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: (21 commits)
  niu: VLAN_ETH_HLEN should be used to make sure that the whole MAC header was copied to the head buffer in the Vlan packets case
  KS8851: Fix ks8851_set_rx_mode() for IFF_MULTICAST
  KS8851: Fix MAC address write order
  KS8851: Add soft reset at probe time
  net: fix section mismatch in fec.c
  net: Fix struct inet_timewait_sock bitfield annotation
  tcp: Try to catch MSG_PEEK bug
  net: Fix IP_MULTICAST_IF
  bluetooth: static lock key fix
  bluetooth: scheduling while atomic bug fix
  tcp: fix TCP_DEFER_ACCEPT retrans calculation
  tcp: reduce SYN-ACK retrans for TCP_DEFER_ACCEPT
  tcp: accept socket after TCP_DEFER_ACCEPT period
  Revert "tcp: fix tcp_defer_accept to consider the timeout"
  AF_UNIX: Fix deadlock on connecting to shutdown socket
  ethoc: clear only pending irqs
  ethoc: inline regs access
  vmxnet3: use dev_dbg, fix build for CONFIG_BLOCK=n
  virtio_net: use dev_kfree_skb_any() in free_old_xmit_skbs()
  be2net: fix support for PCI hot plug
  ...

drivers/net/benet/be_cmds.c

@@ -243,15 +243,26 @@ static int be_POST_stage_get(struct be_adapter *adapter, u16 *stage)
 
 int be_cmd_POST(struct be_adapter *adapter)
 {
-	u16 stage, error;
+	u16 stage;
+	int status, timeout = 0;
 
-	error = be_POST_stage_get(adapter, &stage);
-	if (error || stage != POST_STAGE_ARMFW_RDY) {
-		dev_err(&adapter->pdev->dev, "POST failed.\n");
-		return -1;
-	}
+	do {
+		status = be_POST_stage_get(adapter, &stage);
+		if (status) {
+			dev_err(&adapter->pdev->dev, "POST error; stage=0x%x\n",
+				stage);
+			return -1;
+		} else if (stage != POST_STAGE_ARMFW_RDY) {
+			set_current_state(TASK_INTERRUPTIBLE);
+			schedule_timeout(2 * HZ);
+			timeout += 2;
+		} else {
+			return 0;
+		}
+	} while (timeout < 20);
 
-	return 0;
+	dev_err(&adapter->pdev->dev, "POST timeout; stage=0x%x\n", stage);
+	return -1;
 }
 
 static inline void *embedded_payload(struct be_mcc_wrb *wrb)
@@ -729,8 +740,8 @@ int be_cmd_q_destroy(struct be_adapter *adapter, struct be_queue_info *q,
 /* Create an rx filtering policy configuration on an i/f
  * Uses mbox
  */
-int be_cmd_if_create(struct be_adapter *adapter, u32 flags, u8 *mac,
-		bool pmac_invalid, u32 *if_handle, u32 *pmac_id)
+int be_cmd_if_create(struct be_adapter *adapter, u32 cap_flags, u32 en_flags,
+		u8 *mac, bool pmac_invalid, u32 *if_handle, u32 *pmac_id)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_if_create *req;
@@ -746,8 +757,8 @@ int be_cmd_if_create(struct be_adapter *adapter, u32 flags, u8 *mac,
 	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
 		OPCODE_COMMON_NTWK_INTERFACE_CREATE, sizeof(*req));
 
-	req->capability_flags = cpu_to_le32(flags);
-	req->enable_flags = cpu_to_le32(flags);
+	req->capability_flags = cpu_to_le32(cap_flags);
+	req->enable_flags = cpu_to_le32(en_flags);
 	req->pmac_invalid = pmac_invalid;
 	if (!pmac_invalid)
 		memcpy(req->mac_addr, mac, ETH_ALEN);

drivers/net/benet/be_cmds.h

@@ -720,8 +720,9 @@ extern int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr,
 extern int be_cmd_pmac_add(struct be_adapter *adapter, u8 *mac_addr,
 			u32 if_id, u32 *pmac_id);
 extern int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id, u32 pmac_id);
-extern int be_cmd_if_create(struct be_adapter *adapter, u32 if_flags, u8 *mac,
-			bool pmac_invalid, u32 *if_handle, u32 *pmac_id);
+extern int be_cmd_if_create(struct be_adapter *adapter, u32 cap_flags,
+			u32 en_flags, u8 *mac, bool pmac_invalid,
+			u32 *if_handle, u32 *pmac_id);
 extern int be_cmd_if_destroy(struct be_adapter *adapter, u32 if_handle);
 extern int be_cmd_eq_create(struct be_adapter *adapter,
 			struct be_queue_info *eq, int eq_delay);

drivers/net/benet/be_main.c

@@ -1620,19 +1620,22 @@ static int be_open(struct net_device *netdev)
 static int be_setup(struct be_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
-	u32 if_flags;
+	u32 cap_flags, en_flags;
 	int status;
 
-	if_flags = BE_IF_FLAGS_BROADCAST | BE_IF_FLAGS_PROMISCUOUS |
-		BE_IF_FLAGS_MCAST_PROMISCUOUS | BE_IF_FLAGS_UNTAGGED |
-		BE_IF_FLAGS_PASS_L3L4_ERRORS;
-	status = be_cmd_if_create(adapter, if_flags, netdev->dev_addr,
-			false/* pmac_invalid */, &adapter->if_handle,
-			&adapter->pmac_id);
+	cap_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST |
+			BE_IF_FLAGS_MCAST_PROMISCUOUS |
+			BE_IF_FLAGS_PROMISCUOUS |
+			BE_IF_FLAGS_PASS_L3L4_ERRORS;
+	en_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST |
+			BE_IF_FLAGS_PASS_L3L4_ERRORS;
+
+	status = be_cmd_if_create(adapter, cap_flags, en_flags,
+			netdev->dev_addr, false/* pmac_invalid */,
+			&adapter->if_handle, &adapter->pmac_id);
 	if (status != 0)
 		goto do_none;
 
-
 	status = be_tx_queues_create(adapter);
 	if (status != 0)
 		goto if_destroy;
@@ -2055,6 +2058,10 @@ static int be_hw_up(struct be_adapter *adapter)
 	if (status)
 		return status;
 
+	status = be_cmd_reset_function(adapter);
+	if (status)
+		return status;
+
 	status = be_cmd_get_fw_ver(adapter, adapter->fw_ver);
 	if (status)
 		return status;
@@ -2108,10 +2115,6 @@ static int __devinit be_probe(struct pci_dev *pdev,
 	if (status)
 		goto free_netdev;
 
-	status = be_cmd_reset_function(adapter);
-	if (status)
-		goto ctrl_clean;
-
 	status = be_stats_init(adapter);
 	if (status)
 		goto ctrl_clean;

drivers/net/ethoc.c

@@ -223,24 +223,25 @@ struct ethoc_bd {
 	u32 addr;
 };
 
-static u32 ethoc_read(struct ethoc *dev, loff_t offset)
+static inline u32 ethoc_read(struct ethoc *dev, loff_t offset)
 {
 	return ioread32(dev->iobase + offset);
 }
 
-static void ethoc_write(struct ethoc *dev, loff_t offset, u32 data)
+static inline void ethoc_write(struct ethoc *dev, loff_t offset, u32 data)
 {
 	iowrite32(data, dev->iobase + offset);
 }
 
-static void ethoc_read_bd(struct ethoc *dev, int index, struct ethoc_bd *bd)
+static inline void ethoc_read_bd(struct ethoc *dev, int index,
+		struct ethoc_bd *bd)
 {
 	loff_t offset = ETHOC_BD_BASE + (index * sizeof(struct ethoc_bd));
 	bd->stat = ethoc_read(dev, offset + 0);
 	bd->addr = ethoc_read(dev, offset + 4);
 }
 
-static void ethoc_write_bd(struct ethoc *dev, int index,
+static inline void ethoc_write_bd(struct ethoc *dev, int index,
 		const struct ethoc_bd *bd)
 {
 	loff_t offset = ETHOC_BD_BASE + (index * sizeof(struct ethoc_bd));
@@ -248,33 +249,33 @@ static void ethoc_write_bd(struct ethoc *dev, int index,
 	ethoc_write(dev, offset + 4, bd->addr);
 }
 
-static void ethoc_enable_irq(struct ethoc *dev, u32 mask)
+static inline void ethoc_enable_irq(struct ethoc *dev, u32 mask)
 {
 	u32 imask = ethoc_read(dev, INT_MASK);
 	imask |= mask;
 	ethoc_write(dev, INT_MASK, imask);
 }
 
-static void ethoc_disable_irq(struct ethoc *dev, u32 mask)
+static inline void ethoc_disable_irq(struct ethoc *dev, u32 mask)
 {
 	u32 imask = ethoc_read(dev, INT_MASK);
 	imask &= ~mask;
 	ethoc_write(dev, INT_MASK, imask);
 }
 
-static void ethoc_ack_irq(struct ethoc *dev, u32 mask)
+static inline void ethoc_ack_irq(struct ethoc *dev, u32 mask)
 {
 	ethoc_write(dev, INT_SOURCE, mask);
 }
 
-static void ethoc_enable_rx_and_tx(struct ethoc *dev)
+static inline void ethoc_enable_rx_and_tx(struct ethoc *dev)
 {
 	u32 mode = ethoc_read(dev, MODER);
 	mode |= MODER_RXEN | MODER_TXEN;
 	ethoc_write(dev, MODER, mode);
 }
 
-static void ethoc_disable_rx_and_tx(struct ethoc *dev)
+static inline void ethoc_disable_rx_and_tx(struct ethoc *dev)
 {
 	u32 mode = ethoc_read(dev, MODER);
 	mode &= ~(MODER_RXEN | MODER_TXEN);
@@ -508,7 +509,7 @@ static irqreturn_t ethoc_interrupt(int irq, void *dev_id)
 		return IRQ_NONE;
 	}
 
-	ethoc_ack_irq(priv, INT_MASK_ALL);
+	ethoc_ack_irq(priv, pending);
 
 	if (pending & INT_MASK_BUSY) {
 		dev_err(&dev->dev, "packet dropped\n");

drivers/net/fec.c

@@ -1654,7 +1654,7 @@ static const struct net_device_ops fec_netdev_ops = {
   *
   * index is only used in legacy code
   */
-int __init fec_enet_init(struct net_device *dev, int index)
+static int fec_enet_init(struct net_device *dev, int index)
 {
 	struct fec_enet_private *fep = netdev_priv(dev);
 	struct bufdesc *cbd_base;

drivers/net/ks8851.c

@@ -170,6 +170,36 @@ static void ks8851_wrreg16(struct ks8851_net *ks, unsigned reg, unsigned val)
 		ks_err(ks, "spi_sync() failed\n");
 }
 
+/**
+ * ks8851_wrreg8 - write 8bit register value to chip
+ * @ks: The chip state
+ * @reg: The register address
+ * @val: The value to write
+ *
+ * Issue a write to put the value @val into the register specified in @reg.
+ */
+static void ks8851_wrreg8(struct ks8851_net *ks, unsigned reg, unsigned val)
+{
+	struct spi_transfer *xfer = &ks->spi_xfer1;
+	struct spi_message *msg = &ks->spi_msg1;
+	__le16 txb[2];
+	int ret;
+	int bit;
+
+	bit = 1 << (reg & 3);
+
+	txb[0] = cpu_to_le16(MK_OP(bit, reg) | KS_SPIOP_WR);
+	txb[1] = val;
+
+	xfer->tx_buf = txb;
+	xfer->rx_buf = NULL;
+	xfer->len = 3;
+
+	ret = spi_sync(ks->spidev, msg);
+	if (ret < 0)
+		ks_err(ks, "spi_sync() failed\n");
+}
+
 /**
  * ks8851_rx_1msg - select whether to use one or two messages for spi read
  * @ks: The device structure
@@ -322,13 +352,12 @@ static void ks8851_soft_reset(struct ks8851_net *ks, unsigned op)
 static int ks8851_write_mac_addr(struct net_device *dev)
 {
 	struct ks8851_net *ks = netdev_priv(dev);
-	u16 *mcp = (u16 *)dev->dev_addr;
+	int i;
 
 	mutex_lock(&ks->lock);
 
-	ks8851_wrreg16(ks, KS_MARL, mcp[0]);
-	ks8851_wrreg16(ks, KS_MARM, mcp[1]);
-	ks8851_wrreg16(ks, KS_MARH, mcp[2]);
+	for (i = 0; i < ETH_ALEN; i++)
+		ks8851_wrreg8(ks, KS_MAR(i), dev->dev_addr[i]);
 
 	mutex_unlock(&ks->lock);
 
@@ -951,7 +980,7 @@ static void ks8851_set_rx_mode(struct net_device *dev)
 			mcptr = mcptr->next;
 		}
 
-		rxctrl.rxcr1 = RXCR1_RXME | RXCR1_RXAE | RXCR1_RXPAFMA;
+		rxctrl.rxcr1 = RXCR1_RXME | RXCR1_RXPAFMA;
 	} else {
 		/* just accept broadcast / unicast */
 		rxctrl.rxcr1 = RXCR1_RXPAFMA;
@@ -1239,6 +1268,9 @@ static int __devinit ks8851_probe(struct spi_device *spi)
 	ndev->netdev_ops = &ks8851_netdev_ops;
 	ndev->irq = spi->irq;
 
+	/* issue a global soft reset to reset the device. */
+	ks8851_soft_reset(ks, GRR_GSR);
+
 	/* simple check for a valid chip being connected to the bus */
 
 	if ((ks8851_rdreg16(ks, KS_CIDER) & ~CIDER_REV_MASK) != CIDER_ID) {

drivers/net/ks8851.h

@@ -16,6 +16,7 @@
 #define CCR_32PIN				(1 << 0)
 
 /* MAC address registers */
+#define KS_MAR(_m)				0x15 - (_m)
 #define KS_MARL					0x10
 #define KS_MARM					0x12
 #define KS_MARH					0x14

drivers/net/niu.c

@@ -3545,7 +3545,7 @@ static int niu_process_rx_pkt(struct napi_struct *napi, struct niu *np,
 	rp->rcr_index = index;
 
 	skb_reserve(skb, NET_IP_ALIGN);
-	__pskb_pull_tail(skb, min(len, NIU_RXPULL_MAX));
+	__pskb_pull_tail(skb, min(len, VLAN_ETH_HLEN));
 
 	rp->rx_packets++;
 	rp->rx_bytes += skb->len;

drivers/net/virtio_net.c

@@ -454,7 +454,7 @@ static unsigned int free_old_xmit_skbs(struct virtnet_info *vi)
 		vi->dev->stats.tx_bytes += skb->len;
 		vi->dev->stats.tx_packets++;
 		tot_sgs += skb_vnet_hdr(skb)->num_sg;
-		kfree_skb(skb);
+		dev_kfree_skb_any(skb);
 	}
 	return tot_sgs;
 }

drivers/net/vmxnet3/vmxnet3_drv.c

@@ -481,7 +481,8 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx,
 	}
 	rq->uncommitted[ring_idx] += num_allocated;
 
-	dprintk(KERN_ERR "alloc_rx_buf: %d allocated, next2fill %u, next2comp "
+	dev_dbg(&adapter->netdev->dev,
+		"alloc_rx_buf: %d allocated, next2fill %u, next2comp "
 		"%u, uncommited %u\n", num_allocated, ring->next2fill,
 		ring->next2comp, rq->uncommitted[ring_idx]);
 
@@ -539,7 +540,8 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx,
 		tbi = tq->buf_info + tq->tx_ring.next2fill;
 		tbi->map_type = VMXNET3_MAP_NONE;
 
-		dprintk(KERN_ERR "txd[%u]: 0x%Lx 0x%x 0x%x\n",
+		dev_dbg(&adapter->netdev->dev,
+			"txd[%u]: 0x%Lx 0x%x 0x%x\n",
 			tq->tx_ring.next2fill, ctx->sop_txd->txd.addr,
 			ctx->sop_txd->dword[2], ctx->sop_txd->dword[3]);
 		vmxnet3_cmd_ring_adv_next2fill(&tq->tx_ring);
@@ -572,7 +574,8 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx,
 		gdesc->dword[2] = dw2 | buf_size;
 		gdesc->dword[3] = 0;
 
-		dprintk(KERN_ERR "txd[%u]: 0x%Lx 0x%x 0x%x\n",
+		dev_dbg(&adapter->netdev->dev,
+			"txd[%u]: 0x%Lx 0x%x 0x%x\n",
 			tq->tx_ring.next2fill, gdesc->txd.addr,
 			gdesc->dword[2], gdesc->dword[3]);
 		vmxnet3_cmd_ring_adv_next2fill(&tq->tx_ring);
@@ -600,7 +603,8 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx,
 		gdesc->dword[2] = dw2 | frag->size;
 		gdesc->dword[3] = 0;
 
-		dprintk(KERN_ERR "txd[%u]: 0x%llu %u %u\n",
+		dev_dbg(&adapter->netdev->dev,
+			"txd[%u]: 0x%llu %u %u\n",
 			tq->tx_ring.next2fill, gdesc->txd.addr,
 			gdesc->dword[2], gdesc->dword[3]);
 		vmxnet3_cmd_ring_adv_next2fill(&tq->tx_ring);
@@ -697,7 +701,8 @@ vmxnet3_parse_and_copy_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 	tdd = tq->data_ring.base + tq->tx_ring.next2fill;
 
 	memcpy(tdd->data, skb->data, ctx->copy_size);
-	dprintk(KERN_ERR "copy %u bytes to dataRing[%u]\n",
+	dev_dbg(&adapter->netdev->dev,
+		"copy %u bytes to dataRing[%u]\n",
 		ctx->copy_size, tq->tx_ring.next2fill);
 	return 1;
 
@@ -808,7 +813,8 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 
 	if (count > vmxnet3_cmd_ring_desc_avail(&tq->tx_ring)) {
 		tq->stats.tx_ring_full++;
-		dprintk(KERN_ERR "tx queue stopped on %s, next2comp %u"
+		dev_dbg(&adapter->netdev->dev,
+			"tx queue stopped on %s, next2comp %u"
 			" next2fill %u\n", adapter->netdev->name,
 			tq->tx_ring.next2comp, tq->tx_ring.next2fill);
 
@@ -853,7 +859,8 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 
 	/* finally flips the GEN bit of the SOP desc */
 	gdesc->dword[2] ^= VMXNET3_TXD_GEN;
-	dprintk(KERN_ERR "txd[%u]: SOP 0x%Lx 0x%x 0x%x\n",
+	dev_dbg(&adapter->netdev->dev,
+		"txd[%u]: SOP 0x%Lx 0x%x 0x%x\n",
 		(u32)((union Vmxnet3_GenericDesc *)ctx.sop_txd -
 		tq->tx_ring.base), gdesc->txd.addr, gdesc->dword[2],
 		gdesc->dword[3]);
@@ -990,7 +997,8 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 			if (unlikely(rcd->len == 0)) {
 				/* Pretend the rx buffer is skipped. */
 				BUG_ON(!(rcd->sop && rcd->eop));
-				dprintk(KERN_ERR "rxRing[%u][%u] 0 length\n",
+				dev_dbg(&adapter->netdev->dev,
+					"rxRing[%u][%u] 0 length\n",
 					ring_idx, idx);
 				goto rcd_done;
 			}
@@ -1683,7 +1691,8 @@ vmxnet3_activate_dev(struct vmxnet3_adapter *adapter)
 	int err;
 	u32 ret;
 
-	dprintk(KERN_ERR "%s: skb_buf_size %d, rx_buf_per_pkt %d, ring sizes"
+	dev_dbg(&adapter->netdev->dev,
+		"%s: skb_buf_size %d, rx_buf_per_pkt %d, ring sizes"
 		" %u %u %u\n", adapter->netdev->name, adapter->skb_buf_size,
 		adapter->rx_buf_per_pkt, adapter->tx_queue.tx_ring.size,
 		adapter->rx_queue.rx_ring[0].size,

drivers/net/vmxnet3/vmxnet3_int.h

@@ -30,6 +30,7 @@
 #include <linux/types.h>
 #include <linux/ethtool.h>
 #include <linux/delay.h>
+#include <linux/device.h>
 #include <linux/netdevice.h>
 #include <linux/pci.h>
 #include <linux/ethtool.h>
@@ -59,7 +60,6 @@
 #include <linux/if_vlan.h>
 #include <linux/if_arp.h>
 #include <linux/inetdevice.h>
-#include <linux/dst.h>
 
 #include "vmxnet3_defs.h"
 

include/net/inet_timewait_sock.h

@@ -130,11 +130,11 @@ struct inet_timewait_sock {
 	__u16			tw_num;
 	kmemcheck_bitfield_begin(flags);
 	/* And these are ours. */
-	__u8			tw_ipv6only:1,
-				tw_transparent:1;
-	/* 14 bits hole, try to pack */
+	unsigned int		tw_ipv6only     : 1,
+				tw_transparent  : 1,
+				tw_pad		: 14,	/* 14 bits hole */
+				tw_ipv6_offset  : 16;
 	kmemcheck_bitfield_end(flags);
-	__u16			tw_ipv6_offset;
 	unsigned long		tw_ttd;
 	struct inet_bind_bucket	*tw_tb;
 	struct hlist_node	tw_death_node;

net/bluetooth/hci_sysfs.c

@@ -92,6 +92,8 @@ static void add_conn(struct work_struct *work)
 
 	dev_set_name(&conn->dev, "%s:%d", hdev->name, conn->handle);
 
+	dev_set_drvdata(&conn->dev, conn);
+
 	if (device_add(&conn->dev) < 0) {
 		BT_ERR("Failed to register connection device");
 		return;
@@ -144,8 +146,6 @@ void hci_conn_init_sysfs(struct hci_conn *conn)
 	conn->dev.class = bt_class;
 	conn->dev.parent = &hdev->dev;
 
-	dev_set_drvdata(&conn->dev, conn);
-
 	device_initialize(&conn->dev);
 
 	INIT_WORK(&conn->work_add, add_conn);

net/bluetooth/l2cap.c

@@ -555,12 +555,12 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon, u8 status)
 
 	conn->feat_mask = 0;
 
-	setup_timer(&conn->info_timer, l2cap_info_timeout,
-						(unsigned long) conn);
-
 	spin_lock_init(&conn->lock);
 	rwlock_init(&conn->chan_list.lock);
 
+	setup_timer(&conn->info_timer, l2cap_info_timeout,
+						(unsigned long) conn);
+
 	conn->disc_reason = 0x13;
 
 	return conn;
@@ -783,6 +783,9 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent)
 	/* Default config options */
 	pi->conf_len = 0;
 	pi->flush_to = L2CAP_DEFAULT_FLUSH_TO;
+	skb_queue_head_init(TX_QUEUE(sk));
+	skb_queue_head_init(SREJ_QUEUE(sk));
+	INIT_LIST_HEAD(SREJ_LIST(sk));
 }
 
 static struct proto l2cap_proto = {

net/ipv4/inet_connection_sock.c

@@ -446,6 +446,28 @@ extern int sysctl_tcp_synack_retries;
 
 EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add);
 
+/* Decide when to expire the request and when to resend SYN-ACK */
+static inline void syn_ack_recalc(struct request_sock *req, const int thresh,
+				  const int max_retries,
+				  const u8 rskq_defer_accept,
+				  int *expire, int *resend)
+{
+	if (!rskq_defer_accept) {
+		*expire = req->retrans >= thresh;
+		*resend = 1;
+		return;
+	}
+	*expire = req->retrans >= thresh &&
+		  (!inet_rsk(req)->acked || req->retrans >= max_retries);
+	/*
+	 * Do not resend while waiting for data after ACK,
+	 * start to resend on end of deferring period to give
+	 * last chance for data or ACK to create established socket.
+	 */
+	*resend = !inet_rsk(req)->acked ||
+		  req->retrans >= rskq_defer_accept - 1;
+}
+
 void inet_csk_reqsk_queue_prune(struct sock *parent,
 				const unsigned long interval,
 				const unsigned long timeout,
@@ -501,9 +523,15 @@ void inet_csk_reqsk_queue_prune(struct sock *parent,
 		reqp=&lopt->syn_table[i];
 		while ((req = *reqp) != NULL) {
 			if (time_after_eq(now, req->expires)) {
-				if ((req->retrans < thresh ||
-				     (inet_rsk(req)->acked && req->retrans < max_retries))
-				    && !req->rsk_ops->rtx_syn_ack(parent, req)) {
+				int expire = 0, resend = 0;
+
+				syn_ack_recalc(req, thresh, max_retries,
+					       queue->rskq_defer_accept,
+					       &expire, &resend);
+				if (!expire &&
+				    (!resend ||
+				     !req->rsk_ops->rtx_syn_ack(parent, req) ||
+				     inet_rsk(req)->acked)) {
 					unsigned long timeo;
 
 					if (req->retrans++ == 0)

net/ipv4/ip_sockglue.c

@@ -634,17 +634,16 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 				break;
 			}
 			dev = ip_dev_find(sock_net(sk), mreq.imr_address.s_addr);
-			if (dev) {
+			if (dev)
 				mreq.imr_ifindex = dev->ifindex;
-				dev_put(dev);
-			}
 		} else
-			dev = __dev_get_by_index(sock_net(sk), mreq.imr_ifindex);
+			dev = dev_get_by_index(sock_net(sk), mreq.imr_ifindex);
 
 
 		err = -EADDRNOTAVAIL;
 		if (!dev)
 			break;
+		dev_put(dev);
 
 		err = -EINVAL;
 		if (sk->sk_bound_dev_if &&

net/ipv4/tcp.c

@@ -326,6 +326,43 @@ void tcp_enter_memory_pressure(struct sock *sk)
 
 EXPORT_SYMBOL(tcp_enter_memory_pressure);
 
+/* Convert seconds to retransmits based on initial and max timeout */
+static u8 secs_to_retrans(int seconds, int timeout, int rto_max)
+{
+	u8 res = 0;
+
+	if (seconds > 0) {
+		int period = timeout;
+
+		res = 1;
+		while (seconds > period && res < 255) {
+			res++;
+			timeout <<= 1;
+			if (timeout > rto_max)
+				timeout = rto_max;
+			period += timeout;
+		}
+	}
+	return res;
+}
+
+/* Convert retransmits to seconds based on initial and max timeout */
+static int retrans_to_secs(u8 retrans, int timeout, int rto_max)
+{
+	int period = 0;
+
+	if (retrans > 0) {
+		period = timeout;
+		while (--retrans) {
+			timeout <<= 1;
+			if (timeout > rto_max)
+				timeout = rto_max;
+			period += timeout;
+		}
+	}
+	return period;
+}
+
 /*
  *	Wait for a TCP event.
  *
@@ -1405,7 +1442,9 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 				goto found_ok_skb;
 			if (tcp_hdr(skb)->fin)
 				goto found_fin_ok;
-			WARN_ON(!(flags & MSG_PEEK));
+			if (WARN_ON(!(flags & MSG_PEEK)))
+				printk(KERN_INFO "recvmsg bug 2: copied %X "
+				       "seq %X\n", *seq, TCP_SKB_CB(skb)->seq);
 		}
 
 		/* Well, if we have backlog, try to process it now yet. */
@@ -2163,16 +2202,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		break;
 
 	case TCP_DEFER_ACCEPT:
-		icsk->icsk_accept_queue.rskq_defer_accept = 0;
-		if (val > 0) {
-			/* Translate value in seconds to number of
-			 * retransmits */
-			while (icsk->icsk_accept_queue.rskq_defer_accept < 32 &&
-			       val > ((TCP_TIMEOUT_INIT / HZ) <<
-				       icsk->icsk_accept_queue.rskq_defer_accept))
-				icsk->icsk_accept_queue.rskq_defer_accept++;
-			icsk->icsk_accept_queue.rskq_defer_accept++;
-		}
+		/* Translate value in seconds to number of retransmits */
+		icsk->icsk_accept_queue.rskq_defer_accept =
+			secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ,
+					TCP_RTO_MAX / HZ);
 		break;
 
 	case TCP_WINDOW_CLAMP:
@@ -2353,8 +2386,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 			val = (val ? : sysctl_tcp_fin_timeout) / HZ;
 		break;
 	case TCP_DEFER_ACCEPT:
-		val = !icsk->icsk_accept_queue.rskq_defer_accept ? 0 :
-			((TCP_TIMEOUT_INIT / HZ) << (icsk->icsk_accept_queue.rskq_defer_accept - 1));
+		val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept,
+				      TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ);
 		break;
 	case TCP_WINDOW_CLAMP:
 		val = tp->window_clamp;

net/ipv4/tcp_minisocks.c

@@ -641,10 +641,9 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	if (!(flg & TCP_FLAG_ACK))
 		return NULL;
 
-	/* If TCP_DEFER_ACCEPT is set, drop bare ACK. */
-	if (inet_csk(sk)->icsk_accept_queue.rskq_defer_accept &&
+	/* While TCP_DEFER_ACCEPT is active, drop bare ACK. */
+	if (req->retrans < inet_csk(sk)->icsk_accept_queue.rskq_defer_accept &&
 	    TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) {
-		inet_csk(sk)->icsk_accept_queue.rskq_defer_accept--;
 		inet_rsk(req)->acked = 1;
 		return NULL;
 	}

net/ipv6/ipv6_sockglue.c

@@ -496,13 +496,17 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 			goto e_inval;
 
 		if (val) {
+			struct net_device *dev;
+
 			if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != val)
 				goto e_inval;
 
-			if (__dev_get_by_index(net, val) == NULL) {
+			dev = dev_get_by_index(net, val);
+			if (!dev) {
 				retv = -ENODEV;
 				break;
 			}
+			dev_put(dev);
 		}
 		np->mcast_oif = val;
 		retv = 0;

net/unix/af_unix.c

@@ -1074,6 +1074,8 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 	err = -ECONNREFUSED;
 	if (other->sk_state != TCP_LISTEN)
 		goto out_unlock;
+	if (other->sk_shutdown & RCV_SHUTDOWN)
+		goto out_unlock;
 
 	if (unix_recvq_full(other)) {
 		err = -EAGAIN;