aboutsummaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/8021q/vlan.c2
-rw-r--r--net/8021q/vlan_dev.c5
-rw-r--r--net/9p/client.c114
-rw-r--r--net/9p/trans_fd.c14
-rw-r--r--net/9p/trans_rdma.c1
-rw-r--r--net/9p/trans_virtio.c1
-rw-r--r--net/Kconfig6
-rw-r--r--net/atm/br2684.c1
-rw-r--r--net/bluetooth/hci_conn.c18
-rw-r--r--net/bluetooth/hci_event.c36
-rw-r--r--net/bluetooth/hci_sysfs.c81
-rw-r--r--net/bridge/br_input.c5
-rw-r--r--net/bridge/br_netfilter.c10
-rw-r--r--net/bridge/br_stp.c3
-rw-r--r--net/core/datagram.c14
-rw-r--r--net/core/dev.c9
-rw-r--r--net/core/gen_estimator.c13
-rw-r--r--net/core/netpoll.c8
-rw-r--r--net/core/pktgen.c2
-rw-r--r--net/core/skbuff.c31
-rw-r--r--net/ipv4/Kconfig4
-rw-r--r--net/ipv4/fib_trie.c6
-rw-r--r--net/ipv4/ipconfig.c12
-rw-r--r--net/ipv4/netfilter/arp_tables.c125
-rw-r--r--net/ipv4/netfilter/ip_tables.c126
-rw-r--r--net/ipv4/route.c62
-rw-r--r--net/ipv4/tcp.c5
-rw-r--r--net/ipv4/tcp_input.c10
-rw-r--r--net/ipv4/tcp_vegas.c11
-rw-r--r--net/ipv6/netfilter/ip6_tables.c123
-rw-r--r--net/ipv6/netfilter/ip6t_ipv6header.c6
-rw-r--r--net/ipv6/route.c3
-rw-r--r--net/mac80211/main.c20
-rw-r--r--net/mac80211/rc80211_minstrel.c4
-rw-r--r--net/mac80211/rc80211_pid_algo.c73
-rw-r--r--net/mac80211/tx.c2
-rw-r--r--net/netfilter/Kconfig5
-rw-r--r--net/netfilter/ipvs/ip_vs_conn.c9
-rw-r--r--net/netfilter/ipvs/ip_vs_core.c4
-rw-r--r--net/netfilter/nf_conntrack_netlink.c48
-rw-r--r--net/netfilter/nf_conntrack_proto_dccp.c20
-rw-r--r--net/netfilter/nf_conntrack_proto_tcp.c18
-rw-r--r--net/netfilter/nf_conntrack_proto_udplite.c1
-rw-r--r--net/netfilter/nfnetlink_log.c6
-rw-r--r--net/netfilter/x_tables.c53
-rw-r--r--net/netfilter/xt_cluster.c8
-rw-r--r--net/netfilter/xt_hashlimit.c2
-rw-r--r--net/netfilter/xt_recent.c9
-rw-r--r--net/rxrpc/ar-connection.c12
-rw-r--r--net/sched/cls_api.c25
-rw-r--r--net/sched/cls_cgroup.c25
-rw-r--r--net/sched/sch_fifo.c2
-rw-r--r--net/sched/sch_teql.c5
-rw-r--r--net/sunrpc/svcsock.c35
-rw-r--r--net/sunrpc/xprt.c6
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_recvfrom.c2
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_sendto.c15
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_transport.c13
-rw-r--r--net/sunrpc/xprtrdma/verbs.c3
-rw-r--r--net/sunrpc/xprtsock.c26
-rw-r--r--net/wimax/op-msg.c11
-rw-r--r--net/wimax/stack.c17
-rw-r--r--net/wireless/reg.c24
-rw-r--r--net/wireless/scan.c1
-rw-r--r--net/wireless/wext.c7
-rw-r--r--net/xfrm/xfrm_state.c6
66 files changed, 724 insertions, 660 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 2b7390e377b..d1e10546eb8 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -492,6 +492,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
continue;
dev_change_flags(vlandev, flgs & ~IFF_UP);
+ vlan_transfer_operstate(dev, vlandev);
}
break;
@@ -507,6 +508,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
continue;
dev_change_flags(vlandev, flgs | IFF_UP);
+ vlan_transfer_operstate(dev, vlandev);
}
break;
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 6b092136401..b4b9068e55a 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -462,6 +462,7 @@ static int vlan_dev_open(struct net_device *dev)
if (vlan->flags & VLAN_FLAG_GVRP)
vlan_gvrp_request_join(dev);
+ netif_carrier_on(dev);
return 0;
clear_allmulti:
@@ -471,6 +472,7 @@ del_unicast:
if (compare_ether_addr(dev->dev_addr, real_dev->dev_addr))
dev_unicast_delete(real_dev, dev->dev_addr, ETH_ALEN);
out:
+ netif_carrier_off(dev);
return err;
}
@@ -492,6 +494,7 @@ static int vlan_dev_stop(struct net_device *dev)
if (compare_ether_addr(dev->dev_addr, real_dev->dev_addr))
dev_unicast_delete(real_dev, dev->dev_addr, dev->addr_len);
+ netif_carrier_off(dev);
return 0;
}
@@ -612,6 +615,8 @@ static int vlan_dev_init(struct net_device *dev)
struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
int subclass = 0;
+ netif_carrier_off(dev);
+
/* IFF_BROADCAST|IFF_MULTICAST; ??? */
dev->flags = real_dev->flags & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI);
dev->iflink = real_dev->ifindex;
diff --git a/net/9p/client.c b/net/9p/client.c
index 1eb580c38fb..dd43a8289b0 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -203,7 +203,6 @@ static struct p9_req_t *p9_tag_alloc(struct p9_client *c, u16 tag)
p9pdu_reset(req->tc);
p9pdu_reset(req->rc);
- req->flush_tag = 0;
req->tc->tag = tag-1;
req->status = REQ_STATUS_ALLOC;
@@ -324,35 +323,9 @@ static void p9_free_req(struct p9_client *c, struct p9_req_t *r)
*/
void p9_client_cb(struct p9_client *c, struct p9_req_t *req)
{
- struct p9_req_t *other_req;
- unsigned long flags;
-
P9_DPRINTK(P9_DEBUG_MUX, " tag %d\n", req->tc->tag);
-
- if (req->status == REQ_STATUS_ERROR)
- wake_up(req->wq);
-
- if (req->flush_tag) { /* flush receive path */
- P9_DPRINTK(P9_DEBUG_9P, "<<< RFLUSH %d\n", req->tc->tag);
- spin_lock_irqsave(&c->lock, flags);
- other_req = p9_tag_lookup(c, req->flush_tag);
- if (other_req->status != REQ_STATUS_FLSH) /* stale flush */
- spin_unlock_irqrestore(&c->lock, flags);
- else {
- other_req->status = REQ_STATUS_FLSHD;
- spin_unlock_irqrestore(&c->lock, flags);
- wake_up(other_req->wq);
- }
- p9_free_req(c, req);
- } else { /* normal receive path */
- P9_DPRINTK(P9_DEBUG_MUX, "normal: tag %d\n", req->tc->tag);
- spin_lock_irqsave(&c->lock, flags);
- if (req->status != REQ_STATUS_FLSHD)
- req->status = REQ_STATUS_RCVD;
- spin_unlock_irqrestore(&c->lock, flags);
- wake_up(req->wq);
- P9_DPRINTK(P9_DEBUG_MUX, "wakeup: %d\n", req->tc->tag);
- }
+ wake_up(req->wq);
+ P9_DPRINTK(P9_DEBUG_MUX, "wakeup: %d\n", req->tc->tag);
}
EXPORT_SYMBOL(p9_client_cb);
@@ -486,9 +459,15 @@ static int p9_client_flush(struct p9_client *c, struct p9_req_t *oldreq)
if (IS_ERR(req))
return PTR_ERR(req);
- req->flush_tag = oldtag;
- /* we don't free anything here because RPC isn't complete */
+ /* if we haven't received a response for oldreq,
+ remove it from the list. */
+ spin_lock(&c->lock);
+ if (oldreq->status == REQ_STATUS_FLSH)
+ list_del(&oldreq->req_list);
+ spin_unlock(&c->lock);
+
+ p9_free_req(c, req);
return 0;
}
@@ -509,7 +488,6 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...)
struct p9_req_t *req;
unsigned long flags;
int sigpending;
- int flushed = 0;
P9_DPRINTK(P9_DEBUG_MUX, "client %p op %d\n", c, type);
@@ -546,42 +524,28 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...)
goto reterr;
}
- /* if it was a flush we just transmitted, return our tag */
- if (type == P9_TFLUSH)
- return req;
-again:
P9_DPRINTK(P9_DEBUG_MUX, "wait %p tag: %d\n", req->wq, tag);
err = wait_event_interruptible(*req->wq,
req->status >= REQ_STATUS_RCVD);
- P9_DPRINTK(P9_DEBUG_MUX, "wait %p tag: %d returned %d (flushed=%d)\n",
- req->wq, tag, err, flushed);
+ P9_DPRINTK(P9_DEBUG_MUX, "wait %p tag: %d returned %d\n",
+ req->wq, tag, err);
if (req->status == REQ_STATUS_ERROR) {
P9_DPRINTK(P9_DEBUG_ERROR, "req_status error %d\n", req->t_err);
err = req->t_err;
- } else if (err == -ERESTARTSYS && flushed) {
- P9_DPRINTK(P9_DEBUG_MUX, "flushed - going again\n");
- goto again;
- } else if (req->status == REQ_STATUS_FLSHD) {
- P9_DPRINTK(P9_DEBUG_MUX, "flushed - erestartsys\n");
- err = -ERESTARTSYS;
}
- if ((err == -ERESTARTSYS) && (c->status == Connected) && (!flushed)) {
+ if ((err == -ERESTARTSYS) && (c->status == Connected)) {
P9_DPRINTK(P9_DEBUG_MUX, "flushing\n");
- spin_lock_irqsave(&c->lock, flags);
- if (req->status == REQ_STATUS_SENT)
- req->status = REQ_STATUS_FLSH;
- spin_unlock_irqrestore(&c->lock, flags);
sigpending = 1;
- flushed = 1;
clear_thread_flag(TIF_SIGPENDING);
- if (c->trans_mod->cancel(c, req)) {
- err = p9_client_flush(c, req);
- if (err == 0)
- goto again;
- }
+ if (c->trans_mod->cancel(c, req))
+ p9_client_flush(c, req);
+
+ /* if we received the response anyway, don't signal error */
+ if (req->status == REQ_STATUS_RCVD)
+ err = 0;
}
if (sigpending) {
@@ -1244,19 +1208,53 @@ struct p9_wstat *p9_client_stat(struct p9_fid *fid)
ret->name, ret->uid, ret->gid, ret->muid, ret->extension,
ret->n_uid, ret->n_gid, ret->n_muid);
+ p9_free_req(clnt, req);
+ return ret;
+
free_and_error:
p9_free_req(clnt, req);
error:
- return ret;
+ kfree(ret);
+ return ERR_PTR(err);
}
EXPORT_SYMBOL(p9_client_stat);
+static int p9_client_statsize(struct p9_wstat *wst, int optional)
+{
+ int ret;
+
+ /* size[2] type[2] dev[4] qid[13] */
+ /* mode[4] atime[4] mtime[4] length[8]*/
+ /* name[s] uid[s] gid[s] muid[s] */
+ ret = 2+2+4+13+4+4+4+8+2+2+2+2;
+
+ if (wst->name)
+ ret += strlen(wst->name);
+ if (wst->uid)
+ ret += strlen(wst->uid);
+ if (wst->gid)
+ ret += strlen(wst->gid);
+ if (wst->muid)
+ ret += strlen(wst->muid);
+
+ if (optional) {
+ ret += 2+4+4+4; /* extension[s] n_uid[4] n_gid[4] n_muid[4] */
+ if (wst->extension)
+ ret += strlen(wst->extension);
+ }
+
+ return ret;
+}
+
int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst)
{
int err;
struct p9_req_t *req;
struct p9_client *clnt;
+ err = 0;
+ clnt = fid->clnt;
+ wst->size = p9_client_statsize(wst, clnt->dotu);
P9_DPRINTK(P9_DEBUG_9P, ">>> TWSTAT fid %d\n", fid->fid);
P9_DPRINTK(P9_DEBUG_9P,
" sz=%x type=%x dev=%x qid=%x.%llx.%x\n"
@@ -1268,10 +1266,8 @@ int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst)
wst->atime, wst->mtime, (unsigned long long)wst->length,
wst->name, wst->uid, wst->gid, wst->muid, wst->extension,
wst->n_uid, wst->n_gid, wst->n_muid);
- err = 0;
- clnt = fid->clnt;
- req = p9_client_rpc(clnt, P9_TWSTAT, "dwS", fid->fid, 0, wst);
+ req = p9_client_rpc(clnt, P9_TWSTAT, "dwS", fid->fid, wst->size, wst);
if (IS_ERR(req)) {
err = PTR_ERR(req);
goto error;
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index c613ed08a5e..a2a1814c7a8 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -213,8 +213,8 @@ static void p9_conn_cancel(struct p9_conn *m, int err)
spin_unlock_irqrestore(&m->client->lock, flags);
list_for_each_entry_safe(req, rtmp, &cancel_list, req_list) {
- list_del(&req->req_list);
P9_DPRINTK(P9_DEBUG_ERROR, "call back req %p\n", req);
+ list_del(&req->req_list);
p9_client_cb(m->client, req);
}
}
@@ -336,7 +336,8 @@ static void p9_read_work(struct work_struct *work)
"mux %p pkt: size: %d bytes tag: %d\n", m, n, tag);
m->req = p9_tag_lookup(m->client, tag);
- if (!m->req) {
+ if (!m->req || (m->req->status != REQ_STATUS_SENT &&
+ m->req->status != REQ_STATUS_FLSH)) {
P9_DPRINTK(P9_DEBUG_ERROR, "Unexpected packet tag %d\n",
tag);
err = -EIO;
@@ -361,10 +362,11 @@ static void p9_read_work(struct work_struct *work)
if ((m->req) && (m->rpos == m->rsize)) { /* packet is read in */
P9_DPRINTK(P9_DEBUG_TRANS, "got new packet\n");
spin_lock(&m->client->lock);
+ if (m->req->status != REQ_STATUS_ERROR)
+ m->req->status = REQ_STATUS_RCVD;
list_del(&m->req->req_list);
spin_unlock(&m->client->lock);
p9_client_cb(m->client, m->req);
-
m->rbuf = NULL;
m->rpos = 0;
m->rsize = 0;
@@ -454,6 +456,7 @@ static void p9_write_work(struct work_struct *work)
req = list_entry(m->unsent_req_list.next, struct p9_req_t,
req_list);
req->status = REQ_STATUS_SENT;
+ P9_DPRINTK(P9_DEBUG_TRANS, "move req %p\n", req);
list_move_tail(&req->req_list, &m->req_list);
m->wbuf = req->tc->sdata;
@@ -683,12 +686,13 @@ static int p9_fd_cancel(struct p9_client *client, struct p9_req_t *req)
P9_DPRINTK(P9_DEBUG_TRANS, "client %p req %p\n", client, req);
spin_lock(&client->lock);
- list_del(&req->req_list);
if (req->status == REQ_STATUS_UNSENT) {
+ list_del(&req->req_list);
req->status = REQ_STATUS_FLSHD;
ret = 0;
- }
+ } else if (req->status == REQ_STATUS_SENT)
+ req->status = REQ_STATUS_FLSH;
spin_unlock(&client->lock);
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
index 7fa0eb20b2f..ac4990041eb 100644
--- a/net/9p/trans_rdma.c
+++ b/net/9p/trans_rdma.c
@@ -295,6 +295,7 @@ handle_recv(struct p9_client *client, struct p9_trans_rdma *rdma,
goto err_out;
req->rc = c->rc;
+ req->status = REQ_STATUS_RCVD;
p9_client_cb(client, req);
return;
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 2d7781ec663..bb8579a141a 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -134,6 +134,7 @@ static void req_done(struct virtqueue *vq)
P9_DPRINTK(P9_DEBUG_TRANS, ": rc %p\n", rc);
P9_DPRINTK(P9_DEBUG_TRANS, ": lookup tag %d\n", rc->tag);
req = p9_tag_lookup(chan->client, rc->tag);
+ req->status = REQ_STATUS_RCVD;
p9_client_cb(chan->client, req);
}
}
diff --git a/net/Kconfig b/net/Kconfig
index ce77db4fcec..c19f549c8e7 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -119,12 +119,6 @@ menuconfig NETFILTER
<file:Documentation/Changes> under "iptables" for the location of
these packages.
- Make sure to say N to "Fast switching" below if you intend to say Y
- here, as Fast switching currently bypasses netfilter.
-
- Chances are that you should say Y here if you compile a kernel which
- will run as a router and N for regular hosts. If unsure, say N.
-
if NETFILTER
config NETFILTER_DEBUG
diff --git a/net/atm/br2684.c b/net/atm/br2684.c
index 334fcd4a4ea..3100a8940af 100644
--- a/net/atm/br2684.c
+++ b/net/atm/br2684.c
@@ -549,6 +549,7 @@ static void br2684_setup(struct net_device *netdev)
struct br2684_dev *brdev = BRPRIV(netdev);
ether_setup(netdev);
+ brdev->net_dev = netdev;
netdev->netdev_ops = &br2684_netdev_ops;
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 1181db08d9d..fa47d5d84f5 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -171,10 +171,8 @@ static void hci_conn_timeout(unsigned long arg)
switch (conn->state) {
case BT_CONNECT:
case BT_CONNECT2:
- if (conn->type == ACL_LINK)
+ if (conn->type == ACL_LINK && conn->out)
hci_acl_connect_cancel(conn);
- else
- hci_acl_disconn(conn, 0x13);
break;
case BT_CONFIG:
case BT_CONNECTED:
@@ -215,6 +213,7 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst)
conn->state = BT_OPEN;
conn->power_save = 1;
+ conn->disc_timeout = HCI_DISCONN_TIMEOUT;
switch (type) {
case ACL_LINK:
@@ -247,6 +246,8 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst)
if (hdev->notify)
hdev->notify(hdev, HCI_NOTIFY_CONN_ADD);
+ hci_conn_init_sysfs(conn);
+
tasklet_enable(&hdev->tx_task);
return conn;
@@ -289,6 +290,8 @@ int hci_conn_del(struct hci_conn *conn)
hci_conn_del_sysfs(conn);
+ hci_dev_put(hdev);
+
return 0;
}
@@ -424,12 +427,9 @@ int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type)
if (sec_level == BT_SECURITY_SDP)
return 1;
- if (sec_level == BT_SECURITY_LOW) {
- if (conn->ssp_mode > 0 && conn->hdev->ssp_mode > 0)
- return hci_conn_auth(conn, sec_level, auth_type);
- else
- return 1;
- }
+ if (sec_level == BT_SECURITY_LOW &&
+ (!conn->ssp_mode || !conn->hdev->ssp_mode))
+ return 1;
if (conn->link_mode & HCI_LM_ENCRYPT)
return hci_conn_auth(conn, sec_level, auth_type);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 15f40ea8d54..184ba0a88ec 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -883,6 +883,7 @@ static inline void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *s
if (conn->type == ACL_LINK) {
conn->state = BT_CONFIG;
hci_conn_hold(conn);
+ conn->disc_timeout = HCI_DISCONN_TIMEOUT;
} else
conn->state = BT_CONNECTED;
@@ -1063,9 +1064,14 @@ static inline void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *s
hci_proto_connect_cfm(conn, ev->status);
hci_conn_put(conn);
}
- } else
+ } else {
hci_auth_cfm(conn, ev->status);
+ hci_conn_hold(conn);
+ conn->disc_timeout = HCI_DISCONN_TIMEOUT;
+ hci_conn_put(conn);
+ }
+
if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->pend)) {
if (!ev->status) {
struct hci_cp_set_conn_encrypt cp;
@@ -1479,7 +1485,21 @@ static inline void hci_mode_change_evt(struct hci_dev *hdev, struct sk_buff *skb
static inline void hci_pin_code_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
{
+ struct hci_ev_pin_code_req *ev = (void *) skb->data;
+ struct hci_conn *conn;
+
BT_DBG("%s", hdev->name);
+
+ hci_dev_lock(hdev);
+
+ conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr);
+ if (conn && conn->state == BT_CONNECTED) {
+ hci_conn_hold(conn);
+ conn->disc_timeout = HCI_PAIRING_TIMEOUT;
+ hci_conn_put(conn);
+ }
+
+ hci_dev_unlock(hdev);
}
static inline void hci_link_key_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
@@ -1489,7 +1509,21 @@ static inline void hci_link_key_request_evt(struct hci_dev *hdev, struct sk_buff
static inline void hci_link_key_notify_evt(struct hci_dev *hdev, struct sk_buff *skb)
{
+ struct hci_ev_link_key_notify *ev = (void *) skb->data;
+ struct hci_conn *conn;
+
BT_DBG("%s", hdev->name);
+
+ hci_dev_lock(hdev);
+
+ conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr);
+ if (conn) {
+ hci_conn_hold(conn);
+ conn->disc_timeout = HCI_DISCONN_TIMEOUT;
+ hci_conn_put(conn);
+ }
+
+ hci_dev_unlock(hdev);
}
static inline void hci_clock_offset_evt(struct hci_dev *hdev, struct sk_buff *skb)
diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c
index ed82796d4a0..95f7a7a544b 100644
--- a/net/bluetooth/hci_sysfs.c
+++ b/net/bluetooth/hci_sysfs.c
@@ -9,8 +9,7 @@
struct class *bt_class = NULL;
EXPORT_SYMBOL_GPL(bt_class);
-static struct workqueue_struct *btaddconn;
-static struct workqueue_struct *btdelconn;
+static struct workqueue_struct *bt_workq;
static inline char *link_typetostr(int type)
{
@@ -88,35 +87,17 @@ static struct device_type bt_link = {
static void add_conn(struct work_struct *work)
{
- struct hci_conn *conn = container_of(work, struct hci_conn, work);
+ struct hci_conn *conn = container_of(work, struct hci_conn, work_add);
+ struct hci_dev *hdev = conn->hdev;
- flush_workqueue(btdelconn);
+ dev_set_name(&conn->dev, "%s:%d", hdev->name, conn->handle);
if (device_add(&conn->dev) < 0) {
BT_ERR("Failed to register connection device");
return;
}
-}
-
-void hci_conn_add_sysfs(struct hci_conn *conn)
-{
- struct hci_dev *hdev = conn->hdev;
-
- BT_DBG("conn %p", conn);
-
- conn->dev.type = &bt_link;
- conn->dev.class = bt_class;
- conn->dev.parent = &hdev->dev;
- dev_set_name(&conn->dev, "%s:%d", hdev->name, conn->handle);
-
- dev_set_drvdata(&conn->dev, conn);
-
- device_initialize(&conn->dev);
-
- INIT_WORK(&conn->work, add_conn);
-
- queue_work(btaddconn, &conn->work);
+ hci_dev_hold(hdev);
}
/*
@@ -131,9 +112,12 @@ static int __match_tty(struct device *dev, void *data)
static void del_conn(struct work_struct *work)
{
- struct hci_conn *conn = container_of(work, struct hci_conn, work);
+ struct hci_conn *conn = container_of(work, struct hci_conn, work_del);
struct hci_dev *hdev = conn->hdev;
+ if (!device_is_registered(&conn->dev))
+ return;
+
while (1) {
struct device *dev;
@@ -146,19 +130,40 @@ static void del_conn(struct work_struct *work)
device_del(&conn->dev);
put_device(&conn->dev);
+
hci_dev_put(hdev);
}
-void hci_conn_del_sysfs(struct hci_conn *conn)
+void hci_conn_init_sysfs(struct hci_conn *conn)
{
+ struct hci_dev *hdev = conn->hdev;
+
BT_DBG("conn %p", conn);
- if (!device_is_registered(&conn->dev))
- return;
+ conn->dev.type = &bt_link;
+ conn->dev.class = bt_class;
+ conn->dev.parent = &hdev->dev;
- INIT_WORK(&conn->work, del_conn);
+ dev_set_drvdata(&conn->dev, conn);
+
+ device_initialize(&conn->dev);
- queue_work(btdelconn, &conn->work);
+ INIT_WORK(&conn->work_add, add_conn);
+ INIT_WORK(&conn->work_del, del_conn);
+}
+
+void hci_conn_add_sysfs(struct hci_conn *conn)
+{
+ BT_DBG("conn %p", conn);
+
+ queue_work(bt_workq, &conn->work_add);
+}
+
+void hci_conn_del_sysfs(struct hci_conn *conn)
+{
+ BT_DBG("conn %p", conn);
+
+ queue_work(bt_workq, &conn->work_del);
}
static inline char *host_typetostr(int type)
@@ -435,20 +440,13 @@ void hci_unregister_sysfs(struct hci_dev *hdev)
int __init bt_sysfs_init(void)
{
- btaddconn = create_singlethread_workqueue("btaddconn");
- if (!btaddconn)
+ bt_workq = create_singlethread_workqueue("bluetooth");
+ if (!bt_workq)
return -ENOMEM;
- btdelconn = create_singlethread_workqueue("btdelconn");
- if (!btdelconn) {
- destroy_workqueue(btaddconn);
- return -ENOMEM;
- }
-
bt_class = class_create(THIS_MODULE, "bluetooth");
if (IS_ERR(bt_class)) {
- destroy_workqueue(btdelconn);
- destroy_workqueue(btaddconn);
+ destroy_workqueue(bt_workq);
return PTR_ERR(bt_class);
}
@@ -457,8 +455,7 @@ int __init bt_sysfs_init(void)
void bt_sysfs_cleanup(void)
{
- destroy_workqueue(btaddconn);
- destroy_workqueue(btdelconn);
+ destroy_workqueue(bt_workq);
class_destroy(bt_class);
}
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 30b88777c3d..5ee1a3682bf 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -134,6 +134,10 @@ struct sk_buff *br_handle_frame(struct net_bridge_port *p, struct sk_buff *skb)
if (skb->protocol == htons(ETH_P_PAUSE))
goto drop;
+ /* If STP is turned off, then forward */
+ if (p->br->stp_enabled == BR_NO_STP && dest[5] == 0)
+ goto forward;
+
if (NF_HOOK(PF_BRIDGE, NF_BR_LOCAL_IN, skb, skb->dev,
NULL, br_handle_local_finish))
return NULL; /* frame consumed by filter */
@@ -141,6 +145,7 @@ struct sk_buff *br_handle_frame(struct net_bridge_port *p, struct sk_buff *skb)
return skb; /* continue processing */
}
+forward:
switch (p->state) {
case BR_STATE_FORWARDING:
rhook = rcu_dereference(br_should_route_hook);
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 3953ac4214c..e4a418fcb35 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -788,15 +788,23 @@ static unsigned int br_nf_local_out(unsigned int hook, struct sk_buff *skb,
return NF_STOLEN;
}
+#if defined(CONFIG_NF_CONNTRACK_IPV4) || defined(CONFIG_NF_CONNTRACK_IPV4_MODULE)
static int br_nf_dev_queue_xmit(struct sk_buff *skb)
{
- if (skb->protocol == htons(ETH_P_IP) &&
+ if (skb->nfct != NULL &&
+ (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb)) &&
skb->len > skb->dev->mtu &&
!skb_is_gso(skb))
return ip_fragment(skb, br_dev_queue_push_xmit);
else
return br_dev_queue_push_xmit(skb);
}
+#else
+static int br_nf_dev_queue_xmit(struct sk_buff *skb)
+{
+ return br_dev_queue_push_xmit(skb);
+}
+#endif
/* PF_BRIDGE/POST_ROUTING ********************************************/
static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff *skb,
diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index 6e63ec3f1fc..0660515f399 100644
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -297,6 +297,9 @@ void br_topology_change_detection(struct net_bridge *br)
{
int isroot = br_is_root_bridge(br);
+ if (br->stp_enabled != BR_KERNEL_STP)
+ return;
+
pr_info("%s: topology change detected, %s\n", br->dev->name,
isroot ? "propagating" : "sending tcn bpdu");
diff --git a/net/core/datagram.c b/net/core/datagram.c
index d0de644b378..b01a76abe1d 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -64,13 +64,25 @@ static inline int connection_based(struct sock *sk)
return sk->sk_type == SOCK_SEQPACKET || sk->sk_type == SOCK_STREAM;
}
+static int receiver_wake_function(wait_queue_t *wait, unsigned mode, int sync,
+ void *key)
+{
+ unsigned long bits = (unsigned long)key;
+
+ /*
+ * Avoid a wakeup if event not interesting for us
+ */
+ if (bits && !(bits & (POLLIN | POLLERR)))
+ return 0;
+ return autoremove_wake_function(wait, mode, sync, key);
+}
/*
* Wait for a packet..
*/
static int wait_for_packet(struct sock *sk, int *err, long *timeo_p)
{
int error;
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, receiver_wake_function);
prepare_to_wait_exclusive(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
diff --git a/net/core/dev.c b/net/core/dev.c
index 308a7d0c277..e2e9e4af3ac 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1735,11 +1735,12 @@ u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb)
{
u32 hash;
- if (skb_rx_queue_recorded(skb)) {
- hash = skb_get_rx_queue(skb);
- } else if (skb->sk && skb->sk->sk_hash) {
+ if (skb_rx_queue_recorded(skb))
+ return skb_get_rx_queue(skb) % dev->real_num_tx_queues;
+
+ if (skb->sk && skb->sk->sk_hash)
hash = skb->sk->sk_hash;
- } else
+ else
hash = skb->protocol;
hash = jhash_1word(hash, skb_tx_hashrnd);
diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index 9cc9f95b109..6d62d4618cf 100644
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -66,9 +66,9 @@
NOTES.
- * The stored value for avbps is scaled by 2^5, so that maximal
- rate is ~1Gbit, avpps is scaled by 2^10.
-
+ * avbps is scaled by 2^5, avpps is scaled by 2^10.
+ * both values are reported as 32 bit unsigned values. bps can
+ overflow for fast links : max speed being 34360Mbit/sec
* Minimal interval is HZ/4=250msec (it is the greatest common divisor
for HZ=100 and HZ=1024 8)), maximal interval
is (HZ*2^EST_MAX_INTERVAL)/4 = 8sec. Shorter intervals
@@ -86,9 +86,9 @@ struct gen_estimator
spinlock_t *stats_lock;
int ewma_log;
u64 last_bytes;
+ u64 avbps;
u32 last_packets;
u32 avpps;
- u32 avbps;
struct rcu_head e_rcu;
struct rb_node node;
};
@@ -115,6 +115,7 @@ static void est_timer(unsigned long arg)
rcu_read_lock();
list_for_each_entry_rcu(e, &elist[idx].list, list) {
u64 nbytes;
+ u64 brate;
u32 npackets;
u32 rate;
@@ -125,9 +126,9 @@ static void est_timer(unsigned long arg)
nbytes = e->bstats->bytes;
npackets = e->bstats->packets;
- rate = (nbytes - e->last_bytes)<<(7 - idx);
+ brate = (nbytes - e->last_bytes)<<(7 - idx);
e->last_bytes = nbytes;
- e->avbps += ((long)rate - (long)e->avbps) >> e->ewma_log;
+ e->avbps += ((s64)(brate - e->avbps)) >> e->ewma_log;
e->rate_est->bps = (e->avbps+0xF)>>5;
rate = (npackets - e->last_packets)<<(12 - idx);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index b5873bdff61..64f51eec657 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -175,9 +175,13 @@ static void service_arp_queue(struct netpoll_info *npi)
void netpoll_poll(struct netpoll *np)
{
struct net_device *dev = np->dev;
- const struct net_device_ops *ops = dev->netdev_ops;
+ const struct net_device_ops *ops;
+
+ if (!dev || !netif_running(dev))
+ return;
- if (!dev || !netif_running(dev) || !ops->ndo_poll_controller)
+ ops = dev->netdev_ops;
+ if (!ops->ndo_poll_controller)
return;
/* Process pending work on NIC */
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 3779c1438c1..0666a827bc6 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -2447,7 +2447,7 @@ static inline void free_SAs(struct pktgen_dev *pkt_dev)
if (pkt_dev->cflows) {
/* let go of the SAs if we have them */
int i = 0;
- for (; i < pkt_dev->nflows; i++){
+ for (; i < pkt_dev->cflows; i++) {
struct xfrm_state *x = pkt_dev->flows[i].x;
if (x) {
xfrm_state_put(x);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index ce6356cd9f7..e505b5392e1 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -502,7 +502,9 @@ int skb_recycle_check(struct sk_buff *skb, int skb_size)
shinfo->gso_segs = 0;
shinfo->gso_type = 0;
shinfo->ip6_frag_id = 0;
+ shinfo->tx_flags.flags = 0;
shinfo->frag_list = NULL;
+ memset(&shinfo->hwtstamps, 0, sizeof(shinfo->hwtstamps));
memset(skb, 0, offsetof(struct sk_buff, tail));
skb->data = skb->head + NET_SKB_PAD;
@@ -1365,9 +1367,8 @@ static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i)
static inline struct page *linear_to_page(struct page *page, unsigned int *len,
unsigned int *offset,
- struct sk_buff *skb)
+ struct sk_buff *skb, struct sock *sk)
{
- struct sock *sk = skb->sk;
struct page *p = sk->sk_sndmsg_page;
unsigned int off;
@@ -1405,13 +1406,14 @@ new_page:
*/
static inline int spd_fill_page(struct splice_pipe_desc *spd, struct page *page,
unsigned int *len, unsigned int offset,
- struct sk_buff *skb, int linear)
+ struct sk_buff *skb, int linear,
+ struct sock *sk)
{
if (unlikely(spd->nr_pages == PIPE_BUFFERS))
return 1;
if (linear) {
- page = linear_to_page(page, len, &offset, skb);
+ page = linear_to_page(page, len, &offset, skb, sk);
if (!page)
return 1;
} else
@@ -1442,7 +1444,8 @@ static inline void __segment_seek(struct page **page, unsigned int *poff,
static inline int __splice_segment(struct page *page, unsigned int poff,
unsigned int plen, unsigned int *off,
unsigned int *len, struct sk_buff *skb,
- struct splice_pipe_desc *spd, int linear)
+ struct splice_pipe_desc *spd, int linear,
+ struct sock *sk)
{
if (!*len)
return 1;
@@ -1465,7 +1468,7 @@ static inline int __splice_segment(struct page *page, unsigned int poff,
/* the linear region may spread across several pages */
flen = min_t(unsigned int, flen, PAGE_SIZE - poff);
- if (spd_fill_page(spd, page, &flen, poff, skb, linear))
+ if (spd_fill_page(spd, page, &flen, poff, skb, linear, sk))
return 1;
__segment_seek(&page, &poff, &plen, flen);
@@ -1481,8 +1484,8 @@ static inline int __splice_segment(struct page *page, unsigned int poff,
* pipe is full or if we already spliced the requested length.
*/
static int __skb_splice_bits(struct sk_buff *skb, unsigned int *offset,
- unsigned int *len,
- struct splice_pipe_desc *spd)
+ unsigned int *len, struct splice_pipe_desc *spd,
+ struct sock *sk)
{
int seg;
@@ -1492,7 +1495,7 @@ static int __skb_splice_bits(struct sk_buff *skb, unsigned int *offset,
if (__splice_segment(virt_to_page(skb->data),
(unsigned long) skb->data & (PAGE_SIZE - 1),
skb_headlen(skb),
- offset, len, skb, spd, 1))
+ offset, len, skb, spd, 1, sk))
return 1;
/*
@@ -1502,7 +1505,7 @@ static int __skb_splice_bits(struct sk_buff *skb, unsigned int *offset,
const skb_frag_t *f = &skb_shinfo(skb)->frags[seg];
if (__splice_segment(f->page, f->page_offset, f->size,
- offset, len, skb, spd, 0))
+ offset, len, skb, spd, 0, sk))
return 1;
}
@@ -1528,12 +1531,13 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset,
.ops = &sock_pipe_buf_ops,
.spd_release = sock_spd_release,
};
+ struct sock *sk = skb->sk;
/*
* __skb_splice_bits() only fails if the output has no room left,
* so no point in going over the frag_list for the error case.
*/
- if (__skb_splice_bits(skb, &offset, &tlen, &spd))
+ if (__skb_splice_bits(skb, &offset, &tlen, &spd, sk))
goto done;
else if (!tlen)
goto done;
@@ -1545,14 +1549,13 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset,
struct sk_buff *list = skb_shinfo(skb)->frag_list;
for (; list && tlen; list = list->next) {
- if (__skb_splice_bits(list, &offset, &tlen, &spd))
+ if (__skb_splice_bits(list, &offset, &tlen, &spd, sk))
break;
}
}
done:
if (spd.nr_pages) {
- struct sock *sk = skb->sk;
int ret;
/*
@@ -2285,7 +2288,7 @@ unsigned int skb_seq_read(unsigned int consumed, const u8 **data,
next_skb:
block_limit = skb_headlen(st->cur_skb) + st->stepped_offset;
- if (abs_offset < block_limit) {
+ if (abs_offset < block_limit && !st->frag_data) {
*data = st->cur_skb->data + (abs_offset - st->stepped_offset);
return block_limit - abs_offset;
}
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index b2cf91e4cca..5b919f7b45d 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -407,8 +407,8 @@ config INET_XFRM_MODE_BEET
If unsure, say Y.
config INET_LRO
- tristate "Large Receive Offload (ipv4/tcp)"
-
+ bool "Large Receive Offload (ipv4/tcp)"
+ default y
---help---
Support for Large Receive Offload (ipv4/tcp).
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index ec0ae490f0b..33c7c85dfe4 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -986,9 +986,12 @@ fib_find_node(struct trie *t, u32 key)
static struct node *trie_rebalance(struct trie *t, struct tnode *tn)
{
int wasfull;
- t_key cindex, key = tn->key;
+ t_key cindex, key;
struct tnode *tp;
+ preempt_disable();
+ key = tn->key;
+
while (tn != NULL && (tp = node_parent((struct node *)tn)) != NULL) {
cindex = tkey_extract_bits(key, tp->pos, tp->bits);
wasfull = tnode_full(tp, tnode_get_child(tp, cindex));
@@ -1007,6 +1010,7 @@ static struct node *trie_rebalance(struct trie *t, struct tnode *tn)
if (IS_TNODE(tn))
tn = (struct tnode *)resize(t, (struct tnode *)tn);
+ preempt_enable();
return (struct node *)tn;
}
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 90d22ae0a41..88bf051d0cb 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -139,6 +139,8 @@ __be32 ic_servaddr = NONE; /* Boot server IP address */
__be32 root_server_addr = NONE; /* Address of NFS server */
u8 root_server_path[256] = { 0, }; /* Path to mount as root */
+u32 ic_dev_xid; /* Device under configuration */
+
/* vendor class identifier */
static char vendor_class_identifier[253] __initdata;
@@ -932,6 +934,13 @@ static int __init ic_bootp_recv(struct sk_buff *skb, struct net_device *dev, str
goto drop_unlock;
}
+ /* Is it a reply for the device we are configuring? */
+ if (b->xid != ic_dev_xid) {
+ if (net_ratelimit())
+ printk(KERN_ERR "DHCP/BOOTP: Ignoring delayed packet \n");
+ goto drop_unlock;
+ }
+
/* Parse extensions */
if (ext_len >= 4 &&
!memcmp(b->exten, ic_bootp_cookie, 4)) { /* Check magic cookie */
@@ -1115,6 +1124,9 @@ static int __init ic_dynamic(void)
get_random_bytes(&timeout, sizeof(timeout));
timeout = CONF_BASE_TIMEOUT + (timeout % (unsigned) CONF_TIMEOUT_RANDOM);
for (;;) {
+ /* Track the device we are configuring */
+ ic_dev_xid = d->xid;
+
#ifdef IPCONFIG_BOOTP
if (do_bootp && (d->able & IC_BOOTP))
ic_bootp_send_if(d, jiffies - start_jiffies);
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 5ba533d234d..831fe1879dc 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -253,9 +253,9 @@ unsigned int arpt_do_table(struct sk_buff *skb,
indev = in ? in->name : nulldevname;
outdev = out ? out->name : nulldevname;
- rcu_read_lock_bh();
- private = rcu_dereference(table->private);
- table_base = rcu_dereference(private->entries[smp_processor_id()]);
+ xt_info_rdlock_bh();
+ private = table->private;
+ table_base = private->entries[smp_processor_id()];
e = get_entry(table_base, private->hook_entry[hook]);
back = get_entry(table_base, private->underflow[hook]);
@@ -273,6 +273,7 @@ unsigned int arpt_do_table(struct sk_buff *skb,
hdr_len = sizeof(*arp) + (2 * sizeof(struct in_addr)) +
(2 * skb->dev->addr_len);
+
ADD_COUNTER(e->counters, hdr_len, 1);
t = arpt_get_target(e);
@@ -328,8 +329,7 @@ unsigned int arpt_do_table(struct sk_buff *skb,
e = (void *)e + e->next_offset;
}
} while (!hotdrop);
-
- rcu_read_unlock_bh();
+ xt_info_rdunlock_bh();
if (hotdrop)
return NF_DROP;
@@ -711,9 +711,12 @@ static void get_counters(const struct xt_table_info *t,
/* Instead of clearing (by a previous call to memset())
* the counters and using adds, we set the counters
* with data used by 'current' CPU
- * We dont care about preemption here.
+ *
+ * Bottom half has to be disabled to prevent deadlock
+ * if new softirq were to run and call ipt_do_table
*/
- curcpu = raw_smp_processor_id();
+ local_bh_disable();
+ curcpu = smp_processor_id();
i = 0;
ARPT_ENTRY_ITERATE(t->entries[curcpu],
@@ -726,73 +729,22 @@ static void get_counters(const struct xt_table_info *t,
if (cpu == curcpu)
continue;
i = 0;
+ xt_info_wrlock(cpu);
ARPT_ENTRY_ITERATE(t->entries[cpu],
t->size,
add_entry_to_counter,
counters,
&i);
+ xt_info_wrunlock(cpu);
}
-}
-
-
-/* We're lazy, and add to the first CPU; overflow works its fey magic
- * and everything is OK. */
-static int
-add_counter_to_entry(struct arpt_entry *e,
- const struct xt_counters addme[],
- unsigned int *i)
-{
- ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt);
-
- (*i)++;
- return 0;
-}
-
-/* Take values from counters and add them back onto the current cpu */
-static void put_counters(struct xt_table_info *t,
- const struct xt_counters counters[])
-{
- unsigned int i, cpu;
-
- local_bh_disable();
- cpu = smp_processor_id();
- i = 0;
- ARPT_ENTRY_ITERATE(t->entries[cpu],
- t->size,
- add_counter_to_entry,
- counters,
- &i);
local_bh_enable();
}
-static inline int
-zero_entry_counter(struct arpt_entry *e, void *arg)
-{
- e->counters.bcnt = 0;
- e->counters.pcnt = 0;
- return 0;
-}
-
-static void
-clone_counters(struct xt_table_info *newinfo, const struct xt_table_info *info)
-{
- unsigned int cpu;
- const void *loc_cpu_entry = info->entries[raw_smp_processor_id()];
-
- memcpy(newinfo, info, offsetof(struct xt_table_info, entries));
- for_each_possible_cpu(cpu) {
- memcpy(newinfo->entries[cpu], loc_cpu_entry, info->size);
- ARPT_ENTRY_ITERATE(newinfo->entries[cpu], newinfo->size,
- zero_entry_counter, NULL);
- }
-}
-
static struct xt_counters *alloc_counters(struct xt_table *table)
{
unsigned int countersize;
struct xt_counters *counters;
struct xt_table_info *private = table->private;
- struct xt_table_info *info;
/* We need atomic snapshot of counters: rest doesn't change
* (other than comefrom, which userspace doesn't care
@@ -802,30 +754,11 @@ static struct xt_counters *alloc_counters(struct xt_table *table)
counters = vmalloc_node(countersize, numa_node_id());
if (counters == NULL)
- goto nomem;
-
- info = xt_alloc_table_info(private->size);
- if (!info)
- goto free_counters;
-
- clone_counters(info, private);
-
- mutex_lock(&table->lock);
- xt_table_entry_swap_rcu(private, info);
- synchronize_net(); /* Wait until smoke has cleared */
+ return ERR_PTR(-ENOMEM);
- get_counters(info, counters);
- put_counters(private, counters);
- mutex_unlock(&table->lock);
-
- xt_free_table_info(info);
+ get_counters(private, counters);
return counters;
-
- free_counters:
- vfree(counters);
- nomem:
- return ERR_PTR(-ENOMEM);
}
static int copy_entries_to_user(unsigned int total_size,
@@ -1094,8 +1027,9 @@ static int __do_replace(struct net *net, const char *name,
(newinfo->number <= oldinfo->initial_entries))
module_put(t->me);
- /* Get the old counters. */
+ /* Get the old counters, and synchronize with replace */
get_counters(oldinfo, counters);
+
/* Decrease module usage counts and free resource */
loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()];
ARPT_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry,
@@ -1165,10 +1099,23 @@ static int do_replace(struct net *net, void __user *user, unsigned int len)
return ret;
}
+/* We're lazy, and add to the first CPU; overflow works its fey magic
+ * and everything is OK. */
+static int
+add_counter_to_entry(struct arpt_entry *e,
+ const struct xt_counters addme[],
+ unsigned int *i)
+{
+ ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt);
+
+ (*i)++;
+ return 0;
+}
+
static int do_add_counters(struct net *net, void __user *user, unsigned int len,
int compat)
{
- unsigned int i;
+ unsigned int i, curcpu;
struct xt_counters_info tmp;
struct xt_counters *paddc;
unsigned int num_counters;
@@ -1224,26 +1171,26 @@ static int do_add_counters(struct net *net, void __user *user, unsigned int len,
goto free;
}
- mutex_lock(&t->lock);
+ local_bh_disable();
private = t->private;
if (private->number != num_counters) {
ret = -EINVAL;
goto unlock_up_free;
}
- preempt_disable();
i = 0;
/* Choose the copy that is on our node */
- loc_cpu_entry = private->entries[smp_processor_id()];
+ curcpu = smp_processor_id();
+ loc_cpu_entry = private->entries[curcpu];
+ xt_info_wrlock(curcpu);
ARPT_ENTRY_ITERATE(loc_cpu_entry,
private->size,
add_counter_to_entry,
paddc,
&i);
- preempt_enable();
+ xt_info_wrunlock(curcpu);
unlock_up_free:
- mutex_unlock(&t->lock);
-
+ local_bh_enable();
xt_table_unlock(t);
module_put(t->me);
free:
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 810c0b62c7d..2ec8d7290c4 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -338,10 +338,9 @@ ipt_do_table(struct sk_buff *skb,
tgpar.hooknum = hook;
IP_NF_ASSERT(table->valid_hooks & (1 << hook));
-
- rcu_read_lock_bh();
- private = rcu_dereference(table->private);
- table_base = rcu_dereference(private->entries[smp_processor_id()]);
+ xt_info_rdlock_bh();
+ private = table->private;
+ table_base = private->entries[smp_processor_id()];
e = get_entry(table_base, private->hook_entry[hook]);
@@ -436,8 +435,7 @@ ipt_do_table(struct sk_buff *skb,
e = (void *)e + e->next_offset;
}
} while (!hotdrop);
-
- rcu_read_unlock_bh();
+ xt_info_rdunlock_bh();
#ifdef DEBUG_ALLOW_ALL
return NF_ACCEPT;
@@ -896,10 +894,13 @@ get_counters(const struct xt_table_info *t,
/* Instead of clearing (by a previous call to memset())
* the counters and using adds, we set the counters
- * with data used by 'current' CPU
- * We dont care about preemption here.
+ * with data used by 'current' CPU.
+ *
+ * Bottom half has to be disabled to prevent deadlock
+ * if new softirq were to run and call ipt_do_table
*/
- curcpu = raw_smp_processor_id();
+ local_bh_disable();
+ curcpu = smp_processor_id();
i = 0;
IPT_ENTRY_ITERATE(t->entries[curcpu],
@@ -912,74 +913,22 @@ get_counters(const struct xt_table_info *t,
if (cpu == curcpu)
continue;
i = 0;
+ xt_info_wrlock(cpu);
IPT_ENTRY_ITERATE(t->entries[cpu],
t->size,
add_entry_to_counter,
counters,
&i);
+ xt_info_wrunlock(cpu);
}
-
-}
-
-/* We're lazy, and add to the first CPU; overflow works its fey magic
- * and everything is OK. */
-static int
-add_counter_to_entry(struct ipt_entry *e,
- const struct xt_counters addme[],
- unsigned int *i)
-{
- ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt);
-
- (*i)++;
- return 0;
-}
-
-/* Take values from counters and add them back onto the current cpu */
-static void put_counters(struct xt_table_info *t,
- const struct xt_counters counters[])
-{
- unsigned int i, cpu;
-
- local_bh_disable();
- cpu = smp_processor_id();
- i = 0;
- IPT_ENTRY_ITERATE(t->entries[cpu],
- t->size,
- add_counter_to_entry,
- counters,
- &i);
local_bh_enable();
}
-
-static inline int
-zero_entry_counter(struct ipt_entry *e, void *arg)
-{
- e->counters.bcnt = 0;
- e->counters.pcnt = 0;
- return 0;
-}
-
-static void
-clone_counters(struct xt_table_info *newinfo, const struct xt_table_info *info)
-{
- unsigned int cpu;
- const void *loc_cpu_entry = info->entries[raw_smp_processor_id()];
-
- memcpy(newinfo, info, offsetof(struct xt_table_info, entries));
- for_each_possible_cpu(cpu) {
- memcpy(newinfo->entries[cpu], loc_cpu_entry, info->size);
- IPT_ENTRY_ITERATE(newinfo->entries[cpu], newinfo->size,
- zero_entry_counter, NULL);
- }
-}
-
static struct xt_counters * alloc_counters(struct xt_table *table)
{
unsigned int countersize;
struct xt_counters *counters;
struct xt_table_info *private = table->private;
- struct xt_table_info *info;
/* We need atomic snapshot of counters: rest doesn't change
(other than comefrom, which userspace doesn't care
@@ -988,30 +937,11 @@ static struct xt_counters * alloc_counters(struct xt_table *table)
counters = vmalloc_node(countersize, numa_node_id());
if (counters == NULL)
- goto nomem;
+ return ERR_PTR(-ENOMEM);
- info = xt_alloc_table_info(private->size);
- if (!info)
- goto free_counters;
-
- clone_counters(info, private);
-
- mutex_lock(&table->lock);
- xt_table_entry_swap_rcu(private, info);
- synchronize_net(); /* Wait until smoke has cleared */
-
- get_counters(info, counters);
- put_counters(private, counters);
- mutex_unlock(&table->lock);
-
- xt_free_table_info(info);
+ get_counters(private, counters);
return counters;
-
- free_counters:
- vfree(counters);
- nomem:
- return ERR_PTR(-ENOMEM);
}
static int
@@ -1306,8 +1236,9 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
(newinfo->number <= oldinfo->initial_entries))
module_put(t->me);
- /* Get the old counters. */
+ /* Get the old counters, and synchronize with replace */
get_counters(oldinfo, counters);
+
/* Decrease module usage counts and free resource */
loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()];
IPT_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry,
@@ -1377,11 +1308,23 @@ do_replace(struct net *net, void __user *user, unsigned int len)
return ret;
}
+/* We're lazy, and add to the first CPU; overflow works its fey magic
+ * and everything is OK. */
+static int
+add_counter_to_entry(struct ipt_entry *e,
+ const struct xt_counters addme[],
+ unsigned int *i)
+{
+ ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt);
+
+ (*i)++;
+ return 0;
+}
static int
do_add_counters(struct net *net, void __user *user, unsigned int len, int compat)
{
- unsigned int i;
+ unsigned int i, curcpu;
struct xt_counters_info tmp;
struct xt_counters *paddc;
unsigned int num_counters;
@@ -1437,25 +1380,26 @@ do_add_counters(struct net *net, void __user *user, unsigned int len, int compat
goto free;
}
- mutex_lock(&t->lock);
+ local_bh_disable();
private = t->private;
if (private->number != num_counters) {
ret = -EINVAL;
goto unlock_up_free;
}
- preempt_disable();
i = 0;
/* Choose the copy that is on our node */
- loc_cpu_entry = private->entries[raw_smp_processor_id()];
+ curcpu = smp_processor_id();
+ loc_cpu_entry = private->entries[curcpu];
+ xt_info_wrlock(curcpu);
IPT_ENTRY_ITERATE(loc_cpu_entry,
private->size,
add_counter_to_entry,
paddc,
&i);
- preempt_enable();
+ xt_info_wrunlock(curcpu);
unlock_up_free:
- mutex_unlock(&t->lock);
+ local_bh_enable();
xt_table_unlock(t);
module_put(t->me);
free:
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index c40debe51b3..28205e5bfa9 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -784,8 +784,8 @@ static void rt_check_expire(void)
{
static unsigned int rover;
unsigned int i = rover, goal;
- struct rtable *rth, **rthp;
- unsigned long length = 0, samples = 0;
+ struct rtable *rth, *aux, **rthp;
+ unsigned long samples = 0;
unsigned long sum = 0, sum2 = 0;
u64 mult;
@@ -795,9 +795,9 @@ static void rt_check_expire(void)
goal = (unsigned int)mult;
if (goal > rt_hash_mask)
goal = rt_hash_mask + 1;
- length = 0;
for (; goal > 0; goal--) {
unsigned long tmo = ip_rt_gc_timeout;
+ unsigned long length;
i = (i + 1) & rt_hash_mask;
rthp = &rt_hash_table[i].chain;
@@ -809,8 +809,10 @@ static void rt_check_expire(void)
if (*rthp == NULL)
continue;
+ length = 0;
spin_lock_bh(rt_hash_lock_addr(i));
while ((rth = *rthp) != NULL) {
+ prefetch(rth->u.dst.rt_next);
if (rt_is_expired(rth)) {
*rthp = rth->u.dst.rt_next;
rt_free(rth);
@@ -819,33 +821,30 @@ static void rt_check_expire(void)
if (rth->u.dst.expires) {
/* Entry is expired even if it is in use */
if (time_before_eq(jiffies, rth->u.dst.expires)) {
+nofree:
tmo >>= 1;
rthp = &rth->u.dst.rt_next;
/*
- * Only bump our length if the hash
- * inputs on entries n and n+1 are not
- * the same, we only count entries on
+ * We only count entries on
* a chain with equal hash inputs once
* so that entries for different QOS
* levels, and other non-hash input
* attributes don't unfairly skew
* the length computation
*/
- if ((*rthp == NULL) ||
- !compare_hash_inputs(&(*rthp)->fl,
- &rth->fl))
- length += ONE;
+ for (aux = rt_hash_table[i].chain;;) {
+ if (aux == rth) {
+ length += ONE;
+ break;
+ }
+ if (compare_hash_inputs(&aux->fl, &rth->fl))
+ break;
+ aux = aux->u.dst.rt_next;
+ }
continue;
}
- } else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout)) {
- tmo >>= 1;
- rthp = &rth->u.dst.rt_next;
- if ((*rthp == NULL) ||
- !compare_hash_inputs(&(*rthp)->fl,
- &rth->fl))
- length += ONE;
- continue;
- }
+ } else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout))
+ goto nofree;
/* Cleanup aged off entries. */
*rthp = rth->u.dst.rt_next;
@@ -1068,7 +1067,6 @@ out: return 0;
static int rt_intern_hash(unsigned hash, struct rtable *rt, struct rtable **rp)
{
struct rtable *rth, **rthp;
- struct rtable *rthi;
unsigned long now;
struct rtable *cand, **candp;
u32 min_score;
@@ -1088,7 +1086,6 @@ restart:
}
rthp = &rt_hash_table[hash].chain;
- rthi = NULL;
spin_lock_bh(rt_hash_lock_addr(hash));
while ((rth = *rthp) != NULL) {
@@ -1134,17 +1131,6 @@ restart:
chain_length++;
rthp = &rth->u.dst.rt_next;
-
- /*
- * check to see if the next entry in the chain
- * contains the same hash input values as rt. If it does
- * This is where we will insert into the list, instead of
- * at the head. This groups entries that differ by aspects not
- * relvant to the hash function together, which we use to adjust
- * our chain length
- */
- if (*rthp && compare_hash_inputs(&(*rthp)->fl, &rt->fl))
- rthi = rth;
}
if (cand) {
@@ -1205,10 +1191,7 @@ restart:
}
}
- if (rthi)
- rt->u.dst.rt_next = rthi->u.dst.rt_next;
- else
- rt->u.dst.rt_next = rt_hash_table[hash].chain;
+ rt->u.dst.rt_next = rt_hash_table[hash].chain;
#if RT_CACHE_DEBUG >= 2
if (rt->u.dst.rt_next) {
@@ -1224,10 +1207,7 @@ restart:
* previous writes to rt are comitted to memory
* before making rt visible to other CPUS.
*/
- if (rthi)
- rcu_assign_pointer(rthi->u.dst.rt_next, rt);
- else
- rcu_assign_pointer(rt_hash_table[hash].chain, rt);
+ rcu_assign_pointer(rt_hash_table[hash].chain, rt);
spin_unlock_bh(rt_hash_lock_addr(hash));
*rp = rt;
@@ -3397,7 +3377,7 @@ int __init ip_rt_init(void)
0,
&rt_hash_log,
&rt_hash_mask,
- 0);
+ rhash_entries ? 0 : 512 * 1024);
memset(rt_hash_table, 0, (rt_hash_mask + 1) * sizeof(struct rt_hash_bucket));
rt_hash_lock_init();
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 1d7f49c6f0c..7a0f0b27bf1 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1321,6 +1321,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
struct task_struct *user_recv = NULL;
int copied_early = 0;
struct sk_buff *skb;
+ u32 urg_hole = 0;
lock_sock(sk);
@@ -1532,7 +1533,8 @@ do_prequeue:
}
}
}
- if ((flags & MSG_PEEK) && peek_seq != tp->copied_seq) {
+ if ((flags & MSG_PEEK) &&
+ (peek_seq - copied - urg_hole != tp->copied_seq)) {
if (net_ratelimit())
printk(KERN_DEBUG "TCP(%s:%d): Application bug, race in MSG_PEEK.\n",
current->comm, task_pid_nr(current));
@@ -1553,6 +1555,7 @@ do_prequeue:
if (!urg_offset) {
if (!sock_flag(sk, SOCK_URGINLINE)) {
++*seq;
+ urg_hole++;
offset++;
used--;
if (!used)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c96a6bb2543..eec3e6f9956 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -597,16 +597,6 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb)
tcp_grow_window(sk, skb);
}
-static u32 tcp_rto_min(struct sock *sk)
-{
- struct dst_entry *dst = __sk_dst_get(sk);
- u32 rto_min = TCP_RTO_MIN;
-
- if (dst && dst_metric_locked(dst, RTAX_RTO_MIN))
- rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN);
- return rto_min;
-}
-
/* Called to compute a smoothed rtt estimate. The data fed to this
* routine either comes from timestamps, or from segments that were
* known _not_ to have been retransmitted [see Karn/Partridge
diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c
index a453aac91bd..c6743eec9b7 100644
--- a/net/ipv4/tcp_vegas.c
+++ b/net/ipv4/tcp_vegas.c
@@ -158,6 +158,11 @@ void tcp_vegas_cwnd_event(struct sock *sk, enum tcp_ca_event event)
}
EXPORT_SYMBOL_GPL(tcp_vegas_cwnd_event);
+static inline u32 tcp_vegas_ssthresh(struct tcp_sock *tp)
+{
+ return min(tp->snd_ssthresh, tp->snd_cwnd-1);
+}
+
static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -221,11 +226,10 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
*/
diff = tp->snd_cwnd * (rtt-vegas->baseRTT) / vegas->baseRTT;
- if (diff > gamma && tp->snd_ssthresh > 2 ) {
+ if (diff > gamma && tp->snd_cwnd <= tp->snd_ssthresh) {
/* Going too fast. Time to slow down
* and switch to congestion avoidance.
*/
- tp->snd_ssthresh = 2;
/* Set cwnd to match the actual rate
* exactly:
@@ -235,6 +239,7 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
* utilization.
*/
tp->snd_cwnd = min(tp->snd_cwnd, (u32)target_cwnd+1);
+ tp->snd_ssthresh = tcp_vegas_ssthresh(tp);
} else if (tp->snd_cwnd <= tp->snd_ssthresh) {
/* Slow start. */
@@ -250,6 +255,8 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
* we slow down.
*/
tp->snd_cwnd--;
+ tp->snd_ssthresh
+ = tcp_vegas_ssthresh(tp);
} else if (diff < alpha) {
/* We don't have enough extra packets
* in the network, so speed up.
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 800ae854247..219e165aea1 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -365,9 +365,9 @@ ip6t_do_table(struct sk_buff *skb,
IP_NF_ASSERT(table->valid_hooks & (1 << hook));
- rcu_read_lock_bh();
- private = rcu_dereference(table->private);
- table_base = rcu_dereference(private->entries[smp_processor_id()]);
+ xt_info_rdlock_bh();
+ private = table->private;
+ table_base = private->entries[smp_processor_id()];
e = get_entry(table_base, private->hook_entry[hook]);
@@ -466,7 +466,7 @@ ip6t_do_table(struct sk_buff *skb,
#ifdef CONFIG_NETFILTER_DEBUG
((struct ip6t_entry *)table_base)->comefrom = NETFILTER_LINK_POISON;
#endif
- rcu_read_unlock_bh();
+ xt_info_rdunlock_bh();
#ifdef DEBUG_ALLOW_ALL
return NF_ACCEPT;
@@ -926,9 +926,12 @@ get_counters(const struct xt_table_info *t,
/* Instead of clearing (by a previous call to memset())
* the counters and using adds, we set the counters
* with data used by 'current' CPU
- * We dont care about preemption here.
+ *
+ * Bottom half has to be disabled to prevent deadlock
+ * if new softirq were to run and call ipt_do_table
*/
- curcpu = raw_smp_processor_id();
+ local_bh_disable();
+ curcpu = smp_processor_id();
i = 0;
IP6T_ENTRY_ITERATE(t->entries[curcpu],
@@ -941,72 +944,22 @@ get_counters(const struct xt_table_info *t,
if (cpu == curcpu)
continue;
i = 0;
+ xt_info_wrlock(cpu);
IP6T_ENTRY_ITERATE(t->entries[cpu],
t->size,
add_entry_to_counter,
counters,
&i);
+ xt_info_wrunlock(cpu);
}
-}
-
-/* We're lazy, and add to the first CPU; overflow works its fey magic
- * and everything is OK. */
-static int
-add_counter_to_entry(struct ip6t_entry *e,
- const struct xt_counters addme[],
- unsigned int *i)
-{
- ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt);
-
- (*i)++;
- return 0;
-}
-
-/* Take values from counters and add them back onto the current cpu */
-static void put_counters(struct xt_table_info *t,
- const struct xt_counters counters[])
-{
- unsigned int i, cpu;
-
- local_bh_disable();
- cpu = smp_processor_id();
- i = 0;
- IP6T_ENTRY_ITERATE(t->entries[cpu],
- t->size,
- add_counter_to_entry,
- counters,
- &i);
local_bh_enable();
}
-static inline int
-zero_entry_counter(struct ip6t_entry *e, void *arg)
-{
- e->counters.bcnt = 0;
- e->counters.pcnt = 0;
- return 0;
-}
-
-static void
-clone_counters(struct xt_table_info *newinfo, const struct xt_table_info *info)
-{
- unsigned int cpu;
- const void *loc_cpu_entry = info->entries[raw_smp_processor_id()];
-
- memcpy(newinfo, info, offsetof(struct xt_table_info, entries));
- for_each_possible_cpu(cpu) {
- memcpy(newinfo->entries[cpu], loc_cpu_entry, info->size);
- IP6T_ENTRY_ITERATE(newinfo->entries[cpu], newinfo->size,
- zero_entry_counter, NULL);
- }
-}
-
static struct xt_counters *alloc_counters(struct xt_table *table)
{
unsigned int countersize;
struct xt_counters *counters;
struct xt_table_info *private = table->private;
- struct xt_table_info *info;
/* We need atomic snapshot of counters: rest doesn't change
(other than comefrom, which userspace doesn't care
@@ -1015,30 +968,11 @@ static struct xt_counters *alloc_counters(struct xt_table *table)
counters = vmalloc_node(countersize, numa_node_id());
if (counters == NULL)
- goto nomem;
+ return ERR_PTR(-ENOMEM);
- info = xt_alloc_table_info(private->size);
- if (!info)
- goto free_counters;
-
- clone_counters(info, private);
-
- mutex_lock(&table->lock);
- xt_table_entry_swap_rcu(private, info);
- synchronize_net(); /* Wait until smoke has cleared */
-
- get_counters(info, counters);
- put_counters(private, counters);
- mutex_unlock(&table->lock);
-
- xt_free_table_info(info);
+ get_counters(private, counters);
return counters;
-
- free_counters:
- vfree(counters);
- nomem:
- return ERR_PTR(-ENOMEM);
}
static int
@@ -1334,8 +1268,9 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
(newinfo->number <= oldinfo->initial_entries))
module_put(t->me);
- /* Get the old counters. */
+ /* Get the old counters, and synchronize with replace */
get_counters(oldinfo, counters);
+
/* Decrease module usage counts and free resource */
loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()];
IP6T_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry,
@@ -1405,11 +1340,24 @@ do_replace(struct net *net, void __user *user, unsigned int len)
return ret;
}
+/* We're lazy, and add to the first CPU; overflow works its fey magic
+ * and everything is OK. */
+static int
+add_counter_to_entry(struct ip6t_entry *e,
+ const struct xt_counters addme[],
+ unsigned int *i)
+{
+ ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt);
+
+ (*i)++;
+ return 0;
+}
+
static int
do_add_counters(struct net *net, void __user *user, unsigned int len,
int compat)
{
- unsigned int i;
+ unsigned int i, curcpu;
struct xt_counters_info tmp;
struct xt_counters *paddc;
unsigned int num_counters;
@@ -1465,25 +1413,28 @@ do_add_counters(struct net *net, void __user *user, unsigned int len,
goto free;
}
- mutex_lock(&t->lock);
+
+ local_bh_disable();
private = t->private;
if (private->number != num_counters) {
ret = -EINVAL;
goto unlock_up_free;
}
- preempt_disable();
i = 0;
/* Choose the copy that is on our node */
- loc_cpu_entry = private->entries[raw_smp_processor_id()];
+ curcpu = smp_processor_id();
+ xt_info_wrlock(curcpu);
+ loc_cpu_entry = private->entries[curcpu];
IP6T_ENTRY_ITERATE(loc_cpu_entry,
private->size,
add_counter_to_entry,
paddc,
&i);
- preempt_enable();
+ xt_info_wrunlock(curcpu);
+
unlock_up_free:
- mutex_unlock(&t->lock);
+ local_bh_enable();
xt_table_unlock(t);
module_put(t->me);
free:
diff --git a/net/ipv6/netfilter/ip6t_ipv6header.c b/net/ipv6/netfilter/ip6t_ipv6header.c
index 14e6724d567..91490ad9302 100644
--- a/net/ipv6/netfilter/ip6t_ipv6header.c
+++ b/net/ipv6/netfilter/ip6t_ipv6header.c
@@ -50,14 +50,14 @@ ipv6header_mt6(const struct sk_buff *skb, const struct xt_match_param *par)
struct ipv6_opt_hdr _hdr;
int hdrlen;
- /* Is there enough space for the next ext header? */
- if (len < (int)sizeof(struct ipv6_opt_hdr))
- return false;
/* No more exthdr -> evaluate */
if (nexthdr == NEXTHDR_NONE) {
temp |= MASK_NONE;
break;
}
+ /* Is there enough space for the next ext header? */
+ if (len < (int)sizeof(struct ipv6_opt_hdr))
+ return false;
/* ESP -> evaluate */
if (nexthdr == NEXTHDR_ESP) {
temp |= MASK_ESP;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 1394ddb6e35..032a5ec391c 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -137,6 +137,7 @@ static struct rt6_info ip6_null_entry_template = {
}
},
.rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
+ .rt6i_protocol = RTPROT_KERNEL,
.rt6i_metric = ~(u32) 0,
.rt6i_ref = ATOMIC_INIT(1),
};
@@ -159,6 +160,7 @@ static struct rt6_info ip6_prohibit_entry_template = {
}
},
.rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
+ .rt6i_protocol = RTPROT_KERNEL,
.rt6i_metric = ~(u32) 0,
.rt6i_ref = ATOMIC_INIT(1),
};
@@ -176,6 +178,7 @@ static struct rt6_info ip6_blk_hole_entry_template = {
}
},
.rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
+ .rt6i_protocol = RTPROT_KERNEL,
.rt6i_metric = ~(u32) 0,
.rt6i_ref = ATOMIC_INIT(1),
};
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index fbcbed6cad0..14134193cd1 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -757,6 +757,7 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len,
local->hw.conf.long_frame_max_tx_count = 4;
local->hw.conf.short_frame_max_tx_count = 7;
local->hw.conf.radio_enabled = true;
+ local->user_power_level = -1;
INIT_LIST_HEAD(&local->interfaces);
mutex_init(&local->iflist_mtx);
@@ -909,6 +910,13 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
if (result < 0)
goto fail_sta_info;
+ result = ieee80211_wep_init(local);
+ if (result < 0) {
+ printk(KERN_DEBUG "%s: Failed to initialize wep: %d\n",
+ wiphy_name(local->hw.wiphy), result);
+ goto fail_wep;
+ }
+
rtnl_lock();
result = dev_alloc_name(local->mdev, local->mdev->name);
if (result < 0)
@@ -930,14 +938,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
goto fail_rate;
}
- result = ieee80211_wep_init(local);
-
- if (result < 0) {
- printk(KERN_DEBUG "%s: Failed to initialize wep: %d\n",
- wiphy_name(local->hw.wiphy), result);
- goto fail_wep;
- }
-
/* add one default STA interface if supported */
if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_STATION)) {
result = ieee80211_if_add(local, "wlan%d", NULL,
@@ -967,13 +967,13 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
return 0;
-fail_wep:
- rate_control_deinitialize(local);
fail_rate:
unregister_netdevice(local->mdev);
local->mdev = NULL;
fail_dev:
rtnl_unlock();
+ ieee80211_wep_free(local);
+fail_wep:
sta_info_stop(local);
fail_sta_info:
debugfs_hw_del(local);
diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c
index 3824990d340..d9233ec5061 100644
--- a/net/mac80211/rc80211_minstrel.c
+++ b/net/mac80211/rc80211_minstrel.c
@@ -476,8 +476,8 @@ minstrel_alloc_sta(void *priv, struct ieee80211_sta *sta, gfp_t gfp)
return NULL;
for (i = 0; i < IEEE80211_NUM_BANDS; i++) {
- sband = hw->wiphy->bands[hw->conf.channel->band];
- if (sband->n_bitrates > max_rates)
+ sband = hw->wiphy->bands[i];
+ if (sband && sband->n_bitrates > max_rates)
max_rates = sband->n_bitrates;
}
diff --git a/net/mac80211/rc80211_pid_algo.c b/net/mac80211/rc80211_pid_algo.c
index b16801cde06..8bef9a1262f 100644
--- a/net/mac80211/rc80211_pid_algo.c
+++ b/net/mac80211/rc80211_pid_algo.c
@@ -317,13 +317,44 @@ rate_control_pid_rate_init(void *priv, struct ieee80211_supported_band *sband,
struct ieee80211_sta *sta, void *priv_sta)
{
struct rc_pid_sta_info *spinfo = priv_sta;
+ struct rc_pid_info *pinfo = priv;
+ struct rc_pid_rateinfo *rinfo = pinfo->rinfo;
struct sta_info *si;
+ int i, j, tmp;
+ bool s;
/* TODO: This routine should consider using RSSI from previous packets
* as we need to have IEEE 802.1X auth succeed immediately after assoc..
* Until that method is implemented, we will use the lowest supported
* rate as a workaround. */
+ /* Sort the rates. This is optimized for the most common case (i.e.
+ * almost-sorted CCK+OFDM rates). Kind of bubble-sort with reversed
+ * mapping too. */
+ for (i = 0; i < sband->n_bitrates; i++) {
+ rinfo[i].index = i;
+ rinfo[i].rev_index = i;
+ if (RC_PID_FAST_START)
+ rinfo[i].diff = 0;
+ else
+ rinfo[i].diff = i * pinfo->norm_offset;
+ }
+ for (i = 1; i < sband->n_bitrates; i++) {
+ s = 0;
+ for (j = 0; j < sband->n_bitrates - i; j++)
+ if (unlikely(sband->bitrates[rinfo[j].index].bitrate >
+ sband->bitrates[rinfo[j + 1].index].bitrate)) {
+ tmp = rinfo[j].index;
+ rinfo[j].index = rinfo[j + 1].index;
+ rinfo[j + 1].index = tmp;
+ rinfo[rinfo[j].index].rev_index = j;
+ rinfo[rinfo[j + 1].index].rev_index = j + 1;
+ s = 1;
+ }
+ if (!s)
+ break;
+ }
+
spinfo->txrate_idx = rate_lowest_index(sband, sta);
/* HACK */
si = container_of(sta, struct sta_info, sta);
@@ -336,21 +367,22 @@ static void *rate_control_pid_alloc(struct ieee80211_hw *hw,
struct rc_pid_info *pinfo;
struct rc_pid_rateinfo *rinfo;
struct ieee80211_supported_band *sband;
- int i, j, tmp;
- bool s;
+ int i, max_rates = 0;
#ifdef CONFIG_MAC80211_DEBUGFS
struct rc_pid_debugfs_entries *de;
#endif
- sband = hw->wiphy->bands[hw->conf.channel->band];
-
pinfo = kmalloc(sizeof(*pinfo), GFP_ATOMIC);
if (!pinfo)
return NULL;
- /* We can safely assume that sband won't change unless we get
- * reinitialized. */
- rinfo = kmalloc(sizeof(*rinfo) * sband->n_bitrates, GFP_ATOMIC);
+ for (i = 0; i < IEEE80211_NUM_BANDS; i++) {
+ sband = hw->wiphy->bands[i];
+ if (sband && sband->n_bitrates > max_rates)
+ max_rates = sband->n_bitrates;
+ }
+
+ rinfo = kmalloc(sizeof(*rinfo) * max_rates, GFP_ATOMIC);
if (!rinfo) {
kfree(pinfo);
return NULL;
@@ -368,33 +400,6 @@ static void *rate_control_pid_alloc(struct ieee80211_hw *hw,
pinfo->rinfo = rinfo;
pinfo->oldrate = 0;
- /* Sort the rates. This is optimized for the most common case (i.e.
- * almost-sorted CCK+OFDM rates). Kind of bubble-sort with reversed
- * mapping too. */
- for (i = 0; i < sband->n_bitrates; i++) {
- rinfo[i].index = i;
- rinfo[i].rev_index = i;
- if (RC_PID_FAST_START)
- rinfo[i].diff = 0;
- else
- rinfo[i].diff = i * pinfo->norm_offset;
- }
- for (i = 1; i < sband->n_bitrates; i++) {
- s = 0;
- for (j = 0; j < sband->n_bitrates - i; j++)
- if (unlikely(sband->bitrates[rinfo[j].index].bitrate >
- sband->bitrates[rinfo[j + 1].index].bitrate)) {
- tmp = rinfo[j].index;
- rinfo[j].index = rinfo[j + 1].index;
- rinfo[j + 1].index = tmp;
- rinfo[rinfo[j].index].rev_index = j;
- rinfo[rinfo[j + 1].index].rev_index = j + 1;
- s = 1;
- }
- if (!s)
- break;
- }
-
#ifdef CONFIG_MAC80211_DEBUGFS
de = &pinfo->dentries;
de->target = debugfs_create_u32("target_pf", S_IRUSR | S_IWUSR,
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 3fb04a86444..63656266d56 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -772,7 +772,7 @@ ieee80211_tx_h_fragment(struct ieee80211_tx_data *tx)
hdrlen = ieee80211_hdrlen(hdr->frame_control);
/* internal error, why is TX_FRAGMENTED set? */
- if (WARN_ON(skb->len <= frag_threshold))
+ if (WARN_ON(skb->len + FCS_LEN <= frag_threshold))
return TX_DROP;
/*
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 2329c5f5055..cb3ad741ebf 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -275,6 +275,8 @@ config NF_CT_NETLINK
help
This option enables support for a netlink-based userspace interface
+endif # NF_CONNTRACK
+
# transparent proxy support
config NETFILTER_TPROXY
tristate "Transparent proxying support (EXPERIMENTAL)"
@@ -290,8 +292,6 @@ config NETFILTER_TPROXY
To compile it as a module, choose M here. If unsure, say N.
-endif # NF_CONNTRACK
-
config NETFILTER_XTABLES
tristate "Netfilter Xtables support (required for ip_tables)"
default m if NETFILTER_ADVANCED=n
@@ -837,6 +837,7 @@ config NETFILTER_XT_MATCH_SOCKET
depends on NETFILTER_TPROXY
depends on NETFILTER_XTABLES
depends on NETFILTER_ADVANCED
+ depends on !NF_CONNTRACK || NF_CONNTRACK
select NF_DEFRAG_IPV4
help
This option adds a `socket' match, which can be used to match
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 60aba45023f..77bfdfeb966 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -260,7 +260,10 @@ struct ip_vs_conn *ip_vs_ct_in_get
list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
if (cp->af == af &&
ip_vs_addr_equal(af, s_addr, &cp->caddr) &&
- ip_vs_addr_equal(af, d_addr, &cp->vaddr) &&
+ /* protocol should only be IPPROTO_IP if
+ * d_addr is a fwmark */
+ ip_vs_addr_equal(protocol == IPPROTO_IP ? AF_UNSPEC : af,
+ d_addr, &cp->vaddr) &&
s_port == cp->cport && d_port == cp->vport &&
cp->flags & IP_VS_CONN_F_TEMPLATE &&
protocol == cp->protocol) {
@@ -698,7 +701,9 @@ ip_vs_conn_new(int af, int proto, const union nf_inet_addr *caddr, __be16 cport,
cp->cport = cport;
ip_vs_addr_copy(af, &cp->vaddr, vaddr);
cp->vport = vport;
- ip_vs_addr_copy(af, &cp->daddr, daddr);
+ /* proto should only be IPPROTO_IP if d_addr is a fwmark */
+ ip_vs_addr_copy(proto == IPPROTO_IP ? AF_UNSPEC : af,
+ &cp->daddr, daddr);
cp->dport = dport;
cp->flags = flags;
spin_lock_init(&cp->lock);
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index cb3e031335e..8dddb17a947 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -278,7 +278,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
*/
if (svc->fwmark) {
union nf_inet_addr fwmark = {
- .all = { 0, 0, 0, htonl(svc->fwmark) }
+ .ip = htonl(svc->fwmark)
};
ct = ip_vs_ct_in_get(svc->af, IPPROTO_IP, &snet, 0,
@@ -306,7 +306,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
*/
if (svc->fwmark) {
union nf_inet_addr fwmark = {
- .all = { 0, 0, 0, htonl(svc->fwmark) }
+ .ip = htonl(svc->fwmark)
};
ct = ip_vs_conn_new(svc->af, IPPROTO_IP,
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index f13fc57e1ec..c523f0b8cee 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1186,28 +1186,6 @@ ctnetlink_change_conntrack(struct nf_conn *ct, struct nlattr *cda[])
return 0;
}
-static inline void
-ctnetlink_event_report(struct nf_conn *ct, u32 pid, int report)
-{
- unsigned int events = 0;
-
- if (test_bit(IPS_EXPECTED_BIT, &ct->status))
- events |= IPCT_RELATED;
- else
- events |= IPCT_NEW;
-
- nf_conntrack_event_report(IPCT_STATUS |
- IPCT_HELPER |
- IPCT_REFRESH |
- IPCT_PROTOINFO |
- IPCT_NATSEQADJ |
- IPCT_MARK |
- events,
- ct,
- pid,
- report);
-}
-
static struct nf_conn *
ctnetlink_create_conntrack(struct nlattr *cda[],
struct nf_conntrack_tuple *otuple,
@@ -1373,6 +1351,7 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb,
err = -ENOENT;
if (nlh->nlmsg_flags & NLM_F_CREATE) {
struct nf_conn *ct;
+ enum ip_conntrack_events events;
ct = ctnetlink_create_conntrack(cda, &otuple,
&rtuple, u3);
@@ -1383,9 +1362,18 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb,
err = 0;
nf_conntrack_get(&ct->ct_general);
spin_unlock_bh(&nf_conntrack_lock);
- ctnetlink_event_report(ct,
- NETLINK_CB(skb).pid,
- nlmsg_report(nlh));
+ if (test_bit(IPS_EXPECTED_BIT, &ct->status))
+ events = IPCT_RELATED;
+ else
+ events = IPCT_NEW;
+
+ nf_conntrack_event_report(IPCT_STATUS |
+ IPCT_HELPER |
+ IPCT_PROTOINFO |
+ IPCT_NATSEQADJ |
+ IPCT_MARK | events,
+ ct, NETLINK_CB(skb).pid,
+ nlmsg_report(nlh));
nf_ct_put(ct);
} else
spin_unlock_bh(&nf_conntrack_lock);
@@ -1404,9 +1392,13 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb,
if (err == 0) {
nf_conntrack_get(&ct->ct_general);
spin_unlock_bh(&nf_conntrack_lock);
- ctnetlink_event_report(ct,
- NETLINK_CB(skb).pid,
- nlmsg_report(nlh));
+ nf_conntrack_event_report(IPCT_STATUS |
+ IPCT_HELPER |
+ IPCT_PROTOINFO |
+ IPCT_NATSEQADJ |
+ IPCT_MARK,
+ ct, NETLINK_CB(skb).pid,
+ nlmsg_report(nlh));
nf_ct_put(ct);
} else
spin_unlock_bh(&nf_conntrack_lock);
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index 50dac8dbe7d..aee0d6bea30 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -22,6 +22,7 @@
#include <linux/netfilter/nfnetlink_conntrack.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_l4proto.h>
+#include <net/netfilter/nf_conntrack_ecache.h>
#include <net/netfilter/nf_log.h>
static DEFINE_RWLOCK(dccp_lock);
@@ -553,6 +554,9 @@ static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb,
ct->proto.dccp.state = new_state;
write_unlock_bh(&dccp_lock);
+ if (new_state != old_state)
+ nf_conntrack_event_cache(IPCT_PROTOINFO, ct);
+
dn = dccp_pernet(net);
nf_ct_refresh_acct(ct, ctinfo, skb, dn->dccp_timeout[new_state]);
@@ -633,6 +637,8 @@ static int dccp_to_nlattr(struct sk_buff *skb, struct nlattr *nla,
if (!nest_parms)
goto nla_put_failure;
NLA_PUT_U8(skb, CTA_PROTOINFO_DCCP_STATE, ct->proto.dccp.state);
+ NLA_PUT_U8(skb, CTA_PROTOINFO_DCCP_ROLE,
+ ct->proto.dccp.role[IP_CT_DIR_ORIGINAL]);
nla_nest_end(skb, nest_parms);
read_unlock_bh(&dccp_lock);
return 0;
@@ -644,6 +650,7 @@ nla_put_failure:
static const struct nla_policy dccp_nla_policy[CTA_PROTOINFO_DCCP_MAX + 1] = {
[CTA_PROTOINFO_DCCP_STATE] = { .type = NLA_U8 },
+ [CTA_PROTOINFO_DCCP_ROLE] = { .type = NLA_U8 },
};
static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct)
@@ -661,11 +668,21 @@ static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct)
return err;
if (!tb[CTA_PROTOINFO_DCCP_STATE] ||
- nla_get_u8(tb[CTA_PROTOINFO_DCCP_STATE]) >= CT_DCCP_IGNORE)
+ !tb[CTA_PROTOINFO_DCCP_ROLE] ||
+ nla_get_u8(tb[CTA_PROTOINFO_DCCP_ROLE]) > CT_DCCP_ROLE_MAX ||
+ nla_get_u8(tb[CTA_PROTOINFO_DCCP_STATE]) >= CT_DCCP_IGNORE) {
return -EINVAL;
+ }
write_lock_bh(&dccp_lock);
ct->proto.dccp.state = nla_get_u8(tb[CTA_PROTOINFO_DCCP_STATE]);
+ if (nla_get_u8(tb[CTA_PROTOINFO_DCCP_ROLE]) == CT_DCCP_ROLE_CLIENT) {
+ ct->proto.dccp.role[IP_CT_DIR_ORIGINAL] = CT_DCCP_ROLE_CLIENT;
+ ct->proto.dccp.role[IP_CT_DIR_REPLY] = CT_DCCP_ROLE_SERVER;
+ } else {
+ ct->proto.dccp.role[IP_CT_DIR_ORIGINAL] = CT_DCCP_ROLE_SERVER;
+ ct->proto.dccp.role[IP_CT_DIR_REPLY] = CT_DCCP_ROLE_CLIENT;
+ }
write_unlock_bh(&dccp_lock);
return 0;
}
@@ -777,6 +794,7 @@ static struct nf_conntrack_l4proto dccp_proto6 __read_mostly = {
.print_conntrack = dccp_print_conntrack,
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
.to_nlattr = dccp_to_nlattr,
+ .nlattr_size = dccp_nlattr_size,
.from_nlattr = nlattr_to_dccp,
.tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
.nlattr_tuple_size = nf_ct_port_nlattr_tuple_size,
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index b5ccf2b4b2e..97a6e93d742 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -634,6 +634,14 @@ static bool tcp_in_window(const struct nf_conn *ct,
sender->td_end = end;
sender->flags |= IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED;
}
+ if (tcph->ack) {
+ if (!(sender->flags & IP_CT_TCP_FLAG_MAXACK_SET)) {
+ sender->td_maxack = ack;
+ sender->flags |= IP_CT_TCP_FLAG_MAXACK_SET;
+ } else if (after(ack, sender->td_maxack))
+ sender->td_maxack = ack;
+ }
+
/*
* Update receiver data.
*/
@@ -919,6 +927,16 @@ static int tcp_packet(struct nf_conn *ct,
return -NF_ACCEPT;
case TCP_CONNTRACK_CLOSE:
if (index == TCP_RST_SET
+ && (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET)
+ && before(ntohl(th->seq), ct->proto.tcp.seen[!dir].td_maxack)) {
+ /* Invalid RST */
+ write_unlock_bh(&tcp_lock);
+ if (LOG_INVALID(net, IPPROTO_TCP))
+ nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
+ "nf_ct_tcp: invalid RST ");
+ return -NF_ACCEPT;
+ }
+ if (index == TCP_RST_SET
&& ((test_bit(IPS_SEEN_REPLY_BIT, &ct->status)
&& ct->proto.tcp.last_index == TCP_SYN_SET)
|| (!test_bit(IPS_ASSURED_BIT, &ct->status)
diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c
index 4614696c1b8..0badedc542d 100644
--- a/net/netfilter/nf_conntrack_proto_udplite.c
+++ b/net/netfilter/nf_conntrack_proto_udplite.c
@@ -204,6 +204,7 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 __read_mostly =
.error = udplite_error,
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
.tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
+ .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size,
.nlattr_to_tuple = nf_ct_port_nlattr_to_tuple,
.nla_policy = nf_ct_port_nla_policy,
#endif
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index fd326ac27ec..66a6dd5c519 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -581,6 +581,12 @@ nfulnl_log_packet(u_int8_t pf,
+ nla_total_size(sizeof(struct nfulnl_msg_packet_hw))
+ nla_total_size(sizeof(struct nfulnl_msg_packet_timestamp));
+ if (in && skb_mac_header_was_set(skb)) {
+ size += nla_total_size(skb->dev->hard_header_len)
+ + nla_total_size(sizeof(u_int16_t)) /* hwtype */
+ + nla_total_size(sizeof(u_int16_t)); /* hwlen */
+ }
+
spin_lock_bh(&inst->lock);
if (inst->flags & NFULNL_CFG_F_SEQ)
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 509a95621f9..150e5cf62f8 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -625,20 +625,6 @@ void xt_free_table_info(struct xt_table_info *info)
}
EXPORT_SYMBOL(xt_free_table_info);
-void xt_table_entry_swap_rcu(struct xt_table_info *oldinfo,
- struct xt_table_info *newinfo)
-{
- unsigned int cpu;
-
- for_each_possible_cpu(cpu) {
- void *p = oldinfo->entries[cpu];
- rcu_assign_pointer(oldinfo->entries[cpu], newinfo->entries[cpu]);
- newinfo->entries[cpu] = p;
- }
-
-}
-EXPORT_SYMBOL_GPL(xt_table_entry_swap_rcu);
-
/* Find table by name, grabs mutex & ref. Returns ERR_PTR() on error. */
struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af,
const char *name)
@@ -676,32 +662,43 @@ void xt_compat_unlock(u_int8_t af)
EXPORT_SYMBOL_GPL(xt_compat_unlock);
#endif
+DEFINE_PER_CPU(struct xt_info_lock, xt_info_locks);
+EXPORT_PER_CPU_SYMBOL_GPL(xt_info_locks);
+
+
struct xt_table_info *
xt_replace_table(struct xt_table *table,
unsigned int num_counters,
struct xt_table_info *newinfo,
int *error)
{
- struct xt_table_info *oldinfo, *private;
+ struct xt_table_info *private;
/* Do the substitution. */
- mutex_lock(&table->lock);
+ local_bh_disable();
private = table->private;
+
/* Check inside lock: is the old number correct? */
if (num_counters != private->number) {
duprintf("num_counters != table->private->number (%u/%u)\n",
num_counters, private->number);
- mutex_unlock(&table->lock);
+ local_bh_enable();
*error = -EAGAIN;
return NULL;
}
- oldinfo = private;
- rcu_assign_pointer(table->private, newinfo);
- newinfo->initial_entries = oldinfo->initial_entries;
- mutex_unlock(&table->lock);
- synchronize_net();
- return oldinfo;
+ table->private = newinfo;
+ newinfo->initial_entries = private->initial_entries;
+
+ /*
+ * Even though table entries have now been swapped, other CPU's
+ * may still be using the old entries. This is okay, because
+ * resynchronization happens because of the locking done
+ * during the get_counters() routine.
+ */
+ local_bh_enable();
+
+ return private;
}
EXPORT_SYMBOL_GPL(xt_replace_table);
@@ -734,7 +731,6 @@ struct xt_table *xt_register_table(struct net *net, struct xt_table *table,
/* Simplifies replace_table code. */
table->private = bootstrap;
- mutex_init(&table->lock);
if (!xt_replace_table(table, 0, newinfo, &ret))
goto unlock;
@@ -1147,7 +1143,14 @@ static struct pernet_operations xt_net_ops = {
static int __init xt_init(void)
{
- int i, rv;
+ unsigned int i;
+ int rv;
+
+ for_each_possible_cpu(i) {
+ struct xt_info_lock *lock = &per_cpu(xt_info_locks, i);
+ spin_lock_init(&lock->lock);
+ lock->readers = 0;
+ }
xt = kmalloc(sizeof(struct xt_af) * NFPROTO_NUMPROTO, GFP_KERNEL);
if (!xt)
diff --git a/net/netfilter/xt_cluster.c b/net/netfilter/xt_cluster.c
index 6c4847662b8..69a639f3540 100644
--- a/net/netfilter/xt_cluster.c
+++ b/net/netfilter/xt_cluster.c
@@ -135,7 +135,13 @@ static bool xt_cluster_mt_checkentry(const struct xt_mtchk_param *par)
{
struct xt_cluster_match_info *info = par->matchinfo;
- if (info->node_mask >= (1 << info->total_nodes)) {
+ if (info->total_nodes > XT_CLUSTER_NODES_MAX) {
+ printk(KERN_ERR "xt_cluster: you have exceeded the maximum "
+ "number of cluster nodes (%u > %u)\n",
+ info->total_nodes, XT_CLUSTER_NODES_MAX);
+ return false;
+ }
+ if (info->node_mask >= (1ULL << info->total_nodes)) {
printk(KERN_ERR "xt_cluster: this node mask cannot be "
"higher than the total number of nodes\n");
return false;
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index a5b5369c30f..219dcdbe388 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -926,7 +926,7 @@ static int dl_seq_show(struct seq_file *s, void *v)
if (!hlist_empty(&htable->hash[*bucket])) {
hlist_for_each_entry(ent, pos, &htable->hash[*bucket], node)
if (dl_seq_real_show(ent, htable->family, s))
- return 1;
+ return -1;
}
return 0;
}
diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c
index 791e030ea90..eb0ceb84652 100644
--- a/net/netfilter/xt_recent.c
+++ b/net/netfilter/xt_recent.c
@@ -474,7 +474,7 @@ static ssize_t recent_old_proc_write(struct file *file,
struct recent_table *t = pde->data;
struct recent_entry *e;
char buf[sizeof("+255.255.255.255")], *c = buf;
- __be32 addr;
+ union nf_inet_addr addr = {};
int add;
if (size > sizeof(buf))
@@ -506,14 +506,13 @@ static ssize_t recent_old_proc_write(struct file *file,
add = 1;
break;
}
- addr = in_aton(c);
+ addr.ip = in_aton(c);
spin_lock_bh(&recent_lock);
- e = recent_entry_lookup(t, (const void *)&addr, NFPROTO_IPV4, 0);
+ e = recent_entry_lookup(t, &addr, NFPROTO_IPV4, 0);
if (e == NULL) {
if (add)
- recent_entry_init(t, (const void *)&addr,
- NFPROTO_IPV4, 0);
+ recent_entry_init(t, &addr, NFPROTO_IPV4, 0);
} else {
if (add)
recent_entry_update(t, e);
diff --git a/net/rxrpc/ar-connection.c b/net/rxrpc/ar-connection.c
index 0f1218b8d28..67e38a05624 100644
--- a/net/rxrpc/ar-connection.c
+++ b/net/rxrpc/ar-connection.c
@@ -343,9 +343,9 @@ static int rxrpc_connect_exclusive(struct rxrpc_sock *rx,
/* not yet present - create a candidate for a new connection
* and then redo the check */
conn = rxrpc_alloc_connection(gfp);
- if (IS_ERR(conn)) {
- _leave(" = %ld", PTR_ERR(conn));
- return PTR_ERR(conn);
+ if (!conn) {
+ _leave(" = -ENOMEM");
+ return -ENOMEM;
}
conn->trans = trans;
@@ -508,9 +508,9 @@ int rxrpc_connect_call(struct rxrpc_sock *rx,
/* not yet present - create a candidate for a new connection and then
* redo the check */
candidate = rxrpc_alloc_connection(gfp);
- if (IS_ERR(candidate)) {
- _leave(" = %ld", PTR_ERR(candidate));
- return PTR_ERR(candidate);
+ if (!candidate) {
+ _leave(" = -ENOMEM");
+ return -ENOMEM;
}
candidate->trans = trans;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 173fcc4b050..09cdcdfe7e9 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -135,6 +135,7 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
unsigned long cl;
unsigned long fh;
int err;
+ int tp_created = 0;
if (net != &init_net)
return -EINVAL;
@@ -254,7 +255,7 @@ replay:
}
tp->ops = tp_ops;
tp->protocol = protocol;
- tp->prio = nprio ? : tcf_auto_prio(*back);
+ tp->prio = nprio ? : TC_H_MAJ(tcf_auto_prio(*back));
tp->q = q;
tp->classify = tp_ops->classify;
tp->classid = parent;
@@ -266,10 +267,7 @@ replay:
goto errout;
}
- spin_lock_bh(root_lock);
- tp->next = *back;
- *back = tp;
- spin_unlock_bh(root_lock);
+ tp_created = 1;
} else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind))
goto errout;
@@ -296,8 +294,11 @@ replay:
switch (n->nlmsg_type) {
case RTM_NEWTFILTER:
err = -EEXIST;
- if (n->nlmsg_flags & NLM_F_EXCL)
+ if (n->nlmsg_flags & NLM_F_EXCL) {
+ if (tp_created)
+ tcf_destroy(tp);
goto errout;
+ }
break;
case RTM_DELTFILTER:
err = tp->ops->delete(tp, fh);
@@ -314,8 +315,18 @@ replay:
}
err = tp->ops->change(tp, cl, t->tcm_handle, tca, &fh);
- if (err == 0)
+ if (err == 0) {
+ if (tp_created) {
+ spin_lock_bh(root_lock);
+ tp->next = *back;
+ *back = tp;
+ spin_unlock_bh(root_lock);
+ }
tfilter_notify(skb, n, tp, fh, RTM_NEWTFILTER);
+ } else {
+ if (tp_created)
+ tcf_destroy(tp);
+ }
errout:
if (cl)
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index 91a3db4a76f..e5becb92b3e 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -104,8 +104,7 @@ static int cls_cgroup_classify(struct sk_buff *skb, struct tcf_proto *tp,
struct tcf_result *res)
{
struct cls_cgroup_head *head = tp->root;
- struct cgroup_cls_state *cs;
- int ret = 0;
+ u32 classid;
/*
* Due to the nature of the classifier it is required to ignore all
@@ -121,17 +120,18 @@ static int cls_cgroup_classify(struct sk_buff *skb, struct tcf_proto *tp,
return -1;
rcu_read_lock();
- cs = task_cls_state(current);
- if (cs->classid && tcf_em_tree_match(skb, &head->ematches, NULL)) {
- res->classid = cs->classid;
- res->class = 0;
- ret = tcf_exts_exec(skb, &head->exts, res);
- } else
- ret = -1;
-
+ classid = task_cls_state(current)->classid;
rcu_read_unlock();
- return ret;
+ if (!classid)
+ return -1;
+
+ if (!tcf_em_tree_match(skb, &head->ematches, NULL))
+ return -1;
+
+ res->classid = classid;
+ res->class = 0;
+ return tcf_exts_exec(skb, &head->exts, res);
}
static unsigned long cls_cgroup_get(struct tcf_proto *tp, u32 handle)
@@ -167,6 +167,9 @@ static int cls_cgroup_change(struct tcf_proto *tp, unsigned long base,
struct tcf_exts e;
int err;
+ if (!tca[TCA_OPTIONS])
+ return -EINVAL;
+
if (head == NULL) {
if (!handle)
return -EINVAL;
diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c
index 92cfc9d7e3b..69188e8358b 100644
--- a/net/sched/sch_fifo.c
+++ b/net/sched/sch_fifo.c
@@ -51,7 +51,7 @@ static int fifo_init(struct Qdisc *sch, struct nlattr *opt)
u32 limit = qdisc_dev(sch)->tx_queue_len ? : 1;
if (sch->ops == &bfifo_qdisc_ops)
- limit *= qdisc_dev(sch)->mtu;
+ limit *= psched_mtu(qdisc_dev(sch));
q->limit = limit;
} else {
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index ec697cebb63..3b641829723 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -303,6 +303,8 @@ restart:
switch (teql_resolve(skb, skb_res, slave)) {
case 0:
if (__netif_tx_trylock(slave_txq)) {
+ unsigned int length = qdisc_pkt_len(skb);
+
if (!netif_tx_queue_stopped(slave_txq) &&
!netif_tx_queue_frozen(slave_txq) &&
slave_ops->ndo_start_xmit(skb, slave) == 0) {
@@ -310,8 +312,7 @@ restart:
master->slaves = NEXT_SLAVE(q);
netif_wake_queue(dev);
master->stats.tx_packets++;
- master->stats.tx_bytes +=
- qdisc_pkt_len(skb);
+ master->stats.tx_bytes += length;
return 0;
}
__netif_tx_unlock(slave_txq);
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index af3198814c1..9d504234af4 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -345,6 +345,7 @@ static void svc_sock_setbufsize(struct socket *sock, unsigned int snd,
lock_sock(sock->sk);
sock->sk->sk_sndbuf = snd * 2;
sock->sk->sk_rcvbuf = rcv * 2;
+ sock->sk->sk_userlocks |= SOCK_SNDBUF_LOCK|SOCK_RCVBUF_LOCK;
release_sock(sock->sk);
#endif
}
@@ -796,6 +797,23 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
test_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags),
test_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags));
+ if (test_and_clear_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags))
+ /* sndbuf needs to have room for one request
+ * per thread, otherwise we can stall even when the
+ * network isn't a bottleneck.
+ *
+ * We count all threads rather than threads in a
+ * particular pool, which provides an upper bound
+ * on the number of threads which will access the socket.
+ *
+ * rcvbuf just needs to be able to hold a few requests.
+ * Normally they will be removed from the queue
+ * as soon a a complete request arrives.
+ */
+ svc_sock_setbufsize(svsk->sk_sock,
+ (serv->sv_nrthreads+3) * serv->sv_max_mesg,
+ 3 * serv->sv_max_mesg);
+
clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
/* Receive data. If we haven't got the record length yet, get
@@ -1043,6 +1061,15 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv)
tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF;
+ /* initialise setting must have enough space to
+ * receive and respond to one request.
+ * svc_tcp_recvfrom will re-adjust if necessary
+ */
+ svc_sock_setbufsize(svsk->sk_sock,
+ 3 * svsk->sk_xprt.xpt_server->sv_max_mesg,
+ 3 * svsk->sk_xprt.xpt_server->sv_max_mesg);
+
+ set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
if (sk->sk_state != TCP_ESTABLISHED)
set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
@@ -1112,14 +1139,8 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
/* Initialize the socket */
if (sock->type == SOCK_DGRAM)
svc_udp_init(svsk, serv);
- else {
- /* initialise setting must have enough space to
- * receive and respond to one request.
- */
- svc_sock_setbufsize(svsk->sk_sock, 4 * serv->sv_max_mesg,
- 4 * serv->sv_max_mesg);
+ else
svc_tcp_init(svsk, serv);
- }
dprintk("svc: svc_setup_socket created %p (inet %p)\n",
svsk, svsk->sk_sk);
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index a0bfe53f162..06ca058572f 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -672,10 +672,8 @@ xprt_init_autodisconnect(unsigned long data)
if (test_and_set_bit(XPRT_LOCKED, &xprt->state))
goto out_abort;
spin_unlock(&xprt->transport_lock);
- if (xprt_connecting(xprt))
- xprt_release_write(xprt, NULL);
- else
- queue_work(rpciod_workqueue, &xprt->task_cleanup);
+ set_bit(XPRT_CONNECTION_CLOSE, &xprt->state);
+ queue_work(rpciod_workqueue, &xprt->task_cleanup);
return;
out_abort:
spin_unlock(&xprt->transport_lock);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 629a28764da..42a6f9f2028 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -265,7 +265,7 @@ static int fast_reg_read_chunks(struct svcxprt_rdma *xprt,
frmr->page_list->page_list[page_no] =
ib_dma_map_single(xprt->sc_cm_id->device,
page_address(rqstp->rq_arg.pages[page_no]),
- PAGE_SIZE, DMA_TO_DEVICE);
+ PAGE_SIZE, DMA_FROM_DEVICE);
if (ib_dma_mapping_error(xprt->sc_cm_id->device,
frmr->page_list->page_list[page_no]))
goto fatal_err;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 6c26a675435..f11be72a1a8 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -128,7 +128,8 @@ static int fast_reg_xdr(struct svcxprt_rdma *xprt,
page_bytes -= sge_bytes;
frmr->page_list->page_list[page_no] =
- ib_dma_map_page(xprt->sc_cm_id->device, page, 0,
+ ib_dma_map_single(xprt->sc_cm_id->device,
+ page_address(page),
PAGE_SIZE, DMA_TO_DEVICE);
if (ib_dma_mapping_error(xprt->sc_cm_id->device,
frmr->page_list->page_list[page_no]))
@@ -183,6 +184,7 @@ static int fast_reg_xdr(struct svcxprt_rdma *xprt,
fatal_err:
printk("svcrdma: Error fast registering memory for xprt %p\n", xprt);
+ vec->frmr = NULL;
svc_rdma_put_frmr(xprt, frmr);
return -EIO;
}
@@ -516,6 +518,7 @@ static int send_reply(struct svcxprt_rdma *rdma,
"svcrdma: could not post a receive buffer, err=%d."
"Closing transport %p.\n", ret, rdma);
set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags);
+ svc_rdma_put_frmr(rdma, vec->frmr);
svc_rdma_put_context(ctxt, 0);
return -ENOTCONN;
}
@@ -530,18 +533,17 @@ static int send_reply(struct svcxprt_rdma *rdma,
clear_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags);
/* Prepare the SGE for the RPCRDMA Header */
+ ctxt->sge[0].lkey = rdma->sc_dma_lkey;
+ ctxt->sge[0].length = svc_rdma_xdr_get_reply_hdr_len(rdma_resp);
ctxt->sge[0].addr =
- ib_dma_map_page(rdma->sc_cm_id->device,
- page, 0, PAGE_SIZE, DMA_TO_DEVICE);
+ ib_dma_map_single(rdma->sc_cm_id->device, page_address(page),
+ ctxt->sge[0].length, DMA_TO_DEVICE);
if (ib_dma_mapping_error(rdma->sc_cm_id->device, ctxt->sge[0].addr))
goto err;
atomic_inc(&rdma->sc_dma_used);
ctxt->direction = DMA_TO_DEVICE;
- ctxt->sge[0].length = svc_rdma_xdr_get_reply_hdr_len(rdma_resp);
- ctxt->sge[0].lkey = rdma->sc_dma_lkey;
-
/* Determine how many of our SGE are to be transmitted */
for (sge_no = 1; byte_count && sge_no < vec->count; sge_no++) {
sge_bytes = min_t(size_t, vec->sge[sge_no].iov_len, byte_count);
@@ -606,6 +608,7 @@ static int send_reply(struct svcxprt_rdma *rdma,
return 0;
err:
+ svc_rdma_unmap_dma(ctxt);
svc_rdma_put_frmr(rdma, vec->frmr);
svc_rdma_put_context(ctxt, 1);
return -EIO;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 3d810e7df3f..5151f9f6c57 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -500,8 +500,8 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt)
BUG_ON(sge_no >= xprt->sc_max_sge);
page = svc_rdma_get_page();
ctxt->pages[sge_no] = page;
- pa = ib_dma_map_page(xprt->sc_cm_id->device,
- page, 0, PAGE_SIZE,
+ pa = ib_dma_map_single(xprt->sc_cm_id->device,
+ page_address(page), PAGE_SIZE,
DMA_FROM_DEVICE);
if (ib_dma_mapping_error(xprt->sc_cm_id->device, pa))
goto err_put_ctxt;
@@ -520,8 +520,9 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt)
svc_xprt_get(&xprt->sc_xprt);
ret = ib_post_recv(xprt->sc_qp, &recv_wr, &bad_recv_wr);
if (ret) {
- svc_xprt_put(&xprt->sc_xprt);
+ svc_rdma_unmap_dma(ctxt);
svc_rdma_put_context(ctxt, 1);
+ svc_xprt_put(&xprt->sc_xprt);
}
return ret;
@@ -1314,8 +1315,8 @@ void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp,
length = svc_rdma_xdr_encode_error(xprt, rmsgp, err, va);
/* Prepare SGE for local address */
- sge.addr = ib_dma_map_page(xprt->sc_cm_id->device,
- p, 0, PAGE_SIZE, DMA_FROM_DEVICE);
+ sge.addr = ib_dma_map_single(xprt->sc_cm_id->device,
+ page_address(p), PAGE_SIZE, DMA_FROM_DEVICE);
if (ib_dma_mapping_error(xprt->sc_cm_id->device, sge.addr)) {
put_page(p);
return;
@@ -1342,7 +1343,7 @@ void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp,
if (ret) {
dprintk("svcrdma: Error %d posting send for protocol error\n",
ret);
- ib_dma_unmap_page(xprt->sc_cm_id->device,
+ ib_dma_unmap_single(xprt->sc_cm_id->device,
sge.addr, PAGE_SIZE,
DMA_FROM_DEVICE);
svc_rdma_put_context(ctxt, 1);
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 3b21e0cc5e6..465aafc2007 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -1495,7 +1495,8 @@ rpcrdma_register_frmr_external(struct rpcrdma_mr_seg *seg,
frmr_wr.wr.fast_reg.page_shift = PAGE_SHIFT;
frmr_wr.wr.fast_reg.length = i << PAGE_SHIFT;
frmr_wr.wr.fast_reg.access_flags = (writing ?
- IB_ACCESS_REMOTE_WRITE : IB_ACCESS_REMOTE_READ);
+ IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE :
+ IB_ACCESS_REMOTE_READ);
frmr_wr.wr.fast_reg.rkey = seg1->mr_chunk.rl_mw->r.frmr.fr_mr->rkey;
DECR_CQCOUNT(&r_xprt->rx_ep);
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index d40ff50887a..e1859614601 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -807,6 +807,9 @@ static void xs_reset_transport(struct sock_xprt *transport)
*
* This is used when all requests are complete; ie, no DRC state remains
* on the server we want to save.
+ *
+ * The caller _must_ be holding XPRT_LOCKED in order to avoid issues with
+ * xs_reset_transport() zeroing the socket from underneath a writer.
*/
static void xs_close(struct rpc_xprt *xprt)
{
@@ -824,6 +827,14 @@ static void xs_close(struct rpc_xprt *xprt)
xprt_disconnect_done(xprt);
}
+static void xs_tcp_close(struct rpc_xprt *xprt)
+{
+ if (test_and_clear_bit(XPRT_CONNECTION_CLOSE, &xprt->state))
+ xs_close(xprt);
+ else
+ xs_tcp_shutdown(xprt);
+}
+
/**
* xs_destroy - prepare to shutdown a transport
* @xprt: doomed transport
@@ -1772,6 +1783,15 @@ static void xs_tcp_setup_socket(struct rpc_xprt *xprt,
xprt, -status, xprt_connected(xprt),
sock->sk->sk_state);
switch (status) {
+ default:
+ printk("%s: connect returned unhandled error %d\n",
+ __func__, status);
+ case -EADDRNOTAVAIL:
+ /* We're probably in TIME_WAIT. Get rid of existing socket,
+ * and retry
+ */
+ set_bit(XPRT_CONNECTION_CLOSE, &xprt->state);
+ xprt_force_disconnect(xprt);
case -ECONNREFUSED:
case -ECONNRESET:
case -ENETUNREACH:
@@ -1782,10 +1802,6 @@ static void xs_tcp_setup_socket(struct rpc_xprt *xprt,
xprt_clear_connecting(xprt);
return;
}
- /* get rid of existing socket, and retry */
- xs_tcp_shutdown(xprt);
- printk("%s: connect returned unhandled error %d\n",
- __func__, status);
out_eagain:
status = -EAGAIN;
out:
@@ -1994,7 +2010,7 @@ static struct rpc_xprt_ops xs_tcp_ops = {
.buf_free = rpc_free,
.send_request = xs_tcp_send_request,
.set_retrans_timeout = xprt_set_retrans_timeout_def,
- .close = xs_tcp_shutdown,
+ .close = xs_tcp_close,
.destroy = xs_destroy,
.print_stats = xs_tcp_print_stats,
};
diff --git a/net/wimax/op-msg.c b/net/wimax/op-msg.c
index 5d149c1b5f0..9ad4d893a56 100644
--- a/net/wimax/op-msg.c
+++ b/net/wimax/op-msg.c
@@ -149,7 +149,8 @@ struct sk_buff *wimax_msg_alloc(struct wimax_dev *wimax_dev,
}
result = nla_put(skb, WIMAX_GNL_MSG_DATA, size, msg);
if (result < 0) {
- dev_err(dev, "no memory to add payload in attribute\n");
+ dev_err(dev, "no memory to add payload (msg %p size %zu) in "
+ "attribute: %d\n", msg, size, result);
goto error_nla_put;
}
genlmsg_end(skb, genl_msg);
@@ -299,10 +300,10 @@ int wimax_msg(struct wimax_dev *wimax_dev, const char *pipe_name,
struct sk_buff *skb;
skb = wimax_msg_alloc(wimax_dev, pipe_name, buf, size, gfp_flags);
- if (skb == NULL)
- goto error_msg_new;
- result = wimax_msg_send(wimax_dev, skb);
-error_msg_new:
+ if (IS_ERR(skb))
+ result = PTR_ERR(skb);
+ else
+ result = wimax_msg_send(wimax_dev, skb);
return result;
}
EXPORT_SYMBOL_GPL(wimax_msg);
diff --git a/net/wimax/stack.c b/net/wimax/stack.c
index a0ee76b5251..933e1422b09 100644
--- a/net/wimax/stack.c
+++ b/net/wimax/stack.c
@@ -338,8 +338,21 @@ out:
*/
void wimax_state_change(struct wimax_dev *wimax_dev, enum wimax_st new_state)
{
+ /*
+ * A driver cannot take the wimax_dev out of the
+ * __WIMAX_ST_NULL state unless by calling wimax_dev_add(). If
+ * the wimax_dev's state is still NULL, we ignore any request
+ * to change its state because it means it hasn't been yet
+ * registered.
+ *
+ * There is no need to complain about it, as routines that
+ * call this might be shared from different code paths that
+ * are called before or after wimax_dev_add() has done its
+ * job.
+ */
mutex_lock(&wimax_dev->mutex);
- __wimax_state_change(wimax_dev, new_state);
+ if (wimax_dev->state > __WIMAX_ST_NULL)
+ __wimax_state_change(wimax_dev, new_state);
mutex_unlock(&wimax_dev->mutex);
return;
}
@@ -376,7 +389,7 @@ EXPORT_SYMBOL_GPL(wimax_state_get);
void wimax_dev_init(struct wimax_dev *wimax_dev)
{
INIT_LIST_HEAD(&wimax_dev->id_table_node);
- __wimax_state_set(wimax_dev, WIMAX_ST_UNINITIALIZED);
+ __wimax_state_set(wimax_dev, __WIMAX_ST_NULL);
mutex_init(&wimax_dev->mutex);
mutex_init(&wimax_dev->mutex_reset);
}
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 6c1993d9990..487cb627ddb 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -907,6 +907,7 @@ EXPORT_SYMBOL(freq_reg_info);
int freq_reg_info(struct wiphy *wiphy, u32 center_freq, u32 *bandwidth,
const struct ieee80211_reg_rule **reg_rule)
{
+ assert_cfg80211_lock();
return freq_reg_info_regd(wiphy, center_freq,
bandwidth, reg_rule, NULL);
}
@@ -1133,7 +1134,8 @@ static bool reg_is_world_roaming(struct wiphy *wiphy)
if (is_world_regdom(cfg80211_regdomain->alpha2) ||
(wiphy->regd && is_world_regdom(wiphy->regd->alpha2)))
return true;
- if (last_request->initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE &&
+ if (last_request &&
+ last_request->initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE &&
wiphy->custom_regulatory)
return true;
return false;
@@ -1142,6 +1144,12 @@ static bool reg_is_world_roaming(struct wiphy *wiphy)
/* Reap the advantages of previously found beacons */
static void reg_process_beacons(struct wiphy *wiphy)
{
+ /*
+ * Means we are just firing up cfg80211, so no beacons would
+ * have been processed yet.
+ */
+ if (!last_request)
+ return;
if (!reg_is_world_roaming(wiphy))
return;
wiphy_update_beacon_reg(wiphy);
@@ -1176,6 +1184,8 @@ static void handle_channel_custom(struct wiphy *wiphy,
struct ieee80211_supported_band *sband;
struct ieee80211_channel *chan;
+ assert_cfg80211_lock();
+
sband = wiphy->bands[band];
BUG_ON(chan_idx >= sband->n_channels);
chan = &sband->channels[chan_idx];
@@ -1214,10 +1224,13 @@ void wiphy_apply_custom_regulatory(struct wiphy *wiphy,
const struct ieee80211_regdomain *regd)
{
enum ieee80211_band band;
+
+ mutex_lock(&cfg80211_mutex);
for (band = 0; band < IEEE80211_NUM_BANDS; band++) {
if (wiphy->bands[band])
handle_band_custom(wiphy, band, regd);
}
+ mutex_unlock(&cfg80211_mutex);
}
EXPORT_SYMBOL(wiphy_apply_custom_regulatory);
@@ -1423,7 +1436,7 @@ new_request:
return call_crda(last_request->alpha2);
}
-/* This currently only processes user and driver regulatory hints */
+/* This processes *all* regulatory hints */
static void reg_process_hint(struct regulatory_request *reg_request)
{
int r = 0;
@@ -1538,6 +1551,13 @@ static int regulatory_hint_core(const char *alpha2)
queue_regulatory_request(request);
+ /*
+ * This ensures last_request is populated once modules
+ * come swinging in and calling regulatory hints and
+ * wiphy_apply_custom_regulatory().
+ */
+ flush_scheduled_work();
+
return 0;
}
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 2ae65b39b52..1f260c40b6c 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -395,6 +395,7 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev,
memcpy(ies, res->pub.information_elements, ielen);
found->ies_allocated = true;
found->pub.information_elements = ies;
+ found->pub.len_information_elements = ielen;
}
}
}
diff --git a/net/wireless/wext.c b/net/wireless/wext.c
index cb6a5bb85d8..0e59f9ae9b8 100644
--- a/net/wireless/wext.c
+++ b/net/wireless/wext.c
@@ -786,6 +786,13 @@ static int ioctl_standard_iw_point(struct iw_point *iwp, unsigned int cmd,
err = -EFAULT;
goto out;
}
+
+ if (cmd == SIOCSIWENCODEEXT) {
+ struct iw_encode_ext *ee = (void *) extra;
+
+ if (iwp->length < sizeof(*ee) + ee->key_len)
+ return -EFAULT;
+ }
}
err = handler(dev, info, (union iwreq_data *) iwp, extra);
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 82271720d97..5f1f86565f1 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -794,7 +794,7 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr,
{
static xfrm_address_t saddr_wildcard = { };
struct net *net = xp_net(pol);
- unsigned int h;
+ unsigned int h, h_wildcard;
struct hlist_node *entry;
struct xfrm_state *x, *x0, *to_put;
int acquire_in_progress = 0;
@@ -819,8 +819,8 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr,
if (best)
goto found;
- h = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, family);
- hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) {
+ h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, family);
+ hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h_wildcard, bydst) {
if (x->props.family == family &&
x->props.reqid == tmpl->reqid &&
!(x->props.flags & XFRM_STATE_WILDRECV) &&