linux/net/ipv4/inet_connection_sock.c
Eric Dumazet 83fccfc394 inet: fix potential deadlock in reqsk_queue_unlink()
When replacing del_timer() with del_timer_sync(), I introduced
a deadlock condition :

reqsk_queue_unlink() is called from inet_csk_reqsk_queue_drop()

inet_csk_reqsk_queue_drop() can be called from many contexts,
one being the timer handler itself (reqsk_timer_handler()).

In this case, del_timer_sync() loops forever.

Simple fix is to test if timer is pending.

Fixes: 2235f2ac75 ("inet: fix races with reqsk timers")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-13 22:46:22 -07:00

988 lines
27 KiB
C

/*
* 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>
#ifdef INET_CSK_DEBUG
const char inet_csk_timer_bug_msg[] = "inet_csk BUG: unknown timer value\n";
EXPORT_SYMBOL(inet_csk_timer_bug_msg);
#endif
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);
int inet_csk_bind_conflict(const struct sock *sk,
const struct inet_bind_bucket *tb, bool relax)
{
struct sock *sk2;
int reuse = sk->sk_reuse;
int reuseport = sk->sk_reuseport;
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.
*/
sk_for_each_bound(sk2, &tb->owners) {
if (sk != sk2 &&
!inet_v6_ipv6only(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 ||
(sk2->sk_state != TCP_TIME_WAIT &&
!uid_eq(uid, sock_i_uid(sk2))))) {
if (!sk2->sk_rcv_saddr || !sk->sk_rcv_saddr ||
sk2->sk_rcv_saddr == sk->sk_rcv_saddr)
break;
}
if (!relax && reuse && sk2->sk_reuse &&
sk2->sk_state != TCP_LISTEN) {
if (!sk2->sk_rcv_saddr || !sk->sk_rcv_saddr ||
sk2->sk_rcv_saddr == sk->sk_rcv_saddr)
break;
}
}
}
return sk2 != NULL;
}
EXPORT_SYMBOL_GPL(inet_csk_bind_conflict);
/* Obtain a reference to a local port for the given sock,
* if snum is zero it means select any available local port.
*/
int inet_csk_get_port(struct sock *sk, unsigned short snum)
{
struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
struct inet_bind_hashbucket *head;
struct inet_bind_bucket *tb;
int ret, attempts = 5;
struct net *net = sock_net(sk);
int smallest_size = -1, smallest_rover;
kuid_t uid = sock_i_uid(sk);
int attempt_half = (sk->sk_reuse == SK_CAN_REUSE) ? 1 : 0;
local_bh_disable();
if (!snum) {
int remaining, rover, low, high;
again:
inet_get_local_port_range(net, &low, &high);
if (attempt_half) {
int half = low + ((high - low) >> 1);
if (attempt_half == 1)
high = half;
else
low = half;
}
remaining = (high - low) + 1;
smallest_rover = rover = prandom_u32() % remaining + low;
smallest_size = -1;
do {
if (inet_is_local_reserved_port(net, rover))
goto next_nolock;
head = &hashinfo->bhash[inet_bhashfn(net, rover,
hashinfo->bhash_size)];
spin_lock(&head->lock);
inet_bind_bucket_for_each(tb, &head->chain)
if (net_eq(ib_net(tb), net) && tb->port == rover) {
if (((tb->fastreuse > 0 &&
sk->sk_reuse &&
sk->sk_state != TCP_LISTEN) ||
(tb->fastreuseport > 0 &&
sk->sk_reuseport &&
uid_eq(tb->fastuid, uid))) &&
(tb->num_owners < smallest_size || smallest_size == -1)) {
smallest_size = tb->num_owners;
smallest_rover = rover;
}
if (!inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, false)) {
snum = rover;
goto tb_found;
}
goto next;
}
break;
next:
spin_unlock(&head->lock);
next_nolock:
if (++rover > high)
rover = low;
} while (--remaining > 0);
/* Exhausted local port range during search? It is not
* possible for us to be holding one of the bind hash
* locks if this test triggers, because if 'remaining'
* drops to zero, we broke out of the do/while loop at
* the top level, not from the 'break;' statement.
*/
ret = 1;
if (remaining <= 0) {
if (smallest_size != -1) {
snum = smallest_rover;
goto have_snum;
}
if (attempt_half == 1) {
/* OK we now try the upper half of the range */
attempt_half = 2;
goto again;
}
goto fail;
}
/* OK, here is the one we will use. HEAD is
* non-NULL and we hold it's mutex.
*/
snum = rover;
} else {
have_snum:
head = &hashinfo->bhash[inet_bhashfn(net, snum,
hashinfo->bhash_size)];
spin_lock(&head->lock);
inet_bind_bucket_for_each(tb, &head->chain)
if (net_eq(ib_net(tb), net) && tb->port == snum)
goto tb_found;
}
tb = NULL;
goto tb_not_found;
tb_found:
if (!hlist_empty(&tb->owners)) {
if (sk->sk_reuse == SK_FORCE_REUSE)
goto success;
if (((tb->fastreuse > 0 &&
sk->sk_reuse && sk->sk_state != TCP_LISTEN) ||
(tb->fastreuseport > 0 &&
sk->sk_reuseport && uid_eq(tb->fastuid, uid))) &&
smallest_size == -1) {
goto success;
} else {
ret = 1;
if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, true)) {
if (((sk->sk_reuse && sk->sk_state != TCP_LISTEN) ||
(tb->fastreuseport > 0 &&
sk->sk_reuseport && uid_eq(tb->fastuid, uid))) &&
smallest_size != -1 && --attempts >= 0) {
spin_unlock(&head->lock);
goto again;
}
goto fail_unlock;
}
}
}
tb_not_found:
ret = 1;
if (!tb && (tb = inet_bind_bucket_create(hashinfo->bind_bucket_cachep,
net, head, snum)) == NULL)
goto fail_unlock;
if (hlist_empty(&tb->owners)) {
if (sk->sk_reuse && sk->sk_state != TCP_LISTEN)
tb->fastreuse = 1;
else
tb->fastreuse = 0;
if (sk->sk_reuseport) {
tb->fastreuseport = 1;
tb->fastuid = uid;
} else
tb->fastreuseport = 0;
} else {
if (tb->fastreuse &&
(!sk->sk_reuse || sk->sk_state == TCP_LISTEN))
tb->fastreuse = 0;
if (tb->fastreuseport &&
(!sk->sk_reuseport || !uid_eq(tb->fastuid, uid)))
tb->fastreuseport = 0;
}
success:
if (!inet_csk(sk)->icsk_bind_hash)
inet_bind_hash(sk, tb, snum);
WARN_ON(inet_csk(sk)->icsk_bind_hash != tb);
ret = 0;
fail_unlock:
spin_unlock(&head->lock);
fail:
local_bh_enable();
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);
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.
*/
struct sock *inet_csk_accept(struct sock *sk, int flags, int *err)
{
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);
newsk = req->sk;
sk_acceptq_removed(sk);
if (sk->sk_protocol == IPPROTO_TCP &&
tcp_rsk(req)->tfo_listener &&
queue->fastopenq) {
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)(unsigned long),
void (*delack_handler)(unsigned long),
void (*keepalive_handler)(unsigned long))
{
struct inet_connection_sock *icsk = inet_csk(sk);
setup_timer(&icsk->icsk_retransmit_timer, retransmit_handler,
(unsigned long)sk);
setup_timer(&icsk->icsk_delack_timer, delack_handler,
(unsigned long)sk);
setup_timer(&sk->sk_timer, keepalive_handler, (unsigned long)sk);
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(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);
struct ip_options_rcu *opt = ireq->opt;
struct rtable *rt;
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));
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_BH(net, IPSTATS_MIB_OUTNOROUTES);
return NULL;
}
EXPORT_SYMBOL_GPL(inet_csk_route_req);
struct dst_entry *inet_csk_route_child_sock(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;
fl4 = &newinet->cork.fl.u.ip4;
rcu_read_lock();
opt = rcu_dereference(newinet->inet_opt);
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));
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_BH(net, IPSTATS_MIB_OUTNOROUTES);
return NULL;
}
EXPORT_SYMBOL_GPL(inet_csk_route_child_sock);
static inline u32 inet_synq_hash(const __be32 raddr, const __be16 rport,
const u32 rnd, const u32 synq_hsize)
{
return jhash_2words((__force u32)raddr, (__force u32)rport, rnd) & (synq_hsize - 1);
}
#if IS_ENABLED(CONFIG_IPV6)
#define AF_INET_FAMILY(fam) ((fam) == AF_INET)
#else
#define AF_INET_FAMILY(fam) true
#endif
/* Note: this is temporary :
* req sock will no longer be in listener hash table
*/
struct request_sock *inet_csk_search_req(struct sock *sk,
const __be16 rport,
const __be32 raddr,
const __be32 laddr)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt;
struct request_sock *req;
u32 hash = inet_synq_hash(raddr, rport, lopt->hash_rnd,
lopt->nr_table_entries);
spin_lock(&icsk->icsk_accept_queue.syn_wait_lock);
for (req = lopt->syn_table[hash]; req != NULL; req = req->dl_next) {
const struct inet_request_sock *ireq = inet_rsk(req);
if (ireq->ir_rmt_port == rport &&
ireq->ir_rmt_addr == raddr &&
ireq->ir_loc_addr == laddr &&
AF_INET_FAMILY(req->rsk_ops->family)) {
atomic_inc(&req->rsk_refcnt);
WARN_ON(req->sk);
break;
}
}
spin_unlock(&icsk->icsk_accept_queue.syn_wait_lock);
return req;
}
EXPORT_SYMBOL_GPL(inet_csk_search_req);
void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
unsigned long timeout)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt;
const u32 h = inet_synq_hash(inet_rsk(req)->ir_rmt_addr,
inet_rsk(req)->ir_rmt_port,
lopt->hash_rnd, lopt->nr_table_entries);
reqsk_queue_hash_req(&icsk->icsk_accept_queue, h, req, timeout);
inet_csk_reqsk_queue_added(sk, timeout);
}
EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add);
/* Only thing we need from tcp.h */
extern int sysctl_tcp_synack_retries;
/* 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) {
*expire = req->num_timeout >= thresh;
*resend = 1;
return;
}
*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 ||
req->num_timeout >= rskq_defer_accept - 1;
}
int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req)
{
int err = req->rsk_ops->rtx_syn_ack(parent, req);
if (!err)
req->num_retrans++;
return err;
}
EXPORT_SYMBOL(inet_rtx_syn_ack);
/* return true if req was found in the syn_table[] */
static bool reqsk_queue_unlink(struct request_sock_queue *queue,
struct request_sock *req)
{
struct listen_sock *lopt = queue->listen_opt;
struct request_sock **prev;
bool found = false;
spin_lock(&queue->syn_wait_lock);
for (prev = &lopt->syn_table[req->rsk_hash]; *prev != NULL;
prev = &(*prev)->dl_next) {
if (*prev == req) {
*prev = req->dl_next;
found = true;
break;
}
}
spin_unlock(&queue->syn_wait_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);
static void reqsk_timer_handler(unsigned long data)
{
struct request_sock *req = (struct request_sock *)data;
struct sock *sk_listener = req->rsk_listener;
struct inet_connection_sock *icsk = inet_csk(sk_listener);
struct request_sock_queue *queue = &icsk->icsk_accept_queue;
struct listen_sock *lopt = queue->listen_opt;
int qlen, expire = 0, resend = 0;
int max_retries, thresh;
u8 defer_accept;
if (sk_listener->sk_state != TCP_LISTEN || !lopt) {
reqsk_put(req);
return;
}
max_retries = icsk->icsk_syn_retries ? : 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 = listen_sock_qlen(lopt);
if (qlen >> (lopt->max_qlen_log - 1)) {
int young = listen_sock_young(lopt) << 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_inc(&lopt->young_dec);
timeo = min(TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX);
mod_timer_pinned(&req->rsk_timer, jiffies + timeo);
return;
}
inet_csk_reqsk_queue_drop(sk_listener, req);
reqsk_put(req);
}
void reqsk_queue_hash_req(struct request_sock_queue *queue,
u32 hash, struct request_sock *req,
unsigned long timeout)
{
struct listen_sock *lopt = queue->listen_opt;
req->num_retrans = 0;
req->num_timeout = 0;
req->sk = NULL;
/* before letting lookups find us, make sure all req fields
* are committed to memory and refcnt initialized.
*/
smp_wmb();
atomic_set(&req->rsk_refcnt, 2);
setup_timer(&req->rsk_timer, reqsk_timer_handler, (unsigned long)req);
req->rsk_hash = hash;
spin_lock(&queue->syn_wait_lock);
req->dl_next = lopt->syn_table[hash];
lopt->syn_table[hash] = req;
spin_unlock(&queue->syn_wait_lock);
mod_timer_pinned(&req->rsk_timer, jiffies + timeout);
}
EXPORT_SYMBOL(reqsk_queue_hash_req);
/**
* 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);
newsk->sk_state = 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);
newsk->sk_write_space = sk_stream_write_space;
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);
/* 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)
{
/* 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, const int nr_table_entries)
{
struct inet_sock *inet = inet_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
int rc = reqsk_queue_alloc(&icsk->icsk_accept_queue, nr_table_entries);
if (rc != 0)
return rc;
sk->sk_max_ack_backlog = 0;
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.
*/
sk->sk_state = TCP_LISTEN;
if (!sk->sk_prot->get_port(sk, inet->inet_num)) {
inet->inet_sport = htons(inet->inet_num);
sk_dst_reset(sk);
sk->sk_prot->hash(sk);
return 0;
}
sk->sk_state = TCP_CLOSE;
__reqsk_queue_destroy(&icsk->icsk_accept_queue);
return -EADDRINUSE;
}
EXPORT_SYMBOL_GPL(inet_csk_listen_start);
/*
* 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 *acc_req;
struct request_sock *req;
/* make all the listen_opt local to us */
acc_req = reqsk_queue_yank_acceptq(queue);
/* 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
*/
reqsk_queue_destroy(queue);
while ((req = acc_req) != NULL) {
struct sock *child = req->sk;
acc_req = req->dl_next;
local_bh_disable();
bh_lock_sock(child);
WARN_ON(sock_owned_by_user(child));
sock_hold(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);
bh_unlock_sock(child);
local_bh_enable();
sock_put(child);
sk_acceptq_removed(sk);
reqsk_put(req);
}
if (queue->fastopenq) {
/* Free all the reqs queued in rskq_rst_head. */
spin_lock_bh(&queue->fastopenq->lock);
acc_req = queue->fastopenq->rskq_rst_head;
queue->fastopenq->rskq_rst_head = NULL;
spin_unlock_bh(&queue->fastopenq->lock);
while ((req = acc_req) != NULL) {
acc_req = req->dl_next;
reqsk_put(req);
}
}
WARN_ON(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);