X-Git-Url: https://git.openpandora.org/cgi-bin/gitweb.cgi?p=pandora-kernel.git;a=blobdiff_plain;f=net%2Fcore%2Fdev.c;h=1c0d862b0b12bd82f7245880b4034a0f62b360ff;hp=5a13edfc9f73411f688920b51400489eb3e89ee2;hb=d501ebeb7da7531e92e3c8d194730341c314ff2d;hpb=4d18de944954b973fede3259d206022f90549269

diff --git a/net/core/dev.c b/net/core/dev.c
index 5a13edfc9f73..1c0d862b0b12 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -859,7 +859,7 @@ int dev_valid_name(const char *name)
 		return 0;
 
 	while (*name) {
-		if (*name == '/' || isspace(*name))
+		if (*name == '/' || *name == ':' || isspace(*name))
 			return 0;
 		name++;
 	}
@@ -1059,6 +1059,8 @@ rollback:
  */
 int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
 {
+	char *new_ifalias;
+
 	ASSERT_RTNL();
 
 	if (len >= IFALIASZ)
@@ -1072,9 +1074,10 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
 		return 0;
 	}
 
-	dev->ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL);
-	if (!dev->ifalias)
+	new_ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL);
+	if (!new_ifalias)
 		return -ENOMEM;
+	dev->ifalias = new_ifalias;
 
 	strlcpy(dev->ifalias, alias, len+1);
 	return len;
@@ -1177,6 +1180,7 @@ static int __dev_open(struct net_device *dev)
 		net_dmaengine_get();
 		dev_set_rx_mode(dev);
 		dev_activate(dev);
+		add_device_randomness(dev->dev_addr, dev->addr_len);
 	}
 
 	return ret;
@@ -1421,14 +1425,34 @@ EXPORT_SYMBOL(register_netdevice_notifier);
  *	register_netdevice_notifier(). The notifier is unlinked into the
  *	kernel structures and may then be reused. A negative errno code
  *	is returned on a failure.
+ *
+ * 	After unregistering unregister and down device events are synthesized
+ *	for all devices on the device list to the removed notifier to remove
+ *	the need for special case cleanup code.
  */
 
 int unregister_netdevice_notifier(struct notifier_block *nb)
 {
+	struct net_device *dev;
+	struct net *net;
 	int err;
 
 	rtnl_lock();
 	err = raw_notifier_chain_unregister(&netdev_chain, nb);
+	if (err)
+		goto unlock;
+
+	for_each_net(net) {
+		for_each_netdev(net, dev) {
+			if (dev->flags & IFF_UP) {
+				nb->notifier_call(nb, NETDEV_GOING_DOWN, dev);
+				nb->notifier_call(nb, NETDEV_DOWN, dev);
+			}
+			nb->notifier_call(nb, NETDEV_UNREGISTER, dev);
+			nb->notifier_call(nb, NETDEV_UNREGISTER_BATCH, dev);
+		}
+	}
+unlock:
 	rtnl_unlock();
 	return err;
 }
@@ -1587,10 +1611,16 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 		kfree_skb(skb);
 		return NET_RX_DROP;
 	}
-	skb_set_dev(skb, dev);
+	skb->dev = dev;
+	skb_dst_drop(skb);
 	skb->tstamp.tv64 = 0;
 	skb->pkt_type = PACKET_HOST;
 	skb->protocol = eth_type_trans(skb, dev);
+	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
+	skb->mark = 0;
+	secpath_reset(skb);
+	nf_reset(skb);
+	nf_reset_trace(skb);
 	return netif_rx(skb);
 }
 EXPORT_SYMBOL_GPL(dev_forward_skb);
@@ -1603,6 +1633,19 @@ static inline int deliver_skb(struct sk_buff *skb,
 	return pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
 }
 
+static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb)
+{
+	if (!ptype->af_packet_priv || !skb->sk)
+		return false;
+
+	if (ptype->id_match)
+		return ptype->id_match(ptype, skb->sk);
+	else if ((struct sock *)ptype->af_packet_priv == skb->sk)
+		return true;
+
+	return false;
+}
+
 /*
  *	Support routine. Sends outgoing frames to any network
  *	taps currently in use.
@@ -1620,8 +1663,7 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
 		 * they originated from - MvS (miquels@drinkel.ow.org)
 		 */
 		if ((ptype->dev == dev || !ptype->dev) &&
-		    (ptype->af_packet_priv == NULL ||
-		     (struct sock *)ptype->af_packet_priv != skb->sk)) {
+		    (!skb_loop_sk(ptype, skb))) {
 			if (pt_prev) {
 				deliver_skb(skb2, pt_prev, skb->dev);
 				pt_prev = ptype;
@@ -1845,36 +1887,6 @@ void netif_device_attach(struct net_device *dev)
 }
 EXPORT_SYMBOL(netif_device_attach);
 
-/**
- * skb_dev_set -- assign a new device to a buffer
- * @skb: buffer for the new device
- * @dev: network device
- *
- * If an skb is owned by a device already, we have to reset
- * all data private to the namespace a device belongs to
- * before assigning it a new device.
- */
-#ifdef CONFIG_NET_NS
-void skb_set_dev(struct sk_buff *skb, struct net_device *dev)
-{
-	skb_dst_drop(skb);
-	if (skb->dev && !net_eq(dev_net(skb->dev), dev_net(dev))) {
-		secpath_reset(skb);
-		nf_reset(skb);
-		skb_init_secmark(skb);
-		skb->mark = 0;
-		skb->priority = 0;
-		skb->nf_trace = 0;
-		skb->ipvs_property = 0;
-#ifdef CONFIG_NET_SCHED
-		skb->tc_index = 0;
-#endif
-	}
-	skb->dev = dev;
-}
-EXPORT_SYMBOL(skb_set_dev);
-#endif /* CONFIG_NET_NS */
-
 /*
  * Invalidate hardware checksum when packet is to be mangled, and
  * complete checksum manually on outgoing path.
@@ -2085,25 +2097,6 @@ static int dev_gso_segment(struct sk_buff *skb, int features)
 	return 0;
 }
 
-/*
- * Try to orphan skb early, right before transmission by the device.
- * We cannot orphan skb if tx timestamp is requested or the sk-reference
- * is needed on driver level for other reasons, e.g. see net/can/raw.c
- */
-static inline void skb_orphan_try(struct sk_buff *skb)
-{
-	struct sock *sk = skb->sk;
-
-	if (sk && !skb_shinfo(skb)->tx_flags) {
-		/* skb_tx_hash() wont be able to get sk.
-		 * We copy sk_hash into skb->rxhash
-		 */
-		if (!skb->rxhash)
-			skb->rxhash = sk->sk_hash;
-		skb_orphan(skb);
-	}
-}
-
 static bool can_checksum_protocol(unsigned long features, __be16 protocol)
 {
 	return ((features & NETIF_F_GEN_CSUM) ||
@@ -2117,7 +2110,8 @@ static bool can_checksum_protocol(unsigned long features, __be16 protocol)
 
 static u32 harmonize_features(struct sk_buff *skb, __be16 protocol, u32 features)
 {
-	if (!can_checksum_protocol(features, protocol)) {
+	if (skb->ip_summed != CHECKSUM_NONE &&
+	    !can_checksum_protocol(features, protocol)) {
 		features &= ~NETIF_F_ALL_CSUM;
 		features &= ~NETIF_F_SG;
 	} else if (illegal_highdma(skb->dev, skb)) {
@@ -2132,11 +2126,16 @@ u32 netif_skb_features(struct sk_buff *skb)
 	__be16 protocol = skb->protocol;
 	u32 features = skb->dev->features;
 
-	if (protocol == htons(ETH_P_8021Q)) {
-		struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
-		protocol = veh->h_vlan_encapsulated_proto;
-	} else if (!vlan_tx_tag_present(skb)) {
-		return harmonize_features(skb, protocol, features);
+	if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs)
+		features &= ~NETIF_F_GSO_MASK;
+
+	if (!vlan_tx_tag_present(skb)) {
+		if (unlikely(protocol == htons(ETH_P_8021Q))) {
+			struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
+			protocol = veh->h_vlan_encapsulated_proto;
+		} else {
+			return harmonize_features(skb, protocol, features);
+		}
 	}
 
 	features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_TX);
@@ -2188,8 +2187,6 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 		if (!list_empty(&ptype_all))
 			dev_queue_xmit_nit(skb, dev);
 
-		skb_orphan_try(skb);
-
 		features = netif_skb_features(skb);
 
 		if (vlan_tx_tag_present(skb) &&
@@ -2299,7 +2296,7 @@ u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb,
 	if (skb->sk && skb->sk->sk_hash)
 		hash = skb->sk->sk_hash;
 	else
-		hash = (__force u16) skb->protocol ^ skb->rxhash;
+		hash = (__force u16) skb->protocol;
 	hash = jhash_1word(hash, hashrnd);
 
 	return (u16) (((u64) hash * qcount) >> 32) + qoffset;
@@ -2615,6 +2612,8 @@ ip:
 			goto done;
 
 		ip = (const struct iphdr *) (skb->data + nhoff);
+		if (ip->ihl < 5)
+			goto done;
 		if (ip_is_fragment(ip))
 			ip_proto = 0;
 		else
@@ -2694,16 +2693,17 @@ ipv6:
 		nhoff += poff;
 		if (pskb_may_pull(skb, nhoff + 4)) {
 			ports.v32 = * (__force u32 *) (skb->data + nhoff);
-			if (ports.v16[1] < ports.v16[0])
-				swap(ports.v16[0], ports.v16[1]);
 			skb->l4_rxhash = 1;
 		}
 	}
 
 	/* get a consistent hash (same value on both flow directions) */
-	if (addr2 < addr1)
+	if (addr2 < addr1 ||
+	    (addr2 == addr1 &&
+	     ports.v16[1] < ports.v16[0])) {
 		swap(addr1, addr2);
-
+		swap(ports.v16[0], ports.v16[1]);
+	}
 	hash = jhash_3words(addr1, addr2, ports.v32, hashrnd);
 	if (!hash)
 		hash = 1;
@@ -2835,8 +2835,10 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		if (unlikely(tcpu != next_cpu) &&
 		    (tcpu == RPS_NO_CPU || !cpu_online(tcpu) ||
 		     ((int)(per_cpu(softnet_data, tcpu).input_queue_head -
-		      rflow->last_qtail)) >= 0))
+		      rflow->last_qtail)) >= 0)) {
+			tcpu = next_cpu;
 			rflow = set_rps_cpu(dev, skb, rflow, next_cpu);
+		}
 
 		if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) {
 			*rflowp = rflow;
@@ -3197,6 +3199,7 @@ int netdev_rx_handler_register(struct net_device *dev,
 	if (dev->rx_handler)
 		return -EBUSY;
 
+	/* Note: rx_handler_data must be set before rx_handler */
 	rcu_assign_pointer(dev->rx_handler_data, rx_handler_data);
 	rcu_assign_pointer(dev->rx_handler, rx_handler);
 
@@ -3217,6 +3220,11 @@ void netdev_rx_handler_unregister(struct net_device *dev)
 
 	ASSERT_RTNL();
 	RCU_INIT_POINTER(dev->rx_handler, NULL);
+	/* a reader seeing a non NULL rx_handler in a rcu_read_lock()
+	 * section has a guarantee to see a non NULL rx_handler_data
+	 * as well.
+	 */
+	synchronize_net();
 	RCU_INIT_POINTER(dev->rx_handler_data, NULL);
 }
 EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister);
@@ -3284,18 +3292,18 @@ another_round:
 ncls:
 #endif
 
-	rx_handler = rcu_dereference(skb->dev->rx_handler);
 	if (vlan_tx_tag_present(skb)) {
 		if (pt_prev) {
 			ret = deliver_skb(skb, pt_prev, orig_dev);
 			pt_prev = NULL;
 		}
-		if (vlan_do_receive(&skb, !rx_handler))
+		if (vlan_do_receive(&skb))
 			goto another_round;
 		else if (unlikely(!skb))
 			goto out;
 	}
 
+	rx_handler = rcu_dereference(skb->dev->rx_handler);
 	if (rx_handler) {
 		if (pt_prev) {
 			ret = deliver_skb(skb, pt_prev, orig_dev);
@@ -3303,6 +3311,7 @@ ncls:
 		}
 		switch (rx_handler(&skb)) {
 		case RX_HANDLER_CONSUMED:
+			ret = NET_RX_SUCCESS;
 			goto out;
 		case RX_HANDLER_ANOTHER:
 			goto another_round;
@@ -3315,6 +3324,9 @@ ncls:
 		}
 	}
 
+	if (vlan_tx_nonzero_tag_present(skb))
+		skb->pkt_type = PACKET_OTHERHOST;
+
 	/* deliver only exact match when indicated */
 	null_or_dev = deliver_exact ? skb->dev : NULL;
 
@@ -3565,14 +3577,20 @@ static inline gro_result_t
 __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
 	struct sk_buff *p;
+	unsigned int maclen = skb->dev->hard_header_len;
 
 	for (p = napi->gro_list; p; p = p->next) {
 		unsigned long diffs;
 
 		diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev;
 		diffs |= p->vlan_tci ^ skb->vlan_tci;
-		diffs |= compare_ether_header(skb_mac_header(p),
-					      skb_gro_mac_header(skb));
+		if (maclen == ETH_HLEN)
+			diffs |= compare_ether_header(skb_mac_header(p),
+						      skb_gro_mac_header(skb));
+		else if (!diffs)
+			diffs = memcmp(skb_mac_header(p),
+				       skb_gro_mac_header(skb),
+				       maclen);
 		NAPI_GRO_CB(p)->same_flow = !diffs;
 		NAPI_GRO_CB(p)->flush = 0;
 	}
@@ -3628,10 +3646,12 @@ EXPORT_SYMBOL(napi_gro_receive);
 static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
 {
 	__skb_pull(skb, skb_headlen(skb));
-	skb_reserve(skb, NET_IP_ALIGN - skb_headroom(skb));
+	/* restore the reserve we had after netdev_alloc_skb_ip_align() */
+	skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN - skb_headroom(skb));
 	skb->vlan_tci = 0;
 	skb->dev = napi->dev;
 	skb->skb_iif = 0;
+	skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
 
 	napi->skb = skb;
 }
@@ -4095,54 +4115,41 @@ static int dev_ifconf(struct net *net, char __user *arg)
 
 #ifdef CONFIG_PROC_FS
 
-#define BUCKET_SPACE (32 - NETDEV_HASHBITS)
-
-struct dev_iter_state {
-	struct seq_net_private p;
-	unsigned int pos; /* bucket << BUCKET_SPACE + offset */
-};
+#define BUCKET_SPACE (32 - NETDEV_HASHBITS - 1)
 
 #define get_bucket(x) ((x) >> BUCKET_SPACE)
 #define get_offset(x) ((x) & ((1 << BUCKET_SPACE) - 1))
 #define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o))
 
-static inline struct net_device *dev_from_same_bucket(struct seq_file *seq)
+static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff_t *pos)
 {
-	struct dev_iter_state *state = seq->private;
 	struct net *net = seq_file_net(seq);
 	struct net_device *dev;
 	struct hlist_node *p;
 	struct hlist_head *h;
-	unsigned int count, bucket, offset;
+	unsigned int count = 0, offset = get_offset(*pos);
 
-	bucket = get_bucket(state->pos);
-	offset = get_offset(state->pos);
-	h = &net->dev_name_head[bucket];
-	count = 0;
+	h = &net->dev_name_head[get_bucket(*pos)];
 	hlist_for_each_entry_rcu(dev, p, h, name_hlist) {
-		if (count++ == offset) {
-			state->pos = set_bucket_offset(bucket, count);
+		if (++count == offset)
 			return dev;
-		}
 	}
 
 	return NULL;
 }
 
-static inline struct net_device *dev_from_new_bucket(struct seq_file *seq)
+static inline struct net_device *dev_from_bucket(struct seq_file *seq, loff_t *pos)
 {
-	struct dev_iter_state *state = seq->private;
 	struct net_device *dev;
 	unsigned int bucket;
 
-	bucket = get_bucket(state->pos);
 	do {
-		dev = dev_from_same_bucket(seq);
+		dev = dev_from_same_bucket(seq, pos);
 		if (dev)
 			return dev;
 
-		bucket++;
-		state->pos = set_bucket_offset(bucket, 0);
+		bucket = get_bucket(*pos) + 1;
+		*pos = set_bucket_offset(bucket, 1);
 	} while (bucket < NETDEV_HASHENTRIES);
 
 	return NULL;
@@ -4155,33 +4162,20 @@ static inline struct net_device *dev_from_new_bucket(struct seq_file *seq)
 void *dev_seq_start(struct seq_file *seq, loff_t *pos)
 	__acquires(RCU)
 {
-	struct dev_iter_state *state = seq->private;
-
 	rcu_read_lock();
 	if (!*pos)
 		return SEQ_START_TOKEN;
 
-	/* check for end of the hash */
-	if (state->pos == 0 && *pos > 1)
+	if (get_bucket(*pos) >= NETDEV_HASHENTRIES)
 		return NULL;
 
-	return dev_from_new_bucket(seq);
+	return dev_from_bucket(seq, pos);
 }
 
 void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
-	struct net_device *dev;
-
 	++*pos;
-
-	if (v == SEQ_START_TOKEN)
-		return dev_from_new_bucket(seq);
-
-	dev = dev_from_same_bucket(seq);
-	if (dev)
-		return dev;
-
-	return dev_from_new_bucket(seq);
+	return dev_from_bucket(seq, pos);
 }
 
 void dev_seq_stop(struct seq_file *seq, void *v)
@@ -4280,13 +4274,7 @@ static const struct seq_operations dev_seq_ops = {
 static int dev_seq_open(struct inode *inode, struct file *file)
 {
 	return seq_open_net(inode, file, &dev_seq_ops,
-			    sizeof(struct dev_iter_state));
-}
-
-int dev_seq_open_ops(struct inode *inode, struct file *file,
-		     const struct seq_operations *ops)
-{
-	return seq_open_net(inode, file, ops, sizeof(struct dev_iter_state));
+			    sizeof(struct seq_net_private));
 }
 
 static const struct file_operations dev_seq_fops = {
@@ -4533,7 +4521,7 @@ static void dev_change_rx_flags(struct net_device *dev, int flags)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 
-	if ((dev->flags & IFF_UP) && ops->ndo_change_rx_flags)
+	if (ops->ndo_change_rx_flags)
 		ops->ndo_change_rx_flags(dev, flags);
 }
 
@@ -4893,6 +4881,7 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa)
 	err = ops->ndo_set_mac_address(dev, sa);
 	if (!err)
 		call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
+	add_device_randomness(dev->dev_addr, dev->addr_len);
 	return err;
 }
 EXPORT_SYMBOL(dev_set_mac_address);
@@ -5673,6 +5662,7 @@ int register_netdevice(struct net_device *dev)
 	dev_init_scheduler(dev);
 	dev_hold(dev);
 	list_netdevice(dev);
+	add_device_randomness(dev->dev_addr, dev->addr_len);
 
 	/* Notify protocols, that a new device appeared. */
 	ret = call_netdevice_notifiers(NETDEV_REGISTER, dev);
@@ -6039,6 +6029,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	dev_net_set(dev, &init_net);
 
 	dev->gso_max_size = GSO_MAX_SIZE;
+	dev->gso_max_segs = GSO_MAX_SEGS;
 
 	INIT_LIST_HEAD(&dev->napi_list);
 	INIT_LIST_HEAD(&dev->unreg_list);
@@ -6347,10 +6338,20 @@ static int dev_cpu_callback(struct notifier_block *nfb,
 		oldsd->output_queue = NULL;
 		oldsd->output_queue_tailp = &oldsd->output_queue;
 	}
-	/* Append NAPI poll list from offline CPU. */
-	if (!list_empty(&oldsd->poll_list)) {
-		list_splice_init(&oldsd->poll_list, &sd->poll_list);
-		raise_softirq_irqoff(NET_RX_SOFTIRQ);
+	/* Append NAPI poll list from offline CPU, with one exception :
+	 * process_backlog() must be called by cpu owning percpu backlog.
+	 * We properly handle process_queue & input_pkt_queue later.
+	 */
+	while (!list_empty(&oldsd->poll_list)) {
+		struct napi_struct *napi = list_first_entry(&oldsd->poll_list,
+							    struct napi_struct,
+							    poll_list);
+
+		list_del_init(&napi->poll_list);
+		if (napi->poll == process_backlog)
+			napi->state = 0;
+		else
+			____napi_schedule(sd, napi);
 	}
 
 	raise_softirq_irqoff(NET_TX_SOFTIRQ);
@@ -6361,7 +6362,7 @@ static int dev_cpu_callback(struct notifier_block *nfb,
 		netif_rx(skb);
 		input_queue_head_incr(oldsd);
 	}
-	while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) {
+	while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) {
 		netif_rx(skb);
 		input_queue_head_incr(oldsd);
 	}
@@ -6417,7 +6418,8 @@ static struct hlist_head *netdev_create_hash(void)
 /* Initialize per network namespace state */
 static int __net_init netdev_init(struct net *net)
 {
-	INIT_LIST_HEAD(&net->dev_base_head);
+	if (net != &init_net)
+		INIT_LIST_HEAD(&net->dev_base_head);
 
 	net->dev_name_head = netdev_create_hash();
 	if (net->dev_name_head == NULL)