summaryrefslogtreecommitdiff
path: root/net/tipc/socket.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2018-01-31 14:31:10 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2018-01-31 14:31:10 -0800
commitb2fe5fa68642860e7de76167c3111623aa0d5de1 (patch)
treeb7f9b89b7039ecefbc35fe3c8e73a6ff972641dd /net/tipc/socket.c
parenta103950e0dd2058df5e8a8d4a915707bdcf205f0 (diff)
parenta54667f6728c2714a400f3c884727da74b6d1717 (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: 1) Significantly shrink the core networking routing structures. Result of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf 2) Add netdevsim driver for testing various offloads, from Jakub Kicinski. 3) Support cross-chip FDB operations in DSA, from Vivien Didelot. 4) Add a 2nd listener hash table for TCP, similar to what was done for UDP. From Martin KaFai Lau. 5) Add eBPF based queue selection to tun, from Jason Wang. 6) Lockless qdisc support, from John Fastabend. 7) SCTP stream interleave support, from Xin Long. 8) Smoother TCP receive autotuning, from Eric Dumazet. 9) Lots of erspan tunneling enhancements, from William Tu. 10) Add true function call support to BPF, from Alexei Starovoitov. 11) Add explicit support for GRO HW offloading, from Michael Chan. 12) Support extack generation in more netlink subsystems. From Alexander Aring, Quentin Monnet, and Jakub Kicinski. 13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From Russell King. 14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso. 15) Many improvements and simplifications to the NFP driver bpf JIT, from Jakub Kicinski. 16) Support for ipv6 non-equal cost multipath routing, from Ido Schimmel. 17) Add resource abstration to devlink, from Arkadi Sharshevsky. 18) Packet scheduler classifier shared filter block support, from Jiri Pirko. 19) Avoid locking in act_csum, from Davide Caratti. 20) devinet_ioctl() simplifications from Al viro. 21) More TCP bpf improvements from Lawrence Brakmo. 22) Add support for onlink ipv6 route flag, similar to ipv4, from David Ahern. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits) tls: Add support for encryption using async offload accelerator ip6mr: fix stale iterator net/sched: kconfig: Remove blank help texts openvswitch: meter: Use 64-bit arithmetic instead of 32-bit tcp_nv: fix potential integer overflow in tcpnv_acked r8169: fix RTL8168EP take too long to complete driver initialization. qmi_wwan: Add support for Quectel EP06 rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK ipmr: Fix ptrdiff_t print formatting ibmvnic: Wait for device response when changing MAC qlcnic: fix deadlock bug tcp: release sk_frag.page in tcp_disconnect ipv4: Get the address of interface correctly. net_sched: gen_estimator: fix lockdep splat net: macb: Handle HRESP error net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring ipv6: addrconf: break critical section in addrconf_verify_rtnl() ipv6: change route cache aging logic i40e/i40evf: Update DESC_NEEDED value to reflect larger value bnxt_en: cleanup DIM work on device shutdown ...
Diffstat (limited to 'net/tipc/socket.c')
-rw-r--r--net/tipc/socket.c114
1 files changed, 64 insertions, 50 deletions
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 2aa46e8cd8fe..163f3a547501 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -116,6 +116,7 @@ struct tipc_sock {
struct tipc_mc_method mc_method;
struct rcu_head rcu;
struct tipc_group *group;
+ bool group_is_open;
};
static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb);
@@ -715,7 +716,6 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock,
{
struct sock *sk = sock->sk;
struct tipc_sock *tsk = tipc_sk(sk);
- struct tipc_group *grp = tsk->group;
__poll_t revents = 0;
sock_poll_wait(file, sk_sleep(sk), wait);
@@ -736,9 +736,8 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock,
revents |= POLLIN | POLLRDNORM;
break;
case TIPC_OPEN:
- if (!grp || tipc_group_size(grp))
- if (!tsk->cong_link_cnt)
- revents |= POLLOUT;
+ if (tsk->group_is_open && !tsk->cong_link_cnt)
+ revents |= POLLOUT;
if (!tipc_sk_type_connectionless(sk))
break;
if (skb_queue_empty(&sk->sk_receive_queue))
@@ -772,7 +771,6 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq,
struct net *net = sock_net(sk);
int mtu = tipc_bcast_get_mtu(net);
struct tipc_mc_method *method = &tsk->mc_method;
- u32 domain = addr_domain(net, TIPC_CLUSTER_SCOPE);
struct sk_buff_head pkts;
struct tipc_nlist dsts;
int rc;
@@ -788,7 +786,7 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq,
/* Lookup destination nodes */
tipc_nlist_init(&dsts, tipc_own_addr(net));
tipc_nametbl_lookup_dst_nodes(net, seq->type, seq->lower,
- seq->upper, domain, &dsts);
+ seq->upper, &dsts);
if (!dsts.local && !dsts.remote)
return -EHOSTUNREACH;
@@ -928,21 +926,22 @@ static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m,
struct list_head *cong_links = &tsk->cong_links;
int blks = tsk_blocks(GROUP_H_SIZE + dlen);
struct tipc_group *grp = tsk->group;
+ struct tipc_msg *hdr = &tsk->phdr;
struct tipc_member *first = NULL;
struct tipc_member *mbr = NULL;
struct net *net = sock_net(sk);
u32 node, port, exclude;
- u32 type, inst, domain;
struct list_head dsts;
+ u32 type, inst, scope;
int lookups = 0;
int dstcnt, rc;
bool cong;
INIT_LIST_HEAD(&dsts);
- type = dest->addr.name.name.type;
+ type = msg_nametype(hdr);
inst = dest->addr.name.name.instance;
- domain = addr_domain(net, dest->scope);
+ scope = msg_lookup_scope(hdr);
exclude = tipc_group_exclude(grp);
while (++lookups < 4) {
@@ -950,7 +949,7 @@ static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m,
/* Look for a non-congested destination member, if any */
while (1) {
- if (!tipc_nametbl_lookup(net, type, inst, domain, &dsts,
+ if (!tipc_nametbl_lookup(net, type, inst, scope, &dsts,
&dstcnt, exclude, false))
return -EHOSTUNREACH;
tipc_dest_pop(&dsts, &node, &port);
@@ -1079,22 +1078,23 @@ static int tipc_send_group_mcast(struct socket *sock, struct msghdr *m,
{
struct sock *sk = sock->sk;
DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
- struct tipc_name_seq *seq = &dest->addr.nameseq;
struct tipc_sock *tsk = tipc_sk(sk);
struct tipc_group *grp = tsk->group;
+ struct tipc_msg *hdr = &tsk->phdr;
struct net *net = sock_net(sk);
- u32 domain, exclude, dstcnt;
+ u32 type, inst, scope, exclude;
struct list_head dsts;
+ u32 dstcnt;
INIT_LIST_HEAD(&dsts);
- if (seq->lower != seq->upper)
- return -ENOTSUPP;
-
- domain = addr_domain(net, dest->scope);
+ type = msg_nametype(hdr);
+ inst = dest->addr.name.name.instance;
+ scope = msg_lookup_scope(hdr);
exclude = tipc_group_exclude(grp);
- if (!tipc_nametbl_lookup(net, seq->type, seq->lower, domain,
- &dsts, &dstcnt, exclude, true))
+
+ if (!tipc_nametbl_lookup(net, type, inst, scope, &dsts,
+ &dstcnt, exclude, true))
return -EHOSTUNREACH;
if (dstcnt == 1) {
@@ -1116,24 +1116,29 @@ static int tipc_send_group_mcast(struct socket *sock, struct msghdr *m,
void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
struct sk_buff_head *inputq)
{
- u32 scope = TIPC_CLUSTER_SCOPE;
u32 self = tipc_own_addr(net);
+ u32 type, lower, upper, scope;
struct sk_buff *skb, *_skb;
- u32 lower = 0, upper = ~0;
- struct sk_buff_head tmpq;
u32 portid, oport, onode;
+ struct sk_buff_head tmpq;
struct list_head dports;
- struct tipc_msg *msg;
- int user, mtyp, hsz;
+ struct tipc_msg *hdr;
+ int user, mtyp, hlen;
+ bool exact;
__skb_queue_head_init(&tmpq);
INIT_LIST_HEAD(&dports);
skb = tipc_skb_peek(arrvq, &inputq->lock);
for (; skb; skb = tipc_skb_peek(arrvq, &inputq->lock)) {
- msg = buf_msg(skb);
- user = msg_user(msg);
- mtyp = msg_type(msg);
+ hdr = buf_msg(skb);
+ user = msg_user(hdr);
+ mtyp = msg_type(hdr);
+ hlen = skb_headroom(skb) + msg_hdr_sz(hdr);
+ oport = msg_origport(hdr);
+ onode = msg_orignode(hdr);
+ type = msg_nametype(hdr);
+
if (mtyp == TIPC_GRP_UCAST_MSG || user == GROUP_PROTOCOL) {
spin_lock_bh(&inputq->lock);
if (skb_peek(arrvq) == skb) {
@@ -1144,21 +1149,31 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
spin_unlock_bh(&inputq->lock);
continue;
}
- hsz = skb_headroom(skb) + msg_hdr_sz(msg);
- oport = msg_origport(msg);
- onode = msg_orignode(msg);
- if (onode == self)
- scope = TIPC_NODE_SCOPE;
-
- /* Create destination port list and message clones: */
- if (!msg_in_group(msg)) {
- lower = msg_namelower(msg);
- upper = msg_nameupper(msg);
+
+ /* Group messages require exact scope match */
+ if (msg_in_group(hdr)) {
+ lower = 0;
+ upper = ~0;
+ scope = msg_lookup_scope(hdr);
+ exact = true;
+ } else {
+ /* TIPC_NODE_SCOPE means "any scope" in this context */
+ if (onode == self)
+ scope = TIPC_NODE_SCOPE;
+ else
+ scope = TIPC_CLUSTER_SCOPE;
+ exact = false;
+ lower = msg_namelower(hdr);
+ upper = msg_nameupper(hdr);
}
- tipc_nametbl_mc_translate(net, msg_nametype(msg), lower, upper,
- scope, &dports);
+
+ /* Create destination port list: */
+ tipc_nametbl_mc_lookup(net, type, lower, upper,
+ scope, exact, &dports);
+
+ /* Clone message per destination */
while (tipc_dest_pop(&dports, NULL, &portid)) {
- _skb = __pskb_copy(skb, hsz, GFP_ATOMIC);
+ _skb = __pskb_copy(skb, hlen, GFP_ATOMIC);
if (_skb) {
msg_set_destport(buf_msg(_skb), portid);
__skb_queue_tail(&tmpq, _skb);
@@ -1933,8 +1948,7 @@ static void tipc_sk_proto_rcv(struct sock *sk,
break;
case TOP_SRV:
tipc_group_member_evt(tsk->group, &wakeup, &sk->sk_rcvbuf,
- skb, inputq, xmitq);
- skb = NULL;
+ hdr, inputq, xmitq);
break;
default:
break;
@@ -2640,9 +2654,7 @@ void tipc_sk_reinit(struct net *net)
rhashtable_walk_enter(&tn->sk_rht, &iter);
do {
- tsk = ERR_PTR(rhashtable_walk_start(&iter));
- if (IS_ERR(tsk))
- goto walk_stop;
+ rhashtable_walk_start(&iter);
while ((tsk = rhashtable_walk_next(&iter)) && !IS_ERR(tsk)) {
spin_lock_bh(&tsk->sk.sk_lock.slock);
@@ -2651,7 +2663,7 @@ void tipc_sk_reinit(struct net *net)
msg_set_orignode(msg, tn->own_addr);
spin_unlock_bh(&tsk->sk.sk_lock.slock);
}
-walk_stop:
+
rhashtable_walk_stop(&iter);
} while (tsk == ERR_PTR(-EAGAIN));
}
@@ -2734,7 +2746,6 @@ void tipc_sk_rht_destroy(struct net *net)
static int tipc_sk_join(struct tipc_sock *tsk, struct tipc_group_req *mreq)
{
struct net *net = sock_net(&tsk->sk);
- u32 domain = addr_domain(net, mreq->scope);
struct tipc_group *grp = tsk->group;
struct tipc_msg *hdr = &tsk->phdr;
struct tipc_name_seq seq;
@@ -2742,9 +2753,11 @@ static int tipc_sk_join(struct tipc_sock *tsk, struct tipc_group_req *mreq)
if (mreq->type < TIPC_RESERVED_TYPES)
return -EACCES;
+ if (mreq->scope > TIPC_NODE_SCOPE)
+ return -EINVAL;
if (grp)
return -EACCES;
- grp = tipc_group_create(net, tsk->portid, mreq);
+ grp = tipc_group_create(net, tsk->portid, mreq, &tsk->group_is_open);
if (!grp)
return -ENOMEM;
tsk->group = grp;
@@ -2754,16 +2767,17 @@ static int tipc_sk_join(struct tipc_sock *tsk, struct tipc_group_req *mreq)
seq.type = mreq->type;
seq.lower = mreq->instance;
seq.upper = seq.lower;
- tipc_nametbl_build_group(net, grp, mreq->type, domain);
+ tipc_nametbl_build_group(net, grp, mreq->type, mreq->scope);
rc = tipc_sk_publish(tsk, mreq->scope, &seq);
if (rc) {
tipc_group_delete(net, grp);
tsk->group = NULL;
+ return rc;
}
-
- /* Eliminate any risk that a broadcast overtakes the sent JOIN */
+ /* Eliminate any risk that a broadcast overtakes sent JOINs */
tsk->mc_method.rcast = true;
tsk->mc_method.mandatory = true;
+ tipc_group_join(net, grp, &tsk->sk.sk_rcvbuf);
return rc;
}