summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2008-06-10 11:22:26 +0200
committerDavid S. Miller <davem@davemloft.net>2008-06-10 11:22:26 +0200
commit65b53e4cc90e59936733b3b95b9451d2ca47528d (patch)
tree29932718192962671c48c3fd1ea017a6112459e8 /net
parentMerge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/linville... (diff)
parentipv6 netns: init net is used to set bindv6only for new sock (diff)
downloadlinux-65b53e4cc90e59936733b3b95b9451d2ca47528d.tar.xz
linux-65b53e4cc90e59936733b3b95b9451d2ca47528d.zip
Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6
Conflicts: drivers/net/tg3.c drivers/net/wireless/rt2x00/rt2x00dev.c net/mac80211/ieee80211_i.h
Diffstat (limited to 'net')
-rw-r--r--net/ax25/ax25_subr.c11
-rw-r--r--net/bluetooth/rfcomm/core.c2
-rw-r--r--net/bluetooth/rfcomm/tty.c13
-rw-r--r--net/core/neighbour.c9
-rw-r--r--net/core/rtnetlink.c3
-rw-r--r--net/core/skbuff.c5
-rw-r--r--net/core/user_dma.c2
-rw-r--r--net/dccp/ccids/ccid3.c13
-rw-r--r--net/dccp/ipv4.c4
-rw-r--r--net/ipv4/devinet.c9
-rw-r--r--net/ipv4/fib_frontend.c1
-rw-r--r--net/ipv4/raw.c9
-rw-r--r--net/ipv4/route.c2
-rw-r--r--net/ipv4/tcp.c9
-rw-r--r--net/ipv4/tcp_input.c35
-rw-r--r--net/ipv4/tcp_output.c2
-rw-r--r--net/ipv4/tunnel4.c2
-rw-r--r--net/ipv4/udp.c3
-rw-r--r--net/ipv6/addrconf.c107
-rw-r--r--net/ipv6/af_inet6.c2
-rw-r--r--net/ipv6/datagram.c45
-rw-r--r--net/ipv6/ip6_flowlabel.c2
-rw-r--r--net/ipv6/ipv6_sockglue.c21
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c8
-rw-r--r--net/ipv6/raw.c11
-rw-r--r--net/ipv6/route.c12
-rw-r--r--net/ipv6/tunnel6.c2
-rw-r--r--net/ipv6/udp.c8
-rw-r--r--net/irda/af_irda.c12
-rw-r--r--net/llc/llc_sap.c10
-rw-r--r--net/mac80211/cfg.c4
-rw-r--r--net/mac80211/ieee80211_i.h24
-rw-r--r--net/mac80211/main.c3
-rw-r--r--net/mac80211/mlme.c45
-rw-r--r--net/mac80211/rx.c4
-rw-r--r--net/mac80211/util.c4
-rw-r--r--net/mac80211/wext.c26
-rw-r--r--net/netfilter/nf_conntrack_expect.c4
-rw-r--r--net/netfilter/xt_connlimit.c3
-rw-r--r--net/netlink/attr.c12
-rw-r--r--net/netlink/genetlink.c6
-rw-r--r--net/sched/sch_dsmark.c6
-rw-r--r--net/sched/sch_gred.c3
-rw-r--r--net/sched/sch_hfsc.c2
-rw-r--r--net/sched/sch_red.c3
-rw-r--r--net/sctp/associola.c21
-rw-r--r--net/sctp/ipv6.c11
-rw-r--r--net/sctp/output.c2
-rw-r--r--net/sctp/outqueue.c120
-rw-r--r--net/sctp/protocol.c11
-rw-r--r--net/sctp/transport.c50
-rw-r--r--net/sunrpc/auth_generic.c8
-rw-r--r--net/sunrpc/svc_xprt.c23
-rw-r--r--net/sunrpc/svcauth_unix.c4
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_recvfrom.c102
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_sendto.c11
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_transport.c290
-rw-r--r--net/wireless/nl80211.c12
-rw-r--r--net/xfrm/xfrm_algo.c4
59 files changed, 688 insertions, 504 deletions
diff --git a/net/ax25/ax25_subr.c b/net/ax25/ax25_subr.c
index d8f215733175..034aa10a5198 100644
--- a/net/ax25/ax25_subr.c
+++ b/net/ax25/ax25_subr.c
@@ -64,20 +64,15 @@ void ax25_frames_acked(ax25_cb *ax25, unsigned short nr)
void ax25_requeue_frames(ax25_cb *ax25)
{
- struct sk_buff *skb, *skb_prev = NULL;
+ struct sk_buff *skb;
/*
* Requeue all the un-ack-ed frames on the output queue to be picked
* up by ax25_kick called from the timer. This arrangement handles the
* possibility of an empty output queue.
*/
- while ((skb = skb_dequeue(&ax25->ack_queue)) != NULL) {
- if (skb_prev == NULL)
- skb_queue_head(&ax25->write_queue, skb);
- else
- skb_append(skb_prev, skb, &ax25->write_queue);
- skb_prev = skb;
- }
+ while ((skb = skb_dequeue_tail(&ax25->ack_queue)) != NULL)
+ skb_queue_head(&ax25->write_queue, skb);
}
/*
diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c
index eb62558e9b09..0c2c93735e93 100644
--- a/net/bluetooth/rfcomm/core.c
+++ b/net/bluetooth/rfcomm/core.c
@@ -423,8 +423,8 @@ static int __rfcomm_dlc_close(struct rfcomm_dlc *d, int err)
rfcomm_dlc_lock(d);
d->state = BT_CLOSED;
- rfcomm_dlc_unlock(d);
d->state_change(d, err);
+ rfcomm_dlc_unlock(d);
skb_queue_purge(&d->tx_queue);
rfcomm_dlc_unlink(d);
diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c
index c3f749abb2d0..c9191871c1e0 100644
--- a/net/bluetooth/rfcomm/tty.c
+++ b/net/bluetooth/rfcomm/tty.c
@@ -566,11 +566,22 @@ static void rfcomm_dev_state_change(struct rfcomm_dlc *dlc, int err)
if (dlc->state == BT_CLOSED) {
if (!dev->tty) {
if (test_bit(RFCOMM_RELEASE_ONHUP, &dev->flags)) {
- if (rfcomm_dev_get(dev->id) == NULL)
+ /* Drop DLC lock here to avoid deadlock
+ * 1. rfcomm_dev_get will take rfcomm_dev_lock
+ * but in rfcomm_dev_add there's lock order:
+ * rfcomm_dev_lock -> dlc lock
+ * 2. rfcomm_dev_put will deadlock if it's
+ * the last reference
+ */
+ rfcomm_dlc_unlock(dlc);
+ if (rfcomm_dev_get(dev->id) == NULL) {
+ rfcomm_dlc_lock(dlc);
return;
+ }
rfcomm_dev_del(dev);
rfcomm_dev_put(dev);
+ rfcomm_dlc_lock(dlc);
}
} else
tty_hangup(dev->tty);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 5d9d7130bd6e..65f01f71b3f3 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1714,7 +1714,8 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms)
return nla_nest_end(skb, nest);
nla_put_failure:
- return nla_nest_cancel(skb, nest);
+ nla_nest_cancel(skb, nest);
+ return -EMSGSIZE;
}
static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl,
@@ -2057,9 +2058,9 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh,
goto nla_put_failure;
}
- ci.ndm_used = now - neigh->used;
- ci.ndm_confirmed = now - neigh->confirmed;
- ci.ndm_updated = now - neigh->updated;
+ ci.ndm_used = jiffies_to_clock_t(now - neigh->used);
+ ci.ndm_confirmed = jiffies_to_clock_t(now - neigh->confirmed);
+ ci.ndm_updated = jiffies_to_clock_t(now - neigh->updated);
ci.ndm_refcnt = atomic_read(&neigh->refcnt) - 1;
read_unlock_bh(&neigh->lock);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index ca32ddb8ad17..6c8d7f0ea01a 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -498,7 +498,8 @@ int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics)
return nla_nest_end(skb, mx);
nla_put_failure:
- return nla_nest_cancel(skb, mx);
+ nla_nest_cancel(skb, mx);
+ return -EMSGSIZE;
}
int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id,
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 5c459f2b7985..1e556d312117 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1445,6 +1445,7 @@ done:
if (spd.nr_pages) {
int ret;
+ struct sock *sk = __skb->sk;
/*
* Drop the socket lock, otherwise we have reverse
@@ -1455,9 +1456,9 @@ done:
* we call into ->sendpage() with the i_mutex lock held
* and networking will grab the socket lock.
*/
- release_sock(__skb->sk);
+ release_sock(sk);
ret = splice_to_pipe(pipe, &spd);
- lock_sock(__skb->sk);
+ lock_sock(sk);
return ret;
}
diff --git a/net/core/user_dma.c b/net/core/user_dma.c
index 0ad1cd57bc39..c77aff9c6eb3 100644
--- a/net/core/user_dma.c
+++ b/net/core/user_dma.c
@@ -75,7 +75,7 @@ int dma_skb_copy_datagram_iovec(struct dma_chan *chan,
end = start + skb_shinfo(skb)->frags[i].size;
copy = end - offset;
- if ((copy = end - offset) > 0) {
+ if (copy > 0) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
struct page *page = frag->page;
diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c
index cd61dea2eea1..f813077234b7 100644
--- a/net/dccp/ccids/ccid3.c
+++ b/net/dccp/ccids/ccid3.c
@@ -193,22 +193,17 @@ static inline void ccid3_hc_tx_update_s(struct ccid3_hc_tx_sock *hctx, int len)
/*
* Update Window Counter using the algorithm from [RFC 4342, 8.1].
- * The algorithm is not applicable if RTT < 4 microseconds.
+ * As elsewhere, RTT > 0 is assumed by using dccp_sample_rtt().
*/
static inline void ccid3_hc_tx_update_win_count(struct ccid3_hc_tx_sock *hctx,
ktime_t now)
{
- u32 quarter_rtts;
-
- if (unlikely(hctx->ccid3hctx_rtt < 4)) /* avoid divide-by-zero */
- return;
-
- quarter_rtts = ktime_us_delta(now, hctx->ccid3hctx_t_last_win_count);
- quarter_rtts /= hctx->ccid3hctx_rtt / 4;
+ u32 delta = ktime_us_delta(now, hctx->ccid3hctx_t_last_win_count),
+ quarter_rtts = (4 * delta) / hctx->ccid3hctx_rtt;
if (quarter_rtts > 0) {
hctx->ccid3hctx_t_last_win_count = now;
- hctx->ccid3hctx_last_win_count += min_t(u32, quarter_rtts, 5);
+ hctx->ccid3hctx_last_win_count += min(quarter_rtts, 5U);
hctx->ccid3hctx_last_win_count &= 0xF; /* mod 16 */
}
}
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index b348dd70c685..c22a3780c14e 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -739,8 +739,8 @@ int dccp_invalid_packet(struct sk_buff *skb)
* If P.type is not Data, Ack, or DataAck and P.X == 0 (the packet
* has short sequence numbers), drop packet and return
*/
- if (dh->dccph_type >= DCCP_PKT_DATA &&
- dh->dccph_type <= DCCP_PKT_DATAACK && dh->dccph_x == 0) {
+ if ((dh->dccph_type < DCCP_PKT_DATA ||
+ dh->dccph_type > DCCP_PKT_DATAACK) && dh->dccph_x == 0) {
DCCP_WARN("P.type (%s) not Data || [Data]Ack, while P.X == 0\n",
dccp_packet_name(dh->dccph_type));
return 1;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 6848e4760f34..79a7ef6209ff 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -90,7 +90,6 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = {
[IFA_LOCAL] = { .type = NLA_U32 },
[IFA_ADDRESS] = { .type = NLA_U32 },
[IFA_BROADCAST] = { .type = NLA_U32 },
- [IFA_ANYCAST] = { .type = NLA_U32 },
[IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 },
};
@@ -536,9 +535,6 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh)
if (tb[IFA_BROADCAST])
ifa->ifa_broadcast = nla_get_be32(tb[IFA_BROADCAST]);
- if (tb[IFA_ANYCAST])
- ifa->ifa_anycast = nla_get_be32(tb[IFA_ANYCAST]);
-
if (tb[IFA_LABEL])
nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ);
else
@@ -745,7 +741,6 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
break;
inet_del_ifa(in_dev, ifap, 0);
ifa->ifa_broadcast = 0;
- ifa->ifa_anycast = 0;
ifa->ifa_scope = 0;
}
@@ -1113,7 +1108,6 @@ static inline size_t inet_nlmsg_size(void)
+ nla_total_size(4) /* IFA_ADDRESS */
+ nla_total_size(4) /* IFA_LOCAL */
+ nla_total_size(4) /* IFA_BROADCAST */
- + nla_total_size(4) /* IFA_ANYCAST */
+ nla_total_size(IFNAMSIZ); /* IFA_LABEL */
}
@@ -1143,9 +1137,6 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa,
if (ifa->ifa_broadcast)
NLA_PUT_BE32(skb, IFA_BROADCAST, ifa->ifa_broadcast);
- if (ifa->ifa_anycast)
- NLA_PUT_BE32(skb, IFA_ANYCAST, ifa->ifa_anycast);
-
if (ifa->ifa_label[0])
NLA_PUT_STRING(skb, IFA_LABEL, ifa->ifa_label);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 0f1557a4ac7a..0b2ac6a3d903 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -506,7 +506,6 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX+1] = {
[RTA_PREFSRC] = { .type = NLA_U32 },
[RTA_METRICS] = { .type = NLA_NESTED },
[RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) },
- [RTA_PROTOINFO] = { .type = NLA_U32 },
[RTA_FLOW] = { .type = NLA_U32 },
};
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index fead049daf43..e7e091d365ff 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -608,6 +608,14 @@ static void raw_close(struct sock *sk, long timeout)
sk_common_release(sk);
}
+static int raw_destroy(struct sock *sk)
+{
+ lock_sock(sk);
+ ip_flush_pending_frames(sk);
+ release_sock(sk);
+ return 0;
+}
+
/* This gets rid of all the nasties in af_inet. -DaveM */
static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
@@ -820,6 +828,7 @@ struct proto raw_prot = {
.name = "RAW",
.owner = THIS_MODULE,
.close = raw_close,
+ .destroy = raw_destroy,
.connect = ip4_datagram_connect,
.disconnect = udp_disconnect,
.ioctl = raw_ioctl,
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index df41026b60db..96be336064fb 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1792,7 +1792,7 @@ static int __mkroute_input(struct sk_buff *skb,
if (err)
flags |= RTCF_DIRECTSRC;
- if (out_dev == in_dev && err && !(flags & RTCF_MASQ) &&
+ if (out_dev == in_dev && err &&
(IN_DEV_SHARED_MEDIA(out_dev) ||
inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res))))
flags |= RTCF_DOREDIRECT;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f88653138621..ab66683b8043 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1227,7 +1227,14 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
copied += used;
offset += used;
}
- if (offset != skb->len)
+ /*
+ * If recv_actor drops the lock (e.g. TCP splice
+ * receive) the skb pointer might be invalid when
+ * getting here: tcp_collapse might have deleted it
+ * while aggregating skbs from the socket queue.
+ */
+ skb = tcp_recv_skb(sk, seq-1, &offset);
+ if (!skb || (offset+1 != skb->len))
break;
}
if (tcp_hdr(skb)->fin) {
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b54d9d37b636..eba873e9b560 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1392,9 +1392,9 @@ static struct sk_buff *tcp_maybe_skipping_dsack(struct sk_buff *skb,
if (before(next_dup->start_seq, skip_to_seq)) {
skb = tcp_sacktag_skip(skb, sk, next_dup->start_seq, fack_count);
- tcp_sacktag_walk(skb, sk, NULL,
- next_dup->start_seq, next_dup->end_seq,
- 1, fack_count, reord, flag);
+ skb = tcp_sacktag_walk(skb, sk, NULL,
+ next_dup->start_seq, next_dup->end_seq,
+ 1, fack_count, reord, flag);
}
return skb;
@@ -2483,6 +2483,20 @@ static inline void tcp_complete_cwr(struct sock *sk)
tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR);
}
+static void tcp_try_keep_open(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ int state = TCP_CA_Open;
+
+ if (tcp_left_out(tp) || tp->retrans_out || tp->undo_marker)
+ state = TCP_CA_Disorder;
+
+ if (inet_csk(sk)->icsk_ca_state != state) {
+ tcp_set_ca_state(sk, state);
+ tp->high_seq = tp->snd_nxt;
+ }
+}
+
static void tcp_try_to_open(struct sock *sk, int flag)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -2496,15 +2510,7 @@ static void tcp_try_to_open(struct sock *sk, int flag)
tcp_enter_cwr(sk, 1);
if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) {
- int state = TCP_CA_Open;
-
- if (tcp_left_out(tp) || tp->retrans_out || tp->undo_marker)
- state = TCP_CA_Disorder;
-
- if (inet_csk(sk)->icsk_ca_state != state) {
- tcp_set_ca_state(sk, state);
- tp->high_seq = tp->snd_nxt;
- }
+ tcp_try_keep_open(sk);
tcp_moderate_cwnd(tp);
} else {
tcp_cwnd_down(sk, flag);
@@ -3310,8 +3316,11 @@ no_queue:
return 1;
old_ack:
- if (TCP_SKB_CB(skb)->sacked)
+ if (TCP_SKB_CB(skb)->sacked) {
tcp_sacktag_write_queue(sk, skb, prior_snd_una);
+ if (icsk->icsk_ca_state == TCP_CA_Open)
+ tcp_try_keep_open(sk);
+ }
uninteresting_ack:
SOCK_DEBUG(sk, "Ack %u out of %u:%u\n", ack, tp->snd_una, tp->snd_nxt);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e399bde7813a..ad993ecb4810 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2131,6 +2131,8 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority)
TCP_SKB_CB(skb)->when = tcp_time_stamp;
if (tcp_transmit_skb(sk, skb, 0, priority))
NET_INC_STATS(LINUX_MIB_TCPABORTFAILED);
+
+ TCP_INC_STATS(TCP_MIB_OUTRSTS);
}
/* WARNING: This routine must only be called when we have already sent
diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c
index d3b709a6f264..cb1f0e83830b 100644
--- a/net/ipv4/tunnel4.c
+++ b/net/ipv4/tunnel4.c
@@ -97,7 +97,7 @@ static int tunnel64_rcv(struct sk_buff *skb)
{
struct xfrm_tunnel *handler;
- if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+ if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
goto drop;
for (handler = tunnel64_handlers; handler; handler = handler->next)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index db1cb7c96d63..56fcda3694ba 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -420,7 +420,7 @@ void udp_err(struct sk_buff *skb, u32 info)
/*
* Throw away all pending data and cancel the corking. Socket is locked.
*/
-static void udp_flush_pending_frames(struct sock *sk)
+void udp_flush_pending_frames(struct sock *sk)
{
struct udp_sock *up = udp_sk(sk);
@@ -430,6 +430,7 @@ static void udp_flush_pending_frames(struct sock *sk)
ip_flush_pending_frames(sk);
}
}
+EXPORT_SYMBOL(udp_flush_pending_frames);
/**
* udp4_hwcsum_outgoing - handle outgoing HW checksumming
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 3a835578fd1c..147588f4c7c0 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -731,8 +731,13 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
onlink = -1;
spin_lock(&ifa->lock);
- lifetime = min_t(unsigned long,
- ifa->valid_lft, 0x7fffffffUL/HZ);
+
+ lifetime = addrconf_timeout_fixup(ifa->valid_lft, HZ);
+ /*
+ * Note: Because this address is
+ * not permanent, lifetime <
+ * LONG_MAX / HZ here.
+ */
if (time_before(expires,
ifa->tstamp + lifetime * HZ))
expires = ifa->tstamp + lifetime * HZ;
@@ -1722,7 +1727,6 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len)
__u32 valid_lft;
__u32 prefered_lft;
int addr_type;
- unsigned long rt_expires;
struct inet6_dev *in6_dev;
pinfo = (struct prefix_info *) opt;
@@ -1764,28 +1768,23 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len)
* 2) Configure prefixes with the auto flag set
*/
- if (valid_lft == INFINITY_LIFE_TIME)
- rt_expires = ~0UL;
- else if (valid_lft >= 0x7FFFFFFF/HZ) {
+ if (pinfo->onlink) {
+ struct rt6_info *rt;
+ unsigned long rt_expires;
+
/* Avoid arithmetic overflow. Really, we could
* save rt_expires in seconds, likely valid_lft,
* but it would require division in fib gc, that it
* not good.
*/
- rt_expires = 0x7FFFFFFF - (0x7FFFFFFF % HZ);
- } else
- rt_expires = valid_lft * HZ;
+ if (HZ > USER_HZ)
+ rt_expires = addrconf_timeout_fixup(valid_lft, HZ);
+ else
+ rt_expires = addrconf_timeout_fixup(valid_lft, USER_HZ);
- /*
- * We convert this (in jiffies) to clock_t later.
- * Avoid arithmetic overflow there as well.
- * Overflow can happen only if HZ < USER_HZ.
- */
- if (HZ < USER_HZ && ~rt_expires && rt_expires > 0x7FFFFFFF / USER_HZ)
- rt_expires = 0x7FFFFFFF / USER_HZ;
+ if (addrconf_finite_timeout(rt_expires))
+ rt_expires *= HZ;
- if (pinfo->onlink) {
- struct rt6_info *rt;
rt = rt6_lookup(dev_net(dev), &pinfo->prefix, NULL,
dev->ifindex, 1);
@@ -1794,7 +1793,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len)
if (valid_lft == 0) {
ip6_del_rt(rt);
rt = NULL;
- } else if (~rt_expires) {
+ } else if (addrconf_finite_timeout(rt_expires)) {
/* not infinity */
rt->rt6i_expires = jiffies + rt_expires;
rt->rt6i_flags |= RTF_EXPIRES;
@@ -1803,9 +1802,9 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len)
rt->rt6i_expires = 0;
}
} else if (valid_lft) {
- int flags = RTF_ADDRCONF | RTF_PREFIX_RT;
clock_t expires = 0;
- if (~rt_expires) {
+ int flags = RTF_ADDRCONF | RTF_PREFIX_RT;
+ if (addrconf_finite_timeout(rt_expires)) {
/* not infinity */
flags |= RTF_EXPIRES;
expires = jiffies_to_clock_t(rt_expires);
@@ -2027,7 +2026,7 @@ err_exit:
* Manual configuration of address on an interface
*/
static int inet6_addr_add(struct net *net, int ifindex, struct in6_addr *pfx,
- int plen, __u8 ifa_flags, __u32 prefered_lft,
+ unsigned int plen, __u8 ifa_flags, __u32 prefered_lft,
__u32 valid_lft)
{
struct inet6_ifaddr *ifp;
@@ -2036,9 +2035,13 @@ static int inet6_addr_add(struct net *net, int ifindex, struct in6_addr *pfx,
int scope;
u32 flags;
clock_t expires;
+ unsigned long timeout;
ASSERT_RTNL();
+ if (plen > 128)
+ return -EINVAL;
+
/* check the lifetime */
if (!valid_lft || prefered_lft > valid_lft)
return -EINVAL;
@@ -2052,22 +2055,23 @@ static int inet6_addr_add(struct net *net, int ifindex, struct in6_addr *pfx,
scope = ipv6_addr_scope(pfx);
- if (valid_lft == INFINITY_LIFE_TIME) {
- ifa_flags |= IFA_F_PERMANENT;
- flags = 0;
- expires = 0;
- } else {
- if (valid_lft >= 0x7FFFFFFF/HZ)
- valid_lft = 0x7FFFFFFF/HZ;
+ timeout = addrconf_timeout_fixup(valid_lft, HZ);
+ if (addrconf_finite_timeout(timeout)) {
+ expires = jiffies_to_clock_t(timeout * HZ);
+ valid_lft = timeout;
flags = RTF_EXPIRES;
- expires = jiffies_to_clock_t(valid_lft * HZ);
+ } else {
+ expires = 0;
+ flags = 0;
+ ifa_flags |= IFA_F_PERMANENT;
}
- if (prefered_lft == 0)
- ifa_flags |= IFA_F_DEPRECATED;
- else if ((prefered_lft >= 0x7FFFFFFF/HZ) &&
- (prefered_lft != INFINITY_LIFE_TIME))
- prefered_lft = 0x7FFFFFFF/HZ;
+ timeout = addrconf_timeout_fixup(prefered_lft, HZ);
+ if (addrconf_finite_timeout(timeout)) {
+ if (timeout == 0)
+ ifa_flags |= IFA_F_DEPRECATED;
+ prefered_lft = timeout;
+ }
ifp = ipv6_add_addr(idev, pfx, plen, scope, ifa_flags);
@@ -2095,12 +2099,15 @@ static int inet6_addr_add(struct net *net, int ifindex, struct in6_addr *pfx,
}
static int inet6_addr_del(struct net *net, int ifindex, struct in6_addr *pfx,
- int plen)
+ unsigned int plen)
{
struct inet6_ifaddr *ifp;
struct inet6_dev *idev;
struct net_device *dev;
+ if (plen > 128)
+ return -EINVAL;
+
dev = __dev_get_by_index(net, ifindex);
if (!dev)
return -ENODEV;
@@ -3169,26 +3176,28 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u8 ifa_flags,
{
u32 flags;
clock_t expires;
+ unsigned long timeout;
if (!valid_lft || (prefered_lft > valid_lft))
return -EINVAL;
- if (valid_lft == INFINITY_LIFE_TIME) {
- ifa_flags |= IFA_F_PERMANENT;
- flags = 0;
- expires = 0;
- } else {
- if (valid_lft >= 0x7FFFFFFF/HZ)
- valid_lft = 0x7FFFFFFF/HZ;
+ timeout = addrconf_timeout_fixup(valid_lft, HZ);
+ if (addrconf_finite_timeout(timeout)) {
+ expires = jiffies_to_clock_t(timeout * HZ);
+ valid_lft = timeout;
flags = RTF_EXPIRES;
- expires = jiffies_to_clock_t(valid_lft * HZ);
+ } else {
+ expires = 0;
+ flags = 0;
+ ifa_flags |= IFA_F_PERMANENT;
}
- if (prefered_lft == 0)
- ifa_flags |= IFA_F_DEPRECATED;
- else if ((prefered_lft >= 0x7FFFFFFF/HZ) &&
- (prefered_lft != INFINITY_LIFE_TIME))
- prefered_lft = 0x7FFFFFFF/HZ;
+ timeout = addrconf_timeout_fixup(prefered_lft, HZ);
+ if (addrconf_finite_timeout(timeout)) {
+ if (timeout == 0)
+ ifa_flags |= IFA_F_DEPRECATED;
+ prefered_lft = timeout;
+ }
spin_lock_bh(&ifp->lock);
ifp->flags = (ifp->flags & ~(IFA_F_DEPRECATED | IFA_F_PERMANENT | IFA_F_NODAD | IFA_F_HOMEADDRESS)) | ifa_flags;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 3c6aafb02183..e84b3fd17fb4 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -191,7 +191,7 @@ lookup_protocol:
np->mcast_hops = -1;
np->mc_loop = 1;
np->pmtudisc = IPV6_PMTUDISC_WANT;
- np->ipv6only = init_net.ipv6.sysctl.bindv6only;
+ np->ipv6only = net->ipv6.sysctl.bindv6only;
/* Init the ipv4 part of the socket since we can have sockets
* using v6 API for ipv4.
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 94fa6ae77cfe..b9c2de84a8a2 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -496,7 +496,8 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb)
return 0;
}
-int datagram_send_ctl(struct msghdr *msg, struct flowi *fl,
+int datagram_send_ctl(struct net *net,
+ struct msghdr *msg, struct flowi *fl,
struct ipv6_txoptions *opt,
int *hlimit, int *tclass)
{
@@ -509,7 +510,6 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl,
for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) {
int addr_type;
- struct net_device *dev = NULL;
if (!CMSG_OK(msg, cmsg)) {
err = -EINVAL;
@@ -522,6 +522,9 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl,
switch (cmsg->cmsg_type) {
case IPV6_PKTINFO:
case IPV6_2292PKTINFO:
+ {
+ struct net_device *dev = NULL;
+
if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct in6_pktinfo))) {
err = -EINVAL;
goto exit_f;
@@ -535,32 +538,32 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl,
fl->oif = src_info->ipi6_ifindex;
}
- addr_type = ipv6_addr_type(&src_info->ipi6_addr);
+ addr_type = __ipv6_addr_type(&src_info->ipi6_addr);
- if (addr_type == IPV6_ADDR_ANY)
- break;
+ if (fl->oif) {
+ dev = dev_get_by_index(net, fl->oif);
+ if (!dev)
+ return -ENODEV;
+ } else if (addr_type & IPV6_ADDR_LINKLOCAL)
+ return -EINVAL;
- if (addr_type & IPV6_ADDR_LINKLOCAL) {
- if (!src_info->ipi6_ifindex)
- return -EINVAL;
- else {
- dev = dev_get_by_index(&init_net, src_info->ipi6_ifindex);
- if (!dev)
- return -ENODEV;
- }
- }
- if (!ipv6_chk_addr(&init_net, &src_info->ipi6_addr,
- dev, 0)) {
- if (dev)
- dev_put(dev);
- err = -EINVAL;
- goto exit_f;
+ if (addr_type != IPV6_ADDR_ANY) {
+ int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL;
+ if (!ipv6_chk_addr(net, &src_info->ipi6_addr,
+ strict ? dev : NULL, 0))
+ err = -EINVAL;
+ else
+ ipv6_addr_copy(&fl->fl6_src, &src_info->ipi6_addr);
}
+
if (dev)
dev_put(dev);
- ipv6_addr_copy(&fl->fl6_src, &src_info->ipi6_addr);
+ if (err)
+ goto exit_f;
+
break;
+ }
case IPV6_FLOWINFO:
if (cmsg->cmsg_len < CMSG_LEN(4)) {
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index eb7a940310f4..37a4e777e347 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -354,7 +354,7 @@ fl_create(struct net *net, struct in6_flowlabel_req *freq, char __user *optval,
msg.msg_control = (void*)(fl->opt+1);
flowi.oif = 0;
- err = datagram_send_ctl(&msg, &flowi, fl->opt, &junk, &junk);
+ err = datagram_send_ctl(net, &msg, &flowi, fl->opt, &junk, &junk);
if (err)
goto done;
err = -EINVAL;
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 56d55fecf8ec..26b83e512a09 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -161,9 +161,17 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
struct ipv6_txoptions *opt;
struct sk_buff *pktopt;
- if (sk->sk_protocol != IPPROTO_UDP &&
- sk->sk_protocol != IPPROTO_UDPLITE &&
- sk->sk_protocol != IPPROTO_TCP)
+ if (sk->sk_type == SOCK_RAW)
+ break;
+
+ if (sk->sk_protocol == IPPROTO_UDP ||
+ sk->sk_protocol == IPPROTO_UDPLITE) {
+ struct udp_sock *up = udp_sk(sk);
+ if (up->pending == AF_INET6) {
+ retv = -EBUSY;
+ break;
+ }
+ } else if (sk->sk_protocol != IPPROTO_TCP)
break;
if (sk->sk_state != TCP_ESTABLISHED) {
@@ -416,7 +424,7 @@ sticky_done:
msg.msg_controllen = optlen;
msg.msg_control = (void*)(opt+1);
- retv = datagram_send_ctl(&msg, &fl, opt, &junk, &junk);
+ retv = datagram_send_ctl(net, &msg, &fl, opt, &junk, &junk);
if (retv)
goto done;
update:
@@ -832,7 +840,7 @@ static int ipv6_getsockopt_sticky(struct sock *sk, struct ipv6_txoptions *opt,
len = min_t(unsigned int, len, ipv6_optlen(hdr));
if (copy_to_user(optval, hdr, len))
return -EFAULT;
- return ipv6_optlen(hdr);
+ return len;
}
static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
@@ -975,6 +983,9 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
len = ipv6_getsockopt_sticky(sk, np->opt,
optname, optval, len);
release_sock(sk);
+ /* check if ipv6_getsockopt_sticky() returns err code */
+ if (len < 0)
+ return len;
return put_user(len, optlen);
}
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 2dccad48058c..e65e26e210ee 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -209,7 +209,9 @@ fq_find(__be32 id, struct in6_addr *src, struct in6_addr *dst)
arg.dst = dst;
hash = ip6qhashfn(id, src, dst);
+ local_bh_disable();
q = inet_frag_find(&nf_init_frags, &nf_frags, &arg, hash);
+ local_bh_enable();
if (q == NULL)
goto oom;
@@ -638,10 +640,10 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb)
goto ret_orig;
}
- spin_lock(&fq->q.lock);
+ spin_lock_bh(&fq->q.lock);
if (nf_ct_frag6_queue(fq, clone, fhdr, nhoff) < 0) {
- spin_unlock(&fq->q.lock);
+ spin_unlock_bh(&fq->q.lock);
pr_debug("Can't insert skb to queue\n");
fq_put(fq);
goto ret_orig;
@@ -653,7 +655,7 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb)
if (ret_skb == NULL)
pr_debug("Can't reassemble fragmented packets\n");
}
- spin_unlock(&fq->q.lock);
+ spin_unlock_bh(&fq->q.lock);
fq_put(fq);
return ret_skb;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 232e0dc45bf5..8fee9a15b2d3 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -813,7 +813,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
memset(opt, 0, sizeof(struct ipv6_txoptions));
opt->tot_len = sizeof(struct ipv6_txoptions);
- err = datagram_send_ctl(msg, &fl, opt, &hlimit, &tclass);
+ err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, &tclass);
if (err < 0) {
fl6_sock_release(flowlabel);
return err;
@@ -1164,6 +1164,14 @@ static void rawv6_close(struct sock *sk, long timeout)
sk_common_release(sk);
}
+static int raw6_destroy(struct sock *sk)
+{
+ lock_sock(sk);
+ ip6_flush_pending_frames(sk);
+ release_sock(sk);
+ return 0;
+}
+
static int rawv6_init_sk(struct sock *sk)
{
struct raw6_sock *rp = raw6_sk(sk);
@@ -1187,6 +1195,7 @@ struct proto rawv6_prot = {
.name = "RAWv6",
.owner = THIS_MODULE,
.close = rawv6_close,
+ .destroy = raw6_destroy,
.connect = ip6_datagram_connect,
.disconnect = udp_disconnect,
.ioctl = rawv6_ioctl,
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 48534c6c0735..220cffe9e63b 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -446,7 +446,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
struct route_info *rinfo = (struct route_info *) opt;
struct in6_addr prefix_buf, *prefix;
unsigned int pref;
- u32 lifetime;
+ unsigned long lifetime;
struct rt6_info *rt;
if (len < sizeof(struct route_info)) {
@@ -472,13 +472,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
if (pref == ICMPV6_ROUTER_PREF_INVALID)
pref = ICMPV6_ROUTER_PREF_MEDIUM;
- lifetime = ntohl(rinfo->lifetime);
- if (lifetime == 0xffffffff) {
- /* infinity */
- } else if (lifetime > 0x7fffffff/HZ - 1) {
- /* Avoid arithmetic overflow */
- lifetime = 0x7fffffff/HZ - 1;
- }
+ lifetime = addrconf_timeout_fixup(ntohl(rinfo->lifetime), HZ);
if (rinfo->length == 3)
prefix = (struct in6_addr *)rinfo->prefix;
@@ -506,7 +500,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
(rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref);
if (rt) {
- if (lifetime == 0xffffffff) {
+ if (!addrconf_finite_timeout(lifetime)) {
rt->rt6i_flags &= ~RTF_EXPIRES;
} else {
rt->rt6i_expires = jiffies + HZ * lifetime;
diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c
index 6323921b40be..669f280989c3 100644
--- a/net/ipv6/tunnel6.c
+++ b/net/ipv6/tunnel6.c
@@ -109,7 +109,7 @@ static int tunnel46_rcv(struct sk_buff *skb)
{
struct xfrm6_tunnel *handler;
- if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
+ if (!pskb_may_pull(skb, sizeof(struct iphdr)))
goto drop;
for (handler = tunnel46_handlers; handler; handler = handler->next)
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 1fd784f3e2ec..dd309626ae9a 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -534,7 +534,9 @@ static void udp_v6_flush_pending_frames(struct sock *sk)
{
struct udp_sock *up = udp_sk(sk);
- if (up->pending) {
+ if (up->pending == AF_INET)
+ udp_flush_pending_frames(sk);
+ else if (up->pending) {
up->len = 0;
up->pending = 0;
ip6_flush_pending_frames(sk);
@@ -731,7 +733,7 @@ do_udp_sendmsg:
memset(opt, 0, sizeof(struct ipv6_txoptions));
opt->tot_len = sizeof(*opt);
- err = datagram_send_ctl(msg, &fl, opt, &hlimit, &tclass);
+ err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, &tclass);
if (err < 0) {
fl6_sock_release(flowlabel);
return err;
@@ -848,12 +850,14 @@ do_append_data:
} else {
dst_release(dst);
}
+ dst = NULL;
}
if (err > 0)
err = np->recverr ? net_xmit_errno(err) : 0;
release_sock(sk);
out:
+ dst_release(dst);
fl6_sock_release(flowlabel);
if (!err)
return len;
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index ae54b20d0470..3eb5bcc75f99 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -1093,11 +1093,6 @@ static int irda_create(struct net *net, struct socket *sock, int protocol)
init_waitqueue_head(&self->query_wait);
- /* Initialise networking socket struct */
- sock_init_data(sock, sk); /* Note : set sk->sk_refcnt to 1 */
- sk->sk_family = PF_IRDA;
- sk->sk_protocol = protocol;
-
switch (sock->type) {
case SOCK_STREAM:
sock->ops = &irda_stream_ops;
@@ -1124,13 +1119,20 @@ static int irda_create(struct net *net, struct socket *sock, int protocol)
self->max_sdu_size_rx = TTP_SAR_UNBOUND;
break;
default:
+ sk_free(sk);
return -ESOCKTNOSUPPORT;
}
break;
default:
+ sk_free(sk);
return -ESOCKTNOSUPPORT;
}
+ /* Initialise networking socket struct */
+ sock_init_data(sock, sk); /* Note : set sk->sk_refcnt to 1 */
+ sk->sk_family = PF_IRDA;
+ sk->sk_protocol = protocol;
+
/* Register as a client with IrLMP */
self->ckey = irlmp_register_client(0, NULL, NULL, NULL);
self->mask.word = 0xffff;
diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c
index e2ddde755019..008de1fc42ca 100644
--- a/net/llc/llc_sap.c
+++ b/net/llc/llc_sap.c
@@ -286,12 +286,14 @@ void llc_build_and_send_xid_pkt(struct llc_sap *sap, struct sk_buff *skb,
*
* Sends received pdus to the sap state machine.
*/
-static void llc_sap_rcv(struct llc_sap *sap, struct sk_buff *skb)
+static void llc_sap_rcv(struct llc_sap *sap, struct sk_buff *skb,
+ struct sock *sk)
{
struct llc_sap_state_ev *ev = llc_sap_ev(skb);
ev->type = LLC_SAP_EV_TYPE_PDU;
ev->reason = 0;
+ skb->sk = sk;
llc_sap_state_process(sap, skb);
}
@@ -360,8 +362,7 @@ static void llc_sap_mcast(struct llc_sap *sap,
break;
sock_hold(sk);
- skb_set_owner_r(skb1, sk);
- llc_sap_rcv(sap, skb1);
+ llc_sap_rcv(sap, skb1, sk);
sock_put(sk);
}
read_unlock_bh(&sap->sk_list.lock);
@@ -381,8 +382,7 @@ void llc_sap_handler(struct llc_sap *sap, struct sk_buff *skb)
} else {
struct sock *sk = llc_lookup_dgram(sap, &laddr);
if (sk) {
- skb_set_owner_r(skb, sk);
- llc_sap_rcv(sap, skb);
+ llc_sap_rcv(sap, skb, sk);
sock_put(sk);
} else
kfree_skb(skb);
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index dbf0563c397d..81087281b031 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -674,7 +674,7 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev,
if (params->vlan) {
sdata = IEEE80211_DEV_TO_SUB_IF(params->vlan);
- if (sdata->vif.type != IEEE80211_IF_TYPE_VLAN ||
+ if (sdata->vif.type != IEEE80211_IF_TYPE_VLAN &&
sdata->vif.type != IEEE80211_IF_TYPE_AP)
return -EINVAL;
} else
@@ -762,7 +762,7 @@ static int ieee80211_change_station(struct wiphy *wiphy,
if (params->vlan && params->vlan != sta->sdata->dev) {
vlansdata = IEEE80211_DEV_TO_SUB_IF(params->vlan);
- if (vlansdata->vif.type != IEEE80211_IF_TYPE_VLAN ||
+ if (vlansdata->vif.type != IEEE80211_IF_TYPE_VLAN &&
vlansdata->vif.type != IEEE80211_IF_TYPE_AP) {
rcu_read_unlock();
return -EINVAL;
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 432011cd3647..884be4d100f1 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -853,7 +853,29 @@ u32 ieee80211_handle_ht(struct ieee80211_local *local, int enable_ht,
/* ieee80211_ioctl.c */
extern const struct iw_handler_def ieee80211_iw_handler_def;
-int ieee80211_set_freq(struct ieee80211_local *local, int freq);
+
+/* Least common multiple of the used rates (in 100 kbps). This is used to
+ * calculate rate_inv values for each rate so that only integers are needed. */
+#define CHAN_UTIL_RATE_LCM 95040
+/* 1 usec is 1/8 * (95040/10) = 1188 */
+#define CHAN_UTIL_PER_USEC 1188
+/* Amount of bits to shift the result right to scale the total utilization
+ * to values that will not wrap around 32-bit integers. */
+#define CHAN_UTIL_SHIFT 9
+/* Theoretical maximum of channel utilization counter in 10 ms (stat_time=1):
+ * (CHAN_UTIL_PER_USEC * 10000) >> CHAN_UTIL_SHIFT = 23203. So dividing the
+ * raw value with about 23 should give utilization in 10th of a percentage
+ * (1/1000). However, utilization is only estimated and not all intervals
+ * between frames etc. are calculated. 18 seems to give numbers that are closer
+ * to the real maximum. */
+#define CHAN_UTIL_PER_10MS 18
+#define CHAN_UTIL_HDR_LONG (202 * CHAN_UTIL_PER_USEC)
+#define CHAN_UTIL_HDR_SHORT (40 * CHAN_UTIL_PER_USEC)
+
+
+/* ieee80211_ioctl.c */
+int ieee80211_set_freq(struct net_device *dev, int freq);
+
/* ieee80211_sta.c */
void ieee80211_sta_timer(unsigned long data);
void ieee80211_sta_work(struct work_struct *work);
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index f79f6b9938a6..b182f018a187 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -516,6 +516,7 @@ static int ieee80211_stop(struct net_device *dev)
case IEEE80211_IF_TYPE_STA:
case IEEE80211_IF_TYPE_IBSS:
sdata->u.sta.state = IEEE80211_DISABLED;
+ memset(sdata->u.sta.bssid, 0, ETH_ALEN);
del_timer_sync(&sdata->u.sta.timer);
/*
* When we get here, the interface is marked down.
@@ -1314,7 +1315,7 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local,
/*
* Clear the TX filter mask for this STA when sending the next
* packet. If the STA went to power save mode, this will happen
- * happen when it wakes up for the next time.
+ * when it wakes up for the next time.
*/
set_sta_flags(sta, WLAN_STA_CLEAR_PS_FILT);
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index adbc1c804dd3..7f05820dc629 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -44,7 +44,7 @@
#define IEEE80211_RETRY_AUTH_INTERVAL (1 * HZ)
#define IEEE80211_SCAN_INTERVAL (2 * HZ)
#define IEEE80211_SCAN_INTERVAL_SLOW (15 * HZ)
-#define IEEE80211_IBSS_JOIN_TIMEOUT (20 * HZ)
+#define IEEE80211_IBSS_JOIN_TIMEOUT (7 * HZ)
#define IEEE80211_PROBE_DELAY (HZ / 33)
#define IEEE80211_CHANNEL_TIME (HZ / 33)
@@ -1337,7 +1337,7 @@ static void ieee80211_sta_process_addba_request(struct net_device *dev,
/* prepare reordering buffer */
tid_agg_rx->reorder_buf =
- kmalloc(buf_size * sizeof(struct sk_buf *), GFP_ATOMIC);
+ kmalloc(buf_size * sizeof(struct sk_buff *), GFP_ATOMIC);
if (!tid_agg_rx->reorder_buf) {
if (net_ratelimit())
printk(KERN_ERR "can not allocate reordering buffer "
@@ -1346,7 +1346,7 @@ static void ieee80211_sta_process_addba_request(struct net_device *dev,
goto end;
}
memset(tid_agg_rx->reorder_buf, 0,
- buf_size * sizeof(struct sk_buf *));
+ buf_size * sizeof(struct sk_buff *));
if (local->ops->ampdu_action)
ret = local->ops->ampdu_action(hw, IEEE80211_AMPDU_RX_START,
@@ -1625,7 +1625,7 @@ void sta_addba_resp_timer_expired(unsigned long data)
* only one argument, and both sta_info and TID are needed, so init
* flow in sta_info_create gives the TID as data, while the timer_to_id
* array gives the sta through container_of */
- u16 tid = *(int *)data;
+ u16 tid = *(u8 *)data;
struct sta_info *temp_sta = container_of((void *)data,
struct sta_info, timer_to_tid[tid]);
@@ -1673,7 +1673,7 @@ timer_expired_exit:
static void sta_rx_agg_session_timer_expired(unsigned long data)
{
/* not an elegant detour, but there is no choice as the timer passes
- * only one argument, and verious sta_info are needed here, so init
+ * only one argument, and various sta_info are needed here, so init
* flow in sta_info_create gives the TID as data, while the timer_to_id
* array gives the sta through container_of */
u8 *ptid = (u8 *)data;
@@ -2348,6 +2348,7 @@ static int ieee80211_sta_join_ibss(struct net_device *dev,
u8 *pos;
struct ieee80211_sub_if_data *sdata;
struct ieee80211_supported_band *sband;
+ union iwreq_data wrqu;
sband = local->hw.wiphy->bands[local->hw.conf.channel->band];
@@ -2370,13 +2371,10 @@ static int ieee80211_sta_join_ibss(struct net_device *dev,
sdata->drop_unencrypted = bss->capability &
WLAN_CAPABILITY_PRIVACY ? 1 : 0;
- res = ieee80211_set_freq(local, bss->freq);
+ res = ieee80211_set_freq(dev, bss->freq);
- if (local->oper_channel->flags & IEEE80211_CHAN_NO_IBSS) {
- printk(KERN_DEBUG "%s: IBSS not allowed on frequency "
- "%d MHz\n", dev->name, local->oper_channel->center_freq);
- return -1;
- }
+ if (res)
+ return res;
/* Set beacon template */
skb = dev_alloc_skb(local->hw.extra_tx_headroom + 400);
@@ -2491,7 +2489,9 @@ static int ieee80211_sta_join_ibss(struct net_device *dev,
ifsta->state = IEEE80211_IBSS_JOINED;
mod_timer(&ifsta->timer, jiffies + IEEE80211_IBSS_MERGE_INTERVAL);
- ieee80211_rx_bss_put(dev, bss);
+ memset(&wrqu, 0, sizeof(wrqu));
+ memcpy(wrqu.ap_addr.sa_data, bss->bssid, ETH_ALEN);
+ wireless_send_event(dev, SIOCGIWAP, &wrqu, NULL);
return res;
}
@@ -3518,7 +3518,7 @@ static int ieee80211_sta_config_auth(struct net_device *dev,
spin_unlock_bh(&local->sta_bss_lock);
if (selected) {
- ieee80211_set_freq(local, selected->freq);
+ ieee80211_set_freq(dev, selected->freq);
if (!(ifsta->flags & IEEE80211_STA_SSID_SET))
ieee80211_sta_set_ssid(dev, selected->ssid,
selected->ssid_len);
@@ -3553,6 +3553,7 @@ static int ieee80211_sta_create_ibss(struct net_device *dev,
struct ieee80211_supported_band *sband;
u8 bssid[ETH_ALEN], *pos;
int i;
+ int ret;
DECLARE_MAC_BUF(mac);
#if 0
@@ -3599,7 +3600,9 @@ static int ieee80211_sta_create_ibss(struct net_device *dev,
*pos++ = (u8) (rate / 5);
}
- return ieee80211_sta_join_ibss(dev, ifsta, bss);
+ ret = ieee80211_sta_join_ibss(dev, ifsta, bss);
+ ieee80211_rx_bss_put(dev, bss);
+ return ret;
}
@@ -3647,10 +3650,13 @@ static int ieee80211_sta_find_ibss(struct net_device *dev,
(bss = ieee80211_rx_bss_get(dev, bssid,
local->hw.conf.channel->center_freq,
ifsta->ssid, ifsta->ssid_len))) {
+ int ret;
printk(KERN_DEBUG "%s: Selected IBSS BSSID %s"
" based on configured SSID\n",
dev->name, print_mac(mac, bssid));
- return ieee80211_sta_join_ibss(dev, ifsta, bss);
+ ret = ieee80211_sta_join_ibss(dev, ifsta, bss);
+ ieee80211_rx_bss_put(dev, bss);
+ return ret;
}
#ifdef CONFIG_MAC80211_IBSS_DEBUG
printk(KERN_DEBUG " did not try to join ibss\n");
@@ -4127,18 +4133,17 @@ ieee80211_sta_scan_result(struct net_device *dev,
memset(&iwe, 0, sizeof(iwe));
iwe.cmd = SIOCGIWFREQ;
- iwe.u.freq.m = bss->freq;
- iwe.u.freq.e = 6;
+ iwe.u.freq.m = ieee80211_frequency_to_channel(bss->freq);
+ iwe.u.freq.e = 0;
current_ev = iwe_stream_add_event(current_ev, end_buf, &iwe,
IW_EV_FREQ_LEN);
memset(&iwe, 0, sizeof(iwe));
iwe.cmd = SIOCGIWFREQ;
- iwe.u.freq.m = ieee80211_frequency_to_channel(bss->freq);
- iwe.u.freq.e = 0;
+ iwe.u.freq.m = bss->freq;
+ iwe.u.freq.e = 6;
current_ev = iwe_stream_add_event(current_ev, end_buf, &iwe,
IW_EV_FREQ_LEN);
-
memset(&iwe, 0, sizeof(iwe));
iwe.cmd = IWEVQUAL;
iwe.u.qual.qual = bss->qual;
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 9400a9766a77..a3643fd86af9 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1116,7 +1116,7 @@ ieee80211_data_to_8023(struct ieee80211_rx_data *rx)
u16 fc, hdrlen, ethertype;
u8 *payload;
u8 dst[ETH_ALEN];
- u8 src[ETH_ALEN];
+ u8 src[ETH_ALEN] __aligned(2);
struct sk_buff *skb = rx->skb;
struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
DECLARE_MAC_BUF(mac);
@@ -1259,7 +1259,7 @@ ieee80211_data_to_8023(struct ieee80211_rx_data *rx)
*/
static bool ieee80211_frame_allowed(struct ieee80211_rx_data *rx)
{
- static const u8 pae_group_addr[ETH_ALEN]
+ static const u8 pae_group_addr[ETH_ALEN] __aligned(2)
= { 0x01, 0x80, 0xC2, 0x00, 0x00, 0x03 };
struct ethhdr *ehdr = (struct ethhdr *) rx->skb->data;
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 5a77e2c01f49..6513bc2d2707 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -34,11 +34,11 @@ void *mac80211_wiphy_privid = &mac80211_wiphy_privid;
/* See IEEE 802.1H for LLC/SNAP encapsulation/decapsulation */
/* Ethernet-II snap header (RFC1042 for most EtherTypes) */
-const unsigned char rfc1042_header[] =
+const unsigned char rfc1042_header[] __aligned(2) =
{ 0xaa, 0xaa, 0x03, 0x00, 0x00, 0x00 };
/* Bridge-Tunnel header (for EtherTypes ETH_P_AARP and ETH_P_IPX) */
-const unsigned char bridge_tunnel_header[] =
+const unsigned char bridge_tunnel_header[] __aligned(2) =
{ 0xaa, 0xaa, 0x03, 0x00, 0x00, 0xf8 };
diff --git a/net/mac80211/wext.c b/net/mac80211/wext.c
index c2e2378af082..4806d96b9877 100644
--- a/net/mac80211/wext.c
+++ b/net/mac80211/wext.c
@@ -302,14 +302,22 @@ static int ieee80211_ioctl_giwmode(struct net_device *dev,
return 0;
}
-int ieee80211_set_freq(struct ieee80211_local *local, int freqMHz)
+int ieee80211_set_freq(struct net_device *dev, int freqMHz)
{
int ret = -EINVAL;
struct ieee80211_channel *chan;
+ struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr);
+ struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
chan = ieee80211_get_channel(local->hw.wiphy, freqMHz);
if (chan && !(chan->flags & IEEE80211_CHAN_DISABLED)) {
+ if (sdata->vif.type == IEEE80211_IF_TYPE_IBSS &&
+ chan->flags & IEEE80211_CHAN_NO_IBSS) {
+ printk(KERN_DEBUG "%s: IBSS not allowed on frequency "
+ "%d MHz\n", dev->name, chan->center_freq);
+ return ret;
+ }
local->oper_channel = chan;
if (local->sta_sw_scanning || local->sta_hw_scanning)
@@ -327,7 +335,6 @@ static int ieee80211_ioctl_siwfreq(struct net_device *dev,
struct iw_request_info *info,
struct iw_freq *freq, char *extra)
{
- struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr);
struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
if (sdata->vif.type == IEEE80211_IF_TYPE_STA)
@@ -341,14 +348,14 @@ static int ieee80211_ioctl_siwfreq(struct net_device *dev,
IEEE80211_STA_AUTO_CHANNEL_SEL;
return 0;
} else
- return ieee80211_set_freq(local,
+ return ieee80211_set_freq(dev,
ieee80211_channel_to_frequency(freq->m));
} else {
int i, div = 1000000;
for (i = 0; i < freq->e; i++)
div /= 10;
if (div > 0)
- return ieee80211_set_freq(local, freq->m / div);
+ return ieee80211_set_freq(dev, freq->m / div);
else
return -EINVAL;
}
@@ -501,9 +508,14 @@ static int ieee80211_ioctl_giwap(struct net_device *dev,
sdata = IEEE80211_DEV_TO_SUB_IF(dev);
if (sdata->vif.type == IEEE80211_IF_TYPE_STA ||
sdata->vif.type == IEEE80211_IF_TYPE_IBSS) {
- ap_addr->sa_family = ARPHRD_ETHER;
- memcpy(&ap_addr->sa_data, sdata->u.sta.bssid, ETH_ALEN);
- return 0;
+ if (sdata->u.sta.state == IEEE80211_ASSOCIATED) {
+ ap_addr->sa_family = ARPHRD_ETHER;
+ memcpy(&ap_addr->sa_data, sdata->u.sta.bssid, ETH_ALEN);
+ return 0;
+ } else {
+ memset(&ap_addr->sa_data, 0, ETH_ALEN);
+ return 0;
+ }
} else if (sdata->vif.type == IEEE80211_IF_TYPE_WDS) {
ap_addr->sa_family = ARPHRD_ETHER;
memcpy(&ap_addr->sa_data, sdata->u.wds.remote_addr, ETH_ALEN);
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index e31beeb33b2b..e8f0dead267f 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -587,10 +587,10 @@ int __init nf_conntrack_expect_init(void)
return 0;
err3:
+ kmem_cache_destroy(nf_ct_expect_cachep);
+err2:
nf_ct_free_hashtable(nf_ct_expect_hash, nf_ct_expect_vmalloc,
nf_ct_expect_hsize);
-err2:
- kmem_cache_destroy(nf_ct_expect_cachep);
err1:
return err;
}
diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c
index 2e89a00df92c..70907f6baac3 100644
--- a/net/netfilter/xt_connlimit.c
+++ b/net/netfilter/xt_connlimit.c
@@ -73,7 +73,8 @@ connlimit_iphash6(const union nf_inet_addr *addr,
static inline bool already_closed(const struct nf_conn *conn)
{
if (nf_ct_protonum(conn) == IPPROTO_TCP)
- return conn->proto.tcp.state == TCP_CONNTRACK_TIME_WAIT;
+ return conn->proto.tcp.state == TCP_CONNTRACK_TIME_WAIT ||
+ conn->proto.tcp.state == TCP_CONNTRACK_CLOSE;
else
return 0;
}
diff --git a/net/netlink/attr.c b/net/netlink/attr.c
index feb326f4a752..47bbf45ae5d7 100644
--- a/net/netlink/attr.c
+++ b/net/netlink/attr.c
@@ -400,13 +400,13 @@ void __nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data)
* @attrlen: length of attribute payload
* @data: head of attribute payload
*
- * Returns -1 if the tailroom of the skb is insufficient to store
+ * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store
* the attribute header and payload.
*/
int nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data)
{
if (unlikely(skb_tailroom(skb) < nla_total_size(attrlen)))
- return -1;
+ return -EMSGSIZE;
__nla_put(skb, attrtype, attrlen, data);
return 0;
@@ -418,13 +418,13 @@ int nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data)
* @attrlen: length of attribute payload
* @data: head of attribute payload
*
- * Returns -1 if the tailroom of the skb is insufficient to store
+ * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store
* the attribute payload.
*/
int nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data)
{
if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen)))
- return -1;
+ return -EMSGSIZE;
__nla_put_nohdr(skb, attrlen, data);
return 0;
@@ -436,13 +436,13 @@ int nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data)
* @attrlen: length of attribute payload
* @data: head of attribute payload
*
- * Returns -1 if the tailroom of the skb is insufficient to store
+ * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store
* the attribute payload.
*/
int nla_append(struct sk_buff *skb, int attrlen, const void *data)
{
if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen)))
- return -1;
+ return -EMSGSIZE;
memcpy(skb_put(skb, attrlen), data, attrlen);
return 0;
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index d16929c9b4bc..f5aa23c3e886 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -554,7 +554,8 @@ static int ctrl_fill_info(struct genl_family *family, u32 pid, u32 seq,
return genlmsg_end(skb, hdr);
nla_put_failure:
- return genlmsg_cancel(skb, hdr);
+ genlmsg_cancel(skb, hdr);
+ return -EMSGSIZE;
}
static int ctrl_fill_mcgrp_info(struct genl_multicast_group *grp, u32 pid,
@@ -590,7 +591,8 @@ static int ctrl_fill_mcgrp_info(struct genl_multicast_group *grp, u32 pid,
return genlmsg_end(skb, hdr);
nla_put_failure:
- return genlmsg_cancel(skb, hdr);
+ genlmsg_cancel(skb, hdr);
+ return -EMSGSIZE;
}
static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb)
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 0df911fd67b1..64465bacbe79 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -444,7 +444,8 @@ static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl,
return nla_nest_end(skb, opts);
nla_put_failure:
- return nla_nest_cancel(skb, opts);
+ nla_nest_cancel(skb, opts);
+ return -EMSGSIZE;
}
static int dsmark_dump(struct Qdisc *sch, struct sk_buff *skb)
@@ -466,7 +467,8 @@ static int dsmark_dump(struct Qdisc *sch, struct sk_buff *skb)
return nla_nest_end(skb, opts);
nla_put_failure:
- return nla_nest_cancel(skb, opts);
+ nla_nest_cancel(skb, opts);
+ return -EMSGSIZE;
}
static const struct Qdisc_class_ops dsmark_class_ops = {
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index 3a9d226ff1e4..c89fba56db56 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -582,7 +582,8 @@ append_opt:
return nla_nest_end(skb, opts);
nla_put_failure:
- return nla_nest_cancel(skb, opts);
+ nla_nest_cancel(skb, opts);
+ return -EMSGSIZE;
}
static void gred_destroy(struct Qdisc *sch)
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 87293d0db1d7..fdfaa3fcc16d 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1360,7 +1360,7 @@ hfsc_dump_class(struct Qdisc *sch, unsigned long arg, struct sk_buff *skb,
nla_put_failure:
nla_nest_cancel(skb, nest);
- return -1;
+ return -EMSGSIZE;
}
static int
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 3dcd493f4f4a..5c569853b9c0 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -281,7 +281,8 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb)
return nla_nest_end(skb, opts);
nla_put_failure:
- return nla_nest_cancel(skb, opts);
+ nla_nest_cancel(skb, opts);
+ return -EMSGSIZE;
}
static int red_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 7b79d1e781a8..d5cc731b6798 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1206,6 +1206,9 @@ void sctp_assoc_update_retran_path(struct sctp_association *asoc)
struct list_head *head = &asoc->peer.transport_addr_list;
struct list_head *pos;
+ if (asoc->peer.transport_count == 1)
+ return;
+
/* Find the next transport in a round-robin fashion. */
t = asoc->peer.retran_path;
pos = &t->transports;
@@ -1220,6 +1223,15 @@ void sctp_assoc_update_retran_path(struct sctp_association *asoc)
t = list_entry(pos, struct sctp_transport, transports);
+ /* We have exhausted the list, but didn't find any
+ * other active transports. If so, use the next
+ * transport.
+ */
+ if (t == asoc->peer.retran_path) {
+ t = next;
+ break;
+ }
+
/* Try to find an active transport. */
if ((t->state == SCTP_ACTIVE) ||
@@ -1232,15 +1244,6 @@ void sctp_assoc_update_retran_path(struct sctp_association *asoc)
if (!next)
next = t;
}
-
- /* We have exhausted the list, but didn't find any
- * other active transports. If so, use the next
- * transport.
- */
- if (t == asoc->peer.retran_path) {
- t = next;
- break;
- }
}
asoc->peer.retran_path = t;
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index e45e44c60635..a2f4d4d51593 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -299,7 +299,8 @@ static inline int sctp_v6_addr_match_len(union sctp_addr *s1,
/* Fills in the source address(saddr) based on the destination address(daddr)
* and asoc's bind address list.
*/
-static void sctp_v6_get_saddr(struct sctp_association *asoc,
+static void sctp_v6_get_saddr(struct sctp_sock *sk,
+ struct sctp_association *asoc,
struct dst_entry *dst,
union sctp_addr *daddr,
union sctp_addr *saddr)
@@ -318,7 +319,7 @@ static void sctp_v6_get_saddr(struct sctp_association *asoc,
if (!asoc) {
ipv6_dev_get_saddr(dst ? ip6_dst_idev(dst)->dev : NULL,
&daddr->v6.sin6_addr,
- inet6_sk(asoc->base.sk)->srcprefs,
+ inet6_sk(&sk->inet.sk)->srcprefs,
&saddr->v6.sin6_addr);
SCTP_DEBUG_PRINTK("saddr from ipv6_get_saddr: " NIP6_FMT "\n",
NIP6(saddr->v6.sin6_addr));
@@ -726,6 +727,11 @@ static void sctp_v6_seq_dump_addr(struct seq_file *seq, union sctp_addr *addr)
seq_printf(seq, NIP6_FMT " ", NIP6(addr->v6.sin6_addr));
}
+static void sctp_v6_ecn_capable(struct sock *sk)
+{
+ inet6_sk(sk)->tclass |= INET_ECN_ECT_0;
+}
+
/* Initialize a PF_INET6 socket msg_name. */
static void sctp_inet6_msgname(char *msgname, int *addr_len)
{
@@ -996,6 +1002,7 @@ static struct sctp_af sctp_af_inet6 = {
.skb_iif = sctp_v6_skb_iif,
.is_ce = sctp_v6_is_ce,
.seq_dump_addr = sctp_v6_seq_dump_addr,
+ .ecn_capable = sctp_v6_ecn_capable,
.net_header_len = sizeof(struct ipv6hdr),
.sockaddr_len = sizeof(struct sockaddr_in6),
#ifdef CONFIG_COMPAT
diff --git a/net/sctp/output.c b/net/sctp/output.c
index cf4f9fb6819d..6d45bae93b46 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -548,7 +548,7 @@ int sctp_packet_transmit(struct sctp_packet *packet)
* Note: The works for IPv6 layer checks this bit too later
* in transmission. See IP6_ECN_flow_xmit().
*/
- INET_ECN_xmit(nskb->sk);
+ (*tp->af_specific->ecn_capable)(nskb->sk);
/* Set up the IP options. */
/* BUG: not implemented
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 59edfd25a19c..ace6770e9048 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -208,6 +208,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q)
INIT_LIST_HEAD(&q->sacked);
INIT_LIST_HEAD(&q->abandoned);
+ q->fast_rtx = 0;
q->outstanding_bytes = 0;
q->empty = 1;
q->cork = 0;
@@ -500,6 +501,7 @@ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport,
case SCTP_RTXR_FAST_RTX:
SCTP_INC_STATS(SCTP_MIB_FAST_RETRANSMITS);
sctp_transport_lower_cwnd(transport, SCTP_LOWER_CWND_FAST_RTX);
+ q->fast_rtx = 1;
break;
case SCTP_RTXR_PMTUD:
SCTP_INC_STATS(SCTP_MIB_PMTUD_RETRANSMITS);
@@ -518,9 +520,15 @@ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport,
* the sender SHOULD try to advance the "Advanced.Peer.Ack.Point" by
* following the procedures outlined in C1 - C5.
*/
- sctp_generate_fwdtsn(q, q->asoc->ctsn_ack_point);
+ if (reason == SCTP_RTXR_T3_RTX)
+ sctp_generate_fwdtsn(q, q->asoc->ctsn_ack_point);
- error = sctp_outq_flush(q, /* rtx_timeout */ 1);
+ /* Flush the queues only on timeout, since fast_rtx is only
+ * triggered during sack processing and the queue
+ * will be flushed at the end.
+ */
+ if (reason != SCTP_RTXR_FAST_RTX)
+ error = sctp_outq_flush(q, /* rtx_timeout */ 1);
if (error)
q->asoc->base.sk->sk_err = -error;
@@ -538,17 +546,23 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt,
int rtx_timeout, int *start_timer)
{
struct list_head *lqueue;
- struct list_head *lchunk;
struct sctp_transport *transport = pkt->transport;
sctp_xmit_t status;
struct sctp_chunk *chunk, *chunk1;
struct sctp_association *asoc;
+ int fast_rtx;
int error = 0;
+ int timer = 0;
+ int done = 0;
asoc = q->asoc;
lqueue = &q->retransmit;
+ fast_rtx = q->fast_rtx;
- /* RFC 2960 6.3.3 Handle T3-rtx Expiration
+ /* This loop handles time-out retransmissions, fast retransmissions,
+ * and retransmissions due to opening of whindow.
+ *
+ * RFC 2960 6.3.3 Handle T3-rtx Expiration
*
* E3) Determine how many of the earliest (i.e., lowest TSN)
* outstanding DATA chunks for the address for which the
@@ -563,12 +577,12 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt,
* [Just to be painfully clear, if we are retransmitting
* because a timeout just happened, we should send only ONE
* packet of retransmitted data.]
+ *
+ * For fast retransmissions we also send only ONE packet. However,
+ * if we are just flushing the queue due to open window, we'll
+ * try to send as much as possible.
*/
- lchunk = sctp_list_dequeue(lqueue);
-
- while (lchunk) {
- chunk = list_entry(lchunk, struct sctp_chunk,
- transmitted_list);
+ list_for_each_entry_safe(chunk, chunk1, lqueue, transmitted_list) {
/* Make sure that Gap Acked TSNs are not retransmitted. A
* simple approach is just to move such TSNs out of the
@@ -576,58 +590,60 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt,
* next chunk.
*/
if (chunk->tsn_gap_acked) {
- list_add_tail(lchunk, &transport->transmitted);
- lchunk = sctp_list_dequeue(lqueue);
+ list_del(&chunk->transmitted_list);
+ list_add_tail(&chunk->transmitted_list,
+ &transport->transmitted);
continue;
}
+ /* If we are doing fast retransmit, ignore non-fast_rtransmit
+ * chunks
+ */
+ if (fast_rtx && !chunk->fast_retransmit)
+ continue;
+
/* Attempt to append this chunk to the packet. */
status = sctp_packet_append_chunk(pkt, chunk);
switch (status) {
case SCTP_XMIT_PMTU_FULL:
/* Send this packet. */
- if ((error = sctp_packet_transmit(pkt)) == 0)
- *start_timer = 1;
+ error = sctp_packet_transmit(pkt);
/* If we are retransmitting, we should only
* send a single packet.
*/
- if (rtx_timeout) {
- list_add(lchunk, lqueue);
- lchunk = NULL;
- }
+ if (rtx_timeout || fast_rtx)
+ done = 1;
- /* Bundle lchunk in the next round. */
+ /* Bundle next chunk in the next round. */
break;
case SCTP_XMIT_RWND_FULL:
/* Send this packet. */
- if ((error = sctp_packet_transmit(pkt)) == 0)
- *start_timer = 1;
+ error = sctp_packet_transmit(pkt);
/* Stop sending DATA as there is no more room
* at the receiver.
*/
- list_add(lchunk, lqueue);
- lchunk = NULL;
+ done = 1;
break;
case SCTP_XMIT_NAGLE_DELAY:
/* Send this packet. */
- if ((error = sctp_packet_transmit(pkt)) == 0)
- *start_timer = 1;
+ error = sctp_packet_transmit(pkt);
/* Stop sending DATA because of nagle delay. */
- list_add(lchunk, lqueue);
- lchunk = NULL;
+ done = 1;
break;
default:
/* The append was successful, so add this chunk to
* the transmitted list.
*/
- list_add_tail(lchunk, &transport->transmitted);
+ list_del(&chunk->transmitted_list);
+ list_add_tail(&chunk->transmitted_list,
+ &transport->transmitted);
/* Mark the chunk as ineligible for fast retransmit
* after it is retransmitted.
@@ -635,27 +651,44 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt,
if (chunk->fast_retransmit > 0)
chunk->fast_retransmit = -1;
- *start_timer = 1;
- q->empty = 0;
+ /* Force start T3-rtx timer when fast retransmitting
+ * the earliest outstanding TSN
+ */
+ if (!timer && fast_rtx &&
+ ntohl(chunk->subh.data_hdr->tsn) ==
+ asoc->ctsn_ack_point + 1)
+ timer = 2;
- /* Retrieve a new chunk to bundle. */
- lchunk = sctp_list_dequeue(lqueue);
+ q->empty = 0;
break;
}
- /* If we are here due to a retransmit timeout or a fast
- * retransmit and if there are any chunks left in the retransmit
- * queue that could not fit in the PMTU sized packet, they need
- * to be marked as ineligible for a subsequent fast retransmit.
- */
- if (rtx_timeout && !lchunk) {
- list_for_each_entry(chunk1, lqueue, transmitted_list) {
- if (chunk1->fast_retransmit > 0)
- chunk1->fast_retransmit = -1;
- }
+ /* Set the timer if there were no errors */
+ if (!error && !timer)
+ timer = 1;
+
+ if (done)
+ break;
+ }
+
+ /* If we are here due to a retransmit timeout or a fast
+ * retransmit and if there are any chunks left in the retransmit
+ * queue that could not fit in the PMTU sized packet, they need
+ * to be marked as ineligible for a subsequent fast retransmit.
+ */
+ if (rtx_timeout || fast_rtx) {
+ list_for_each_entry(chunk1, lqueue, transmitted_list) {
+ if (chunk1->fast_retransmit > 0)
+ chunk1->fast_retransmit = -1;
}
}
+ *start_timer = timer;
+
+ /* Clear fast retransmit hint */
+ if (fast_rtx)
+ q->fast_rtx = 0;
+
return error;
}
@@ -862,7 +895,8 @@ int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout)
rtx_timeout, &start_timer);
if (start_timer)
- sctp_transport_reset_timers(transport);
+ sctp_transport_reset_timers(transport,
+ start_timer-1);
/* This can happen on COOKIE-ECHO resend. Only
* one chunk can get bundled with a COOKIE-ECHO.
@@ -977,7 +1011,7 @@ int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout)
list_add_tail(&chunk->transmitted_list,
&transport->transmitted);
- sctp_transport_reset_timers(transport);
+ sctp_transport_reset_timers(transport, start_timer-1);
q->empty = 0;
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index b8bd9e014498..d6af466091d2 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -473,11 +473,11 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc,
/* Walk through the bind address list and look for a bind
* address that matches the source address of the returned dst.
*/
+ sctp_v4_dst_saddr(&dst_saddr, dst, htons(bp->port));
rcu_read_lock();
list_for_each_entry_rcu(laddr, &bp->address_list, list) {
if (!laddr->valid || (laddr->state != SCTP_ADDR_SRC))
continue;
- sctp_v4_dst_saddr(&dst_saddr, dst, htons(bp->port));
if (sctp_v4_cmp_addr(&dst_saddr, &laddr->a))
goto out_unlock;
}
@@ -522,7 +522,8 @@ out:
/* For v4, the source address is cached in the route entry(dst). So no need
* to cache it separately and hence this is an empty routine.
*/
-static void sctp_v4_get_saddr(struct sctp_association *asoc,
+static void sctp_v4_get_saddr(struct sctp_sock *sk,
+ struct sctp_association *asoc,
struct dst_entry *dst,
union sctp_addr *daddr,
union sctp_addr *saddr)
@@ -619,6 +620,11 @@ static void sctp_v4_seq_dump_addr(struct seq_file *seq, union sctp_addr *addr)
seq_printf(seq, "%d.%d.%d.%d ", NIPQUAD(addr->v4.sin_addr));
}
+static void sctp_v4_ecn_capable(struct sock *sk)
+{
+ INET_ECN_xmit(sk);
+}
+
/* Event handler for inet address addition/deletion events.
* The sctp_local_addr_list needs to be protocted by a spin lock since
* multiple notifiers (say IPv4 and IPv6) may be running at the same
@@ -937,6 +943,7 @@ static struct sctp_af sctp_af_inet = {
.skb_iif = sctp_v4_skb_iif,
.is_ce = sctp_v4_is_ce,
.seq_dump_addr = sctp_v4_seq_dump_addr,
+ .ecn_capable = sctp_v4_ecn_capable,
.net_header_len = sizeof(struct iphdr),
.sockaddr_len = sizeof(struct sockaddr_in),
#ifdef CONFIG_COMPAT
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index f4938f6c5abe..3f34f61221ec 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -79,6 +79,7 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer,
peer->rttvar = 0;
peer->srtt = 0;
peer->rto_pending = 0;
+ peer->fast_recovery = 0;
peer->last_time_heard = jiffies;
peer->last_time_used = jiffies;
@@ -190,7 +191,7 @@ static void sctp_transport_destroy(struct sctp_transport *transport)
/* Start T3_rtx timer if it is not already running and update the heartbeat
* timer. This routine is called every time a DATA chunk is sent.
*/
-void sctp_transport_reset_timers(struct sctp_transport *transport)
+void sctp_transport_reset_timers(struct sctp_transport *transport, int force)
{
/* RFC 2960 6.3.2 Retransmission Timer Rules
*
@@ -200,7 +201,7 @@ void sctp_transport_reset_timers(struct sctp_transport *transport)
* address.
*/
- if (!timer_pending(&transport->T3_rtx_timer))
+ if (force || !timer_pending(&transport->T3_rtx_timer))
if (!mod_timer(&transport->T3_rtx_timer,
jiffies + transport->rto))
sctp_transport_hold(transport);
@@ -291,7 +292,7 @@ void sctp_transport_route(struct sctp_transport *transport,
if (saddr)
memcpy(&transport->saddr, saddr, sizeof(union sctp_addr));
else
- af->get_saddr(asoc, dst, daddr, &transport->saddr);
+ af->get_saddr(opt, asoc, dst, daddr, &transport->saddr);
transport->dst = dst;
if ((transport->param_flags & SPP_PMTUD_DISABLE) && transport->pathmtu) {
@@ -403,11 +404,16 @@ void sctp_transport_raise_cwnd(struct sctp_transport *transport,
cwnd = transport->cwnd;
flight_size = transport->flight_size;
+ /* See if we need to exit Fast Recovery first */
+ if (transport->fast_recovery &&
+ TSN_lte(transport->fast_recovery_exit, sack_ctsn))
+ transport->fast_recovery = 0;
+
/* The appropriate cwnd increase algorithm is performed if, and only
- * if the cumulative TSN has advanced and the congestion window is
+ * if the cumulative TSN whould advanced and the congestion window is
* being fully utilized.
*/
- if ((transport->asoc->ctsn_ack_point >= sack_ctsn) ||
+ if (TSN_lte(sack_ctsn, transport->asoc->ctsn_ack_point) ||
(flight_size < cwnd))
return;
@@ -416,17 +422,23 @@ void sctp_transport_raise_cwnd(struct sctp_transport *transport,
pmtu = transport->asoc->pathmtu;
if (cwnd <= ssthresh) {
- /* RFC 2960 7.2.1, sctpimpguide-05 2.14.2 When cwnd is less
- * than or equal to ssthresh an SCTP endpoint MUST use the
- * slow start algorithm to increase cwnd only if the current
- * congestion window is being fully utilized and an incoming
- * SACK advances the Cumulative TSN Ack Point. Only when these
- * two conditions are met can the cwnd be increased otherwise
- * the cwnd MUST not be increased. If these conditions are met
- * then cwnd MUST be increased by at most the lesser of
- * 1) the total size of the previously outstanding DATA
- * chunk(s) acknowledged, and 2) the destination's path MTU.
+ /* RFC 4960 7.2.1
+ * o When cwnd is less than or equal to ssthresh, an SCTP
+ * endpoint MUST use the slow-start algorithm to increase
+ * cwnd only if the current congestion window is being fully
+ * utilized, an incoming SACK advances the Cumulative TSN
+ * Ack Point, and the data sender is not in Fast Recovery.
+ * Only when these three conditions are met can the cwnd be
+ * increased; otherwise, the cwnd MUST not be increased.
+ * If these conditions are met, then cwnd MUST be increased
+ * by, at most, the lesser of 1) the total size of the
+ * previously outstanding DATA chunk(s) acknowledged, and
+ * 2) the destination's path MTU. This upper bound protects
+ * against the ACK-Splitting attack outlined in [SAVAGE99].
*/
+ if (transport->fast_recovery)
+ return;
+
if (bytes_acked > pmtu)
cwnd += pmtu;
else
@@ -502,6 +514,13 @@ void sctp_transport_lower_cwnd(struct sctp_transport *transport,
* cwnd = ssthresh
* partial_bytes_acked = 0
*/
+ if (transport->fast_recovery)
+ return;
+
+ /* Mark Fast recovery */
+ transport->fast_recovery = 1;
+ transport->fast_recovery_exit = transport->asoc->next_tsn - 1;
+
transport->ssthresh = max(transport->cwnd/2,
4*transport->asoc->pathmtu);
transport->cwnd = transport->ssthresh;
@@ -586,6 +605,7 @@ void sctp_transport_reset(struct sctp_transport *t)
t->flight_size = 0;
t->error_count = 0;
t->rto_pending = 0;
+ t->fast_recovery = 0;
/* Initialize the state information for SFR-CACC */
t->cacc.changeover_active = 0;
diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c
index d927d9f57412..744b79fdcb19 100644
--- a/net/sunrpc/auth_generic.c
+++ b/net/sunrpc/auth_generic.c
@@ -17,8 +17,8 @@
# define RPCDBG_FACILITY RPCDBG_AUTH
#endif
-#define RPC_ANONYMOUS_USERID ((uid_t)-2)
-#define RPC_ANONYMOUS_GROUPID ((gid_t)-2)
+#define RPC_MACHINE_CRED_USERID ((uid_t)0)
+#define RPC_MACHINE_CRED_GROUPID ((gid_t)0)
struct generic_cred {
struct rpc_cred gc_base;
@@ -44,8 +44,8 @@ EXPORT_SYMBOL_GPL(rpc_lookup_cred);
struct rpc_cred *rpc_lookup_machine_cred(void)
{
struct auth_cred acred = {
- .uid = RPC_ANONYMOUS_USERID,
- .gid = RPC_ANONYMOUS_GROUPID,
+ .uid = RPC_MACHINE_CRED_USERID,
+ .gid = RPC_MACHINE_CRED_GROUPID,
.machine_cred = 1,
};
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index d8e8d79a8451..e46c825f4954 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -6,30 +6,9 @@
#include <linux/sched.h>
#include <linux/errno.h>
-#include <linux/fcntl.h>
-#include <linux/net.h>
-#include <linux/in.h>
-#include <linux/inet.h>
-#include <linux/udp.h>
-#include <linux/tcp.h>
-#include <linux/unistd.h>
-#include <linux/slab.h>
-#include <linux/netdevice.h>
-#include <linux/skbuff.h>
-#include <linux/file.h>
#include <linux/freezer.h>
#include <linux/kthread.h>
#include <net/sock.h>
-#include <net/checksum.h>
-#include <net/ip.h>
-#include <net/ipv6.h>
-#include <net/tcp_states.h>
-#include <linux/uaccess.h>
-#include <asm/ioctls.h>
-
-#include <linux/sunrpc/types.h>
-#include <linux/sunrpc/clnt.h>
-#include <linux/sunrpc/xdr.h>
#include <linux/sunrpc/stats.h>
#include <linux/sunrpc/svc_xprt.h>
@@ -296,8 +275,6 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
if (!(xprt->xpt_flags &
((1<<XPT_CONN)|(1<<XPT_DATA)|(1<<XPT_CLOSE)|(1<<XPT_DEFERRED))))
return;
- if (test_bit(XPT_DEAD, &xprt->xpt_flags))
- return;
cpu = get_cpu();
pool = svc_pool_for_cpu(xprt->xpt_server, cpu);
diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c
index 3f30ee6006ae..f24800f2c098 100644
--- a/net/sunrpc/svcauth_unix.c
+++ b/net/sunrpc/svcauth_unix.c
@@ -278,7 +278,7 @@ static int ip_map_show(struct seq_file *m,
dom = im->m_client->h.name;
if (ipv6_addr_v4mapped(&addr)) {
- seq_printf(m, "%s" NIPQUAD_FMT "%s\n",
+ seq_printf(m, "%s " NIPQUAD_FMT " %s\n",
im->m_class,
ntohl(addr.s6_addr32[3]) >> 24 & 0xff,
ntohl(addr.s6_addr32[3]) >> 16 & 0xff,
@@ -286,7 +286,7 @@ static int ip_map_show(struct seq_file *m,
ntohl(addr.s6_addr32[3]) >> 0 & 0xff,
dom);
} else {
- seq_printf(m, "%s" NIP6_FMT "%s\n",
+ seq_printf(m, "%s " NIP6_FMT " %s\n",
im->m_class, NIP6(addr), dom);
}
return 0;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index c22d6b6f2db4..06ab4841537b 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -260,11 +260,16 @@ static int rdma_read_max_sge(struct svcxprt_rdma *xprt, int sge_count)
* On our side, we need to read into a pagelist. The first page immediately
* follows the RPC header.
*
- * This function returns 1 to indicate success. The data is not yet in
+ * This function returns:
+ * 0 - No error and no read-list found.
+ *
+ * 1 - Successful read-list processing. The data is not yet in
* the pagelist and therefore the RPC request must be deferred. The
* I/O completion will enqueue the transport again and
* svc_rdma_recvfrom will complete the request.
*
+ * <0 - Error processing/posting read-list.
+ *
* NOTE: The ctxt must not be touched after the last WR has been posted
* because the I/O completion processing may occur on another
* processor and free / modify the context. Ne touche pas!
@@ -284,7 +289,6 @@ static int rdma_read_xdr(struct svcxprt_rdma *xprt,
u64 sgl_offset;
struct rpcrdma_read_chunk *ch;
struct svc_rdma_op_ctxt *ctxt = NULL;
- struct svc_rdma_op_ctxt *head;
struct svc_rdma_op_ctxt *tmp_sge_ctxt;
struct svc_rdma_op_ctxt *tmp_ch_ctxt;
struct chunk_sge *ch_sge_ary;
@@ -302,25 +306,19 @@ static int rdma_read_xdr(struct svcxprt_rdma *xprt,
ch_sge_ary = (struct chunk_sge *)tmp_ch_ctxt->sge;
svc_rdma_rcl_chunk_counts(ch, &ch_count, &byte_count);
+ if (ch_count > RPCSVC_MAXPAGES)
+ return -EINVAL;
sge_count = rdma_rcl_to_sge(xprt, rqstp, hdr_ctxt, rmsgp,
sge, ch_sge_ary,
ch_count, byte_count);
- head = svc_rdma_get_context(xprt);
sgl_offset = 0;
ch_no = 0;
for (ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
ch->rc_discrim != 0; ch++, ch_no++) {
next_sge:
- if (!ctxt)
- ctxt = head;
- else {
- ctxt->next = svc_rdma_get_context(xprt);
- ctxt = ctxt->next;
- }
- ctxt->next = NULL;
+ ctxt = svc_rdma_get_context(xprt);
ctxt->direction = DMA_FROM_DEVICE;
- clear_bit(RDMACTXT_F_READ_DONE, &ctxt->flags);
clear_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
/* Prepare READ WR */
@@ -347,20 +345,15 @@ next_sge:
* the client and the RPC needs to be enqueued.
*/
set_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
- ctxt->next = hdr_ctxt;
- hdr_ctxt->next = head;
+ ctxt->read_hdr = hdr_ctxt;
}
/* Post the read */
err = svc_rdma_send(xprt, &read_wr);
if (err) {
- printk(KERN_ERR "svcrdma: Error posting send = %d\n",
+ printk(KERN_ERR "svcrdma: Error %d posting RDMA_READ\n",
err);
- /*
- * Break the circular list so free knows when
- * to stop if the error happened to occur on
- * the last read
- */
- ctxt->next = NULL;
+ set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
+ svc_rdma_put_context(ctxt, 0);
goto out;
}
atomic_inc(&rdma_stat_read);
@@ -371,7 +364,7 @@ next_sge:
goto next_sge;
}
sgl_offset = 0;
- err = 0;
+ err = 1;
}
out:
@@ -389,25 +382,12 @@ next_sge:
while (rqstp->rq_resused)
rqstp->rq_respages[--rqstp->rq_resused] = NULL;
- if (err) {
- printk(KERN_ERR "svcrdma : RDMA_READ error = %d\n", err);
- set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
- /* Free the linked list of read contexts */
- while (head != NULL) {
- ctxt = head->next;
- svc_rdma_put_context(head, 1);
- head = ctxt;
- }
- return 0;
- }
-
- return 1;
+ return err;
}
static int rdma_read_complete(struct svc_rqst *rqstp,
- struct svc_rdma_op_ctxt *data)
+ struct svc_rdma_op_ctxt *head)
{
- struct svc_rdma_op_ctxt *head = data->next;
int page_no;
int ret;
@@ -433,21 +413,12 @@ static int rdma_read_complete(struct svc_rqst *rqstp,
rqstp->rq_arg.len = head->arg.len;
rqstp->rq_arg.buflen = head->arg.buflen;
+ /* Free the context */
+ svc_rdma_put_context(head, 0);
+
/* XXX: What should this be? */
rqstp->rq_prot = IPPROTO_MAX;
-
- /*
- * Free the contexts we used to build the RDMA_READ. We have
- * to be careful here because the context list uses the same
- * next pointer used to chain the contexts associated with the
- * RDMA_READ
- */
- data->next = NULL; /* terminate circular list */
- do {
- data = head->next;
- svc_rdma_put_context(head, 0);
- head = data;
- } while (head != NULL);
+ svc_xprt_copy_addrs(rqstp, rqstp->rq_xprt);
ret = rqstp->rq_arg.head[0].iov_len
+ rqstp->rq_arg.page_len
@@ -457,8 +428,6 @@ static int rdma_read_complete(struct svc_rqst *rqstp,
ret, rqstp->rq_arg.len, rqstp->rq_arg.head[0].iov_base,
rqstp->rq_arg.head[0].iov_len);
- /* Indicate that we've consumed an RQ credit */
- rqstp->rq_xprt_ctxt = rqstp->rq_xprt;
svc_xprt_received(rqstp->rq_xprt);
return ret;
}
@@ -480,13 +449,6 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
dprintk("svcrdma: rqstp=%p\n", rqstp);
- /*
- * The rq_xprt_ctxt indicates if we've consumed an RQ credit
- * or not. It is used in the rdma xpo_release_rqst function to
- * determine whether or not to return an RQ WQE to the RQ.
- */
- rqstp->rq_xprt_ctxt = NULL;
-
spin_lock_bh(&rdma_xprt->sc_read_complete_lock);
if (!list_empty(&rdma_xprt->sc_read_complete_q)) {
ctxt = list_entry(rdma_xprt->sc_read_complete_q.next,
@@ -537,21 +499,22 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
/* If the request is invalid, reply with an error */
if (len < 0) {
if (len == -ENOSYS)
- (void)svc_rdma_send_error(rdma_xprt, rmsgp, ERR_VERS);
+ svc_rdma_send_error(rdma_xprt, rmsgp, ERR_VERS);
goto close_out;
}
- /* Read read-list data. If we would need to wait, defer
- * it. Not that in this case, we don't return the RQ credit
- * until after the read completes.
- */
- if (rdma_read_xdr(rdma_xprt, rmsgp, rqstp, ctxt)) {
+ /* Read read-list data. */
+ ret = rdma_read_xdr(rdma_xprt, rmsgp, rqstp, ctxt);
+ if (ret > 0) {
+ /* read-list posted, defer until data received from client. */
svc_xprt_received(xprt);
return 0;
}
-
- /* Indicate we've consumed an RQ credit */
- rqstp->rq_xprt_ctxt = rqstp->rq_xprt;
+ if (ret < 0) {
+ /* Post of read-list failed, free context. */
+ svc_rdma_put_context(ctxt, 1);
+ return 0;
+ }
ret = rqstp->rq_arg.head[0].iov_len
+ rqstp->rq_arg.page_len
@@ -569,11 +532,8 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
return ret;
close_out:
- if (ctxt) {
+ if (ctxt)
svc_rdma_put_context(ctxt, 1);
- /* Indicate we've consumed an RQ credit */
- rqstp->rq_xprt_ctxt = rqstp->rq_xprt;
- }
dprintk("svcrdma: transport %p is closing\n", xprt);
/*
* Set the close bit and enqueue it. svc_recv will see the
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 981f190c1b39..fb82b1b683f8 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -389,6 +389,17 @@ static int send_reply(struct svcxprt_rdma *rdma,
int page_no;
int ret;
+ /* Post a recv buffer to handle another request. */
+ ret = svc_rdma_post_recv(rdma);
+ if (ret) {
+ printk(KERN_INFO
+ "svcrdma: could not post a receive buffer, err=%d."
+ "Closing transport %p.\n", ret, rdma);
+ set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags);
+ svc_rdma_put_context(ctxt, 0);
+ return -ENOTCONN;
+ }
+
/* Prepare the context */
ctxt->pages[0] = page;
ctxt->count = 1;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index af408fc12634..e132509d1db0 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -103,8 +103,8 @@ static int rdma_bump_context_cache(struct svcxprt_rdma *xprt)
spin_lock_bh(&xprt->sc_ctxt_lock);
if (ctxt) {
at_least_one = 1;
- ctxt->next = xprt->sc_ctxt_head;
- xprt->sc_ctxt_head = ctxt;
+ INIT_LIST_HEAD(&ctxt->free_list);
+ list_add(&ctxt->free_list, &xprt->sc_ctxt_free);
} else {
/* kmalloc failed...give up for now */
xprt->sc_ctxt_cnt--;
@@ -123,7 +123,7 @@ struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt)
while (1) {
spin_lock_bh(&xprt->sc_ctxt_lock);
- if (unlikely(xprt->sc_ctxt_head == NULL)) {
+ if (unlikely(list_empty(&xprt->sc_ctxt_free))) {
/* Try to bump my cache. */
spin_unlock_bh(&xprt->sc_ctxt_lock);
@@ -136,12 +136,15 @@ struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt)
schedule_timeout_uninterruptible(msecs_to_jiffies(500));
continue;
}
- ctxt = xprt->sc_ctxt_head;
- xprt->sc_ctxt_head = ctxt->next;
+ ctxt = list_entry(xprt->sc_ctxt_free.next,
+ struct svc_rdma_op_ctxt,
+ free_list);
+ list_del_init(&ctxt->free_list);
spin_unlock_bh(&xprt->sc_ctxt_lock);
ctxt->xprt = xprt;
INIT_LIST_HEAD(&ctxt->dto_q);
ctxt->count = 0;
+ atomic_inc(&xprt->sc_ctxt_used);
break;
}
return ctxt;
@@ -159,14 +162,15 @@ void svc_rdma_put_context(struct svc_rdma_op_ctxt *ctxt, int free_pages)
put_page(ctxt->pages[i]);
for (i = 0; i < ctxt->count; i++)
- dma_unmap_single(xprt->sc_cm_id->device->dma_device,
- ctxt->sge[i].addr,
- ctxt->sge[i].length,
- ctxt->direction);
+ ib_dma_unmap_single(xprt->sc_cm_id->device,
+ ctxt->sge[i].addr,
+ ctxt->sge[i].length,
+ ctxt->direction);
+
spin_lock_bh(&xprt->sc_ctxt_lock);
- ctxt->next = xprt->sc_ctxt_head;
- xprt->sc_ctxt_head = ctxt;
+ list_add(&ctxt->free_list, &xprt->sc_ctxt_free);
spin_unlock_bh(&xprt->sc_ctxt_lock);
+ atomic_dec(&xprt->sc_ctxt_used);
}
/* ib_cq event handler */
@@ -228,23 +232,8 @@ static void dto_tasklet_func(unsigned long data)
list_del_init(&xprt->sc_dto_q);
spin_unlock_irqrestore(&dto_lock, flags);
- if (test_and_clear_bit(RDMAXPRT_RQ_PENDING, &xprt->sc_flags)) {
- ib_req_notify_cq(xprt->sc_rq_cq, IB_CQ_NEXT_COMP);
- rq_cq_reap(xprt);
- set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags);
- /*
- * If data arrived before established event,
- * don't enqueue. This defers RPC I/O until the
- * RDMA connection is complete.
- */
- if (!test_bit(RDMAXPRT_CONN_PENDING, &xprt->sc_flags))
- svc_xprt_enqueue(&xprt->sc_xprt);
- }
-
- if (test_and_clear_bit(RDMAXPRT_SQ_PENDING, &xprt->sc_flags)) {
- ib_req_notify_cq(xprt->sc_sq_cq, IB_CQ_NEXT_COMP);
- sq_cq_reap(xprt);
- }
+ rq_cq_reap(xprt);
+ sq_cq_reap(xprt);
svc_xprt_put(&xprt->sc_xprt);
spin_lock_irqsave(&dto_lock, flags);
@@ -263,11 +252,15 @@ static void rq_comp_handler(struct ib_cq *cq, void *cq_context)
struct svcxprt_rdma *xprt = cq_context;
unsigned long flags;
+ /* Guard against unconditional flush call for destroyed QP */
+ if (atomic_read(&xprt->sc_xprt.xpt_ref.refcount)==0)
+ return;
+
/*
* Set the bit regardless of whether or not it's on the list
* because it may be on the list already due to an SQ
* completion.
- */
+ */
set_bit(RDMAXPRT_RQ_PENDING, &xprt->sc_flags);
/*
@@ -290,6 +283,8 @@ static void rq_comp_handler(struct ib_cq *cq, void *cq_context)
*
* Take all completing WC off the CQE and enqueue the associated DTO
* context on the dto_q for the transport.
+ *
+ * Note that caller must hold a transport reference.
*/
static void rq_cq_reap(struct svcxprt_rdma *xprt)
{
@@ -297,29 +292,47 @@ static void rq_cq_reap(struct svcxprt_rdma *xprt)
struct ib_wc wc;
struct svc_rdma_op_ctxt *ctxt = NULL;
+ if (!test_and_clear_bit(RDMAXPRT_RQ_PENDING, &xprt->sc_flags))
+ return;
+
+ ib_req_notify_cq(xprt->sc_rq_cq, IB_CQ_NEXT_COMP);
atomic_inc(&rdma_stat_rq_poll);
- spin_lock_bh(&xprt->sc_rq_dto_lock);
while ((ret = ib_poll_cq(xprt->sc_rq_cq, 1, &wc)) > 0) {
ctxt = (struct svc_rdma_op_ctxt *)(unsigned long)wc.wr_id;
ctxt->wc_status = wc.status;
ctxt->byte_len = wc.byte_len;
if (wc.status != IB_WC_SUCCESS) {
/* Close the transport */
+ dprintk("svcrdma: transport closing putting ctxt %p\n", ctxt);
set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
svc_rdma_put_context(ctxt, 1);
+ svc_xprt_put(&xprt->sc_xprt);
continue;
}
+ spin_lock_bh(&xprt->sc_rq_dto_lock);
list_add_tail(&ctxt->dto_q, &xprt->sc_rq_dto_q);
+ spin_unlock_bh(&xprt->sc_rq_dto_lock);
+ svc_xprt_put(&xprt->sc_xprt);
}
- spin_unlock_bh(&xprt->sc_rq_dto_lock);
if (ctxt)
atomic_inc(&rdma_stat_rq_prod);
+
+ set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags);
+ /*
+ * If data arrived before established event,
+ * don't enqueue. This defers RPC I/O until the
+ * RDMA connection is complete.
+ */
+ if (!test_bit(RDMAXPRT_CONN_PENDING, &xprt->sc_flags))
+ svc_xprt_enqueue(&xprt->sc_xprt);
}
/*
* Send Queue Completion Handler - potentially called on interrupt context.
+ *
+ * Note that caller must hold a transport reference.
*/
static void sq_cq_reap(struct svcxprt_rdma *xprt)
{
@@ -328,6 +341,11 @@ static void sq_cq_reap(struct svcxprt_rdma *xprt)
struct ib_cq *cq = xprt->sc_sq_cq;
int ret;
+
+ if (!test_and_clear_bit(RDMAXPRT_SQ_PENDING, &xprt->sc_flags))
+ return;
+
+ ib_req_notify_cq(xprt->sc_sq_cq, IB_CQ_NEXT_COMP);
atomic_inc(&rdma_stat_sq_poll);
while ((ret = ib_poll_cq(cq, 1, &wc)) > 0) {
ctxt = (struct svc_rdma_op_ctxt *)(unsigned long)wc.wr_id;
@@ -349,14 +367,16 @@ static void sq_cq_reap(struct svcxprt_rdma *xprt)
case IB_WR_RDMA_READ:
if (test_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags)) {
+ struct svc_rdma_op_ctxt *read_hdr = ctxt->read_hdr;
+ BUG_ON(!read_hdr);
set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags);
- set_bit(RDMACTXT_F_READ_DONE, &ctxt->flags);
spin_lock_bh(&xprt->sc_read_complete_lock);
- list_add_tail(&ctxt->dto_q,
+ list_add_tail(&read_hdr->dto_q,
&xprt->sc_read_complete_q);
spin_unlock_bh(&xprt->sc_read_complete_lock);
svc_xprt_enqueue(&xprt->sc_xprt);
}
+ svc_rdma_put_context(ctxt, 0);
break;
default:
@@ -365,6 +385,7 @@ static void sq_cq_reap(struct svcxprt_rdma *xprt)
wc.opcode, wc.status);
break;
}
+ svc_xprt_put(&xprt->sc_xprt);
}
if (ctxt)
@@ -376,11 +397,15 @@ static void sq_comp_handler(struct ib_cq *cq, void *cq_context)
struct svcxprt_rdma *xprt = cq_context;
unsigned long flags;
+ /* Guard against unconditional flush call for destroyed QP */
+ if (atomic_read(&xprt->sc_xprt.xpt_ref.refcount)==0)
+ return;
+
/*
* Set the bit regardless of whether or not it's on the list
* because it may be on the list already due to an RQ
* completion.
- */
+ */
set_bit(RDMAXPRT_SQ_PENDING, &xprt->sc_flags);
/*
@@ -407,28 +432,29 @@ static void create_context_cache(struct svcxprt_rdma *xprt,
xprt->sc_ctxt_max = ctxt_max;
xprt->sc_ctxt_bump = ctxt_bump;
xprt->sc_ctxt_cnt = 0;
- xprt->sc_ctxt_head = NULL;
+ atomic_set(&xprt->sc_ctxt_used, 0);
+
+ INIT_LIST_HEAD(&xprt->sc_ctxt_free);
for (i = 0; i < ctxt_count; i++) {
ctxt = kmalloc(sizeof(*ctxt), GFP_KERNEL);
if (ctxt) {
- ctxt->next = xprt->sc_ctxt_head;
- xprt->sc_ctxt_head = ctxt;
+ INIT_LIST_HEAD(&ctxt->free_list);
+ list_add(&ctxt->free_list, &xprt->sc_ctxt_free);
xprt->sc_ctxt_cnt++;
}
}
}
-static void destroy_context_cache(struct svc_rdma_op_ctxt *ctxt)
+static void destroy_context_cache(struct svcxprt_rdma *xprt)
{
- struct svc_rdma_op_ctxt *next;
- if (!ctxt)
- return;
-
- do {
- next = ctxt->next;
+ while (!list_empty(&xprt->sc_ctxt_free)) {
+ struct svc_rdma_op_ctxt *ctxt;
+ ctxt = list_entry(xprt->sc_ctxt_free.next,
+ struct svc_rdma_op_ctxt,
+ free_list);
+ list_del_init(&ctxt->free_list);
kfree(ctxt);
- ctxt = next;
- } while (next);
+ }
}
static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv,
@@ -465,7 +491,7 @@ static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv,
reqs +
cma_xprt->sc_sq_depth +
RPCRDMA_MAX_THREADS + 1); /* max */
- if (!cma_xprt->sc_ctxt_head) {
+ if (list_empty(&cma_xprt->sc_ctxt_free)) {
kfree(cma_xprt);
return NULL;
}
@@ -520,7 +546,12 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt)
recv_wr.num_sge = ctxt->count;
recv_wr.wr_id = (u64)(unsigned long)ctxt;
+ svc_xprt_get(&xprt->sc_xprt);
ret = ib_post_recv(xprt->sc_qp, &recv_wr, &bad_recv_wr);
+ if (ret) {
+ svc_xprt_put(&xprt->sc_xprt);
+ svc_rdma_put_context(ctxt, 1);
+ }
return ret;
}
@@ -539,6 +570,7 @@ static void handle_connect_req(struct rdma_cm_id *new_cma_id)
{
struct svcxprt_rdma *listen_xprt = new_cma_id->context;
struct svcxprt_rdma *newxprt;
+ struct sockaddr *sa;
/* Create a new transport */
newxprt = rdma_create_xprt(listen_xprt->sc_xprt.xpt_server, 0);
@@ -551,6 +583,12 @@ static void handle_connect_req(struct rdma_cm_id *new_cma_id)
dprintk("svcrdma: Creating newxprt=%p, cm_id=%p, listenxprt=%p\n",
newxprt, newxprt->sc_cm_id, listen_xprt);
+ /* Set the local and remote addresses in the transport */
+ sa = (struct sockaddr *)&newxprt->sc_cm_id->route.addr.dst_addr;
+ svc_xprt_set_remote(&newxprt->sc_xprt, sa, svc_addr_len(sa));
+ sa = (struct sockaddr *)&newxprt->sc_cm_id->route.addr.src_addr;
+ svc_xprt_set_local(&newxprt->sc_xprt, sa, svc_addr_len(sa));
+
/*
* Enqueue the new transport on the accept queue of the listening
* transport
@@ -627,6 +665,7 @@ static int rdma_cma_handler(struct rdma_cm_id *cma_id,
if (xprt) {
set_bit(XPT_CLOSE, &xprt->xpt_flags);
svc_xprt_enqueue(xprt);
+ svc_xprt_put(xprt);
}
break;
case RDMA_CM_EVENT_DEVICE_REMOVAL:
@@ -661,31 +700,27 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
cma_xprt = rdma_create_xprt(serv, 1);
if (!cma_xprt)
- return ERR_PTR(ENOMEM);
+ return ERR_PTR(-ENOMEM);
xprt = &cma_xprt->sc_xprt;
listen_id = rdma_create_id(rdma_listen_handler, cma_xprt, RDMA_PS_TCP);
if (IS_ERR(listen_id)) {
- svc_xprt_put(&cma_xprt->sc_xprt);
- dprintk("svcrdma: rdma_create_id failed = %ld\n",
- PTR_ERR(listen_id));
- return (void *)listen_id;
+ ret = PTR_ERR(listen_id);
+ dprintk("svcrdma: rdma_create_id failed = %d\n", ret);
+ goto err0;
}
+
ret = rdma_bind_addr(listen_id, sa);
if (ret) {
- rdma_destroy_id(listen_id);
- svc_xprt_put(&cma_xprt->sc_xprt);
dprintk("svcrdma: rdma_bind_addr failed = %d\n", ret);
- return ERR_PTR(ret);
+ goto err1;
}
cma_xprt->sc_cm_id = listen_id;
ret = rdma_listen(listen_id, RPCRDMA_LISTEN_BACKLOG);
if (ret) {
- rdma_destroy_id(listen_id);
- svc_xprt_put(&cma_xprt->sc_xprt);
dprintk("svcrdma: rdma_listen failed = %d\n", ret);
- return ERR_PTR(ret);
+ goto err1;
}
/*
@@ -696,6 +731,12 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
svc_xprt_set_local(&cma_xprt->sc_xprt, sa, salen);
return &cma_xprt->sc_xprt;
+
+ err1:
+ rdma_destroy_id(listen_id);
+ err0:
+ kfree(cma_xprt);
+ return ERR_PTR(ret);
}
/*
@@ -716,7 +757,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
struct rdma_conn_param conn_param;
struct ib_qp_init_attr qp_attr;
struct ib_device_attr devattr;
- struct sockaddr *sa;
int ret;
int i;
@@ -826,7 +866,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
newxprt->sc_sq_depth = qp_attr.cap.max_send_wr;
newxprt->sc_max_requests = qp_attr.cap.max_recv_wr;
}
- svc_xprt_get(&newxprt->sc_xprt);
newxprt->sc_qp = newxprt->sc_cm_id->qp;
/* Register all of physical memory */
@@ -850,6 +889,13 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
/* Swap out the handler */
newxprt->sc_cm_id->event_handler = rdma_cma_handler;
+ /*
+ * Arm the CQs for the SQ and RQ before accepting so we can't
+ * miss the first message
+ */
+ ib_req_notify_cq(newxprt->sc_sq_cq, IB_CQ_NEXT_COMP);
+ ib_req_notify_cq(newxprt->sc_rq_cq, IB_CQ_NEXT_COMP);
+
/* Accept Connection */
set_bit(RDMAXPRT_CONN_PENDING, &newxprt->sc_flags);
memset(&conn_param, 0, sizeof conn_param);
@@ -886,58 +932,26 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
newxprt->sc_max_requests,
newxprt->sc_ord);
- /* Set the local and remote addresses in the transport */
- sa = (struct sockaddr *)&newxprt->sc_cm_id->route.addr.dst_addr;
- svc_xprt_set_remote(&newxprt->sc_xprt, sa, svc_addr_len(sa));
- sa = (struct sockaddr *)&newxprt->sc_cm_id->route.addr.src_addr;
- svc_xprt_set_local(&newxprt->sc_xprt, sa, svc_addr_len(sa));
-
- ib_req_notify_cq(newxprt->sc_sq_cq, IB_CQ_NEXT_COMP);
- ib_req_notify_cq(newxprt->sc_rq_cq, IB_CQ_NEXT_COMP);
return &newxprt->sc_xprt;
errout:
dprintk("svcrdma: failure accepting new connection rc=%d.\n", ret);
/* Take a reference in case the DTO handler runs */
svc_xprt_get(&newxprt->sc_xprt);
- if (newxprt->sc_qp && !IS_ERR(newxprt->sc_qp)) {
+ if (newxprt->sc_qp && !IS_ERR(newxprt->sc_qp))
ib_destroy_qp(newxprt->sc_qp);
- svc_xprt_put(&newxprt->sc_xprt);
- }
rdma_destroy_id(newxprt->sc_cm_id);
/* This call to put will destroy the transport */
svc_xprt_put(&newxprt->sc_xprt);
return NULL;
}
-/*
- * Post an RQ WQE to the RQ when the rqst is being released. This
- * effectively returns an RQ credit to the client. The rq_xprt_ctxt
- * will be null if the request is deferred due to an RDMA_READ or the
- * transport had no data ready (EAGAIN). Note that an RPC deferred in
- * svc_process will still return the credit, this is because the data
- * is copied and no longer consume a WQE/WC.
- */
static void svc_rdma_release_rqst(struct svc_rqst *rqstp)
{
- int err;
- struct svcxprt_rdma *rdma =
- container_of(rqstp->rq_xprt, struct svcxprt_rdma, sc_xprt);
- if (rqstp->rq_xprt_ctxt) {
- BUG_ON(rqstp->rq_xprt_ctxt != rdma);
- err = svc_rdma_post_recv(rdma);
- if (err)
- dprintk("svcrdma: failed to post an RQ WQE error=%d\n",
- err);
- }
- rqstp->rq_xprt_ctxt = NULL;
}
/*
- * When connected, an svc_xprt has at least three references:
- *
- * - A reference held by the QP. We still hold that here because this
- * code deletes the QP and puts the reference.
+ * When connected, an svc_xprt has at least two references:
*
* - A reference held by the cm_id between the ESTABLISHED and
* DISCONNECTED events. If the remote peer disconnected first, this
@@ -946,7 +960,7 @@ static void svc_rdma_release_rqst(struct svc_rqst *rqstp)
* - A reference held by the svc_recv code that called this function
* as part of close processing.
*
- * At a minimum two references should still be held.
+ * At a minimum one references should still be held.
*/
static void svc_rdma_detach(struct svc_xprt *xprt)
{
@@ -956,23 +970,53 @@ static void svc_rdma_detach(struct svc_xprt *xprt)
/* Disconnect and flush posted WQE */
rdma_disconnect(rdma->sc_cm_id);
-
- /* Destroy the QP if present (not a listener) */
- if (rdma->sc_qp && !IS_ERR(rdma->sc_qp)) {
- ib_destroy_qp(rdma->sc_qp);
- svc_xprt_put(xprt);
- }
-
- /* Destroy the CM ID */
- rdma_destroy_id(rdma->sc_cm_id);
}
-static void svc_rdma_free(struct svc_xprt *xprt)
+static void __svc_rdma_free(struct work_struct *work)
{
- struct svcxprt_rdma *rdma = (struct svcxprt_rdma *)xprt;
+ struct svcxprt_rdma *rdma =
+ container_of(work, struct svcxprt_rdma, sc_work);
dprintk("svcrdma: svc_rdma_free(%p)\n", rdma);
+
/* We should only be called from kref_put */
- BUG_ON(atomic_read(&xprt->xpt_ref.refcount) != 0);
+ BUG_ON(atomic_read(&rdma->sc_xprt.xpt_ref.refcount) != 0);
+
+ /*
+ * Destroy queued, but not processed read completions. Note
+ * that this cleanup has to be done before destroying the
+ * cm_id because the device ptr is needed to unmap the dma in
+ * svc_rdma_put_context.
+ */
+ spin_lock_bh(&rdma->sc_read_complete_lock);
+ while (!list_empty(&rdma->sc_read_complete_q)) {
+ struct svc_rdma_op_ctxt *ctxt;
+ ctxt = list_entry(rdma->sc_read_complete_q.next,
+ struct svc_rdma_op_ctxt,
+ dto_q);
+ list_del_init(&ctxt->dto_q);
+ svc_rdma_put_context(ctxt, 1);
+ }
+ spin_unlock_bh(&rdma->sc_read_complete_lock);
+
+ /* Destroy queued, but not processed recv completions */
+ spin_lock_bh(&rdma->sc_rq_dto_lock);
+ while (!list_empty(&rdma->sc_rq_dto_q)) {
+ struct svc_rdma_op_ctxt *ctxt;
+ ctxt = list_entry(rdma->sc_rq_dto_q.next,
+ struct svc_rdma_op_ctxt,
+ dto_q);
+ list_del_init(&ctxt->dto_q);
+ svc_rdma_put_context(ctxt, 1);
+ }
+ spin_unlock_bh(&rdma->sc_rq_dto_lock);
+
+ /* Warn if we leaked a resource or under-referenced */
+ WARN_ON(atomic_read(&rdma->sc_ctxt_used) != 0);
+
+ /* Destroy the QP if present (not a listener) */
+ if (rdma->sc_qp && !IS_ERR(rdma->sc_qp))
+ ib_destroy_qp(rdma->sc_qp);
+
if (rdma->sc_sq_cq && !IS_ERR(rdma->sc_sq_cq))
ib_destroy_cq(rdma->sc_sq_cq);
@@ -985,10 +1029,21 @@ static void svc_rdma_free(struct svc_xprt *xprt)
if (rdma->sc_pd && !IS_ERR(rdma->sc_pd))
ib_dealloc_pd(rdma->sc_pd);
- destroy_context_cache(rdma->sc_ctxt_head);
+ /* Destroy the CM ID */
+ rdma_destroy_id(rdma->sc_cm_id);
+
+ destroy_context_cache(rdma);
kfree(rdma);
}
+static void svc_rdma_free(struct svc_xprt *xprt)
+{
+ struct svcxprt_rdma *rdma =
+ container_of(xprt, struct svcxprt_rdma, sc_xprt);
+ INIT_WORK(&rdma->sc_work, __svc_rdma_free);
+ schedule_work(&rdma->sc_work);
+}
+
static int svc_rdma_has_wspace(struct svc_xprt *xprt)
{
struct svcxprt_rdma *rdma =
@@ -1018,7 +1073,7 @@ int svc_rdma_send(struct svcxprt_rdma *xprt, struct ib_send_wr *wr)
int ret;
if (test_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags))
- return 0;
+ return -ENOTCONN;
BUG_ON(wr->send_flags != IB_SEND_SIGNALED);
BUG_ON(((struct svc_rdma_op_ctxt *)(unsigned long)wr->wr_id)->wr_op !=
@@ -1029,7 +1084,8 @@ int svc_rdma_send(struct svcxprt_rdma *xprt, struct ib_send_wr *wr)
if (xprt->sc_sq_depth == atomic_read(&xprt->sc_sq_count)) {
spin_unlock_bh(&xprt->sc_lock);
atomic_inc(&rdma_stat_sq_starve);
- /* See if we can reap some SQ WR */
+
+ /* See if we can opportunistically reap SQ WR to make room */
sq_cq_reap(xprt);
/* Wait until SQ WR available if SQ still full */
@@ -1041,22 +1097,25 @@ int svc_rdma_send(struct svcxprt_rdma *xprt, struct ib_send_wr *wr)
continue;
}
/* Bumped used SQ WR count and post */
+ svc_xprt_get(&xprt->sc_xprt);
ret = ib_post_send(xprt->sc_qp, wr, &bad_wr);
if (!ret)
atomic_inc(&xprt->sc_sq_count);
- else
+ else {
+ svc_xprt_put(&xprt->sc_xprt);
dprintk("svcrdma: failed to post SQ WR rc=%d, "
"sc_sq_count=%d, sc_sq_depth=%d\n",
ret, atomic_read(&xprt->sc_sq_count),
xprt->sc_sq_depth);
+ }
spin_unlock_bh(&xprt->sc_lock);
break;
}
return ret;
}
-int svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp,
- enum rpcrdma_errcode err)
+void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp,
+ enum rpcrdma_errcode err)
{
struct ib_send_wr err_wr;
struct ib_sge sge;
@@ -1094,9 +1153,8 @@ int svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp,
/* Post It */
ret = svc_rdma_send(xprt, &err_wr);
if (ret) {
- dprintk("svcrdma: Error posting send = %d\n", ret);
+ dprintk("svcrdma: Error %d posting send for protocol error\n",
+ ret);
svc_rdma_put_context(ctxt, 1);
}
-
- return ret;
}
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 2bdd4dddc0e1..fb75f265b39c 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -187,7 +187,8 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags,
return genlmsg_end(msg, hdr);
nla_put_failure:
- return genlmsg_cancel(msg, hdr);
+ genlmsg_cancel(msg, hdr);
+ return -EMSGSIZE;
}
static int nl80211_dump_wiphy(struct sk_buff *skb, struct netlink_callback *cb)
@@ -273,7 +274,8 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 pid, u32 seq, int flags,
return genlmsg_end(msg, hdr);
nla_put_failure:
- return genlmsg_cancel(msg, hdr);
+ genlmsg_cancel(msg, hdr);
+ return -EMSGSIZE;
}
static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback *cb)
@@ -928,7 +930,8 @@ static int nl80211_send_station(struct sk_buff *msg, u32 pid, u32 seq,
return genlmsg_end(msg, hdr);
nla_put_failure:
- return genlmsg_cancel(msg, hdr);
+ genlmsg_cancel(msg, hdr);
+ return -EMSGSIZE;
}
static int nl80211_dump_station(struct sk_buff *skb,
@@ -1267,7 +1270,8 @@ static int nl80211_send_mpath(struct sk_buff *msg, u32 pid, u32 seq,
return genlmsg_end(msg, hdr);
nla_put_failure:
- return genlmsg_cancel(msg, hdr);
+ genlmsg_cancel(msg, hdr);
+ return -EMSGSIZE;
}
static int nl80211_dump_mpath(struct sk_buff *skb,
diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c
index ac765dd9c7f5..23a2cc04b8cd 100644
--- a/net/xfrm/xfrm_algo.c
+++ b/net/xfrm/xfrm_algo.c
@@ -200,8 +200,8 @@ static struct xfrm_algo_desc aalg_list[] = {
}
},
{
- .name = "hmac(ripemd160)",
- .compat = "ripemd160",
+ .name = "hmac(rmd160)",
+ .compat = "rmd160",
.uinfo = {
.auth = {