Merge remote-tracking branch 'stable/linux-4.4.y' into rpi-4.4.y

justinasjaronis · Feb 20, 2017 · e223d71 · e223d71
2 parents 8d1dd63 + c50b74d
commit e223d71
Show file tree

Hide file tree

Showing 29 changed files with 172 additions and 89 deletions.
diff --git a/Makefile b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 4
-SUBLEVEL = 49
+SUBLEVEL = 50
 EXTRAVERSION =
 NAME = Blurry Fish Butt
 

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -502,8 +502,11 @@ void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv)
 		return;
 
 	for (ring = 0; ring < priv->rx_ring_num; ring++) {
-		if (mlx4_en_is_ring_empty(priv->rx_ring[ring]))
+		if (mlx4_en_is_ring_empty(priv->rx_ring[ring])) {
+			local_bh_disable();
 			napi_reschedule(&priv->rx_cq[ring]->napi);
+			local_bh_enable();
+		}
 	}
 }
 

diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
@@ -164,6 +164,7 @@ static void loopback_setup(struct net_device *dev)
 {
 	dev->mtu		= 64 * 1024;
 	dev->hard_header_len	= ETH_HLEN;	/* 14	*/
+	dev->min_header_len	= ETH_HLEN;	/* 14	*/
 	dev->addr_len		= ETH_ALEN;	/* 6	*/
 	dev->type		= ARPHRD_LOOPBACK;	/* 0x0001*/
 	dev->flags		= IFF_LOOPBACK;

diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
@@ -725,7 +725,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 	ssize_t n;
 
 	if (q->flags & IFF_VNET_HDR) {
-		vnet_hdr_len = q->vnet_hdr_sz;
+		vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
 
 		err = -EINVAL;
 		if (len < vnet_hdr_len)
@@ -865,7 +865,7 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
 
 	if (q->flags & IFF_VNET_HDR) {
 		struct virtio_net_hdr vnet_hdr;
-		vnet_hdr_len = q->vnet_hdr_sz;
+		vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
 		if (iov_iter_count(iter) < vnet_hdr_len)
 			return -EINVAL;
 

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
@@ -1108,9 +1108,11 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	}
 
 	if (tun->flags & IFF_VNET_HDR) {
-		if (len < tun->vnet_hdr_sz)
+		int vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz);
+
+		if (len < vnet_hdr_sz)
 			return -EINVAL;
-		len -= tun->vnet_hdr_sz;
+		len -= vnet_hdr_sz;
 
 		n = copy_from_iter(&gso, sizeof(gso), from);
 		if (n != sizeof(gso))
@@ -1122,7 +1124,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 
 		if (tun16_to_cpu(tun, gso.hdr_len) > len)
 			return -EINVAL;
-		iov_iter_advance(from, tun->vnet_hdr_sz - sizeof(gso));
+		iov_iter_advance(from, vnet_hdr_sz - sizeof(gso));
 	}
 
 	if ((tun->flags & TUN_TYPE_MASK) == IFF_TAP) {
@@ -1301,7 +1303,7 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 		vlan_hlen = VLAN_HLEN;
 
 	if (tun->flags & IFF_VNET_HDR)
-		vnet_hdr_sz = tun->vnet_hdr_sz;
+		vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz);
 
 	total = skb->len + vlan_hlen + vnet_hdr_sz;
 

diff --git a/include/linux/can/core.h b/include/linux/can/core.h
@@ -45,10 +45,9 @@ struct can_proto {
 extern int  can_proto_register(const struct can_proto *cp);
 extern void can_proto_unregister(const struct can_proto *cp);
 
-extern int  can_rx_register(struct net_device *dev, canid_t can_id,
-			    canid_t mask,
-			    void (*func)(struct sk_buff *, void *),
-			    void *data, char *ident);
+int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
+		    void (*func)(struct sk_buff *, void *),
+		    void *data, char *ident, struct sock *sk);
 
 extern void can_rx_unregister(struct net_device *dev, canid_t can_id,
 			      canid_t mask,

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
@@ -1399,6 +1399,7 @@ enum netdev_priv_flags {
  *	@mtu:		Interface MTU value
  *	@type:		Interface hardware type
  *	@hard_header_len: Maximum hardware header length.
+ *	@min_header_len:  Minimum hardware header length
  *
  *	@needed_headroom: Extra headroom the hardware may need, but not in all
  *			  cases can this be guaranteed
@@ -1619,6 +1620,7 @@ struct net_device {
 	unsigned int		mtu;
 	unsigned short		type;
 	unsigned short		hard_header_len;
+	unsigned short		min_header_len;
 
 	unsigned short		needed_headroom;
 	unsigned short		needed_tailroom;
@@ -2541,6 +2543,8 @@ static inline bool dev_validate_header(const struct net_device *dev,
 {
 	if (likely(len >= dev->hard_header_len))
 		return true;
+	if (len < dev->min_header_len)
+		return false;
 
 	if (capable(CAP_SYS_RAWIO)) {
 		memset(ll_header + len, 0, dev->hard_header_len - len);

diff --git a/include/net/cipso_ipv4.h b/include/net/cipso_ipv4.h
@@ -309,6 +309,10 @@ static inline int cipso_v4_validate(const struct sk_buff *skb,
 	}
 
 	for (opt_iter = 6; opt_iter < opt_len;) {
+		if (opt_iter + 1 == opt_len) {
+			err_offset = opt_iter;
+			goto out;
+		}
 		tag_len = opt[opt_iter + 1];
 		if ((tag_len == 0) || (tag_len > (opt_len - opt_iter))) {
 			err_offset = opt_iter + 1;

diff --git a/net/can/af_can.c b/net/can/af_can.c
@@ -445,6 +445,7 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask,
  * @func: callback function on filter match
  * @data: returned parameter for callback function
  * @ident: string for calling module identification
+ * @sk: socket pointer (might be NULL)
  *
  * Description:
  *  Invokes the callback function with the received sk_buff and the given
@@ -468,7 +469,7 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask,
  */
 int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
 		    void (*func)(struct sk_buff *, void *), void *data,
-		    char *ident)
+		    char *ident, struct sock *sk)
 {
 	struct receiver *r;
 	struct hlist_head *rl;
@@ -496,6 +497,7 @@ int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
 		r->func    = func;
 		r->data    = data;
 		r->ident   = ident;
+		r->sk      = sk;
 
 		hlist_add_head_rcu(&r->list, rl);
 		d->entries++;
@@ -520,8 +522,11 @@ EXPORT_SYMBOL(can_rx_register);
 static void can_rx_delete_receiver(struct rcu_head *rp)
 {
 	struct receiver *r = container_of(rp, struct receiver, rcu);
+	struct sock *sk = r->sk;
 
 	kmem_cache_free(rcv_cache, r);
+	if (sk)
+		sock_put(sk);
 }
 
 /**
@@ -596,8 +601,11 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask,
 	spin_unlock(&can_rcvlists_lock);
 
 	/* schedule the receiver item for deletion */
-	if (r)
+	if (r) {
+		if (r->sk)
+			sock_hold(r->sk);
 		call_rcu(&r->rcu, can_rx_delete_receiver);
+	}
 }
 EXPORT_SYMBOL(can_rx_unregister);
 

diff --git a/net/can/af_can.h b/net/can/af_can.h
@@ -50,13 +50,14 @@
 
 struct receiver {
 	struct hlist_node list;
-	struct rcu_head rcu;
 	canid_t can_id;
 	canid_t mask;
 	unsigned long matches;
 	void (*func)(struct sk_buff *, void *);
 	void *data;
 	char *ident;
+	struct sock *sk;
+	struct rcu_head rcu;
 };
 
 #define CAN_SFF_RCV_ARRAY_SZ (1 << CAN_SFF_ID_BITS)

diff --git a/net/can/bcm.c b/net/can/bcm.c
@@ -1179,7 +1179,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 				err = can_rx_register(dev, op->can_id,
 						      REGMASK(op->can_id),
 						      bcm_rx_handler, op,
-						      "bcm");
+						      "bcm", sk);
 
 				op->rx_reg_dev = dev;
 				dev_put(dev);
@@ -1188,7 +1188,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		} else
 			err = can_rx_register(NULL, op->can_id,
 					      REGMASK(op->can_id),
-					      bcm_rx_handler, op, "bcm");
+					      bcm_rx_handler, op, "bcm", sk);
 		if (err) {
 			/* this bcm rx op is broken -> remove it */
 			list_del(&op->list);

diff --git a/net/can/gw.c b/net/can/gw.c
@@ -442,7 +442,7 @@ static inline int cgw_register_filter(struct cgw_job *gwj)
 {
 	return can_rx_register(gwj->src.dev, gwj->ccgw.filter.can_id,
 			       gwj->ccgw.filter.can_mask, can_can_gw_rcv,
-			       gwj, "gw");
+			       gwj, "gw", NULL);
 }
 
 static inline void cgw_unregister_filter(struct cgw_job *gwj)

diff --git a/net/can/raw.c b/net/can/raw.c
@@ -190,7 +190,7 @@ static int raw_enable_filters(struct net_device *dev, struct sock *sk,
 	for (i = 0; i < count; i++) {
 		err = can_rx_register(dev, filter[i].can_id,
 				      filter[i].can_mask,
-				      raw_rcv, sk, "raw");
+				      raw_rcv, sk, "raw", sk);
 		if (err) {
 			/* clean up successfully registered filters */
 			while (--i >= 0)
@@ -211,7 +211,7 @@ static int raw_enable_errfilter(struct net_device *dev, struct sock *sk,
 
 	if (err_mask)
 		err = can_rx_register(dev, 0, err_mask | CAN_ERR_FLAG,
-				      raw_rcv, sk, "raw");
+				      raw_rcv, sk, "raw", sk);
 
 	return err;
 }

diff --git a/net/core/dev.c b/net/core/dev.c
@@ -1676,37 +1676,32 @@ EXPORT_SYMBOL_GPL(net_dec_ingress_queue);
 
 static struct static_key netstamp_needed __read_mostly;
 #ifdef HAVE_JUMP_LABEL
-/* We are not allowed to call static_key_slow_dec() from irq context
- * If net_disable_timestamp() is called from irq context, defer the
- * static_key_slow_dec() calls.
- */
 static atomic_t netstamp_needed_deferred;
-#endif
-
-void net_enable_timestamp(void)
+static void netstamp_clear(struct work_struct *work)
 {
-#ifdef HAVE_JUMP_LABEL
 	int deferred = atomic_xchg(&netstamp_needed_deferred, 0);
 
-	if (deferred) {
-		while (--deferred)
-			static_key_slow_dec(&netstamp_needed);
-		return;
-	}
+	while (deferred--)
+		static_key_slow_dec(&netstamp_needed);
+}
+static DECLARE_WORK(netstamp_work, netstamp_clear);
 #endif
+
+void net_enable_timestamp(void)
+{
 	static_key_slow_inc(&netstamp_needed);
 }
 EXPORT_SYMBOL(net_enable_timestamp);
 
 void net_disable_timestamp(void)
 {
 #ifdef HAVE_JUMP_LABEL
-	if (in_interrupt()) {
-		atomic_inc(&netstamp_needed_deferred);
-		return;
-	}
-#endif
+	/* net_disable_timestamp() can be called from non process context */
+	atomic_inc(&netstamp_needed_deferred);
+	schedule_work(&netstamp_work);
+#else
 	static_key_slow_dec(&netstamp_needed);
+#endif
 }
 EXPORT_SYMBOL(net_disable_timestamp);
 

diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
@@ -353,6 +353,7 @@ void ether_setup(struct net_device *dev)
 	dev->header_ops		= &eth_header_ops;
 	dev->type		= ARPHRD_ETHER;
 	dev->hard_header_len 	= ETH_HLEN;
+	dev->min_header_len	= ETH_HLEN;
 	dev->mtu		= ETH_DATA_LEN;
 	dev->addr_len		= ETH_ALEN;
 	dev->tx_queue_len	= 1000;	/* Ethernet wants good queues */

diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
@@ -1657,6 +1657,10 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option)
 				goto validate_return_locked;
 			}
 
+		if (opt_iter + 1 == opt_len) {
+			err_offset = opt_iter;
+			goto validate_return_locked;
+		}
 		tag_len = tag[1];
 		if (tag_len > (opt_len - opt_iter)) {
 			err_offset = opt_iter + 1;

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
@@ -1192,7 +1192,14 @@ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb)
 		pktinfo->ipi_ifindex = 0;
 		pktinfo->ipi_spec_dst.s_addr = 0;
 	}
-	skb_dst_drop(skb);
+	/* We need to keep the dst for __ip_options_echo()
+	 * We could restrict the test to opt.ts_needtime || opt.srr,
+	 * but the following is good enough as IP options are not often used.
+	 */
+	if (unlikely(IPCB(skb)->opt.optlen))
+		skb_dst_force(skb);
+	else
+		skb_dst_drop(skb);
 }
 
 int ip_setsockopt(struct sock *sk, int level,

diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
@@ -645,6 +645,8 @@ static int ping_v4_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh,
 {
 	struct sk_buff *skb = skb_peek(&sk->sk_write_queue);
 
+	if (!skb)
+		return 0;
 	pfh->wcheck = csum_partial((char *)&pfh->icmph,
 		sizeof(struct icmphdr), pfh->wcheck);
 	pfh->icmph.checksum = csum_fold(pfh->wcheck);

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
@@ -783,6 +783,12 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
 				ret = -EAGAIN;
 				break;
 			}
+			/* if __tcp_splice_read() got nothing while we have
+			 * an skb in receive queue, we do not want to loop.
+			 * This might happen with URG data.
+			 */
+			if (!skb_queue_empty(&sk->sk_receive_queue))
+				break;
 			sk_wait_data(sk, &timeo, NULL);
 			if (signal_pending(current)) {
 				ret = sock_intr_errno(timeo);

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
@@ -2383,9 +2383,11 @@ u32 __tcp_select_window(struct sock *sk)
 	int full_space = min_t(int, tp->window_clamp, allowed_space);
 	int window;
 
-	if (mss > full_space)
+	if (unlikely(mss > full_space)) {
 		mss = full_space;
-
+		if (mss <= 0)
+			return 0;
+	}
 	if (free_space < (full_space >> 1)) {
 		icsk->icsk_ack.quick = 0;