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: (22 commits)
  netlink: bug fix: wrong size was calculated for vfinfo list blob
  netlink: bug fix: don't overrun skbs on vf_port dump
  xt_tee: use skb_dst_drop()
  netdev/fec: fix ifconfig eth0 down hang issue
  cnic: Fix context memory init. on 5709.
  drivers/net: Eliminate a NULL pointer dereference
  drivers/net/hamradio: Eliminate a NULL pointer dereference
  be2net: Patch removes redundant while statement in loop.
  ipv6: Add GSO support on forwarding path
  net: fix __neigh_event_send()
  vhost: fix the memory leak which will happen when memory_access_ok fails
  vhost-net: fix to check the return value of copy_to/from_user() correctly
  vhost: fix to check the return value of copy_to/from_user() correctly
  vhost: Fix host panic if ioctl called with wrong index
  net: fix lock_sock_bh/unlock_sock_bh
  net/iucv: Add missing spin_unlock
  net: ll_temac: fix checksum offload logic
  net: ll_temac: fix interrupt bug when interrupt 0 is used
  sctp: dubious bitfields in sctp_transport
  ipmr: off by one in __ipmr_fill_mroute()
  ...

drivers/net/3c507.c

@@ -551,8 +551,7 @@ static irqreturn_t el16_interrupt(int irq, void *dev_id)
 	void __iomem *shmem;
 
 	if (dev == NULL) {
-		pr_err("%s: net_interrupt(): irq %d for unknown device.\n",
-			dev->name, irq);
+		pr_err("net_interrupt(): irq %d for unknown device.\n", irq);
 		return IRQ_NONE;
 	}
 

drivers/net/benet/be_cmds.c

@@ -294,7 +294,7 @@ int be_cmd_POST(struct be_adapter *adapter)
 		} else {
 			return 0;
 		}
-	} while (timeout < 20);
+	} while (timeout < 40);
 
 	dev_err(&adapter->pdev->dev, "POST timeout; stage=0x%x\n", stage);
 	return -1;

drivers/net/benet/be_main.c

@@ -1861,7 +1861,7 @@ static int be_setup(struct be_adapter *adapter)
 				goto if_destroy;
 			}
 			vf++;
-		} while (vf < num_vfs);
+		}
 	} else if (!be_physfn(adapter)) {
 		status = be_cmd_mac_addr_query(adapter, mac,
 			MAC_ADDRESS_TYPE_NETWORK, false, adapter->if_handle);

drivers/net/cnic.c

@@ -3367,13 +3367,9 @@ static int cnic_cm_shutdown(struct cnic_dev *dev)
 
 static void cnic_init_context(struct cnic_dev *dev, u32 cid)
 {
-	struct cnic_local *cp = dev->cnic_priv;
 	u32 cid_addr;
 	int i;
 
-	if (CHIP_NUM(cp) == CHIP_NUM_5709)
-		return;
-
 	cid_addr = GET_CID_ADDR(cid);
 
 	for (i = 0; i < CTX_SIZE; i += 4)
@@ -3530,14 +3526,11 @@ static void cnic_init_bnx2_tx_ring(struct cnic_dev *dev)
 
 	sb_id = cp->status_blk_num;
 	tx_cid = 20;
-	cnic_init_context(dev, tx_cid);
-	cnic_init_context(dev, tx_cid + 1);
 	cp->tx_cons_ptr = &s_blk->status_tx_quick_consumer_index2;
 	if (ethdev->drv_state & CNIC_DRV_STATE_USING_MSIX) {
 		struct status_block_msix *sblk = cp->status_blk.bnx2;
 
 		tx_cid = TX_TSS_CID + sb_id - 1;
-		cnic_init_context(dev, tx_cid);
 		CNIC_WR(dev, BNX2_TSCH_TSS_CFG, (sb_id << 24) |
 			(TX_TSS_CID << 7));
 		cp->tx_cons_ptr = &sblk->status_tx_quick_consumer_index;
@@ -3556,6 +3549,9 @@ static void cnic_init_bnx2_tx_ring(struct cnic_dev *dev)
 		offset2 = BNX2_L2CTX_TBDR_BHADDR_HI_XI;
 		offset3 = BNX2_L2CTX_TBDR_BHADDR_LO_XI;
 	} else {
+		cnic_init_context(dev, tx_cid);
+		cnic_init_context(dev, tx_cid + 1);
+
 		offset0 = BNX2_L2CTX_TYPE;
 		offset1 = BNX2_L2CTX_CMD_TYPE;
 		offset2 = BNX2_L2CTX_TBDR_BHADDR_HI;

drivers/net/cnic_if.h

@@ -12,8 +12,8 @@
 #ifndef CNIC_IF_H
 #define CNIC_IF_H
 
-#define CNIC_MODULE_VERSION	"2.1.1"
-#define CNIC_MODULE_RELDATE	"Feb 22, 2010"
+#define CNIC_MODULE_VERSION	"2.1.2"
+#define CNIC_MODULE_RELDATE	"May 26, 2010"
 
 #define CNIC_ULP_RDMA		0
 #define CNIC_ULP_ISCSI		1

drivers/net/fec.c

@@ -681,6 +681,8 @@ static int fec_enet_mii_probe(struct net_device *dev)
 	struct phy_device *phy_dev = NULL;
 	int phy_addr;
 
+	fep->phy_dev = NULL;
+
 	/* find the first phy */
 	for (phy_addr = 0; phy_addr < PHY_MAX_ADDR; phy_addr++) {
 		if (fep->mii_bus->phy_map[phy_addr]) {
@@ -711,6 +713,11 @@ static int fec_enet_mii_probe(struct net_device *dev)
 	fep->link = 0;
 	fep->full_duplex = 0;
 
+	printk(KERN_INFO "%s: Freescale FEC PHY driver [%s] "
+		"(mii_bus:phy_addr=%s, irq=%d)\n", dev->name,
+		fep->phy_dev->drv->name, dev_name(&fep->phy_dev->dev),
+		fep->phy_dev->irq);
+
 	return 0;
 }
 
@@ -756,13 +763,8 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 	if (mdiobus_register(fep->mii_bus))
 		goto err_out_free_mdio_irq;
 
-	if (fec_enet_mii_probe(dev) != 0)
-		goto err_out_unregister_bus;
-
 	return 0;
 
-err_out_unregister_bus:
-	mdiobus_unregister(fep->mii_bus);
 err_out_free_mdio_irq:
 	kfree(fep->mii_bus->irq);
 err_out_free_mdiobus:
@@ -915,7 +917,12 @@ fec_enet_open(struct net_device *dev)
 	if (ret)
 		return ret;
 
-	/* schedule a link state check */
+	/* Probe and connect to PHY when open the interface */
+	ret = fec_enet_mii_probe(dev);
+	if (ret) {
+		fec_enet_free_buffers(dev);
+		return ret;
+	}
 	phy_start(fep->phy_dev);
 	netif_start_queue(dev);
 	fep->opened = 1;
@@ -929,10 +936,12 @@ fec_enet_close(struct net_device *dev)
 
 	/* Don't know what to do yet. */
 	fep->opened = 0;
-	phy_stop(fep->phy_dev);
 	netif_stop_queue(dev);
 	fec_stop(dev);
 
+	if (fep->phy_dev)
+		phy_disconnect(fep->phy_dev);
+
         fec_enet_free_buffers(dev);
 
 	return 0;
@@ -1316,11 +1325,6 @@ fec_probe(struct platform_device *pdev)
 	if (ret)
 		goto failed_register;
 
-	printk(KERN_INFO "%s: Freescale FEC PHY driver [%s] "
-		"(mii_bus:phy_addr=%s, irq=%d)\n", ndev->name,
-		fep->phy_dev->drv->name, dev_name(&fep->phy_dev->dev),
-		fep->phy_dev->irq);
-
 	return 0;
 
 failed_register:

drivers/net/hamradio/yam.c

@@ -1151,8 +1151,7 @@ static int __init yam_init_driver(void)
 		dev = alloc_netdev(sizeof(struct yam_port), name,
 				   yam_setup);
 		if (!dev) {
-			printk(KERN_ERR "yam: cannot allocate net device %s\n",
-			       dev->name);
+			pr_err("yam: cannot allocate net device\n");
 			err = -ENOMEM;
 			goto error;
 		}

drivers/net/ll_temac.h

@@ -295,6 +295,10 @@ This option defaults to enabled (set) */
 
 #define MULTICAST_CAM_TABLE_NUM 4
 
+/* TEMAC Synthesis features */
+#define TEMAC_FEATURE_RX_CSUM  (1 << 0)
+#define TEMAC_FEATURE_TX_CSUM  (1 << 1)
+
 /* TX/RX CURDESC_PTR points to first descriptor */
 /* TX/RX TAILDESC_PTR points to last descriptor in linked list */
 
@@ -353,6 +357,7 @@ struct temac_local {
 	struct mutex indirect_mutex;
 	u32 options;			/* Current options word */
 	int last_link;
+	unsigned int temac_features;
 
 	/* Buffer descriptors */
 	struct cdmac_bd *tx_bd_v;

drivers/net/ll_temac_main.c

@@ -245,7 +245,7 @@ static int temac_dma_bd_init(struct net_device *ndev)
 					  CHNL_CTRL_IRQ_COAL_EN);
 	/* 0x10220483 */
 	/* 0x00100483 */
-	lp->dma_out(lp, RX_CHNL_CTRL, 0xff010000 |
+	lp->dma_out(lp, RX_CHNL_CTRL, 0xff070000 |
 					  CHNL_CTRL_IRQ_EN |
 					  CHNL_CTRL_IRQ_DLY_EN |
 					  CHNL_CTRL_IRQ_COAL_EN |
@@ -574,6 +574,10 @@ static void temac_start_xmit_done(struct net_device *ndev)
 		if (cur_p->app4)
 			dev_kfree_skb_irq((struct sk_buff *)cur_p->app4);
 		cur_p->app0 = 0;
+		cur_p->app1 = 0;
+		cur_p->app2 = 0;
+		cur_p->app3 = 0;
+		cur_p->app4 = 0;
 
 		ndev->stats.tx_packets++;
 		ndev->stats.tx_bytes += cur_p->len;
@@ -589,6 +593,29 @@ static void temac_start_xmit_done(struct net_device *ndev)
 	netif_wake_queue(ndev);
 }
 
+static inline int temac_check_tx_bd_space(struct temac_local *lp, int num_frag)
+{
+	struct cdmac_bd *cur_p;
+	int tail;
+
+	tail = lp->tx_bd_tail;
+	cur_p = &lp->tx_bd_v[tail];
+
+	do {
+		if (cur_p->app0)
+			return NETDEV_TX_BUSY;
+
+		tail++;
+		if (tail >= TX_BD_NUM)
+			tail = 0;
+
+		cur_p = &lp->tx_bd_v[tail];
+		num_frag--;
+	} while (num_frag >= 0);
+
+	return 0;
+}
+
 static int temac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 {
 	struct temac_local *lp = netdev_priv(ndev);
@@ -603,7 +630,7 @@ static int temac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	start_p = lp->tx_bd_p + sizeof(*lp->tx_bd_v) * lp->tx_bd_tail;
 	cur_p = &lp->tx_bd_v[lp->tx_bd_tail];
 
-	if (cur_p->app0 & STS_CTRL_APP0_CMPLT) {
+	if (temac_check_tx_bd_space(lp, num_frag)) {
 		if (!netif_queue_stopped(ndev)) {
 			netif_stop_queue(ndev);
 			return NETDEV_TX_BUSY;
@@ -613,29 +640,14 @@ static int temac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 
 	cur_p->app0 = 0;
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		const struct iphdr *ip = ip_hdr(skb);
-		int length = 0, start = 0, insert = 0;
-
-		switch (ip->protocol) {
-		case IPPROTO_TCP:
-			start = sizeof(struct iphdr) + ETH_HLEN;
-			insert = sizeof(struct iphdr) + ETH_HLEN + 16;
-			length = ip->tot_len - sizeof(struct iphdr);
-			break;
-		case IPPROTO_UDP:
-			start = sizeof(struct iphdr) + ETH_HLEN;
-			insert = sizeof(struct iphdr) + ETH_HLEN + 6;
-			length = ip->tot_len - sizeof(struct iphdr);
-			break;
-		default:
-			break;
-		}
-		cur_p->app1 = ((start << 16) | insert);
-		cur_p->app2 = csum_tcpudp_magic(ip->saddr, ip->daddr,
-						length, ip->protocol, 0);
-		skb->data[insert] = 0;
-		skb->data[insert + 1] = 0;
+		unsigned int csum_start_off = skb_transport_offset(skb);
+		unsigned int csum_index_off = csum_start_off + skb->csum_offset;
+
+		cur_p->app0 |= 1; /* TX Checksum Enabled */
+		cur_p->app1 = (csum_start_off << 16) | csum_index_off;
+		cur_p->app2 = 0;  /* initial checksum seed */
 	}
+
 	cur_p->app0 |= STS_CTRL_APP0_SOP;
 	cur_p->len = skb_headlen(skb);
 	cur_p->phys = dma_map_single(ndev->dev.parent, skb->data, skb->len,
@@ -699,6 +711,15 @@ static void ll_temac_recv(struct net_device *ndev)
 		skb->protocol = eth_type_trans(skb, ndev);
 		skb->ip_summed = CHECKSUM_NONE;
 
+		/* if we're doing rx csum offload, set it up */
+		if (((lp->temac_features & TEMAC_FEATURE_RX_CSUM) != 0) &&
+			(skb->protocol == __constant_htons(ETH_P_IP)) &&
+			(skb->len > 64)) {
+
+			skb->csum = cur_p->app3 & 0xFFFF;
+			skb->ip_summed = CHECKSUM_COMPLETE;
+		}
+
 		netif_rx(skb);
 
 		ndev->stats.rx_packets++;
@@ -883,6 +904,7 @@ temac_of_probe(struct of_device *op, const struct of_device_id *match)
 	struct temac_local *lp;
 	struct net_device *ndev;
 	const void *addr;
+	__be32 *p;
 	int size, rc = 0;
 
 	/* Init network device structure */
@@ -926,6 +948,18 @@ temac_of_probe(struct of_device *op, const struct of_device_id *match)
 		goto nodev;
 	}
 
+	/* Setup checksum offload, but default to off if not specified */
+	lp->temac_features = 0;
+	p = (__be32 *)of_get_property(op->dev.of_node, "xlnx,txcsum", NULL);
+	if (p && be32_to_cpu(*p)) {
+		lp->temac_features |= TEMAC_FEATURE_TX_CSUM;
+		/* Can checksum TCP/UDP over IPv4. */
+		ndev->features |= NETIF_F_IP_CSUM;
+	}
+	p = (__be32 *)of_get_property(op->dev.of_node, "xlnx,rxcsum", NULL);
+	if (p && be32_to_cpu(*p))
+		lp->temac_features |= TEMAC_FEATURE_RX_CSUM;
+
 	/* Find the DMA node, map the DMA registers, and decode the DMA IRQs */
 	np = of_parse_phandle(op->dev.of_node, "llink-connected", 0);
 	if (!np) {
@@ -950,7 +984,7 @@ temac_of_probe(struct of_device *op, const struct of_device_id *match)
 
 	lp->rx_irq = irq_of_parse_and_map(np, 0);
 	lp->tx_irq = irq_of_parse_and_map(np, 1);
-	if (!lp->rx_irq || !lp->tx_irq) {
+	if ((lp->rx_irq == NO_IRQ) || (lp->tx_irq == NO_IRQ)) {
 		dev_err(&op->dev, "could not determine irqs\n");
 		rc = -ENOMEM;
 		goto nodev;

drivers/vhost/net.c

@@ -593,17 +593,17 @@ static long vhost_net_ioctl(struct file *f, unsigned int ioctl,
 	int r;
 	switch (ioctl) {
 	case VHOST_NET_SET_BACKEND:
-		r = copy_from_user(&backend, argp, sizeof backend);
-		if (r < 0)
-			return r;
+		if (copy_from_user(&backend, argp, sizeof backend))
+			return -EFAULT;
 		return vhost_net_set_backend(n, backend.index, backend.fd);
 	case VHOST_GET_FEATURES:
 		features = VHOST_FEATURES;
-		return copy_to_user(featurep, &features, sizeof features);
+		if (copy_to_user(featurep, &features, sizeof features))
+			return -EFAULT;
+		return 0;
 	case VHOST_SET_FEATURES:
-		r = copy_from_user(&features, featurep, sizeof features);
-		if (r < 0)
-			return r;
+		if (copy_from_user(&features, featurep, sizeof features))
+			return -EFAULT;
 		if (features & ~VHOST_FEATURES)
 			return -EOPNOTSUPP;
 		return vhost_net_set_features(n, features);

drivers/vhost/vhost.c

@@ -320,10 +320,8 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
 {
 	struct vhost_memory mem, *newmem, *oldmem;
 	unsigned long size = offsetof(struct vhost_memory, regions);
-	long r;
-	r = copy_from_user(&mem, m, size);
-	if (r)
-		return r;
+	if (copy_from_user(&mem, m, size))
+		return -EFAULT;
 	if (mem.padding)
 		return -EOPNOTSUPP;
 	if (mem.nregions > VHOST_MEMORY_MAX_NREGIONS)
@@ -333,15 +331,16 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
 		return -ENOMEM;
 
 	memcpy(newmem, &mem, size);
-	r = copy_from_user(newmem->regions, m->regions,
-			   mem.nregions * sizeof *m->regions);
-	if (r) {
+	if (copy_from_user(newmem->regions, m->regions,
+			   mem.nregions * sizeof *m->regions)) {
 		kfree(newmem);
-		return r;
+		return -EFAULT;
 	}
 
-	if (!memory_access_ok(d, newmem, vhost_has_feature(d, VHOST_F_LOG_ALL)))
+	if (!memory_access_ok(d, newmem, vhost_has_feature(d, VHOST_F_LOG_ALL))) {
+		kfree(newmem);
 		return -EFAULT;
+	}
 	oldmem = d->memory;
 	rcu_assign_pointer(d->memory, newmem);
 	synchronize_rcu();
@@ -374,7 +373,7 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
 	r = get_user(idx, idxp);
 	if (r < 0)
 		return r;
-	if (idx > d->nvqs)
+	if (idx >= d->nvqs)
 		return -ENOBUFS;
 
 	vq = d->vqs + idx;
@@ -389,9 +388,10 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
 			r = -EBUSY;
 			break;
 		}
-		r = copy_from_user(&s, argp, sizeof s);
-		if (r < 0)
+		if (copy_from_user(&s, argp, sizeof s)) {
+			r = -EFAULT;
 			break;
+		}
 		if (!s.num || s.num > 0xffff || (s.num & (s.num - 1))) {
 			r = -EINVAL;
 			break;
@@ -405,9 +405,10 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
 			r = -EBUSY;
 			break;
 		}
-		r = copy_from_user(&s, argp, sizeof s);
-		if (r < 0)
+		if (copy_from_user(&s, argp, sizeof s)) {
+			r = -EFAULT;
 			break;
+		}
 		if (s.num > 0xffff) {
 			r = -EINVAL;
 			break;
@@ -419,12 +420,14 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
 	case VHOST_GET_VRING_BASE:
 		s.index = idx;
 		s.num = vq->last_avail_idx;
-		r = copy_to_user(argp, &s, sizeof s);
+		if (copy_to_user(argp, &s, sizeof s))
+			r = -EFAULT;
 		break;
 	case VHOST_SET_VRING_ADDR:
-		r = copy_from_user(&a, argp, sizeof a);
-		if (r < 0)
+		if (copy_from_user(&a, argp, sizeof a)) {
+			r = -EFAULT;
 			break;
+		}
 		if (a.flags & ~(0x1 << VHOST_VRING_F_LOG)) {
 			r = -EOPNOTSUPP;
 			break;
@@ -477,9 +480,10 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
 		vq->used = (void __user *)(unsigned long)a.used_user_addr;
 		break;
 	case VHOST_SET_VRING_KICK:
-		r = copy_from_user(&f, argp, sizeof f);
-		if (r < 0)
+		if (copy_from_user(&f, argp, sizeof f)) {
+			r = -EFAULT;
 			break;
+		}
 		eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd);
 		if (IS_ERR(eventfp)) {
 			r = PTR_ERR(eventfp);
@@ -492,9 +496,10 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
 			filep = eventfp;
 		break;
 	case VHOST_SET_VRING_CALL:
-		r = copy_from_user(&f, argp, sizeof f);
-		if (r < 0)
+		if (copy_from_user(&f, argp, sizeof f)) {
+			r = -EFAULT;
 			break;
+		}
 		eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd);
 		if (IS_ERR(eventfp)) {
 			r = PTR_ERR(eventfp);
@@ -510,9 +515,10 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
 			filep = eventfp;
 		break;
 	case VHOST_SET_VRING_ERR:
-		r = copy_from_user(&f, argp, sizeof f);
-		if (r < 0)
+		if (copy_from_user(&f, argp, sizeof f)) {
+			r = -EFAULT;
 			break;
+		}
 		eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd);
 		if (IS_ERR(eventfp)) {
 			r = PTR_ERR(eventfp);
@@ -575,9 +581,10 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, unsigned long arg)
 		r = vhost_set_memory(d, argp);
 		break;
 	case VHOST_SET_LOG_BASE:
-		r = copy_from_user(&p, argp, sizeof p);
-		if (r < 0)
+		if (copy_from_user(&p, argp, sizeof p)) {
+			r = -EFAULT;
 			break;
+		}
 		if ((u64)(unsigned long)p != p) {
 			r = -EFAULT;
 			break;

include/net/cls_cgroup.h

@@ -39,7 +39,7 @@ extern int net_cls_subsys_id;
 static inline u32 task_cls_classid(struct task_struct *p)
 {
 	int id;
-	u32 classid;
+	u32 classid = 0;
 
 	if (in_interrupt())
 		return 0;

include/net/sctp/structs.h

@@ -876,7 +876,7 @@ struct sctp_transport {
 
 	/* Reference counting. */
 	atomic_t refcnt;
-	int	 dead:1,
+	__u32	 dead:1,
 		/* RTO-Pending : A flag used to track if one of the DATA
 		 *		chunks sent to this address is currently being
 		 *		used to compute a RTT. If this flag is 0,

include/net/sock.h

@@ -1026,16 +1026,24 @@ extern void release_sock(struct sock *sk);
 				SINGLE_DEPTH_NESTING)
 #define bh_unlock_sock(__sk)	spin_unlock(&((__sk)->sk_lock.slock))
 
-static inline void lock_sock_bh(struct sock *sk)
-{
-	spin_lock_bh(&sk->sk_lock.slock);
-}
-
-static inline void unlock_sock_bh(struct sock *sk)
+extern bool lock_sock_fast(struct sock *sk);
+/**
+ * unlock_sock_fast - complement of lock_sock_fast
+ * @sk: socket
+ * @slow: slow mode
+ *
+ * fast unlock socket for user context.
+ * If slow mode is on, we call regular release_sock()
+ */
+static inline void unlock_sock_fast(struct sock *sk, bool slow)
 {
+	if (slow)
+		release_sock(sk);
+	else
 		spin_unlock_bh(&sk->sk_lock.slock);
 }
 
+
 extern struct sock		*sk_alloc(struct net *net, int family,
 					  gfp_t priority,
 					  struct proto *prot);

net/core/datagram.c

@@ -229,15 +229,17 @@ EXPORT_SYMBOL(skb_free_datagram);
 
 void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb)
 {
+	bool slow;
+
 	if (likely(atomic_read(&skb->users) == 1))
 		smp_rmb();
 	else if (likely(!atomic_dec_and_test(&skb->users)))
 		return;
 
-	lock_sock_bh(sk);
+	slow = lock_sock_fast(sk);
 	skb_orphan(skb);
 	sk_mem_reclaim_partial(sk);
-	unlock_sock_bh(sk);
+	unlock_sock_fast(sk, slow);
 
 	/* skb is now orphaned, can be freed outside of locked section */
 	__kfree_skb(skb);

net/core/neighbour.c

@@ -934,6 +934,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
 				kfree_skb(buff);
 				NEIGH_CACHE_STAT_INC(neigh->tbl, unres_discards);
 			}
+			skb_dst_force(skb);
 			__skb_queue_tail(&neigh->arp_queue, skb);
 		}
 		rc = 1;

net/core/rtnetlink.c

@@ -650,11 +650,12 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev)
 	if (dev->dev.parent && dev_is_pci(dev->dev.parent)) {
 
 		int num_vfs = dev_num_vf(dev->dev.parent);
-		size_t size = nlmsg_total_size(sizeof(struct nlattr));
-		size += nlmsg_total_size(num_vfs * sizeof(struct nlattr));
-		size += num_vfs * (sizeof(struct ifla_vf_mac) +
-				  sizeof(struct ifla_vf_vlan) +
-				  sizeof(struct ifla_vf_tx_rate));
+		size_t size = nla_total_size(sizeof(struct nlattr));
+		size += nla_total_size(num_vfs * sizeof(struct nlattr));
+		size += num_vfs *
+			(nla_total_size(sizeof(struct ifla_vf_mac)) +
+			 nla_total_size(sizeof(struct ifla_vf_vlan)) +
+			 nla_total_size(sizeof(struct ifla_vf_tx_rate)));
 		return size;
 	} else
 		return 0;
@@ -722,14 +723,13 @@ static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev)
 
 	for (vf = 0; vf < dev_num_vf(dev->dev.parent); vf++) {
 		vf_port = nla_nest_start(skb, IFLA_VF_PORT);
-		if (!vf_port) {
-			nla_nest_cancel(skb, vf_ports);
-			return -EMSGSIZE;
-		}
+		if (!vf_port)
+			goto nla_put_failure;
 		NLA_PUT_U32(skb, IFLA_PORT_VF, vf);
 		err = dev->netdev_ops->ndo_get_vf_port(dev, vf, skb);
+		if (err == -EMSGSIZE)
+			goto nla_put_failure;
 		if (err) {
-nla_put_failure:
 			nla_nest_cancel(skb, vf_port);
 			continue;
 		}
@@ -739,6 +739,10 @@ static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev)
 	nla_nest_end(skb, vf_ports);
 
 	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, vf_ports);
+	return -EMSGSIZE;
 }
 
 static int rtnl_port_self_fill(struct sk_buff *skb, struct net_device *dev)
@@ -753,7 +757,7 @@ static int rtnl_port_self_fill(struct sk_buff *skb, struct net_device *dev)
 	err = dev->netdev_ops->ndo_get_vf_port(dev, PORT_SELF_VF, skb);
 	if (err) {
 		nla_nest_cancel(skb, port_self);
-		return err;
+		return (err == -EMSGSIZE) ? err : 0;
 	}
 
 	nla_nest_end(skb, port_self);

net/core/sock.c

@@ -2007,6 +2007,39 @@ void release_sock(struct sock *sk)
 }
 EXPORT_SYMBOL(release_sock);
 
+/**
+ * lock_sock_fast - fast version of lock_sock
+ * @sk: socket
+ *
+ * This version should be used for very small section, where process wont block
+ * return false if fast path is taken
+ *   sk_lock.slock locked, owned = 0, BH disabled
+ * return true if slow path is taken
+ *   sk_lock.slock unlocked, owned = 1, BH enabled
+ */
+bool lock_sock_fast(struct sock *sk)
+{
+	might_sleep();
+	spin_lock_bh(&sk->sk_lock.slock);
+
+	if (!sk->sk_lock.owned)
+		/*
+		 * Note : We must disable BH
+		 */
+		return false;
+
+	__lock_sock(sk);
+	sk->sk_lock.owned = 1;
+	spin_unlock(&sk->sk_lock.slock);
+	/*
+	 * The sk_lock has mutex_lock() semantics here:
+	 */
+	mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_);
+	local_bh_enable();
+	return true;
+}
+EXPORT_SYMBOL(lock_sock_fast);
+
 int sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp)
 {
 	struct timeval tv;

net/ipv4/ipmr.c

@@ -1911,7 +1911,7 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 	struct rtattr *mp_head;
 
 	/* If cache is unresolved, don't try to parse IIF and OIF */
-	if (c->mfc_parent > MAXVIFS)
+	if (c->mfc_parent >= MAXVIFS)
 		return -ENOENT;
 
 	if (VIF_EXISTS(mrt, c->mfc_parent))

net/ipv4/udp.c

@@ -1063,10 +1063,11 @@ static unsigned int first_packet_length(struct sock *sk)
 	spin_unlock_bh(&rcvq->lock);
 
 	if (!skb_queue_empty(&list_kill)) {
-		lock_sock_bh(sk);
+		bool slow = lock_sock_fast(sk);
+
 		__skb_queue_purge(&list_kill);
 		sk_mem_reclaim_partial(sk);
-		unlock_sock_bh(sk);
+		unlock_sock_fast(sk, slow);
 	}
 	return res;
 }
@@ -1123,6 +1124,7 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	int peeked;
 	int err;
 	int is_udplite = IS_UDPLITE(sk);
+	bool slow;
 
 	/*
 	 *	Check any passed addresses
@@ -1197,10 +1199,10 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	return err;
 
 csum_copy_err:
-	lock_sock_bh(sk);
+	slow = lock_sock_fast(sk);
 	if (!skb_kill_datagram(sk, skb, flags))
 		UDP_INC_STATS_USER(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
-	unlock_sock_bh(sk);
+	unlock_sock_fast(sk, slow);
 
 	if (noblock)
 		return -EAGAIN;
@@ -1625,9 +1627,9 @@ int udp_rcv(struct sk_buff *skb)
 
 void udp_destroy_sock(struct sock *sk)
 {
-	lock_sock_bh(sk);
+	bool slow = lock_sock_fast(sk);
 	udp_flush_pending_frames(sk);
-	unlock_sock_bh(sk);
+	unlock_sock_fast(sk, slow);
 }
 
 /*

net/ipv6/ip6_output.c

@@ -507,7 +507,7 @@ int ip6_forward(struct sk_buff *skb)
 	if (mtu < IPV6_MIN_MTU)
 		mtu = IPV6_MIN_MTU;
 
-	if (skb->len > mtu) {
+	if (skb->len > mtu && !skb_is_gso(skb)) {
 		/* Again, force OUTPUT device used as source address */
 		skb->dev = dst->dev;
 		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);

net/ipv6/ip6mr.c

@@ -2017,7 +2017,7 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
 	struct rtattr *mp_head;
 
 	/* If cache is unresolved, don't try to parse IIF and OIF */
-	if (c->mf6c_parent > MAXMIFS)
+	if (c->mf6c_parent >= MAXMIFS)
 		return -ENOENT;
 
 	if (MIF_EXISTS(mrt, c->mf6c_parent))

net/ipv6/udp.c

@@ -328,6 +328,7 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk,
 	int err;
 	int is_udplite = IS_UDPLITE(sk);
 	int is_udp4;
+	bool slow;
 
 	if (addr_len)
 		*addr_len=sizeof(struct sockaddr_in6);
@@ -424,7 +425,7 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk,
 	return err;
 
 csum_copy_err:
-	lock_sock_bh(sk);
+	slow = lock_sock_fast(sk);
 	if (!skb_kill_datagram(sk, skb, flags)) {
 		if (is_udp4)
 			UDP_INC_STATS_USER(sock_net(sk),
@@ -433,7 +434,7 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk,
 			UDP6_INC_STATS_USER(sock_net(sk),
 					UDP_MIB_INERRORS, is_udplite);
 	}
-	unlock_sock_bh(sk);
+	unlock_sock_fast(sk, slow);
 
 	if (flags & MSG_DONTWAIT)
 		return -EAGAIN;

net/iucv/af_iucv.c

@@ -1619,7 +1619,7 @@ static void iucv_callback_rx(struct iucv_path *path, struct iucv_message *msg)
 save_message:
 	save_msg = kzalloc(sizeof(struct sock_msg_q), GFP_ATOMIC | GFP_DMA);
 	if (!save_msg)
-		return;
+		goto out_unlock;
 	save_msg->path = path;
 	save_msg->msg = *msg;
 

net/netfilter/xt_TEE.c

@@ -76,7 +76,7 @@ tee_tg_route4(struct sk_buff *skb, const struct xt_tee_tginfo *info)
 	if (ip_route_output_key(net, &rt, &fl) != 0)
 		return false;
 
-	dst_release(skb_dst(skb));
+	skb_dst_drop(skb);
 	skb_dst_set(skb, &rt->u.dst);
 	skb->dev      = rt->u.dst.dev;
 	skb->protocol = htons(ETH_P_IP);
@@ -157,7 +157,7 @@ tee_tg_route6(struct sk_buff *skb, const struct xt_tee_tginfo *info)
 	if (dst == NULL)
 		return false;
 
-	dst_release(skb_dst(skb));
+	skb_dst_drop(skb);
 	skb_dst_set(skb, dst);
 	skb->dev      = dst->dev;
 	skb->protocol = htons(ETH_P_IPV6);