diff options
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/af_inet.c | 1 | ||||
-rw-r--r-- | net/ipv4/devinet.c | 19 | ||||
-rw-r--r-- | net/ipv4/icmp.c | 2 | ||||
-rw-r--r-- | net/ipv4/igmp.c | 6 | ||||
-rw-r--r-- | net/ipv4/inet_connection_sock.c | 42 | ||||
-rw-r--r-- | net/ipv4/inet_hashtables.c | 10 | ||||
-rw-r--r-- | net/ipv4/inet_timewait_sock.c | 31 | ||||
-rw-r--r-- | net/ipv4/ipmr.c | 2 | ||||
-rw-r--r-- | net/ipv4/route.c | 4 | ||||
-rw-r--r-- | net/ipv4/syncookies.c | 7 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 4 | ||||
-rw-r--r-- | net/ipv4/tcp_bbr.c | 2 | ||||
-rw-r--r-- | net/ipv4/tcp_input.c | 3 | ||||
-rw-r--r-- | net/ipv4/tcp_plb.c | 2 | ||||
-rw-r--r-- | net/ipv4/tcp_ulp.c | 4 | ||||
-rw-r--r-- | net/ipv4/udp_tunnel_core.c | 1 |
16 files changed, 104 insertions, 36 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index ab4a06be489b..6c0ec2789943 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1665,6 +1665,7 @@ int inet_ctl_sock_create(struct sock **sk, unsigned short family, if (rc == 0) { *sk = sock->sk; (*sk)->sk_allocation = GFP_ATOMIC; + (*sk)->sk_use_task_frag = false; /* * Unhash it so that IP input processing does not even see it, * we do not wish this socket to see incoming packets. diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index e8b9a9202fec..b0acf6e19aed 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -234,13 +234,20 @@ static void inet_free_ifa(struct in_ifaddr *ifa) call_rcu(&ifa->rcu_head, inet_rcu_free_ifa); } +static void in_dev_free_rcu(struct rcu_head *head) +{ + struct in_device *idev = container_of(head, struct in_device, rcu_head); + + kfree(rcu_dereference_protected(idev->mc_hash, 1)); + kfree(idev); +} + void in_dev_finish_destroy(struct in_device *idev) { struct net_device *dev = idev->dev; WARN_ON(idev->ifa_list); WARN_ON(idev->mc_list); - kfree(rcu_dereference_protected(idev->mc_hash, 1)); #ifdef NET_REFCNT_DEBUG pr_debug("%s: %p=%s\n", __func__, idev, dev ? dev->name : "NIL"); #endif @@ -248,7 +255,7 @@ void in_dev_finish_destroy(struct in_device *idev) if (!idev->dead) pr_err("Freeing alive in_device %p\n", idev); else - kfree(idev); + call_rcu(&idev->rcu_head, in_dev_free_rcu); } EXPORT_SYMBOL(in_dev_finish_destroy); @@ -298,12 +305,6 @@ out_kfree: goto out; } -static void in_dev_rcu_put(struct rcu_head *head) -{ - struct in_device *idev = container_of(head, struct in_device, rcu_head); - in_dev_put(idev); -} - static void inetdev_destroy(struct in_device *in_dev) { struct net_device *dev; @@ -328,7 +329,7 @@ static void inetdev_destroy(struct in_device *in_dev) neigh_parms_release(&arp_tbl, in_dev->arp_parms); arp_ifdown(dev); - call_rcu(&in_dev->rcu_head, in_dev_rcu_put); + in_dev_put(in_dev); } int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index d5d745c3e345..46aa2d65e40a 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -263,7 +263,7 @@ bool icmp_global_allow(void) /* We want to use a credit of one in average, but need to randomize * it for security reasons. */ - credit = max_t(int, credit - prandom_u32_max(3), 0); + credit = max_t(int, credit - get_random_u32_below(3), 0); rc = true; } WRITE_ONCE(icmp_global.credit, credit); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 81be3e0f0e70..c920aa9a62a9 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -213,7 +213,7 @@ static void igmp_stop_timer(struct ip_mc_list *im) /* It must be called with locked im->lock */ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) { - int tv = prandom_u32_max(max_delay); + int tv = get_random_u32_below(max_delay); im->tm_running = 1; if (!mod_timer(&im->timer, jiffies+tv+2)) @@ -222,7 +222,7 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) static void igmp_gq_start_timer(struct in_device *in_dev) { - int tv = prandom_u32_max(in_dev->mr_maxdelay); + int tv = get_random_u32_below(in_dev->mr_maxdelay); unsigned long exp = jiffies + tv + 2; if (in_dev->mr_gq_running && @@ -236,7 +236,7 @@ static void igmp_gq_start_timer(struct in_device *in_dev) static void igmp_ifc_start_timer(struct in_device *in_dev, int delay) { - int tv = prandom_u32_max(delay); + int tv = get_random_u32_below(delay); if (!mod_timer(&in_dev->mr_ifc_timer, jiffies+tv+2)) in_dev_hold(in_dev); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 4a34bc7cb15e..d1f837579398 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -173,22 +173,40 @@ static bool inet_bind_conflict(const struct sock *sk, struct sock *sk2, return false; } +static bool __inet_bhash2_conflict(const struct sock *sk, struct sock *sk2, + kuid_t sk_uid, bool relax, + bool reuseport_cb_ok, bool reuseport_ok) +{ + if (sk->sk_family == AF_INET && ipv6_only_sock(sk2)) + return false; + + return inet_bind_conflict(sk, sk2, sk_uid, relax, + reuseport_cb_ok, reuseport_ok); +} + static bool inet_bhash2_conflict(const struct sock *sk, const struct inet_bind2_bucket *tb2, kuid_t sk_uid, bool relax, bool reuseport_cb_ok, bool reuseport_ok) { + struct inet_timewait_sock *tw2; struct sock *sk2; sk_for_each_bound_bhash2(sk2, &tb2->owners) { - if (sk->sk_family == AF_INET && ipv6_only_sock(sk2)) - continue; + if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax, + reuseport_cb_ok, reuseport_ok)) + return true; + } - if (inet_bind_conflict(sk, sk2, sk_uid, relax, - reuseport_cb_ok, reuseport_ok)) + twsk_for_each_bound_bhash2(tw2, &tb2->deathrow) { + sk2 = (struct sock *)tw2; + + if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax, + reuseport_cb_ok, reuseport_ok)) return true; } + return false; } @@ -314,7 +332,7 @@ other_half_scan: if (likely(remaining > 1)) remaining &= ~1U; - offset = prandom_u32_max(remaining); + offset = get_random_u32_below(remaining); /* __inet_hash_connect() favors ports having @low parity * We do the opposite to not pollute connect() users. */ @@ -1182,12 +1200,26 @@ void inet_csk_prepare_forced_close(struct sock *sk) } EXPORT_SYMBOL(inet_csk_prepare_forced_close); +static int inet_ulp_can_listen(const struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + + if (icsk->icsk_ulp_ops && !icsk->icsk_ulp_ops->clone) + return -EINVAL; + + return 0; +} + int inet_csk_listen_start(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet = inet_sk(sk); int err; + err = inet_ulp_can_listen(sk); + if (unlikely(err)) + return err; + reqsk_queue_alloc(&icsk->icsk_accept_queue); sk->sk_ack_backlog = 0; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 3cec471a2cd2..24a38b56fab9 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -116,6 +116,7 @@ static void inet_bind2_bucket_init(struct inet_bind2_bucket *tb, #endif tb->rcv_saddr = sk->sk_rcv_saddr; INIT_HLIST_HEAD(&tb->owners); + INIT_HLIST_HEAD(&tb->deathrow); hlist_add_head(&tb->node, &head->chain); } @@ -137,7 +138,7 @@ struct inet_bind2_bucket *inet_bind2_bucket_create(struct kmem_cache *cachep, /* Caller must hold hashbucket lock for this tb with local BH disabled */ void inet_bind2_bucket_destroy(struct kmem_cache *cachep, struct inet_bind2_bucket *tb) { - if (hlist_empty(&tb->owners)) { + if (hlist_empty(&tb->owners) && hlist_empty(&tb->deathrow)) { __hlist_del(&tb->node); kmem_cache_free(cachep, tb); } @@ -1097,21 +1098,22 @@ ok: * on low contention the randomness is maximal and on high contention * it may be inexistent. */ - i = max_t(int, i, prandom_u32_max(8) * 2); + i = max_t(int, i, get_random_u32_below(8) * 2); WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + 2); /* Head lock still held and bh's disabled */ inet_bind_hash(sk, tb, tb2, port); - spin_unlock(&head2->lock); - if (sk_unhashed(sk)) { inet_sk(sk)->inet_sport = htons(port); inet_ehash_nolisten(sk, (struct sock *)tw, NULL); } if (tw) inet_twsk_bind_unhash(tw, hinfo); + + spin_unlock(&head2->lock); spin_unlock(&head->lock); + if (tw) inet_twsk_deschedule_put(tw); local_bh_enable(); diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 66fc940f9521..1d77d992e6e7 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -29,6 +29,7 @@ void inet_twsk_bind_unhash(struct inet_timewait_sock *tw, struct inet_hashinfo *hashinfo) { + struct inet_bind2_bucket *tb2 = tw->tw_tb2; struct inet_bind_bucket *tb = tw->tw_tb; if (!tb) @@ -37,6 +38,11 @@ void inet_twsk_bind_unhash(struct inet_timewait_sock *tw, __hlist_del(&tw->tw_bind_node); tw->tw_tb = NULL; inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb); + + __hlist_del(&tw->tw_bind2_node); + tw->tw_tb2 = NULL; + inet_bind2_bucket_destroy(hashinfo->bind2_bucket_cachep, tb2); + __sock_put((struct sock *)tw); } @@ -45,7 +51,7 @@ static void inet_twsk_kill(struct inet_timewait_sock *tw) { struct inet_hashinfo *hashinfo = tw->tw_dr->hashinfo; spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash); - struct inet_bind_hashbucket *bhead; + struct inet_bind_hashbucket *bhead, *bhead2; spin_lock(lock); sk_nulls_del_node_init_rcu((struct sock *)tw); @@ -54,9 +60,13 @@ static void inet_twsk_kill(struct inet_timewait_sock *tw) /* Disassociate with bind bucket. */ bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), tw->tw_num, hashinfo->bhash_size)]; + bhead2 = inet_bhashfn_portaddr(hashinfo, (struct sock *)tw, + twsk_net(tw), tw->tw_num); spin_lock(&bhead->lock); + spin_lock(&bhead2->lock); inet_twsk_bind_unhash(tw, hashinfo); + spin_unlock(&bhead2->lock); spin_unlock(&bhead->lock); refcount_dec(&tw->tw_dr->tw_refcount); @@ -93,6 +103,12 @@ static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw, hlist_add_head(&tw->tw_bind_node, list); } +static void inet_twsk_add_bind2_node(struct inet_timewait_sock *tw, + struct hlist_head *list) +{ + hlist_add_head(&tw->tw_bind2_node, list); +} + /* * Enter the time wait state. This is called with locally disabled BH. * Essentially we whip up a timewait bucket, copy the relevant info into it @@ -105,17 +121,28 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, const struct inet_connection_sock *icsk = inet_csk(sk); struct inet_ehash_bucket *ehead = inet_ehash_bucket(hashinfo, sk->sk_hash); spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash); - struct inet_bind_hashbucket *bhead; + struct inet_bind_hashbucket *bhead, *bhead2; + /* Step 1: Put TW into bind hash. Original socket stays there too. Note, that any socket with inet->num != 0 MUST be bound in binding cache, even if it is closed. */ bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num, hashinfo->bhash_size)]; + bhead2 = inet_bhashfn_portaddr(hashinfo, sk, twsk_net(tw), inet->inet_num); + spin_lock(&bhead->lock); + spin_lock(&bhead2->lock); + tw->tw_tb = icsk->icsk_bind_hash; WARN_ON(!icsk->icsk_bind_hash); inet_twsk_add_bind_node(tw, &tw->tw_tb->owners); + + tw->tw_tb2 = icsk->icsk_bind2_hash; + WARN_ON(!icsk->icsk_bind2_hash); + inet_twsk_add_bind2_node(tw, &tw->tw_tb2->deathrow); + + spin_unlock(&bhead2->lock); spin_unlock(&bhead->lock); spin_lock(lock); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index b58df3c1bf7d..eec1f6df80d8 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -412,7 +412,7 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id) static void ipmr_free_table(struct mr_table *mrt) { - del_timer_sync(&mrt->ipmr_expire_timer); + timer_shutdown_sync(&mrt->ipmr_expire_timer); mroute_clean_tables(mrt, MRT_FLUSH_VIFS | MRT_FLUSH_VIFS_STATIC | MRT_FLUSH_MFC | MRT_FLUSH_MFC_STATIC); rhltable_destroy(&mrt->mfc_hash); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index cd1fa9f70f1a..de6e3515ab4f 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -471,7 +471,7 @@ static u32 ip_idents_reserve(u32 hash, int segs) old = READ_ONCE(*p_tstamp); if (old != now && cmpxchg(p_tstamp, old, now) == old) - delta = prandom_u32_max(now - old); + delta = get_random_u32_below(now - old); /* If UBSAN reports an error there, please make sure your compiler * supports -fno-strict-overflow before reporting it that was a bug @@ -689,7 +689,7 @@ static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr, } else { /* Randomize max depth to avoid some side channels attacks. */ int max_depth = FNHE_RECLAIM_DEPTH + - prandom_u32_max(FNHE_RECLAIM_DEPTH); + get_random_u32_below(FNHE_RECLAIM_DEPTH); while (depth > max_depth) { fnhe_remove_oldest(hash); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 942d2dfa1115..26fb97d1d4d9 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -288,12 +288,11 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, struct tcp_request_sock *treq; struct request_sock *req; -#ifdef CONFIG_MPTCP if (sk_is_mptcp(sk)) - ops = &mptcp_subflow_request_sock_ops; -#endif + req = mptcp_subflow_reqsk_alloc(ops, sk, false); + else + req = inet_reqsk_alloc(ops, sk, false); - req = inet_reqsk_alloc(ops, sk, false); if (!req) return NULL; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 001947136b0a..c567d5e8053e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2000,7 +2000,7 @@ static int receive_fallback_to_copy(struct sock *sk, if (copy_address != zc->copybuf_address) return -EINVAL; - err = import_single_range(READ, (void __user *)copy_address, + err = import_single_range(ITER_DEST, (void __user *)copy_address, inq, &iov, &msg.msg_iter); if (err) return err; @@ -2034,7 +2034,7 @@ static int tcp_copy_straggler_data(struct tcp_zerocopy_receive *zc, if (copy_address != zc->copybuf_address) return -EINVAL; - err = import_single_range(READ, (void __user *)copy_address, + err = import_single_range(ITER_DEST, (void __user *)copy_address, copylen, &iov, &msg.msg_iter); if (err) return err; diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 54eec33c6e1c..d2c470524e58 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -618,7 +618,7 @@ static void bbr_reset_probe_bw_mode(struct sock *sk) struct bbr *bbr = inet_csk_ca(sk); bbr->mode = BBR_PROBE_BW; - bbr->cycle_idx = CYCLE_LEN - 1 - prandom_u32_max(bbr_cycle_rand); + bbr->cycle_idx = CYCLE_LEN - 1 - get_random_u32_below(bbr_cycle_rand); bbr_advance_cycle_phase(sk); /* flip to next phase of gain cycle */ } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 1efacbe948da..cc072d2cfcd8 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3646,7 +3646,8 @@ static void tcp_send_challenge_ack(struct sock *sk) u32 half = (ack_limit + 1) >> 1; WRITE_ONCE(net->ipv4.tcp_challenge_timestamp, now); - WRITE_ONCE(net->ipv4.tcp_challenge_count, half + prandom_u32_max(ack_limit)); + WRITE_ONCE(net->ipv4.tcp_challenge_count, + get_random_u32_inclusive(half, ack_limit + half - 1)); } count = READ_ONCE(net->ipv4.tcp_challenge_count); if (count > 0) { diff --git a/net/ipv4/tcp_plb.c b/net/ipv4/tcp_plb.c index bb1a08fda113..4bcf7eff95e3 100644 --- a/net/ipv4/tcp_plb.c +++ b/net/ipv4/tcp_plb.c @@ -97,7 +97,7 @@ void tcp_plb_update_state_upon_rto(struct sock *sk, struct tcp_plb_state *plb) return; pause = READ_ONCE(net->ipv4.sysctl_tcp_plb_suspend_rto_sec) * HZ; - pause += prandom_u32_max(pause); + pause += get_random_u32_below(pause); plb->pause_until = tcp_jiffies32 + pause; /* Reset PLB state upon RTO, since an RTO causes a sk_rethink_txhash() call diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c index 9ae50b1bd844..05b6077b9f2c 100644 --- a/net/ipv4/tcp_ulp.c +++ b/net/ipv4/tcp_ulp.c @@ -139,6 +139,10 @@ static int __tcp_set_ulp(struct sock *sk, const struct tcp_ulp_ops *ulp_ops) if (sk->sk_socket) clear_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); + err = -EINVAL; + if (!ulp_ops->clone && sk->sk_state == TCP_LISTEN) + goto out_err; + err = ulp_ops->init(sk); if (err) goto out_err; diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c index 8242c8947340..5f8104cf082d 100644 --- a/net/ipv4/udp_tunnel_core.c +++ b/net/ipv4/udp_tunnel_core.c @@ -176,6 +176,7 @@ EXPORT_SYMBOL_GPL(udp_tunnel_xmit_skb); void udp_tunnel_sock_release(struct socket *sock) { rcu_assign_sk_user_data(sock->sk, NULL); + synchronize_rcu(); kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); } |