Merge bk://kernel.bkbits.net/davem/net-2.6

into ppc970.osdl.org:/home/torvalds/v2.6/linux

Documentation/DocBook/kernel-api.tmpl

@@ -133,6 +133,11 @@ KAO -->
      <sect1><title>Socket Filter</title>
 !Enet/core/filter.c
      </sect1>
+     <sect1><title>Generic Network Statistics</title>
+!Iinclude/linux/gen_stats.h
+!Enet/core/gen_stats.c
+!Enet/core/gen_estimator.c
+     </sect1>
   </chapter>
 
   <chapter id="netdev">

include/linux/gen_stats.h

@@ -14,6 +14,7 @@ enum {
 #define TCA_STATS_MAX (__TCA_STATS_MAX - 1)
 
 /**
+ * struct gnet_stats_basic - byte/packet throughput statistics
  * @bytes: number of seen bytes
  * @packets: number of seen packets
  */
@@ -24,6 +25,7 @@ struct gnet_stats_basic
 };
 
 /**
+ * struct gnet_stats_rate_est - rate estimator
  * @bps: current byte rate
  * @pps: current packet rate
  */
@@ -34,10 +36,12 @@ struct gnet_stats_rate_est
 };
 
 /**
+ * struct gnet_stats_queue - queuing statistics
  * @qlen: queue length
  * @backlog: backlog size of queue
  * @drops: number of dropped packets
  * @requeues: number of requeues
+ * @overlimits: number of enqueues over the limit
  */
 struct gnet_stats_queue
 {
@@ -49,6 +53,7 @@ struct gnet_stats_queue
 };
 
 /**
+ * struct gnet_estimator - rate estimator configuration
  * @interval: sampling period
  * @ewma_log: the log of measurement window weight
  */

include/net/udp.h

@@ -71,6 +71,8 @@ extern int	udp_sendmsg(struct kiocb *iocb, struct sock *sk,
 extern int	udp_rcv(struct sk_buff *skb);
 extern int	udp_ioctl(struct sock *sk, int cmd, unsigned long arg);
 extern int	udp_disconnect(struct sock *sk, int flags);
+extern unsigned int udp_poll(struct file *file, struct socket *sock,
+			     poll_table *wait);
 
 DECLARE_SNMP_STAT(struct udp_mib, udp_statistics);
 #define UDP_INC_STATS(field)		SNMP_INC_STATS(udp_statistics, field)

net/compat.c

@@ -22,6 +22,7 @@
 #include <linux/filter.h>
 #include <linux/compat.h>
 #include <linux/netfilter_ipv4/ip_tables.h>
+#include <linux/security.h>
 
 #include <net/scm.h>
 #include <net/sock.h>
@@ -264,6 +265,9 @@ void scm_detach_fds_compat(struct msghdr *kmsg, struct scm_cookie *scm)
 
 	for (i = 0, cmfptr = (int __user *) CMSG_COMPAT_DATA(cm); i < fdmax; i++, cmfptr++) {
 		int new_fd;
+		err = security_file_receive(fp[i]);
+		if (err)
+			break;
 		err = get_unused_fd();
 		if (err < 0)
 			break;

net/core/gen_estimator.c

@@ -132,6 +132,21 @@ static void est_timer(unsigned long arg)
 	read_unlock(&est_lock);
 }
 
+/**
+ * gen_new_estimator - create a new rate estimator
+ * @bstats: basic statistics
+ * @rate_est: rate estimator statistics
+ * @stats_lock: statistics lock
+ * @opt: rate estimator configuration TLV
+ *
+ * Creates a new rate estimator with &bstats as source and &rate_est
+ * as destination. A new timer with the interval specified in the
+ * configuration TLV is created. Upon each interval, the latest statistics
+ * will be read from &bstats and the estimated rate will be stored in
+ * &rate_est with the statistics lock grabed during this period.
+ * 
+ * Returns 0 on success or a negative error code.
+ */
 int gen_new_estimator(struct gnet_stats_basic *bstats,
 	struct gnet_stats_rate_est *rate_est, spinlock_t *stats_lock, struct rtattr *opt)
 {
@@ -173,6 +188,14 @@ int gen_new_estimator(struct gnet_stats_basic *bstats,
 	return 0;
 }
 
+/**
+ * gen_kill_estimator - remove a rate estimator
+ * @bstats: basic statistics
+ * @rate_est: rate estimator statistics
+ *
+ * Removes the rate estimator specified by &bstats and &rate_est
+ * and deletes the timer.
+ */
 void gen_kill_estimator(struct gnet_stats_basic *bstats,
 	struct gnet_stats_rate_est *rate_est)
 {
@@ -200,6 +223,18 @@ void gen_kill_estimator(struct gnet_stats_basic *bstats,
 	}
 }
 
+/**
+ * gen_replace_estimator - replace rate estimator configruation
+ * @bstats: basic statistics
+ * @rate_est: rate estimator statistics
+ * @stats_lock: statistics lock
+ * @opt: rate estimator configuration TLV
+ *
+ * Replaces the configuration of a rate estimator by calling
+ * gen_kill_estimator() and gen_new_estimator().
+ * 
+ * Returns 0 on success or a negative error code.
+ */
 int
 gen_replace_estimator(struct gnet_stats_basic *bstats,
 	struct gnet_stats_rate_est *rate_est, spinlock_t *stats_lock,

net/core/gen_stats.c

@@ -34,6 +34,24 @@ gnet_stats_copy(struct gnet_dump *d, int type, void *buf, int size)
 	return -1;
 }
 
+/**
+ * gnet_stats_start_copy_compat - start dumping procedure in compatibility mode
+ * @skb: socket buffer to put statistics TLVs into
+ * @type: TLV type for top level statistic TLV
+ * @tc_stats_type: TLV type for backward compatibility struct tc_stats TLV
+ * @xstats_type: TLV type for backward compatibility xstats TLV
+ * @lock: statistics lock
+ * @d: dumping handle
+ *
+ * Initializes the dumping handle, grabs the statistic lock and appends
+ * an empty TLV header to the socket buffer for use a container for all
+ * other statistic TLVS.
+ *
+ * The dumping handle is marked to be in backward compatibility mode telling
+ * all gnet_stats_copy_XXX() functions to fill a local copy of struct tc_stats.
+ *
+ * Returns 0 on success or -1 if the room in the socket buffer was not sufficient.
+ */
 int
 gnet_stats_start_copy_compat(struct sk_buff *skb, int type, int tc_stats_type,
 	int xstats_type, spinlock_t *lock, struct gnet_dump *d)
@@ -52,6 +70,19 @@ gnet_stats_start_copy_compat(struct sk_buff *skb, int type, int tc_stats_type,
 	return gnet_stats_copy(d, type, NULL, 0);
 }
 
+/**
+ * gnet_stats_start_copy_compat - start dumping procedure in compatibility mode
+ * @skb: socket buffer to put statistics TLVs into
+ * @type: TLV type for top level statistic TLV
+ * @lock: statistics lock
+ * @d: dumping handle
+ *
+ * Initializes the dumping handle, grabs the statistic lock and appends
+ * an empty TLV header to the socket buffer for use a container for all
+ * other statistic TLVS.
+ *
+ * Returns 0 on success or -1 if the room in the socket buffer was not sufficient.
+ */
 int
 gnet_stats_start_copy(struct sk_buff *skb, int type, spinlock_t *lock,
 	struct gnet_dump *d)
@@ -59,7 +90,17 @@ gnet_stats_start_copy(struct sk_buff *skb, int type, spinlock_t *lock,
 	return gnet_stats_start_copy_compat(skb, type, 0, 0, lock, d);
 }
 
-
+/**
+ * gnet_stats_copy_basic - copy basic statistics into statistic TLV
+ * @d: dumping handle
+ * @b: basic statistics
+ *
+ * Appends the basic statistics to the top level TLV created by
+ * gnet_stats_start_copy().
+ *
+ * Returns 0 on success or -1 with the statistic lock released
+ * if the room in the socket buffer was not sufficient.
+ */
 int
 gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic *b)
 {
@@ -71,6 +112,17 @@ gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic *b)
 	return gnet_stats_copy(d, TCA_STATS_BASIC, b, sizeof(*b));
 }
 
+/**
+ * gnet_stats_copy_rate_est - copy rate estimator statistics into statistics TLV
+ * @d: dumping handle
+ * @r: rate estimator statistics
+ *
+ * Appends the rate estimator statistics to the top level TLV created by
+ * gnet_stats_start_copy().
+ *
+ * Returns 0 on success or -1 with the statistic lock released
+ * if the room in the socket buffer was not sufficient.
+ */
 int
 gnet_stats_copy_rate_est(struct gnet_dump *d, struct gnet_stats_rate_est *r)
 {
@@ -82,6 +134,17 @@ gnet_stats_copy_rate_est(struct gnet_dump *d, struct gnet_stats_rate_est *r)
 	return gnet_stats_copy(d, TCA_STATS_RATE_EST, r, sizeof(*r));
 }
 
+/**
+ * gnet_stats_copy_queue - copy queue statistics into statistics TLV
+ * @d: dumping handle
+ * @q: queue statistics
+ *
+ * Appends the queue statistics to the top level TLV created by
+ * gnet_stats_start_copy().
+ *
+ * Returns 0 on success or -1 with the statistic lock released
+ * if the room in the socket buffer was not sufficient.
+ */
 int
 gnet_stats_copy_queue(struct gnet_dump *d, struct gnet_stats_queue *q)
 {
@@ -95,6 +158,19 @@ gnet_stats_copy_queue(struct gnet_dump *d, struct gnet_stats_queue *q)
 	return gnet_stats_copy(d, TCA_STATS_QUEUE, q, sizeof(*q));
 }
 
+/**
+ * gnet_stats_copy_app - copy application specific statistics into statistics TLV
+ * @d: dumping handle
+ * @st: application specific statistics data
+ * @len: length of data
+ *
+ * Appends the application sepecific statistics to the top level TLV created by
+ * gnet_stats_start_copy() and remembers the data for XSTATS if the dumping
+ * handle is in backward compatibility mode.
+ *
+ * Returns 0 on success or -1 with the statistic lock released
+ * if the room in the socket buffer was not sufficient.
+ */
 int
 gnet_stats_copy_app(struct gnet_dump *d, void *st, int len)
 {
@@ -103,6 +179,18 @@ gnet_stats_copy_app(struct gnet_dump *d, void *st, int len)
 	return gnet_stats_copy(d, TCA_STATS_APP, st, len);
 }
 
+/**
+ * gnet_stats_finish_copy - finish dumping procedure
+ * @d: dumping handle
+ *
+ * Corrects the length of the top level TLV to include all TLVs added
+ * by gnet_stats_copy_XXX() calls. Adds the backward compatibility TLVs
+ * if gnet_stats_start_copy_compat() was used and releases the statistics
+ * lock.
+ *
+ * Returns 0 on success or -1 with the statistic lock released
+ * if the room in the socket buffer was not sufficient.
+ */
 int
 gnet_stats_finish_copy(struct gnet_dump *d)
 {

net/core/pktgen.c

@@ -647,6 +647,7 @@ static void inject(struct pktgen_info* info)
 	info->do_run_run = 1; /* Cranke yeself! */
 	info->idle_acc = 0;
 	info->sofar = 0;
+	info->errors = 0;
 	lcount = info->count;
 
 

net/ipv4/af_inet.c

@@ -809,7 +809,7 @@ struct proto_ops inet_dgram_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	inet_getname,
-	.poll =		datagram_poll,
+	.poll =		udp_poll,
 	.ioctl =	inet_ioctl,
 	.listen =	sock_no_listen,
 	.shutdown =	inet_shutdown,

net/ipv4/udp.c

@@ -1303,6 +1303,52 @@ static int udp_getsockopt(struct sock *sk, int level, int optname,
   	return 0;
 }
 
+/**
+ * 	udp_poll - wait for a UDP event.
+ *	@file - file struct
+ *	@sock - socket
+ *	@wait - poll table
+ *
+ *	This is same as datagram poll, except for the special case of 
+ *	blocking sockets. If application is using a blocking fd
+ *	and a packet with checksum error is in the queue;
+ *	then it could get return from select indicating data available
+ *	but then block when reading it. Add special case code
+ *	to work around these arguably broken applications.
+ */
+unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait)
+{
+	unsigned int mask = datagram_poll(file, sock, wait);
+	struct sock *sk = sock->sk;
+	
+	/* Check for false positives due to checksum errors */
+	if ( (mask & POLLRDNORM) &&
+	     !(file->f_flags & O_NONBLOCK) &&
+	     !(sk->sk_shutdown & RCV_SHUTDOWN)){
+		struct sk_buff_head *rcvq = &sk->sk_receive_queue;
+		struct sk_buff *skb;
+
+		spin_lock_irq(&rcvq->lock);
+		while ((skb = skb_peek(rcvq)) != NULL) {
+			if (udp_checksum_complete(skb)) {
+				UDP_INC_STATS_BH(UDP_MIB_INERRORS);
+				__skb_unlink(skb, rcvq);
+				kfree_skb(skb);
+			} else {
+				skb->ip_summed = CHECKSUM_UNNECESSARY;
+				break;
+			}
+		}
+		spin_unlock_irq(&rcvq->lock);
+
+		/* nothing to see, move along */
+		if (skb == NULL)
+			mask &= ~(POLLIN | POLLRDNORM);
+	}
+
+	return mask;
+	
+}
 
 struct proto udp_prot = {
  	.name =		"UDP",
@@ -1517,6 +1563,7 @@ EXPORT_SYMBOL(udp_ioctl);
 EXPORT_SYMBOL(udp_port_rover);
 EXPORT_SYMBOL(udp_prot);
 EXPORT_SYMBOL(udp_sendmsg);
+EXPORT_SYMBOL(udp_poll);
 
 #ifdef CONFIG_PROC_FS
 EXPORT_SYMBOL(udp_proc_register);

net/ipv6/af_inet6.c

@@ -501,7 +501,7 @@ struct proto_ops inet6_dgram_ops = {
 	.socketpair =	sock_no_socketpair,		/* a do nothing	*/
 	.accept =	sock_no_accept,			/* a do nothing	*/
 	.getname =	inet6_getname, 
-	.poll =		datagram_poll,			/* ok		*/
+	.poll =		udp_poll,			/* ok		*/
 	.ioctl =	inet6_ioctl,			/* must change  */
 	.listen =	sock_no_listen,			/* ok		*/
 	.shutdown =	inet_shutdown,			/* ok		*/