summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/8021q/vlan_core.c14
-rw-r--r--net/8021q/vlan_dev.c3
-rw-r--r--net/9p/client.c7
-rw-r--r--net/9p/trans_rdma.c29
-rw-r--r--net/9p/trans_virtio.c3
-rw-r--r--net/Kconfig3
-rw-r--r--net/Makefile1
-rw-r--r--net/atm/br2684.c12
-rw-r--r--net/ax25/ax25_ds_timer.c2
-rw-r--r--net/bluetooth/l2cap.c62
-rw-r--r--net/bluetooth/rfcomm/sock.c4
-rw-r--r--net/bridge/br_netfilter.c8
-rw-r--r--net/caif/caif_socket.c21
-rw-r--r--net/caif/cfpkt_skbuff.c2
-rw-r--r--net/caif/cfrfml.c2
-rw-r--r--net/can/bcm.c41
-rw-r--r--net/core/dev.c20
-rw-r--r--net/core/gen_estimator.c12
-rw-r--r--net/core/iovec.c5
-rw-r--r--net/core/skbuff.c6
-rw-r--r--net/core/sock.c8
-rw-r--r--net/core/stream.c8
-rw-r--r--net/dns_resolver/Kconfig27
-rw-r--r--net/dns_resolver/Makefile7
-rw-r--r--net/dns_resolver/dns_key.c293
-rw-r--r--net/dns_resolver/dns_query.c165
-rw-r--r--net/dns_resolver/internal.h44
-rw-r--r--net/dsa/Kconfig2
-rw-r--r--net/ipv4/Kconfig5
-rw-r--r--net/ipv4/datagram.c5
-rw-r--r--net/ipv4/fib_frontend.c15
-rw-r--r--net/ipv4/fib_trie.c8
-rw-r--r--net/ipv4/igmp.c12
-rw-r--r--net/ipv4/ip_gre.c8
-rw-r--r--net/ipv4/ip_output.c19
-rw-r--r--net/ipv4/ip_sockglue.c3
-rw-r--r--net/ipv4/netfilter/arp_tables.c5
-rw-r--r--net/ipv4/netfilter/ip_tables.c5
-rw-r--r--net/ipv4/netfilter/ipt_REJECT.c1
-rw-r--r--net/ipv4/netfilter/nf_defrag_ipv4.c4
-rw-r--r--net/ipv4/netfilter/nf_nat_snmp_basic.c6
-rw-r--r--net/ipv4/route.c9
-rw-r--r--net/ipv4/tcp.c41
-rw-r--r--net/ipv4/tcp_cong.c5
-rw-r--r--net/ipv4/tcp_input.c5
-rw-r--r--net/ipv4/tcp_timer.c32
-rw-r--r--net/ipv4/udp.c44
-rw-r--r--net/ipv4/xfrm4_policy.c2
-rw-r--r--net/ipv4/xfrm4_state.c33
-rw-r--r--net/ipv6/addrconf.c11
-rw-r--r--net/ipv6/addrlabel.c5
-rw-r--r--net/ipv6/datagram.c7
-rw-r--r--net/ipv6/ip6_output.c18
-rw-r--r--net/ipv6/netfilter/ip6_tables.c5
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c80
-rw-r--r--net/ipv6/reassembly.c71
-rw-r--r--net/ipv6/route.c34
-rw-r--r--net/ipv6/udp.c10
-rw-r--r--net/ipv6/xfrm6_state.c33
-rw-r--r--net/irda/af_irda.c4
-rw-r--r--net/irda/irlan/irlan_common.c2
-rw-r--r--net/irda/irlan/irlan_eth.c4
-rw-r--r--net/l2tp/l2tp_eth.c2
-rw-r--r--net/llc/af_llc.c3
-rw-r--r--net/llc/llc_station.c2
-rw-r--r--net/mac80211/rate.c2
-rw-r--r--net/netfilter/ipvs/ip_vs_core.c1
-rw-r--r--net/netfilter/ipvs/ip_vs_ftp.c9
-rw-r--r--net/netfilter/ipvs/ip_vs_xmit.c18
-rw-r--r--net/netfilter/nf_conntrack_extend.c4
-rw-r--r--net/netfilter/nf_conntrack_sip.c2
-rw-r--r--net/netfilter/nf_tproxy_core.c6
-rw-r--r--net/netlink/af_netlink.c78
-rw-r--r--net/phonet/pep.c3
-rw-r--r--net/rds/recv.c2
-rw-r--r--net/rds/tcp_connect.c4
-rw-r--r--net/rds/tcp_listen.c4
-rw-r--r--net/rds/tcp_recv.c4
-rw-r--r--net/rds/tcp_send.c4
-rw-r--r--net/rose/af_rose.c4
-rw-r--r--net/rxrpc/ar-internal.h16
-rw-r--r--net/sched/act_gact.c21
-rw-r--r--net/sched/act_mirred.c15
-rw-r--r--net/sched/act_nat.c22
-rw-r--r--net/sched/act_police.c21
-rw-r--r--net/sched/act_simple.c11
-rw-r--r--net/sched/act_skbedit.c11
-rw-r--r--net/sched/cls_u32.c2
-rw-r--r--net/sched/sch_api.c22
-rw-r--r--net/sched/sch_atm.c8
-rw-r--r--net/sched/sch_hfsc.c2
-rw-r--r--net/sched/sch_sfq.c14
-rw-r--r--net/sched/sch_tbf.c4
-rw-r--r--net/sched/sch_teql.c2
-rw-r--r--net/sctp/auth.c8
-rw-r--r--net/sctp/output.c1
-rw-r--r--net/sctp/sm_statefuns.c46
-rw-r--r--net/sctp/socket.c13
-rw-r--r--net/sunrpc/Kconfig9
-rw-r--r--net/sunrpc/auth.c162
-rw-r--r--net/sunrpc/auth_generic.c23
-rw-r--r--net/sunrpc/auth_gss/auth_gss.c38
-rw-r--r--net/sunrpc/auth_gss/gss_krb5_mech.c10
-rw-r--r--net/sunrpc/auth_gss/gss_spkm3_mech.c5
-rw-r--r--net/sunrpc/auth_null.c2
-rw-r--r--net/sunrpc/auth_unix.c21
-rw-r--r--net/sunrpc/cache.c8
-rw-r--r--net/sunrpc/clnt.c208
-rw-r--r--net/sunrpc/rpc_pipe.c20
-rw-r--r--net/sunrpc/sched.c104
-rw-r--r--net/sunrpc/sunrpc_syms.c16
-rw-r--r--net/sunrpc/xprt.c3
-rw-r--r--net/sunrpc/xprtrdma/rpc_rdma.c2
-rw-r--r--net/sunrpc/xprtrdma/verbs.c22
-rw-r--r--net/sunrpc/xprtsock.c82
-rw-r--r--net/unix/af_unix.c15
-rw-r--r--net/xfrm/xfrm_output.c2
-rw-r--r--net/xfrm/xfrm_policy.c5
-rw-r--r--net/xfrm/xfrm_state.c45
-rw-r--r--net/xfrm/xfrm_user.c4
120 files changed, 1700 insertions, 859 deletions
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 01ddb0472f8..0eb96f7e44b 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -24,8 +24,11 @@ int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp,
if (vlan_dev)
skb->dev = vlan_dev;
- else if (vlan_id)
- goto drop;
+ else if (vlan_id) {
+ if (!(skb->dev->flags & IFF_PROMISC))
+ goto drop;
+ skb->pkt_type = PACKET_OTHERHOST;
+ }
return (polling ? netif_receive_skb(skb) : netif_rx(skb));
@@ -102,8 +105,11 @@ vlan_gro_common(struct napi_struct *napi, struct vlan_group *grp,
if (vlan_dev)
skb->dev = vlan_dev;
- else if (vlan_id)
- goto drop;
+ else if (vlan_id) {
+ if (!(skb->dev->flags & IFF_PROMISC))
+ goto drop;
+ skb->pkt_type = PACKET_OTHERHOST;
+ }
for (p = napi->gro_list; p; p = p->next) {
NAPI_GRO_CB(p)->same_flow =
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 3d59c9bf8fe..3bccdd12a26 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -510,7 +510,8 @@ static int vlan_dev_open(struct net_device *dev)
if (vlan->flags & VLAN_FLAG_GVRP)
vlan_gvrp_request_join(dev);
- netif_carrier_on(dev);
+ if (netif_carrier_ok(real_dev))
+ netif_carrier_on(dev);
return 0;
clear_allmulti:
diff --git a/net/9p/client.c b/net/9p/client.c
index dc6f2f26d02..9eb72505308 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -331,8 +331,10 @@ static void p9_tag_cleanup(struct p9_client *c)
}
}
- if (c->tagpool)
+ if (c->tagpool) {
+ p9_idpool_put(0, c->tagpool); /* free reserved tag 0 */
p9_idpool_destroy(c->tagpool);
+ }
/* free requests associated with tags */
for (row = 0; row < (c->max_tag/P9_ROW_MAXTAG); row++) {
@@ -944,6 +946,7 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, int nwname, char **wnames,
int16_t nwqids, count;
err = 0;
+ wqids = NULL;
clnt = oldfid->clnt;
if (clone) {
fid = p9_fid_create(clnt);
@@ -994,9 +997,11 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, int nwname, char **wnames,
else
fid->qid = oldfid->qid;
+ kfree(wqids);
return fid;
clunk_fid:
+ kfree(wqids);
p9_client_clunk(fid);
fid = NULL;
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
index 0ea20c30466..17c5ba7551a 100644
--- a/net/9p/trans_rdma.c
+++ b/net/9p/trans_rdma.c
@@ -426,8 +426,10 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req)
/* Allocate an fcall for the reply */
rpl_context = kmalloc(sizeof *rpl_context, GFP_KERNEL);
- if (!rpl_context)
+ if (!rpl_context) {
+ err = -ENOMEM;
goto err_close;
+ }
/*
* If the request has a buffer, steal it, otherwise
@@ -445,8 +447,8 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req)
}
rpl_context->rc = req->rc;
if (!rpl_context->rc) {
- kfree(rpl_context);
- goto err_close;
+ err = -ENOMEM;
+ goto err_free2;
}
/*
@@ -458,11 +460,8 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req)
*/
if (atomic_inc_return(&rdma->rq_count) <= rdma->rq_depth) {
err = post_recv(client, rpl_context);
- if (err) {
- kfree(rpl_context->rc);
- kfree(rpl_context);
- goto err_close;
- }
+ if (err)
+ goto err_free1;
} else
atomic_dec(&rdma->rq_count);
@@ -471,8 +470,10 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req)
/* Post the request */
c = kmalloc(sizeof *c, GFP_KERNEL);
- if (!c)
- goto err_close;
+ if (!c) {
+ err = -ENOMEM;
+ goto err_free1;
+ }
c->req = req;
c->busa = ib_dma_map_single(rdma->cm_id->device,
@@ -499,9 +500,15 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req)
return ib_post_send(rdma->qp, &wr, &bad_wr);
error:
+ kfree(c);
+ kfree(rpl_context->rc);
+ kfree(rpl_context);
P9_DPRINTK(P9_DEBUG_ERROR, "EIO\n");
return -EIO;
-
+ err_free1:
+ kfree(rpl_context->rc);
+ err_free2:
+ kfree(rpl_context);
err_close:
spin_lock_irqsave(&rdma->req_lock, flags);
if (rdma->state < P9_RDMA_CLOSING) {
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index dcfbe99ff81..b88515936e4 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -329,7 +329,8 @@ p9_virtio_create(struct p9_client *client, const char *devname, char *args)
mutex_lock(&virtio_9p_lock);
list_for_each_entry(chan, &virtio_chan_list, chan_list) {
- if (!strncmp(devname, chan->tag, chan->tag_len)) {
+ if (!strncmp(devname, chan->tag, chan->tag_len) &&
+ strlen(devname) == chan->tag_len) {
if (!chan->inuse) {
chan->inuse = true;
found = 1;
diff --git a/net/Kconfig b/net/Kconfig
index e24fa0873f3..e926884c167 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -213,10 +213,11 @@ source "net/phonet/Kconfig"
source "net/ieee802154/Kconfig"
source "net/sched/Kconfig"
source "net/dcb/Kconfig"
+source "net/dns_resolver/Kconfig"
config RPS
boolean
- depends on SMP && SYSFS
+ depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS
default y
menu "Network testing"
diff --git a/net/Makefile b/net/Makefile
index 41d420070a3..ea60fbce9b1 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -67,3 +67,4 @@ ifeq ($(CONFIG_NET),y)
obj-$(CONFIG_SYSCTL) += sysctl_net.o
endif
obj-$(CONFIG_WIMAX) += wimax/
+obj-$(CONFIG_DNS_RESOLVER) += dns_resolver/
diff --git a/net/atm/br2684.c b/net/atm/br2684.c
index 651babdfab3..ad2b232a205 100644
--- a/net/atm/br2684.c
+++ b/net/atm/br2684.c
@@ -399,12 +399,6 @@ static void br2684_push(struct atm_vcc *atmvcc, struct sk_buff *skb)
unregister_netdev(net_dev);
free_netdev(net_dev);
}
- read_lock_irq(&devs_lock);
- if (list_empty(&br2684_devs)) {
- /* last br2684 device */
- unregister_atmdevice_notifier(&atm_dev_notifier);
- }
- read_unlock_irq(&devs_lock);
return;
}
@@ -675,7 +669,6 @@ static int br2684_create(void __user *arg)
if (list_empty(&br2684_devs)) {
/* 1st br2684 device */
- register_atmdevice_notifier(&atm_dev_notifier);
brdev->number = 1;
} else
brdev->number = BRPRIV(list_entry_brdev(br2684_devs.prev))->number + 1;
@@ -815,6 +808,7 @@ static int __init br2684_init(void)
return -ENOMEM;
#endif
register_atm_ioctl(&br2684_ioctl_ops);
+ register_atmdevice_notifier(&atm_dev_notifier);
return 0;
}
@@ -830,9 +824,7 @@ static void __exit br2684_exit(void)
#endif
- /* if not already empty */
- if (!list_empty(&br2684_devs))
- unregister_atmdevice_notifier(&atm_dev_notifier);
+ unregister_atmdevice_notifier(&atm_dev_notifier);
while (!list_empty(&br2684_devs)) {
net_dev = list_entry_brdev(br2684_devs.next);
diff --git a/net/ax25/ax25_ds_timer.c b/net/ax25/ax25_ds_timer.c
index 2ce79df0068..c7d81436213 100644
--- a/net/ax25/ax25_ds_timer.c
+++ b/net/ax25/ax25_ds_timer.c
@@ -112,8 +112,8 @@ void ax25_ds_heartbeat_expiry(ax25_cb *ax25)
if (sk) {
sock_hold(sk);
ax25_destroy_socket(ax25);
- sock_put(sk);
bh_unlock_sock(sk);
+ sock_put(sk);
} else
ax25_destroy_socket(ax25);
return;
diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c
index fadf26b4ed7..0b54b7dd840 100644
--- a/net/bluetooth/l2cap.c
+++ b/net/bluetooth/l2cap.c
@@ -1441,33 +1441,23 @@ static inline void l2cap_do_send(struct sock *sk, struct sk_buff *skb)
static void l2cap_streaming_send(struct sock *sk)
{
- struct sk_buff *skb, *tx_skb;
+ struct sk_buff *skb;
struct l2cap_pinfo *pi = l2cap_pi(sk);
u16 control, fcs;
- while ((skb = sk->sk_send_head)) {
- tx_skb = skb_clone(skb, GFP_ATOMIC);
-
- control = get_unaligned_le16(tx_skb->data + L2CAP_HDR_SIZE);
+ while ((skb = skb_dequeue(TX_QUEUE(sk)))) {
+ control = get_unaligned_le16(skb->data + L2CAP_HDR_SIZE);
control |= pi->next_tx_seq << L2CAP_CTRL_TXSEQ_SHIFT;
- put_unaligned_le16(control, tx_skb->data + L2CAP_HDR_SIZE);
+ put_unaligned_le16(control, skb->data + L2CAP_HDR_SIZE);
if (pi->fcs == L2CAP_FCS_CRC16) {
- fcs = crc16(0, (u8 *)tx_skb->data, tx_skb->len - 2);
- put_unaligned_le16(fcs, tx_skb->data + tx_skb->len - 2);
+ fcs = crc16(0, (u8 *)skb->data, skb->len - 2);
+ put_unaligned_le16(fcs, skb->data + skb->len - 2);
}
- l2cap_do_send(sk, tx_skb);
+ l2cap_do_send(sk, skb);
pi->next_tx_seq = (pi->next_tx_seq + 1) % 64;
-
- if (skb_queue_is_last(TX_QUEUE(sk), skb))
- sk->sk_send_head = NULL;
- else
- sk->sk_send_head = skb_queue_next(TX_QUEUE(sk), skb);
-
- skb = skb_dequeue(TX_QUEUE(sk));
- kfree_skb(skb);
}
}
@@ -1960,6 +1950,11 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __us
switch (optname) {
case L2CAP_OPTIONS:
+ if (sk->sk_state == BT_CONNECTED) {
+ err = -EINVAL;
+ break;
+ }
+
opts.imtu = l2cap_pi(sk)->imtu;
opts.omtu = l2cap_pi(sk)->omtu;
opts.flush_to = l2cap_pi(sk)->flush_to;
@@ -2771,10 +2766,10 @@ static int l2cap_parse_conf_rsp(struct sock *sk, void *rsp, int len, void *data,
case L2CAP_CONF_MTU:
if (val < L2CAP_DEFAULT_MIN_MTU) {
*result = L2CAP_CONF_UNACCEPT;
- pi->omtu = L2CAP_DEFAULT_MIN_MTU;
+ pi->imtu = L2CAP_DEFAULT_MIN_MTU;
} else
- pi->omtu = val;
- l2cap_add_conf_opt(&ptr, L2CAP_CONF_MTU, 2, pi->omtu);
+ pi->imtu = val;
+ l2cap_add_conf_opt(&ptr, L2CAP_CONF_MTU, 2, pi->imtu);
break;
case L2CAP_CONF_FLUSH_TO:
@@ -3071,6 +3066,17 @@ static inline int l2cap_connect_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hd
return 0;
}
+static inline void set_default_fcs(struct l2cap_pinfo *pi)
+{
+ /* FCS is enabled only in ERTM or streaming mode, if one or both
+ * sides request it.
+ */
+ if (pi->mode != L2CAP_MODE_ERTM && pi->mode != L2CAP_MODE_STREAMING)
+ pi->fcs = L2CAP_FCS_NONE;
+ else if (!(pi->conf_state & L2CAP_CONF_NO_FCS_RECV))
+ pi->fcs = L2CAP_FCS_CRC16;
+}
+
static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, u16 cmd_len, u8 *data)
{
struct l2cap_conf_req *req = (struct l2cap_conf_req *) data;
@@ -3088,14 +3094,8 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr
if (!sk)
return -ENOENT;
- if (sk->sk_state != BT_CONFIG) {
- struct l2cap_cmd_rej rej;
-
- rej.reason = cpu_to_le16(0x0002);
- l2cap_send_cmd(conn, cmd->ident, L2CAP_COMMAND_REJ,
- sizeof(rej), &rej);
+ if (sk->sk_state == BT_DISCONN)
goto unlock;
- }
/* Reject if config buffer is too small. */
len = cmd_len - sizeof(*req);
@@ -3135,9 +3135,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr
goto unlock;
if (l2cap_pi(sk)->conf_state & L2CAP_CONF_INPUT_DONE) {
- if (!(l2cap_pi(sk)->conf_state & L2CAP_CONF_NO_FCS_RECV) ||
- l2cap_pi(sk)->fcs != L2CAP_FCS_NONE)
- l2cap_pi(sk)->fcs = L2CAP_FCS_CRC16;
+ set_default_fcs(l2cap_pi(sk));
sk->sk_state = BT_CONNECTED;
@@ -3225,9 +3223,7 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hdr
l2cap_pi(sk)->conf_state |= L2CAP_CONF_INPUT_DONE;
if (l2cap_pi(sk)->conf_state & L2CAP_CONF_OUTPUT_DONE) {
- if (!(l2cap_pi(sk)->conf_state & L2CAP_CONF_NO_FCS_RECV) ||
- l2cap_pi(sk)->fcs != L2CAP_FCS_NONE)
- l2cap_pi(sk)->fcs = L2CAP_FCS_CRC16;
+ set_default_fcs(l2cap_pi(sk));
sk->sk_state = BT_CONNECTED;
l2cap_pi(sk)->next_tx_seq = 0;
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 44a62327595..194b3a04cfd 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -82,11 +82,14 @@ static void rfcomm_sk_data_ready(struct rfcomm_dlc *d, struct sk_buff *skb)
static void rfcomm_sk_state_change(struct rfcomm_dlc *d, int err)
{
struct sock *sk = d->owner, *parent;
+ unsigned long flags;
+
if (!sk)
return;
BT_DBG("dlc %p state %ld err %d", d, d->state, err);
+ local_irq_save(flags);
bh_lock_sock(sk);
if (err)
@@ -108,6 +111,7 @@ static void rfcomm_sk_state_change(struct rfcomm_dlc *d, int err)
}
bh_unlock_sock(sk);
+ local_irq_restore(flags);
if (parent && sock_flag(sk, SOCK_ZAPPED)) {
/* We have to drop DLC lock here, otherwise
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 2c911c0759c..137f23259a9 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -162,8 +162,8 @@ static inline struct nf_bridge_info *nf_bridge_unshare(struct sk_buff *skb)
if (tmp) {
memcpy(tmp, nf_bridge, sizeof(struct nf_bridge_info));
atomic_set(&tmp->use, 1);
- nf_bridge_put(nf_bridge);
}
+ nf_bridge_put(nf_bridge);
nf_bridge = tmp;
}
return nf_bridge;
@@ -761,9 +761,11 @@ static int br_nf_dev_queue_xmit(struct sk_buff *skb)
{
if (skb->nfct != NULL && skb->protocol == htons(ETH_P_IP) &&
skb->len + nf_bridge_mtu_reduction(skb) > skb->dev->mtu &&
- !skb_is_gso(skb))
+ !skb_is_gso(skb)) {
+ /* BUG: Should really parse the IP options here. */
+ memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
return ip_fragment(skb, br_dev_queue_push_xmit);
- else
+ } else
return br_dev_queue_push_xmit(skb);
}
#else
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 8ce90478611..4bf28f25f36 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -827,6 +827,7 @@ static int caif_connect(struct socket *sock, struct sockaddr *uaddr,
long timeo;
int err;
int ifindex, headroom, tailroom;
+ unsigned int mtu;
struct net_device *dev;
lock_sock(sk);
@@ -896,15 +897,23 @@ static int caif_connect(struct socket *sock, struct sockaddr *uaddr,
cf_sk->sk.sk_state = CAIF_DISCONNECTED;
goto out;
}
- dev = dev_get_by_index(sock_net(sk), ifindex);
+
+ err = -ENODEV;
+ rcu_read_lock();
+ dev = dev_get_by_index_rcu(sock_net(sk), ifindex);
+ if (!dev) {
+ rcu_read_unlock();
+ goto out;
+ }
cf_sk->headroom = LL_RESERVED_SPACE_EXTRA(dev, headroom);
+ mtu = dev->mtu;
+ rcu_read_unlock();
+
cf_sk->tailroom = tailroom;
- cf_sk->maxframe = dev->mtu - (headroom + tailroom);
- dev_put(dev);
+ cf_sk->maxframe = mtu - (headroom + tailroom);
if (cf_sk->maxframe < 1) {
- pr_warning("CAIF: %s(): CAIF Interface MTU too small (%d)\n",
- __func__, dev->mtu);
- err = -ENODEV;
+ pr_warning("CAIF: %s(): CAIF Interface MTU too small (%u)\n",
+ __func__, mtu);
goto out;
}
diff --git a/net/caif/cfpkt_skbuff.c b/net/caif/cfpkt_skbuff.c
index 01f238ff234..c49a6695793 100644
--- a/net/caif/cfpkt_skbuff.c
+++ b/net/caif/cfpkt_skbuff.c
@@ -9,7 +9,7 @@
#include <linux/hardirq.h>
#include <net/caif/cfpkt.h>
-#define PKT_PREFIX 16
+#define PKT_PREFIX 48
#define PKT_POSTFIX 2
#define PKT_LEN_WHEN_EXTENDING 128
#define PKT_ERROR(pkt, errmsg) do { \
diff --git a/net/caif/cfrfml.c b/net/caif/cfrfml.c
index eb1602022ac..9a699242d10 100644
--- a/net/caif/cfrfml.c
+++ b/net/caif/cfrfml.c
@@ -7,7 +7,7 @@
#include <linux/stddef.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
-#include <linux/unaligned/le_byteshift.h>
+#include <asm/unaligned.h>
#include <net/caif/caif_layer.h>
#include <net/caif/cfsrvl.h>
#include <net/caif/cfpkt.h>
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 9c65e9deb9c..08ffe9e4be2 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -60,6 +60,13 @@
#include <net/sock.h>
#include <net/net_namespace.h>
+/*
+ * To send multiple CAN frame content within TX_SETUP or to filter
+ * CAN messages with multiplex index within RX_SETUP, the number of
+ * different filters is limited to 256 due to the one byte index value.
+ */
+#define MAX_NFRAMES 256
+
/* use of last_frames[index].can_dlc */
#define RX_RECV 0x40 /* received data for this element */
#define RX_THR 0x80 /* element not been sent due to throttle feature */
@@ -89,16 +96,16 @@ struct bcm_op {
struct list_head list;
int ifindex;
canid_t can_id;
- int flags;
+ u32 flags;
unsigned long frames_abs, frames_filtered;
struct timeval ival1, ival2;
struct hrtimer timer, thrtimer;
struct tasklet_struct tsklet, thrtsklet;
ktime_t rx_stamp, kt_ival1, kt_ival2, kt_lastmsg;
int rx_ifindex;
- int count;
- int nframes;
- int currframe;
+ u32 count;
+ u32 nframes;
+ u32 currframe;
struct can_frame *frames;
struct can_frame *last_frames;
struct can_frame sframe;
@@ -175,7 +182,7 @@ static int bcm_proc_show(struct seq_file *m, void *v)
seq_printf(m, "rx_op: %03X %-5s ",
op->can_id, bcm_proc_getifname(ifname, op->ifindex));
- seq_printf(m, "[%d]%c ", op->nframes,
+ seq_printf(m, "[%u]%c ", op->nframes,
(op->flags & RX_CHECK_DLC)?'d':' ');
if (op->kt_ival1.tv64)
seq_printf(m, "timeo=%lld ",
@@ -198,7 +205,7 @@ static int bcm_proc_show(struct seq_file *m, void *v)
list_for_each_entry(op, &bo->tx_ops, list) {
- seq_printf(m, "tx_op: %03X %s [%d] ",
+ seq_printf(m, "tx_op: %03X %s [%u] ",
op->can_id,
bcm_proc_getifname(ifname, op->ifindex),
op->nframes);
@@ -283,7 +290,7 @@ static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head,
struct can_frame *firstframe;
struct sockaddr_can *addr;
struct sock *sk = op->sk;
- int datalen = head->nframes * CFSIZ;
+ unsigned int datalen = head->nframes * CFSIZ;
int err;
skb = alloc_skb(sizeof(*head) + datalen, gfp_any());
@@ -468,7 +475,7 @@ rx_changed_settime:
* bcm_rx_cmp_to_index - (bit)compares the currently received data to formerly
* received data stored in op->last_frames[]
*/
-static void bcm_rx_cmp_to_index(struct bcm_op *op, int index,
+static void bcm_rx_cmp_to_index(struct bcm_op *op, unsigned int index,
const struct can_frame *rxdata)
{
/*
@@ -554,7 +561,8 @@ static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer)
/*
* bcm_rx_do_flush - helper for bcm_rx_thr_flush
*/
-static inline int bcm_rx_do_flush(struct bcm_op *op, int update, int index)
+static inline int bcm_rx_do_flush(struct bcm_op *op, int update,
+ unsigned int index)
{
if ((op->last_frames) && (op->last_frames[index].can_dlc & RX_THR)) {
if (update)
@@ -575,7 +583,7 @@ static int bcm_rx_thr_flush(struct bcm_op *op, int update)
int updated = 0;
if (op->nframes > 1) {
- int i;
+ unsigned int i;
/* for MUX filter we start at index 1 */
for (i = 1; i < op->nframes; i++)
@@ -624,7 +632,7 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data)
{
struct bcm_op *op = (struct bcm_op *)data;
const struct can_frame *rxframe = (struct can_frame *)skb->data;
- int i;
+ unsigned int i;
/* disable timeout */
hrtimer_cancel(&op->timer);
@@ -822,14 +830,15 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
{
struct bcm_sock *bo = bcm_sk(sk);
struct bcm_op *op;
- int i, err;
+ unsigned int i;
+ int err;
/* we need a real device to send frames */
if (!ifindex)
return -ENODEV;
- /* we need at least one can_frame */
- if (msg_head->nframes < 1)
+ /* check nframes boundaries - we need at least one can_frame */
+ if (msg_head->nframes < 1 || msg_head->nframes > MAX_NFRAMES)
return -EINVAL;
/* check the given can_id */
@@ -993,6 +1002,10 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
msg_head->nframes = 0;
}
+ /* the first element contains the mux-mask => MAX_NFRAMES + 1 */
+ if (msg_head->nframes > MAX_NFRAMES + 1)
+ return -EINVAL;
+
if ((msg_head->flags & RX_RTR_FRAME) &&
((msg_head->nframes != 1) ||
(!(msg_head->can_id & CAN_RTR_FLAG))))
diff --git a/net/core/dev.c b/net/core/dev.c
index 1ae65439144..660dd41aaaa 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2058,16 +2058,16 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev,
struct sk_buff *skb)
{
int queue_index;
- struct sock *sk = skb->sk;
+ const struct net_device_ops *ops = dev->netdev_ops;
- queue_index = sk_tx_queue_get(sk);
- if (queue_index < 0) {
- const struct net_device_ops *ops = dev->netdev_ops;
+ if (ops->ndo_select_queue) {
+ queue_index = ops->ndo_select_queue(dev, skb);
+ queue_index = dev_cap_txqueue(dev, queue_index);
+ } else {
+ struct sock *sk = skb->sk;
+ queue_index = sk_tx_queue_get(sk);
+ if (queue_index < 0) {
- if (ops->ndo_select_queue) {
- queue_index = ops->ndo_select_queue(dev, skb);
- queue_index = dev_cap_txqueue(dev, queue_index);
- } else {
queue_index = 0;
if (dev->real_num_tx_queues > 1)
queue_index = skb_tx_hash(dev, skb);
@@ -3143,7 +3143,7 @@ pull:
put_page(skb_shinfo(skb)->frags[0].page);
memmove(skb_shinfo(skb)->frags,
skb_shinfo(skb)->frags + 1,
- --skb_shinfo(skb)->nr_frags);
+ --skb_shinfo(skb)->nr_frags * sizeof(skb_frag_t));
}
}
@@ -4845,7 +4845,7 @@ static void rollback_registered_many(struct list_head *head)
dev = list_first_entry(head, struct net_device, unreg_list);
call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev);
- synchronize_net();
+ rcu_barrier();
list_for_each_entry(dev, head, unreg_list)
dev_put(dev);
diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index 9fbe7f7429b..6743146e4d6 100644
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -232,7 +232,7 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
est->last_packets = bstats->packets;
est->avpps = rate_est->pps<<10;
- spin_lock(&est_tree_lock);
+ spin_lock_bh(&est_tree_lock);
if (!elist[idx].timer.function) {
INIT_LIST_HEAD(&elist[idx].list);
setup_timer(&elist[idx].timer, est_timer, idx);
@@ -243,7 +243,7 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
list_add_rcu(&est->list, &elist[idx].list);
gen_add_node(est);
- spin_unlock(&est_tree_lock);
+ spin_unlock_bh(&est_tree_lock);
return 0;
}
@@ -270,7 +270,7 @@ void gen_kill_estimator(struct gnet_stats_basic_packed *bstats,
{
struct gen_estimator *e;
- spin_lock(&est_tree_lock);
+ spin_lock_bh(&est_tree_lock);
while ((e = gen_find_node(bstats, rate_est))) {
rb_erase(&e->node, &est_root);
@@ -281,7 +281,7 @@ void gen_kill_estimator(struct gnet_stats_basic_packed *bstats,
list_del_rcu(&e->list);
call_rcu(&e->e_rcu, __gen_kill_estimator);
}
- spin_unlock(&est_tree_lock);
+ spin_unlock_bh(&est_tree_lock);
}
EXPORT_SYMBOL(gen_kill_estimator);
@@ -320,9 +320,9 @@ bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats,
ASSERT_RTNL();
- spin_lock(&est_tree_lock);
+ spin_lock_bh(&est_tree_lock);
res = gen_find_node(bstats, rate_est) != NULL;
- spin_unlock(&est_tree_lock);
+ spin_unlock_bh(&est_tree_lock);
return res;
}
diff --git a/net/core/iovec.c b/net/core/iovec.c
index 1cd98df412d..e6b133b77cc 100644
--- a/net/core/iovec.c
+++ b/net/core/iovec.c
@@ -35,9 +35,10 @@
* in any case.
*/
-int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode)
+long verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode)
{
- int size, err, ct;
+ int size, ct;
+ long err;
if (m->msg_namelen) {
if (mode == VERIFY_READ) {
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 3a2513f0d0c..c83b421341c 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2573,6 +2573,10 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features)
__copy_skb_header(nskb, skb);
nskb->mac_len = skb->mac_len;
+ /* nskb and skb might have different headroom */
+ if (nskb->ip_summed == CHECKSUM_PARTIAL)
+ nskb->csum_start += skb_headroom(nskb) - headroom;
+
skb_reset_mac_header(nskb);
skb_set_network_header(nskb, skb->mac_len);
nskb->transport_header = (nskb->network_header +
@@ -2703,7 +2707,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
return -E2BIG;
headroom = skb_headroom(p);
- nskb = netdev_alloc_skb(p->dev, headroom + skb_gro_offset(p));
+ nskb = alloc_skb(headroom + skb_gro_offset(p), GFP_ATOMIC);
if (unlikely(!nskb))
return -ENOMEM;
diff --git a/net/core/sock.c b/net/core/sock.c
index b05b9b6ddb8..ef30e9d286e 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1351,9 +1351,9 @@ int sock_i_uid(struct sock *sk)
{
int uid;
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : 0;
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
return uid;
}
EXPORT_SYMBOL(sock_i_uid);
@@ -1362,9 +1362,9 @@ unsigned long sock_i_ino(struct sock *sk)
{
unsigned long ino;
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0;
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
return ino;
}
EXPORT_SYMBOL(sock_i_ino);
diff --git a/net/core/stream.c b/net/core/stream.c
index d959e0f4152..f5df85dcd20 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -141,10 +141,10 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
sk->sk_write_pending++;
- sk_wait_event(sk, &current_timeo, !sk->sk_err &&
- !(sk->sk_shutdown & SEND_SHUTDOWN) &&
- sk_stream_memory_free(sk) &&
- vm_wait);
+ sk_wait_event(sk, &current_timeo, sk->sk_err ||
+ (sk->sk_shutdown & SEND_SHUTDOWN) ||
+ (sk_stream_memory_free(sk) &&
+ !vm_wait));
sk->sk_write_pending--;
if (vm_wait) {
diff --git a/net/dns_resolver/Kconfig b/net/dns_resolver/Kconfig
new file mode 100644
index 00000000000..50d49f7e047
--- /dev/null
+++ b/net/dns_resolver/Kconfig
@@ -0,0 +1,27 @@
+#
+# Configuration for DNS Resolver
+#
+config DNS_RESOLVER
+ tristate "DNS Resolver support"
+ depends on NET && KEYS
+ help
+ Saying Y here will include support for the DNS Resolver key type
+ which can be used to make upcalls to perform DNS lookups in
+ userspace.
+
+ DNS Resolver is used to query DNS server for information. Examples
+ being resolving a UNC hostname element to an IP address for CIFS or
+ performing a DNS query for AFSDB records so that AFS can locate a
+ cell's volume location database servers.
+
+ DNS Resolver is used by the CIFS and AFS modules, and would support
+ SMB2 later. DNS Resolver is supported by the userspace upcall
+ helper "/sbin/dns.resolver" via /etc/request-key.conf.
+
+ See <file:Documentation/networking/dns_resolver.txt> for further
+ information.
+
+ To compile this as a module, choose M here: the module will be called
+ dnsresolver.
+
+ If unsure, say N.
diff --git a/net/dns_resolver/Makefile b/net/dns_resolver/Makefile
new file mode 100644
index 00000000000..c0ef4e71dc4
--- /dev/null
+++ b/net/dns_resolver/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for the Linux DNS Resolver.
+#
+
+obj-$(CONFIG_DNS_RESOLVER) += dns_resolver.o
+
+dns_resolver-objs := dns_key.o dns_query.o
diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c
new file mode 100644
index 00000000000..739435a6af3
--- /dev/null
+++ b/net/dns_resolver/dns_key.c
@@ -0,0 +1,293 @@
+/* Key type used to cache DNS lookups made by the kernel
+ *
+ * See Documentation/networking/dns_resolver.txt
+ *
+ * Copyright (c) 2007 Igor Mammedov
+ * Author(s): Igor Mammedov (niallain@gmail.com)
+ * Steve French (sfrench@us.ibm.com)
+ * Wang Lei (wang840925@gmail.com)
+ * David Howells (dhowells@redhat.com)
+ *
+ * This library is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published
+ * by the Free Software Foundation; either version 2.1 of the License, or
+ * (at your option) any later version.
+ *
+ * This library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
+ * the GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public License
+ * along with this library; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/keyctl.h>
+#include <linux/err.h>
+#include <linux/seq_file.h>
+#include <keys/dns_resolver-type.h>
+#include <keys/user-type.h>
+#include "internal.h"
+
+MODULE_DESCRIPTION("DNS Resolver");
+MODULE_AUTHOR("Wang Lei");
+MODULE_LICENSE("GPL");
+
+unsigned dns_resolver_debug;
+module_param_named(debug, dns_resolver_debug, uint, S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(debug, "DNS Resolver debugging mask");
+
+const struct cred *dns_resolver_cache;
+
+#define DNS_ERRORNO_OPTION "dnserror"
+
+/*
+ * Instantiate a user defined key for dns_resolver.
+ *
+ * The data must be a NUL-terminated string, with the NUL char accounted in
+ * datalen.
+ *
+ * If the data contains a '#' characters, then we take the clause after each
+ * one to be an option of the form 'key=value'. The actual data of interest is
+ * the string leading up to the first '#'. For instance:
+ *
+ * "ip1,ip2,...#foo=bar"
+ */
+static int
+dns_resolver_instantiate(struct key *key, const void *_data, size_t datalen)
+{
+ struct user_key_payload *upayload;
+ unsigned long derrno;
+ int ret;
+ size_t result_len = 0;
+ const char *data = _data, *end, *opt;
+
+ kenter("%%%d,%s,'%s',%zu",
+ key->serial, key->description, data, datalen);
+
+ if (datalen <= 1 || !data || data[datalen - 1] != '\0')
+ return -EINVAL;
+ datalen--;
+
+ /* deal with any options embedded in the data */
+ end = data + datalen;
+ opt = memchr(data, '#', datalen);
+ if (!opt) {
+ /* no options: the entire data is the result */
+ kdebug("no options");
+ result_len = datalen;
+ } else {
+ const char *next_opt;
+
+ result_len = opt - data;
+ opt++;
+ kdebug("options: '%s'", opt);
+ do {
+ const char *eq;
+ int opt_len, opt_nlen, opt_vlen, tmp;
+
+ next_opt = memchr(opt, '#', end - opt) ?: end;
+ opt_len = next_opt - opt;
+ if (!opt_len) {
+ printk(KERN_WARNING
+ "Empty option to dns_resolver key %d\n",
+ key->serial);
+ return -EINVAL;
+ }
+
+ eq = memchr(opt, '=', opt_len) ?: end;
+ opt_nlen = eq - opt;
+ eq++;
+ opt_vlen = next_opt - eq; /* will be -1 if no value */
+
+ tmp = opt_vlen >= 0 ? opt_vlen : 0;
+ kdebug("option '%*.*s' val '%*.*s'",
+ opt_nlen, opt_nlen, opt, tmp, tmp, eq);
+
+ /* see if it's an error number representing a DNS error
+ * that's to be recorded as the result in this key */
+ if (opt_nlen == sizeof(DNS_ERRORNO_OPTION) - 1 &&
+ memcmp(opt, DNS_ERRORNO_OPTION, opt_nlen) == 0) {
+ kdebug("dns error number option");
+ if (opt_vlen <= 0)
+ goto bad_option_value;
+
+ ret = strict_strtoul(eq, 10, &derrno);
+ if (ret < 0)
+ goto bad_option_value;
+
+ if (derrno < 1 || derrno > 511)
+ goto bad_option_value;
+
+ kdebug("dns error no. = %lu", derrno);
+ key->type_data.x[0] = -derrno;
+ continue;
+ }
+
+ bad_option_value:
+ printk(KERN_WARNING
+ "Option '%*.*s' to dns_resolver key %d:"
+ " bad/missing value\n",
+ opt_nlen, opt_nlen, opt, key->serial);
+ return -EINVAL;
+ } while (opt = next_opt + 1, opt < end);
+ }
+
+ /* don't cache the result if we're caching an error saying there's no
+ * result */
+ if (key->type_data.x[0]) {
+ kleave(" = 0 [h_error %ld]", key->type_data.x[0]);
+ return 0;
+ }
+
+ kdebug("store result");
+ ret = key_payload_reserve(key, result_len);
+ if (ret < 0)
+ return -EINVAL;
+
+ upayload = kmalloc(sizeof(*upayload) + result_len + 1, GFP_KERNEL);
+ if (!upayload) {
+ kleave(" = -ENOMEM");
+ return -ENOMEM;
+ }
+
+ upayload->datalen = result_len;
+ memcpy(upayload->data, data, result_len);
+ upayload->data[result_len] = '\0';
+ rcu_assign_pointer(key->payload.data, upayload);
+
+ kleave(" = 0");
+ return 0;
+}
+
+/*
+ * The description is of the form "[<type>:]<domain_name>"
+ *
+ * The domain name may be a simple name or an absolute domain name (which
+ * should end with a period). The domain name is case-independent.
+ */
+static int
+dns_resolver_match(const struct key *key, const void *description)
+{
+ int slen, dlen, ret = 0;
+ const char *src = key->description, *dsp = description;
+
+ kenter("%s,%s", src, dsp);
+
+ if (!src || !dsp)
+ goto no_match;
+
+ if (strcasecmp(src, dsp) == 0)
+ goto matched;
+
+ slen = strlen(src);
+ dlen = strlen(dsp);
+ if (slen <= 0 || dlen <= 0)
+ goto no_match;
+ if (src[slen - 1] == '.')
+ slen--;
+ if (dsp[dlen - 1] == '.')
+ dlen--;
+ if (slen != dlen || strncasecmp(src, dsp, slen) != 0)
+ goto no_match;
+
+matched:
+ ret = 1;
+no_match:
+ kleave(" = %d", ret);
+ return ret;
+}
+
+/*
+ * Describe a DNS key
+ */
+static void dns_resolver_describe(const struct key *key, struct seq_file *m)
+{
+ int err = key->type_data.x[0];
+
+ seq_puts(m, key->description);
+ if (err)
+ seq_printf(m, ": %d", err);
+ else
+ seq_printf(m, ": %u", key->datalen);
+}
+
+struct key_type key_type_dns_resolver = {
+ .name = "dns_resolver",
+ .instantiate = dns_resolver_instantiate,
+ .match = dns_resolver_match,
+ .revoke = user_revoke,
+ .destroy = user_destroy,
+ .describe = dns_resolver_describe,
+ .read = user_read,
+};
+
+static int __init init_dns_resolver(void)
+{
+ struct cred *cred;
+ struct key *keyring;
+ int ret;
+
+ printk(KERN_NOTICE "Registering the %s key type\n",
+ key_type_dns_resolver.name);
+
+ /* create an override credential set with a special thread keyring in
+ * which DNS requests are cached
+ *
+ * this is used to prevent malicious redirections from being installed
+ * with add_key().
+ */
+ cred = prepare_kernel_cred(NULL);
+ if (!cred)
+ return -ENOMEM;
+
+ keyring = key_alloc(&key_type_keyring, ".dns_resolver", 0, 0, cred,
+ (KEY_POS_ALL & ~KEY_POS_SETATTR) |
+ KEY_USR_VIEW | KEY_USR_READ,
+ KEY_ALLOC_NOT_IN_QUOTA);
+ if (IS_ERR(keyring)) {
+ ret = PTR_ERR(keyring);
+ goto failed_put_cred;
+ }
+
+ ret = key_instantiate_and_link(keyring, NULL, 0, NULL, NULL);
+ if (ret < 0)
+ goto failed_put_key;
+
+ ret = register_key_type(&key_type_dns_resolver);
+ if (ret < 0)
+ goto failed_put_key;
+
+ /* instruct request_key() to use this special keyring as a cache for
+ * the results it looks up */
+ cred->thread_keyring = keyring;
+ cred->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING;
+ dns_resolver_cache = cred;
+
+ kdebug("DNS resolver keyring: %d\n", key_serial(keyring));
+ return 0;
+
+failed_put_key:
+ key_put(keyring);
+failed_put_cred:
+ put_cred(cred);
+ return ret;
+}
+
+static void __exit exit_dns_resolver(void)
+{
+ key_revoke(dns_resolver_cache->thread_keyring);
+ unregister_key_type(&key_type_dns_resolver);
+ put_cred(dns_resolver_cache);
+ printk(KERN_NOTICE "Unregistered %s key type\n",
+ key_type_dns_resolver.name);
+}
+
+module_init(init_dns_resolver)
+module_exit(exit_dns_resolver)
+MODULE_LICENSE("GPL");
diff --git a/net/dns_resolver/dns_query.c b/net/dns_resolver/dns_query.c
new file mode 100644
index 00000000000..c32be292c7e
--- /dev/null
+++ b/net/dns_resolver/dns_query.c
@@ -0,0 +1,165 @@
+/* Upcall routine, designed to work as a key type and working through
+ * /sbin/request-key to contact userspace when handling DNS queries.
+ *
+ * See Documentation/networking/dns_resolver.txt
+ *
+ * Copyright (c) 2007 Igor Mammedov
+ * Author(s): Igor Mammedov (niallain@gmail.com)
+ * Steve French (sfrench@us.ibm.com)
+ * Wang Lei (wang840925@gmail.com)
+ * David Howells (dhowells@redhat.com)
+ *
+ * The upcall wrapper used to make an arbitrary DNS query.
+ *
+ * This function requires the appropriate userspace tool dns.upcall to be
+ * installed and something like the following lines should be added to the
+ * /etc/request-key.conf file:
+ *
+ * create dns_resolver * * /sbin/dns.upcall %k
+ *
+ * For example to use this module to query AFSDB RR:
+ *
+ * create dns_resolver afsdb:* * /sbin/dns.afsdb %k
+ *
+ * This library is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published
+ * by the Free Software Foundation; either version 2.1 of the License, or
+ * (at your option) any later version.
+ *
+ * This library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
+ * the GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public License
+ * along with this library; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/dns_resolver.h>
+#include <linux/err.h>
+#include <keys/dns_resolver-type.h>
+#include <keys/user-type.h>
+
+#include "internal.h"
+
+/**
+ * dns_query - Query the DNS
+ * @type: Query type (or NULL for straight host->IP lookup)
+ * @name: Name to look up
+ * @namelen: Length of name
+ * @options: Request options (or NULL if no options)
+ * @_result: Where to place the returned data.
+ * @_expiry: Where to store the result expiry time (or NULL)
+ *
+ * The data will be returned in the pointer at *result, and the caller is
+ * responsible for freeing it.
+ *
+ * The description should be of the form "[<query_type>:]<domain_name>", and
+ * the options need to be appropriate for the query type requested. If no
+ * query_type is given, then the query is a straight hostname to IP address
+ * lookup.
+ *
+ * The DNS resolution lookup is performed by upcalling to userspace by way of
+ * requesting a key of type dns_resolver.
+ *
+ * Returns the size of the result on success, -ve error code otherwise.
+ */
+int dns_query(const char *type, const char *name, size_t namelen,
+ const char *options, char **_result, time_t *_expiry)
+{
+ struct key *rkey;
+ struct user_key_payload *upayload;
+ const struct cred *saved_cred;
+ size_t typelen, desclen;
+ char *desc, *cp;
+ int ret, len;
+
+ kenter("%s,%*.*s,%zu,%s",
+ type, (int)namelen, (int)namelen, name, namelen, options);
+
+ if (!name || namelen == 0 || !_result)
+ return -EINVAL;
+
+ /* construct the query key description as "[<type>:]<name>" */
+ typelen = 0;
+ desclen = 0;
+ if (type) {
+ typelen = strlen(type);
+ if (typelen < 1)
+ return -EINVAL;
+ desclen += typelen + 1;
+ }
+
+ if (!namelen)
+ namelen = strlen(name);
+ if (namelen < 3)
+ return -EINVAL;
+ desclen += namelen + 1;
+
+ desc = kmalloc(desclen, GFP_KERNEL);
+ if (!desc)
+ return -ENOMEM;
+
+ cp = desc;
+ if (type) {
+ memcpy(cp, type, typelen);
+ cp += typelen;
+ *cp++ = ':';
+ }
+ memcpy(cp, name, namelen);
+ cp += namelen;
+ *cp = '\0';
+
+ if (!options)
+ options = "";
+ kdebug("call request_key(,%s,%s)", desc, options);
+
+ /* make the upcall, using special credentials to prevent the use of
+ * add_key() to preinstall malicious redirections
+ */
+ saved_cred = override_creds(dns_resolver_cache);
+ rkey = request_key(&key_type_dns_resolver, desc, options);
+ revert_creds(saved_cred);
+ kfree(desc);
+ if (IS_ERR(rkey)) {
+ ret = PTR_ERR(rkey);
+ goto out;
+ }
+
+ down_read(&rkey->sem);
+ rkey->perm |= KEY_USR_VIEW;
+
+ ret = key_validate(rkey);
+ if (ret < 0)
+ goto put;
+
+ /* If the DNS server gave an error, return that to the caller */
+ ret = rkey->type_data.x[0];
+ if (ret)
+ goto put;
+
+ upayload = rcu_dereference_protected(rkey->payload.data,
+ lockdep_is_held(&rkey->sem));
+ len = upayload->datalen;
+
+ ret = -ENOMEM;
+ *_result = kmalloc(len + 1, GFP_KERNEL);
+ if (!*_result)
+ goto put;
+
+ memcpy(*_result, upayload->data, len + 1);
+ if (_expiry)
+ *_expiry = rkey->expiry;
+
+ ret = len;
+put:
+ up_read(&rkey->sem);
+ key_put(rkey);
+out:
+ kleave(" = %d", ret);
+ return ret;
+}
+EXPORT_SYMBOL(dns_query);
diff --git a/net/dns_resolver/internal.h b/net/dns_resolver/internal.h
new file mode 100644
index 00000000000..189ca9e9b78
--- /dev/null
+++ b/net/dns_resolver/internal.h
@@ -0,0 +1,44 @@
+/*
+ * Copyright (c) 2010 Wang Lei
+ * Author(s): Wang Lei (wang840925@gmail.com). All Rights Reserved.
+ *
+ * Internal DNS Rsolver stuff
+ *
+ * This library is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published
+ * by the Free Software Foundation; either version 2.1 of the License, or
+ * (at your option) any later version.
+ *
+ * This library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
+ * the GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public License
+ * along with this library; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+
+/*
+ * dns_key.c
+ */
+extern const struct cred *dns_resolver_cache;
+
+/*
+ * debug tracing
+ */
+extern unsigned dns_resolver_debug;
+
+#define kdebug(FMT, ...) \
+do { \
+ if (unlikely(dns_resolver_debug)) \
+ printk(KERN_DEBUG "[%-6.6s] "FMT"\n", \
+ current->comm, ##__VA_ARGS__); \
+} while (0)
+
+#define kenter(FMT, ...) kdebug("==> %s("FMT")", __func__, ##__VA_ARGS__)
+#define kleave(FMT, ...) kdebug("<== %s()"FMT"", __func__, ##__VA_ARGS__)
diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig
index 11201784d29..87bb5f4de0e 100644
--- a/net/dsa/Kconfig
+++ b/net/dsa/Kconfig
@@ -1,7 +1,7 @@
menuconfig NET_DSA
bool "Distributed Switch Architecture support"
default n
- depends on EXPERIMENTAL && NET_ETHERNET && !S390
+ depends on EXPERIMENTAL && NETDEVICES && !S390
select PHYLIB
---help---
This allows you to use hardware switch chips that use
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 7c3a7d19124..7cd7760144f 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -46,7 +46,7 @@ config IP_ADVANCED_ROUTER
rp_filter on use:
echo 1 > /proc/sys/net/ipv4/conf/<device>/rp_filter
- and
+ or
echo 1 > /proc/sys/net/ipv4/conf/all/rp_filter
Note that some distributions enable it in startup scripts.
@@ -217,6 +217,7 @@ config NET_IPIP
config NET_IPGRE
tristate "IP: GRE tunnels over IP"
+ depends on IPV6 || IPV6=n
help
Tunneling means encapsulating data of one protocol type within
another protocol and sending it over a channel that understands the
@@ -412,7 +413,7 @@ config INET_XFRM_MODE_BEET
If unsure, say Y.
config INET_LRO
- bool "Large Receive Offload (ipv4/tcp)"
+ tristate "Large Receive Offload (ipv4/tcp)"
default y
---help---
Support for Large Receive Offload (ipv4/tcp).
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index f0550941df7..721a8a37b45 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -62,8 +62,11 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
}
if (!inet->inet_saddr)
inet->inet_saddr = rt->rt_src; /* Update source address */
- if (!inet->inet_rcv_saddr)
+ if (!inet->inet_rcv_saddr) {
inet->inet_rcv_saddr = rt->rt_src;
+ if (sk->sk_prot->rehash)
+ sk->sk_prot->rehash(sk);
+ }
inet->inet_daddr = rt->rt_dst;
inet->inet_dport = usin->sin_port;
sk->sk_state = TCP_ESTABLISHED;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index a4396891835..7d02a9f999f 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -246,6 +246,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
struct fib_result res;
int no_addr, rpf, accept_local;
+ bool dev_match;
int ret;
struct net *net;
@@ -273,12 +274,22 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
}
*spec_dst = FIB_RES_PREFSRC(res);
fib_combine_itag(itag, &res);
+ dev_match = false;
+
#ifdef CONFIG_IP_ROUTE_MULTIPATH
- if (FIB_RES_DEV(res) == dev || res.fi->fib_nhs > 1)
+ for (ret = 0; ret < res.fi->fib_nhs; ret++) {
+ struct fib_nh *nh = &res.fi->fib_nh[ret];
+
+ if (nh->nh_dev == dev) {
+ dev_match = true;
+ break;
+ }
+ }
#else
if (FIB_RES_DEV(res) == dev)
+ dev_match = true;
#endif
- {
+ if (dev_match) {
ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST;
fib_res_put(&res);
return ret;
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 79d057a939b..4a8e370862b 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -186,7 +186,9 @@ static inline struct tnode *node_parent_rcu(struct node *node)
{
struct tnode *ret = node_parent(node);
- return rcu_dereference(ret);
+ return rcu_dereference_check(ret,
+ rcu_read_lock_held() ||
+ lockdep_rtnl_is_held());
}
/* Same as rcu_assign_pointer
@@ -1753,7 +1755,9 @@ static struct leaf *leaf_walk_rcu(struct tnode *p, struct node *c)
static struct leaf *trie_firstleaf(struct trie *t)
{
- struct tnode *n = (struct tnode *) rcu_dereference(t->trie);
+ struct tnode *n = (struct tnode *) rcu_dereference_check(t->trie,
+ rcu_read_lock_held() ||
+ lockdep_rtnl_is_held());
if (!n)
return NULL;
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index a1ad0e7180d..2a4bb76f213 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -856,6 +856,18 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
igmpv3_clear_delrec(in_dev);
} else if (len < 12) {
return; /* ignore bogus packet; freed by caller */
+ } else if (IGMP_V1_SEEN(in_dev)) {
+ /* This is a v3 query with v1 queriers present */
+ max_delay = IGMP_Query_Response_Interval;
+ group = 0;
+ } else if (IGMP_V2_SEEN(in_dev)) {
+ /* this is a v3 query with v2 queriers present;
+ * Interpretation of the max_delay code is problematic here.
+ * A real v2 host would use ih_code directly, while v3 has a
+ * different encoding. We use the v3 encoding as more likely
+ * to be intended in a v3 query.
+ */
+ max_delay = IGMPV3_MRC(ih3->code)*(HZ/IGMP_TIMER_SCALE);
} else { /* v3 */
if (!pskb_may_pull(skb, sizeof(struct igmpv3_query)))
return;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 945b20a5ad5..35c93e8b6a4 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -45,7 +45,7 @@
#include <net/netns/generic.h>
#include <net/rtnetlink.h>
-#ifdef CONFIG_IPV6
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
#include <net/ipv6.h>
#include <net/ip6_fib.h>
#include <net/ip6_route.h>
@@ -699,7 +699,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
if ((dst = rt->rt_gateway) == 0)
goto tx_error_icmp;
}
-#ifdef CONFIG_IPV6
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
else if (skb->protocol == htons(ETH_P_IPV6)) {
struct in6_addr *addr6;
int addr_type;
@@ -774,7 +774,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
goto tx_error;
}
}
-#ifdef CONFIG_IPV6
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
else if (skb->protocol == htons(ETH_P_IPV6)) {
struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb);
@@ -850,7 +850,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
if ((iph->ttl = tiph->ttl) == 0) {
if (skb->protocol == htons(ETH_P_IP))
iph->ttl = old_iph->ttl;
-#ifdef CONFIG_IPV6
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
else if (skb->protocol == htons(ETH_P_IPV6))
iph->ttl = ((struct ipv6hdr *)old_iph)->hop_limit;
#endif
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 04b69896df5..7649d775007 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -488,9 +488,8 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
* we can switch to copy when see the first bad fragment.
*/
if (skb_has_frags(skb)) {
- struct sk_buff *frag;
+ struct sk_buff *frag, *frag2;
int first_len = skb_pagelen(skb);
- int truesizes = 0;
if (first_len - hlen > mtu ||
((first_len - hlen) & 7) ||
@@ -503,18 +502,18 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
if (frag->len > mtu ||
((frag->len & 7) && frag->next) ||
skb_headroom(frag) < hlen)
- goto slow_path;
+ goto slow_path_clean;
/* Partially cloned skb? */
if (skb_shared(frag))
- goto slow_path;
+ goto slow_path_clean;
BUG_ON(frag->sk);
if (skb->sk) {
frag->sk = skb->sk;
frag->destructor = sock_wfree;
}
- truesizes += frag->truesize;
+ skb->truesize -= frag->truesize;
}
/* Everything is OK. Generate! */
@@ -524,7 +523,6 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
frag = skb_shinfo(skb)->frag_list;
skb_frag_list_init(skb);
skb->data_len = first_len - skb_headlen(skb);
- skb->truesize -= truesizes;
skb->len = first_len;
iph->tot_len = htons(first_len);
iph->frag_off = htons(IP_MF);
@@ -576,6 +574,15 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
}
IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
return err;
+
+slow_path_clean:
+ skb_walk_frags(skb, frag2) {
+ if (frag2 == frag)
+ break;
+ frag2->sk = NULL;
+ frag2->destructor = NULL;
+ skb->truesize += frag2->truesize;
+ }
}
slow_path:
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 6c40a8c46e7..64b70ad162e 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1129,6 +1129,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
case IP_HDRINCL:
val = inet->hdrincl;
break;
+ case IP_NODEFRAG:
+ val = inet->nodefrag;
+ break;
case IP_MTU_DISCOVER:
val = inet->pmtudisc;
break;
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 6bccba31d13..e8f4f9a57f1 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -735,6 +735,7 @@ static void get_counters(const struct xt_table_info *t,
if (cpu == curcpu)
continue;
i = 0;
+ local_bh_disable();
xt_info_wrlock(cpu);
xt_entry_foreach(iter, t->entries[cpu], t->size) {
ADD_COUNTER(counters[i], iter->counters.bcnt,
@@ -742,6 +743,7 @@ static void get_counters(const struct xt_table_info *t,
++i;
}
xt_info_wrunlock(cpu);
+ local_bh_enable();
}
put_cpu();
}
@@ -1418,6 +1420,9 @@ static int translate_compat_table(const char *name,
if (ret != 0)
break;
++i;
+ if (strcmp(arpt_get_target(iter1)->u.user.name,
+ XT_ERROR_TARGET) == 0)
+ ++newinfo->stacksize;
}
if (ret) {
/*
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index c439721b165..d163f2e3b2e 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -909,6 +909,7 @@ get_counters(const struct xt_table_info *t,
if (cpu == curcpu)
continue;
i = 0;
+ local_bh_disable();
xt_info_wrlock(cpu);
xt_entry_foreach(iter, t->entries[cpu], t->size) {
ADD_COUNTER(counters[i], iter->counters.bcnt,
@@ -916,6 +917,7 @@ get_counters(const struct xt_table_info *t,
++i; /* macro does multi eval of i */
}
xt_info_wrunlock(cpu);
+ local_bh_enable();
}
put_cpu();
}
@@ -1749,6 +1751,9 @@ translate_compat_table(struct net *net,
if (ret != 0)
break;
++i;
+ if (strcmp(ipt_get_target(iter1)->u.user.name,
+ XT_ERROR_TARGET) == 0)
+ ++newinfo->stacksize;
}
if (ret) {
/*
diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c
index b254dafaf42..43eec80c0e7 100644
--- a/net/ipv4/netfilter/ipt_REJECT.c
+++ b/net/ipv4/netfilter/ipt_REJECT.c
@@ -112,6 +112,7 @@ static void send_reset(struct sk_buff *oldskb, int hook)
/* ip_route_me_harder expects skb->dst to be set */
skb_dst_set_noref(nskb, skb_dst(oldskb));
+ nskb->protocol = htons(ETH_P_IP);
if (ip_route_me_harder(nskb, addr_type))
goto free_nskb;
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index eab8de32f20..f3a9b42b16c 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -66,9 +66,11 @@ static unsigned int ipv4_conntrack_defrag(unsigned int hooknum,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
+ struct sock *sk = skb->sk;
struct inet_sock *inet = inet_sk(skb->sk);
- if (inet && inet->nodefrag)
+ if (sk && (sk->sk_family == PF_INET) &&
+ inet->nodefrag)
return NF_ACCEPT;
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c
index 1679e2c0963..ee5f419d0a5 100644
--- a/net/ipv4/netfilter/nf_nat_snmp_basic.c
+++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c
@@ -893,13 +893,15 @@ static void fast_csum(__sum16 *csum,
unsigned char s[4];
if (offset & 1) {
- s[0] = s[2] = 0;
+ s[0] = ~0;
s[1] = ~*optr;
+ s[2] = 0;
s[3] = *nptr;
} else {
- s[1] = s[3] = 0;
s[0] = ~*optr;
+ s[1] = ~0;
s[2] = *nptr;
+ s[3] = 0;
}
*csum = csum_fold(csum_partial(s, 4, ~csum_unfold(*csum)));
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 3f56b6e6c6a..ac6559cb54f 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1231,7 +1231,7 @@ restart:
}
if (net_ratelimit())
- printk(KERN_WARNING "Neighbour table overflow.\n");
+ printk(KERN_WARNING "ipv4: Neighbour table overflow.\n");
rt_drop(rt);
return -ENOBUFS;
}
@@ -2738,6 +2738,11 @@ slow_output:
}
EXPORT_SYMBOL_GPL(__ip_route_output_key);
+static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie)
+{
+ return NULL;
+}
+
static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
{
}
@@ -2746,7 +2751,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = {
.family = AF_INET,
.protocol = cpu_to_be16(ETH_P_IP),
.destroy = ipv4_dst_destroy,
- .check = ipv4_dst_check,
+ .check = ipv4_blackhole_dst_check,
.update_pmtu = ipv4_rt_blackhole_update_pmtu,
.entries = ATOMIC_INIT(0),
};
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 176e11aaea7..f115ea68a4e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -386,8 +386,6 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
*/
mask = 0;
- if (sk->sk_err)
- mask = POLLERR;
/*
* POLLHUP is certainly not done right. But poll() doesn't
@@ -451,11 +449,17 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk))
mask |= POLLOUT | POLLWRNORM;
}
- }
+ } else
+ mask |= POLLOUT | POLLWRNORM;
if (tp->urg_data & TCP_URG_VALID)
mask |= POLLPRI;
}
+ /* This barrier is coupled with smp_wmb() in tcp_reset() */
+ smp_rmb();
+ if (sk->sk_err)
+ mask |= POLLERR;
+
return mask;
}
EXPORT_SYMBOL(tcp_poll);
@@ -939,7 +943,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
sg = sk->sk_route_caps & NETIF_F_SG;
while (--iovlen >= 0) {
- int seglen = iov->iov_len;
+ size_t seglen = iov->iov_len;
unsigned char __user *from = iov->iov_base;
iov++;
@@ -2011,11 +2015,8 @@ adjudge_to_death:
}
}
if (sk->sk_state != TCP_CLOSE) {
- int orphan_count = percpu_counter_read_positive(
- sk->sk_prot->orphan_count);
-
sk_mem_reclaim(sk);
- if (tcp_too_many_orphans(sk, orphan_count)) {
+ if (tcp_too_many_orphans(sk, 0)) {
if (net_ratelimit())
printk(KERN_INFO "TCP: too many of orphaned "
"sockets\n");
@@ -3212,7 +3213,7 @@ void __init tcp_init(void)
{
struct sk_buff *skb = NULL;
unsigned long nr_pages, limit;
- int order, i, max_share;
+ int i, max_share, cnt;
unsigned long jiffy = jiffies;
BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
@@ -3261,22 +3262,12 @@ void __init tcp_init(void)
INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain);
}
- /* Try to be a bit smarter and adjust defaults depending
- * on available memory.
- */
- for (order = 0; ((1 << order) << PAGE_SHIFT) <
- (tcp_hashinfo.bhash_size * sizeof(struct inet_bind_hashbucket));
- order++)
- ;
- if (order >= 4) {
- tcp_death_row.sysctl_max_tw_buckets = 180000;
- sysctl_tcp_max_orphans = 4096 << (order - 4);
- sysctl_max_syn_backlog = 1024;
- } else if (order < 3) {
- tcp_death_row.sysctl_max_tw_buckets >>= (3 - order);
- sysctl_tcp_max_orphans >>= (3 - order);
- sysctl_max_syn_backlog = 128;
- }
+
+ cnt = tcp_hashinfo.ehash_mask + 1;
+
+ tcp_death_row.sysctl_max_tw_buckets = cnt / 2;
+ sysctl_tcp_max_orphans = cnt / 2;
+ sysctl_max_syn_backlog = max(128, cnt / 256);
/* Set the pressure threshold to be a fraction of global memory that
* is up to 1/2 at 256 MB, decreasing toward zero with the amount of
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 0ec9bd0ae94..850c737e08e 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -196,10 +196,10 @@ void tcp_get_allowed_congestion_control(char *buf, size_t maxlen)
int tcp_set_allowed_congestion_control(char *val)
{
struct tcp_congestion_ops *ca;
- char *clone, *name;
+ char *saved_clone, *clone, *name;
int ret = 0;
- clone = kstrdup(val, GFP_USER);
+ saved_clone = clone = kstrdup(val, GFP_USER);
if (!clone)
return -ENOMEM;
@@ -226,6 +226,7 @@ int tcp_set_allowed_congestion_control(char *val)
}
out:
spin_unlock(&tcp_cong_list_lock);
+ kfree(saved_clone);
return ret;
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e663b78a2ef..b55f60f6fcb 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2545,7 +2545,8 @@ static void tcp_mark_head_lost(struct sock *sk, int packets)
cnt += tcp_skb_pcount(skb);
if (cnt > packets) {
- if (tcp_is_sack(tp) || (oldcnt >= packets))
+ if ((tcp_is_sack(tp) && !tcp_is_fack(tp)) ||
+ (oldcnt >= packets))
break;
mss = skb_shinfo(skb)->gso_size;
@@ -4048,6 +4049,8 @@ static void tcp_reset(struct sock *sk)
default:
sk->sk_err = ECONNRESET;
}
+ /* This barrier is coupled with smp_rmb() in tcp_poll() */
+ smp_wmb();
if (!sock_flag(sk, SOCK_DEAD))
sk->sk_error_report(sk);
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 808bb920c9f..74c54b30600 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -66,18 +66,18 @@ static void tcp_write_err(struct sock *sk)
static int tcp_out_of_resources(struct sock *sk, int do_reset)
{
struct tcp_sock *tp = tcp_sk(sk);
- int orphans = percpu_counter_read_positive(&tcp_orphan_count);
+ int shift = 0;
/* If peer does not open window for long time, or did not transmit
* anything for long time, penalize it. */
if ((s32)(tcp_time_stamp - tp->lsndtime) > 2*TCP_RTO_MAX || !do_reset)
- orphans <<= 1;
+ shift++;
/* If some dubious ICMP arrived, penalize even more. */
if (sk->sk_err_soft)
- orphans <<= 1;
+ shift++;
- if (tcp_too_many_orphans(sk, orphans)) {
+ if (tcp_too_many_orphans(sk, shift)) {
if (net_ratelimit())
printk(KERN_INFO "Out of socket memory\n");
@@ -135,13 +135,16 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
/* This function calculates a "timeout" which is equivalent to the timeout of a
* TCP connection after "boundary" unsuccessful, exponentially backed-off
- * retransmissions with an initial RTO of TCP_RTO_MIN.
+ * retransmissions with an initial RTO of TCP_RTO_MIN or TCP_TIMEOUT_INIT if
+ * syn_set flag is set.
*/
static bool retransmits_timed_out(struct sock *sk,
- unsigned int boundary)
+ unsigned int boundary,
+ bool syn_set)
{
unsigned int timeout, linear_backoff_thresh;
unsigned int start_ts;
+ unsigned int rto_base = syn_set ? TCP_TIMEOUT_INIT : TCP_RTO_MIN;
if (!inet_csk(sk)->icsk_retransmits)
return false;
@@ -151,12 +154,12 @@ static bool retransmits_timed_out(struct sock *sk,
else
start_ts = tcp_sk(sk)->retrans_stamp;
- linear_backoff_thresh = ilog2(TCP_RTO_MAX/TCP_RTO_MIN);
+ linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base);
if (boundary <= linear_backoff_thresh)
- timeout = ((2 << boundary) - 1) * TCP_RTO_MIN;
+ timeout = ((2 << boundary) - 1) * rto_base;
else
- timeout = ((2 << linear_backoff_thresh) - 1) * TCP_RTO_MIN +
+ timeout = ((2 << linear_backoff_thresh) - 1) * rto_base +
(boundary - linear_backoff_thresh) * TCP_RTO_MAX;
return (tcp_time_stamp - start_ts) >= timeout;
@@ -167,14 +170,15 @@ static int tcp_write_timeout(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
int retry_until;
- bool do_reset;
+ bool do_reset, syn_set = 0;
if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
if (icsk->icsk_retransmits)
dst_negative_advice(sk);
retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
+ syn_set = 1;
} else {
- if (retransmits_timed_out(sk, sysctl_tcp_retries1)) {
+ if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0)) {
/* Black hole detection */
tcp_mtu_probing(icsk, sk);
@@ -187,14 +191,14 @@ static int tcp_write_timeout(struct sock *sk)
retry_until = tcp_orphan_retries(sk, alive);
do_reset = alive ||
- !retransmits_timed_out(sk, retry_until);
+ !retransmits_timed_out(sk, retry_until, 0);
if (tcp_out_of_resources(sk, do_reset))
return 1;
}
}
- if (retransmits_timed_out(sk, retry_until)) {
+ if (retransmits_timed_out(sk, retry_until, syn_set)) {
/* Has it gone just too far? */
tcp_write_err(sk);
return 1;
@@ -436,7 +440,7 @@ out_reset_timer:
icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX);
}
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, TCP_RTO_MAX);
- if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1))
+ if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1, 0))
__sk_dst_reset(sk);
out:;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 32e0bef60d0..fb23c2e63b5 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1260,6 +1260,49 @@ void udp_lib_unhash(struct sock *sk)
}
EXPORT_SYMBOL(udp_lib_unhash);
+/*
+ * inet_rcv_saddr was changed, we must rehash secondary hash
+ */
+void udp_lib_rehash(struct sock *sk, u16 newhash)
+{
+ if (sk_hashed(sk)) {
+ struct udp_table *udptable = sk->sk_prot->h.udp_table;
+ struct udp_hslot *hslot, *hslot2, *nhslot2;
+
+ hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
+ nhslot2 = udp_hashslot2(udptable, newhash);
+ udp_sk(sk)->udp_portaddr_hash = newhash;
+ if (hslot2 != nhslot2) {
+ hslot = udp_hashslot(udptable, sock_net(sk),
+ udp_sk(sk)->udp_port_hash);
+ /* we must lock primary chain too */
+ spin_lock_bh(&hslot->lock);
+
+ spin_lock(&hslot2->lock);
+ hlist_nulls_del_init_rcu(&udp_sk(sk)->udp_portaddr_node);
+ hslot2->count--;
+ spin_unlock(&hslot2->lock);
+
+ spin_lock(&nhslot2->lock);
+ hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node,
+ &nhslot2->head);
+ nhslot2->count++;
+ spin_unlock(&nhslot2->lock);
+
+ spin_unlock_bh(&hslot->lock);
+ }
+ }
+}
+EXPORT_SYMBOL(udp_lib_rehash);
+
+static void udp_v4_rehash(struct sock *sk)
+{
+ u16 new_hash = udp4_portaddr_hash(sock_net(sk),
+ inet_sk(sk)->inet_rcv_saddr,
+ inet_sk(sk)->inet_num);
+ udp_lib_rehash(sk, new_hash);
+}
+
static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
int rc;
@@ -1843,6 +1886,7 @@ struct proto udp_prot = {
.backlog_rcv = __udp_queue_rcv_skb,
.hash = udp_lib_hash,
.unhash = udp_lib_unhash,
+ .rehash = udp_v4_rehash,
.get_port = udp_v4_get_port,
.memory_allocated = &udp_memory_allocated,
.sysctl_mem = sysctl_udp_mem,
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 869078d4eeb..a580349f0b8 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -61,7 +61,7 @@ static int xfrm4_get_saddr(struct net *net,
static int xfrm4_get_tos(struct flowi *fl)
{
- return fl->fl4_tos;
+ return IPTOS_RT_MASK & fl->fl4_tos; /* Strip ECN bits */
}
static int xfrm4_init_path(struct xfrm_dst *path, struct dst_entry *dst,
diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c
index 1ef1366a0a0..47947624ecc 100644
--- a/net/ipv4/xfrm4_state.c
+++ b/net/ipv4/xfrm4_state.c
@@ -21,21 +21,25 @@ static int xfrm4_init_flags(struct xfrm_state *x)
}
static void
-__xfrm4_init_tempsel(struct xfrm_state *x, struct flowi *fl,
- struct xfrm_tmpl *tmpl,
- xfrm_address_t *daddr, xfrm_address_t *saddr)
+__xfrm4_init_tempsel(struct xfrm_selector *sel, struct flowi *fl)
+{
+ sel->daddr.a4 = fl->fl4_dst;
+ sel->saddr.a4 = fl->fl4_src;
+ sel->dport = xfrm_flowi_dport(fl);
+ sel->dport_mask = htons(0xffff);
+ sel->sport = xfrm_flowi_sport(fl);
+ sel->sport_mask = htons(0xffff);
+ sel->family = AF_INET;
+ sel->prefixlen_d = 32;
+ sel->prefixlen_s = 32;
+ sel->proto = fl->proto;
+ sel->ifindex = fl->oif;
+}
+
+static void
+xfrm4_init_temprop(struct xfrm_state *x, struct xfrm_tmpl *tmpl,
+ xfrm_address_t *daddr, xfrm_address_t *saddr)
{
- x->sel.daddr.a4 = fl->fl4_dst;
- x->sel.saddr.a4 = fl->fl4_src;
- x->sel.dport = xfrm_flowi_dport(fl);
- x->sel.dport_mask = htons(0xffff);
- x->sel.sport = xfrm_flowi_sport(fl);
- x->sel.sport_mask = htons(0xffff);
- x->sel.family = AF_INET;
- x->sel.prefixlen_d = 32;
- x->sel.prefixlen_s = 32;
- x->sel.proto = fl->proto;
- x->sel.ifindex = fl->oif;
x->id = tmpl->id;
if (x->id.daddr.a4 == 0)
x->id.daddr.a4 = daddr->a4;
@@ -70,6 +74,7 @@ static struct xfrm_state_afinfo xfrm4_state_afinfo = {
.owner = THIS_MODULE,
.init_flags = xfrm4_init_flags,
.init_tempsel = __xfrm4_init_tempsel,
+ .init_temprop = xfrm4_init_temprop,
.output = xfrm4_output,
.extract_input = xfrm4_extract_input,
.extract_output = xfrm4_extract_output,
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index ab70a3fbcaf..324fac3b6c1 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4637,10 +4637,12 @@ int __init addrconf_init(void)
if (err < 0) {
printk(KERN_CRIT "IPv6 Addrconf:"
" cannot initialize default policy table: %d.\n", err);
- return err;
+ goto out;
}
- register_pernet_subsys(&addrconf_ops);
+ err = register_pernet_subsys(&addrconf_ops);
+ if (err < 0)
+ goto out_addrlabel;
/* The addrconf netdev notifier requires that loopback_dev
* has it's ipv6 private information allocated and setup
@@ -4692,7 +4694,9 @@ errout:
unregister_netdevice_notifier(&ipv6_dev_notf);
errlo:
unregister_pernet_subsys(&addrconf_ops);
-
+out_addrlabel:
+ ipv6_addr_label_cleanup();
+out:
return err;
}
@@ -4703,6 +4707,7 @@ void addrconf_cleanup(void)
unregister_netdevice_notifier(&ipv6_dev_notf);
unregister_pernet_subsys(&addrconf_ops);
+ ipv6_addr_label_cleanup();
rtnl_lock();
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index f0e774cea38..8175f802651 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -393,6 +393,11 @@ int __init ipv6_addr_label_init(void)
return register_pernet_subsys(&ipv6_addr_label_ops);
}
+void ipv6_addr_label_cleanup(void)
+{
+ unregister_pernet_subsys(&ipv6_addr_label_ops);
+}
+
static const struct nla_policy ifal_policy[IFAL_MAX+1] = {
[IFAL_ADDRESS] = { .len = sizeof(struct in6_addr), },
[IFAL_LABEL] = { .len = sizeof(u32), },
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 7d929a22cbc..ef371aa01ac 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -105,9 +105,12 @@ ipv4_connected:
if (ipv6_addr_any(&np->saddr))
ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr);
- if (ipv6_addr_any(&np->rcv_saddr))
+ if (ipv6_addr_any(&np->rcv_saddr)) {
ipv6_addr_set_v4mapped(inet->inet_rcv_saddr,
&np->rcv_saddr);
+ if (sk->sk_prot->rehash)
+ sk->sk_prot->rehash(sk);
+ }
goto out;
}
@@ -181,6 +184,8 @@ ipv4_connected:
if (ipv6_addr_any(&np->rcv_saddr)) {
ipv6_addr_copy(&np->rcv_saddr, &fl.fl6_src);
inet->inet_rcv_saddr = LOOPBACK4_IPV6;
+ if (sk->sk_prot->rehash)
+ sk->sk_prot->rehash(sk);
}
ip6_dst_store(sk, dst,
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index d40b330c0ee..980912ed7a3 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -639,7 +639,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
if (skb_has_frags(skb)) {
int first_len = skb_pagelen(skb);
- int truesizes = 0;
+ struct sk_buff *frag2;
if (first_len - hlen > mtu ||
((first_len - hlen) & 7) ||
@@ -651,18 +651,18 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
if (frag->len > mtu ||
((frag->len & 7) && frag->next) ||
skb_headroom(frag) < hlen)
- goto slow_path;
+ goto slow_path_clean;
/* Partially cloned skb? */
if (skb_shared(frag))
- goto slow_path;
+ goto slow_path_clean;
BUG_ON(frag->sk);
if (skb->sk) {
frag->sk = skb->sk;
frag->destructor = sock_wfree;
- truesizes += frag->truesize;
}
+ skb->truesize -= frag->truesize;
}
err = 0;
@@ -693,7 +693,6 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
first_len = skb_pagelen(skb);
skb->data_len = first_len - skb_headlen(skb);
- skb->truesize -= truesizes;
skb->len = first_len;
ipv6_hdr(skb)->payload_len = htons(first_len -
sizeof(struct ipv6hdr));
@@ -756,6 +755,15 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
IPSTATS_MIB_FRAGFAILS);
dst_release(&rt->dst);
return err;
+
+slow_path_clean:
+ skb_walk_frags(skb, frag2) {
+ if (frag2 == frag)
+ break;
+ frag2->sk = NULL;
+ frag2->destructor = NULL;
+ skb->truesize += frag2->truesize;
+ }
}
slow_path:
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 5359ef4daac..8e754be92c2 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -922,6 +922,7 @@ get_counters(const struct xt_table_info *t,
if (cpu == curcpu)
continue;
i = 0;
+ local_bh_disable();
xt_info_wrlock(cpu);
xt_entry_foreach(iter, t->entries[cpu], t->size) {
ADD_COUNTER(counters[i], iter->counters.bcnt,
@@ -929,6 +930,7 @@ get_counters(const struct xt_table_info *t,
++i;
}
xt_info_wrunlock(cpu);
+ local_bh_enable();
}
put_cpu();
}
@@ -1764,6 +1766,9 @@ translate_compat_table(struct net *net,
if (ret != 0)
break;
++i;
+ if (strcmp(ip6t_get_target(iter1)->u.user.name,
+ XT_ERROR_TARGET) == 0)
+ ++newinfo->stacksize;
}
if (ret) {
/*
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 13ef5bc05cf..578f3c1a16d 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -113,14 +113,6 @@ static void nf_skb_free(struct sk_buff *skb)
kfree_skb(NFCT_FRAG6_CB(skb)->orig);
}
-/* Memory Tracking Functions. */
-static void frag_kfree_skb(struct sk_buff *skb)
-{
- atomic_sub(skb->truesize, &nf_init_frags.mem);
- nf_skb_free(skb);
- kfree_skb(skb);
-}
-
/* Destruction primitives. */
static __inline__ void fq_put(struct nf_ct_frag6_queue *fq)
@@ -282,66 +274,22 @@ static int nf_ct_frag6_queue(struct nf_ct_frag6_queue *fq, struct sk_buff *skb,
}
found:
- /* We found where to put this one. Check for overlap with
- * preceding fragment, and, if needed, align things so that
- * any overlaps are eliminated.
- */
- if (prev) {
- int i = (NFCT_FRAG6_CB(prev)->offset + prev->len) - offset;
-
- if (i > 0) {
- offset += i;
- if (end <= offset) {
- pr_debug("overlap\n");
- goto err;
- }
- if (!pskb_pull(skb, i)) {
- pr_debug("Can't pull\n");
- goto err;
- }
- if (skb->ip_summed != CHECKSUM_UNNECESSARY)
- skb->ip_summed = CHECKSUM_NONE;
- }
- }
-
- /* Look for overlap with succeeding segments.
- * If we can merge fragments, do it.
+ /* RFC5722, Section 4:
+ * When reassembling an IPv6 datagram, if
+ * one or more its constituent fragments is determined to be an
+ * overlapping fragment, the entire datagram (and any constituent
+ * fragments, including those not yet received) MUST be silently
+ * discarded.
*/
- while (next && NFCT_FRAG6_CB(next)->offset < end) {
- /* overlap is 'i' bytes */
- int i = end - NFCT_FRAG6_CB(next)->offset;
-
- if (i < next->len) {
- /* Eat head of the next overlapped fragment
- * and leave the loop. The next ones cannot overlap.
- */
- pr_debug("Eat head of the overlapped parts.: %d", i);
- if (!pskb_pull(next, i))
- goto err;
- /* next fragment */
- NFCT_FRAG6_CB(next)->offset += i;
- fq->q.meat -= i;
- if (next->ip_summed != CHECKSUM_UNNECESSARY)
- next->ip_summed = CHECKSUM_NONE;
- break;
- } else {
- struct sk_buff *free_it = next;
-
- /* Old fragmnet is completely overridden with
- * new one drop it.
- */
- next = next->next;
+ /* Check for overlap with preceding fragment. */
+ if (prev &&
+ (NFCT_FRAG6_CB(prev)->offset + prev->len) - offset > 0)
+ goto discard_fq;
- if (prev)
- prev->next = next;
- else
- fq->q.fragments = next;
-
- fq->q.meat -= free_it->len;
- frag_kfree_skb(free_it);
- }
- }
+ /* Look for overlap with succeeding segment. */
+ if (next && NFCT_FRAG6_CB(next)->offset < end)
+ goto discard_fq;
NFCT_FRAG6_CB(skb)->offset = offset;
@@ -371,6 +319,8 @@ found:
write_unlock(&nf_frags.lock);
return 0;
+discard_fq:
+ fq_kill(fq);
err:
return -1;
}
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 545c4141b75..64cfef1b0a4 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -149,13 +149,6 @@ int ip6_frag_match(struct inet_frag_queue *q, void *a)
}
EXPORT_SYMBOL(ip6_frag_match);
-/* Memory Tracking Functions. */
-static void frag_kfree_skb(struct netns_frags *nf, struct sk_buff *skb)
-{
- atomic_sub(skb->truesize, &nf->mem);
- kfree_skb(skb);
-}
-
void ip6_frag_init(struct inet_frag_queue *q, void *a)
{
struct frag_queue *fq = container_of(q, struct frag_queue, q);
@@ -346,58 +339,22 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
}
found:
- /* We found where to put this one. Check for overlap with
- * preceding fragment, and, if needed, align things so that
- * any overlaps are eliminated.
+ /* RFC5722, Section 4:
+ * When reassembling an IPv6 datagram, if
+ * one or more its constituent fragments is determined to be an
+ * overlapping fragment, the entire datagram (and any constituent
+ * fragments, including those not yet received) MUST be silently
+ * discarded.
*/
- if (prev) {
- int i = (FRAG6_CB(prev)->offset + prev->len) - offset;
- if (i > 0) {
- offset += i;
- if (end <= offset)
- goto err;
- if (!pskb_pull(skb, i))
- goto err;
- if (skb->ip_summed != CHECKSUM_UNNECESSARY)
- skb->ip_summed = CHECKSUM_NONE;
- }
- }
+ /* Check for overlap with preceding fragment. */
+ if (prev &&
+ (FRAG6_CB(prev)->offset + prev->len) - offset > 0)
+ goto discard_fq;
- /* Look for overlap with succeeding segments.
- * If we can merge fragments, do it.
- */
- while (next && FRAG6_CB(next)->offset < end) {
- int i = end - FRAG6_CB(next)->offset; /* overlap is 'i' bytes */
-
- if (i < next->len) {
- /* Eat head of the next overlapped fragment
- * and leave the loop. The next ones cannot overlap.
- */
- if (!pskb_pull(next, i))
- goto err;
- FRAG6_CB(next)->offset += i; /* next fragment */
- fq->q.meat -= i;
- if (next->ip_summed != CHECKSUM_UNNECESSARY)
- next->ip_summed = CHECKSUM_NONE;
- break;
- } else {
- struct sk_buff *free_it = next;
-
- /* Old fragment is completely overridden with
- * new one drop it.
- */
- next = next->next;
-
- if (prev)
- prev->next = next;
- else
- fq->q.fragments = next;
-
- fq->q.meat -= free_it->len;
- frag_kfree_skb(fq->q.net, free_it);
- }
- }
+ /* Look for overlap with succeeding segment. */
+ if (next && FRAG6_CB(next)->offset < end)
+ goto discard_fq;
FRAG6_CB(skb)->offset = offset;
@@ -436,6 +393,8 @@ found:
write_unlock(&ip6_frags.lock);
return -1;
+discard_fq:
+ fq_kill(fq);
err:
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_REASMFAILS);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 8f2d0400cf8..a275c6e1e25 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -670,7 +670,7 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *dad
if (net_ratelimit())
printk(KERN_WARNING
- "Neighbour table overflow.\n");
+ "ipv6: Neighbour table overflow.\n");
dst_free(&rt->dst);
return NULL;
}
@@ -1556,14 +1556,13 @@ out:
* i.e. Path MTU discovery
*/
-void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr,
- struct net_device *dev, u32 pmtu)
+static void rt6_do_pmtu_disc(struct in6_addr *daddr, struct in6_addr *saddr,
+ struct net *net, u32 pmtu, int ifindex)
{
struct rt6_info *rt, *nrt;
- struct net *net = dev_net(dev);
int allfrag = 0;
- rt = rt6_lookup(net, daddr, saddr, dev->ifindex, 0);
+ rt = rt6_lookup(net, daddr, saddr, ifindex, 0);
if (rt == NULL)
return;
@@ -1631,6 +1630,27 @@ out:
dst_release(&rt->dst);
}
+void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr,
+ struct net_device *dev, u32 pmtu)
+{
+ struct net *net = dev_net(dev);
+
+ /*
+ * RFC 1981 states that a node "MUST reduce the size of the packets it
+ * is sending along the path" that caused the Packet Too Big message.
+ * Since it's not possible in the general case to determine which
+ * interface was used to send the original packet, we update the MTU
+ * on the interface that will be used to send future packets. We also
+ * update the MTU on the interface that received the Packet Too Big in
+ * case the original packet was forced out that interface with
+ * SO_BINDTODEVICE or similar. This is the next best thing to the
+ * correct behaviour, which would be to update the MTU on all
+ * interfaces.
+ */
+ rt6_do_pmtu_disc(daddr, saddr, net, pmtu, 0);
+ rt6_do_pmtu_disc(daddr, saddr, net, pmtu, dev->ifindex);
+}
+
/*
* Misc support functions
*/
@@ -2580,7 +2600,7 @@ ctl_table ipv6_route_table_template[] = {
.data = &init_net.ipv6.sysctl.ip6_rt_gc_elasticity,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec_jiffies,
+ .proc_handler = proc_dointvec,
},
{
.procname = "mtu_expires",
@@ -2594,7 +2614,7 @@ ctl_table ipv6_route_table_template[] = {
.data = &init_net.ipv6.sysctl.ip6_rt_min_advmss,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec_jiffies,
+ .proc_handler = proc_dointvec,
},
{
.procname = "gc_min_interval_ms",
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 1dd1affdead..5acb3560ff1 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -111,6 +111,15 @@ int udp_v6_get_port(struct sock *sk, unsigned short snum)
return udp_lib_get_port(sk, snum, ipv6_rcv_saddr_equal, hash2_nulladdr);
}
+static void udp_v6_rehash(struct sock *sk)
+{
+ u16 new_hash = udp6_portaddr_hash(sock_net(sk),
+ &inet6_sk(sk)->rcv_saddr,
+ inet_sk(sk)->inet_num);
+
+ udp_lib_rehash(sk, new_hash);
+}
+
static inline int compute_score(struct sock *sk, struct net *net,
unsigned short hnum,
struct in6_addr *saddr, __be16 sport,
@@ -1447,6 +1456,7 @@ struct proto udpv6_prot = {
.backlog_rcv = udpv6_queue_rcv_skb,
.hash = udp_lib_hash,
.unhash = udp_lib_unhash,
+ .rehash = udp_v6_rehash,
.get_port = udp_v6_get_port,
.memory_allocated = &udp_memory_allocated,
.sysctl_mem = sysctl_udp_mem,
diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c
index f417b77fa0e..a67575d472a 100644
--- a/net/ipv6/xfrm6_state.c
+++ b/net/ipv6/xfrm6_state.c
@@ -20,23 +20,27 @@
#include <net/addrconf.h>
static void
-__xfrm6_init_tempsel(struct xfrm_state *x, struct flowi *fl,
- struct xfrm_tmpl *tmpl,
- xfrm_address_t *daddr, xfrm_address_t *saddr)
+__xfrm6_init_tempsel(struct xfrm_selector *sel, struct flowi *fl)
{
/* Initialize temporary selector matching only
* to current session. */
- ipv6_addr_copy((struct in6_addr *)&x->sel.daddr, &fl->fl6_dst);
- ipv6_addr_copy((struct in6_addr *)&x->sel.saddr, &fl->fl6_src);
- x->sel.dport = xfrm_flowi_dport(fl);
- x->sel.dport_mask = htons(0xffff);
- x->sel.sport = xfrm_flowi_sport(fl);
- x->sel.sport_mask = htons(0xffff);
- x->sel.family = AF_INET6;
- x->sel.prefixlen_d = 128;
- x->sel.prefixlen_s = 128;
- x->sel.proto = fl->proto;
- x->sel.ifindex = fl->oif;
+ ipv6_addr_copy((struct in6_addr *)&sel->daddr, &fl->fl6_dst);
+ ipv6_addr_copy((struct in6_addr *)&sel->saddr, &fl->fl6_src);
+ sel->dport = xfrm_flowi_dport(fl);
+ sel->dport_mask = htons(0xffff);
+ sel->sport = xfrm_flowi_sport(fl);
+ sel->sport_mask = htons(0xffff);
+ sel->family = AF_INET6;
+ sel->prefixlen_d = 128;
+ sel->prefixlen_s = 128;
+ sel->proto = fl->proto;
+ sel->ifindex = fl->oif;
+}
+
+static void
+xfrm6_init_temprop(struct xfrm_state *x, struct xfrm_tmpl *tmpl,
+ xfrm_address_t *daddr, xfrm_address_t *saddr)
+{
x->id = tmpl->id;
if (ipv6_addr_any((struct in6_addr*)&x->id.daddr))
memcpy(&x->id.daddr, daddr, sizeof(x->sel.daddr));
@@ -168,6 +172,7 @@ static struct xfrm_state_afinfo xfrm6_state_afinfo = {
.eth_proto = htons(ETH_P_IPV6),
.owner = THIS_MODULE,
.init_tempsel = __xfrm6_init_tempsel,
+ .init_temprop = xfrm6_init_temprop,
.tmpl_sort = __xfrm6_tmpl_sort,
.state_sort = __xfrm6_state_sort,
.output = xfrm6_output,
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 79986a674f6..fd55b5135de 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -824,8 +824,8 @@ static int irda_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
err = irda_open_tsap(self, addr->sir_lsap_sel, addr->sir_name);
if (err < 0) {
- kfree(self->ias_obj->name);
- kfree(self->ias_obj);
+ irias_delete_object(self->ias_obj);
+ self->ias_obj = NULL;
goto out;
}
diff --git a/net/irda/irlan/irlan_common.c b/net/irda/irlan/irlan_common.c
index a788f9e9427..6130f9d9dbe 100644
--- a/net/irda/irlan/irlan_common.c
+++ b/net/irda/irlan/irlan_common.c
@@ -1102,7 +1102,7 @@ int irlan_extract_param(__u8 *buf, char *name, char *value, __u16 *len)
memcpy(&val_len, buf+n, 2); /* To avoid alignment problems */
le16_to_cpus(&val_len); n+=2;
- if (val_len > 1016) {
+ if (val_len >= 1016) {
IRDA_DEBUG(2, "%s(), parameter length to long\n", __func__ );
return -RSP_INVALID_COMMAND_FORMAT;
}
diff --git a/net/irda/irlan/irlan_eth.c b/net/irda/irlan/irlan_eth.c
index 9616c32d107..5bb8353105c 100644
--- a/net/irda/irlan/irlan_eth.c
+++ b/net/irda/irlan/irlan_eth.c
@@ -169,6 +169,7 @@ static netdev_tx_t irlan_eth_xmit(struct sk_buff *skb,
{
struct irlan_cb *self = netdev_priv(dev);
int ret;
+ unsigned int len;
/* skb headroom large enough to contain all IrDA-headers? */
if ((skb_headroom(skb) < self->max_header_size) || (skb_shared(skb))) {
@@ -188,6 +189,7 @@ static netdev_tx_t irlan_eth_xmit(struct sk_buff *skb,
dev->trans_start = jiffies;
+ len = skb->len;
/* Now queue the packet in the transport layer */
if (self->use_udata)
ret = irttp_udata_request(self->tsap_data, skb);
@@ -209,7 +211,7 @@ static netdev_tx_t irlan_eth_xmit(struct sk_buff *skb,
self->stats.tx_dropped++;
} else {
self->stats.tx_packets++;
- self->stats.tx_bytes += skb->len;
+ self->stats.tx_bytes += len;
}
return NETDEV_TX_OK;
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index 58c6c4cda73..1ae697681bc 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -132,7 +132,7 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb,
printk("\n");
}
- if (data_len < ETH_HLEN)
+ if (!pskb_may_pull(skb, sizeof(ETH_HLEN)))
goto error;
secpath_reset(skb);
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 023ba820236..58261299821 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -1024,7 +1024,8 @@ static int llc_ui_setsockopt(struct socket *sock, int level, int optname,
{
struct sock *sk = sock->sk;
struct llc_sock *llc = llc_sk(sk);
- int rc = -EINVAL, opt;
+ unsigned int opt;
+ int rc = -EINVAL;
lock_sock(sk);
if (unlikely(level != SOL_LLC || optlen != sizeof(int)))
diff --git a/net/llc/llc_station.c b/net/llc/llc_station.c
index e4dae0244d7..cf4aea3ba30 100644
--- a/net/llc/llc_station.c
+++ b/net/llc/llc_station.c
@@ -689,7 +689,7 @@ static void llc_station_rcv(struct sk_buff *skb)
int __init llc_station_init(void)
{
- u16 rc = -ENOBUFS;
+ int rc = -ENOBUFS;
struct sk_buff *skb;
struct llc_station_state_ev *ev;
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index 6d0bd198af1..be04d46110f 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -103,6 +103,7 @@ ieee80211_rate_control_ops_get(const char *name)
struct rate_control_ops *ops;
const char *alg_name;
+ kparam_block_sysfs_write(ieee80211_default_rc_algo);
if (!name)
alg_name = ieee80211_default_rc_algo;
else
@@ -120,6 +121,7 @@ ieee80211_rate_control_ops_get(const char *name)
/* try built-in one if specific alg requested but not found */
if (!ops && strlen(CONFIG_MAC80211_RC_DEFAULT))
ops = ieee80211_try_rate_control_ops_get(CONFIG_MAC80211_RC_DEFAULT);
+ kparam_unblock_sysfs_write(ieee80211_default_rc_algo);
return ops;
}
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 4f8ddba4801..4c2f89df5cc 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -924,6 +924,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
ip_vs_out_stats(cp, skb);
ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pp);
+ ip_vs_update_conntrack(skb, cp, 0);
ip_vs_conn_put(cp);
skb->ipvs_property = 1;
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index f228a17ec64..7e9af5b76d9 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -45,6 +45,7 @@
#include <linux/netfilter.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_expect.h>
+#include <net/netfilter/nf_nat.h>
#include <net/netfilter/nf_nat_helper.h>
#include <linux/gfp.h>
#include <net/protocol.h>
@@ -359,7 +360,7 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
buf_len = strlen(buf);
ct = nf_ct_get(skb, &ctinfo);
- if (ct && !nf_ct_is_untracked(ct)) {
+ if (ct && !nf_ct_is_untracked(ct) && nfct_nat(ct)) {
/* If mangling fails this function will return 0
* which will cause the packet to be dropped.
* Mangling can only fail under memory pressure,
@@ -409,7 +410,6 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
union nf_inet_addr to;
__be16 port;
struct ip_vs_conn *n_cp;
- struct nf_conn *ct;
#ifdef CONFIG_IP_VS_IPV6
/* This application helper doesn't work with IPv6 yet,
@@ -496,11 +496,6 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
ip_vs_control_add(n_cp, cp);
}
- ct = (struct nf_conn *)skb->nfct;
- if (ct && ct != &nf_conntrack_untracked)
- ip_vs_expect_related(skb, ct, n_cp,
- IPPROTO_TCP, &n_cp->dport, 1);
-
/*
* Move tunnel to listen state
*/
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 21e1a5e9b9d..49df6bea6a2 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -349,8 +349,8 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
}
#endif
-static void
-ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp)
+void
+ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp, int outin)
{
struct nf_conn *ct = (struct nf_conn *)skb->nfct;
struct nf_conntrack_tuple new_tuple;
@@ -365,11 +365,17 @@ ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp)
* real-server we will see RIP->DIP.
*/
new_tuple = ct->tuplehash[IP_CT_DIR_REPLY].tuple;
- new_tuple.src.u3 = cp->daddr;
+ if (outin)
+ new_tuple.src.u3 = cp->daddr;
+ else
+ new_tuple.dst.u3 = cp->vaddr;
/*
* This will also take care of UDP and other protocols.
*/
- new_tuple.src.u.tcp.port = cp->dport;
+ if (outin)
+ new_tuple.src.u.tcp.port = cp->dport;
+ else
+ new_tuple.dst.u.tcp.port = cp->vport;
nf_conntrack_alter_reply(ct, &new_tuple);
}
@@ -428,7 +434,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT");
- ip_vs_update_conntrack(skb, cp);
+ ip_vs_update_conntrack(skb, cp, 1);
/* FIXME: when application helper enlarges the packet and the length
is larger than the MTU of outgoing device, there will be still
@@ -506,7 +512,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT");
- ip_vs_update_conntrack(skb, cp);
+ ip_vs_update_conntrack(skb, cp, 1);
/* FIXME: when application helper enlarges the packet and the length
is larger than the MTU of outgoing device, there will be still
diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c
index 7dcf7a40419..8d9e4c949b9 100644
--- a/net/netfilter/nf_conntrack_extend.c
+++ b/net/netfilter/nf_conntrack_extend.c
@@ -48,15 +48,17 @@ nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id, gfp_t gfp)
{
unsigned int off, len;
struct nf_ct_ext_type *t;
+ size_t alloc_size;
rcu_read_lock();
t = rcu_dereference(nf_ct_ext_types[id]);
BUG_ON(t == NULL);
off = ALIGN(sizeof(struct nf_ct_ext), t->align);
len = off + t->len;
+ alloc_size = t->alloc_size;
rcu_read_unlock();
- *ext = kzalloc(t->alloc_size, gfp);
+ *ext = kzalloc(alloc_size, gfp);
if (!*ext)
return NULL;
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 53d892210a0..f64de954486 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -1376,7 +1376,7 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff,
unsigned int msglen, origlen;
const char *dptr, *end;
s16 diff, tdiff = 0;
- int ret;
+ int ret = NF_ACCEPT;
typeof(nf_nat_sip_seq_adjust_hook) nf_nat_sip_seq_adjust;
if (ctinfo != IP_CT_ESTABLISHED &&
diff --git a/net/netfilter/nf_tproxy_core.c b/net/netfilter/nf_tproxy_core.c
index 5490fc37c92..daab8c4a903 100644
--- a/net/netfilter/nf_tproxy_core.c
+++ b/net/netfilter/nf_tproxy_core.c
@@ -70,7 +70,11 @@ nf_tproxy_destructor(struct sk_buff *skb)
int
nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk)
{
- if (inet_sk(sk)->transparent) {
+ bool transparent = (sk->sk_state == TCP_TIME_WAIT) ?
+ inet_twsk(sk)->tw_transparent :
+ inet_sk(sk)->transparent;
+
+ if (transparent) {
skb_orphan(skb);
skb->sk = sk;
skb->destructor = nf_tproxy_destructor;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 2cbf380377d..cd96ed3ccee 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1406,7 +1406,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
struct netlink_sock *nlk = nlk_sk(sk);
int noblock = flags&MSG_DONTWAIT;
size_t copied;
- struct sk_buff *skb;
+ struct sk_buff *skb, *data_skb;
int err;
if (flags&MSG_OOB)
@@ -1418,59 +1418,35 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
if (skb == NULL)
goto out;
+ data_skb = skb;
+
#ifdef CONFIG_COMPAT_NETLINK_MESSAGES
if (unlikely(skb_shinfo(skb)->frag_list)) {
- bool need_compat = !!(flags & MSG_CMSG_COMPAT);
-
/*
- * If this skb has a frag_list, then here that means that
- * we will have to use the frag_list skb for compat tasks
- * and the regular skb for non-compat tasks.
+ * If this skb has a frag_list, then here that means that we
+ * will have to use the frag_list skb's data for compat tasks
+ * and the regular skb's data for normal (non-compat) tasks.
*
- * The skb might (and likely will) be cloned, so we can't
- * just reset frag_list and go on with things -- we need to
- * keep that. For the compat case that's easy -- simply get
- * a reference to the compat skb and free the regular one
- * including the frag. For the non-compat case, we need to
- * avoid sending the frag to the user -- so assign NULL but
- * restore it below before freeing the skb.
+ * If we need to send the compat skb, assign it to the
+ * 'data_skb' variable so that it will be used below for data
+ * copying. We keep 'skb' for everything else, including
+ * freeing both later.
*/
- if (need_compat) {
- struct sk_buff *compskb = skb_shinfo(skb)->frag_list;
- skb_get(compskb);
- kfree_skb(skb);
- skb = compskb;
- } else {
- /*
- * Before setting frag_list to NULL, we must get a
- * private copy of skb if shared (because of MSG_PEEK)
- */
- if (skb_shared(skb)) {
- struct sk_buff *nskb;
-
- nskb = pskb_copy(skb, GFP_KERNEL);
- kfree_skb(skb);
- skb = nskb;
- err = -ENOMEM;
- if (!skb)
- goto out;
- }
- kfree_skb(skb_shinfo(skb)->frag_list);
- skb_shinfo(skb)->frag_list = NULL;
- }
+ if (flags & MSG_CMSG_COMPAT)
+ data_skb = skb_shinfo(skb)->frag_list;
}
#endif
msg->msg_namelen = 0;
- copied = skb->len;
+ copied = data_skb->len;
if (len < copied) {
msg->msg_flags |= MSG_TRUNC;
copied = len;
}
- skb_reset_transport_header(skb);
- err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+ skb_reset_transport_header(data_skb);
+ err = skb_copy_datagram_iovec(data_skb, 0, msg->msg_iov, copied);
if (msg->msg_name) {
struct sockaddr_nl *addr = (struct sockaddr_nl *)msg->msg_name;
@@ -1490,7 +1466,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
}
siocb->scm->creds = *NETLINK_CREDS(skb);
if (flags & MSG_TRUNC)
- copied = skb->len;
+ copied = data_skb->len;
skb_free_datagram(sk, skb);
@@ -2126,6 +2102,26 @@ static void __net_exit netlink_net_exit(struct net *net)
#endif
}
+static void __init netlink_add_usersock_entry(void)
+{
+ unsigned long *listeners;
+ int groups = 32;
+
+ listeners = kzalloc(NLGRPSZ(groups) + sizeof(struct listeners_rcu_head),
+ GFP_KERNEL);
+ if (!listeners)
+ panic("netlink_add_usersock_entry: Cannot allocate listneres\n");
+
+ netlink_table_grab();
+
+ nl_table[NETLINK_USERSOCK].groups = groups;
+ nl_table[NETLINK_USERSOCK].listeners = listeners;
+ nl_table[NETLINK_USERSOCK].module = THIS_MODULE;
+ nl_table[NETLINK_USERSOCK].registered = 1;
+
+ netlink_table_ungrab();
+}
+
static struct pernet_operations __net_initdata netlink_net_ops = {
.init = netlink_net_init,
.exit = netlink_net_exit,
@@ -2174,6 +2170,8 @@ static int __init netlink_proto_init(void)
hash->rehash_time = jiffies;
}
+ netlink_add_usersock_entry();
+
sock_register(&netlink_family_ops);
register_pernet_subsys(&netlink_net_ops);
/* The netlink device handler may be needed early. */
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index b2a3ae6cad7..15003021f4f 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -225,12 +225,13 @@ static void pipe_grant_credits(struct sock *sk)
static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb)
{
struct pep_sock *pn = pep_sk(sk);
- struct pnpipehdr *hdr = pnp_hdr(skb);
+ struct pnpipehdr *hdr;
int wake = 0;
if (!pskb_may_pull(skb, sizeof(*hdr) + 4))
return -EINVAL;
+ hdr = pnp_hdr(skb);
if (hdr->data[0] != PN_PEP_TYPE_COMMON) {
LIMIT_NETDEBUG(KERN_DEBUG"Phonet unknown PEP type: %u\n",
(unsigned)hdr->data[0]);
diff --git a/net/rds/recv.c b/net/rds/recv.c
index 795a00b7f2c..c93588c2d55 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -297,7 +297,7 @@ static int rds_still_queued(struct rds_sock *rs, struct rds_incoming *inc,
int rds_notify_queue_get(struct rds_sock *rs, struct msghdr *msghdr)
{
struct rds_notifier *notifier;
- struct rds_rdma_notify cmsg;
+ struct rds_rdma_notify cmsg = { 0 }; /* fill holes with zero */
unsigned int count = 0, max_messages = ~0U;
unsigned long flags;
LIST_HEAD(copy);
diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c
index c397524c039..c519939e8da 100644
--- a/net/rds/tcp_connect.c
+++ b/net/rds/tcp_connect.c
@@ -43,7 +43,7 @@ void rds_tcp_state_change(struct sock *sk)
struct rds_connection *conn;
struct rds_tcp_connection *tc;
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
conn = sk->sk_user_data;
if (conn == NULL) {
state_change = sk->sk_state_change;
@@ -68,7 +68,7 @@ void rds_tcp_state_change(struct sock *sk)
break;
}
out:
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
state_change(sk);
}
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 975183fe695..27844f231d1 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -114,7 +114,7 @@ void rds_tcp_listen_data_ready(struct sock *sk, int bytes)
rdsdebug("listen data ready sk %p\n", sk);
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
ready = sk->sk_user_data;
if (ready == NULL) { /* check for teardown race */
ready = sk->sk_data_ready;
@@ -131,7 +131,7 @@ void rds_tcp_listen_data_ready(struct sock *sk, int bytes)
queue_work(rds_wq, &rds_tcp_listen_work);
out:
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
ready(sk, bytes);
}
diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c
index 1aba6878fa5..e4379740410 100644
--- a/net/rds/tcp_recv.c
+++ b/net/rds/tcp_recv.c
@@ -324,7 +324,7 @@ void rds_tcp_data_ready(struct sock *sk, int bytes)
rdsdebug("data ready sk %p bytes %d\n", sk, bytes);
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
conn = sk->sk_user_data;
if (conn == NULL) { /* check for teardown race */
ready = sk->sk_data_ready;
@@ -338,7 +338,7 @@ void rds_tcp_data_ready(struct sock *sk, int bytes)
if (rds_tcp_read_sock(conn, GFP_ATOMIC, KM_SOFTIRQ0) == -ENOMEM)
queue_delayed_work(rds_wq, &conn->c_recv_w, 0);
out:
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
ready(sk, bytes);
}
diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c
index a28b895ff0d..2f012a07d94 100644
--- a/net/rds/tcp_send.c
+++ b/net/rds/tcp_send.c
@@ -224,7 +224,7 @@ void rds_tcp_write_space(struct sock *sk)
struct rds_connection *conn;
struct rds_tcp_connection *tc;
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
conn = sk->sk_user_data;
if (conn == NULL) {
write_space = sk->sk_write_space;
@@ -244,7 +244,7 @@ void rds_tcp_write_space(struct sock *sk)
queue_delayed_work(rds_wq, &conn->c_send_w, 0);
out:
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
/*
* write_space is only called when data leaves tcp's send queue if
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 8e45e76a95f..d952e7eac18 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -679,7 +679,7 @@ static int rose_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
if (addr_len == sizeof(struct sockaddr_rose) && addr->srose_ndigis > 1)
return -EINVAL;
- if (addr->srose_ndigis > ROSE_MAX_DIGIS)
+ if ((unsigned int) addr->srose_ndigis > ROSE_MAX_DIGIS)
return -EINVAL;
if ((dev = rose_dev_get(&addr->srose_addr)) == NULL) {
@@ -739,7 +739,7 @@ static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_le
if (addr_len == sizeof(struct sockaddr_rose) && addr->srose_ndigis > 1)
return -EINVAL;
- if (addr->srose_ndigis > ROSE_MAX_DIGIS)
+ if ((unsigned int) addr->srose_ndigis > ROSE_MAX_DIGIS)
return -EINVAL;
/* Source + Destination digis should not exceed ROSE_MAX_DIGIS */
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 7043b294bb6..8e22bd345e7 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -597,12 +597,6 @@ extern unsigned rxrpc_debug;
#define dbgprintk(FMT,...) \
printk("[%-6.6s] "FMT"\n", current->comm ,##__VA_ARGS__)
-/* make sure we maintain the format strings, even when debugging is disabled */
-static inline __attribute__((format(printf,1,2)))
-void _dbprintk(const char *fmt, ...)
-{
-}
-
#define kenter(FMT,...) dbgprintk("==> %s("FMT")",__func__ ,##__VA_ARGS__)
#define kleave(FMT,...) dbgprintk("<== %s()"FMT"",__func__ ,##__VA_ARGS__)
#define kdebug(FMT,...) dbgprintk(" "FMT ,##__VA_ARGS__)
@@ -655,11 +649,11 @@ do { \
} while (0)
#else
-#define _enter(FMT,...) _dbprintk("==> %s("FMT")",__func__ ,##__VA_ARGS__)
-#define _leave(FMT,...) _dbprintk("<== %s()"FMT"",__func__ ,##__VA_ARGS__)
-#define _debug(FMT,...) _dbprintk(" "FMT ,##__VA_ARGS__)
-#define _proto(FMT,...) _dbprintk("### "FMT ,##__VA_ARGS__)
-#define _net(FMT,...) _dbprintk("@@@ "FMT ,##__VA_ARGS__)
+#define _enter(FMT,...) no_printk("==> %s("FMT")",__func__ ,##__VA_ARGS__)
+#define _leave(FMT,...) no_printk("<== %s()"FMT"",__func__ ,##__VA_ARGS__)
+#define _debug(FMT,...) no_printk(" "FMT ,##__VA_ARGS__)
+#define _proto(FMT,...) no_printk("### "FMT ,##__VA_ARGS__)
+#define _net(FMT,...) no_printk("@@@ "FMT ,##__VA_ARGS__)
#endif
/*
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index 8406c665499..c2ed90a4c0b 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -152,21 +152,24 @@ static int tcf_gact(struct sk_buff *skb, struct tc_action *a, struct tcf_result
static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
{
unsigned char *b = skb_tail_pointer(skb);
- struct tc_gact opt;
struct tcf_gact *gact = a->priv;
+ struct tc_gact opt = {
+ .index = gact->tcf_index,
+ .refcnt = gact->tcf_refcnt - ref,
+ .bindcnt = gact->tcf_bindcnt - bind,
+ .action = gact->tcf_action,
+ };
struct tcf_t t;
- opt.index = gact->tcf_index;
- opt.refcnt = gact->tcf_refcnt - ref;
- opt.bindcnt = gact->tcf_bindcnt - bind;
- opt.action = gact->tcf_action;
NLA_PUT(skb, TCA_GACT_PARMS, sizeof(opt), &opt);
#ifdef CONFIG_GACT_PROB
if (gact->tcfg_ptype) {
- struct tc_gact_p p_opt;
- p_opt.paction = gact->tcfg_paction;
- p_opt.pval = gact->tcfg_pval;
- p_opt.ptype = gact->tcfg_ptype;
+ struct tc_gact_p p_opt = {
+ .paction = gact->tcfg_paction,
+ .pval = gact->tcfg_pval,
+ .ptype = gact->tcfg_ptype,
+ };
+
NLA_PUT(skb, TCA_GACT_PROB, sizeof(p_opt), &p_opt);
}
#endif
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 11f195af2da..0c311be9282 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -219,15 +219,16 @@ static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, i
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_mirred *m = a->priv;
- struct tc_mirred opt;
+ struct tc_mirred opt = {
+ .index = m->tcf_index,
+ .action = m->tcf_action,
+ .refcnt = m->tcf_refcnt - ref,
+ .bindcnt = m->tcf_bindcnt - bind,
+ .eaction = m->tcfm_eaction,
+ .ifindex = m->tcfm_ifindex,
+ };
struct tcf_t t;
- opt.index = m->tcf_index;
- opt.action = m->tcf_action;
- opt.refcnt = m->tcf_refcnt - ref;
- opt.bindcnt = m->tcf_bindcnt - bind;
- opt.eaction = m->tcfm_eaction;
- opt.ifindex = m->tcfm_ifindex;
NLA_PUT(skb, TCA_MIRRED_PARMS, sizeof(opt), &opt);
t.install = jiffies_to_clock_t(jiffies - m->tcf_tm.install);
t.lastuse = jiffies_to_clock_t(jiffies - m->tcf_tm.lastuse);
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 509a2d53a99..186eb837e60 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -272,19 +272,19 @@ static int tcf_nat_dump(struct sk_buff *skb, struct tc_action *a,
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_nat *p = a->priv;
- struct tc_nat opt;
+ struct tc_nat opt = {
+ .old_addr = p->old_addr,
+ .new_addr = p->new_addr,
+ .mask = p->mask,
+ .flags = p->flags,
+
+ .index = p->tcf_index,
+ .action = p->tcf_action,
+ .refcnt = p->tcf_refcnt - ref,
+ .bindcnt = p->tcf_bindcnt - bind,
+ };
struct tcf_t t;
- opt.old_addr = p->old_addr;
- opt.new_addr = p->new_addr;
- opt.mask = p->mask;
- opt.flags = p->flags;
-
- opt.index = p->tcf_index;
- opt.action = p->tcf_action;
- opt.refcnt = p->tcf_refcnt - ref;
- opt.bindcnt = p->tcf_bindcnt - bind;
-
NLA_PUT(skb, TCA_NAT_PARMS, sizeof(opt), &opt);
t.install = jiffies_to_clock_t(jiffies - p->tcf_tm.install);
t.lastuse = jiffies_to_clock_t(jiffies - p->tcf_tm.lastuse);
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 537a48732e9..7ebf7439b47 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -350,22 +350,19 @@ tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_police *police = a->priv;
- struct tc_police opt;
-
- opt.index = police->tcf_index;
- opt.action = police->tcf_action;
- opt.mtu = police->tcfp_mtu;
- opt.burst = police->tcfp_burst;
- opt.refcnt = police->tcf_refcnt - ref;
- opt.bindcnt = police->tcf_bindcnt - bind;
+ struct tc_police opt = {
+ .index = police->tcf_index,
+ .action = police->tcf_action,
+ .mtu = police->tcfp_mtu,
+ .burst = police->tcfp_burst,
+ .refcnt = police->tcf_refcnt - ref,
+ .bindcnt = police->tcf_bindcnt - bind,
+ };
+
if (police->tcfp_R_tab)
opt.rate = police->tcfp_R_tab->rate;
- else
- memset(&opt.rate, 0, sizeof(opt.rate));
if (police->tcfp_P_tab)
opt.peakrate = police->tcfp_P_tab->rate;
- else
- memset(&opt.peakrate, 0, sizeof(opt.peakrate));
NLA_PUT(skb, TCA_POLICE_TBF, sizeof(opt), &opt);
if (police->tcfp_result)
NLA_PUT_U32(skb, TCA_POLICE_RESULT, police->tcfp_result);
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 4a1d640b0cf..97e84f3ee77 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -164,13 +164,14 @@ static inline int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a,
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_defact *d = a->priv;
- struct tc_defact opt;
+ struct tc_defact opt = {
+ .index = d->tcf_index,
+ .refcnt = d->tcf_refcnt - ref,
+ .bindcnt = d->tcf_bindcnt - bind,
+ .action = d->tcf_action,
+ };
struct tcf_t t;
- opt.index = d->tcf_index;
- opt.refcnt = d->tcf_refcnt - ref;
- opt.bindcnt = d->tcf_bindcnt - bind;
- opt.action = d->tcf_action;
NLA_PUT(skb, TCA_DEF_PARMS, sizeof(opt), &opt);
NLA_PUT_STRING(skb, TCA_DEF_DATA, d->tcfd_defdata);
t.install = jiffies_to_clock_t(jiffies - d->tcf_tm.install);
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index e9607fe55b5..66cbf4eb885 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -159,13 +159,14 @@ static inline int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a,
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_skbedit *d = a->priv;
- struct tc_skbedit opt;
+ struct tc_skbedit opt = {
+ .index = d->tcf_index,
+ .refcnt = d->tcf_refcnt - ref,
+ .bindcnt = d->tcf_bindcnt - bind,
+ .action = d->tcf_action,
+ };
struct tcf_t t;
- opt.index = d->tcf_index;
- opt.refcnt = d->tcf_refcnt - ref;
- opt.bindcnt = d->tcf_bindcnt - bind;
- opt.action = d->tcf_action;
NLA_PUT(skb, TCA_SKBEDIT_PARMS, sizeof(opt), &opt);
if (d->flags & SKBEDIT_F_PRIORITY)
NLA_PUT(skb, TCA_SKBEDIT_PRIORITY, sizeof(d->priority),
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 7416a5c73b2..b0c2a82178a 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -137,7 +137,7 @@ next_knode:
int toff = off + key->off + (off2 & key->offmask);
__be32 *data, _data;
- if (skb_headroom(skb) + toff < 0)
+ if (skb_headroom(skb) + toff > INT_MAX)
goto out;
data = skb_header_pointer(skb, toff, 4, &_data);
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index b9e8c3b7d40..408eea7086a 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -150,22 +150,34 @@ int register_qdisc(struct Qdisc_ops *qops)
if (qops->enqueue == NULL)
qops->enqueue = noop_qdisc_ops.enqueue;
if (qops->peek == NULL) {
- if (qops->dequeue == NULL) {
+ if (qops->dequeue == NULL)
qops->peek = noop_qdisc_ops.peek;
- } else {
- rc = -EINVAL;
- goto out;
- }
+ else
+ goto out_einval;
}
if (qops->dequeue == NULL)
qops->dequeue = noop_qdisc_ops.dequeue;
+ if (qops->cl_ops) {
+ const struct Qdisc_class_ops *cops = qops->cl_ops;
+
+ if (!(cops->get && cops->put && cops->walk && cops->leaf))
+ goto out_einval;
+
+ if (cops->tcf_chain && !(cops->bind_tcf && cops->unbind_tcf))
+ goto out_einval;
+ }
+
qops->next = NULL;
*qp = qops;
rc = 0;
out:
write_unlock(&qdisc_mod_lock);
return rc;
+
+out_einval:
+ rc = -EINVAL;
+ goto out;
}
EXPORT_SYMBOL(register_qdisc);
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index e114f23d5ea..6318e1136b8 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -255,10 +255,6 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent,
error = -EINVAL;
goto err_out;
}
- if (!list_empty(&flow->list)) {
- error = -EEXIST;
- goto err_out;
- }
} else {
int i;
unsigned long cl;
@@ -418,7 +414,7 @@ static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch)
}
ret = qdisc_enqueue(skb, flow->q);
- if (ret != 0) {
+ if (ret != NET_XMIT_SUCCESS) {
drop: __maybe_unused
if (net_xmit_drop_count(ret)) {
sch->qstats.drops++;
@@ -442,7 +438,7 @@ drop: __maybe_unused
*/
if (flow == &p->link) {
sch->q.qlen++;
- return 0;
+ return NET_XMIT_SUCCESS;
}
tasklet_schedule(&p->task);
return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index abd904be428..47496098d35 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -761,8 +761,8 @@ init_vf(struct hfsc_class *cl, unsigned int len)
if (f != cl->cl_f) {
cl->cl_f = f;
cftree_update(cl);
- update_cfmin(cl->cl_parent);
}
+ update_cfmin(cl->cl_parent);
}
}
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 534f33231c1..201cbac2b32 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -334,7 +334,7 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
if (++sch->q.qlen <= q->limit) {
sch->bstats.bytes += qdisc_pkt_len(skb);
sch->bstats.packets++;
- return 0;
+ return NET_XMIT_SUCCESS;
}
sfq_drop(sch);
@@ -508,6 +508,11 @@ nla_put_failure:
return -1;
}
+static struct Qdisc *sfq_leaf(struct Qdisc *sch, unsigned long arg)
+{
+ return NULL;
+}
+
static unsigned long sfq_get(struct Qdisc *sch, u32 classid)
{
return 0;
@@ -519,6 +524,10 @@ static unsigned long sfq_bind(struct Qdisc *sch, unsigned long parent,
return 0;
}
+static void sfq_put(struct Qdisc *q, unsigned long cl)
+{
+}
+
static struct tcf_proto **sfq_find_tcf(struct Qdisc *sch, unsigned long cl)
{
struct sfq_sched_data *q = qdisc_priv(sch);
@@ -571,9 +580,12 @@ static void sfq_walk(struct Qdisc *sch, struct qdisc_walker *arg)
}
static const struct Qdisc_class_ops sfq_class_ops = {
+ .leaf = sfq_leaf,
.get = sfq_get,
+ .put = sfq_put,
.tcf_chain = sfq_find_tcf,
.bind_tcf = sfq_bind,
+ .unbind_tcf = sfq_put,
.dump = sfq_dump_class,
.dump_stats = sfq_dump_class_stats,
.walk = sfq_walk,
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 0991c640cd3..641a30d6463 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -127,7 +127,7 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc* sch)
return qdisc_reshape_fail(skb, sch);
ret = qdisc_enqueue(skb, q->qdisc);
- if (ret != 0) {
+ if (ret != NET_XMIT_SUCCESS) {
if (net_xmit_drop_count(ret))
sch->qstats.drops++;
return ret;
@@ -136,7 +136,7 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc* sch)
sch->q.qlen++;
sch->bstats.bytes += qdisc_pkt_len(skb);
sch->bstats.packets++;
- return 0;
+ return NET_XMIT_SUCCESS;
}
static unsigned int tbf_drop(struct Qdisc* sch)
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index 807643bdcba..feaabc103ce 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -85,7 +85,7 @@ teql_enqueue(struct sk_buff *skb, struct Qdisc* sch)
__skb_queue_tail(&q->q, skb);
sch->bstats.bytes += qdisc_pkt_len(skb);
sch->bstats.packets++;
- return 0;
+ return NET_XMIT_SUCCESS;
}
kfree_skb(skb);
diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index 86366390038..ddbbf7c81fa 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -543,16 +543,20 @@ struct sctp_hmac *sctp_auth_asoc_get_hmac(const struct sctp_association *asoc)
id = ntohs(hmacs->hmac_ids[i]);
/* Check the id is in the supported range */
- if (id > SCTP_AUTH_HMAC_ID_MAX)
+ if (id > SCTP_AUTH_HMAC_ID_MAX) {
+ id = 0;
continue;
+ }
/* See is we support the id. Supported IDs have name and
* length fields set, so that we can allocated and use
* them. We can safely just check for name, for without the
* name, we can't allocate the TFM.
*/
- if (!sctp_hmac_list[id].hmac_name)
+ if (!sctp_hmac_list[id].hmac_name) {
+ id = 0;
continue;
+ }
break;
}
diff --git a/net/sctp/output.c b/net/sctp/output.c
index a646681f5ac..bcc4590ccaf 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -92,7 +92,6 @@ struct sctp_packet *sctp_packet_config(struct sctp_packet *packet,
SCTP_DEBUG_PRINTK("%s: packet:%p vtag:0x%x\n", __func__,
packet, vtag);
- sctp_packet_reset(packet);
packet->vtag = vtag;
if (ecn_capable && sctp_packet_empty(packet)) {
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 24b2cd55563..d344dc481cc 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -1232,6 +1232,18 @@ out:
return 0;
}
+static bool list_has_sctp_addr(const struct list_head *list,
+ union sctp_addr *ipaddr)
+{
+ struct sctp_transport *addr;
+
+ list_for_each_entry(addr, list, transports) {
+ if (sctp_cmp_addr_exact(ipaddr, &addr->ipaddr))
+ return true;
+ }
+
+ return false;
+}
/* A restart is occurring, check to make sure no new addresses
* are being added as we may be under a takeover attack.
*/
@@ -1240,10 +1252,10 @@ static int sctp_sf_check_restart_addrs(const struct sctp_association *new_asoc,
struct sctp_chunk *init,
sctp_cmd_seq_t *commands)
{
- struct sctp_transport *new_addr, *addr;
- int found;
+ struct sctp_transport *new_addr;
+ int ret = 1;
- /* Implementor's Guide - Sectin 5.2.2
+ /* Implementor's Guide - Section 5.2.2
* ...
* Before responding the endpoint MUST check to see if the
* unexpected INIT adds new addresses to the association. If new
@@ -1254,31 +1266,19 @@ static int sctp_sf_check_restart_addrs(const struct sctp_association *new_asoc,
/* Search through all current addresses and make sure
* we aren't adding any new ones.
*/
- new_addr = NULL;
- found = 0;
-
list_for_each_entry(new_addr, &new_asoc->peer.transport_addr_list,
- transports) {
- found = 0;
- list_for_each_entry(addr, &asoc->peer.transport_addr_list,
- transports) {
- if (sctp_cmp_addr_exact(&new_addr->ipaddr,
- &addr->ipaddr)) {
- found = 1;
- break;
- }
- }
- if (!found)
+ transports) {
+ if (!list_has_sctp_addr(&asoc->peer.transport_addr_list,
+ &new_addr->ipaddr)) {
+ sctp_sf_send_restart_abort(&new_addr->ipaddr, init,
+ commands);
+ ret = 0;
break;
- }
-
- /* If a new address was added, ABORT the sender. */
- if (!found && new_addr) {
- sctp_sf_send_restart_abort(&new_addr->ipaddr, init, commands);
+ }
}
/* Return success if all addresses were found. */
- return found;
+ return ret;
}
/* Populate the verification/tie tags based on overlapping INIT
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index ca44917872d..fbb70770ad0 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -916,6 +916,11 @@ SCTP_STATIC int sctp_setsockopt_bindx(struct sock* sk,
/* Walk through the addrs buffer and count the number of addresses. */
addr_buf = kaddrs;
while (walk_size < addrs_size) {
+ if (walk_size + sizeof(sa_family_t) > addrs_size) {
+ kfree(kaddrs);
+ return -EINVAL;
+ }
+
sa_addr = (struct sockaddr *)addr_buf;
af = sctp_get_af_specific(sa_addr->sa_family);
@@ -1002,9 +1007,13 @@ static int __sctp_connect(struct sock* sk,
/* Walk through the addrs buffer and count the number of addresses. */
addr_buf = kaddrs;
while (walk_size < addrs_size) {
+ if (walk_size + sizeof(sa_family_t) > addrs_size) {
+ err = -EINVAL;
+ goto out_free;
+ }
+
sa_addr = (union sctp_addr *)addr_buf;
af = sctp_get_af_specific(sa_addr->sa.sa_family);
- port = ntohs(sa_addr->v4.sin_port);
/* If the address family is not supported or if this address
* causes the address buffer to overflow return EINVAL.
@@ -1014,6 +1023,8 @@ static int __sctp_connect(struct sock* sk,
goto out_free;
}
+ port = ntohs(sa_addr->v4.sin_port);
+
/* Save current address so we can work with it */
memcpy(&to, sa_addr, af->sockaddr_len);
diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig
index 443c161eb8b..3376d765718 100644
--- a/net/sunrpc/Kconfig
+++ b/net/sunrpc/Kconfig
@@ -18,10 +18,11 @@ config SUNRPC_XPRT_RDMA
If unsure, say N.
config RPCSEC_GSS_KRB5
- tristate "Secure RPC: Kerberos V mechanism (EXPERIMENTAL)"
- depends on SUNRPC && EXPERIMENTAL
+ tristate
+ depends on SUNRPC && CRYPTO
+ prompt "Secure RPC: Kerberos V mechanism" if !(NFS_V4 || NFSD_V4)
+ default y
select SUNRPC_GSS
- select CRYPTO
select CRYPTO_MD5
select CRYPTO_DES
select CRYPTO_CBC
@@ -34,7 +35,7 @@ config RPCSEC_GSS_KRB5
available from http://linux-nfs.org/. In addition, user-space
Kerberos support should be installed.
- If unsure, say N.
+ If unsure, say Y.
config RPCSEC_GSS_SPKM3
tristate "Secure RPC: SPKM3 mechanism (EXPERIMENTAL)"
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index 8dc47f1d000..e9eaaf7d43c 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -19,6 +19,15 @@
# define RPCDBG_FACILITY RPCDBG_AUTH
#endif
+#define RPC_CREDCACHE_DEFAULT_HASHBITS (4)
+struct rpc_cred_cache {
+ struct hlist_head *hashtable;
+ unsigned int hashbits;
+ spinlock_t lock;
+};
+
+static unsigned int auth_hashbits = RPC_CREDCACHE_DEFAULT_HASHBITS;
+
static DEFINE_SPINLOCK(rpc_authflavor_lock);
static const struct rpc_authops *auth_flavors[RPC_AUTH_MAXFLAVOR] = {
&authnull_ops, /* AUTH_NULL */
@@ -29,6 +38,47 @@ static const struct rpc_authops *auth_flavors[RPC_AUTH_MAXFLAVOR] = {
static LIST_HEAD(cred_unused);
static unsigned long number_cred_unused;
+#define MAX_HASHTABLE_BITS (14)
+static int param_set_hashtbl_sz(const char *val, const struct kernel_param *kp)
+{
+ unsigned long num;
+ unsigned int nbits;
+ int ret;
+
+ if (!val)
+ goto out_inval;
+ ret = strict_strtoul(val, 0, &num);
+ if (ret == -EINVAL)
+ goto out_inval;
+ nbits = fls(num);
+ if (num > (1U << nbits))
+ nbits++;
+ if (nbits > MAX_HASHTABLE_BITS || nbits < 2)
+ goto out_inval;
+ *(unsigned int *)kp->arg = nbits;
+ return 0;
+out_inval:
+ return -EINVAL;
+}
+
+static int param_get_hashtbl_sz(char *buffer, const struct kernel_param *kp)
+{
+ unsigned int nbits;
+
+ nbits = *(unsigned int *)kp->arg;
+ return sprintf(buffer, "%u", 1U << nbits);
+}
+
+#define param_check_hashtbl_sz(name, p) __param_check(name, p, unsigned int);
+
+static struct kernel_param_ops param_ops_hashtbl_sz = {
+ .set = param_set_hashtbl_sz,
+ .get = param_get_hashtbl_sz,
+};
+
+module_param_named(auth_hashtable_size, auth_hashbits, hashtbl_sz, 0644);
+MODULE_PARM_DESC(auth_hashtable_size, "RPC credential cache hashtable size");
+
static u32
pseudoflavor_to_flavor(u32 flavor) {
if (flavor >= RPC_AUTH_MAXFLAVOR)
@@ -145,16 +195,23 @@ int
rpcauth_init_credcache(struct rpc_auth *auth)
{
struct rpc_cred_cache *new;
- int i;
+ unsigned int hashsize;
new = kmalloc(sizeof(*new), GFP_KERNEL);
if (!new)
- return -ENOMEM;
- for (i = 0; i < RPC_CREDCACHE_NR; i++)
- INIT_HLIST_HEAD(&new->hashtable[i]);
+ goto out_nocache;
+ new->hashbits = auth_hashbits;
+ hashsize = 1U << new->hashbits;
+ new->hashtable = kcalloc(hashsize, sizeof(new->hashtable[0]), GFP_KERNEL);
+ if (!new->hashtable)
+ goto out_nohashtbl;
spin_lock_init(&new->lock);
auth->au_credcache = new;
return 0;
+out_nohashtbl:
+ kfree(new);
+out_nocache:
+ return -ENOMEM;
}
EXPORT_SYMBOL_GPL(rpcauth_init_credcache);
@@ -183,11 +240,12 @@ rpcauth_clear_credcache(struct rpc_cred_cache *cache)
LIST_HEAD(free);
struct hlist_head *head;
struct rpc_cred *cred;
+ unsigned int hashsize = 1U << cache->hashbits;
int i;
spin_lock(&rpc_credcache_lock);
spin_lock(&cache->lock);
- for (i = 0; i < RPC_CREDCACHE_NR; i++) {
+ for (i = 0; i < hashsize; i++) {
head = &cache->hashtable[i];
while (!hlist_empty(head)) {
cred = hlist_entry(head->first, struct rpc_cred, cr_hash);
@@ -216,6 +274,7 @@ rpcauth_destroy_credcache(struct rpc_auth *auth)
if (cache) {
auth->au_credcache = NULL;
rpcauth_clear_credcache(cache);
+ kfree(cache->hashtable);
kfree(cache);
}
}
@@ -297,7 +356,7 @@ rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred,
*entry, *new;
unsigned int nr;
- nr = hash_long(acred->uid, RPC_CREDCACHE_HASHBITS);
+ nr = hash_long(acred->uid, cache->hashbits);
rcu_read_lock();
hlist_for_each_entry_rcu(entry, pos, &cache->hashtable[nr], cr_hash) {
@@ -390,16 +449,16 @@ rpcauth_init_cred(struct rpc_cred *cred, const struct auth_cred *acred,
}
EXPORT_SYMBOL_GPL(rpcauth_init_cred);
-void
+struct rpc_cred *
rpcauth_generic_bind_cred(struct rpc_task *task, struct rpc_cred *cred, int lookupflags)
{
- task->tk_msg.rpc_cred = get_rpccred(cred);
dprintk("RPC: %5u holding %s cred %p\n", task->tk_pid,
cred->cr_auth->au_ops->au_name, cred);
+ return get_rpccred(cred);
}
EXPORT_SYMBOL_GPL(rpcauth_generic_bind_cred);
-static void
+static struct rpc_cred *
rpcauth_bind_root_cred(struct rpc_task *task, int lookupflags)
{
struct rpc_auth *auth = task->tk_client->cl_auth;
@@ -407,45 +466,43 @@ rpcauth_bind_root_cred(struct rpc_task *task, int lookupflags)
.uid = 0,
.gid = 0,
};
- struct rpc_cred *ret;
dprintk("RPC: %5u looking up %s cred\n",
task->tk_pid, task->tk_client->cl_auth->au_ops->au_name);
- ret = auth->au_ops->lookup_cred(auth, &acred, lookupflags);
- if (!IS_ERR(ret))
- task->tk_msg.rpc_cred = ret;
- else
- task->tk_status = PTR_ERR(ret);
+ return auth->au_ops->lookup_cred(auth, &acred, lookupflags);
}
-static void
+static struct rpc_cred *
rpcauth_bind_new_cred(struct rpc_task *task, int lookupflags)
{
struct rpc_auth *auth = task->tk_client->cl_auth;
- struct rpc_cred *ret;
dprintk("RPC: %5u looking up %s cred\n",
task->tk_pid, auth->au_ops->au_name);
- ret = rpcauth_lookupcred(auth, lookupflags);
- if (!IS_ERR(ret))
- task->tk_msg.rpc_cred = ret;
- else
- task->tk_status = PTR_ERR(ret);
+ return rpcauth_lookupcred(auth, lookupflags);
}
-void
+static int
rpcauth_bindcred(struct rpc_task *task, struct rpc_cred *cred, int flags)
{
+ struct rpc_rqst *req = task->tk_rqstp;
+ struct rpc_cred *new;
int lookupflags = 0;
if (flags & RPC_TASK_ASYNC)
lookupflags |= RPCAUTH_LOOKUP_NEW;
if (cred != NULL)
- cred->cr_ops->crbind(task, cred, lookupflags);
+ new = cred->cr_ops->crbind(task, cred, lookupflags);
else if (flags & RPC_TASK_ROOTCREDS)
- rpcauth_bind_root_cred(task, lookupflags);
+ new = rpcauth_bind_root_cred(task, lookupflags);
else
- rpcauth_bind_new_cred(task, lookupflags);
+ new = rpcauth_bind_new_cred(task, lookupflags);
+ if (IS_ERR(new))
+ return PTR_ERR(new);
+ if (req->rq_cred != NULL)
+ put_rpccred(req->rq_cred);
+ req->rq_cred = new;
+ return 0;
}
void
@@ -484,22 +541,10 @@ out_nodestroy:
}
EXPORT_SYMBOL_GPL(put_rpccred);
-void
-rpcauth_unbindcred(struct rpc_task *task)
-{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
-
- dprintk("RPC: %5u releasing %s cred %p\n",
- task->tk_pid, cred->cr_auth->au_ops->au_name, cred);
-
- put_rpccred(cred);
- task->tk_msg.rpc_cred = NULL;
-}
-
__be32 *
rpcauth_marshcred(struct rpc_task *task, __be32 *p)
{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
+ struct rpc_cred *cred = task->tk_rqstp->rq_cred;
dprintk("RPC: %5u marshaling %s cred %p\n",
task->tk_pid, cred->cr_auth->au_ops->au_name, cred);
@@ -510,7 +555,7 @@ rpcauth_marshcred(struct rpc_task *task, __be32 *p)
__be32 *
rpcauth_checkverf(struct rpc_task *task, __be32 *p)
{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
+ struct rpc_cred *cred = task->tk_rqstp->rq_cred;
dprintk("RPC: %5u validating %s cred %p\n",
task->tk_pid, cred->cr_auth->au_ops->au_name, cred);
@@ -522,7 +567,7 @@ int
rpcauth_wrap_req(struct rpc_task *task, kxdrproc_t encode, void *rqstp,
__be32 *data, void *obj)
{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
+ struct rpc_cred *cred = task->tk_rqstp->rq_cred;
dprintk("RPC: %5u using %s cred %p to wrap rpc data\n",
task->tk_pid, cred->cr_ops->cr_name, cred);
@@ -536,7 +581,7 @@ int
rpcauth_unwrap_resp(struct rpc_task *task, kxdrproc_t decode, void *rqstp,
__be32 *data, void *obj)
{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
+ struct rpc_cred *cred = task->tk_rqstp->rq_cred;
dprintk("RPC: %5u using %s cred %p to unwrap rpc data\n",
task->tk_pid, cred->cr_ops->cr_name, cred);
@@ -550,13 +595,21 @@ rpcauth_unwrap_resp(struct rpc_task *task, kxdrproc_t decode, void *rqstp,
int
rpcauth_refreshcred(struct rpc_task *task)
{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
+ struct rpc_cred *cred = task->tk_rqstp->rq_cred;
int err;
+ cred = task->tk_rqstp->rq_cred;
+ if (cred == NULL) {
+ err = rpcauth_bindcred(task, task->tk_msg.rpc_cred, task->tk_flags);
+ if (err < 0)
+ goto out;
+ cred = task->tk_rqstp->rq_cred;
+ };
dprintk("RPC: %5u refreshing %s cred %p\n",
task->tk_pid, cred->cr_auth->au_ops->au_name, cred);
err = cred->cr_ops->crrefresh(task);
+out:
if (err < 0)
task->tk_status = err;
return err;
@@ -565,7 +618,7 @@ rpcauth_refreshcred(struct rpc_task *task)
void
rpcauth_invalcred(struct rpc_task *task)
{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
+ struct rpc_cred *cred = task->tk_rqstp->rq_cred;
dprintk("RPC: %5u invalidating %s cred %p\n",
task->tk_pid, cred->cr_auth->au_ops->au_name, cred);
@@ -576,7 +629,7 @@ rpcauth_invalcred(struct rpc_task *task)
int
rpcauth_uptodatecred(struct rpc_task *task)
{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
+ struct rpc_cred *cred = task->tk_rqstp->rq_cred;
return cred == NULL ||
test_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags) != 0;
@@ -587,14 +640,27 @@ static struct shrinker rpc_cred_shrinker = {
.seeks = DEFAULT_SEEKS,
};
-void __init rpcauth_init_module(void)
+int __init rpcauth_init_module(void)
{
- rpc_init_authunix();
- rpc_init_generic_auth();
+ int err;
+
+ err = rpc_init_authunix();
+ if (err < 0)
+ goto out1;
+ err = rpc_init_generic_auth();
+ if (err < 0)
+ goto out2;
register_shrinker(&rpc_cred_shrinker);
+ return 0;
+out2:
+ rpc_destroy_authunix();
+out1:
+ return err;
}
void __exit rpcauth_remove_module(void)
{
+ rpc_destroy_authunix();
+ rpc_destroy_generic_auth();
unregister_shrinker(&rpc_cred_shrinker);
}
diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c
index 8f623b0f03d..43162bb3b78 100644
--- a/net/sunrpc/auth_generic.c
+++ b/net/sunrpc/auth_generic.c
@@ -27,7 +27,6 @@ struct generic_cred {
};
static struct rpc_auth generic_auth;
-static struct rpc_cred_cache generic_cred_cache;
static const struct rpc_credops generic_credops;
/*
@@ -55,18 +54,13 @@ struct rpc_cred *rpc_lookup_machine_cred(void)
}
EXPORT_SYMBOL_GPL(rpc_lookup_machine_cred);
-static void
-generic_bind_cred(struct rpc_task *task, struct rpc_cred *cred, int lookupflags)
+static struct rpc_cred *generic_bind_cred(struct rpc_task *task,
+ struct rpc_cred *cred, int lookupflags)
{
struct rpc_auth *auth = task->tk_client->cl_auth;
struct auth_cred *acred = &container_of(cred, struct generic_cred, gc_base)->acred;
- struct rpc_cred *ret;
- ret = auth->au_ops->lookup_cred(auth, acred, lookupflags);
- if (!IS_ERR(ret))
- task->tk_msg.rpc_cred = ret;
- else
- task->tk_status = PTR_ERR(ret);
+ return auth->au_ops->lookup_cred(auth, acred, lookupflags);
}
/*
@@ -159,20 +153,16 @@ out_nomatch:
return 0;
}
-void __init rpc_init_generic_auth(void)
+int __init rpc_init_generic_auth(void)
{
- spin_lock_init(&generic_cred_cache.lock);
+ return rpcauth_init_credcache(&generic_auth);
}
void __exit rpc_destroy_generic_auth(void)
{
- rpcauth_clear_credcache(&generic_cred_cache);
+ rpcauth_destroy_credcache(&generic_auth);
}
-static struct rpc_cred_cache generic_cred_cache = {
- {{ NULL, },},
-};
-
static const struct rpc_authops generic_auth_ops = {
.owner = THIS_MODULE,
.au_name = "Generic",
@@ -183,7 +173,6 @@ static const struct rpc_authops generic_auth_ops = {
static struct rpc_auth generic_auth = {
.au_ops = &generic_auth_ops,
.au_count = ATOMIC_INIT(0),
- .au_credcache = &generic_cred_cache,
};
static const struct rpc_credops generic_credops = {
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 8da2a0e6857..12c48598281 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -373,7 +373,7 @@ gss_handle_downcall_result(struct gss_cred *gss_cred, struct gss_upcall_msg *gss
static void
gss_upcall_callback(struct rpc_task *task)
{
- struct gss_cred *gss_cred = container_of(task->tk_msg.rpc_cred,
+ struct gss_cred *gss_cred = container_of(task->tk_rqstp->rq_cred,
struct gss_cred, gc_base);
struct gss_upcall_msg *gss_msg = gss_cred->gc_upcall;
struct inode *inode = &gss_msg->inode->vfs_inode;
@@ -502,7 +502,7 @@ static void warn_gssd(void)
static inline int
gss_refresh_upcall(struct rpc_task *task)
{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
+ struct rpc_cred *cred = task->tk_rqstp->rq_cred;
struct gss_auth *gss_auth = container_of(cred->cr_auth,
struct gss_auth, rpc_auth);
struct gss_cred *gss_cred = container_of(cred,
@@ -745,17 +745,18 @@ gss_pipe_release(struct inode *inode)
struct rpc_inode *rpci = RPC_I(inode);
struct gss_upcall_msg *gss_msg;
+restart:
spin_lock(&inode->i_lock);
- while (!list_empty(&rpci->in_downcall)) {
+ list_for_each_entry(gss_msg, &rpci->in_downcall, list) {
- gss_msg = list_entry(rpci->in_downcall.next,
- struct gss_upcall_msg, list);
+ if (!list_empty(&gss_msg->msg.list))
+ continue;
gss_msg->msg.errno = -EPIPE;
atomic_inc(&gss_msg->count);
__gss_unhash_msg(gss_msg);
spin_unlock(&inode->i_lock);
gss_release_msg(gss_msg);
- spin_lock(&inode->i_lock);
+ goto restart;
}
spin_unlock(&inode->i_lock);
@@ -928,6 +929,7 @@ gss_do_free_ctx(struct gss_cl_ctx *ctx)
{
dprintk("RPC: gss_free_ctx\n");
+ gss_delete_sec_context(&ctx->gc_gss_ctx);
kfree(ctx->gc_wire_ctx.data);
kfree(ctx);
}
@@ -942,13 +944,7 @@ gss_free_ctx_callback(struct rcu_head *head)
static void
gss_free_ctx(struct gss_cl_ctx *ctx)
{
- struct gss_ctx *gc_gss_ctx;
-
- gc_gss_ctx = rcu_dereference(ctx->gc_gss_ctx);
- rcu_assign_pointer(ctx->gc_gss_ctx, NULL);
call_rcu(&ctx->gc_rcu, gss_free_ctx_callback);
- if (gc_gss_ctx)
- gss_delete_sec_context(&gc_gss_ctx);
}
static void
@@ -1064,12 +1060,12 @@ out:
static __be32 *
gss_marshal(struct rpc_task *task, __be32 *p)
{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
+ struct rpc_rqst *req = task->tk_rqstp;
+ struct rpc_cred *cred = req->rq_cred;
struct gss_cred *gss_cred = container_of(cred, struct gss_cred,
gc_base);
struct gss_cl_ctx *ctx = gss_cred_get_ctx(cred);
__be32 *cred_len;
- struct rpc_rqst *req = task->tk_rqstp;
u32 maj_stat = 0;
struct xdr_netobj mic;
struct kvec iov;
@@ -1119,7 +1115,7 @@ out_put_ctx:
static int gss_renew_cred(struct rpc_task *task)
{
- struct rpc_cred *oldcred = task->tk_msg.rpc_cred;
+ struct rpc_cred *oldcred = task->tk_rqstp->rq_cred;
struct gss_cred *gss_cred = container_of(oldcred,
struct gss_cred,
gc_base);
@@ -1133,7 +1129,7 @@ static int gss_renew_cred(struct rpc_task *task)
new = gss_lookup_cred(auth, &acred, RPCAUTH_LOOKUP_NEW);
if (IS_ERR(new))
return PTR_ERR(new);
- task->tk_msg.rpc_cred = new;
+ task->tk_rqstp->rq_cred = new;
put_rpccred(oldcred);
return 0;
}
@@ -1161,7 +1157,7 @@ static int gss_cred_is_negative_entry(struct rpc_cred *cred)
static int
gss_refresh(struct rpc_task *task)
{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
+ struct rpc_cred *cred = task->tk_rqstp->rq_cred;
int ret = 0;
if (gss_cred_is_negative_entry(cred))
@@ -1172,7 +1168,7 @@ gss_refresh(struct rpc_task *task)
ret = gss_renew_cred(task);
if (ret < 0)
goto out;
- cred = task->tk_msg.rpc_cred;
+ cred = task->tk_rqstp->rq_cred;
}
if (test_bit(RPCAUTH_CRED_NEW, &cred->cr_flags))
@@ -1191,7 +1187,7 @@ gss_refresh_null(struct rpc_task *task)
static __be32 *
gss_validate(struct rpc_task *task, __be32 *p)
{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
+ struct rpc_cred *cred = task->tk_rqstp->rq_cred;
struct gss_cl_ctx *ctx = gss_cred_get_ctx(cred);
__be32 seq;
struct kvec iov;
@@ -1400,7 +1396,7 @@ static int
gss_wrap_req(struct rpc_task *task,
kxdrproc_t encode, void *rqstp, __be32 *p, void *obj)
{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
+ struct rpc_cred *cred = task->tk_rqstp->rq_cred;
struct gss_cred *gss_cred = container_of(cred, struct gss_cred,
gc_base);
struct gss_cl_ctx *ctx = gss_cred_get_ctx(cred);
@@ -1503,7 +1499,7 @@ static int
gss_unwrap_resp(struct rpc_task *task,
kxdrproc_t decode, void *rqstp, __be32 *p, void *obj)
{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
+ struct rpc_cred *cred = task->tk_rqstp->rq_cred;
struct gss_cred *gss_cred = container_of(cred, struct gss_cred,
gc_base);
struct gss_cl_ctx *ctx = gss_cred_get_ctx(cred);
diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c
index 03264461052..778e5dfc514 100644
--- a/net/sunrpc/auth_gss/gss_krb5_mech.c
+++ b/net/sunrpc/auth_gss/gss_krb5_mech.c
@@ -237,6 +237,7 @@ get_key(const void *p, const void *end,
if (!supported_gss_krb5_enctype(alg)) {
printk(KERN_WARNING "gss_kerberos_mech: unsupported "
"encryption key algorithm %d\n", alg);
+ p = ERR_PTR(-EINVAL);
goto out_err;
}
p = simple_get_netobj(p, end, &key);
@@ -282,15 +283,19 @@ gss_import_v1_context(const void *p, const void *end, struct krb5_ctx *ctx)
ctx->enctype = ENCTYPE_DES_CBC_RAW;
ctx->gk5e = get_gss_krb5_enctype(ctx->enctype);
- if (ctx->gk5e == NULL)
+ if (ctx->gk5e == NULL) {
+ p = ERR_PTR(-EINVAL);
goto out_err;
+ }
/* The downcall format was designed before we completely understood
* the uses of the context fields; so it includes some stuff we
* just give some minimal sanity-checking, and some we ignore
* completely (like the next twenty bytes): */
- if (unlikely(p + 20 > end || p + 20 < p))
+ if (unlikely(p + 20 > end || p + 20 < p)) {
+ p = ERR_PTR(-EFAULT);
goto out_err;
+ }
p += 20;
p = simple_get_bytes(p, end, &tmp, sizeof(tmp));
if (IS_ERR(p))
@@ -619,6 +624,7 @@ gss_import_v2_context(const void *p, const void *end, struct krb5_ctx *ctx,
if (ctx->seq_send64 != ctx->seq_send) {
dprintk("%s: seq_send64 %lx, seq_send %x overflow?\n", __func__,
(long unsigned)ctx->seq_send64, ctx->seq_send);
+ p = ERR_PTR(-EINVAL);
goto out_err;
}
p = simple_get_bytes(p, end, &ctx->enctype, sizeof(ctx->enctype));
diff --git a/net/sunrpc/auth_gss/gss_spkm3_mech.c b/net/sunrpc/auth_gss/gss_spkm3_mech.c
index dc3f1f5ed86..adade3d313f 100644
--- a/net/sunrpc/auth_gss/gss_spkm3_mech.c
+++ b/net/sunrpc/auth_gss/gss_spkm3_mech.c
@@ -100,6 +100,7 @@ gss_import_sec_context_spkm3(const void *p, size_t len,
if (version != 1) {
dprintk("RPC: unknown spkm3 token format: "
"obsolete nfs-utils?\n");
+ p = ERR_PTR(-EINVAL);
goto out_err_free_ctx;
}
@@ -135,8 +136,10 @@ gss_import_sec_context_spkm3(const void *p, size_t len,
if (IS_ERR(p))
goto out_err_free_intg_alg;
- if (p != end)
+ if (p != end) {
+ p = ERR_PTR(-EFAULT);
goto out_err_free_intg_key;
+ }
ctx_id->internal_ctx_id = ctx;
diff --git a/net/sunrpc/auth_null.c b/net/sunrpc/auth_null.c
index 1db618f56ec..a5c36c01707 100644
--- a/net/sunrpc/auth_null.c
+++ b/net/sunrpc/auth_null.c
@@ -75,7 +75,7 @@ nul_marshal(struct rpc_task *task, __be32 *p)
static int
nul_refresh(struct rpc_task *task)
{
- set_bit(RPCAUTH_CRED_UPTODATE, &task->tk_msg.rpc_cred->cr_flags);
+ set_bit(RPCAUTH_CRED_UPTODATE, &task->tk_rqstp->rq_cred->cr_flags);
return 0;
}
diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c
index aac2f8b4ee2..4cb70dc6e7a 100644
--- a/net/sunrpc/auth_unix.c
+++ b/net/sunrpc/auth_unix.c
@@ -29,7 +29,6 @@ struct unx_cred {
#endif
static struct rpc_auth unix_auth;
-static struct rpc_cred_cache unix_cred_cache;
static const struct rpc_credops unix_credops;
static struct rpc_auth *
@@ -141,7 +140,7 @@ static __be32 *
unx_marshal(struct rpc_task *task, __be32 *p)
{
struct rpc_clnt *clnt = task->tk_client;
- struct unx_cred *cred = container_of(task->tk_msg.rpc_cred, struct unx_cred, uc_base);
+ struct unx_cred *cred = container_of(task->tk_rqstp->rq_cred, struct unx_cred, uc_base);
__be32 *base, *hold;
int i;
@@ -174,7 +173,7 @@ unx_marshal(struct rpc_task *task, __be32 *p)
static int
unx_refresh(struct rpc_task *task)
{
- set_bit(RPCAUTH_CRED_UPTODATE, &task->tk_msg.rpc_cred->cr_flags);
+ set_bit(RPCAUTH_CRED_UPTODATE, &task->tk_rqstp->rq_cred->cr_flags);
return 0;
}
@@ -197,15 +196,20 @@ unx_validate(struct rpc_task *task, __be32 *p)
printk("RPC: giant verf size: %u\n", size);
return NULL;
}
- task->tk_msg.rpc_cred->cr_auth->au_rslack = (size >> 2) + 2;
+ task->tk_rqstp->rq_cred->cr_auth->au_rslack = (size >> 2) + 2;
p += (size >> 2);
return p;
}
-void __init rpc_init_authunix(void)
+int __init rpc_init_authunix(void)
{
- spin_lock_init(&unix_cred_cache.lock);
+ return rpcauth_init_credcache(&unix_auth);
+}
+
+void rpc_destroy_authunix(void)
+{
+ rpcauth_destroy_credcache(&unix_auth);
}
const struct rpc_authops authunix_ops = {
@@ -219,17 +223,12 @@ const struct rpc_authops authunix_ops = {
};
static
-struct rpc_cred_cache unix_cred_cache = {
-};
-
-static
struct rpc_auth unix_auth = {
.au_cslack = UNX_WRITESLACK,
.au_rslack = 2, /* assume AUTH_NULL verf */
.au_ops = &authunix_ops,
.au_flavor = RPC_AUTH_UNIX,
.au_count = ATOMIC_INIT(0),
- .au_credcache = &unix_cred_cache,
};
static
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 58de76c8540..2b06410e584 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -34,7 +34,6 @@
#include <linux/sunrpc/cache.h>
#include <linux/sunrpc/stats.h>
#include <linux/sunrpc/rpc_pipe_fs.h>
-#include <linux/smp_lock.h>
#define RPCDBG_FACILITY RPCDBG_CACHE
@@ -320,7 +319,7 @@ static struct cache_detail *current_detail;
static int current_index;
static void do_cache_clean(struct work_struct *work);
-static DECLARE_DELAYED_WORK(cache_cleaner, do_cache_clean);
+static struct delayed_work cache_cleaner;
static void sunrpc_init_cache_detail(struct cache_detail *cd)
{
@@ -1504,6 +1503,11 @@ static int create_cache_proc_entries(struct cache_detail *cd)
}
#endif
+void __init cache_initialize(void)
+{
+ INIT_DELAYED_WORK_DEFERRABLE(&cache_cleaner, do_cache_clean);
+}
+
int cache_register(struct cache_detail *cd)
{
int ret;
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 756fc324db9..fa5549079d7 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -226,7 +226,7 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, stru
goto out_no_principal;
}
- kref_init(&clnt->cl_kref);
+ atomic_set(&clnt->cl_count, 1);
err = rpc_setup_pipedir(clnt, program->pipe_dir_name);
if (err < 0)
@@ -390,14 +390,14 @@ rpc_clone_client(struct rpc_clnt *clnt)
if (new->cl_principal == NULL)
goto out_no_principal;
}
- kref_init(&new->cl_kref);
+ atomic_set(&new->cl_count, 1);
err = rpc_setup_pipedir(new, clnt->cl_program->pipe_dir_name);
if (err != 0)
goto out_no_path;
if (new->cl_auth)
atomic_inc(&new->cl_auth->au_count);
xprt_get(clnt->cl_xprt);
- kref_get(&clnt->cl_kref);
+ atomic_inc(&clnt->cl_count);
rpc_register_client(new);
rpciod_up();
return new;
@@ -414,6 +414,35 @@ out_no_clnt:
EXPORT_SYMBOL_GPL(rpc_clone_client);
/*
+ * Kill all tasks for the given client.
+ * XXX: kill their descendants as well?
+ */
+void rpc_killall_tasks(struct rpc_clnt *clnt)
+{
+ struct rpc_task *rovr;
+
+
+ if (list_empty(&clnt->cl_tasks))
+ return;
+ dprintk("RPC: killing all tasks for client %p\n", clnt);
+ /*
+ * Spin lock all_tasks to prevent changes...
+ */
+ spin_lock(&clnt->cl_lock);
+ list_for_each_entry(rovr, &clnt->cl_tasks, tk_task) {
+ if (!RPC_IS_ACTIVATED(rovr))
+ continue;
+ if (!(rovr->tk_flags & RPC_TASK_KILLED)) {
+ rovr->tk_flags |= RPC_TASK_KILLED;
+ rpc_exit(rovr, -EIO);
+ rpc_wake_up_queued_task(rovr->tk_waitqueue, rovr);
+ }
+ }
+ spin_unlock(&clnt->cl_lock);
+}
+EXPORT_SYMBOL_GPL(rpc_killall_tasks);
+
+/*
* Properly shut down an RPC client, terminating all outstanding
* requests.
*/
@@ -436,10 +465,8 @@ EXPORT_SYMBOL_GPL(rpc_shutdown_client);
* Free an RPC client
*/
static void
-rpc_free_client(struct kref *kref)
+rpc_free_client(struct rpc_clnt *clnt)
{
- struct rpc_clnt *clnt = container_of(kref, struct rpc_clnt, cl_kref);
-
dprintk("RPC: destroying %s client for %s\n",
clnt->cl_protname, clnt->cl_server);
if (!IS_ERR(clnt->cl_path.dentry)) {
@@ -466,12 +493,10 @@ out_free:
* Free an RPC client
*/
static void
-rpc_free_auth(struct kref *kref)
+rpc_free_auth(struct rpc_clnt *clnt)
{
- struct rpc_clnt *clnt = container_of(kref, struct rpc_clnt, cl_kref);
-
if (clnt->cl_auth == NULL) {
- rpc_free_client(kref);
+ rpc_free_client(clnt);
return;
}
@@ -480,10 +505,11 @@ rpc_free_auth(struct kref *kref)
* release remaining GSS contexts. This mechanism ensures
* that it can do so safely.
*/
- kref_init(kref);
+ atomic_inc(&clnt->cl_count);
rpcauth_release(clnt->cl_auth);
clnt->cl_auth = NULL;
- kref_put(kref, rpc_free_client);
+ if (atomic_dec_and_test(&clnt->cl_count))
+ rpc_free_client(clnt);
}
/*
@@ -496,7 +522,8 @@ rpc_release_client(struct rpc_clnt *clnt)
if (list_empty(&clnt->cl_tasks))
wake_up(&destroy_wait);
- kref_put(&clnt->cl_kref, rpc_free_auth);
+ if (atomic_dec_and_test(&clnt->cl_count))
+ rpc_free_auth(clnt);
}
/**
@@ -538,6 +565,49 @@ out:
}
EXPORT_SYMBOL_GPL(rpc_bind_new_program);
+void rpc_task_release_client(struct rpc_task *task)
+{
+ struct rpc_clnt *clnt = task->tk_client;
+
+ if (clnt != NULL) {
+ /* Remove from client task list */
+ spin_lock(&clnt->cl_lock);
+ list_del(&task->tk_task);
+ spin_unlock(&clnt->cl_lock);
+ task->tk_client = NULL;
+
+ rpc_release_client(clnt);
+ }
+}
+
+static
+void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt)
+{
+ if (clnt != NULL) {
+ rpc_task_release_client(task);
+ task->tk_client = clnt;
+ atomic_inc(&clnt->cl_count);
+ if (clnt->cl_softrtry)
+ task->tk_flags |= RPC_TASK_SOFT;
+ /* Add to the client's list of all tasks */
+ spin_lock(&clnt->cl_lock);
+ list_add_tail(&task->tk_task, &clnt->cl_tasks);
+ spin_unlock(&clnt->cl_lock);
+ }
+}
+
+static void
+rpc_task_set_rpc_message(struct rpc_task *task, const struct rpc_message *msg)
+{
+ if (msg != NULL) {
+ task->tk_msg.rpc_proc = msg->rpc_proc;
+ task->tk_msg.rpc_argp = msg->rpc_argp;
+ task->tk_msg.rpc_resp = msg->rpc_resp;
+ if (msg->rpc_cred != NULL)
+ task->tk_msg.rpc_cred = get_rpccred(msg->rpc_cred);
+ }
+}
+
/*
* Default callback for async RPC calls
*/
@@ -562,6 +632,18 @@ struct rpc_task *rpc_run_task(const struct rpc_task_setup *task_setup_data)
if (IS_ERR(task))
goto out;
+ rpc_task_set_client(task, task_setup_data->rpc_client);
+ rpc_task_set_rpc_message(task, task_setup_data->rpc_message);
+
+ if (task->tk_status != 0) {
+ int ret = task->tk_status;
+ rpc_put_task(task);
+ return ERR_PTR(ret);
+ }
+
+ if (task->tk_action == NULL)
+ rpc_call_start(task);
+
atomic_inc(&task->tk_count);
rpc_execute(task);
out:
@@ -756,12 +838,13 @@ EXPORT_SYMBOL_GPL(rpc_force_rebind);
* Restart an (async) RPC call from the call_prepare state.
* Usually called from within the exit handler.
*/
-void
+int
rpc_restart_call_prepare(struct rpc_task *task)
{
if (RPC_ASSASSINATED(task))
- return;
+ return 0;
task->tk_action = rpc_prepare_task;
+ return 1;
}
EXPORT_SYMBOL_GPL(rpc_restart_call_prepare);
@@ -769,13 +852,13 @@ EXPORT_SYMBOL_GPL(rpc_restart_call_prepare);
* Restart an (async) RPC call. Usually called from within the
* exit handler.
*/
-void
+int
rpc_restart_call(struct rpc_task *task)
{
if (RPC_ASSASSINATED(task))
- return;
-
+ return 0;
task->tk_action = call_start;
+ return 1;
}
EXPORT_SYMBOL_GPL(rpc_restart_call);
@@ -824,11 +907,6 @@ call_reserve(struct rpc_task *task)
{
dprint_status(task);
- if (!rpcauth_uptodatecred(task)) {
- task->tk_action = call_refresh;
- return;
- }
-
task->tk_status = 0;
task->tk_action = call_reserveresult;
xprt_reserve(task);
@@ -851,7 +929,7 @@ call_reserveresult(struct rpc_task *task)
task->tk_status = 0;
if (status >= 0) {
if (task->tk_rqstp) {
- task->tk_action = call_allocate;
+ task->tk_action = call_refresh;
return;
}
@@ -886,13 +964,54 @@ call_reserveresult(struct rpc_task *task)
}
/*
- * 2. Allocate the buffer. For details, see sched.c:rpc_malloc.
+ * 2. Bind and/or refresh the credentials
+ */
+static void
+call_refresh(struct rpc_task *task)
+{
+ dprint_status(task);
+
+ task->tk_action = call_refreshresult;
+ task->tk_status = 0;
+ task->tk_client->cl_stats->rpcauthrefresh++;
+ rpcauth_refreshcred(task);
+}
+
+/*
+ * 2a. Process the results of a credential refresh
+ */
+static void
+call_refreshresult(struct rpc_task *task)
+{
+ int status = task->tk_status;
+
+ dprint_status(task);
+
+ task->tk_status = 0;
+ task->tk_action = call_allocate;
+ if (status >= 0 && rpcauth_uptodatecred(task))
+ return;
+ switch (status) {
+ case -EACCES:
+ rpc_exit(task, -EACCES);
+ return;
+ case -ENOMEM:
+ rpc_exit(task, -ENOMEM);
+ return;
+ case -ETIMEDOUT:
+ rpc_delay(task, 3*HZ);
+ }
+ task->tk_action = call_refresh;
+}
+
+/*
+ * 2b. Allocate the buffer. For details, see sched.c:rpc_malloc.
* (Note: buffer memory is freed in xprt_release).
*/
static void
call_allocate(struct rpc_task *task)
{
- unsigned int slack = task->tk_msg.rpc_cred->cr_auth->au_cslack;
+ unsigned int slack = task->tk_rqstp->rq_cred->cr_auth->au_cslack;
struct rpc_rqst *req = task->tk_rqstp;
struct rpc_xprt *xprt = task->tk_xprt;
struct rpc_procinfo *proc = task->tk_msg.rpc_proc;
@@ -1472,43 +1591,6 @@ out_retry:
}
}
-/*
- * 8. Refresh the credentials if rejected by the server
- */
-static void
-call_refresh(struct rpc_task *task)
-{
- dprint_status(task);
-
- task->tk_action = call_refreshresult;
- task->tk_status = 0;
- task->tk_client->cl_stats->rpcauthrefresh++;
- rpcauth_refreshcred(task);
-}
-
-/*
- * 8a. Process the results of a credential refresh
- */
-static void
-call_refreshresult(struct rpc_task *task)
-{
- int status = task->tk_status;
-
- dprint_status(task);
-
- task->tk_status = 0;
- task->tk_action = call_reserve;
- if (status >= 0 && rpcauth_uptodatecred(task))
- return;
- if (status == -EACCES) {
- rpc_exit(task, -EACCES);
- return;
- }
- task->tk_action = call_refresh;
- if (status != -ETIMEDOUT)
- rpc_delay(task, 3*HZ);
-}
-
static __be32 *
rpc_encode_header(struct rpc_task *task)
{
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index 95ccbcf45d3..8c8eef2b8f2 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -48,7 +48,7 @@ static void rpc_purge_list(struct rpc_inode *rpci, struct list_head *head,
return;
do {
msg = list_entry(head->next, struct rpc_pipe_msg, list);
- list_del(&msg->list);
+ list_del_init(&msg->list);
msg->errno = err;
destroy_msg(msg);
} while (!list_empty(head));
@@ -208,7 +208,7 @@ rpc_pipe_release(struct inode *inode, struct file *filp)
if (msg != NULL) {
spin_lock(&inode->i_lock);
msg->errno = -EAGAIN;
- list_del(&msg->list);
+ list_del_init(&msg->list);
spin_unlock(&inode->i_lock);
rpci->ops->destroy_msg(msg);
}
@@ -268,7 +268,7 @@ rpc_pipe_read(struct file *filp, char __user *buf, size_t len, loff_t *offset)
if (res < 0 || msg->len == msg->copied) {
filp->private_data = NULL;
spin_lock(&inode->i_lock);
- list_del(&msg->list);
+ list_del_init(&msg->list);
spin_unlock(&inode->i_lock);
rpci->ops->destroy_msg(msg);
}
@@ -371,21 +371,23 @@ rpc_show_info(struct seq_file *m, void *v)
static int
rpc_info_open(struct inode *inode, struct file *file)
{
- struct rpc_clnt *clnt;
+ struct rpc_clnt *clnt = NULL;
int ret = single_open(file, rpc_show_info, NULL);
if (!ret) {
struct seq_file *m = file->private_data;
- mutex_lock(&inode->i_mutex);
- clnt = RPC_I(inode)->private;
- if (clnt) {
- kref_get(&clnt->cl_kref);
+
+ spin_lock(&file->f_path.dentry->d_lock);
+ if (!d_unhashed(file->f_path.dentry))
+ clnt = RPC_I(inode)->private;
+ if (clnt != NULL && atomic_inc_not_zero(&clnt->cl_count)) {
+ spin_unlock(&file->f_path.dentry->d_lock);
m->private = clnt;
} else {
+ spin_unlock(&file->f_path.dentry->d_lock);
single_release(inode, file);
ret = -EINVAL;
}
- mutex_unlock(&inode->i_mutex);
}
return ret;
}
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 4a843b883b8..cace6049e4a 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -246,17 +246,8 @@ static inline void rpc_task_set_debuginfo(struct rpc_task *task)
static void rpc_set_active(struct rpc_task *task)
{
- struct rpc_clnt *clnt;
- if (test_and_set_bit(RPC_TASK_ACTIVE, &task->tk_runstate) != 0)
- return;
rpc_task_set_debuginfo(task);
- /* Add to global list of all tasks */
- clnt = task->tk_client;
- if (clnt != NULL) {
- spin_lock(&clnt->cl_lock);
- list_add_tail(&task->tk_task, &clnt->cl_tasks);
- spin_unlock(&clnt->cl_lock);
- }
+ set_bit(RPC_TASK_ACTIVE, &task->tk_runstate);
}
/*
@@ -319,11 +310,6 @@ static void __rpc_sleep_on(struct rpc_wait_queue *q, struct rpc_task *task,
dprintk("RPC: %5u sleep_on(queue \"%s\" time %lu)\n",
task->tk_pid, rpc_qname(q), jiffies);
- if (!RPC_IS_ASYNC(task) && !RPC_IS_ACTIVATED(task)) {
- printk(KERN_ERR "RPC: Inactive synchronous task put to sleep!\n");
- return;
- }
-
__rpc_add_wait_queue(q, task);
BUG_ON(task->tk_callback != NULL);
@@ -334,8 +320,8 @@ static void __rpc_sleep_on(struct rpc_wait_queue *q, struct rpc_task *task,
void rpc_sleep_on(struct rpc_wait_queue *q, struct rpc_task *task,
rpc_action action)
{
- /* Mark the task as being activated if so needed */
- rpc_set_active(task);
+ /* We shouldn't ever put an inactive task to sleep */
+ BUG_ON(!RPC_IS_ACTIVATED(task));
/*
* Protect the queue operations.
@@ -406,14 +392,6 @@ void rpc_wake_up_queued_task(struct rpc_wait_queue *queue, struct rpc_task *task
EXPORT_SYMBOL_GPL(rpc_wake_up_queued_task);
/*
- * Wake up the specified task
- */
-static void rpc_wake_up_task(struct rpc_task *task)
-{
- rpc_wake_up_queued_task(task->tk_waitqueue, task);
-}
-
-/*
* Wake up the next task on a priority queue.
*/
static struct rpc_task * __rpc_wake_up_next_priority(struct rpc_wait_queue *queue)
@@ -600,7 +578,15 @@ void rpc_exit_task(struct rpc_task *task)
}
}
}
-EXPORT_SYMBOL_GPL(rpc_exit_task);
+
+void rpc_exit(struct rpc_task *task, int status)
+{
+ task->tk_status = status;
+ task->tk_action = rpc_exit_task;
+ if (RPC_IS_QUEUED(task))
+ rpc_wake_up_queued_task(task->tk_waitqueue, task);
+}
+EXPORT_SYMBOL_GPL(rpc_exit);
void rpc_release_calldata(const struct rpc_call_ops *ops, void *calldata)
{
@@ -690,7 +676,6 @@ static void __rpc_execute(struct rpc_task *task)
dprintk("RPC: %5u got signal\n", task->tk_pid);
task->tk_flags |= RPC_TASK_KILLED;
rpc_exit(task, -ERESTARTSYS);
- rpc_wake_up_task(task);
}
rpc_set_running(task);
dprintk("RPC: %5u sync task resuming\n", task->tk_pid);
@@ -714,8 +699,9 @@ static void __rpc_execute(struct rpc_task *task)
void rpc_execute(struct rpc_task *task)
{
rpc_set_active(task);
- rpc_set_running(task);
- __rpc_execute(task);
+ rpc_make_runnable(task);
+ if (!RPC_IS_ASYNC(task))
+ __rpc_execute(task);
}
static void rpc_async_schedule(struct work_struct *work)
@@ -808,26 +794,9 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta
/* Initialize workqueue for async tasks */
task->tk_workqueue = task_setup_data->workqueue;
- task->tk_client = task_setup_data->rpc_client;
- if (task->tk_client != NULL) {
- kref_get(&task->tk_client->cl_kref);
- if (task->tk_client->cl_softrtry)
- task->tk_flags |= RPC_TASK_SOFT;
- }
-
if (task->tk_ops->rpc_call_prepare != NULL)
task->tk_action = rpc_prepare_task;
- if (task_setup_data->rpc_message != NULL) {
- task->tk_msg.rpc_proc = task_setup_data->rpc_message->rpc_proc;
- task->tk_msg.rpc_argp = task_setup_data->rpc_message->rpc_argp;
- task->tk_msg.rpc_resp = task_setup_data->rpc_message->rpc_resp;
- /* Bind the user cred */
- rpcauth_bindcred(task, task_setup_data->rpc_message->rpc_cred, task_setup_data->flags);
- if (task->tk_action == NULL)
- rpc_call_start(task);
- }
-
/* starting timestamp */
task->tk_start = ktime_get();
@@ -896,11 +865,8 @@ void rpc_put_task(struct rpc_task *task)
if (task->tk_rqstp)
xprt_release(task);
if (task->tk_msg.rpc_cred)
- rpcauth_unbindcred(task);
- if (task->tk_client) {
- rpc_release_client(task->tk_client);
- task->tk_client = NULL;
- }
+ put_rpccred(task->tk_msg.rpc_cred);
+ rpc_task_release_client(task);
if (task->tk_workqueue != NULL) {
INIT_WORK(&task->u.tk_work, rpc_async_release);
queue_work(task->tk_workqueue, &task->u.tk_work);
@@ -913,13 +879,6 @@ static void rpc_release_task(struct rpc_task *task)
{
dprintk("RPC: %5u release task\n", task->tk_pid);
- if (!list_empty(&task->tk_task)) {
- struct rpc_clnt *clnt = task->tk_client;
- /* Remove from client task list */
- spin_lock(&clnt->cl_lock);
- list_del(&task->tk_task);
- spin_unlock(&clnt->cl_lock);
- }
BUG_ON (RPC_IS_QUEUED(task));
/* Wake up anyone who is waiting for task completion */
@@ -928,35 +887,6 @@ static void rpc_release_task(struct rpc_task *task)
rpc_put_task(task);
}
-/*
- * Kill all tasks for the given client.
- * XXX: kill their descendants as well?
- */
-void rpc_killall_tasks(struct rpc_clnt *clnt)
-{
- struct rpc_task *rovr;
-
-
- if (list_empty(&clnt->cl_tasks))
- return;
- dprintk("RPC: killing all tasks for client %p\n", clnt);
- /*
- * Spin lock all_tasks to prevent changes...
- */
- spin_lock(&clnt->cl_lock);
- list_for_each_entry(rovr, &clnt->cl_tasks, tk_task) {
- if (! RPC_IS_ACTIVATED(rovr))
- continue;
- if (!(rovr->tk_flags & RPC_TASK_KILLED)) {
- rovr->tk_flags |= RPC_TASK_KILLED;
- rpc_exit(rovr, -EIO);
- rpc_wake_up_task(rovr);
- }
- }
- spin_unlock(&clnt->cl_lock);
-}
-EXPORT_SYMBOL_GPL(rpc_killall_tasks);
-
int rpciod_up(void)
{
return try_module_get(THIS_MODULE) ? 0 : -EINVAL;
diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c
index f438347d817..c0d085013a2 100644
--- a/net/sunrpc/sunrpc_syms.c
+++ b/net/sunrpc/sunrpc_syms.c
@@ -33,21 +33,27 @@ init_sunrpc(void)
if (err)
goto out;
err = rpc_init_mempool();
- if (err) {
- unregister_rpc_pipefs();
- goto out;
- }
+ if (err)
+ goto out2;
+ err = rpcauth_init_module();
+ if (err)
+ goto out3;
#ifdef RPC_DEBUG
rpc_register_sysctl();
#endif
#ifdef CONFIG_PROC_FS
rpc_proc_init();
#endif
+ cache_initialize();
cache_register(&ip_map_cache);
cache_register(&unix_gid_cache);
svc_init_xprt_sock(); /* svc sock transport */
init_socket_xprt(); /* clnt sock transport */
- rpcauth_init_module();
+ return 0;
+out3:
+ rpc_destroy_mempool();
+out2:
+ unregister_rpc_pipefs();
out:
return err;
}
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index dcd0132396b..970fb00f388 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1032,6 +1032,8 @@ void xprt_release(struct rpc_task *task)
spin_unlock_bh(&xprt->transport_lock);
if (req->rq_buffer)
xprt->ops->buf_free(req->rq_buffer);
+ if (req->rq_cred != NULL)
+ put_rpccred(req->rq_cred);
task->tk_rqstp = NULL;
if (req->rq_release_snd_buf)
req->rq_release_snd_buf(req);
@@ -1129,6 +1131,7 @@ static void xprt_destroy(struct kref *kref)
rpc_destroy_wait_queue(&xprt->sending);
rpc_destroy_wait_queue(&xprt->resend);
rpc_destroy_wait_queue(&xprt->backlog);
+ cancel_work_sync(&xprt->task_cleanup);
/*
* Tear down transport state and free the rpc_xprt
*/
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index e5e28d1946a..2ac3f6e8adf 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -249,6 +249,8 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target,
req->rl_nchunks = nchunks;
BUG_ON(nchunks == 0);
+ BUG_ON((r_xprt->rx_ia.ri_memreg_strategy == RPCRDMA_FRMR)
+ && (nchunks > 3));
/*
* finish off header. If write, marshal discrim and nchunks.
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 27015c6d8eb..5f4c7b3bc71 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -650,10 +650,22 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
ep->rep_attr.cap.max_send_wr = cdata->max_requests;
switch (ia->ri_memreg_strategy) {
case RPCRDMA_FRMR:
- /* Add room for frmr register and invalidate WRs */
- ep->rep_attr.cap.max_send_wr *= 3;
- if (ep->rep_attr.cap.max_send_wr > devattr.max_qp_wr)
- return -EINVAL;
+ /* Add room for frmr register and invalidate WRs.
+ * 1. FRMR reg WR for head
+ * 2. FRMR invalidate WR for head
+ * 3. FRMR reg WR for pagelist
+ * 4. FRMR invalidate WR for pagelist
+ * 5. FRMR reg WR for tail
+ * 6. FRMR invalidate WR for tail
+ * 7. The RDMA_SEND WR
+ */
+ ep->rep_attr.cap.max_send_wr *= 7;
+ if (ep->rep_attr.cap.max_send_wr > devattr.max_qp_wr) {
+ cdata->max_requests = devattr.max_qp_wr / 7;
+ if (!cdata->max_requests)
+ return -EINVAL;
+ ep->rep_attr.cap.max_send_wr = cdata->max_requests * 7;
+ }
break;
case RPCRDMA_MEMWINDOWS_ASYNC:
case RPCRDMA_MEMWINDOWS:
@@ -1490,7 +1502,7 @@ rpcrdma_register_frmr_external(struct rpcrdma_mr_seg *seg,
memset(&frmr_wr, 0, sizeof frmr_wr);
frmr_wr.opcode = IB_WR_FAST_REG_MR;
frmr_wr.send_flags = 0; /* unsignaled */
- frmr_wr.wr.fast_reg.iova_start = (unsigned long)seg1->mr_dma;
+ frmr_wr.wr.fast_reg.iova_start = seg1->mr_dma;
frmr_wr.wr.fast_reg.page_list = seg1->mr_chunk.rl_mw->r.frmr.fr_pgl;
frmr_wr.wr.fast_reg.page_list_len = i;
frmr_wr.wr.fast_reg.page_shift = PAGE_SHIFT;
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 7ca65c7005e..fe9306bf10c 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -800,7 +800,7 @@ static void xs_udp_data_ready(struct sock *sk, int len)
u32 _xid;
__be32 *xp;
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
dprintk("RPC: xs_udp_data_ready...\n");
if (!(xprt = xprt_from_sock(sk)))
goto out;
@@ -852,7 +852,7 @@ static void xs_udp_data_ready(struct sock *sk, int len)
dropit:
skb_free_datagram(sk, skb);
out:
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
}
static inline void xs_tcp_read_fraghdr(struct rpc_xprt *xprt, struct xdr_skb_reader *desc)
@@ -1229,7 +1229,7 @@ static void xs_tcp_data_ready(struct sock *sk, int bytes)
dprintk("RPC: xs_tcp_data_ready...\n");
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
if (!(xprt = xprt_from_sock(sk)))
goto out;
if (xprt->shutdown)
@@ -1248,7 +1248,7 @@ static void xs_tcp_data_ready(struct sock *sk, int bytes)
read = tcp_read_sock(sk, &rd_desc, xs_tcp_data_recv);
} while (read > 0);
out:
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
}
/*
@@ -1301,18 +1301,19 @@ static void xs_tcp_state_change(struct sock *sk)
{
struct rpc_xprt *xprt;
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
if (!(xprt = xprt_from_sock(sk)))
goto out;
dprintk("RPC: xs_tcp_state_change client %p...\n", xprt);
- dprintk("RPC: state %x conn %d dead %d zapped %d\n",
+ dprintk("RPC: state %x conn %d dead %d zapped %d sk_shutdown %d\n",
sk->sk_state, xprt_connected(xprt),
sock_flag(sk, SOCK_DEAD),
- sock_flag(sk, SOCK_ZAPPED));
+ sock_flag(sk, SOCK_ZAPPED),
+ sk->sk_shutdown);
switch (sk->sk_state) {
case TCP_ESTABLISHED:
- spin_lock_bh(&xprt->transport_lock);
+ spin_lock(&xprt->transport_lock);
if (!xprt_test_and_set_connected(xprt)) {
struct sock_xprt *transport = container_of(xprt,
struct sock_xprt, xprt);
@@ -1326,7 +1327,7 @@ static void xs_tcp_state_change(struct sock *sk)
xprt_wake_pending_tasks(xprt, -EAGAIN);
}
- spin_unlock_bh(&xprt->transport_lock);
+ spin_unlock(&xprt->transport_lock);
break;
case TCP_FIN_WAIT1:
/* The client initiated a shutdown of the socket */
@@ -1364,7 +1365,7 @@ static void xs_tcp_state_change(struct sock *sk)
xs_sock_mark_closed(xprt);
}
out:
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
}
/**
@@ -1375,7 +1376,7 @@ static void xs_error_report(struct sock *sk)
{
struct rpc_xprt *xprt;
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
if (!(xprt = xprt_from_sock(sk)))
goto out;
dprintk("RPC: %s client %p...\n"
@@ -1383,7 +1384,7 @@ static void xs_error_report(struct sock *sk)
__func__, xprt, sk->sk_err);
xprt_wake_pending_tasks(xprt, -EAGAIN);
out:
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
}
static void xs_write_space(struct sock *sk)
@@ -1415,13 +1416,13 @@ static void xs_write_space(struct sock *sk)
*/
static void xs_udp_write_space(struct sock *sk)
{
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
/* from net/core/sock.c:sock_def_write_space */
if (sock_writeable(sk))
xs_write_space(sk);
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
}
/**
@@ -1436,13 +1437,13 @@ static void xs_udp_write_space(struct sock *sk)
*/
static void xs_tcp_write_space(struct sock *sk)
{
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
/* from net/core/stream.c:sk_stream_write_space */
if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk))
xs_write_space(sk);
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
}
static void xs_udp_do_set_buffer_size(struct rpc_xprt *xprt)
@@ -1779,10 +1780,25 @@ static void xs_tcp_reuse_connection(struct rpc_xprt *xprt, struct sock_xprt *tra
{
unsigned int state = transport->inet->sk_state;
- if (state == TCP_CLOSE && transport->sock->state == SS_UNCONNECTED)
- return;
- if ((1 << state) & (TCPF_ESTABLISHED|TCPF_SYN_SENT))
- return;
+ if (state == TCP_CLOSE && transport->sock->state == SS_UNCONNECTED) {
+ /* we don't need to abort the connection if the socket
+ * hasn't undergone a shutdown
+ */
+ if (transport->inet->sk_shutdown == 0)
+ return;
+ dprintk("RPC: %s: TCP_CLOSEd and sk_shutdown set to %d\n",
+ __func__, transport->inet->sk_shutdown);
+ }
+ if ((1 << state) & (TCPF_ESTABLISHED|TCPF_SYN_SENT)) {
+ /* we don't need to abort the connection if the socket
+ * hasn't undergone a shutdown
+ */
+ if (transport->inet->sk_shutdown == 0)
+ return;
+ dprintk("RPC: %s: ESTABLISHED/SYN_SENT "
+ "sk_shutdown set to %d\n",
+ __func__, transport->inet->sk_shutdown);
+ }
xs_abort_connection(xprt, transport);
}
@@ -2577,7 +2593,8 @@ void cleanup_socket_xprt(void)
xprt_unregister_transport(&xs_bc_tcp_transport);
}
-static int param_set_uint_minmax(const char *val, struct kernel_param *kp,
+static int param_set_uint_minmax(const char *val,
+ const struct kernel_param *kp,
unsigned int min, unsigned int max)
{
unsigned long num;
@@ -2592,34 +2609,37 @@ static int param_set_uint_minmax(const char *val, struct kernel_param *kp,
return 0;
}
-static int param_set_portnr(const char *val, struct kernel_param *kp)
+static int param_set_portnr(const char *val, const struct kernel_param *kp)
{
return param_set_uint_minmax(val, kp,
RPC_MIN_RESVPORT,
RPC_MAX_RESVPORT);
}
-static int param_get_portnr(char *buffer, struct kernel_param *kp)
-{
- return param_get_uint(buffer, kp);
-}
+static struct kernel_param_ops param_ops_portnr = {
+ .set = param_set_portnr,
+ .get = param_get_uint,
+};
+
#define param_check_portnr(name, p) \
__param_check(name, p, unsigned int);
module_param_named(min_resvport, xprt_min_resvport, portnr, 0644);
module_param_named(max_resvport, xprt_max_resvport, portnr, 0644);
-static int param_set_slot_table_size(const char *val, struct kernel_param *kp)
+static int param_set_slot_table_size(const char *val,
+ const struct kernel_param *kp)
{
return param_set_uint_minmax(val, kp,
RPC_MIN_SLOT_TABLE,
RPC_MAX_SLOT_TABLE);
}
-static int param_get_slot_table_size(char *buffer, struct kernel_param *kp)
-{
- return param_get_uint(buffer, kp);
-}
+static struct kernel_param_ops param_ops_slot_table_size = {
+ .set = param_set_slot_table_size,
+ .get = param_get_uint,
+};
+
#define param_check_slot_table_size(name, p) \
__param_check(name, p, unsigned int);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 4414a18c63b..0b39b2451ea 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -692,6 +692,7 @@ static int unix_autobind(struct socket *sock)
static u32 ordernum = 1;
struct unix_address *addr;
int err;
+ unsigned int retries = 0;
mutex_lock(&u->readlock);
@@ -717,9 +718,17 @@ retry:
if (__unix_find_socket_byname(net, addr->name, addr->len, sock->type,
addr->hash)) {
spin_unlock(&unix_table_lock);
- /* Sanity yield. It is unusual case, but yet... */
- if (!(ordernum&0xFF))
- yield();
+ /*
+ * __unix_find_socket_byname() may take long time if many names
+ * are already in use.
+ */
+ cond_resched();
+ /* Give up if all names seems to be in use. */
+ if (retries++ == 0xFFFFF) {
+ err = -ENOSPC;
+ kfree(addr);
+ goto out;
+ }
goto retry;
}
addr->hash ^= sk->sk_type;
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index a3cca0a9434..64f2ae1fdc1 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -101,7 +101,7 @@ resume:
err = -EHOSTUNREACH;
goto error_nolock;
}
- skb_dst_set_noref(skb, dst);
+ skb_dst_set(skb, dst_clone(dst));
x = dst->xfrm;
} while (x && !(x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL));
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 2b3ed7ad493..cbab6e1a8c9 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1175,9 +1175,8 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, struct flowi *fl,
tmpl->mode == XFRM_MODE_BEET) {
remote = &tmpl->id.daddr;
local = &tmpl->saddr;
- family = tmpl->encap_family;
- if (xfrm_addr_any(local, family)) {
- error = xfrm_get_saddr(net, &tmp, remote, family);
+ if (xfrm_addr_any(local, tmpl->encap_family)) {
+ error = xfrm_get_saddr(net, &tmp, remote, tmpl->encap_family);
if (error)
goto fail;
local = &tmp;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 5208b12fbfb..eb96ce52f17 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -656,15 +656,23 @@ void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si)
EXPORT_SYMBOL(xfrm_sad_getinfo);
static int
-xfrm_init_tempsel(struct xfrm_state *x, struct flowi *fl,
- struct xfrm_tmpl *tmpl,
- xfrm_address_t *daddr, xfrm_address_t *saddr,
- unsigned short family)
+xfrm_init_tempstate(struct xfrm_state *x, struct flowi *fl,
+ struct xfrm_tmpl *tmpl,
+ xfrm_address_t *daddr, xfrm_address_t *saddr,
+ unsigned short family)
{
struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
if (!afinfo)
return -1;
- afinfo->init_tempsel(x, fl, tmpl, daddr, saddr);
+ afinfo->init_tempsel(&x->sel, fl);
+
+ if (family != tmpl->encap_family) {
+ xfrm_state_put_afinfo(afinfo);
+ afinfo = xfrm_state_get_afinfo(tmpl->encap_family);
+ if (!afinfo)
+ return -1;
+ }
+ afinfo->init_temprop(x, tmpl, daddr, saddr);
xfrm_state_put_afinfo(afinfo);
return 0;
}
@@ -790,37 +798,38 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr,
int error = 0;
struct xfrm_state *best = NULL;
u32 mark = pol->mark.v & pol->mark.m;
+ unsigned short encap_family = tmpl->encap_family;
to_put = NULL;
spin_lock_bh(&xfrm_state_lock);
- h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, family);
+ h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family);
hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) {
- if (x->props.family == family &&
+ if (x->props.family == encap_family &&
x->props.reqid == tmpl->reqid &&
(mark & x->mark.m) == x->mark.v &&
!(x->props.flags & XFRM_STATE_WILDRECV) &&
- xfrm_state_addr_check(x, daddr, saddr, family) &&
+ xfrm_state_addr_check(x, daddr, saddr, encap_family) &&
tmpl->mode == x->props.mode &&
tmpl->id.proto == x->id.proto &&
(tmpl->id.spi == x->id.spi || !tmpl->id.spi))
- xfrm_state_look_at(pol, x, fl, family, daddr, saddr,
+ xfrm_state_look_at(pol, x, fl, encap_family, daddr, saddr,
&best, &acquire_in_progress, &error);
}
if (best)
goto found;
- h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, family);
+ h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, encap_family);
hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h_wildcard, bydst) {
- if (x->props.family == family &&
+ if (x->props.family == encap_family &&
x->props.reqid == tmpl->reqid &&
(mark & x->mark.m) == x->mark.v &&
!(x->props.flags & XFRM_STATE_WILDRECV) &&
- xfrm_state_addr_check(x, daddr, saddr, family) &&
+ xfrm_state_addr_check(x, daddr, saddr, encap_family) &&
tmpl->mode == x->props.mode &&
tmpl->id.proto == x->id.proto &&
(tmpl->id.spi == x->id.spi || !tmpl->id.spi))
- xfrm_state_look_at(pol, x, fl, family, daddr, saddr,
+ xfrm_state_look_at(pol, x, fl, encap_family, daddr, saddr,
&best, &acquire_in_progress, &error);
}
@@ -829,7 +838,7 @@ found:
if (!x && !error && !acquire_in_progress) {
if (tmpl->id.spi &&
(x0 = __xfrm_state_lookup(net, mark, daddr, tmpl->id.spi,
- tmpl->id.proto, family)) != NULL) {
+ tmpl->id.proto, encap_family)) != NULL) {
to_put = x0;
error = -EEXIST;
goto out;
@@ -839,9 +848,9 @@ found:
error = -ENOMEM;
goto out;
}
- /* Initialize temporary selector matching only
+ /* Initialize temporary state matching only
* to current session. */
- xfrm_init_tempsel(x, fl, tmpl, daddr, saddr, family);
+ xfrm_init_tempstate(x, fl, tmpl, daddr, saddr, family);
memcpy(&x->mark, &pol->mark, sizeof(x->mark));
error = security_xfrm_state_alloc_acquire(x, pol->security, fl->secid);
@@ -856,10 +865,10 @@ found:
x->km.state = XFRM_STATE_ACQ;
list_add(&x->km.all, &net->xfrm.state_all);
hlist_add_head(&x->bydst, net->xfrm.state_bydst+h);
- h = xfrm_src_hash(net, daddr, saddr, family);
+ h = xfrm_src_hash(net, daddr, saddr, encap_family);
hlist_add_head(&x->bysrc, net->xfrm.state_bysrc+h);
if (x->id.spi) {
- h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, family);
+ h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, encap_family);
hlist_add_head(&x->byspi, net->xfrm.state_byspi+h);
}
x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires;
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index ba59983aaff..8bae6b22c84 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -1801,7 +1801,7 @@ static int xfrm_add_sa_expire(struct sk_buff *skb, struct nlmsghdr *nlh,
struct xfrm_user_expire *ue = nlmsg_data(nlh);
struct xfrm_usersa_info *p = &ue->state;
struct xfrm_mark m;
- u32 mark = xfrm_mark_get(attrs, &m);;
+ u32 mark = xfrm_mark_get(attrs, &m);
x = xfrm_state_lookup(net, mark, &p->id.daddr, p->id.spi, p->id.proto, p->family);
@@ -2504,7 +2504,7 @@ static struct xfrm_policy *xfrm_compile_policy(struct sock *sk, int opt,
if (p->dir > XFRM_POLICY_OUT)
return NULL;
- xp = xfrm_policy_alloc(net, GFP_KERNEL);
+ xp = xfrm_policy_alloc(net, GFP_ATOMIC);
if (xp == NULL) {
*dir = -ENOBUFS;
return NULL;