summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/atm/clip.c64
-rw-r--r--net/bluetooth/hci_event.c3
-rw-r--r--net/bluetooth/hci_sync.c4
-rw-r--r--net/ipv4/tcp.c2
-rw-r--r--net/ipv4/tcp_input.c4
-rw-r--r--net/netlink/af_netlink.c81
-rw-r--r--net/rxrpc/ar-internal.h15
-rw-r--r--net/rxrpc/call_accept.c4
-rw-r--r--net/rxrpc/output.c5
-rw-r--r--net/sched/sch_api.c33
-rw-r--r--net/sched/sch_hfsc.c16
-rw-r--r--net/sched/sch_qfq.c2
-rw-r--r--net/tipc/topsrv.c2
-rw-r--r--net/vmw_vsock/af_vsock.c57
14 files changed, 188 insertions, 104 deletions
diff --git a/net/atm/clip.c b/net/atm/clip.c
index b234dc3bcb0d..f7a5565e794e 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -45,7 +45,8 @@
#include <net/atmclip.h>
static struct net_device *clip_devs;
-static struct atm_vcc *atmarpd;
+static struct atm_vcc __rcu *atmarpd;
+static DEFINE_MUTEX(atmarpd_lock);
static struct timer_list idle_timer;
static const struct neigh_ops clip_neigh_ops;
@@ -53,24 +54,35 @@ static int to_atmarpd(enum atmarp_ctrl_type type, int itf, __be32 ip)
{
struct sock *sk;
struct atmarp_ctrl *ctrl;
+ struct atm_vcc *vcc;
struct sk_buff *skb;
+ int err = 0;
pr_debug("(%d)\n", type);
- if (!atmarpd)
- return -EUNATCH;
+
+ rcu_read_lock();
+ vcc = rcu_dereference(atmarpd);
+ if (!vcc) {
+ err = -EUNATCH;
+ goto unlock;
+ }
skb = alloc_skb(sizeof(struct atmarp_ctrl), GFP_ATOMIC);
- if (!skb)
- return -ENOMEM;
+ if (!skb) {
+ err = -ENOMEM;
+ goto unlock;
+ }
ctrl = skb_put(skb, sizeof(struct atmarp_ctrl));
ctrl->type = type;
ctrl->itf_num = itf;
ctrl->ip = ip;
- atm_force_charge(atmarpd, skb->truesize);
+ atm_force_charge(vcc, skb->truesize);
- sk = sk_atm(atmarpd);
+ sk = sk_atm(vcc);
skb_queue_tail(&sk->sk_receive_queue, skb);
sk->sk_data_ready(sk);
- return 0;
+unlock:
+ rcu_read_unlock();
+ return err;
}
static void link_vcc(struct clip_vcc *clip_vcc, struct atmarp_entry *entry)
@@ -417,6 +429,8 @@ static int clip_mkip(struct atm_vcc *vcc, int timeout)
if (!vcc->push)
return -EBADFD;
+ if (vcc->user_back)
+ return -EINVAL;
clip_vcc = kmalloc(sizeof(struct clip_vcc), GFP_KERNEL);
if (!clip_vcc)
return -ENOMEM;
@@ -607,17 +621,27 @@ static void atmarpd_close(struct atm_vcc *vcc)
{
pr_debug("\n");
- rtnl_lock();
- atmarpd = NULL;
+ mutex_lock(&atmarpd_lock);
+ RCU_INIT_POINTER(atmarpd, NULL);
+ mutex_unlock(&atmarpd_lock);
+
+ synchronize_rcu();
skb_queue_purge(&sk_atm(vcc)->sk_receive_queue);
- rtnl_unlock();
pr_debug("(done)\n");
module_put(THIS_MODULE);
}
+static int atmarpd_send(struct atm_vcc *vcc, struct sk_buff *skb)
+{
+ atm_return_tx(vcc, skb);
+ dev_kfree_skb_any(skb);
+ return 0;
+}
+
static const struct atmdev_ops atmarpd_dev_ops = {
- .close = atmarpd_close
+ .close = atmarpd_close,
+ .send = atmarpd_send
};
@@ -631,15 +655,18 @@ static struct atm_dev atmarpd_dev = {
static int atm_init_atmarp(struct atm_vcc *vcc)
{
- rtnl_lock();
+ if (vcc->push == clip_push)
+ return -EINVAL;
+
+ mutex_lock(&atmarpd_lock);
if (atmarpd) {
- rtnl_unlock();
+ mutex_unlock(&atmarpd_lock);
return -EADDRINUSE;
}
mod_timer(&idle_timer, jiffies + CLIP_CHECK_INTERVAL * HZ);
- atmarpd = vcc;
+ rcu_assign_pointer(atmarpd, vcc);
set_bit(ATM_VF_META, &vcc->flags);
set_bit(ATM_VF_READY, &vcc->flags);
/* allow replies and avoid getting closed if signaling dies */
@@ -648,13 +675,14 @@ static int atm_init_atmarp(struct atm_vcc *vcc)
vcc->push = NULL;
vcc->pop = NULL; /* crash */
vcc->push_oam = NULL; /* crash */
- rtnl_unlock();
+ mutex_unlock(&atmarpd_lock);
return 0;
}
static int clip_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
struct atm_vcc *vcc = ATM_SD(sock);
+ struct sock *sk = sock->sk;
int err = 0;
switch (cmd) {
@@ -675,14 +703,18 @@ static int clip_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
err = clip_create(arg);
break;
case ATMARPD_CTRL:
+ lock_sock(sk);
err = atm_init_atmarp(vcc);
if (!err) {
sock->state = SS_CONNECTED;
__module_get(THIS_MODULE);
}
+ release_sock(sk);
break;
case ATMARP_MKIP:
+ lock_sock(sk);
err = clip_mkip(vcc, arg);
+ release_sock(sk);
break;
case ATMARP_SETENTRY:
err = clip_setentry(vcc, (__force __be32)arg);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 4d5ace9d245d..992131f88a45 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -6966,7 +6966,10 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data,
bis->iso_qos.bcast.in.sdu = le16_to_cpu(ev->max_pdu);
if (!ev->status) {
+ bis->state = BT_CONNECTED;
set_bit(HCI_CONN_BIG_SYNC, &bis->flags);
+ hci_debugfs_create_conn(bis);
+ hci_conn_add_sysfs(bis);
hci_iso_setup_path(bis);
}
}
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 77b3691f3423..5f178db8d40d 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -1345,7 +1345,7 @@ int hci_setup_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance)
* Command Disallowed error, so we must first disable the
* instance if it is active.
*/
- if (adv && !adv->pending) {
+ if (adv) {
err = hci_disable_ext_adv_instance_sync(hdev, instance);
if (err)
return err;
@@ -5493,7 +5493,7 @@ static int hci_disconnect_sync(struct hci_dev *hdev, struct hci_conn *conn,
{
struct hci_cp_disconnect cp;
- if (test_bit(HCI_CONN_BIG_CREATED, &conn->flags)) {
+ if (conn->type == BIS_LINK) {
/* This is a BIS connection, hci_conn_del will
* do the necessary cleanup.
*/
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f64f8276a73c..461a9ab540af 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1176,7 +1176,7 @@ restart:
goto do_error;
while (msg_data_left(msg)) {
- ssize_t copy = 0;
+ int copy = 0;
skb = tcp_write_queue_tail(sk);
if (skb)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 12c2e6fc85c6..68bc79eb9019 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5181,7 +5181,9 @@ end:
skb_condense(skb);
skb_set_owner_r(skb, sk);
}
- tcp_rcvbuf_grow(sk);
+ /* do not grow rcvbuf for not-yet-accepted or orphaned sockets. */
+ if (sk->sk_socket)
+ tcp_rcvbuf_grow(sk);
}
static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb,
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index e8972a857e51..79fbaf7333ce 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -387,7 +387,6 @@ static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
WARN_ON(skb->sk != NULL);
skb->sk = sk;
skb->destructor = netlink_skb_destructor;
- atomic_add(skb->truesize, &sk->sk_rmem_alloc);
sk_mem_charge(sk, skb->truesize);
}
@@ -1212,41 +1211,48 @@ struct sk_buff *netlink_alloc_large_skb(unsigned int size, int broadcast)
int netlink_attachskb(struct sock *sk, struct sk_buff *skb,
long *timeo, struct sock *ssk)
{
+ DECLARE_WAITQUEUE(wait, current);
struct netlink_sock *nlk;
+ unsigned int rmem;
nlk = nlk_sk(sk);
+ rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc);
- if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
- test_bit(NETLINK_S_CONGESTED, &nlk->state))) {
- DECLARE_WAITQUEUE(wait, current);
- if (!*timeo) {
- if (!ssk || netlink_is_kernel(ssk))
- netlink_overrun(sk);
- sock_put(sk);
- kfree_skb(skb);
- return -EAGAIN;
- }
-
- __set_current_state(TASK_INTERRUPTIBLE);
- add_wait_queue(&nlk->wait, &wait);
+ if ((rmem == skb->truesize || rmem < READ_ONCE(sk->sk_rcvbuf)) &&
+ !test_bit(NETLINK_S_CONGESTED, &nlk->state)) {
+ netlink_skb_set_owner_r(skb, sk);
+ return 0;
+ }
- if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
- test_bit(NETLINK_S_CONGESTED, &nlk->state)) &&
- !sock_flag(sk, SOCK_DEAD))
- *timeo = schedule_timeout(*timeo);
+ atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
- __set_current_state(TASK_RUNNING);
- remove_wait_queue(&nlk->wait, &wait);
+ if (!*timeo) {
+ if (!ssk || netlink_is_kernel(ssk))
+ netlink_overrun(sk);
sock_put(sk);
+ kfree_skb(skb);
+ return -EAGAIN;
+ }
- if (signal_pending(current)) {
- kfree_skb(skb);
- return sock_intr_errno(*timeo);
- }
- return 1;
+ __set_current_state(TASK_INTERRUPTIBLE);
+ add_wait_queue(&nlk->wait, &wait);
+ rmem = atomic_read(&sk->sk_rmem_alloc);
+
+ if (((rmem && rmem + skb->truesize > READ_ONCE(sk->sk_rcvbuf)) ||
+ test_bit(NETLINK_S_CONGESTED, &nlk->state)) &&
+ !sock_flag(sk, SOCK_DEAD))
+ *timeo = schedule_timeout(*timeo);
+
+ __set_current_state(TASK_RUNNING);
+ remove_wait_queue(&nlk->wait, &wait);
+ sock_put(sk);
+
+ if (signal_pending(current)) {
+ kfree_skb(skb);
+ return sock_intr_errno(*timeo);
}
- netlink_skb_set_owner_r(skb, sk);
- return 0;
+
+ return 1;
}
static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb)
@@ -1307,6 +1313,7 @@ static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb,
ret = -ECONNREFUSED;
if (nlk->netlink_rcv != NULL) {
ret = skb->len;
+ atomic_add(skb->truesize, &sk->sk_rmem_alloc);
netlink_skb_set_owner_r(skb, sk);
NETLINK_CB(skb).sk = ssk;
netlink_deliver_tap_kernel(sk, ssk, skb);
@@ -1383,13 +1390,19 @@ EXPORT_SYMBOL_GPL(netlink_strict_get_check);
static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb)
{
struct netlink_sock *nlk = nlk_sk(sk);
+ unsigned int rmem, rcvbuf;
- if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
+ rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc);
+ rcvbuf = READ_ONCE(sk->sk_rcvbuf);
+
+ if ((rmem != skb->truesize || rmem <= rcvbuf) &&
!test_bit(NETLINK_S_CONGESTED, &nlk->state)) {
netlink_skb_set_owner_r(skb, sk);
__netlink_sendskb(sk, skb);
- return atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1);
+ return rmem > (rcvbuf >> 1);
}
+
+ atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
return -1;
}
@@ -2249,6 +2262,7 @@ static int netlink_dump(struct sock *sk, bool lock_taken)
struct module *module;
int err = -ENOBUFS;
int alloc_min_size;
+ unsigned int rmem;
int alloc_size;
if (!lock_taken)
@@ -2258,9 +2272,6 @@ static int netlink_dump(struct sock *sk, bool lock_taken)
goto errout_skb;
}
- if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
- goto errout_skb;
-
/* NLMSG_GOODSIZE is small to avoid high order allocations being
* required, but it makes sense to _attempt_ a 32KiB allocation
* to reduce number of system calls on dump operations, if user
@@ -2283,6 +2294,12 @@ static int netlink_dump(struct sock *sk, bool lock_taken)
if (!skb)
goto errout_skb;
+ rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc);
+ if (rmem >= READ_ONCE(sk->sk_rcvbuf)) {
+ atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
+ goto errout_skb;
+ }
+
/* Trim skb to allocated size. User is expected to provide buffer as
* large as max(min_dump_alloc, 32KiB (max_recvmsg_len capped at
* netlink_recvmsg())). dump will pack as many smaller messages as
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 5bd3922c310d..376e33dce8c1 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -361,12 +361,15 @@ struct rxrpc_local {
struct list_head new_client_calls; /* Newly created client calls need connection */
spinlock_t client_call_lock; /* Lock for ->new_client_calls */
struct sockaddr_rxrpc srx; /* local address */
- /* Provide a kvec table sufficiently large to manage either a DATA
- * packet with a maximum set of jumbo subpackets or a PING ACK padded
- * out to 64K with zeropages for PMTUD.
- */
- struct kvec kvec[1 + RXRPC_MAX_NR_JUMBO > 3 + 16 ?
- 1 + RXRPC_MAX_NR_JUMBO : 3 + 16];
+ union {
+ /* Provide a kvec table sufficiently large to manage either a
+ * DATA packet with a maximum set of jumbo subpackets or a PING
+ * ACK padded out to 64K with zeropages for PMTUD.
+ */
+ struct kvec kvec[1 + RXRPC_MAX_NR_JUMBO > 3 + 16 ?
+ 1 + RXRPC_MAX_NR_JUMBO : 3 + 16];
+ struct bio_vec bvec[3 + 16];
+ };
};
/*
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index a4b363b47cca..49fccee1a726 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -149,6 +149,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx,
id_in_use:
write_unlock(&rx->call_lock);
+ rxrpc_prefail_call(call, RXRPC_CALL_LOCAL_ERROR, -EBADSLT);
rxrpc_cleanup_call(call);
_leave(" = -EBADSLT");
return -EBADSLT;
@@ -254,6 +255,9 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
unsigned short call_tail, conn_tail, peer_tail;
unsigned short call_count, conn_count;
+ if (!b)
+ return NULL;
+
/* #calls >= #conns >= #peers must hold true. */
call_head = smp_load_acquire(&b->call_backlog_head);
call_tail = b->call_backlog_tail;
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 0af19bcdc80a..ef7b3096c95e 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -924,7 +924,7 @@ void rxrpc_send_response(struct rxrpc_connection *conn, struct sk_buff *response
{
struct rxrpc_skb_priv *sp = rxrpc_skb(response);
struct scatterlist sg[16];
- struct bio_vec bvec[16];
+ struct bio_vec *bvec = conn->local->bvec;
struct msghdr msg;
size_t len = sp->resp.len;
__be32 wserial;
@@ -938,6 +938,9 @@ void rxrpc_send_response(struct rxrpc_connection *conn, struct sk_buff *response
if (ret < 0)
goto fail;
nr_sg = ret;
+ ret = -EIO;
+ if (WARN_ON_ONCE(nr_sg > ARRAY_SIZE(conn->local->bvec)))
+ goto fail;
for (int i = 0; i < nr_sg; i++)
bvec_set_page(&bvec[i], sg_page(&sg[i]), sg[i].length, sg[i].offset);
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index d8a33486c511..d7c767b861a4 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -336,17 +336,22 @@ out:
return q;
}
-static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid)
+static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid,
+ struct netlink_ext_ack *extack)
{
unsigned long cl;
const struct Qdisc_class_ops *cops = p->ops->cl_ops;
- if (cops == NULL)
- return NULL;
+ if (cops == NULL) {
+ NL_SET_ERR_MSG(extack, "Parent qdisc is not classful");
+ return ERR_PTR(-EOPNOTSUPP);
+ }
cl = cops->find(p, classid);
- if (cl == 0)
- return NULL;
+ if (cl == 0) {
+ NL_SET_ERR_MSG(extack, "Specified class not found");
+ return ERR_PTR(-ENOENT);
+ }
return cops->leaf(p, cl);
}
@@ -596,16 +601,6 @@ out:
qdisc_skb_cb(skb)->pkt_len = pkt_len;
}
-void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc)
-{
- if (!(qdisc->flags & TCQ_F_WARN_NONWC)) {
- pr_warn("%s: %s qdisc %X: is non-work-conserving?\n",
- txt, qdisc->ops->id, qdisc->handle >> 16);
- qdisc->flags |= TCQ_F_WARN_NONWC;
- }
-}
-EXPORT_SYMBOL(qdisc_warn_nonwc);
-
static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer)
{
struct qdisc_watchdog *wd = container_of(timer, struct qdisc_watchdog,
@@ -1490,7 +1485,7 @@ static int __tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
NL_SET_ERR_MSG(extack, "Failed to find qdisc with specified classid");
return -ENOENT;
}
- q = qdisc_leaf(p, clid);
+ q = qdisc_leaf(p, clid, extack);
} else if (dev_ingress_queue(dev)) {
q = rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping);
}
@@ -1501,6 +1496,8 @@ static int __tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
NL_SET_ERR_MSG(extack, "Cannot find specified qdisc on specified device");
return -ENOENT;
}
+ if (IS_ERR(q))
+ return PTR_ERR(q);
if (tcm->tcm_handle && q->handle != tcm->tcm_handle) {
NL_SET_ERR_MSG(extack, "Invalid handle");
@@ -1602,7 +1599,9 @@ static int __tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
NL_SET_ERR_MSG(extack, "Failed to find specified qdisc");
return -ENOENT;
}
- q = qdisc_leaf(p, clid);
+ q = qdisc_leaf(p, clid, extack);
+ if (IS_ERR(q))
+ return PTR_ERR(q);
} else if (dev_ingress_queue_create(dev)) {
q = rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping);
}
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 5a7745170e84..d8fd35da32a7 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -835,22 +835,6 @@ update_vf(struct hfsc_class *cl, unsigned int len, u64 cur_time)
}
}
-static unsigned int
-qdisc_peek_len(struct Qdisc *sch)
-{
- struct sk_buff *skb;
- unsigned int len;
-
- skb = sch->ops->peek(sch);
- if (unlikely(skb == NULL)) {
- qdisc_warn_nonwc("qdisc_peek_len", sch);
- return 0;
- }
- len = qdisc_pkt_len(skb);
-
- return len;
-}
-
static void
hfsc_adjust_levels(struct hfsc_class *cl)
{
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index bf1282cb22eb..bcce36608871 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -989,7 +989,7 @@ static struct sk_buff *agg_dequeue(struct qfq_aggregate *agg,
if (cl->qdisc->q.qlen == 0) /* no more packets, remove from list */
list_del_init(&cl->alist);
- else if (cl->deficit < qdisc_pkt_len(cl->qdisc->ops->peek(cl->qdisc))) {
+ else if (cl->deficit < qdisc_peek_len(cl->qdisc)) {
cl->deficit += agg->lmax;
list_move_tail(&cl->alist, &agg->active);
}
diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c
index 8ee0c07d00e9..ffe577bf6b51 100644
--- a/net/tipc/topsrv.c
+++ b/net/tipc/topsrv.c
@@ -704,8 +704,10 @@ static void tipc_topsrv_stop(struct net *net)
for (id = 0; srv->idr_in_use; id++) {
con = idr_find(&srv->conn_idr, id);
if (con) {
+ conn_get(con);
spin_unlock_bh(&srv->idr_lock);
tipc_conn_close(con);
+ conn_put(con);
spin_lock_bh(&srv->idr_lock);
}
}
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 2e7a3034e965..1053662725f8 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -407,6 +407,8 @@ EXPORT_SYMBOL_GPL(vsock_enqueue_accept);
static bool vsock_use_local_transport(unsigned int remote_cid)
{
+ lockdep_assert_held(&vsock_register_mutex);
+
if (!transport_local)
return false;
@@ -464,6 +466,8 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
remote_flags = vsk->remote_addr.svm_flags;
+ mutex_lock(&vsock_register_mutex);
+
switch (sk->sk_type) {
case SOCK_DGRAM:
new_transport = transport_dgram;
@@ -479,12 +483,15 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
new_transport = transport_h2g;
break;
default:
- return -ESOCKTNOSUPPORT;
+ ret = -ESOCKTNOSUPPORT;
+ goto err;
}
if (vsk->transport) {
- if (vsk->transport == new_transport)
- return 0;
+ if (vsk->transport == new_transport) {
+ ret = 0;
+ goto err;
+ }
/* transport->release() must be called with sock lock acquired.
* This path can only be taken during vsock_connect(), where we
@@ -508,8 +515,16 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
/* We increase the module refcnt to prevent the transport unloading
* while there are open sockets assigned to it.
*/
- if (!new_transport || !try_module_get(new_transport->module))
- return -ENODEV;
+ if (!new_transport || !try_module_get(new_transport->module)) {
+ ret = -ENODEV;
+ goto err;
+ }
+
+ /* It's safe to release the mutex after a successful try_module_get().
+ * Whichever transport `new_transport` points at, it won't go away until
+ * the last module_put() below or in vsock_deassign_transport().
+ */
+ mutex_unlock(&vsock_register_mutex);
if (sk->sk_type == SOCK_SEQPACKET) {
if (!new_transport->seqpacket_allow ||
@@ -528,12 +543,31 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
vsk->transport = new_transport;
return 0;
+err:
+ mutex_unlock(&vsock_register_mutex);
+ return ret;
}
EXPORT_SYMBOL_GPL(vsock_assign_transport);
+/*
+ * Provide safe access to static transport_{h2g,g2h,dgram,local} callbacks.
+ * Otherwise we may race with module removal. Do not use on `vsk->transport`.
+ */
+static u32 vsock_registered_transport_cid(const struct vsock_transport **transport)
+{
+ u32 cid = VMADDR_CID_ANY;
+
+ mutex_lock(&vsock_register_mutex);
+ if (*transport)
+ cid = (*transport)->get_local_cid();
+ mutex_unlock(&vsock_register_mutex);
+
+ return cid;
+}
+
bool vsock_find_cid(unsigned int cid)
{
- if (transport_g2h && cid == transport_g2h->get_local_cid())
+ if (cid == vsock_registered_transport_cid(&transport_g2h))
return true;
if (transport_h2g && cid == VMADDR_CID_HOST)
@@ -2536,18 +2570,19 @@ static long vsock_dev_do_ioctl(struct file *filp,
unsigned int cmd, void __user *ptr)
{
u32 __user *p = ptr;
- u32 cid = VMADDR_CID_ANY;
int retval = 0;
+ u32 cid;
switch (cmd) {
case IOCTL_VM_SOCKETS_GET_LOCAL_CID:
/* To be compatible with the VMCI behavior, we prioritize the
* guest CID instead of well-know host CID (VMADDR_CID_HOST).
*/
- if (transport_g2h)
- cid = transport_g2h->get_local_cid();
- else if (transport_h2g)
- cid = transport_h2g->get_local_cid();
+ cid = vsock_registered_transport_cid(&transport_g2h);
+ if (cid == VMADDR_CID_ANY)
+ cid = vsock_registered_transport_cid(&transport_h2g);
+ if (cid == VMADDR_CID_ANY)
+ cid = vsock_registered_transport_cid(&transport_local);
if (put_user(cid, p) != 0)
retval = -EFAULT;
generated by cgit (git 2.34.1) at 2025-07-11 04:45:53 +0000