summary refs log tree commit diff
path: root/net
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2010-10-29 14:17:12 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2010-10-29 14:17:12 -0700
commit1840897ab5d39b2e510c610ee262ded79919e718 (patch)
tree0b7fe95e3eda357d35b0d017f2b678b652307827 /net
parentd56f84e7e317c69adefb2454a3d538a6d7e11e4b (diff)
parenta4765fa7bfb92d5b9de19a503674b6624f95a7ae (diff)
downloadlinux-1840897ab5d39b2e510c610ee262ded79919e718.tar.gz
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (34 commits)
  b43: Fix warning at drivers/mmc/core/core.c:237 in mmc_wait_for_cmd
  mac80211: fix failure to check kmalloc return value in key_key_read
  libertas: Fix sd8686 firmware reload
  ath9k: Fix incorrect access of rate flags in RC
  netfilter: xt_socket: Make tproto signed in socket_mt6_v1().
  stmmac: enable/disable rx/tx in the core with a single write.
  net: atarilance - flags should be unsigned long
  netxen: fix kdump
  pktgen: Limit how much data we copy onto the stack.
  net: Limit socket I/O iovec total length to INT_MAX.
  USB: gadget: fix ethernet gadget crash in gether_setup
  fib: Fix fib zone and its hash leak on namespace stop
  cxgb3: Fix panic in free_tx_desc()
  cxgb3: fix crash due to manipulating queues before registration
  8390: Don't oops on starting dev queue
  dccp ccid-2: Stop polling
  dccp: Refine the wait-for-ccid mechanism
  dccp: Extend CCID packet dequeueing interface
  dccp: Return-value convention of hc_tx_send_packet()
  igbvf: fix panic on load
  ...
Diffstat (limited to 'net')
-rw-r--r--net/compat.c10
-rw-r--r--net/core/iovec.c20
-rw-r--r--net/core/pktgen.c7
-rw-r--r--net/dccp/ccid.h34
-rw-r--r--net/dccp/ccids/ccid2.c23
-rw-r--r--net/dccp/ccids/ccid2.h5
-rw-r--r--net/dccp/ccids/ccid3.c12
-rw-r--r--net/dccp/dccp.h5
-rw-r--r--net/dccp/output.c209
-rw-r--r--net/dccp/proto.c21
-rw-r--r--net/dccp/timer.c27
-rw-r--r--net/ipv4/fib_frontend.c2
-rw-r--r--net/ipv4/fib_hash.c18
-rw-r--r--net/ipv4/fib_trie.c5
-rw-r--r--net/mac80211/debugfs_key.c6
-rw-r--r--net/mac80211/main.c5
-rw-r--r--net/netfilter/xt_socket.c7
17 files changed, 274 insertions, 142 deletions
diff --git a/net/compat.c b/net/compat.c
index 63d260e81472..3649d5895361 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -41,10 +41,12 @@ static inline int iov_from_user_compat_to_kern(struct iovec *kiov,
 		compat_size_t len;
 
 		if (get_user(len, &uiov32->iov_len) ||
-		   get_user(buf, &uiov32->iov_base)) {
-			tot_len = -EFAULT;
-			break;
-		}
+		    get_user(buf, &uiov32->iov_base))
+			return -EFAULT;
+
+		if (len > INT_MAX - tot_len)
+			len = INT_MAX - tot_len;
+
 		tot_len += len;
 		kiov->iov_base = compat_ptr(buf);
 		kiov->iov_len = (__kernel_size_t) len;
diff --git a/net/core/iovec.c b/net/core/iovec.c
index 72aceb1fe4fa..c40f27e7d208 100644
--- a/net/core/iovec.c
+++ b/net/core/iovec.c
@@ -35,10 +35,9 @@
  *	in any case.
  */
 
-long verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode)
+int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode)
 {
-	int size, ct;
-	long err;
+	int size, ct, err;
 
 	if (m->msg_namelen) {
 		if (mode == VERIFY_READ) {
@@ -62,14 +61,13 @@ long verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address,
 	err = 0;
 
 	for (ct = 0; ct < m->msg_iovlen; ct++) {
-		err += iov[ct].iov_len;
-		/*
-		 * Goal is not to verify user data, but to prevent returning
-		 * negative value, which is interpreted as errno.
-		 * Overflow is still possible, but it is harmless.
-		 */
-		if (err < 0)
-			return -EMSGSIZE;
+		size_t len = iov[ct].iov_len;
+
+		if (len > INT_MAX - err) {
+			len = INT_MAX - err;
+			iov[ct].iov_len = len;
+		}
+		err += len;
 	}
 
 	return err;
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 679b797d06b1..fbce4b05a53e 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -887,10 +887,11 @@ static ssize_t pktgen_if_write(struct file *file,
 	i += len;
 
 	if (debug) {
-		char tb[count + 1];
-		if (copy_from_user(tb, user_buffer, count))
+		size_t copy = min(count, 1023);
+		char tb[copy + 1];
+		if (copy_from_user(tb, user_buffer, copy))
 			return -EFAULT;
-		tb[count] = 0;
+		tb[copy] = 0;
 		printk(KERN_DEBUG "pktgen: %s,%lu  buffer -:%s:-\n", name,
 		       (unsigned long)count, tb);
 	}
diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h
index 117fb093dcaf..75c3582a7678 100644
--- a/net/dccp/ccid.h
+++ b/net/dccp/ccid.h
@@ -134,13 +134,41 @@ static inline int ccid_get_current_tx_ccid(struct dccp_sock *dp)
 extern void ccid_hc_rx_delete(struct ccid *ccid, struct sock *sk);
 extern void ccid_hc_tx_delete(struct ccid *ccid, struct sock *sk);
 
+/*
+ * Congestion control of queued data packets via CCID decision.
+ *
+ * The TX CCID performs its congestion-control by indicating whether and when a
+ * queued packet may be sent, using the return code of ccid_hc_tx_send_packet().
+ * The following modes are supported via the symbolic constants below:
+ * - timer-based pacing    (CCID returns a delay value in milliseconds);
+ * - autonomous dequeueing (CCID internally schedules dccps_xmitlet).
+ */
+
+enum ccid_dequeueing_decision {
+	CCID_PACKET_SEND_AT_ONCE =	 0x00000,  /* "green light": no delay */
+	CCID_PACKET_DELAY_MAX =		 0x0FFFF,  /* maximum delay in msecs  */
+	CCID_PACKET_DELAY =		 0x10000,  /* CCID msec-delay mode */
+	CCID_PACKET_WILL_DEQUEUE_LATER = 0x20000,  /* CCID autonomous mode */
+	CCID_PACKET_ERR =		 0xF0000,  /* error condition */
+};
+
+static inline int ccid_packet_dequeue_eval(const int return_code)
+{
+	if (return_code < 0)
+		return CCID_PACKET_ERR;
+	if (return_code == 0)
+		return CCID_PACKET_SEND_AT_ONCE;
+	if (return_code <= CCID_PACKET_DELAY_MAX)
+		return CCID_PACKET_DELAY;
+	return return_code;
+}
+
 static inline int ccid_hc_tx_send_packet(struct ccid *ccid, struct sock *sk,
 					 struct sk_buff *skb)
 {
-	int rc = 0;
 	if (ccid->ccid_ops->ccid_hc_tx_send_packet != NULL)
-		rc = ccid->ccid_ops->ccid_hc_tx_send_packet(sk, skb);
-	return rc;
+		return ccid->ccid_ops->ccid_hc_tx_send_packet(sk, skb);
+	return CCID_PACKET_SEND_AT_ONCE;
 }
 
 static inline void ccid_hc_tx_packet_sent(struct ccid *ccid, struct sock *sk,
diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index d850e291f87c..6576eae9e779 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -78,12 +78,9 @@ static int ccid2_hc_tx_alloc_seq(struct ccid2_hc_tx_sock *hc)
 
 static int ccid2_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb)
 {
-	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
-
-	if (hc->tx_pipe < hc->tx_cwnd)
-		return 0;
-
-	return 1; /* XXX CCID should dequeue when ready instead of polling */
+	if (ccid2_cwnd_network_limited(ccid2_hc_tx_sk(sk)))
+		return CCID_PACKET_WILL_DEQUEUE_LATER;
+	return CCID_PACKET_SEND_AT_ONCE;
 }
 
 static void ccid2_change_l_ack_ratio(struct sock *sk, u32 val)
@@ -115,6 +112,7 @@ static void ccid2_hc_tx_rto_expire(unsigned long data)
 {
 	struct sock *sk = (struct sock *)data;
 	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
+	const bool sender_was_blocked = ccid2_cwnd_network_limited(hc);
 
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk)) {
@@ -129,8 +127,6 @@ static void ccid2_hc_tx_rto_expire(unsigned long data)
 	if (hc->tx_rto > DCCP_RTO_MAX)
 		hc->tx_rto = DCCP_RTO_MAX;
 
-	sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto);
-
 	/* adjust pipe, cwnd etc */
 	hc->tx_ssthresh = hc->tx_cwnd / 2;
 	if (hc->tx_ssthresh < 2)
@@ -146,6 +142,12 @@ static void ccid2_hc_tx_rto_expire(unsigned long data)
 	hc->tx_rpseq    = 0;
 	hc->tx_rpdupack = -1;
 	ccid2_change_l_ack_ratio(sk, 1);
+
+	/* if we were blocked before, we may now send cwnd=1 packet */
+	if (sender_was_blocked)
+		tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet);
+	/* restart backed-off timer */
+	sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto);
 out:
 	bh_unlock_sock(sk);
 	sock_put(sk);
@@ -434,6 +436,7 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
 {
 	struct dccp_sock *dp = dccp_sk(sk);
 	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
+	const bool sender_was_blocked = ccid2_cwnd_network_limited(hc);
 	u64 ackno, seqno;
 	struct ccid2_seq *seqp;
 	unsigned char *vector;
@@ -631,6 +634,10 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
 		sk_stop_timer(sk, &hc->tx_rtotimer);
 	else
 		sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto);
+
+	/* check if incoming Acks allow pending packets to be sent */
+	if (sender_was_blocked && !ccid2_cwnd_network_limited(hc))
+		tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet);
 }
 
 static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk)
diff --git a/net/dccp/ccids/ccid2.h b/net/dccp/ccids/ccid2.h
index 9731c2dc1487..25cb6b216eda 100644
--- a/net/dccp/ccids/ccid2.h
+++ b/net/dccp/ccids/ccid2.h
@@ -81,6 +81,11 @@ struct ccid2_hc_tx_sock {
 	u64			tx_high_ack;
 };
 
+static inline bool ccid2_cwnd_network_limited(struct ccid2_hc_tx_sock *hc)
+{
+	return hc->tx_pipe >= hc->tx_cwnd;
+}
+
 struct ccid2_hc_rx_sock {
 	int	rx_data;
 };
diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c
index 3060a60ed5ab..3d604e1349c0 100644
--- a/net/dccp/ccids/ccid3.c
+++ b/net/dccp/ccids/ccid3.c
@@ -268,11 +268,11 @@ out:
 	sock_put(sk);
 }
 
-/*
- * returns
- *   > 0: delay (in msecs) that should pass before actually sending
- *   = 0: can send immediately
- *   < 0: error condition; do not send packet
+/**
+ * ccid3_hc_tx_send_packet  -  Delay-based dequeueing of TX packets
+ * @skb: next packet candidate to send on @sk
+ * This function uses the convention of ccid_packet_dequeue_eval() and
+ * returns a millisecond-delay value between 0 and t_mbi = 64000 msec.
  */
 static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb)
 {
@@ -348,7 +348,7 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb)
 
 	/* set the nominal send time for the next following packet */
 	hc->tx_t_nom = ktime_add_us(hc->tx_t_nom, hc->tx_t_ipi);
-	return 0;
+	return CCID_PACKET_SEND_AT_ONCE;
 }
 
 static void ccid3_hc_tx_packet_sent(struct sock *sk, unsigned int len)
diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index 3eb264b60823..a8ed459508b2 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -243,8 +243,9 @@ extern void dccp_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
 extern void dccp_send_sync(struct sock *sk, const u64 seq,
 			   const enum dccp_pkt_type pkt_type);
 
-extern void dccp_write_xmit(struct sock *sk, int block);
-extern void dccp_write_space(struct sock *sk);
+extern void   dccp_write_xmit(struct sock *sk);
+extern void   dccp_write_space(struct sock *sk);
+extern void   dccp_flush_write_queue(struct sock *sk, long *time_budget);
 
 extern void dccp_init_xmit_timers(struct sock *sk);
 static inline void dccp_clear_xmit_timers(struct sock *sk)
diff --git a/net/dccp/output.c b/net/dccp/output.c
index a988fe9ffcba..45b91853f5ae 100644
--- a/net/dccp/output.c
+++ b/net/dccp/output.c
@@ -209,108 +209,150 @@ void dccp_write_space(struct sock *sk)
 }
 
 /**
- * dccp_wait_for_ccid - Wait for ccid to tell us we can send a packet
+ * dccp_wait_for_ccid  -  Await CCID send permission
  * @sk:    socket to wait for
- * @skb:   current skb to pass on for waiting
- * @delay: sleep timeout in milliseconds (> 0)
- * This function is called by default when the socket is closed, and
- * when a non-zero linger time is set on the socket. For consistency
+ * @delay: timeout in jiffies
+ * This is used by CCIDs which need to delay the send time in process context.
  */
-static int dccp_wait_for_ccid(struct sock *sk, struct sk_buff *skb, int delay)
+static int dccp_wait_for_ccid(struct sock *sk, unsigned long delay)
 {
-	struct dccp_sock *dp = dccp_sk(sk);
 	DEFINE_WAIT(wait);
-	unsigned long jiffdelay;
-	int rc;
+	long remaining;
+
+	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+	sk->sk_write_pending++;
+	release_sock(sk);
+
+	remaining = schedule_timeout(delay);
+
+	lock_sock(sk);
+	sk->sk_write_pending--;
+	finish_wait(sk_sleep(sk), &wait);
+
+	if (signal_pending(current) || sk->sk_err)
+		return -1;
+	return remaining;
+}
+
+/**
+ * dccp_xmit_packet  -  Send data packet under control of CCID
+ * Transmits next-queued payload and informs CCID to account for the packet.
+ */
+static void dccp_xmit_packet(struct sock *sk)
+{
+	int err, len;
+	struct dccp_sock *dp = dccp_sk(sk);
+	struct sk_buff *skb = skb_dequeue(&sk->sk_write_queue);
 
-	do {
-		dccp_pr_debug("delayed send by %d msec\n", delay);
-		jiffdelay = msecs_to_jiffies(delay);
+	if (unlikely(skb == NULL))
+		return;
+	len = skb->len;
 
-		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+	if (sk->sk_state == DCCP_PARTOPEN) {
+		const u32 cur_mps = dp->dccps_mss_cache - DCCP_FEATNEG_OVERHEAD;
+		/*
+		 * See 8.1.5 - Handshake Completion.
+		 *
+		 * For robustness we resend Confirm options until the client has
+		 * entered OPEN. During the initial feature negotiation, the MPS
+		 * is smaller than usual, reduced by the Change/Confirm options.
+		 */
+		if (!list_empty(&dp->dccps_featneg) && len > cur_mps) {
+			DCCP_WARN("Payload too large (%d) for featneg.\n", len);
+			dccp_send_ack(sk);
+			dccp_feat_list_purge(&dp->dccps_featneg);
+		}
 
-		sk->sk_write_pending++;
-		release_sock(sk);
-		schedule_timeout(jiffdelay);
-		lock_sock(sk);
-		sk->sk_write_pending--;
+		inet_csk_schedule_ack(sk);
+		inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
+					      inet_csk(sk)->icsk_rto,
+					      DCCP_RTO_MAX);
+		DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_DATAACK;
+	} else if (dccp_ack_pending(sk)) {
+		DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_DATAACK;
+	} else {
+		DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_DATA;
+	}
+
+	err = dccp_transmit_skb(sk, skb);
+	if (err)
+		dccp_pr_debug("transmit_skb() returned err=%d\n", err);
+	/*
+	 * Register this one as sent even if an error occurred. To the remote
+	 * end a local packet drop is indistinguishable from network loss, i.e.
+	 * any local drop will eventually be reported via receiver feedback.
+	 */
+	ccid_hc_tx_packet_sent(dp->dccps_hc_tx_ccid, sk, len);
+}
 
-		if (sk->sk_err)
-			goto do_error;
-		if (signal_pending(current))
-			goto do_interrupted;
+/**
+ * dccp_flush_write_queue  -  Drain queue at end of connection
+ * Since dccp_sendmsg queues packets without waiting for them to be sent, it may
+ * happen that the TX queue is not empty at the end of a connection. We give the
+ * HC-sender CCID a grace period of up to @time_budget jiffies. If this function
+ * returns with a non-empty write queue, it will be purged later.
+ */
+void dccp_flush_write_queue(struct sock *sk, long *time_budget)
+{
+	struct dccp_sock *dp = dccp_sk(sk);
+	struct sk_buff *skb;
+	long delay, rc;
 
+	while (*time_budget > 0 && (skb = skb_peek(&sk->sk_write_queue))) {
 		rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb);
-	} while ((delay = rc) > 0);
-out:
-	finish_wait(sk_sleep(sk), &wait);
-	return rc;
-
-do_error:
-	rc = -EPIPE;
-	goto out;
-do_interrupted:
-	rc = -EINTR;
-	goto out;
+
+		switch (ccid_packet_dequeue_eval(rc)) {
+		case CCID_PACKET_WILL_DEQUEUE_LATER:
+			/*
+			 * If the CCID determines when to send, the next sending
+			 * time is unknown or the CCID may not even send again
+			 * (e.g. remote host crashes or lost Ack packets).
+			 */
+			DCCP_WARN("CCID did not manage to send all packets\n");
+			return;
+		case CCID_PACKET_DELAY:
+			delay = msecs_to_jiffies(rc);
+			if (delay > *time_budget)
+				return;
+			rc = dccp_wait_for_ccid(sk, delay);
+			if (rc < 0)
+				return;
+			*time_budget -= (delay - rc);
+			/* check again if we can send now */
+			break;
+		case CCID_PACKET_SEND_AT_ONCE:
+			dccp_xmit_packet(sk);
+			break;
+		case CCID_PACKET_ERR:
+			skb_dequeue(&sk->sk_write_queue);
+			kfree_skb(skb);
+			dccp_pr_debug("packet discarded due to err=%ld\n", rc);
+		}
+	}
 }
 
-void dccp_write_xmit(struct sock *sk, int block)
+void dccp_write_xmit(struct sock *sk)
 {
 	struct dccp_sock *dp = dccp_sk(sk);
 	struct sk_buff *skb;
 
 	while ((skb = skb_peek(&sk->sk_write_queue))) {
-		int err = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb);
-
-		if (err > 0) {
-			if (!block) {
-				sk_reset_timer(sk, &dp->dccps_xmit_timer,
-						msecs_to_jiffies(err)+jiffies);
-				break;
-			} else
-				err = dccp_wait_for_ccid(sk, skb, err);
-			if (err && err != -EINTR)
-				DCCP_BUG("err=%d after dccp_wait_for_ccid", err);
-		}
+		int rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb);
 
-		skb_dequeue(&sk->sk_write_queue);
-		if (err == 0) {
-			struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
-			const int len = skb->len;
-
-			if (sk->sk_state == DCCP_PARTOPEN) {
-				const u32 cur_mps = dp->dccps_mss_cache - DCCP_FEATNEG_OVERHEAD;
-				/*
-				 * See 8.1.5 - Handshake Completion.
-				 *
-				 * For robustness we resend Confirm options until the client has
-				 * entered OPEN. During the initial feature negotiation, the MPS
-				 * is smaller than usual, reduced by the Change/Confirm options.
-				 */
-				if (!list_empty(&dp->dccps_featneg) && len > cur_mps) {
-					DCCP_WARN("Payload too large (%d) for featneg.\n", len);
-					dccp_send_ack(sk);
-					dccp_feat_list_purge(&dp->dccps_featneg);
-				}
-
-				inet_csk_schedule_ack(sk);
-				inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
-						  inet_csk(sk)->icsk_rto,
-						  DCCP_RTO_MAX);
-				dcb->dccpd_type = DCCP_PKT_DATAACK;
-			} else if (dccp_ack_pending(sk))
-				dcb->dccpd_type = DCCP_PKT_DATAACK;
-			else
-				dcb->dccpd_type = DCCP_PKT_DATA;
-
-			err = dccp_transmit_skb(sk, skb);
-			ccid_hc_tx_packet_sent(dp->dccps_hc_tx_ccid, sk, len);
-			if (err)
-				DCCP_BUG("err=%d after ccid_hc_tx_packet_sent",
-					 err);
-		} else {
-			dccp_pr_debug("packet discarded due to err=%d\n", err);
+		switch (ccid_packet_dequeue_eval(rc)) {
+		case CCID_PACKET_WILL_DEQUEUE_LATER:
+			return;
+		case CCID_PACKET_DELAY:
+			sk_reset_timer(sk, &dp->dccps_xmit_timer,
+				       jiffies + msecs_to_jiffies(rc));
+			return;
+		case CCID_PACKET_SEND_AT_ONCE:
+			dccp_xmit_packet(sk);
+			break;
+		case CCID_PACKET_ERR:
+			skb_dequeue(&sk->sk_write_queue);
 			kfree_skb(skb);
+			dccp_pr_debug("packet discarded due to err=%d\n", rc);
 		}
 	}
 }
@@ -622,7 +664,6 @@ void dccp_send_close(struct sock *sk, const int active)
 		DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_CLOSE;
 
 	if (active) {
-		dccp_write_xmit(sk, 1);
 		dccp_skb_entail(sk, skb);
 		dccp_transmit_skb(sk, skb_clone(skb, prio));
 		/*
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 7e5fc04eb6d1..ef343d53fcea 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -726,7 +726,13 @@ int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		goto out_discard;
 
 	skb_queue_tail(&sk->sk_write_queue, skb);
-	dccp_write_xmit(sk,0);
+	/*
+	 * The xmit_timer is set if the TX CCID is rate-based and will expire
+	 * when congestion control permits to release further packets into the
+	 * network. Window-based CCIDs do not use this timer.
+	 */
+	if (!timer_pending(&dp->dccps_xmit_timer))
+		dccp_write_xmit(sk);
 out_release:
 	release_sock(sk);
 	return rc ? : len;
@@ -951,9 +957,22 @@ void dccp_close(struct sock *sk, long timeout)
 		/* Check zero linger _after_ checking for unread data. */
 		sk->sk_prot->disconnect(sk, 0);
 	} else if (sk->sk_state != DCCP_CLOSED) {
+		/*
+		 * Normal connection termination. May need to wait if there are
+		 * still packets in the TX queue that are delayed by the CCID.
+		 */
+		dccp_flush_write_queue(sk, &timeout);
 		dccp_terminate_connection(sk);
 	}
 
+	/*
+	 * Flush write queue. This may be necessary in several cases:
+	 * - we have been closed by the peer but still have application data;
+	 * - abortive termination (unread data or zero linger time),
+	 * - normal termination but queue could not be flushed within time limit
+	 */
+	__skb_queue_purge(&sk->sk_write_queue);
+
 	sk_stream_wait_close(sk, timeout);
 
 adjudge_to_death:
diff --git a/net/dccp/timer.c b/net/dccp/timer.c
index 1a9aa05d4dc4..7587870b7040 100644
--- a/net/dccp/timer.c
+++ b/net/dccp/timer.c
@@ -237,32 +237,35 @@ out:
 	sock_put(sk);
 }
 
-/* Transmit-delay timer: used by the CCIDs to delay actual send time */
-static void dccp_write_xmit_timer(unsigned long data)
+/**
+ * dccp_write_xmitlet  -  Workhorse for CCID packet dequeueing interface
+ * See the comments above %ccid_dequeueing_decision for supported modes.
+ */
+static void dccp_write_xmitlet(unsigned long data)
 {
 	struct sock *sk = (struct sock *)data;
-	struct dccp_sock *dp = dccp_sk(sk);
 
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk))
-		sk_reset_timer(sk, &dp->dccps_xmit_timer, jiffies+1);
+		sk_reset_timer(sk, &dccp_sk(sk)->dccps_xmit_timer, jiffies + 1);
 	else
-		dccp_write_xmit(sk, 0);
+		dccp_write_xmit(sk);
 	bh_unlock_sock(sk);
-	sock_put(sk);
 }
 
-static void dccp_init_write_xmit_timer(struct sock *sk)
+static void dccp_write_xmit_timer(unsigned long data)
 {
-	struct dccp_sock *dp = dccp_sk(sk);
-
-	setup_timer(&dp->dccps_xmit_timer, dccp_write_xmit_timer,
-			(unsigned long)sk);
+	dccp_write_xmitlet(data);
+	sock_put((struct sock *)data);
 }
 
 void dccp_init_xmit_timers(struct sock *sk)
 {
-	dccp_init_write_xmit_timer(sk);
+	struct dccp_sock *dp = dccp_sk(sk);
+
+	tasklet_init(&dp->dccps_xmitlet, dccp_write_xmitlet, (unsigned long)sk);
+	setup_timer(&dp->dccps_xmit_timer, dccp_write_xmit_timer,
+							     (unsigned long)sk);
 	inet_csk_init_xmit_timers(sk, &dccp_write_timer, &dccp_delack_timer,
 				  &dccp_keepalive_timer);
 }
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 36e27c2107de..eb6f69a8f27a 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1052,7 +1052,7 @@ static void ip_fib_net_exit(struct net *net)
 		hlist_for_each_entry_safe(tb, node, tmp, head, tb_hlist) {
 			hlist_del(node);
 			fib_table_flush(tb);
-			kfree(tb);
+			fib_free_table(tb);
 		}
 	}
 	kfree(net->ipv4.fib_table_hash);
diff --git a/net/ipv4/fib_hash.c b/net/ipv4/fib_hash.c
index b232375a0b75..b3acb0417b21 100644
--- a/net/ipv4/fib_hash.c
+++ b/net/ipv4/fib_hash.c
@@ -716,6 +716,24 @@ int fib_table_flush(struct fib_table *tb)
 	return found;
 }
 
+void fib_free_table(struct fib_table *tb)
+{
+	struct fn_hash *table = (struct fn_hash *) tb->tb_data;
+	struct fn_zone *fz, *next;
+
+	next = table->fn_zone_list;
+	while (next != NULL) {
+		fz = next;
+		next = fz->fz_next;
+
+		if (fz->fz_hash != fz->fz_embedded_hash)
+			fz_hash_free(fz->fz_hash, fz->fz_divisor);
+
+		kfree(fz);
+	}
+
+	kfree(tb);
+}
 
 static inline int
 fn_hash_dump_bucket(struct sk_buff *skb, struct netlink_callback *cb,
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index b14450895102..200eb538fbb3 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1797,6 +1797,11 @@ int fib_table_flush(struct fib_table *tb)
 	return found;
 }
 
+void fib_free_table(struct fib_table *tb)
+{
+	kfree(tb);
+}
+
 void fib_table_select_default(struct fib_table *tb,
 			      const struct flowi *flp,
 			      struct fib_result *res)
diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c
index 4aa47d074a79..1243d1db5c59 100644
--- a/net/mac80211/debugfs_key.c
+++ b/net/mac80211/debugfs_key.c
@@ -203,9 +203,13 @@ static ssize_t key_key_read(struct file *file, char __user *userbuf,
 			    size_t count, loff_t *ppos)
 {
 	struct ieee80211_key *key = file->private_data;
-	int i, res, bufsize = 2 * key->conf.keylen + 2;
+	int i, bufsize = 2 * key->conf.keylen + 2;
 	char *buf = kmalloc(bufsize, GFP_KERNEL);
 	char *p = buf;
+	ssize_t res;
+
+	if (!buf)
+		return -ENOMEM;
 
 	for (i = 0; i < key->conf.keylen; i++)
 		p += scnprintf(p, bufsize + buf - p, "%02x", key->conf.key[i]);
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 6b322fa681f5..107a0cbe52ac 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -677,10 +677,11 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 	/*
 	 * Calculate scan IE length -- we need this to alloc
 	 * memory and to subtract from the driver limit. It
-	 * includes the (extended) supported rates and HT
+	 * includes the DS Params, (extended) supported rates, and HT
 	 * information -- SSID is the driver's responsibility.
 	 */
-	local->scan_ies_len = 4 + max_bitrates; /* (ext) supp rates */
+	local->scan_ies_len = 4 + max_bitrates /* (ext) supp rates */ +
+		3 /* DS Params */;
 	if (supp_ht)
 		local->scan_ies_len += 2 + sizeof(struct ieee80211_ht_cap);
 
diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c
index d94a858dc52a..00d6ae838303 100644
--- a/net/netfilter/xt_socket.c
+++ b/net/netfilter/xt_socket.c
@@ -195,7 +195,7 @@ socket_mt4_v1(const struct sk_buff *skb, struct xt_action_param *par)
 static int
 extract_icmp6_fields(const struct sk_buff *skb,
 		     unsigned int outside_hdrlen,
-		     u8 *protocol,
+		     int *protocol,
 		     struct in6_addr **raddr,
 		     struct in6_addr **laddr,
 		     __be16 *rport,
@@ -252,8 +252,7 @@ socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par)
 	struct sock *sk;
 	struct in6_addr *daddr, *saddr;
 	__be16 dport, sport;
-	int thoff;
-	u8 tproto;
+	int thoff, tproto;
 	const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo;
 
 	tproto = ipv6_find_hdr(skb, &thoff, -1, NULL);
@@ -305,7 +304,7 @@ socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par)
 			sk = NULL;
 	}
 
-	pr_debug("proto %hhu %pI6:%hu -> %pI6:%hu "
+	pr_debug("proto %hhd %pI6:%hu -> %pI6:%hu "
 		 "(orig %pI6:%hu) sock %p\n",
 		 tproto, saddr, ntohs(sport),
 		 daddr, ntohs(dport),