linux_dsm_epyc7002/net/ipv4/inet_connection_sock.c

1107 lines
31 KiB
C
Raw Normal View History

/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Support for INET connection oriented protocols.
*
* Authors: See the TCP sources
*
* 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/module.h>
#include <linux/jhash.h>
#include <net/inet_connection_sock.h>
#include <net/inet_hashtables.h>
#include <net/inet_timewait_sock.h>
#include <net/ip.h>
#include <net/route.h>
#include <net/tcp_states.h>
#include <net/xfrm.h>
#include <net/tcp.h>
#include <net/sock_reuseport.h>
#include <net/addrconf.h>
#if IS_ENABLED(CONFIG_IPV6)
/* match_wildcard == true: IPV6_ADDR_ANY equals to any IPv6 addresses if IPv6
* only, and any IPv4 addresses if not IPv6 only
* match_wildcard == false: addresses must be exactly the same, i.e.
* IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY,
* and 0.0.0.0 equals to 0.0.0.0 only
*/
static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
const struct in6_addr *sk2_rcv_saddr6,
__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
bool sk1_ipv6only, bool sk2_ipv6only,
bool match_wildcard)
{
int addr_type = ipv6_addr_type(sk1_rcv_saddr6);
int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED;
/* if both are mapped, treat as IPv4 */
if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) {
if (!sk2_ipv6only) {
if (sk1_rcv_saddr == sk2_rcv_saddr)
return true;
if (!sk1_rcv_saddr || !sk2_rcv_saddr)
return match_wildcard;
}
return false;
}
if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY)
return true;
if (addr_type2 == IPV6_ADDR_ANY && match_wildcard &&
!(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED))
return true;
if (addr_type == IPV6_ADDR_ANY && match_wildcard &&
!(sk1_ipv6only && addr_type2 == IPV6_ADDR_MAPPED))
return true;
if (sk2_rcv_saddr6 &&
ipv6_addr_equal(sk1_rcv_saddr6, sk2_rcv_saddr6))
return true;
return false;
}
#endif
/* match_wildcard == true: 0.0.0.0 equals to any IPv4 addresses
* match_wildcard == false: addresses must be exactly the same, i.e.
* 0.0.0.0 only equals to 0.0.0.0
*/
static bool ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
bool sk2_ipv6only, bool match_wildcard)
{
if (!sk2_ipv6only) {
if (sk1_rcv_saddr == sk2_rcv_saddr)
return true;
if (!sk1_rcv_saddr || !sk2_rcv_saddr)
return match_wildcard;
}
return false;
}
bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
bool match_wildcard)
{
#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family == AF_INET6)
return ipv6_rcv_saddr_equal(&sk->sk_v6_rcv_saddr,
inet6_rcv_saddr(sk2),
sk->sk_rcv_saddr,
sk2->sk_rcv_saddr,
ipv6_only_sock(sk),
ipv6_only_sock(sk2),
match_wildcard);
#endif
return ipv4_rcv_saddr_equal(sk->sk_rcv_saddr, sk2->sk_rcv_saddr,
ipv6_only_sock(sk2), match_wildcard);
}
EXPORT_SYMBOL(inet_rcv_saddr_equal);
bpf: Introduce BPF_PROG_TYPE_SK_REUSEPORT This patch adds a BPF_PROG_TYPE_SK_REUSEPORT which can select a SO_REUSEPORT sk from a BPF_MAP_TYPE_REUSEPORT_ARRAY. Like other non SK_FILTER/CGROUP_SKB program, it requires CAP_SYS_ADMIN. BPF_PROG_TYPE_SK_REUSEPORT introduces "struct sk_reuseport_kern" to store the bpf context instead of using the skb->cb[48]. At the SO_REUSEPORT sk lookup time, it is in the middle of transiting from a lower layer (ipv4/ipv6) to a upper layer (udp/tcp). At this point, it is not always clear where the bpf context can be appended in the skb->cb[48] to avoid saving-and-restoring cb[]. Even putting aside the difference between ipv4-vs-ipv6 and udp-vs-tcp. It is not clear if the lower layer is only ipv4 and ipv6 in the future and will it not touch the cb[] again before transiting to the upper layer. For example, in udp_gro_receive(), it uses the 48 byte NAPI_GRO_CB instead of IP[6]CB and it may still modify the cb[] after calling the udp[46]_lib_lookup_skb(). Because of the above reason, if sk->cb is used for the bpf ctx, saving-and-restoring is needed and likely the whole 48 bytes cb[] has to be saved and restored. Instead of saving, setting and restoring the cb[], this patch opts to create a new "struct sk_reuseport_kern" and setting the needed values in there. The new BPF_PROG_TYPE_SK_REUSEPORT and "struct sk_reuseport_(kern|md)" will serve all ipv4/ipv6 + udp/tcp combinations. There is no protocol specific usage at this point and it is also inline with the current sock_reuseport.c implementation (i.e. no protocol specific requirement). In "struct sk_reuseport_md", this patch exposes data/data_end/len with semantic similar to other existing usages. Together with "bpf_skb_load_bytes()" and "bpf_skb_load_bytes_relative()", the bpf prog can peek anywhere in the skb. The "bind_inany" tells the bpf prog that the reuseport group is bind-ed to a local INANY address which cannot be learned from skb. The new "bind_inany" is added to "struct sock_reuseport" which will be used when running the new "BPF_PROG_TYPE_SK_REUSEPORT" bpf prog in order to avoid repeating the "bind INANY" test on "sk_v6_rcv_saddr/sk->sk_rcv_saddr" every time a bpf prog is run. It can only be properly initialized when a "sk->sk_reuseport" enabled sk is adding to a hashtable (i.e. during "reuseport_alloc()" and "reuseport_add_sock()"). The new "sk_select_reuseport()" is the main helper that the bpf prog will use to select a SO_REUSEPORT sk. It is the only function that can use the new BPF_MAP_TYPE_REUSEPORT_ARRAY. As mentioned in the earlier patch, the validity of a selected sk is checked in run time in "sk_select_reuseport()". Doing the check in verification time is difficult and inflexible (consider the map-in-map use case). The runtime check is to compare the selected sk's reuseport_id with the reuseport_id that we want. This helper will return -EXXX if the selected sk cannot serve the incoming request (e.g. reuseport_id not match). The bpf prog can decide if it wants to do SK_DROP as its discretion. When the bpf prog returns SK_PASS, the kernel will check if a valid sk has been selected (i.e. "reuse_kern->selected_sk != NULL"). If it does , it will use the selected sk. If not, the kernel will select one from "reuse->socks[]" (as before this patch). The SK_DROP and SK_PASS handling logic will be in the next patch. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-08-08 15:01:25 +07:00
bool inet_rcv_saddr_any(const struct sock *sk)
{
#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family == AF_INET6)
return ipv6_addr_any(&sk->sk_v6_rcv_saddr);
#endif
return !sk->sk_rcv_saddr;
}
void inet_get_local_port_range(struct net *net, int *low, int *high)
{
unsigned int seq;
do {
seq = read_seqbegin(&net->ipv4.ip_local_ports.lock);
*low = net->ipv4.ip_local_ports.range[0];
*high = net->ipv4.ip_local_ports.range[1];
} while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq));
}
EXPORT_SYMBOL(inet_get_local_port_range);
static int inet_csk_bind_conflict(const struct sock *sk,
const struct inet_bind_bucket *tb,
bool relax, bool reuseport_ok)
{
struct sock *sk2;
bool reuse = sk->sk_reuse;
bool reuseport = !!sk->sk_reuseport && reuseport_ok;
kuid_t uid = sock_i_uid((struct sock *)sk);
/*
* Unlike other sk lookup places we do not check
* for sk_net here, since _all_ the socks listed
* in tb->owners list belong to the same net - the
* one this bucket belongs to.
*/
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 08:06:00 +07:00
sk_for_each_bound(sk2, &tb->owners) {
if (sk != sk2 &&
(!sk->sk_bound_dev_if ||
!sk2->sk_bound_dev_if ||
sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) {
if ((!reuse || !sk2->sk_reuse ||
sk2->sk_state == TCP_LISTEN) &&
(!reuseport || !sk2->sk_reuseport ||
rcu_access_pointer(sk->sk_reuseport_cb) ||
(sk2->sk_state != TCP_TIME_WAIT &&
!uid_eq(uid, sock_i_uid(sk2))))) {
if (inet_rcv_saddr_equal(sk, sk2, true))
break;
}
if (!relax && reuse && sk2->sk_reuse &&
sk2->sk_state != TCP_LISTEN) {
if (inet_rcv_saddr_equal(sk, sk2, true))
break;
}
}
}
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 08:06:00 +07:00
return sk2 != NULL;
}
/*
* Find an open port number for the socket. Returns with the
* inet_bind_hashbucket lock held.
*/
static struct inet_bind_hashbucket *
inet_csk_find_open_port(struct sock *sk, struct inet_bind_bucket **tb_ret, int *port_ret)
{
struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo;
int port = 0;
struct inet_bind_hashbucket *head;
struct net *net = sock_net(sk);
int i, low, high, attempt_half;
struct inet_bind_bucket *tb;
u32 remaining, offset;
int l3mdev;
l3mdev = inet_sk_bound_l3mdev(sk);
attempt_half = (sk->sk_reuse == SK_CAN_REUSE) ? 1 : 0;
other_half_scan:
inet_get_local_port_range(net, &low, &high);
high++; /* [32768, 60999] -> [32768, 61000[ */
if (high - low < 4)
attempt_half = 0;
if (attempt_half) {
int half = low + (((high - low) >> 2) << 1);
if (attempt_half == 1)
high = half;
else
low = half;
}
remaining = high - low;
if (likely(remaining > 1))
remaining &= ~1U;
offset = prandom_u32() % remaining;
/* __inet_hash_connect() favors ports having @low parity
* We do the opposite to not pollute connect() users.
*/
offset |= 1U;
other_parity_scan:
port = low + offset;
for (i = 0; i < remaining; i += 2, port += 2) {
if (unlikely(port >= high))
port -= remaining;
if (inet_is_local_reserved_port(net, port))
continue;
head = &hinfo->bhash[inet_bhashfn(net, port,
hinfo->bhash_size)];
spin_lock_bh(&head->lock);
inet_bind_bucket_for_each(tb, &head->chain)
if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev &&
tb->port == port) {
if (!inet_csk_bind_conflict(sk, tb, false, false))
goto success;
goto next_port;
}
tb = NULL;
goto success;
next_port:
spin_unlock_bh(&head->lock);
cond_resched();
}
offset--;
if (!(offset & 1))
goto other_parity_scan;
if (attempt_half == 1) {
/* OK we now try the upper half of the range */
attempt_half = 2;
goto other_half_scan;
}
return NULL;
success:
*port_ret = port;
*tb_ret = tb;
return head;
}
static inline int sk_reuseport_match(struct inet_bind_bucket *tb,
struct sock *sk)
{
kuid_t uid = sock_i_uid(sk);
if (tb->fastreuseport <= 0)
return 0;
if (!sk->sk_reuseport)
return 0;
if (rcu_access_pointer(sk->sk_reuseport_cb))
return 0;
if (!uid_eq(tb->fastuid, uid))
return 0;
/* We only need to check the rcv_saddr if this tb was once marked
* without fastreuseport and then was reset, as we can only know that
* the fast_*rcv_saddr doesn't have any conflicts with the socks on the
* owners list.
*/
if (tb->fastreuseport == FASTREUSEPORT_ANY)
return 1;
#if IS_ENABLED(CONFIG_IPV6)
if (tb->fast_sk_family == AF_INET6)
return ipv6_rcv_saddr_equal(&tb->fast_v6_rcv_saddr,
inet6_rcv_saddr(sk),
tb->fast_rcv_saddr,
sk->sk_rcv_saddr,
tb->fast_ipv6_only,
ipv6_only_sock(sk), true);
#endif
return ipv4_rcv_saddr_equal(tb->fast_rcv_saddr, sk->sk_rcv_saddr,
ipv6_only_sock(sk), true);
}
/* Obtain a reference to a local port for the given sock,
* if snum is zero it means select any available local port.
* We try to allocate an odd port (and leave even ports for connect())
*/
int inet_csk_get_port(struct sock *sk, unsigned short snum)
{
bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN;
struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo;
int ret = 1, port = snum;
struct inet_bind_hashbucket *head;
struct net *net = sock_net(sk);
struct inet_bind_bucket *tb = NULL;
kuid_t uid = sock_i_uid(sk);
int l3mdev;
l3mdev = inet_sk_bound_l3mdev(sk);
if (!port) {
head = inet_csk_find_open_port(sk, &tb, &port);
if (!head)
return ret;
if (!tb)
goto tb_not_found;
goto success;
}
head = &hinfo->bhash[inet_bhashfn(net, port,
hinfo->bhash_size)];
spin_lock_bh(&head->lock);
inet_bind_bucket_for_each(tb, &head->chain)
if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev &&
tb->port == port)
goto tb_found;
tb_not_found:
tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep,
net, head, port, l3mdev);
if (!tb)
goto fail_unlock;
tb_found:
if (!hlist_empty(&tb->owners)) {
if (sk->sk_reuse == SK_FORCE_REUSE)
goto success;
if ((tb->fastreuse > 0 && reuse) ||
sk_reuseport_match(tb, sk))
goto success;
if (inet_csk_bind_conflict(sk, tb, true, true))
goto fail_unlock;
}
success:
if (hlist_empty(&tb->owners)) {
tb->fastreuse = reuse;
if (sk->sk_reuseport) {
tb->fastreuseport = FASTREUSEPORT_ANY;
tb->fastuid = uid;
tb->fast_rcv_saddr = sk->sk_rcv_saddr;
tb->fast_ipv6_only = ipv6_only_sock(sk);
tb->fast_sk_family = sk->sk_family;
#if IS_ENABLED(CONFIG_IPV6)
tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
#endif
} else {
tb->fastreuseport = 0;
}
} else {
if (!reuse)
tb->fastreuse = 0;
if (sk->sk_reuseport) {
/* We didn't match or we don't have fastreuseport set on
* the tb, but we have sk_reuseport set on this socket
* and we know that there are no bind conflicts with
* this socket in this tb, so reset our tb's reuseport
* settings so that any subsequent sockets that match
* our current socket will be put on the fast path.
*
* If we reset we need to set FASTREUSEPORT_STRICT so we
* do extra checking for all subsequent sk_reuseport
* socks.
*/
if (!sk_reuseport_match(tb, sk)) {
tb->fastreuseport = FASTREUSEPORT_STRICT;
tb->fastuid = uid;
tb->fast_rcv_saddr = sk->sk_rcv_saddr;
tb->fast_ipv6_only = ipv6_only_sock(sk);
tb->fast_sk_family = sk->sk_family;
#if IS_ENABLED(CONFIG_IPV6)
tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
#endif
}
} else {
tb->fastreuseport = 0;
}
}
if (!inet_csk(sk)->icsk_bind_hash)
inet_bind_hash(sk, tb, port);
WARN_ON(inet_csk(sk)->icsk_bind_hash != tb);
ret = 0;
fail_unlock:
spin_unlock_bh(&head->lock);
return ret;
}
EXPORT_SYMBOL_GPL(inet_csk_get_port);
/*
* Wait for an incoming connection, avoid race conditions. This must be called
* with the socket locked.
*/
static int inet_csk_wait_for_connect(struct sock *sk, long timeo)
{
struct inet_connection_sock *icsk = inet_csk(sk);
DEFINE_WAIT(wait);
int err;
/*
* True wake-one mechanism for incoming connections: only
* one process gets woken up, not the 'whole herd'.
* Since we do not 'race & poll' for established sockets
* anymore, the common case will execute the loop only once.
*
* Subtle issue: "add_wait_queue_exclusive()" will be added
* after any current non-exclusive waiters, and we know that
* it will always _stay_ after any new non-exclusive waiters
* because all non-exclusive waiters are added at the
* beginning of the wait-queue. As such, it's ok to "drop"
* our exclusiveness temporarily when we get woken up without
* having to remove and re-insert us on the wait queue.
*/
for (;;) {
prepare_to_wait_exclusive(sk_sleep(sk), &wait,
TASK_INTERRUPTIBLE);
release_sock(sk);
if (reqsk_queue_empty(&icsk->icsk_accept_queue))
timeo = schedule_timeout(timeo);
inet: Clean up inet_csk_wait_for_connect() vs. might_sleep() I got the following trace with current net-next kernel : [14723.885290] WARNING: CPU: 26 PID: 22658 at kernel/sched/core.c:7285 __might_sleep+0x89/0xa0() [14723.885325] do not call blocking ops when !TASK_RUNNING; state=1 set at [<ffffffff810e8734>] prepare_to_wait_exclusive+0x34/0xa0 [14723.885355] CPU: 26 PID: 22658 Comm: netserver Not tainted 4.0.0-dbg-DEV #1379 [14723.885359] ffffffff81a223a8 ffff881fae9e7ca8 ffffffff81650b5d 0000000000000001 [14723.885364] ffff881fae9e7cf8 ffff881fae9e7ce8 ffffffff810a72e7 0000000000000000 [14723.885367] ffffffff81a57620 000000000000093a 0000000000000000 ffff881fae9e7e64 [14723.885371] Call Trace: [14723.885377] [<ffffffff81650b5d>] dump_stack+0x4c/0x65 [14723.885382] [<ffffffff810a72e7>] warn_slowpath_common+0x97/0xe0 [14723.885386] [<ffffffff810a73e6>] warn_slowpath_fmt+0x46/0x50 [14723.885390] [<ffffffff810f4c5d>] ? trace_hardirqs_on_caller+0x10d/0x1d0 [14723.885393] [<ffffffff810e8734>] ? prepare_to_wait_exclusive+0x34/0xa0 [14723.885396] [<ffffffff810e8734>] ? prepare_to_wait_exclusive+0x34/0xa0 [14723.885399] [<ffffffff810ccdc9>] __might_sleep+0x89/0xa0 [14723.885403] [<ffffffff81581846>] lock_sock_nested+0x36/0xb0 [14723.885406] [<ffffffff815829a3>] ? release_sock+0x173/0x1c0 [14723.885411] [<ffffffff815ea1f7>] inet_csk_accept+0x157/0x2a0 [14723.885415] [<ffffffff810e8900>] ? abort_exclusive_wait+0xc0/0xc0 [14723.885419] [<ffffffff8161b96d>] inet_accept+0x2d/0x150 [14723.885424] [<ffffffff8157db6f>] SYSC_accept4+0xff/0x210 [14723.885428] [<ffffffff8165a451>] ? retint_swapgs+0xe/0x44 [14723.885431] [<ffffffff810f4c5d>] ? trace_hardirqs_on_caller+0x10d/0x1d0 [14723.885437] [<ffffffff81369c0e>] ? trace_hardirqs_on_thunk+0x3a/0x3f [14723.885441] [<ffffffff8157ef40>] SyS_accept+0x10/0x20 [14723.885444] [<ffffffff81659872>] system_call_fastpath+0x12/0x17 [14723.885447] ---[ end trace ff74cd83355b1873 ]--- In commit 26cabd31259ba43f68026ce3f62b78094124333f Peter added a sched_annotate_sleep() in sk_wait_event() Is the following patch needed as well ? Alternative would be to use sk_wait_event() from inet_csk_wait_for_connect() Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-17 02:19:24 +07:00
sched_annotate_sleep();
lock_sock(sk);
err = 0;
if (!reqsk_queue_empty(&icsk->icsk_accept_queue))
break;
err = -EINVAL;
if (sk->sk_state != TCP_LISTEN)
break;
err = sock_intr_errno(timeo);
if (signal_pending(current))
break;
err = -EAGAIN;
if (!timeo)
break;
}
finish_wait(sk_sleep(sk), &wait);
return err;
}
/*
* This will accept the next outstanding connection.
*/
net: Work around lockdep limitation in sockets that use sockets Lockdep issues a circular dependency warning when AFS issues an operation through AF_RXRPC from a context in which the VFS/VM holds the mmap_sem. The theory lockdep comes up with is as follows: (1) If the pagefault handler decides it needs to read pages from AFS, it calls AFS with mmap_sem held and AFS begins an AF_RXRPC call, but creating a call requires the socket lock: mmap_sem must be taken before sk_lock-AF_RXRPC (2) afs_open_socket() opens an AF_RXRPC socket and binds it. rxrpc_bind() binds the underlying UDP socket whilst holding its socket lock. inet_bind() takes its own socket lock: sk_lock-AF_RXRPC must be taken before sk_lock-AF_INET (3) Reading from a TCP socket into a userspace buffer might cause a fault and thus cause the kernel to take the mmap_sem, but the TCP socket is locked whilst doing this: sk_lock-AF_INET must be taken before mmap_sem However, lockdep's theory is wrong in this instance because it deals only with lock classes and not individual locks. The AF_INET lock in (2) isn't really equivalent to the AF_INET lock in (3) as the former deals with a socket entirely internal to the kernel that never sees userspace. This is a limitation in the design of lockdep. Fix the general case by: (1) Double up all the locking keys used in sockets so that one set are used if the socket is created by userspace and the other set is used if the socket is created by the kernel. (2) Store the kern parameter passed to sk_alloc() in a variable in the sock struct (sk_kern_sock). This informs sock_lock_init(), sock_init_data() and sk_clone_lock() as to the lock keys to be used. Note that the child created by sk_clone_lock() inherits the parent's kern setting. (3) Add a 'kern' parameter to ->accept() that is analogous to the one passed in to ->create() that distinguishes whether kernel_accept() or sys_accept4() was the caller and can be passed to sk_alloc(). Note that a lot of accept functions merely dequeue an already allocated socket. I haven't touched these as the new socket already exists before we get the parameter. Note also that there are a couple of places where I've made the accepted socket unconditionally kernel-based: irda_accept() rds_rcp_accept_one() tcp_accept_from_sock() because they follow a sock_create_kern() and accept off of that. Whilst creating this, I noticed that lustre and ocfs don't create sockets through sock_create_kern() and thus they aren't marked as for-kernel, though they appear to be internal. I wonder if these should do that so that they use the new set of lock keys. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 15:09:05 +07:00
struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct request_sock_queue *queue = &icsk->icsk_accept_queue;
struct request_sock *req;
struct sock *newsk;
int error;
lock_sock(sk);
/* We need to make sure that this socket is listening,
* and that it has something pending.
*/
error = -EINVAL;
if (sk->sk_state != TCP_LISTEN)
goto out_err;
/* Find already established connection */
if (reqsk_queue_empty(queue)) {
long timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK);
/* If this is a non blocking socket don't sleep */
error = -EAGAIN;
if (!timeo)
goto out_err;
error = inet_csk_wait_for_connect(sk, timeo);
if (error)
goto out_err;
}
req = reqsk_queue_remove(queue, sk);
newsk = req->sk;
if (sk->sk_protocol == IPPROTO_TCP &&
tcp_rsk(req)->tfo_listener) {
spin_lock_bh(&queue->fastopenq.lock);
if (tcp_rsk(req)->tfo_listener) {
/* We are still waiting for the final ACK from 3WHS
* so can't free req now. Instead, we set req->sk to
* NULL to signify that the child socket is taken
* so reqsk_fastopen_remove() will free the req
* when 3WHS finishes (or is aborted).
*/
req->sk = NULL;
req = NULL;
}
spin_unlock_bh(&queue->fastopenq.lock);
}
out:
release_sock(sk);
if (req)
reqsk_put(req);
return newsk;
out_err:
newsk = NULL;
req = NULL;
*err = error;
goto out;
}
EXPORT_SYMBOL(inet_csk_accept);
/*
* Using different timers for retransmit, delayed acks and probes
* We may wish use just one timer maintaining a list of expire jiffies
* to optimize.
*/
void inet_csk_init_xmit_timers(struct sock *sk,
void (*retransmit_handler)(struct timer_list *t),
void (*delack_handler)(struct timer_list *t),
void (*keepalive_handler)(struct timer_list *t))
{
struct inet_connection_sock *icsk = inet_csk(sk);
timer_setup(&icsk->icsk_retransmit_timer, retransmit_handler, 0);
timer_setup(&icsk->icsk_delack_timer, delack_handler, 0);
timer_setup(&sk->sk_timer, keepalive_handler, 0);
icsk->icsk_pending = icsk->icsk_ack.pending = 0;
}
EXPORT_SYMBOL(inet_csk_init_xmit_timers);
void inet_csk_clear_xmit_timers(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
icsk->icsk_pending = icsk->icsk_ack.pending = icsk->icsk_ack.blocked = 0;
sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
sk_stop_timer(sk, &icsk->icsk_delack_timer);
sk_stop_timer(sk, &sk->sk_timer);
}
EXPORT_SYMBOL(inet_csk_clear_xmit_timers);
void inet_csk_delete_keepalive_timer(struct sock *sk)
{
sk_stop_timer(sk, &sk->sk_timer);
}
EXPORT_SYMBOL(inet_csk_delete_keepalive_timer);
void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long len)
{
sk_reset_timer(sk, &sk->sk_timer, jiffies + len);
}
EXPORT_SYMBOL(inet_csk_reset_keepalive_timer);
struct dst_entry *inet_csk_route_req(const struct sock *sk,
struct flowi4 *fl4,
const struct request_sock *req)
{
const struct inet_request_sock *ireq = inet_rsk(req);
struct net *net = read_pnet(&ireq->ireq_net);
tcp/dccp: fix ireq->opt races syzkaller found another bug in DCCP/TCP stacks [1] For the reasons explained in commit ce1050089c96 ("tcp/dccp: fix ireq->pktopts race"), we need to make sure we do not access ireq->opt unless we own the request sock. Note the opt field is renamed to ireq_opt to ease grep games. [1] BUG: KASAN: use-after-free in ip_queue_xmit+0x1687/0x18e0 net/ipv4/ip_output.c:474 Read of size 1 at addr ffff8801c951039c by task syz-executor5/3295 CPU: 1 PID: 3295 Comm: syz-executor5 Not tainted 4.14.0-rc4+ #80 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:16 [inline] dump_stack+0x194/0x257 lib/dump_stack.c:52 print_address_description+0x73/0x250 mm/kasan/report.c:252 kasan_report_error mm/kasan/report.c:351 [inline] kasan_report+0x25b/0x340 mm/kasan/report.c:409 __asan_report_load1_noabort+0x14/0x20 mm/kasan/report.c:427 ip_queue_xmit+0x1687/0x18e0 net/ipv4/ip_output.c:474 tcp_transmit_skb+0x1ab7/0x3840 net/ipv4/tcp_output.c:1135 tcp_send_ack.part.37+0x3bb/0x650 net/ipv4/tcp_output.c:3587 tcp_send_ack+0x49/0x60 net/ipv4/tcp_output.c:3557 __tcp_ack_snd_check+0x2c6/0x4b0 net/ipv4/tcp_input.c:5072 tcp_ack_snd_check net/ipv4/tcp_input.c:5085 [inline] tcp_rcv_state_process+0x2eff/0x4850 net/ipv4/tcp_input.c:6071 tcp_child_process+0x342/0x990 net/ipv4/tcp_minisocks.c:816 tcp_v4_rcv+0x1827/0x2f80 net/ipv4/tcp_ipv4.c:1682 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216 NF_HOOK include/linux/netfilter.h:249 [inline] ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257 dst_input include/net/dst.h:464 [inline] ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397 NF_HOOK include/linux/netfilter.h:249 [inline] ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587 netif_receive_skb+0xae/0x390 net/core/dev.c:4611 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792 call_write_iter include/linux/fs.h:1770 [inline] new_sync_write fs/read_write.c:468 [inline] __vfs_write+0x68a/0x970 fs/read_write.c:481 vfs_write+0x18f/0x510 fs/read_write.c:543 SYSC_write fs/read_write.c:588 [inline] SyS_write+0xef/0x220 fs/read_write.c:580 entry_SYSCALL_64_fastpath+0x1f/0xbe RIP: 0033:0x40c341 RSP: 002b:00007f469523ec10 EFLAGS: 00000293 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000718000 RCX: 000000000040c341 RDX: 0000000000000037 RSI: 0000000020004000 RDI: 0000000000000015 RBP: 0000000000000086 R08: 0000000000000000 R09: 0000000000000000 R10: 00000000000f4240 R11: 0000000000000293 R12: 00000000004b7fd1 R13: 00000000ffffffff R14: 0000000020000000 R15: 0000000000025000 Allocated by task 3295: save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59 save_stack+0x43/0xd0 mm/kasan/kasan.c:447 set_track mm/kasan/kasan.c:459 [inline] kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:551 __do_kmalloc mm/slab.c:3725 [inline] __kmalloc+0x162/0x760 mm/slab.c:3734 kmalloc include/linux/slab.h:498 [inline] tcp_v4_save_options include/net/tcp.h:1962 [inline] tcp_v4_init_req+0x2d3/0x3e0 net/ipv4/tcp_ipv4.c:1271 tcp_conn_request+0xf6d/0x3410 net/ipv4/tcp_input.c:6283 tcp_v4_conn_request+0x157/0x210 net/ipv4/tcp_ipv4.c:1313 tcp_rcv_state_process+0x8ea/0x4850 net/ipv4/tcp_input.c:5857 tcp_v4_do_rcv+0x55c/0x7d0 net/ipv4/tcp_ipv4.c:1482 tcp_v4_rcv+0x2d10/0x2f80 net/ipv4/tcp_ipv4.c:1711 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216 NF_HOOK include/linux/netfilter.h:249 [inline] ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257 dst_input include/net/dst.h:464 [inline] ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397 NF_HOOK include/linux/netfilter.h:249 [inline] ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587 netif_receive_skb+0xae/0x390 net/core/dev.c:4611 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792 call_write_iter include/linux/fs.h:1770 [inline] new_sync_write fs/read_write.c:468 [inline] __vfs_write+0x68a/0x970 fs/read_write.c:481 vfs_write+0x18f/0x510 fs/read_write.c:543 SYSC_write fs/read_write.c:588 [inline] SyS_write+0xef/0x220 fs/read_write.c:580 entry_SYSCALL_64_fastpath+0x1f/0xbe Freed by task 3306: save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59 save_stack+0x43/0xd0 mm/kasan/kasan.c:447 set_track mm/kasan/kasan.c:459 [inline] kasan_slab_free+0x71/0xc0 mm/kasan/kasan.c:524 __cache_free mm/slab.c:3503 [inline] kfree+0xca/0x250 mm/slab.c:3820 inet_sock_destruct+0x59d/0x950 net/ipv4/af_inet.c:157 __sk_destruct+0xfd/0x910 net/core/sock.c:1560 sk_destruct+0x47/0x80 net/core/sock.c:1595 __sk_free+0x57/0x230 net/core/sock.c:1603 sk_free+0x2a/0x40 net/core/sock.c:1614 sock_put include/net/sock.h:1652 [inline] inet_csk_complete_hashdance+0xd5/0xf0 net/ipv4/inet_connection_sock.c:959 tcp_check_req+0xf4d/0x1620 net/ipv4/tcp_minisocks.c:765 tcp_v4_rcv+0x17f6/0x2f80 net/ipv4/tcp_ipv4.c:1675 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216 NF_HOOK include/linux/netfilter.h:249 [inline] ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257 dst_input include/net/dst.h:464 [inline] ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397 NF_HOOK include/linux/netfilter.h:249 [inline] ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587 netif_receive_skb+0xae/0x390 net/core/dev.c:4611 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792 call_write_iter include/linux/fs.h:1770 [inline] new_sync_write fs/read_write.c:468 [inline] __vfs_write+0x68a/0x970 fs/read_write.c:481 vfs_write+0x18f/0x510 fs/read_write.c:543 SYSC_write fs/read_write.c:588 [inline] SyS_write+0xef/0x220 fs/read_write.c:580 entry_SYSCALL_64_fastpath+0x1f/0xbe Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets") Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table") Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-20 23:04:13 +07:00
struct ip_options_rcu *opt;
struct rtable *rt;
rcu_read_lock();
opt = rcu_dereference(ireq->ireq_opt);
tcp/dccp: fix other lockdep splats accessing ireq_opt In my first attempt to fix the lockdep splat, I forgot we could enter inet_csk_route_req() with a freshly allocated request socket, for which refcount has not yet been elevated, due to complex SLAB_TYPESAFE_BY_RCU rules. We either are in rcu_read_lock() section _or_ we own a refcount on the request. Correct RCU verb to use here is rcu_dereference_check(), although it is not possible to prove we actually own a reference on a shared refcount :/ In v2, I added ireq_opt_deref() helper and use in three places, to fix other possible splats. [ 49.844590] lockdep_rcu_suspicious+0xea/0xf3 [ 49.846487] inet_csk_route_req+0x53/0x14d [ 49.848334] tcp_v4_route_req+0xe/0x10 [ 49.850174] tcp_conn_request+0x31c/0x6a0 [ 49.851992] ? __lock_acquire+0x614/0x822 [ 49.854015] tcp_v4_conn_request+0x5a/0x79 [ 49.855957] ? tcp_v4_conn_request+0x5a/0x79 [ 49.858052] tcp_rcv_state_process+0x98/0xdcc [ 49.859990] ? sk_filter_trim_cap+0x2f6/0x307 [ 49.862085] tcp_v4_do_rcv+0xfc/0x145 [ 49.864055] ? tcp_v4_do_rcv+0xfc/0x145 [ 49.866173] tcp_v4_rcv+0x5ab/0xaf9 [ 49.868029] ip_local_deliver_finish+0x1af/0x2e7 [ 49.870064] ip_local_deliver+0x1b2/0x1c5 [ 49.871775] ? inet_del_offload+0x45/0x45 [ 49.873916] ip_rcv_finish+0x3f7/0x471 [ 49.875476] ip_rcv+0x3f1/0x42f [ 49.876991] ? ip_local_deliver_finish+0x2e7/0x2e7 [ 49.878791] __netif_receive_skb_core+0x6d3/0x950 [ 49.880701] ? process_backlog+0x7e/0x216 [ 49.882589] __netif_receive_skb+0x1d/0x5e [ 49.884122] process_backlog+0x10c/0x216 [ 49.885812] net_rx_action+0x147/0x3df Fixes: a6ca7abe53633 ("tcp/dccp: fix lockdep splat in inet_csk_route_req()") Fixes: c92e8c02fe66 ("tcp/dccp: fix ireq->opt races") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: kernel test robot <fengguang.wu@intel.com> Reported-by: Maciej Żenczykowski <maze@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-24 22:20:31 +07:00
flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
sk->sk_protocol, inet_sk_flowi_flags(sk),
(opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
ireq->ir_loc_addr, ireq->ir_rmt_port,
htons(ireq->ir_num), sk->sk_uid);
security_req_classify_flow(req, flowi4_to_flowi(fl4));
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
goto no_route;
if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
goto route_err;
rcu_read_unlock();
return &rt->dst;
route_err:
ip_rt_put(rt);
no_route:
rcu_read_unlock();
__IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
return NULL;
}
EXPORT_SYMBOL_GPL(inet_csk_route_req);
struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
struct sock *newsk,
const struct request_sock *req)
{
const struct inet_request_sock *ireq = inet_rsk(req);
struct net *net = read_pnet(&ireq->ireq_net);
struct inet_sock *newinet = inet_sk(newsk);
struct ip_options_rcu *opt;
struct flowi4 *fl4;
struct rtable *rt;
tcp/dccp: fix ireq->opt races syzkaller found another bug in DCCP/TCP stacks [1] For the reasons explained in commit ce1050089c96 ("tcp/dccp: fix ireq->pktopts race"), we need to make sure we do not access ireq->opt unless we own the request sock. Note the opt field is renamed to ireq_opt to ease grep games. [1] BUG: KASAN: use-after-free in ip_queue_xmit+0x1687/0x18e0 net/ipv4/ip_output.c:474 Read of size 1 at addr ffff8801c951039c by task syz-executor5/3295 CPU: 1 PID: 3295 Comm: syz-executor5 Not tainted 4.14.0-rc4+ #80 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:16 [inline] dump_stack+0x194/0x257 lib/dump_stack.c:52 print_address_description+0x73/0x250 mm/kasan/report.c:252 kasan_report_error mm/kasan/report.c:351 [inline] kasan_report+0x25b/0x340 mm/kasan/report.c:409 __asan_report_load1_noabort+0x14/0x20 mm/kasan/report.c:427 ip_queue_xmit+0x1687/0x18e0 net/ipv4/ip_output.c:474 tcp_transmit_skb+0x1ab7/0x3840 net/ipv4/tcp_output.c:1135 tcp_send_ack.part.37+0x3bb/0x650 net/ipv4/tcp_output.c:3587 tcp_send_ack+0x49/0x60 net/ipv4/tcp_output.c:3557 __tcp_ack_snd_check+0x2c6/0x4b0 net/ipv4/tcp_input.c:5072 tcp_ack_snd_check net/ipv4/tcp_input.c:5085 [inline] tcp_rcv_state_process+0x2eff/0x4850 net/ipv4/tcp_input.c:6071 tcp_child_process+0x342/0x990 net/ipv4/tcp_minisocks.c:816 tcp_v4_rcv+0x1827/0x2f80 net/ipv4/tcp_ipv4.c:1682 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216 NF_HOOK include/linux/netfilter.h:249 [inline] ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257 dst_input include/net/dst.h:464 [inline] ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397 NF_HOOK include/linux/netfilter.h:249 [inline] ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587 netif_receive_skb+0xae/0x390 net/core/dev.c:4611 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792 call_write_iter include/linux/fs.h:1770 [inline] new_sync_write fs/read_write.c:468 [inline] __vfs_write+0x68a/0x970 fs/read_write.c:481 vfs_write+0x18f/0x510 fs/read_write.c:543 SYSC_write fs/read_write.c:588 [inline] SyS_write+0xef/0x220 fs/read_write.c:580 entry_SYSCALL_64_fastpath+0x1f/0xbe RIP: 0033:0x40c341 RSP: 002b:00007f469523ec10 EFLAGS: 00000293 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000718000 RCX: 000000000040c341 RDX: 0000000000000037 RSI: 0000000020004000 RDI: 0000000000000015 RBP: 0000000000000086 R08: 0000000000000000 R09: 0000000000000000 R10: 00000000000f4240 R11: 0000000000000293 R12: 00000000004b7fd1 R13: 00000000ffffffff R14: 0000000020000000 R15: 0000000000025000 Allocated by task 3295: save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59 save_stack+0x43/0xd0 mm/kasan/kasan.c:447 set_track mm/kasan/kasan.c:459 [inline] kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:551 __do_kmalloc mm/slab.c:3725 [inline] __kmalloc+0x162/0x760 mm/slab.c:3734 kmalloc include/linux/slab.h:498 [inline] tcp_v4_save_options include/net/tcp.h:1962 [inline] tcp_v4_init_req+0x2d3/0x3e0 net/ipv4/tcp_ipv4.c:1271 tcp_conn_request+0xf6d/0x3410 net/ipv4/tcp_input.c:6283 tcp_v4_conn_request+0x157/0x210 net/ipv4/tcp_ipv4.c:1313 tcp_rcv_state_process+0x8ea/0x4850 net/ipv4/tcp_input.c:5857 tcp_v4_do_rcv+0x55c/0x7d0 net/ipv4/tcp_ipv4.c:1482 tcp_v4_rcv+0x2d10/0x2f80 net/ipv4/tcp_ipv4.c:1711 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216 NF_HOOK include/linux/netfilter.h:249 [inline] ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257 dst_input include/net/dst.h:464 [inline] ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397 NF_HOOK include/linux/netfilter.h:249 [inline] ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587 netif_receive_skb+0xae/0x390 net/core/dev.c:4611 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792 call_write_iter include/linux/fs.h:1770 [inline] new_sync_write fs/read_write.c:468 [inline] __vfs_write+0x68a/0x970 fs/read_write.c:481 vfs_write+0x18f/0x510 fs/read_write.c:543 SYSC_write fs/read_write.c:588 [inline] SyS_write+0xef/0x220 fs/read_write.c:580 entry_SYSCALL_64_fastpath+0x1f/0xbe Freed by task 3306: save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59 save_stack+0x43/0xd0 mm/kasan/kasan.c:447 set_track mm/kasan/kasan.c:459 [inline] kasan_slab_free+0x71/0xc0 mm/kasan/kasan.c:524 __cache_free mm/slab.c:3503 [inline] kfree+0xca/0x250 mm/slab.c:3820 inet_sock_destruct+0x59d/0x950 net/ipv4/af_inet.c:157 __sk_destruct+0xfd/0x910 net/core/sock.c:1560 sk_destruct+0x47/0x80 net/core/sock.c:1595 __sk_free+0x57/0x230 net/core/sock.c:1603 sk_free+0x2a/0x40 net/core/sock.c:1614 sock_put include/net/sock.h:1652 [inline] inet_csk_complete_hashdance+0xd5/0xf0 net/ipv4/inet_connection_sock.c:959 tcp_check_req+0xf4d/0x1620 net/ipv4/tcp_minisocks.c:765 tcp_v4_rcv+0x17f6/0x2f80 net/ipv4/tcp_ipv4.c:1675 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216 NF_HOOK include/linux/netfilter.h:249 [inline] ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257 dst_input include/net/dst.h:464 [inline] ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397 NF_HOOK include/linux/netfilter.h:249 [inline] ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587 netif_receive_skb+0xae/0x390 net/core/dev.c:4611 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792 call_write_iter include/linux/fs.h:1770 [inline] new_sync_write fs/read_write.c:468 [inline] __vfs_write+0x68a/0x970 fs/read_write.c:481 vfs_write+0x18f/0x510 fs/read_write.c:543 SYSC_write fs/read_write.c:588 [inline] SyS_write+0xef/0x220 fs/read_write.c:580 entry_SYSCALL_64_fastpath+0x1f/0xbe Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets") Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table") Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-20 23:04:13 +07:00
opt = rcu_dereference(ireq->ireq_opt);
fl4 = &newinet->cork.fl.u.ip4;
flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
sk->sk_protocol, inet_sk_flowi_flags(sk),
(opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
ireq->ir_loc_addr, ireq->ir_rmt_port,
htons(ireq->ir_num), sk->sk_uid);
security_req_classify_flow(req, flowi4_to_flowi(fl4));
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
goto no_route;
if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
goto route_err;
return &rt->dst;
route_err:
ip_rt_put(rt);
no_route:
__IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
return NULL;
}
EXPORT_SYMBOL_GPL(inet_csk_route_child_sock);
#if IS_ENABLED(CONFIG_IPV6)
#define AF_INET_FAMILY(fam) ((fam) == AF_INET)
#else
#define AF_INET_FAMILY(fam) true
#endif
/* Decide when to expire the request and when to resend SYN-ACK */
static inline void syn_ack_recalc(struct request_sock *req, const int thresh,
const int max_retries,
const u8 rskq_defer_accept,
int *expire, int *resend)
{
if (!rskq_defer_accept) {
tcp: better retrans tracking for defer-accept For passive TCP connections using TCP_DEFER_ACCEPT facility, we incorrectly increment req->retrans each time timeout triggers while no SYNACK is sent. SYNACK are not sent for TCP_DEFER_ACCEPT that were established (for which we received the ACK from client). Only the last SYNACK is sent so that we can receive again an ACK from client, to move the req into accept queue. We plan to change this later to avoid the useless retransmit (and potential problem as this SYNACK could be lost) TCP_INFO later gives wrong information to user, claiming imaginary retransmits. Decouple req->retrans field into two independent fields : num_retrans : number of retransmit num_timeout : number of timeouts num_timeout is the counter that is incremented at each timeout, regardless of actual SYNACK being sent or not, and used to compute the exponential timeout. Introduce inet_rtx_syn_ack() helper to increment num_retrans only if ->rtx_syn_ack() succeeded. Use inet_rtx_syn_ack() from tcp_check_req() to increment num_retrans when we re-send a SYNACK in answer to a (retransmitted) SYN. Prior to this patch, we were not counting these retransmits. Change tcp_v[46]_rtx_synack() to increment TCP_MIB_RETRANSSEGS only if a synack packet was successfully queued. Reported-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Julian Anastasov <ja@ssi.bg> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Elliott Hughes <enh@google.com> Cc: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-10-28 06:16:46 +07:00
*expire = req->num_timeout >= thresh;
*resend = 1;
return;
}
tcp: better retrans tracking for defer-accept For passive TCP connections using TCP_DEFER_ACCEPT facility, we incorrectly increment req->retrans each time timeout triggers while no SYNACK is sent. SYNACK are not sent for TCP_DEFER_ACCEPT that were established (for which we received the ACK from client). Only the last SYNACK is sent so that we can receive again an ACK from client, to move the req into accept queue. We plan to change this later to avoid the useless retransmit (and potential problem as this SYNACK could be lost) TCP_INFO later gives wrong information to user, claiming imaginary retransmits. Decouple req->retrans field into two independent fields : num_retrans : number of retransmit num_timeout : number of timeouts num_timeout is the counter that is incremented at each timeout, regardless of actual SYNACK being sent or not, and used to compute the exponential timeout. Introduce inet_rtx_syn_ack() helper to increment num_retrans only if ->rtx_syn_ack() succeeded. Use inet_rtx_syn_ack() from tcp_check_req() to increment num_retrans when we re-send a SYNACK in answer to a (retransmitted) SYN. Prior to this patch, we were not counting these retransmits. Change tcp_v[46]_rtx_synack() to increment TCP_MIB_RETRANSSEGS only if a synack packet was successfully queued. Reported-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Julian Anastasov <ja@ssi.bg> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Elliott Hughes <enh@google.com> Cc: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-10-28 06:16:46 +07:00
*expire = req->num_timeout >= thresh &&
(!inet_rsk(req)->acked || req->num_timeout >= max_retries);
/*
* Do not resend while waiting for data after ACK,
* start to resend on end of deferring period to give
* last chance for data or ACK to create established socket.
*/
*resend = !inet_rsk(req)->acked ||
tcp: better retrans tracking for defer-accept For passive TCP connections using TCP_DEFER_ACCEPT facility, we incorrectly increment req->retrans each time timeout triggers while no SYNACK is sent. SYNACK are not sent for TCP_DEFER_ACCEPT that were established (for which we received the ACK from client). Only the last SYNACK is sent so that we can receive again an ACK from client, to move the req into accept queue. We plan to change this later to avoid the useless retransmit (and potential problem as this SYNACK could be lost) TCP_INFO later gives wrong information to user, claiming imaginary retransmits. Decouple req->retrans field into two independent fields : num_retrans : number of retransmit num_timeout : number of timeouts num_timeout is the counter that is incremented at each timeout, regardless of actual SYNACK being sent or not, and used to compute the exponential timeout. Introduce inet_rtx_syn_ack() helper to increment num_retrans only if ->rtx_syn_ack() succeeded. Use inet_rtx_syn_ack() from tcp_check_req() to increment num_retrans when we re-send a SYNACK in answer to a (retransmitted) SYN. Prior to this patch, we were not counting these retransmits. Change tcp_v[46]_rtx_synack() to increment TCP_MIB_RETRANSSEGS only if a synack packet was successfully queued. Reported-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Julian Anastasov <ja@ssi.bg> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Elliott Hughes <enh@google.com> Cc: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-10-28 06:16:46 +07:00
req->num_timeout >= rskq_defer_accept - 1;
}
int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req)
tcp: better retrans tracking for defer-accept For passive TCP connections using TCP_DEFER_ACCEPT facility, we incorrectly increment req->retrans each time timeout triggers while no SYNACK is sent. SYNACK are not sent for TCP_DEFER_ACCEPT that were established (for which we received the ACK from client). Only the last SYNACK is sent so that we can receive again an ACK from client, to move the req into accept queue. We plan to change this later to avoid the useless retransmit (and potential problem as this SYNACK could be lost) TCP_INFO later gives wrong information to user, claiming imaginary retransmits. Decouple req->retrans field into two independent fields : num_retrans : number of retransmit num_timeout : number of timeouts num_timeout is the counter that is incremented at each timeout, regardless of actual SYNACK being sent or not, and used to compute the exponential timeout. Introduce inet_rtx_syn_ack() helper to increment num_retrans only if ->rtx_syn_ack() succeeded. Use inet_rtx_syn_ack() from tcp_check_req() to increment num_retrans when we re-send a SYNACK in answer to a (retransmitted) SYN. Prior to this patch, we were not counting these retransmits. Change tcp_v[46]_rtx_synack() to increment TCP_MIB_RETRANSSEGS only if a synack packet was successfully queued. Reported-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Julian Anastasov <ja@ssi.bg> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Elliott Hughes <enh@google.com> Cc: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-10-28 06:16:46 +07:00
{
int err = req->rsk_ops->rtx_syn_ack(parent, req);
tcp: better retrans tracking for defer-accept For passive TCP connections using TCP_DEFER_ACCEPT facility, we incorrectly increment req->retrans each time timeout triggers while no SYNACK is sent. SYNACK are not sent for TCP_DEFER_ACCEPT that were established (for which we received the ACK from client). Only the last SYNACK is sent so that we can receive again an ACK from client, to move the req into accept queue. We plan to change this later to avoid the useless retransmit (and potential problem as this SYNACK could be lost) TCP_INFO later gives wrong information to user, claiming imaginary retransmits. Decouple req->retrans field into two independent fields : num_retrans : number of retransmit num_timeout : number of timeouts num_timeout is the counter that is incremented at each timeout, regardless of actual SYNACK being sent or not, and used to compute the exponential timeout. Introduce inet_rtx_syn_ack() helper to increment num_retrans only if ->rtx_syn_ack() succeeded. Use inet_rtx_syn_ack() from tcp_check_req() to increment num_retrans when we re-send a SYNACK in answer to a (retransmitted) SYN. Prior to this patch, we were not counting these retransmits. Change tcp_v[46]_rtx_synack() to increment TCP_MIB_RETRANSSEGS only if a synack packet was successfully queued. Reported-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Julian Anastasov <ja@ssi.bg> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Elliott Hughes <enh@google.com> Cc: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-10-28 06:16:46 +07:00
if (!err)
req->num_retrans++;
return err;
}
EXPORT_SYMBOL(inet_rtx_syn_ack);
/* return true if req was found in the ehash table */
static bool reqsk_queue_unlink(struct request_sock_queue *queue,
struct request_sock *req)
{
struct inet_hashinfo *hashinfo = req_to_sk(req)->sk_prot->h.hashinfo;
bool found = false;
if (sk_hashed(req_to_sk(req))) {
spinlock_t *lock = inet_ehash_lockp(hashinfo, req->rsk_hash);
spin_lock(lock);
found = __sk_nulls_del_node_init_rcu(req_to_sk(req));
spin_unlock(lock);
}
if (timer_pending(&req->rsk_timer) && del_timer_sync(&req->rsk_timer))
reqsk_put(req);
return found;
}
void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req)
{
if (reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req)) {
reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
reqsk_put(req);
}
}
EXPORT_SYMBOL(inet_csk_reqsk_queue_drop);
void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req)
{
inet_csk_reqsk_queue_drop(sk, req);
reqsk_put(req);
}
EXPORT_SYMBOL(inet_csk_reqsk_queue_drop_and_put);
static void reqsk_timer_handler(struct timer_list *t)
{
struct request_sock *req = from_timer(req, t, rsk_timer);
struct sock *sk_listener = req->rsk_listener;
struct net *net = sock_net(sk_listener);
struct inet_connection_sock *icsk = inet_csk(sk_listener);
struct request_sock_queue *queue = &icsk->icsk_accept_queue;
int qlen, expire = 0, resend = 0;
int max_retries, thresh;
u8 defer_accept;
if (inet_sk_state_load(sk_listener) != TCP_LISTEN)
goto drop;
max_retries = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_synack_retries;
thresh = max_retries;
/* Normally all the openreqs are young and become mature
* (i.e. converted to established socket) for first timeout.
* If synack was not acknowledged for 1 second, it means
* one of the following things: synack was lost, ack was lost,
* rtt is high or nobody planned to ack (i.e. synflood).
* When server is a bit loaded, queue is populated with old
* open requests, reducing effective size of queue.
* When server is well loaded, queue size reduces to zero
* after several minutes of work. It is not synflood,
* it is normal operation. The solution is pruning
* too old entries overriding normal timeout, when
* situation becomes dangerous.
*
* Essentially, we reserve half of room for young
* embrions; and abort old ones without pity, if old
* ones are about to clog our table.
*/
qlen = reqsk_queue_len(queue);
if ((qlen << 1) > max(8U, sk_listener->sk_max_ack_backlog)) {
int young = reqsk_queue_len_young(queue) << 1;
while (thresh > 2) {
if (qlen < young)
break;
thresh--;
young <<= 1;
}
}
defer_accept = READ_ONCE(queue->rskq_defer_accept);
if (defer_accept)
max_retries = defer_accept;
syn_ack_recalc(req, thresh, max_retries, defer_accept,
&expire, &resend);
req->rsk_ops->syn_ack_timeout(req);
if (!expire &&
(!resend ||
!inet_rtx_syn_ack(sk_listener, req) ||
inet_rsk(req)->acked)) {
unsigned long timeo;
if (req->num_timeout++ == 0)
atomic_dec(&queue->young);
timeo = min(TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX);
mod_timer(&req->rsk_timer, jiffies + timeo);
return;
}
drop:
inet_csk_reqsk_queue_drop_and_put(sk_listener, req);
}
tcp: Revert 'process defer accept as established' changes. This reverts two changesets, ec3c0982a2dd1e671bad8e9d26c28dcba0039d87 ("[TCP]: TCP_DEFER_ACCEPT updates - process as established") and the follow-on bug fix 9ae27e0adbf471c7a6b80102e38e1d5a346b3b38 ("tcp: Fix slab corruption with ipv6 and tcp6fuzz"). This change causes several problems, first reported by Ingo Molnar as a distcc-over-loopback regression where connections were getting stuck. Ilpo Järvinen first spotted the locking problems. The new function added by this code, tcp_defer_accept_check(), only has the child socket locked, yet it is modifying state of the parent listening socket. Fixing that is non-trivial at best, because we can't simply just grab the parent listening socket lock at this point, because it would create an ABBA deadlock. The normal ordering is parent listening socket --> child socket, but this code path would require the reverse lock ordering. Next is a problem noticed by Vitaliy Gusev, he noted: ---------------------------------------- >--- a/net/ipv4/tcp_timer.c >+++ b/net/ipv4/tcp_timer.c >@@ -481,6 +481,11 @@ static void tcp_keepalive_timer (unsigned long data) > goto death; > } > >+ if (tp->defer_tcp_accept.request && sk->sk_state == TCP_ESTABLISHED) { >+ tcp_send_active_reset(sk, GFP_ATOMIC); >+ goto death; Here socket sk is not attached to listening socket's request queue. tcp_done() will not call inet_csk_destroy_sock() (and tcp_v4_destroy_sock() which should release this sk) as socket is not DEAD. Therefore socket sk will be lost for freeing. ---------------------------------------- Finally, Alexey Kuznetsov argues that there might not even be any real value or advantage to these new semantics even if we fix all of the bugs: ---------------------------------------- Hiding from accept() sockets with only out-of-order data only is the only thing which is impossible with old approach. Is this really so valuable? My opinion: no, this is nothing but a new loophole to consume memory without control. ---------------------------------------- So revert this thing for now. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-06-13 06:31:35 +07:00
static void reqsk_queue_hash_req(struct request_sock *req,
unsigned long timeout)
{
req->num_retrans = 0;
req->num_timeout = 0;
req->sk = NULL;
timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED);
mod_timer(&req->rsk_timer, jiffies + timeout);
inet_ehash_insert(req_to_sk(req), NULL);
/* before letting lookups find us, make sure all req fields
* are committed to memory and refcnt initialized.
*/
smp_wmb();
refcount_set(&req->rsk_refcnt, 2 + 1);
}
void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
unsigned long timeout)
{
reqsk_queue_hash_req(req, timeout);
inet_csk_reqsk_queue_added(sk);
}
EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add);
/**
* inet_csk_clone_lock - clone an inet socket, and lock its clone
* @sk: the socket to clone
* @req: request_sock
* @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc)
*
* Caller must unlock socket even in error path (bh_unlock_sock(newsk))
*/
struct sock *inet_csk_clone_lock(const struct sock *sk,
const struct request_sock *req,
const gfp_t priority)
{
struct sock *newsk = sk_clone_lock(sk, priority);
if (newsk) {
struct inet_connection_sock *newicsk = inet_csk(newsk);
inet_sk_set_state(newsk, TCP_SYN_RECV);
newicsk->icsk_bind_hash = NULL;
inet_sk(newsk)->inet_dport = inet_rsk(req)->ir_rmt_port;
inet_sk(newsk)->inet_num = inet_rsk(req)->ir_num;
inet_sk(newsk)->inet_sport = htons(inet_rsk(req)->ir_num);
/* listeners have SOCK_RCU_FREE, not the children */
sock_reset_flag(newsk, SOCK_RCU_FREE);
inet_sk(newsk)->mc_list = NULL;
newsk->sk_mark = inet_rsk(req)->ir_mark;
atomic64_set(&newsk->sk_cookie,
atomic64_read(&inet_rsk(req)->ir_cookie));
newicsk->icsk_retransmits = 0;
newicsk->icsk_backoff = 0;
newicsk->icsk_probes_out = 0;
/* Deinitialize accept_queue to trap illegal accesses. */
memset(&newicsk->icsk_accept_queue, 0, sizeof(newicsk->icsk_accept_queue));
security_inet_csk_clone(newsk, req);
}
return newsk;
}
EXPORT_SYMBOL_GPL(inet_csk_clone_lock);
/*
* At this point, there should be no process reference to this
* socket, and thus no user references at all. Therefore we
* can assume the socket waitqueue is inactive and nobody will
* try to jump onto it.
*/
void inet_csk_destroy_sock(struct sock *sk)
{
WARN_ON(sk->sk_state != TCP_CLOSE);
WARN_ON(!sock_flag(sk, SOCK_DEAD));
/* It cannot be in hash table! */
WARN_ON(!sk_unhashed(sk));
/* If it has not 0 inet_sk(sk)->inet_num, it must be bound */
WARN_ON(inet_sk(sk)->inet_num && !inet_csk(sk)->icsk_bind_hash);
sk->sk_prot->destroy(sk);
sk_stream_kill_queues(sk);
xfrm_sk_free_policy(sk);
sk_refcnt_debug_release(sk);
percpu_counter_dec(sk->sk_prot->orphan_count);
sock_put(sk);
}
EXPORT_SYMBOL(inet_csk_destroy_sock);
inet: Fix kmemleak in tcp_v4/6_syn_recv_sock and dccp_v4/6_request_recv_sock If in either of the above functions inet_csk_route_child_sock() or __inet_inherit_port() fails, the newsk will not be freed: unreferenced object 0xffff88022e8a92c0 (size 1592): comm "softirq", pid 0, jiffies 4294946244 (age 726.160s) hex dump (first 32 bytes): 0a 01 01 01 0a 01 01 02 00 00 00 00 a7 cc 16 00 ................ 02 00 03 01 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<ffffffff8153d190>] kmemleak_alloc+0x21/0x3e [<ffffffff810ab3e7>] kmem_cache_alloc+0xb5/0xc5 [<ffffffff8149b65b>] sk_prot_alloc.isra.53+0x2b/0xcd [<ffffffff8149b784>] sk_clone_lock+0x16/0x21e [<ffffffff814d711a>] inet_csk_clone_lock+0x10/0x7b [<ffffffff814ebbc3>] tcp_create_openreq_child+0x21/0x481 [<ffffffff814e8fa5>] tcp_v4_syn_recv_sock+0x3a/0x23b [<ffffffff814ec5ba>] tcp_check_req+0x29f/0x416 [<ffffffff814e8e10>] tcp_v4_do_rcv+0x161/0x2bc [<ffffffff814eb917>] tcp_v4_rcv+0x6c9/0x701 [<ffffffff814cea9f>] ip_local_deliver_finish+0x70/0xc4 [<ffffffff814cec20>] ip_local_deliver+0x4e/0x7f [<ffffffff814ce9f8>] ip_rcv_finish+0x1fc/0x233 [<ffffffff814cee68>] ip_rcv+0x217/0x267 [<ffffffff814a7bbe>] __netif_receive_skb+0x49e/0x553 [<ffffffff814a7cc3>] netif_receive_skb+0x50/0x82 This happens, because sk_clone_lock initializes sk_refcnt to 2, and thus a single sock_put() is not enough to free the memory. Additionally, things like xfrm, memcg, cookie_values,... may have been initialized. We have to free them properly. This is fixed by forcing a call to tcp_done(), ending up in inet_csk_destroy_sock, doing the final sock_put(). tcp_done() is necessary, because it ends up doing all the cleanup on xfrm, memcg, cookie_values, xfrm,... Before calling tcp_done, we have to set the socket to SOCK_DEAD, to force it entering inet_csk_destroy_sock. To avoid the warning in inet_csk_destroy_sock, inet_num has to be set to 0. As inet_csk_destroy_sock does a dec on orphan_count, we first have to increase it. Calling tcp_done() allows us to remove the calls to tcp_clear_xmit_timer() and tcp_cleanup_congestion_control(). A similar approach is taken for dccp by calling dccp_done(). This is in the kernel since 093d282321 (tproxy: fix hash locking issue when using port redirection in __inet_inherit_port()), thus since version >= 2.6.37. Signed-off-by: Christoph Paasch <christoph.paasch@uclouvain.be> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-12-14 11:07:58 +07:00
/* This function allows to force a closure of a socket after the call to
* tcp/dccp_create_openreq_child().
*/
void inet_csk_prepare_forced_close(struct sock *sk)
__releases(&sk->sk_lock.slock)
inet: Fix kmemleak in tcp_v4/6_syn_recv_sock and dccp_v4/6_request_recv_sock If in either of the above functions inet_csk_route_child_sock() or __inet_inherit_port() fails, the newsk will not be freed: unreferenced object 0xffff88022e8a92c0 (size 1592): comm "softirq", pid 0, jiffies 4294946244 (age 726.160s) hex dump (first 32 bytes): 0a 01 01 01 0a 01 01 02 00 00 00 00 a7 cc 16 00 ................ 02 00 03 01 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<ffffffff8153d190>] kmemleak_alloc+0x21/0x3e [<ffffffff810ab3e7>] kmem_cache_alloc+0xb5/0xc5 [<ffffffff8149b65b>] sk_prot_alloc.isra.53+0x2b/0xcd [<ffffffff8149b784>] sk_clone_lock+0x16/0x21e [<ffffffff814d711a>] inet_csk_clone_lock+0x10/0x7b [<ffffffff814ebbc3>] tcp_create_openreq_child+0x21/0x481 [<ffffffff814e8fa5>] tcp_v4_syn_recv_sock+0x3a/0x23b [<ffffffff814ec5ba>] tcp_check_req+0x29f/0x416 [<ffffffff814e8e10>] tcp_v4_do_rcv+0x161/0x2bc [<ffffffff814eb917>] tcp_v4_rcv+0x6c9/0x701 [<ffffffff814cea9f>] ip_local_deliver_finish+0x70/0xc4 [<ffffffff814cec20>] ip_local_deliver+0x4e/0x7f [<ffffffff814ce9f8>] ip_rcv_finish+0x1fc/0x233 [<ffffffff814cee68>] ip_rcv+0x217/0x267 [<ffffffff814a7bbe>] __netif_receive_skb+0x49e/0x553 [<ffffffff814a7cc3>] netif_receive_skb+0x50/0x82 This happens, because sk_clone_lock initializes sk_refcnt to 2, and thus a single sock_put() is not enough to free the memory. Additionally, things like xfrm, memcg, cookie_values,... may have been initialized. We have to free them properly. This is fixed by forcing a call to tcp_done(), ending up in inet_csk_destroy_sock, doing the final sock_put(). tcp_done() is necessary, because it ends up doing all the cleanup on xfrm, memcg, cookie_values, xfrm,... Before calling tcp_done, we have to set the socket to SOCK_DEAD, to force it entering inet_csk_destroy_sock. To avoid the warning in inet_csk_destroy_sock, inet_num has to be set to 0. As inet_csk_destroy_sock does a dec on orphan_count, we first have to increase it. Calling tcp_done() allows us to remove the calls to tcp_clear_xmit_timer() and tcp_cleanup_congestion_control(). A similar approach is taken for dccp by calling dccp_done(). This is in the kernel since 093d282321 (tproxy: fix hash locking issue when using port redirection in __inet_inherit_port()), thus since version >= 2.6.37. Signed-off-by: Christoph Paasch <christoph.paasch@uclouvain.be> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-12-14 11:07:58 +07:00
{
/* sk_clone_lock locked the socket and set refcnt to 2 */
bh_unlock_sock(sk);
sock_put(sk);
/* The below has to be done to allow calling inet_csk_destroy_sock */
sock_set_flag(sk, SOCK_DEAD);
percpu_counter_inc(sk->sk_prot->orphan_count);
inet_sk(sk)->inet_num = 0;
}
EXPORT_SYMBOL(inet_csk_prepare_forced_close);
int inet_csk_listen_start(struct sock *sk, int backlog)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_sock *inet = inet_sk(sk);
int err = -EADDRINUSE;
reqsk_queue_alloc(&icsk->icsk_accept_queue);
sk->sk_ack_backlog = 0;
inet_csk_delack_init(sk);
/* There is race window here: we announce ourselves listening,
* but this transition is still not validated by get_port().
* It is OK, because this socket enters to hash table only
* after validation is complete.
*/
inet_sk_state_store(sk, TCP_LISTEN);
if (!sk->sk_prot->get_port(sk, inet->inet_num)) {
inet->inet_sport = htons(inet->inet_num);
sk_dst_reset(sk);
err = sk->sk_prot->hash(sk);
if (likely(!err))
return 0;
}
inet_sk_set_state(sk, TCP_CLOSE);
return err;
}
EXPORT_SYMBOL_GPL(inet_csk_listen_start);
static void inet_child_forget(struct sock *sk, struct request_sock *req,
struct sock *child)
{
sk->sk_prot->disconnect(child, O_NONBLOCK);
sock_orphan(child);
percpu_counter_inc(sk->sk_prot->orphan_count);
if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) {
BUG_ON(tcp_sk(child)->fastopen_rsk != req);
BUG_ON(sk != req->rsk_listener);
/* Paranoid, to prevent race condition if
* an inbound pkt destined for child is
* blocked by sock lock in tcp_v4_rcv().
* Also to satisfy an assertion in
* tcp_v4_destroy_sock().
*/
tcp_sk(child)->fastopen_rsk = NULL;
}
inet_csk_destroy_sock(child);
}
struct sock *inet_csk_reqsk_queue_add(struct sock *sk,
struct request_sock *req,
struct sock *child)
{
struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
spin_lock(&queue->rskq_lock);
if (unlikely(sk->sk_state != TCP_LISTEN)) {
inet_child_forget(sk, req, child);
child = NULL;
} else {
req->sk = child;
req->dl_next = NULL;
if (queue->rskq_accept_head == NULL)
queue->rskq_accept_head = req;
else
queue->rskq_accept_tail->dl_next = req;
queue->rskq_accept_tail = req;
sk_acceptq_added(sk);
}
spin_unlock(&queue->rskq_lock);
return child;
}
EXPORT_SYMBOL(inet_csk_reqsk_queue_add);
struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child,
struct request_sock *req, bool own_req)
{
if (own_req) {
inet_csk_reqsk_queue_drop(sk, req);
reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
if (inet_csk_reqsk_queue_add(sk, req, child))
return child;
}
/* Too bad, another child took ownership of the request, undo. */
bh_unlock_sock(child);
sock_put(child);
return NULL;
}
EXPORT_SYMBOL(inet_csk_complete_hashdance);
/*
* This routine closes sockets which have been at least partially
* opened, but not yet accepted.
*/
void inet_csk_listen_stop(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct request_sock_queue *queue = &icsk->icsk_accept_queue;
struct request_sock *next, *req;
/* Following specs, it would be better either to send FIN
* (and enter FIN-WAIT-1, it is normal close)
* or to send active reset (abort).
* Certainly, it is pretty dangerous while synflood, but it is
* bad justification for our negligence 8)
* To be honest, we are not able to make either
* of the variants now. --ANK
*/
while ((req = reqsk_queue_remove(queue, sk)) != NULL) {
struct sock *child = req->sk;
local_bh_disable();
bh_lock_sock(child);
WARN_ON(sock_owned_by_user(child));
sock_hold(child);
inet_child_forget(sk, req, child);
tcp/dccp: remove reqsk_put() from inet_child_forget() Back in linux-4.4, I inadvertently put a call to reqsk_put() in inet_child_forget(), forgetting it could be called from two different points. In the case it is called from inet_csk_reqsk_queue_add(), we want to keep the reference on the request socket, since it is released later by the caller (tcp_v{4|6}_rcv()) This bug never showed up because atomic_dec_and_test() was not signaling the underflow, and SLAB_DESTROY_BY RCU semantic for request sockets prevented the request to be put in quarantine. Recent conversion of socket refcount from atomic_t to refcount_t finally exposed the bug. So move the reqsk_put() to inet_csk_listen_stop() to fix this. Thanks to Shankara Pailoor for using syzkaller and providing a nice set of .config and C repro. WARNING: CPU: 2 PID: 4277 at lib/refcount.c:186 refcount_sub_and_test+0x167/0x1b0 lib/refcount.c:186 Kernel panic - not syncing: panic_on_warn set ... CPU: 2 PID: 4277 Comm: syz-executor0 Not tainted 4.13.0-rc7 #3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:16 [inline] dump_stack+0xf7/0x1aa lib/dump_stack.c:52 panic+0x1ae/0x3a7 kernel/panic.c:180 __warn+0x1c4/0x1d9 kernel/panic.c:541 report_bug+0x211/0x2d0 lib/bug.c:183 fixup_bug+0x40/0x90 arch/x86/kernel/traps.c:190 do_trap_no_signal arch/x86/kernel/traps.c:224 [inline] do_trap+0x260/0x390 arch/x86/kernel/traps.c:273 do_error_trap+0x118/0x340 arch/x86/kernel/traps.c:310 do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:323 invalid_op+0x18/0x20 arch/x86/entry/entry_64.S:846 RIP: 0010:refcount_sub_and_test+0x167/0x1b0 lib/refcount.c:186 RSP: 0018:ffff88006e006b60 EFLAGS: 00010286 RAX: 0000000000000026 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000026 RSI: 1ffff1000dc00d2c RDI: ffffed000dc00d60 RBP: ffff88006e006bf0 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 1ffff1000dc00d6d R13: 00000000ffffffff R14: 0000000000000001 R15: ffff88006ce9d340 refcount_dec_and_test+0x1a/0x20 lib/refcount.c:211 reqsk_put+0x71/0x2b0 include/net/request_sock.h:123 tcp_v4_rcv+0x259e/0x2e20 net/ipv4/tcp_ipv4.c:1729 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216 NF_HOOK include/linux/netfilter.h:248 [inline] ip_local_deliver+0x1ce/0x6d0 net/ipv4/ip_input.c:257 dst_input include/net/dst.h:477 [inline] ip_rcv_finish+0x8db/0x19c0 net/ipv4/ip_input.c:397 NF_HOOK include/linux/netfilter.h:248 [inline] ip_rcv+0xc3f/0x17d0 net/ipv4/ip_input.c:488 __netif_receive_skb_core+0x1fb7/0x31f0 net/core/dev.c:4298 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4336 process_backlog+0x1c5/0x6d0 net/core/dev.c:5102 napi_poll net/core/dev.c:5499 [inline] net_rx_action+0x6d3/0x14a0 net/core/dev.c:5565 __do_softirq+0x2cb/0xb2d kernel/softirq.c:284 do_softirq_own_stack+0x1c/0x30 arch/x86/entry/entry_64.S:898 </IRQ> do_softirq.part.16+0x63/0x80 kernel/softirq.c:328 do_softirq kernel/softirq.c:176 [inline] __local_bh_enable_ip+0x84/0x90 kernel/softirq.c:181 local_bh_enable include/linux/bottom_half.h:31 [inline] rcu_read_unlock_bh include/linux/rcupdate.h:705 [inline] ip_finish_output2+0x8ad/0x1360 net/ipv4/ip_output.c:231 ip_finish_output+0x74e/0xb80 net/ipv4/ip_output.c:317 NF_HOOK_COND include/linux/netfilter.h:237 [inline] ip_output+0x1cc/0x850 net/ipv4/ip_output.c:405 dst_output include/net/dst.h:471 [inline] ip_local_out+0x95/0x160 net/ipv4/ip_output.c:124 ip_queue_xmit+0x8c6/0x1810 net/ipv4/ip_output.c:504 tcp_transmit_skb+0x1963/0x3320 net/ipv4/tcp_output.c:1123 tcp_send_ack.part.35+0x38c/0x620 net/ipv4/tcp_output.c:3575 tcp_send_ack+0x49/0x60 net/ipv4/tcp_output.c:3545 tcp_rcv_synsent_state_process net/ipv4/tcp_input.c:5795 [inline] tcp_rcv_state_process+0x4876/0x4b60 net/ipv4/tcp_input.c:5930 tcp_v4_do_rcv+0x58a/0x820 net/ipv4/tcp_ipv4.c:1483 sk_backlog_rcv include/net/sock.h:907 [inline] __release_sock+0x124/0x360 net/core/sock.c:2223 release_sock+0xa4/0x2a0 net/core/sock.c:2715 inet_wait_for_connect net/ipv4/af_inet.c:557 [inline] __inet_stream_connect+0x671/0xf00 net/ipv4/af_inet.c:643 inet_stream_connect+0x58/0xa0 net/ipv4/af_inet.c:682 SYSC_connect+0x204/0x470 net/socket.c:1628 SyS_connect+0x24/0x30 net/socket.c:1609 entry_SYSCALL_64_fastpath+0x18/0xad RIP: 0033:0x451e59 RSP: 002b:00007f474843fc08 EFLAGS: 00000216 ORIG_RAX: 000000000000002a RAX: ffffffffffffffda RBX: 0000000000718000 RCX: 0000000000451e59 RDX: 0000000000000010 RSI: 0000000020002000 RDI: 0000000000000007 RBP: 0000000000000046 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000216 R12: 0000000000000000 R13: 00007ffc040a0f8f R14: 00007f47484409c0 R15: 0000000000000000 Fixes: ebb516af60e1 ("tcp/dccp: fix race at listener dismantle phase") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Shankara Pailoor <sp3485@columbia.edu> Tested-by: Shankara Pailoor <sp3485@columbia.edu> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-12 05:58:38 +07:00
reqsk_put(req);
bh_unlock_sock(child);
local_bh_enable();
sock_put(child);
cond_resched();
}
if (queue->fastopenq.rskq_rst_head) {
/* Free all the reqs queued in rskq_rst_head. */
spin_lock_bh(&queue->fastopenq.lock);
req = queue->fastopenq.rskq_rst_head;
queue->fastopenq.rskq_rst_head = NULL;
spin_unlock_bh(&queue->fastopenq.lock);
while (req != NULL) {
next = req->dl_next;
reqsk_put(req);
req = next;
}
}
WARN_ON_ONCE(sk->sk_ack_backlog);
}
EXPORT_SYMBOL_GPL(inet_csk_listen_stop);
void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr)
{
struct sockaddr_in *sin = (struct sockaddr_in *)uaddr;
const struct inet_sock *inet = inet_sk(sk);
sin->sin_family = AF_INET;
sin->sin_addr.s_addr = inet->inet_daddr;
sin->sin_port = inet->inet_dport;
}
EXPORT_SYMBOL_GPL(inet_csk_addr2sockaddr);
#ifdef CONFIG_COMPAT
int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
if (icsk->icsk_af_ops->compat_getsockopt)
return icsk->icsk_af_ops->compat_getsockopt(sk, level, optname,
optval, optlen);
return icsk->icsk_af_ops->getsockopt(sk, level, optname,
optval, optlen);
}
EXPORT_SYMBOL_GPL(inet_csk_compat_getsockopt);
int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname,
char __user *optval, unsigned int optlen)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
if (icsk->icsk_af_ops->compat_setsockopt)
return icsk->icsk_af_ops->compat_setsockopt(sk, level, optname,
optval, optlen);
return icsk->icsk_af_ops->setsockopt(sk, level, optname,
optval, optlen);
}
EXPORT_SYMBOL_GPL(inet_csk_compat_setsockopt);
#endif
static struct dst_entry *inet_csk_rebuild_route(struct sock *sk, struct flowi *fl)
{
const struct inet_sock *inet = inet_sk(sk);
const struct ip_options_rcu *inet_opt;
__be32 daddr = inet->inet_daddr;
struct flowi4 *fl4;
struct rtable *rt;
rcu_read_lock();
inet_opt = rcu_dereference(inet->inet_opt);
if (inet_opt && inet_opt->opt.srr)
daddr = inet_opt->opt.faddr;
fl4 = &fl->u.ip4;
rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr,
inet->inet_saddr, inet->inet_dport,
inet->inet_sport, sk->sk_protocol,
RT_CONN_FLAGS(sk), sk->sk_bound_dev_if);
if (IS_ERR(rt))
rt = NULL;
if (rt)
sk_setup_caps(sk, &rt->dst);
rcu_read_unlock();
return &rt->dst;
}
struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu)
{
struct dst_entry *dst = __sk_dst_check(sk, 0);
struct inet_sock *inet = inet_sk(sk);
if (!dst) {
dst = inet_csk_rebuild_route(sk, &inet->cork.fl);
if (!dst)
goto out;
}
dst->ops->update_pmtu(dst, sk, NULL, mtu);
dst = __sk_dst_check(sk, 0);
if (!dst)
dst = inet_csk_rebuild_route(sk, &inet->cork.fl);
out:
return dst;
}
EXPORT_SYMBOL_GPL(inet_csk_update_pmtu);