summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/core/dev.c28
-rw-r--r--net/core/devlink.c43
-rw-r--r--net/core/skbuff.c12
-rw-r--r--net/ipv4/fib_frontend.c12
-rw-r--r--net/ipv4/fib_semantics.c50
-rw-r--r--net/ipv4/route.c7
-rw-r--r--net/ipv4/udp.c2
-rw-r--r--net/ipv6/ip6_fib.c2
-rw-r--r--net/rds/send.c13
-rw-r--r--net/rxrpc/ar-internal.h23
-rw-r--r--net/rxrpc/call_accept.c27
-rw-r--r--net/rxrpc/call_object.c5
-rw-r--r--net/rxrpc/conn_client.c10
-rw-r--r--net/rxrpc/conn_event.c26
-rw-r--r--net/rxrpc/input.c251
-rw-r--r--net/rxrpc/local_object.c30
-rw-r--r--net/rxrpc/peer_event.c5
-rw-r--r--net/rxrpc/peer_object.c29
-rw-r--r--net/sched/cls_u32.c6
-rw-r--r--net/sched/sch_cake.c2
-rw-r--r--net/tipc/link.c27
-rw-r--r--net/tipc/socket.c14
22 files changed, 414 insertions, 210 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index 0b2d777e5b9e..a4d39b87b4e5 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1752,6 +1752,28 @@ int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
}
EXPORT_SYMBOL(call_netdevice_notifiers);
+/**
+ * call_netdevice_notifiers_mtu - call all network notifier blocks
+ * @val: value passed unmodified to notifier function
+ * @dev: net_device pointer passed unmodified to notifier function
+ * @arg: additional u32 argument passed to the notifier function
+ *
+ * Call all network notifier blocks. Parameters and return value
+ * are as for raw_notifier_call_chain().
+ */
+static int call_netdevice_notifiers_mtu(unsigned long val,
+ struct net_device *dev, u32 arg)
+{
+ struct netdev_notifier_info_ext info = {
+ .info.dev = dev,
+ .ext.mtu = arg,
+ };
+
+ BUILD_BUG_ON(offsetof(struct netdev_notifier_info_ext, info) != 0);
+
+ return call_netdevice_notifiers_info(val, &info.info);
+}
+
#ifdef CONFIG_NET_INGRESS
static DEFINE_STATIC_KEY_FALSE(ingress_needed_key);
@@ -7575,14 +7597,16 @@ int dev_set_mtu_ext(struct net_device *dev, int new_mtu,
err = __dev_set_mtu(dev, new_mtu);
if (!err) {
- err = call_netdevice_notifiers(NETDEV_CHANGEMTU, dev);
+ err = call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev,
+ orig_mtu);
err = notifier_to_errno(err);
if (err) {
/* setting mtu back and notifying everyone again,
* so that they have a chance to revert changes.
*/
__dev_set_mtu(dev, orig_mtu);
- call_netdevice_notifiers(NETDEV_CHANGEMTU, dev);
+ call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev,
+ new_mtu);
}
}
return err;
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 6dae81d65d5c..3a4b29a13d31 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3012,6 +3012,8 @@ devlink_param_value_get_from_info(const struct devlink_param *param,
struct genl_info *info,
union devlink_param_value *value)
{
+ int len;
+
if (param->type != DEVLINK_PARAM_TYPE_BOOL &&
!info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA])
return -EINVAL;
@@ -3027,10 +3029,13 @@ devlink_param_value_get_from_info(const struct devlink_param *param,
value->vu32 = nla_get_u32(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]);
break;
case DEVLINK_PARAM_TYPE_STRING:
- if (nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) >
- DEVLINK_PARAM_MAX_STRING_VALUE)
+ len = strnlen(nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]),
+ nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]));
+ if (len == nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) ||
+ len >= __DEVLINK_PARAM_MAX_STRING_VALUE)
return -EINVAL;
- value->vstr = nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]);
+ strcpy(value->vstr,
+ nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]));
break;
case DEVLINK_PARAM_TYPE_BOOL:
value->vbool = info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA] ?
@@ -3117,7 +3122,10 @@ static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb,
return -EOPNOTSUPP;
if (cmode == DEVLINK_PARAM_CMODE_DRIVERINIT) {
- param_item->driverinit_value = value;
+ if (param->type == DEVLINK_PARAM_TYPE_STRING)
+ strcpy(param_item->driverinit_value.vstr, value.vstr);
+ else
+ param_item->driverinit_value = value;
param_item->driverinit_value_valid = true;
} else {
if (!param->set)
@@ -4557,7 +4565,10 @@ int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id,
DEVLINK_PARAM_CMODE_DRIVERINIT))
return -EOPNOTSUPP;
- *init_val = param_item->driverinit_value;
+ if (param_item->param->type == DEVLINK_PARAM_TYPE_STRING)
+ strcpy(init_val->vstr, param_item->driverinit_value.vstr);
+ else
+ *init_val = param_item->driverinit_value;
return 0;
}
@@ -4588,7 +4599,10 @@ int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id,
DEVLINK_PARAM_CMODE_DRIVERINIT))
return -EOPNOTSUPP;
- param_item->driverinit_value = init_val;
+ if (param_item->param->type == DEVLINK_PARAM_TYPE_STRING)
+ strcpy(param_item->driverinit_value.vstr, init_val.vstr);
+ else
+ param_item->driverinit_value = init_val;
param_item->driverinit_value_valid = true;
devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW);
@@ -4621,6 +4635,23 @@ void devlink_param_value_changed(struct devlink *devlink, u32 param_id)
EXPORT_SYMBOL_GPL(devlink_param_value_changed);
/**
+ * devlink_param_value_str_fill - Safely fill-up the string preventing
+ * from overflow of the preallocated buffer
+ *
+ * @dst_val: destination devlink_param_value
+ * @src: source buffer
+ */
+void devlink_param_value_str_fill(union devlink_param_value *dst_val,
+ const char *src)
+{
+ size_t len;
+
+ len = strlcpy(dst_val->vstr, src, __DEVLINK_PARAM_MAX_STRING_VALUE);
+ WARN_ON(len >= __DEVLINK_PARAM_MAX_STRING_VALUE);
+}
+EXPORT_SYMBOL_GPL(devlink_param_value_str_fill);
+
+/**
* devlink_region_create - create a new address region
*
* @devlink: devlink
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 0e937d3d85b5..54b961de9538 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4394,14 +4394,16 @@ EXPORT_SYMBOL_GPL(skb_complete_wifi_ack);
*/
bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off)
{
- if (unlikely(start > skb_headlen(skb)) ||
- unlikely((int)start + off > skb_headlen(skb) - 2)) {
- net_warn_ratelimited("bad partial csum: csum=%u/%u len=%u\n",
- start, off, skb_headlen(skb));
+ u32 csum_end = (u32)start + (u32)off + sizeof(__sum16);
+ u32 csum_start = skb_headroom(skb) + (u32)start;
+
+ if (unlikely(csum_start > U16_MAX || csum_end > skb_headlen(skb))) {
+ net_warn_ratelimited("bad partial csum: csum=%u/%u headroom=%u headlen=%u\n",
+ start, off, skb_headroom(skb), skb_headlen(skb));
return false;
}
skb->ip_summed = CHECKSUM_PARTIAL;
- skb->csum_start = skb_headroom(skb) + start;
+ skb->csum_start = csum_start;
skb->csum_offset = off;
skb_set_transport_header(skb, start);
return true;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 038f511c73fa..0f1beceb47d5 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1291,7 +1291,8 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event,
static int fib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
- struct netdev_notifier_changeupper_info *info;
+ struct netdev_notifier_changeupper_info *upper_info = ptr;
+ struct netdev_notifier_info_ext *info_ext = ptr;
struct in_device *in_dev;
struct net *net = dev_net(dev);
unsigned int flags;
@@ -1326,16 +1327,19 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
fib_sync_up(dev, RTNH_F_LINKDOWN);
else
fib_sync_down_dev(dev, event, false);
- /* fall through */
+ rt_cache_flush(net);
+ break;
case NETDEV_CHANGEMTU:
+ fib_sync_mtu(dev, info_ext->ext.mtu);
rt_cache_flush(net);
break;
case NETDEV_CHANGEUPPER:
- info = ptr;
+ upper_info = ptr;
/* flush all routes if dev is linked to or unlinked from
* an L3 master device (e.g., VRF)
*/
- if (info->upper_dev && netif_is_l3_master(info->upper_dev))
+ if (upper_info->upper_dev &&
+ netif_is_l3_master(upper_info->upper_dev))
fib_disable_ip(dev, NETDEV_DOWN, true);
break;
}
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index f8c7ec8171a8..b5c3937ca6ec 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1457,6 +1457,56 @@ static int call_fib_nh_notifiers(struct fib_nh *fib_nh,
return NOTIFY_DONE;
}
+/* Update the PMTU of exceptions when:
+ * - the new MTU of the first hop becomes smaller than the PMTU
+ * - the old MTU was the same as the PMTU, and it limited discovery of
+ * larger MTUs on the path. With that limit raised, we can now
+ * discover larger MTUs
+ * A special case is locked exceptions, for which the PMTU is smaller
+ * than the minimal accepted PMTU:
+ * - if the new MTU is greater than the PMTU, don't make any change
+ * - otherwise, unlock and set PMTU
+ */
+static void nh_update_mtu(struct fib_nh *nh, u32 new, u32 orig)
+{
+ struct fnhe_hash_bucket *bucket;
+ int i;
+
+ bucket = rcu_dereference_protected(nh->nh_exceptions, 1);
+ if (!bucket)
+ return;
+
+ for (i = 0; i < FNHE_HASH_SIZE; i++) {
+ struct fib_nh_exception *fnhe;
+
+ for (fnhe = rcu_dereference_protected(bucket[i].chain, 1);
+ fnhe;
+ fnhe = rcu_dereference_protected(fnhe->fnhe_next, 1)) {
+ if (fnhe->fnhe_mtu_locked) {
+ if (new <= fnhe->fnhe_pmtu) {
+ fnhe->fnhe_pmtu = new;
+ fnhe->fnhe_mtu_locked = false;
+ }
+ } else if (new < fnhe->fnhe_pmtu ||
+ orig == fnhe->fnhe_pmtu) {
+ fnhe->fnhe_pmtu = new;
+ }
+ }
+ }
+}
+
+void fib_sync_mtu(struct net_device *dev, u32 orig_mtu)
+{
+ unsigned int hash = fib_devindex_hashfn(dev->ifindex);
+ struct hlist_head *head = &fib_info_devhash[hash];
+ struct fib_nh *nh;
+
+ hlist_for_each_entry(nh, head, nh_hash) {
+ if (nh->nh_dev == dev)
+ nh_update_mtu(nh, dev->mtu, orig_mtu);
+ }
+}
+
/* Event force Flags Description
* NETDEV_CHANGE 0 LINKDOWN Carrier OFF, not for scope host
* NETDEV_DOWN 0 LINKDOWN|DEAD Link down, not for scope host
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f71d2395c428..c0a9d26c06ce 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1001,21 +1001,22 @@ out: kfree_skb(skb);
static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
{
struct dst_entry *dst = &rt->dst;
+ u32 old_mtu = ipv4_mtu(dst);
struct fib_result res;
bool lock = false;
if (ip_mtu_locked(dst))
return;
- if (ipv4_mtu(dst) < mtu)
+ if (old_mtu < mtu)
return;
if (mtu < ip_rt_min_pmtu) {
lock = true;
- mtu = ip_rt_min_pmtu;
+ mtu = min(old_mtu, ip_rt_min_pmtu);
}
- if (rt->rt_pmtu == mtu &&
+ if (rt->rt_pmtu == mtu && !lock &&
time_before(jiffies, dst->expires - ip_rt_mtu_expires / 2))
return;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 1bec2203d558..cf8252d05a01 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1627,7 +1627,7 @@ busy_check:
*err = error;
return NULL;
}
-EXPORT_SYMBOL_GPL(__skb_recv_udp);
+EXPORT_SYMBOL(__skb_recv_udp);
/*
* This should be easy, if there is something there we
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 9ba72d94d60f..0783af11b0b7 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -195,6 +195,8 @@ void fib6_info_destroy_rcu(struct rcu_head *head)
*ppcpu_rt = NULL;
}
}
+
+ free_percpu(f6i->rt6i_pcpu);
}
lwtstate_put(f6i->fib6_nh.nh_lwtstate);
diff --git a/net/rds/send.c b/net/rds/send.c
index 57b3d5a8b2db..fe785ee819dd 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1007,7 +1007,8 @@ static int rds_cmsg_send(struct rds_sock *rs, struct rds_message *rm,
return ret;
}
-static int rds_send_mprds_hash(struct rds_sock *rs, struct rds_connection *conn)
+static int rds_send_mprds_hash(struct rds_sock *rs,
+ struct rds_connection *conn, int nonblock)
{
int hash;
@@ -1023,10 +1024,16 @@ static int rds_send_mprds_hash(struct rds_sock *rs, struct rds_connection *conn)
* used. But if we are interrupted, we have to use the zero
* c_path in case the connection ends up being non-MP capable.
*/
- if (conn->c_npaths == 0)
+ if (conn->c_npaths == 0) {
+ /* Cannot wait for the connection be made, so just use
+ * the base c_path.
+ */
+ if (nonblock)
+ return 0;
if (wait_event_interruptible(conn->c_hs_waitq,
conn->c_npaths != 0))
hash = 0;
+ }
if (conn->c_npaths == 1)
hash = 0;
}
@@ -1256,7 +1263,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
}
if (conn->c_trans->t_mp_capable)
- cpath = &conn->c_path[rds_send_mprds_hash(rs, conn)];
+ cpath = &conn->c_path[rds_send_mprds_hash(rs, conn, nonblock)];
else
cpath = &conn->c_path[0];
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 76569c178915..8cee7644965c 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -302,6 +302,7 @@ struct rxrpc_peer {
/* calculated RTT cache */
#define RXRPC_RTT_CACHE_SIZE 32
+ spinlock_t rtt_input_lock; /* RTT lock for input routine */
ktime_t rtt_last_req; /* Time of last RTT request */
u64 rtt; /* Current RTT estimate (in nS) */
u64 rtt_sum; /* Sum of cache contents */
@@ -442,17 +443,17 @@ struct rxrpc_connection {
spinlock_t state_lock; /* state-change lock */
enum rxrpc_conn_cache_state cache_state;
enum rxrpc_conn_proto_state state; /* current state of connection */
- u32 local_abort; /* local abort code */
- u32 remote_abort; /* remote abort code */
+ u32 abort_code; /* Abort code of connection abort */
int debug_id; /* debug ID for printks */
atomic_t serial; /* packet serial number counter */
unsigned int hi_serial; /* highest serial number received */
u32 security_nonce; /* response re-use preventer */
- u16 service_id; /* Service ID, possibly upgraded */
+ u32 service_id; /* Service ID, possibly upgraded */
u8 size_align; /* data size alignment (for security) */
u8 security_size; /* security header size */
u8 security_ix; /* security type */
u8 out_clientflag; /* RXRPC_CLIENT_INITIATED if we are client */
+ short error; /* Local error code */
};
static inline bool rxrpc_to_server(const struct rxrpc_skb_priv *sp)
@@ -635,6 +636,8 @@ struct rxrpc_call {
bool tx_phase; /* T if transmission phase, F if receive phase */
u8 nr_jumbo_bad; /* Number of jumbo dups/exceeds-windows */
+ spinlock_t input_lock; /* Lock for packet input to this call */
+
/* receive-phase ACK management */
u8 ackr_reason; /* reason to ACK */
u16 ackr_skew; /* skew on packet being ACK'd */
@@ -720,8 +723,6 @@ int rxrpc_service_prealloc(struct rxrpc_sock *, gfp_t);
void rxrpc_discard_prealloc(struct rxrpc_sock *);
struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *,
struct rxrpc_sock *,
- struct rxrpc_peer *,
- struct rxrpc_connection *,
struct sk_buff *);
void rxrpc_accept_incoming_calls(struct rxrpc_local *);
struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *, unsigned long,
@@ -891,8 +892,9 @@ extern unsigned long rxrpc_conn_idle_client_fast_expiry;
extern struct idr rxrpc_client_conn_ids;
void rxrpc_destroy_client_conn_ids(void);
-int rxrpc_connect_call(struct rxrpc_call *, struct rxrpc_conn_parameters *,
- struct sockaddr_rxrpc *, gfp_t);
+int rxrpc_connect_call(struct rxrpc_sock *, struct rxrpc_call *,
+ struct rxrpc_conn_parameters *, struct sockaddr_rxrpc *,
+ gfp_t);
void rxrpc_expose_client_call(struct rxrpc_call *);
void rxrpc_disconnect_client_call(struct rxrpc_call *);
void rxrpc_put_client_conn(struct rxrpc_connection *);
@@ -965,7 +967,7 @@ void rxrpc_unpublish_service_conn(struct rxrpc_connection *);
/*
* input.c
*/
-void rxrpc_data_ready(struct sock *);
+int rxrpc_input_packet(struct sock *, struct sk_buff *);
/*
* insecure.c
@@ -1045,10 +1047,11 @@ void rxrpc_peer_keepalive_worker(struct work_struct *);
*/
struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *,
const struct sockaddr_rxrpc *);
-struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *,
+struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *, struct rxrpc_local *,
struct sockaddr_rxrpc *, gfp_t);
struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t);
-void rxrpc_new_incoming_peer(struct rxrpc_local *, struct rxrpc_peer *);
+void rxrpc_new_incoming_peer(struct rxrpc_sock *, struct rxrpc_local *,
+ struct rxrpc_peer *);
void rxrpc_destroy_all_peers(struct rxrpc_net *);
struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *);
struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *);
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index 8354cadbb839..e0d8ca03169a 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -287,7 +287,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
(peer_tail + 1) &
(RXRPC_BACKLOG_MAX - 1));
- rxrpc_new_incoming_peer(local, peer);
+ rxrpc_new_incoming_peer(rx, local, peer);
}
/* Now allocate and set up the connection */
@@ -333,11 +333,11 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
*/
struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local,
struct rxrpc_sock *rx,
- struct rxrpc_peer *peer,
- struct rxrpc_connection *conn,
struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+ struct rxrpc_connection *conn;
+ struct rxrpc_peer *peer;
struct rxrpc_call *call;
_enter("");
@@ -354,6 +354,13 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local,
goto out;
}
+ /* The peer, connection and call may all have sprung into existence due
+ * to a duplicate packet being handled on another CPU in parallel, so
+ * we have to recheck the routing. However, we're now holding
+ * rx->incoming_lock, so the values should remain stable.
+ */
+ conn = rxrpc_find_connection_rcu(local, skb, &peer);
+
call = rxrpc_alloc_incoming_call(rx, local, peer, conn, skb);
if (!call) {
skb->mark = RXRPC_SKB_MARK_REJECT_BUSY;
@@ -396,20 +403,22 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local,
case RXRPC_CONN_SERVICE:
write_lock(&call->state_lock);
- if (rx->discard_new_call)
- call->state = RXRPC_CALL_SERVER_RECV_REQUEST;
- else
- call->state = RXRPC_CALL_SERVER_ACCEPTING;
+ if (call->state < RXRPC_CALL_COMPLETE) {
+ if (rx->discard_new_call)
+ call->state = RXRPC_CALL_SERVER_RECV_REQUEST;
+ else
+ call->state = RXRPC_CALL_SERVER_ACCEPTING;
+ }
write_unlock(&call->state_lock);
break;
case RXRPC_CONN_REMOTELY_ABORTED:
rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED,
- conn->remote_abort, -ECONNABORTED);
+ conn->abort_code, conn->error);
break;
case RXRPC_CONN_LOCALLY_ABORTED:
rxrpc_abort_call("CON", call, sp->hdr.seq,
- conn->local_abort, -ECONNABORTED);
+ conn->abort_code, conn->error);
break;
default:
BUG();
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 799f75b6900d..8f1a8f85b1f9 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -138,6 +138,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp,
init_waitqueue_head(&call->waitq);
spin_lock_init(&call->lock);
spin_lock_init(&call->notify_lock);
+ spin_lock_init(&call->input_lock);
rwlock_init(&call->state_lock);
atomic_set(&call->usage, 1);
call->debug_id = debug_id;
@@ -287,7 +288,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
/* Set up or get a connection record and set the protocol parameters,
* including channel number and call ID.
*/
- ret = rxrpc_connect_call(call, cp, srx, gfp);
+ ret = rxrpc_connect_call(rx, call, cp, srx, gfp);
if (ret < 0)
goto error;
@@ -339,7 +340,7 @@ int rxrpc_retry_client_call(struct rxrpc_sock *rx,
/* Set up or get a connection record and set the protocol parameters,
* including channel number and call ID.
*/
- ret = rxrpc_connect_call(call, cp, srx, gfp);
+ ret = rxrpc_connect_call(rx, call, cp, srx, gfp);
if (ret < 0)
goto error;
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index 8acf74fe24c0..521189f4b666 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -276,7 +276,8 @@ dont_reuse:
* If we return with a connection, the call will be on its waiting list. It's
* left to the caller to assign a channel and wake up the call.
*/
-static int rxrpc_get_client_conn(struct rxrpc_call *call,
+static int rxrpc_get_client_conn(struct rxrpc_sock *rx,
+ struct rxrpc_call *call,
struct rxrpc_conn_parameters *cp,
struct sockaddr_rxrpc *srx,
gfp_t gfp)
@@ -289,7 +290,7 @@ static int rxrpc_get_client_conn(struct rxrpc_call *call,
_enter("{%d,%lx},", call->debug_id, call->user_call_ID);
- cp->peer = rxrpc_lookup_peer(cp->local, srx, gfp);
+ cp->peer = rxrpc_lookup_peer(rx, cp->local, srx, gfp);
if (!cp->peer)
goto error;
@@ -683,7 +684,8 @@ out:
* find a connection for a call
* - called in process context with IRQs enabled
*/
-int rxrpc_connect_call(struct rxrpc_call *call,
+int rxrpc_connect_call(struct rxrpc_sock *rx,
+ struct rxrpc_call *call,
struct rxrpc_conn_parameters *cp,
struct sockaddr_rxrpc *srx,
gfp_t gfp)
@@ -696,7 +698,7 @@ int rxrpc_connect_call(struct rxrpc_call *call,
rxrpc_discard_expired_client_conns(&rxnet->client_conn_reaper);
rxrpc_cull_active_client_conns(rxnet);
- ret = rxrpc_get_client_conn(call, cp, srx, gfp);
+ ret = rxrpc_get_client_conn(rx, call, cp, srx, gfp);
if (ret < 0)
goto out;
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 6df56ce68861..b6fca8ebb117 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -126,7 +126,7 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
switch (chan->last_type) {
case RXRPC_PACKET_TYPE_ABORT:
- _proto("Tx ABORT %%%u { %d } [re]", serial, conn->local_abort);
+ _proto("Tx ABORT %%%u { %d } [re]", serial, conn->abort_code);
break;
case RXRPC_PACKET_TYPE_ACK:
trace_rxrpc_tx_ack(chan->call_debug_id, serial,
@@ -153,13 +153,12 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
* pass a connection-level abort onto all calls on that connection
*/
static void rxrpc_abort_calls(struct rxrpc_connection *conn,
- enum rxrpc_call_completion compl,
- u32 abort_code, int error)
+ enum rxrpc_call_completion compl)
{
struct rxrpc_call *call;
int i;
- _enter("{%d},%x", conn->debug_id, abort_code);
+ _enter("{%d},%x", conn->debug_id, conn->abort_code);
spin_lock(&conn->channel_lock);
@@ -172,9 +171,11 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn,
trace_rxrpc_abort(call->debug_id,
"CON", call->cid,
call->call_id, 0,
- abort_code, error);
+ conn->abort_code,
+ conn->error);
if (rxrpc_set_call_completion(call, compl,
- abort_code, error))
+ conn->abort_code,
+ conn->error))
rxrpc_notify_socket(call);
}
}
@@ -207,10 +208,12 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn,
return 0;
}
+ conn->error = error;
+ conn->abort_code = abort_code;
conn->state = RXRPC_CONN_LOCALLY_ABORTED;
spin_unlock_bh(&conn->state_lock);
- rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED, abort_code, error);
+ rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED);
msg.msg_name = &conn->params.peer->srx.transport;
msg.msg_namelen = conn->params.peer->srx.transport_len;
@@ -229,7 +232,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn,
whdr._rsvd = 0;
whdr.serviceId = htons(conn->service_id);
- word = htonl(conn->local_abort);
+ word = htonl(conn->abort_code);
iov[0].iov_base = &whdr;
iov[0].iov_len = sizeof(whdr);
@@ -240,7 +243,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn,
serial = atomic_inc_return(&conn->serial);
whdr.serial = htonl(serial);
- _proto("Tx CONN ABORT %%%u { %d }", serial, conn->local_abort);
+ _proto("Tx CONN ABORT %%%u { %d }", serial, conn->abort_code);
ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
if (ret < 0) {
@@ -315,9 +318,10 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
abort_code = ntohl(wtmp);
_proto("Rx ABORT %%%u { ac=%d }", sp->hdr.serial, abort_code);
+ conn->error = -ECONNABORTED;
+ conn->abort_code = abort_code;
conn->state = RXRPC_CONN_REMOTELY_ABORTED;
- rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED,
- abort_code, -ECONNABORTED);
+ rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED);
return -ECONNABORTED;
case RXRPC_PACKET_TYPE_CHALLENGE:
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 5b2626929822..9128aa0e40aa 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -216,10 +216,11 @@ static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb,
/*
* Apply a hard ACK by advancing the Tx window.
*/
-static void rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
+static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
struct rxrpc_ack_summary *summary)
{
struct sk_buff *skb, *list = NULL;
+ bool rot_last = false;
int ix;
u8 annotation;
@@ -243,15 +244,17 @@ static void rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
skb->next = list;
list = skb;
- if (annotation & RXRPC_TX_ANNO_LAST)
+ if (annotation & RXRPC_TX_ANNO_LAST) {
set_bit(RXRPC_CALL_TX_LAST, &call->flags);
+ rot_last = true;
+ }
if ((annotation & RXRPC_TX_ANNO_MASK) != RXRPC_TX_ANNO_ACK)
summary->nr_rot_new_acks++;
}
spin_unlock(&call->lock);
- trace_rxrpc_transmit(call, (test_bit(RXRPC_CALL_TX_LAST, &call->flags) ?
+ trace_rxrpc_transmit(call, (rot_last ?
rxrpc_transmit_rotate_last :
rxrpc_transmit_rotate));
wake_up(&call->waitq);
@@ -262,6 +265,8 @@ static void rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
skb_mark_not_on_list(skb);
rxrpc_free_skb(skb, rxrpc_skb_tx_freed);
}
+
+ return rot_last;
}
/*
@@ -273,23 +278,26 @@ static void rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
static bool rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun,
const char *abort_why)
{
+ unsigned int state;
ASSERT(test_bit(RXRPC_CALL_TX_LAST, &call->flags));
write_lock(&call->state_lock);
- switch (call->state) {
+ state = call->state;
+ switch (state) {
case RXRPC_CALL_CLIENT_SEND_REQUEST:
case RXRPC_CALL_CLIENT_AWAIT_REPLY:
if (reply_begun)
- call->state = RXRPC_CALL_CLIENT_RECV_REPLY;
+ call->state = state = RXRPC_CALL_CLIENT_RECV_REPLY;
else
- call->state = RXRPC_CALL_CLIENT_AWAIT_REPLY;
+ call->state = state = RXRPC_CALL_CLIENT_AWAIT_REPLY;
break;
case RXRPC_CALL_SERVER_AWAIT_ACK:
__rxrpc_call_completed(call);
rxrpc_notify_socket(call);
+ state = call->state;
break;
default:
@@ -297,11 +305,10 @@ static bool rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun,
}
write_unlock(&call->state_lock);
- if (call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY) {
+ if (state == RXRPC_CALL_CLIENT_AWAIT_REPLY)
trace_rxrpc_transmit(call, rxrpc_transmit_await_reply);
- } else {
+ else
trace_rxrpc_transmit(call, rxrpc_transmit_end);
- }
_leave(" = ok");
return true;
@@ -332,11 +339,11 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call)
trace_rxrpc_timer(call, rxrpc_timer_init_for_reply, now);
}
- if (!test_bit(RXRPC_CALL_TX_LAST, &call->flags))
- rxrpc_rotate_tx_window(call, top, &summary);
if (!test_bit(RXRPC_CALL_TX_LAST, &call->flags)) {
- rxrpc_proto_abort("TXL", call, top);
- return false;
+ if (!rxrpc_rotate_tx_window(call, top, &summary)) {
+ rxrpc_proto_abort("TXL", call, top);
+ return false;
+ }
}
if (!rxrpc_end_tx_phase(call, true, "ETD"))
return false;
@@ -452,13 +459,15 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb,
}
}
+ spin_lock(&call->input_lock);
+
/* Received data implicitly ACKs all of the request packets we sent
* when we're acting as a client.
*/
if ((state == RXRPC_CALL_CLIENT_SEND_REQUEST ||
state == RXRPC_CALL_CLIENT_AWAIT_REPLY) &&
!rxrpc_receiving_reply(call))
- return;
+ goto unlock;
call->ackr_prev_seq = seq;
@@ -488,12 +497,16 @@ next_subpacket:
if (flags & RXRPC_LAST_PACKET) {
if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) &&
- seq != call->rx_top)
- return rxrpc_proto_abort("LSN", call, seq);
+ seq != call->rx_top) {
+ rxrpc_proto_abort("LSN", call, seq);
+ goto unlock;
+ }
} else {
if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) &&
- after_eq(seq, call->rx_top))
- return rxrpc_proto_abort("LSA", call, seq);
+ after_eq(seq, call->rx_top)) {
+ rxrpc_proto_abort("LSA", call, seq);
+ goto unlock;
+ }
}
trace_rxrpc_rx_data(call->debug_id, seq, serial, flags, annotation);
@@ -560,8 +573,10 @@ next_subpacket:
skip:
offset += len;
if (flags & RXRPC_JUMBO_PACKET) {
- if (skb_copy_bits(skb, offset, &flags, 1) < 0)
- return rxrpc_proto_abort("XJF", call, seq);
+ if (skb_copy_bits(skb, offset, &flags, 1) < 0) {
+ rxrpc_proto_abort("XJF", call, seq);
+ goto unlock;
+ }
offset += sizeof(struct rxrpc_jumbo_header);
seq++;
serial++;
@@ -601,6 +616,9 @@ ack:
trace_rxrpc_notify_socket(call->debug_id, serial);
rxrpc_notify_socket(call);
}
+
+unlock:
+ spin_unlock(&call->input_lock);
_leave(" [queued]");
}
@@ -687,15 +705,14 @@ static void rxrpc_input_ping_response(struct rxrpc_call *call,
ping_time = call->ping_time;
smp_rmb();
- ping_serial = call->ping_serial;
+ ping_serial = READ_ONCE(call->ping_serial);
if (orig_serial == call->acks_lost_ping)
rxrpc_input_check_for_lost_ack(call);
- if (!test_bit(RXRPC_CALL_PINGING, &call->flags) ||
- before(orig_serial, ping_serial))
+ if (before(orig_serial, ping_serial) ||
+ !test_and_clear_bit(RXRPC_CALL_PINGING, &call->flags))
return;
- clear_bit(RXRPC_CALL_PINGING, &call->flags);
if (after(orig_serial, ping_serial))
return;
@@ -861,15 +878,32 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
rxrpc_propose_ack_respond_to_ack);
}
+ /* Discard any out-of-order or duplicate ACKs. */
+ if (before_eq(sp->hdr.serial, call->acks_latest))
+ return;
+
+ buf.info.rxMTU = 0;
ioffset = offset + nr_acks + 3;
- if (skb->len >= ioffset + sizeof(buf.info)) {
- if (skb_copy_bits(skb, ioffset, &buf.info, sizeof(buf.info)) < 0)
- return rxrpc_proto_abort("XAI", call, 0);
+ if (skb->len >= ioffset + sizeof(buf.info) &&
+ skb_copy_bits(skb, ioffset, &buf.info, sizeof(buf.info)) < 0)
+ return rxrpc_proto_abort("XAI", call, 0);
+
+ spin_lock(&call->input_lock);
+
+ /* Discard any out-of-order or duplicate ACKs. */
+ if (before_eq(sp->hdr.serial, call->acks_latest))
+ goto out;
+ call->acks_latest_ts = skb->tstamp;
+ call->acks_latest = sp->hdr.serial;
+
+ /* Parse rwind and mtu sizes if provided. */
+ if (buf.info.rxMTU)
rxrpc_input_ackinfo(call, skb, &buf.info);
- }
- if (first_soft_ack == 0)
- return rxrpc_proto_abort("AK0", call, 0);
+ if (first_soft_ack == 0) {
+ rxrpc_proto_abort("AK0", call, 0);
+ goto out;
+ }
/* Ignore ACKs unless we are or have just been transmitting. */
switch (READ_ONCE(call->state)) {
@@ -879,39 +913,35 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
case RXRPC_CALL_SERVER_AWAIT_ACK:
break;
default:
- return;
- }
-
- /* Discard any out-of-order or duplicate ACKs. */
- if (before_eq(sp->hdr.serial, call->acks_latest)) {
- _debug("discard ACK %d <= %d",
- sp->hdr.serial, call->acks_latest);
- return;
+ goto out;
}
- call->acks_latest_ts = skb->tstamp;
- call->acks_latest = sp->hdr.serial;
if (before(hard_ack, call->tx_hard_ack) ||
- after(hard_ack, call->tx_top))
- return rxrpc_proto_abort("AKW", call, 0);
- if (nr_acks > call->tx_top - hard_ack)
- return rxrpc_proto_abort("AKN", call, 0);
+ after(hard_ack, call->tx_top)) {
+ rxrpc_proto_abort("AKW", call, 0);
+ goto out;
+ }
+ if (nr_acks > call->tx_top - hard_ack) {
+ rxrpc_proto_abort("AKN", call, 0);
+ goto out;
+ }
- if (after(hard_ack, call->tx_hard_ack))
- rxrpc_rotate_tx_window(call, hard_ack, &summary);
+ if (after(hard_ack, call->tx_hard_ack)) {
+ if (rxrpc_rotate_tx_window(call, hard_ack, &summary)) {
+ rxrpc_end_tx_phase(call, false, "ETA");
+ goto out;
+ }
+ }
if (nr_acks > 0) {
- if (skb_copy_bits(skb, offset, buf.acks, nr_acks) < 0)
- return rxrpc_proto_abort("XSA", call, 0);
+ if (skb_copy_bits(skb, offset, buf.acks, nr_acks) < 0) {
+ rxrpc_proto_abort("XSA", call, 0);
+ goto out;
+ }
rxrpc_input_soft_acks(call, buf.acks, first_soft_ack, nr_acks,
&summary);
}
- if (test_bit(RXRPC_CALL_TX_LAST, &call->flags)) {
- rxrpc_end_tx_phase(call, false, "ETA");
- return;
- }
-
if (call->rxtx_annotations[call->tx_top & RXRPC_RXTX_BUFF_MASK] &
RXRPC_TX_ANNO_LAST &&
summary.nr_acks == call->tx_top - hard_ack &&
@@ -920,7 +950,9 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
false, true,
rxrpc_propose_ack_ping_for_lost_reply);
- return rxrpc_congestion_management(call, skb, &summary, acked_serial);
+ rxrpc_congestion_management(call, skb, &summary, acked_serial);
+out:
+ spin_unlock(&call->input_lock);
}
/*
@@ -933,9 +965,12 @@ static void rxrpc_input_ackall(struct rxrpc_call *call, struct sk_buff *skb)
_proto("Rx ACKALL %%%u", sp->hdr.serial);
- rxrpc_rotate_tx_window(call, call->tx_top, &summary);
- if (test_bit(RXRPC_CALL_TX_LAST, &call->flags))
+ spin_lock(&call->input_lock);
+
+ if (rxrpc_rotate_tx_window(call, call->tx_top, &summary))
rxrpc_end_tx_phase(call, false, "ETL");
+
+ spin_unlock(&call->input_lock);
}
/*
@@ -1018,18 +1053,19 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call,
}
/*
- * Handle a new call on a channel implicitly completing the preceding call on
- * that channel.
+ * Handle a new service call on a channel implicitly completing the preceding
+ * call on that channel. This does not apply to client conns.
*
* TODO: If callNumber > call_id + 1, renegotiate security.
*/
-static void rxrpc_input_implicit_end_call(struct rxrpc_connection *conn,
+static void rxrpc_input_implicit_end_call(struct rxrpc_sock *rx,
+ struct rxrpc_connection *conn,
struct rxrpc_call *call)
{
switch (READ_ONCE(call->state)) {
case RXRPC_CALL_SERVER_AWAIT_ACK:
rxrpc_call_completed(call);
- break;
+ /* Fall through */
case RXRPC_CALL_COMPLETE:
break;
default:
@@ -1037,11 +1073,13 @@ static void rxrpc_input_implicit_end_call(struct rxrpc_connection *conn,
set_bit(RXRPC_CALL_EV_ABORT, &call->events);
rxrpc_queue_call(call);
}
+ trace_rxrpc_improper_term(call);
break;
}
- trace_rxrpc_improper_term(call);
+ spin_lock(&rx->incoming_lock);
__rxrpc_disconnect_call(conn, call);
+ spin_unlock(&rx->incoming_lock);
rxrpc_notify_socket(call);
}
@@ -1120,8 +1158,10 @@ int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb)
* The socket is locked by the caller and this prevents the socket from being
* shut down and the local endpoint from going away, thus sk_user_data will not
* be cleared until this function returns.
+ *
+ * Called with the RCU read lock held from the IP layer via UDP.
*/
-void rxrpc_data_ready(struct sock *udp_sk)
+int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb)
{
struct rxrpc_connection *conn;
struct rxrpc_channel *chan;
@@ -1130,38 +1170,17 @@ void rxrpc_data_ready(struct sock *udp_sk)
struct rxrpc_local *local = udp_sk->sk_user_data;
struct rxrpc_peer *peer = NULL;
struct rxrpc_sock *rx = NULL;
- struct sk_buff *skb;
unsigned int channel;
- int ret, skew = 0;
+ int skew = 0;
_enter("%p", udp_sk);
- ASSERT(!irqs_disabled());
-
- skb = skb_recv_udp(udp_sk, 0, 1, &ret);
- if (!skb) {
- if (ret == -EAGAIN)
- return;
- _debug("UDP socket error %d", ret);
- return;
- }
-
if (skb->tstamp == 0)
skb->tstamp = ktime_get_real();
rxrpc_new_skb(skb, rxrpc_skb_rx_received);
- _net("recv skb %p", skb);
-
- /* we'll probably need to checksum it (didn't call sock_recvmsg) */
- if (skb_checksum_complete(skb)) {
- rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
- __UDP_INC_STATS(&init_net, UDP_MIB_INERRORS, 0);
- _leave(" [CSUM failed]");
- return;
- }
-
- __UDP_INC_STATS(&init_net, UDP_MIB_INDATAGRAMS, 0);
+ skb_pull(skb, sizeof(struct udphdr));
/* The UDP protocol already released all skb resources;
* we are free to add our own data there.
@@ -1177,10 +1196,12 @@ void rxrpc_data_ready(struct sock *udp_sk)
if ((lose++ & 7) == 7) {
trace_rxrpc_rx_lose(sp);
rxrpc_free_skb(skb, rxrpc_skb_rx_lost);
- return;
+ return 0;
}
}
+ if (skb->tstamp == 0)
+ skb->tstamp = ktime_get_real();
trace_rxrpc_rx_packet(sp);
switch (sp->hdr.type) {
@@ -1234,8 +1255,6 @@ void rxrpc_data_ready(struct sock *udp_sk)
if (sp->hdr.serviceId == 0)
goto bad_message;
- rcu_read_lock();
-
if (rxrpc_to_server(sp)) {
/* Weed out packets to services we're not offering. Packets
* that would begin a call are explicitly rejected and the rest
@@ -1247,7 +1266,7 @@ void rxrpc_data_ready(struct sock *udp_sk)
if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA &&
sp->hdr.seq == 1)
goto unsupported_service;
- goto discard_unlock;
+ goto discard;
}
}
@@ -1257,17 +1276,23 @@ void rxrpc_data_ready(struct sock *udp_sk)
goto wrong_security;
if (sp->hdr.serviceId != conn->service_id) {
- if (!test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags) ||
- conn->service_id != conn->params.service_id)
+ int old_id;
+
+ if (!test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags))
+ goto reupgrade;
+ old_id = cmpxchg(&conn->service_id, conn->params.service_id,
+ sp->hdr.serviceId);
+
+ if (old_id != conn->params.service_id &&
+ old_id != sp->hdr.serviceId)
goto reupgrade;
- conn->service_id = sp->hdr.serviceId;
}
if (sp->hdr.callNumber == 0) {
/* Connection-level packet */
_debug("CONN %p {%d}", conn, conn->debug_id);
rxrpc_post_packet_to_conn(conn, skb);
- goto out_unlock;
+ goto out;
}
/* Note the serial number skew here */
@@ -1286,19 +1311,19 @@ void rxrpc_data_ready(struct sock *udp_sk)
/* Ignore really old calls */
if (sp->hdr.callNumber < chan->last_call)
- goto discard_unlock;
+ goto discard;
if (sp->hdr.callNumber == chan->last_call) {
if (chan->call ||
sp->hdr.type == RXRPC_PACKET_TYPE_ABORT)
- goto discard_unlock;
+ goto discard;
/* For the previous service call, if completed
* successfully, we discard all further packets.
*/
if (rxrpc_conn_is_service(conn) &&
chan->last_type == RXRPC_PACKET_TYPE_ACK)
- goto discard_unlock;
+ goto discard;
/* But otherwise we need to retransmit the final packet
* from data cached in the connection record.
@@ -1309,18 +1334,16 @@ void rxrpc_data_ready(struct sock *udp_sk)
sp->hdr.serial,
sp->hdr.flags, 0);
rxrpc_post_packet_to_conn(conn, skb);
- goto out_unlock;
+ goto out;
}
call = rcu_dereference(chan->call);
if (sp->hdr.callNumber > chan->call_id) {
- if (rxrpc_to_client(sp)) {
- rcu_read_unlock();
+ if (rxrpc_to_client(sp))
goto reject_packet;
- }
if (call)
- rxrpc_input_implicit_end_call(conn, call);
+ rxrpc_input_implicit_end_call(rx, conn, call);
call = NULL;
}
@@ -1337,55 +1360,42 @@ void rxrpc_data_ready(struct sock *udp_sk)
if (!call || atomic_read(&call->usage) == 0) {
if (rxrpc_to_client(sp) ||
sp->hdr.type != RXRPC_PACKET_TYPE_DATA)
- goto bad_message_unlock;
+ goto bad_message;
if (sp->hdr.seq != 1)
- goto discard_unlock;
- call = rxrpc_new_incoming_call(local, rx, peer, conn, skb);
- if (!call) {
- rcu_read_unlock();
+ goto discard;
+ call = rxrpc_new_incoming_call(local, rx, skb);
+ if (!call)
goto reject_packet;
- }
rxrpc_send_ping(call, skb, skew);
mutex_unlock(&call->user_mutex);
}
rxrpc_input_call_packet(call, skb, skew);
- goto discard_unlock;
+ goto discard;
-discard_unlock:
- rcu_read_unlock();
discard:
rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
out:
trace_rxrpc_rx_done(0, 0);
- return;
-
-out_unlock:
- rcu_read_unlock();
- goto out;
+ return 0;
wrong_security:
- rcu_read_unlock();
trace_rxrpc_abort(0, "SEC", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
RXKADINCONSISTENCY, EBADMSG);
skb->priority = RXKADINCONSISTENCY;
goto post_abort;
unsupported_service:
- rcu_read_unlock();
trace_rxrpc_abort(0, "INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
RX_INVALID_OPERATION, EOPNOTSUPP);
skb->priority = RX_INVALID_OPERATION;
goto post_abort;
reupgrade:
- rcu_read_unlock();
trace_rxrpc_abort(0, "UPG", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
RX_PROTOCOL_ERROR, EBADMSG);
goto protocol_error;
-bad_message_unlock:
- rcu_read_unlock();
bad_message:
trace_rxrpc_abort(0, "BAD", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
RX_PROTOCOL_ERROR, EBADMSG);
@@ -1397,4 +1407,5 @@ reject_packet:
trace_rxrpc_rx_done(skb->mark, skb->priority);
rxrpc_reject_packet(local, skb);
_leave(" [badmsg]");
+ return 0;
}
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 94d234e9c685..cad0691c2bb4 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -19,6 +19,7 @@
#include <linux/ip.h>
#include <linux/hashtable.h>
#include <net/sock.h>
+#include <net/udp.h>
#include <net/af_rxrpc.h>
#include "ar-internal.h"
@@ -108,7 +109,7 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet,
*/
static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
{
- struct sock *sock;
+ struct sock *usk;
int ret, opt;
_enter("%p{%d,%d}",
@@ -122,6 +123,28 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
return ret;
}
+ /* set the socket up */
+ usk = local->socket->sk;
+ inet_sk(usk)->mc_loop = 0;
+
+ /* Enable CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE conversion */
+ inet_inc_convert_csum(usk);
+
+ rcu_assign_sk_user_data(usk, local);
+
+ udp_sk(usk)->encap_type = UDP_ENCAP_RXRPC;
+ udp_sk(usk)->encap_rcv = rxrpc_input_packet;
+ udp_sk(usk)->encap_destroy = NULL;
+ udp_sk(usk)->gro_receive = NULL;
+ udp_sk(usk)->gro_complete = NULL;
+
+ udp_encap_enable();
+#if IS_ENABLED(CONFIG_IPV6)
+ if (local->srx.transport.family == AF_INET6)
+ udpv6_encap_enable();
+#endif
+ usk->sk_error_report = rxrpc_error_report;
+
/* if a local address was supplied then bind it */
if (local->srx.transport_len > sizeof(sa_family_t)) {
_debug("bind");
@@ -191,11 +214,6 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
BUG();
}
- /* set the socket up */
- sock = local->socket->sk;
- sock->sk_user_data = local;
- sock->sk_data_ready = rxrpc_data_ready;
- sock->sk_error_report = rxrpc_error_report;
_leave(" = 0");
return 0;
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index 81a7869325a6..7feb611c7258 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -303,6 +303,8 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
if (rtt < 0)
return;
+ spin_lock(&peer->rtt_input_lock);
+
/* Replace the oldest datum in the RTT buffer */
sum -= peer->rtt_cache[cursor];
sum += rtt;
@@ -314,6 +316,8 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
peer->rtt_usage = usage;
}
+ spin_unlock(&peer->rtt_input_lock);
+
/* Now recalculate the average */
if (usage == RXRPC_RTT_CACHE_SIZE) {
avg = sum / RXRPC_RTT_CACHE_SIZE;
@@ -322,6 +326,7 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
do_div(avg, usage);
}
+ /* Don't need to update this under lock */
peer->rtt = avg;
trace_rxrpc_rtt_rx(call, why, send_serial, resp_serial, rtt,
usage, avg);
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 01a9febfa367..5691b7d266ca 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -153,8 +153,10 @@ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *local,
* assess the MTU size for the network interface through which this peer is
* reached
*/
-static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer)
+static void rxrpc_assess_MTU_size(struct rxrpc_sock *rx,
+ struct rxrpc_peer *peer)
{
+ struct net *net = sock_net(&rx->sk);
struct dst_entry *dst;
struct rtable *rt;
struct flowi fl;
@@ -169,7 +171,7 @@ static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer)
switch (peer->srx.transport.family) {
case AF_INET:
rt = ip_route_output_ports(
- &init_net, fl4, NULL,
+ net, fl4, NULL,
peer->srx.transport.sin.sin_addr.s_addr, 0,
htons(7000), htons(7001), IPPROTO_UDP, 0, 0);
if (IS_ERR(rt)) {
@@ -188,7 +190,7 @@ static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer)
sizeof(struct in6_addr));
fl6->fl6_dport = htons(7001);
fl6->fl6_sport = htons(7000);
- dst = ip6_route_output(&init_net, NULL, fl6);
+ dst = ip6_route_output(net, NULL, fl6);
if (dst->error) {
_leave(" [route err %d]", dst->error);
return;
@@ -223,6 +225,7 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp)
peer->service_conns = RB_ROOT;
seqlock_init(&peer->service_conn_lock);
spin_lock_init(&peer->lock);
+ spin_lock_init(&peer->rtt_input_lock);
peer->debug_id = atomic_inc_return(&rxrpc_debug_id);
if (RXRPC_TX_SMSS > 2190)
@@ -240,10 +243,11 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp)
/*
* Initialise peer record.
*/
-static void rxrpc_init_peer(struct rxrpc_peer *peer, unsigned long hash_key)
+static void rxrpc_init_peer(struct rxrpc_sock *rx, struct rxrpc_peer *peer,
+ unsigned long hash_key)
{
peer->hash_key = hash_key;
- rxrpc_assess_MTU_size(peer);
+ rxrpc_assess_MTU_size(rx, peer);
peer->mtu = peer->if_mtu;
peer->rtt_last_req = ktime_get_real();
@@ -275,7 +279,8 @@ static void rxrpc_init_peer(struct rxrpc_peer *peer, unsigned long hash_key)
/*
* Set up a new peer.
*/
-static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local,
+static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_sock *rx,
+ struct rxrpc_local *local,
struct sockaddr_rxrpc *srx,
unsigned long hash_key,
gfp_t gfp)
@@ -287,7 +292,7 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local,
peer = rxrpc_alloc_peer(local, gfp);
if (peer) {
memcpy(&peer->srx, srx, sizeof(*srx));
- rxrpc_init_peer(peer, hash_key);
+ rxrpc_init_peer(rx, peer, hash_key);
}
_leave(" = %p", peer);
@@ -299,14 +304,15 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local,
* since we've already done a search in the list from the non-reentrant context
* (the data_ready handler) that is the only place we can add new peers.
*/
-void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer)
+void rxrpc_new_incoming_peer(struct rxrpc_sock *rx, struct rxrpc_local *local,
+ struct rxrpc_peer *peer)
{
struct rxrpc_net *rxnet = local->rxnet;
unsigned long hash_key;
hash_key = rxrpc_peer_hash_key(local, &peer->srx);
peer->local = local;
- rxrpc_init_peer(peer, hash_key);
+ rxrpc_init_peer(rx, peer, hash_key);
spin_lock(&rxnet->peer_hash_lock);
hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key);
@@ -317,7 +323,8 @@ void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer)
/*
* obtain a remote transport endpoint for the specified address
*/
-struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local,
+struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx,
+ struct rxrpc_local *local,
struct sockaddr_rxrpc *srx, gfp_t gfp)
{
struct rxrpc_peer *peer, *candidate;
@@ -337,7 +344,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local,
/* The peer is not yet present in hash - create a candidate
* for a new record and then redo the search.
*/
- candidate = rxrpc_create_peer(local, srx, hash_key, gfp);
+ candidate = rxrpc_create_peer(rx, local, srx, hash_key, gfp);
if (!candidate) {
_leave(" = NULL [nomem]");
return NULL;
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index ac79a40a0392..4b28fd44576d 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -391,6 +391,7 @@ static int u32_init(struct tcf_proto *tp)
RCU_INIT_POINTER(root_ht->next, tp_c->hlist);
rcu_assign_pointer(tp_c->hlist, root_ht);
+ root_ht->refcnt++;
rcu_assign_pointer(tp->root, root_ht);
tp->data = tp_c;
return 0;
@@ -606,7 +607,7 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht,
struct tc_u_hnode __rcu **hn;
struct tc_u_hnode *phn;
- WARN_ON(ht->refcnt);
+ WARN_ON(--ht->refcnt);
u32_clear_hnode(tp, ht, extack);
@@ -634,7 +635,7 @@ static void u32_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
WARN_ON(root_ht == NULL);
- if (root_ht && --root_ht->refcnt == 0)
+ if (root_ht && --root_ht->refcnt == 1)
u32_destroy_hnode(tp, root_ht, extack);
if (--tp_c->refcnt == 0) {
@@ -679,7 +680,6 @@ static int u32_delete(struct tcf_proto *tp, void *arg, bool *last,
}
if (ht->refcnt == 1) {
- ht->refcnt--;
u32_destroy_hnode(tp, ht, extack);
} else {
NL_SET_ERR_MSG_MOD(extack, "Can not delete in-use filter");
diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index dc539295ae65..b910cd5c56f7 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -2644,7 +2644,7 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt,
for (i = 1; i <= CAKE_QUEUES; i++)
quantum_div[i] = 65535 / i;
- q->tins = kvzalloc(CAKE_MAX_TINS * sizeof(struct cake_tin_data),
+ q->tins = kvcalloc(CAKE_MAX_TINS, sizeof(struct cake_tin_data),
GFP_KERNEL);
if (!q->tins)
goto nomem;
diff --git a/net/tipc/link.c b/net/tipc/link.c
index fb886b525d95..f6552e4f4b43 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -477,6 +477,8 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id,
l->in_session = false;
l->bearer_id = bearer_id;
l->tolerance = tolerance;
+ if (bc_rcvlink)
+ bc_rcvlink->tolerance = tolerance;
l->net_plane = net_plane;
l->advertised_mtu = mtu;
l->mtu = mtu;
@@ -843,14 +845,21 @@ static void link_prepare_wakeup(struct tipc_link *l)
void tipc_link_reset(struct tipc_link *l)
{
+ struct sk_buff_head list;
+
+ __skb_queue_head_init(&list);
+
l->in_session = false;
l->session++;
l->mtu = l->advertised_mtu;
+
spin_lock_bh(&l->wakeupq.lock);
+ skb_queue_splice_init(&l->wakeupq, &list);
+ spin_unlock_bh(&l->wakeupq.lock);
+
spin_lock_bh(&l->inputq->lock);
- skb_queue_splice_init(&l->wakeupq, l->inputq);
+ skb_queue_splice_init(&list, l->inputq);
spin_unlock_bh(&l->inputq->lock);
- spin_unlock_bh(&l->wakeupq.lock);
__skb_queue_purge(&l->transmq);
__skb_queue_purge(&l->deferdq);
@@ -1031,7 +1040,7 @@ static int tipc_link_retrans(struct tipc_link *l, struct tipc_link *r,
/* Detect repeated retransmit failures on same packet */
if (r->last_retransm != buf_seqno(skb)) {
r->last_retransm = buf_seqno(skb);
- r->stale_limit = jiffies + msecs_to_jiffies(l->tolerance);
+ r->stale_limit = jiffies + msecs_to_jiffies(r->tolerance);
} else if (++r->stale_cnt > 99 && time_after(jiffies, r->stale_limit)) {
link_retransmit_failure(l, skb);
if (link_is_bc_sndlink(l))
@@ -1576,9 +1585,10 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
strncpy(if_name, data, TIPC_MAX_IF_NAME);
/* Update own tolerance if peer indicates a non-zero value */
- if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL))
+ if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) {
l->tolerance = peers_tol;
-
+ l->bc_rcvlink->tolerance = peers_tol;
+ }
/* Update own priority if peer's priority is higher */
if (in_range(peers_prio, l->priority + 1, TIPC_MAX_LINK_PRI))
l->priority = peers_prio;
@@ -1604,9 +1614,10 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
l->rcv_nxt_state = msg_seqno(hdr) + 1;
/* Update own tolerance if peer indicates a non-zero value */
- if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL))
+ if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) {
l->tolerance = peers_tol;
-
+ l->bc_rcvlink->tolerance = peers_tol;
+ }
/* Update own prio if peer indicates a different value */
if ((peers_prio != l->priority) &&
in_range(peers_prio, 1, TIPC_MAX_LINK_PRI)) {
@@ -2223,6 +2234,8 @@ void tipc_link_set_tolerance(struct tipc_link *l, u32 tol,
struct sk_buff_head *xmitq)
{
l->tolerance = tol;
+ if (l->bc_rcvlink)
+ l->bc_rcvlink->tolerance = tol;
if (link_is_up(l))
tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, tol, 0, xmitq);
}
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index db148c4a916a..de09f514428c 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1198,6 +1198,7 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
* @skb: pointer to message buffer.
*/
static void tipc_sk_conn_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb,
+ struct sk_buff_head *inputq,
struct sk_buff_head *xmitq)
{
struct tipc_msg *hdr = buf_msg(skb);
@@ -1215,7 +1216,16 @@ static void tipc_sk_conn_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb,
tipc_node_remove_conn(sock_net(sk), tsk_peer_node(tsk),
tsk_peer_port(tsk));
sk->sk_state_change(sk);
- goto exit;
+
+ /* State change is ignored if socket already awake,
+ * - convert msg to abort msg and add to inqueue
+ */
+ msg_set_user(hdr, TIPC_CRITICAL_IMPORTANCE);
+ msg_set_type(hdr, TIPC_CONN_MSG);
+ msg_set_size(hdr, BASIC_H_SIZE);
+ msg_set_hdr_sz(hdr, BASIC_H_SIZE);
+ __skb_queue_tail(inputq, skb);
+ return;
}
tsk->probe_unacked = false;
@@ -1943,7 +1953,7 @@ static void tipc_sk_proto_rcv(struct sock *sk,
switch (msg_user(hdr)) {
case CONN_MANAGER:
- tipc_sk_conn_proto_rcv(tsk, skb, xmitq);
+ tipc_sk_conn_proto_rcv(tsk, skb, inputq, xmitq);
return;
case SOCK_WAKEUP:
tipc_dest_del(&tsk->cong_links, msg_orignode(hdr), 0);