctp_epaddr_lookup_transport(ep, paddr);
if (!t)
goto out;
*transport = t;
asoc = t->asoc;
out:
rcu_read_unlock();
return asoc;
}
/* Look for any peeled off association from the endpoint that matches the
* given peer address.
*/
bool sctp_endpoint_is_peeled_off(struct sctp_endpoint *ep,
const union sctp_addr *paddr)
{
struct sctp_sockaddr_entry *addr;
struct sctp_bind_addr *bp;
struct net *net = sock_net(ep->base.sk);
bp = &ep->base.bind_addr;
/* This function is called with the socket lock held,
* so the address_list can not change.
*/
list_for_each_entry(addr, &bp->address_list, list) {
if (sctp_has_association(net, &addr->a, paddr))
return true;
}
return false;
}
/* Do delayed input processing. This is scheduled by sctp_rcv().
* This may be called on BH or task time.
*/
static void sctp_endpoint_bh_rcv(struct work_struct *work)
{
struct sctp_endpoint *ep =
container_of(work, struct sctp_endpoint,
base.inqueue.immediate);
struct sctp_association *asoc;
struct sock *sk;
struct net *net;
struct sctp_transport *transport;
struct sctp_chunk *chunk;
struct sctp_inq *inqueue;
union sctp_subtype subtype;
enum sctp_state state;
int error = 0;
int first_time = 1; /* is this the first time through the loop */
if (ep->base.dead)
return;
asoc = NULL;
inqueue = &ep->base.inqueue;
sk = ep->base.sk;
net = sock_net(sk);
while (NULL != (chunk = sctp_inq_pop(inqueue))) {
subtype = SCTP_ST_CHUNK(chunk->chunk_hdr->type);
/* If the first chunk in the packet is AUTH, do special
* processing specified in Section 6.3 of SCTP-AUTH spec
*/
if (first_time && (subtype.chunk == SCTP_CID_AUTH)) {
struct sctp_chunkhdr *next_hdr;
next_hdr = sctp_inq_peek(inqueue);
if (!next_hdr)
goto normal;
/* If the next chunk is COOKIE-ECHO, skip the AUTH
* chunk while saving a pointer to it so we can do
* Authentication later (during cookie-echo
* processing).
*/
if (next_hdr->type == SCTP_CID_COOKIE_ECHO) {
chunk->auth_chunk = skb_clone(chunk->skb,
GFP_ATOMIC);
chunk->auth = 1;
continue;
}
}
normal:
/* We might have grown an association since last we
* looked, so try again.
*
* This happens when we've just processed our
* COOKIE-ECHO chunk.
*/
if (NULL == chunk->asoc) {
asoc = sctp_endpoint_lookup_assoc(ep,
sctp_source(chunk),
&transport);
chunk->asoc = asoc;
chunk->transport = transport;
}
state = asoc ? asoc->state : SCTP_STATE_CLOSED;
if (sctp_auth_recv_cid(subtype.chunk, asoc) && !chunk->auth)
continue;
/* Remember where the last DATA chunk came from so we
* know where to send the SACK.
*/
if (asoc && sctp_chunk_is_data(chunk))
asoc->peer.last_data_from = chunk->transport;
sctp: Add support to per-association statistics via a new SCTP_GET_ASSOC_STATS call The current SCTP stack is lacking a mechanism to have per association statistics. This is an implementation modeled after OpenSolaris' SCTP_GET_ASSOC_STATS. Userspace part will follow on lksctp if/when there is a general ACK on this. V4: - Move ipackets++ before q->immediate.func() for consistency reasons - Move sctp_max_rto() at the end of sctp_transport_update_rto() to avoid returning bogus RTO values - return asoc->rto_min when max_obs_rto value has not changed V3: - Increase ictrlchunks in sctp_assoc_bh_rcv() as well - Move ipackets++ to sctp_inq_push() - return 0 when no rto updates took place since the last call V2: - Implement partial retrieval of stat struct to cope for future expansion - Kill the rtxpackets counter as it cannot be precise anyway - Rename outseqtsns to outofseqtsns to make it clearer that these are out of sequence unexpected TSNs - Move asoc->ipackets++ under a lock to avoid potential miscounts - Fold asoc->opackets++ into the already existing asoc check - Kill unneeded (q->asoc) test when increasing rtxchunks - Do not count octrlchunks if sending failed (SCTP_XMIT_OK != 0) - Don't count SHUTDOWNs as SACKs - Move SCTP_GET_ASSOC_STATS to the private space API - Adjust the len check in sctp_getsockopt_assoc_stats() to allow for future struct growth - Move association statistics in their own struct - Update idupchunks when we send a SACK with dup TSNs - return min_rto in max_rto when RTO has not changed. Also return the transport when max_rto last changed. Signed-off: Michele Baldessari <michele@acksyn.org> Acked-by: Vlad Yasevich <vyasevich@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-12-01 13:49:42 +09:00
else {
SCTP_INC_STATS(sock_net(ep->base.sk), SCTP_MIB_INCTRLCHUNKS);
sctp: Add support to per-association statistics via a new SCTP_GET_ASSOC_STATS call The current SCTP stack is lacking a mechanism to have per association statistics. This is an implementation modeled after OpenSolaris' SCTP_GET_ASSOC_STATS. Userspace part will follow on lksctp if/when there is a general ACK on this. V4: - Move ipackets++ before q->immediate.func() for consistency reasons - Move sctp_max_rto() at the end of sctp_transport_update_rto() to avoid returning bogus RTO values - return asoc->rto_min when max_obs_rto value has not changed V3: - Increase ictrlchunks in sctp_assoc_bh_rcv() as well - Move ipackets++ to sctp_inq_push() - return 0 when no rto updates took place since the last call V2: - Implement partial retrieval of stat struct to cope for future expansion - Kill the rtxpackets counter as it cannot be precise anyway - Rename outseqtsns to outofseqtsns to make it clearer that these are out of sequence unexpected TSNs - Move asoc->ipackets++ under a lock to avoid potential miscounts - Fold asoc->opackets++ into the already existing asoc check - Kill unneeded (q->asoc) test when increasing rtxchunks - Do not count octrlchunks if sending failed (SCTP_XMIT_OK != 0) - Don't count SHUTDOWNs as SACKs - Move SCTP_GET_ASSOC_STATS to the private space API - Adjust the len check in sctp_getsockopt_assoc_stats() to allow for future struct growth - Move association statistics in their own struct - Update idupchunks when we send a SACK with dup TSNs - return min_rto in max_rto when RTO has not changed. Also return the transport when max_rto last changed. Signed-off: Michele Baldessari <michele@acksyn.org> Acked-by: Vlad Yasevich <vyasevich@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-12-01 13:49:42 +09:00
if (asoc)
asoc->stats.ictrlchunks++;
}
if (chunk->transport)
chunk->transport->last_time_heard = ktime_get();
error = sctp_do_sm(net, SCTP_EVENT_T_CHUNK, subtype, state,
ep, asoc, chunk, GFP_ATOMIC);
if (error && chunk)
chunk->pdiscard = 1;
/* Check to see if the endpoint is freed in response to
* the incoming chunk. If so, get out of the while loop.
*/
if (!sctp_sk(sk)->ep)
break;
if (first_time)
first_time = 0;
}
}