Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull more networking updates from David Miller:

 1) If a VXLAN interface is created with no groups, we can crash on
    reception of packets.  Fix from Mike Rapoport.

 2) Missing includes in CPTS driver, from Alexei Starovoitov.

 3) Fix string validations in isdnloop driver, from YOSHIFUJI Hideaki
    and Dan Carpenter.

 4) Missing irq.h include in bnxw2x, enic, and qlcnic drivers.  From
    Josh Boyer.

 5) AF_PACKET transmit doesn't statistically count TX drops, from Daniel
    Borkmann.

 6) Byte-Queue-Limit enabled drivers aren't handled properly in
    AF_PACKET transmit path, also from Daniel Borkmann.

    Same problem exists in pktgen, and Daniel fixed it there too.

 7) Fix resource leaks in driver probe error paths of new sxgbe driver,
    from Francois Romieu.

 8) Truesize of SKBs can gradually get more and more corrupted in NAPI
    packet recycling path, fix from Eric Dumazet.

 9) Fix uniprocessor netfilter build, from Florian Westphal.  In the
    longer term we should perhaps try to find a way for ARRAY_SIZE() to
    work even with zero sized array elements.

10) Fix crash in netfilter conntrack extensions due to mis-estimation of
    required extension space.  From Andrey Vagin.

11) Since we commit table rule updates before trying to copy the
    counters back to userspace (it's the last action we perform), we
    really can't signal the user copy with an error as we are beyond the
    point from which we can unwind everything.  This causes all kinds of
    use after free crashes and other mysterious behavior.

    From Thomas Graf.

12) Restore previous behvaior of div/mod by zero in BPF filter
    processing.  From Daniel Borkmann.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (38 commits)
  net: sctp: wake up all assocs if sndbuf policy is per socket
  isdnloop: several buffer overflows
  netdev: remove potentially harmful checks
  pktgen: fix xmit test for BQL enabled devices
  net/at91_ether: avoid NULL pointer dereference
  tipc: Let tipc_release() return 0
  at86rf230: fix MAX_CSMA_RETRIES parameter
  mac802154: fix duplicate #include headers
  sxgbe: fix duplicate #include headers
  net: filter: be more defensive on div/mod by X==0
  netfilter: Can't fail and free after table replacement
  xen-netback: Trivial format string fix
  net: bcmgenet: Remove unnecessary version.h inclusion
  net: smc911x: Remove unused local variable
  bonding: Inactive slaves should keep inactive flag's value
  netfilter: nf_tables: fix wrong format in request_module()
  netfilter: nf_tables: set names cannot be larger than 15 bytes
  netfilter: nf_conntrack: reserve two bytes for nf_ct_ext->len
  netfilter: Add {ipt,ip6t}_osf aliases for xt_osf
  netfilter: x_tables: allow to use cgroup match for LOCAL_IN nf hooks
  ...

18 files changed, 190 insertions, 113 deletions

diff --git a/drivers/isdn/isdnloop/isdnloop.c b/drivers/isdn/isdnloop/isdnloop.c
index 02125e6a9109..5a4da94aefb0 100644
--- a/drivers/isdn/isdnloop/isdnloop.c
+++ b/drivers/isdn/isdnloop/isdnloop.c
@@ -518,9 +518,9 @@ static isdnloop_stat isdnloop_cmd_table[] =
 static void
 isdnloop_fake_err(isdnloop_card *card)
 {
-	char buf[60];
+	char buf[64];
 
-	sprintf(buf, "E%s", card->omsg);
+	snprintf(buf, sizeof(buf), "E%s", card->omsg);
 	isdnloop_fake(card, buf, -1);
 	isdnloop_fake(card, "NAK", -1);
 }
@@ -903,6 +903,8 @@ isdnloop_parse_cmd(isdnloop_card *card)
 	case 7:
 		/* 0x;EAZ */
 		p += 3;
+		if (strlen(p) >= sizeof(card->eazlist[0]))
+			break;
 		strcpy(card->eazlist[ch - 1], p);
 		break;
 	case 8:
@@ -1070,6 +1072,12 @@ isdnloop_start(isdnloop_card *card, isdnloop_sdef *sdefp)
 		return -EBUSY;
 	if (copy_from_user((char *) &sdef, (char *) sdefp, sizeof(sdef)))
 		return -EFAULT;
+
+	for (i = 0; i < 3; i++) {
+		if (!memchr(sdef.num[i], 0, sizeof(sdef.num[i])))
+			return -EINVAL;
+	}
+
 	spin_lock_irqsave(&card->isdnloop_lock, flags);
 	switch (sdef.ptype) {
 	case ISDN_PTYPE_EURO:
@@ -1127,7 +1135,7 @@ isdnloop_command(isdn_ctrl *c, isdnloop_card *card)
 {
 	ulong a;
 	int i;
-	char cbuf[60];
+	char cbuf[80];
 	isdn_ctrl cmd;
 	isdnloop_cdef cdef;
 
@@ -1192,7 +1200,6 @@ isdnloop_command(isdn_ctrl *c, isdnloop_card *card)
 			break;
 		if ((c->arg & 255) < ISDNLOOP_BCH) {
 			char *p;
-			char dial[50];
 			char dcode[4];
 
 			a = c->arg;
@@ -1204,10 +1211,10 @@ isdnloop_command(isdn_ctrl *c, isdnloop_card *card)
 			} else
 				/* Normal Dial */
 				strcpy(dcode, "CAL");
-			strcpy(dial, p);
-			sprintf(cbuf, "%02d;D%s_R%s,%02d,%02d,%s\n", (int) (a + 1),
-				dcode, dial, c->parm.setup.si1,
-				c->parm.setup.si2, c->parm.setup.eazmsn);
+			snprintf(cbuf, sizeof(cbuf),
+				 "%02d;D%s_R%s,%02d,%02d,%s\n", (int) (a + 1),
+				 dcode, p, c->parm.setup.si1,
+				 c->parm.setup.si2, c->parm.setup.eazmsn);
 			i = isdnloop_writecmd(cbuf, strlen(cbuf), 0, card);
 		}
 		break;
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 95a6ca7d9e51..d9f85464b362 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3077,7 +3077,7 @@ static int bond_open(struct net_device *bond_dev)
 	if (bond_has_slaves(bond)) {
 		read_lock(&bond->curr_slave_lock);
 		bond_for_each_slave(bond, slave, iter) {
-			if ((bond->params.mode == BOND_MODE_ACTIVEBACKUP)
+			if (USES_PRIMARY(bond->params.mode)
 				&& (slave != bond->curr_active_slave)) {
 				bond_set_slave_inactive_flags(slave,
 							      BOND_SLAVE_NOTIFY_NOW);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index 05f4f5f52635..3448cc033ca5 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -21,6 +21,7 @@
 #include <linux/pci.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
+#include <linux/irq.h>
 
 #include "bnx2x.h"
 #include "bnx2x_sriov.h"
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index adf8acbddf56..0966bd04375f 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -34,7 +34,6 @@
 #include <linux/dma-mapping.h>
 #include <linux/pm.h>
 #include <linux/clk.h>
-#include <linux/version.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
diff --git a/drivers/net/ethernet/cadence/at91_ether.c b/drivers/net/ethernet/cadence/at91_ether.c
index ce75de9bae9e..4a79edaf3885 100644
--- a/drivers/net/ethernet/cadence/at91_ether.c
+++ b/drivers/net/ethernet/cadence/at91_ether.c
@@ -342,6 +342,9 @@ static int __init at91ether_probe(struct platform_device *pdev)
 	}
 	clk_enable(lp->pclk);
 
+	lp->hclk = ERR_PTR(-ENOENT);
+	lp->tx_clk = ERR_PTR(-ENOENT);
+
 	/* Install the interrupt handler */
 	dev->irq = platform_get_irq(pdev, 0);
 	res = devm_request_irq(&pdev->dev, dev->irq, at91ether_interrupt, 0, dev->name, dev);
diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h
index e9f7c656ddda..e35c8e0202ad 100644
--- a/drivers/net/ethernet/cisco/enic/enic.h
+++ b/drivers/net/ethernet/cisco/enic/enic.h
@@ -29,6 +29,7 @@
 #include "vnic_stats.h"
 #include "vnic_nic.h"
 #include "vnic_rss.h"
+#include <linux/irq.h>
 
 #define DRV_NAME		"enic"
 #define DRV_DESCRIPTION		"Cisco VIC Ethernet NIC Driver"
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index f31bb5e9d8a9..7b52a88923ef 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -23,6 +23,7 @@
 #include <linux/ethtool.h>
 #include <linux/mii.h>
 #include <linux/timer.h>
+#include <linux/irq.h>
 
 #include <linux/vmalloc.h>
 
diff --git a/drivers/net/ethernet/samsung/Kconfig b/drivers/net/ethernet/samsung/Kconfig
index 7902341f2623..2360d8150777 100644
--- a/drivers/net/ethernet/samsung/Kconfig
+++ b/drivers/net/ethernet/samsung/Kconfig
@@ -3,14 +3,30 @@
 #
 
 config NET_VENDOR_SAMSUNG
-	bool "Samsung Ethernet device"
+	bool "Samsung Ethernet devices"
 	default y
 	---help---
-	  This is the driver for the SXGBE 10G Ethernet IP block found on Samsung
-	  platforms.
+	  If you have a network (Ethernet) chipset belonging to this class,
+	  say Y.
+
+	  Note that the answer to this question does not directly affect
+	  the kernel: saying N will just case the configurator to skip all
+	  the questions about Samsung chipsets. If you say Y, you will be asked
+	  for your specific chipset/driver in the following questions.
 
 if NET_VENDOR_SAMSUNG
 
-source "drivers/net/ethernet/samsung/sxgbe/Kconfig"
+config SXGBE_ETH
+	tristate "Samsung 10G/2.5G/1G SXGBE Ethernet driver"
+	depends on HAS_IOMEM && HAS_DMA
+	select PHYLIB
+	select CRC32
+	select PTP_1588_CLOCK
+	---help---
+	  This is the driver for the SXGBE 10G Ethernet IP block found on
+	  Samsung platforms.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called samsung-sxgbe.
 
 endif # NET_VENDOR_SAMSUNG
diff --git a/drivers/net/ethernet/samsung/sxgbe/Kconfig b/drivers/net/ethernet/samsung/sxgbe/Kconfig
deleted file mode 100644
index d79288c51d0a..000000000000
--- a/drivers/net/ethernet/samsung/sxgbe/Kconfig
+++ /dev/null
@@ -1,9 +0,0 @@
-config SXGBE_ETH
-	tristate "Samsung 10G/2.5G/1G SXGBE Ethernet driver"
-	depends on HAS_IOMEM && HAS_DMA
-	select PHYLIB
-	select CRC32
-	select PTP_1588_CLOCK
-	---help---
-	  This is the driver for the SXGBE 10G Ethernet IP block found on Samsung
-	  platforms.
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.c
index 28f89c41d0cd..4d989ff6c978 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.c
@@ -9,7 +9,6 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
-#include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/export.h>
 #include <linux/io.h>
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
index a72688e8dc6c..27e8c824b204 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
@@ -2113,11 +2113,11 @@ struct sxgbe_priv_data *sxgbe_drv_probe(struct device *device,
 	/* allocate memory resources for Descriptor rings */
 	ret = txring_mem_alloc(priv);
 	if (ret)
-		goto error_free_netdev;
+		goto error_free_hw;
 
 	ret = rxring_mem_alloc(priv);
 	if (ret)
-		goto error_free_netdev;
+		goto error_free_hw;
 
 	ndev->netdev_ops = &sxgbe_netdev_ops;
 
@@ -2163,7 +2163,7 @@ struct sxgbe_priv_data *sxgbe_drv_probe(struct device *device,
 	if (IS_ERR(priv->sxgbe_clk)) {
 		netdev_warn(ndev, "%s: warning: cannot get CSR clock\n",
 			    __func__);
-		goto error_clk_get;
+		goto error_napi_del;
 	}
 
 	/* If a specific clk_csr value is passed from the platform
@@ -2182,24 +2182,27 @@ struct sxgbe_priv_data *sxgbe_drv_probe(struct device *device,
 	if (ret < 0) {
 		netdev_dbg(ndev, "%s: MDIO bus (id: %d) registration failed\n",
 			   __func__, priv->plat->bus_id);
-		goto error_mdio_register;
+		goto error_clk_put;
 	}
 
 	ret = register_netdev(ndev);
 	if (ret) {
 		pr_err("%s: ERROR %i registering the device\n", __func__, ret);
-		goto error_netdev_register;
+		goto error_mdio_unregister;
 	}
 
 	sxgbe_check_ether_addr(priv);
 
 	return priv;
 
-error_mdio_register:
+error_mdio_unregister:
+	sxgbe_mdio_unregister(ndev);
+error_clk_put:
 	clk_put(priv->sxgbe_clk);
-error_clk_get:
-error_netdev_register:
+error_napi_del:
 	netif_napi_del(&priv->napi);
+error_free_hw:
+	kfree(priv->hw);
 error_free_netdev:
 	free_netdev(ndev);
 
@@ -2224,11 +2227,15 @@ int sxgbe_drv_remove(struct net_device *ndev)
 	priv->hw->mac->enable_tx(priv->ioaddr, false);
 	priv->hw->mac->enable_rx(priv->ioaddr, false);
 
-	netif_napi_del(&priv->napi);
+	unregister_netdev(ndev);
 
 	sxgbe_mdio_unregister(ndev);
 
-	unregister_netdev(ndev);
+	clk_put(priv->sxgbe_clk);
+
+	netif_napi_del(&priv->napi);
+
+	kfree(priv->hw);
 
 	free_netdev(ndev);
 
diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c
index 66b05e62f70a..1c44e67c3067 100644
--- a/drivers/net/ethernet/smsc/smc911x.c
+++ b/drivers/net/ethernet/smsc/smc911x.c
@@ -1211,7 +1211,6 @@ static void
 smc911x_rx_dma_irq(int dma, void *data)
 {
 	struct net_device *dev = (struct net_device *)data;
-	unsigned long ioaddr = dev->base_addr;
 	struct smc911x_local *lp = netdev_priv(dev);
 	struct sk_buff *skb = lp->current_rx_skb;
 	unsigned long flags;
diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index a3bbf59eaafd..243513980b51 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -26,6 +26,8 @@
 #include <linux/time.h>
 #include <linux/uaccess.h>
 #include <linux/workqueue.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
 
 #include "cpts.h"
 
diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index 89417ac41083..430bb0db9bc4 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -852,7 +852,7 @@ at86rf212_set_csma_params(struct ieee802154_dev *dev, u8 min_be, u8 max_be,
 	if (rc)
 		return rc;
 
-	return at86rf230_write_subreg(lp, SR_MAX_CSMA_RETRIES, max_be);
+	return at86rf230_write_subreg(lp, SR_MAX_CSMA_RETRIES, retries);
 }
 
 static int
diff --git a/drivers/net/phy/spi_ks8995.c b/drivers/net/phy/spi_ks8995.c
index 4cf5fb922e59..22b047f1fcdc 100644
--- a/drivers/net/phy/spi_ks8995.c
+++ b/drivers/net/phy/spi_ks8995.c
@@ -1,5 +1,5 @@
 /*
- * SPI driver for Micrel/Kendin KS8995M ethernet switch
+ * SPI driver for Micrel/Kendin KS8995M and KSZ8864RMN ethernet switches
  *
  * Copyright (C) 2008 Gabor Juhos <juhosg at openwrt.org>
  *
@@ -70,7 +70,10 @@
 #define KS8995_REG_IAD1		0x76    /* Indirect Access Data 1 */
 #define KS8995_REG_IAD0		0x77    /* Indirect Access Data 0 */
 
+#define KSZ8864_REG_ID1		0xfe	/* Chip ID in bit 7 */
+
 #define KS8995_REGS_SIZE	0x80
+#define KSZ8864_REGS_SIZE	0x100
 
 #define ID1_CHIPID_M		0xf
 #define ID1_CHIPID_S		4
@@ -94,6 +97,7 @@ struct ks8995_switch {
 	struct spi_device	*spi;
 	struct mutex		lock;
 	struct ks8995_pdata	*pdata;
+	struct bin_attribute	regs_attr;
 };
 
 static inline u8 get_chip_id(u8 val)
@@ -216,11 +220,11 @@ static ssize_t ks8995_registers_read(struct file *filp, struct kobject *kobj,
 	dev = container_of(kobj, struct device, kobj);
 	ks8995 = dev_get_drvdata(dev);
 
-	if (unlikely(off > KS8995_REGS_SIZE))
+	if (unlikely(off > ks8995->regs_attr.size))
 		return 0;
 
-	if ((off + count) > KS8995_REGS_SIZE)
-		count = KS8995_REGS_SIZE - off;
+	if ((off + count) > ks8995->regs_attr.size)
+		count = ks8995->regs_attr.size - off;
 
 	if (unlikely(!count))
 		return count;
@@ -238,11 +242,11 @@ static ssize_t ks8995_registers_write(struct file *filp, struct kobject *kobj,
 	dev = container_of(kobj, struct device, kobj);
 	ks8995 = dev_get_drvdata(dev);
 
-	if (unlikely(off >= KS8995_REGS_SIZE))
+	if (unlikely(off >= ks8995->regs_attr.size))
 		return -EFBIG;
 
-	if ((off + count) > KS8995_REGS_SIZE)
-		count = KS8995_REGS_SIZE - off;
+	if ((off + count) > ks8995->regs_attr.size)
+		count = ks8995->regs_attr.size - off;
 
 	if (unlikely(!count))
 		return count;
@@ -251,7 +255,7 @@ static ssize_t ks8995_registers_write(struct file *filp, struct kobject *kobj,
 }
 
 
-static struct bin_attribute ks8995_registers_attr = {
+static const struct bin_attribute ks8995_registers_attr = {
 	.attr = {
 		.name   = "registers",
 		.mode   = S_IRUSR | S_IWUSR,
@@ -306,20 +310,44 @@ static int ks8995_probe(struct spi_device *spi)
 		goto err_drvdata;
 	}
 
+	memcpy(&ks->regs_attr, &ks8995_registers_attr, sizeof(ks->regs_attr));
+	if (get_chip_id(ids[1]) != CHIPID_M) {
+		u8 val;
+
+		/* Check if this is a KSZ8864RMN */
+		err = ks8995_read(ks, &val, KSZ8864_REG_ID1, sizeof(val));
+		if (err < 0) {
+			dev_err(&spi->dev,
+				"unable to read chip id register, err=%d\n",
+				err);
+			goto err_drvdata;
+		}
+		if ((val & 0x80) == 0) {
+			dev_err(&spi->dev, "unknown chip:%02x,0\n", ids[1]);
+			goto err_drvdata;
+		}
+		ks->regs_attr.size = KSZ8864_REGS_SIZE;
+	}
+
 	err = ks8995_reset(ks);
 	if (err)
 		goto err_drvdata;
 
-	err = sysfs_create_bin_file(&spi->dev.kobj, &ks8995_registers_attr);
+	err = sysfs_create_bin_file(&spi->dev.kobj, &ks->regs_attr);
 	if (err) {
 		dev_err(&spi->dev, "unable to create sysfs file, err=%d\n",
 				    err);
 		goto err_drvdata;
 	}
 
-	dev_info(&spi->dev, "KS89%02X device found, Chip ID:%01x, "
-			"Revision:%01x\n", ids[0],
-			get_chip_id(ids[1]), get_chip_rev(ids[1]));
+	if (get_chip_id(ids[1]) == CHIPID_M) {
+		dev_info(&spi->dev,
+			 "KS8995 device found, Chip ID:%x, Revision:%x\n",
+			 get_chip_id(ids[1]), get_chip_rev(ids[1]));
+	} else {
+		dev_info(&spi->dev, "KSZ8864 device found, Revision:%x\n",
+			 get_chip_rev(ids[1]));
+	}
 
 	return 0;
 
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 0d862a5077ab..c55e316373a1 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -871,6 +871,9 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 	if (err)
 		return err;
 
+	if (vxlan->default_dst.remote_ip.sa.sa_family != ip.sa.sa_family)
+		return -EAFNOSUPPORT;
+
 	spin_lock_bh(&vxlan->hash_lock);
 	err = vxlan_fdb_create(vxlan, addr, &ip, ndm->ndm_state, flags,
 			       port, vni, ifindex, ndm->ndm_flags);
@@ -2601,9 +2604,10 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
 	vni = nla_get_u32(data[IFLA_VXLAN_ID]);
 	dst->remote_vni = vni;
 
+	/* Unless IPv6 is explicitly requested, assume IPv4 */
+	dst->remote_ip.sa.sa_family = AF_INET;
 	if (data[IFLA_VXLAN_GROUP]) {
 		dst->remote_ip.sin.sin_addr.s_addr = nla_get_be32(data[IFLA_VXLAN_GROUP]);
-		dst->remote_ip.sa.sa_family = AF_INET;
 	} else if (data[IFLA_VXLAN_GROUP6]) {
 		if (!IS_ENABLED(CONFIG_IPV6))
 			return -EPFNOSUPPORT;
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 89d1d0556b6e..630a3fcf65bc 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -124,6 +124,7 @@ struct xenvif {
 	struct pending_tx_info pending_tx_info[MAX_PENDING_REQS];
 	grant_handle_t grant_tx_handle[MAX_PENDING_REQS];
 
+	struct gnttab_copy tx_copy_ops[MAX_PENDING_REQS];
 	struct gnttab_map_grant_ref tx_map_ops[MAX_PENDING_REQS];
 	struct gnttab_unmap_grant_ref tx_unmap_ops[MAX_PENDING_REQS];
 	/* passed to gnttab_[un]map_refs with pages under (un)mapping */
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 3f021e054ba1..76665405c5aa 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -820,13 +820,13 @@ struct xenvif_tx_cb {
 
 #define XENVIF_TX_CB(skb) ((struct xenvif_tx_cb *)(skb)->cb)
 
-static inline void xenvif_tx_create_gop(struct xenvif *vif,
-					u16 pending_idx,
-					struct xen_netif_tx_request *txp,
-					struct gnttab_map_grant_ref *gop)
+static inline void xenvif_tx_create_map_op(struct xenvif *vif,
+					  u16 pending_idx,
+					  struct xen_netif_tx_request *txp,
+					  struct gnttab_map_grant_ref *mop)
 {
-	vif->pages_to_map[gop-vif->tx_map_ops] = vif->mmap_pages[pending_idx];
-	gnttab_set_map_op(gop, idx_to_kaddr(vif, pending_idx),
+	vif->pages_to_map[mop-vif->tx_map_ops] = vif->mmap_pages[pending_idx];
+	gnttab_set_map_op(mop, idx_to_kaddr(vif, pending_idx),
 			  GNTMAP_host_map | GNTMAP_readonly,
 			  txp->gref, vif->domid);
 
@@ -880,7 +880,7 @@ static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif,
 	     shinfo->nr_frags++, txp++, gop++) {
 		index = pending_index(vif->pending_cons++);
 		pending_idx = vif->pending_ring[index];
-		xenvif_tx_create_gop(vif, pending_idx, txp, gop);
+		xenvif_tx_create_map_op(vif, pending_idx, txp, gop);
 		frag_set_pending_idx(&frags[shinfo->nr_frags], pending_idx);
 	}
 
@@ -900,7 +900,7 @@ static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif,
 		     shinfo->nr_frags++, txp++, gop++) {
 			index = pending_index(vif->pending_cons++);
 			pending_idx = vif->pending_ring[index];
-			xenvif_tx_create_gop(vif, pending_idx, txp, gop);
+			xenvif_tx_create_map_op(vif, pending_idx, txp, gop);
 			frag_set_pending_idx(&frags[shinfo->nr_frags],
 					     pending_idx);
 		}
@@ -940,38 +940,42 @@ static inline void xenvif_grant_handle_reset(struct xenvif *vif,
 
 static int xenvif_tx_check_gop(struct xenvif *vif,
 			       struct sk_buff *skb,
-			       struct gnttab_map_grant_ref **gopp)
+			       struct gnttab_map_grant_ref **gopp_map,
+			       struct gnttab_copy **gopp_copy)
 {
-	struct gnttab_map_grant_ref *gop = *gopp;
+	struct gnttab_map_grant_ref *gop_map = *gopp_map;
 	u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx;
 	struct skb_shared_info *shinfo = skb_shinfo(skb);
-	struct pending_tx_info *tx_info;
 	int nr_frags = shinfo->nr_frags;
-	int i, err, start;
+	int i, err;
 	struct sk_buff *first_skb = NULL;
 
 	/* Check status of header. */
-	err = gop->status;
-	if (unlikely(err))
+	err = (*gopp_copy)->status;
+	(*gopp_copy)++;
+	if (unlikely(err)) {
+		if (net_ratelimit())
+			netdev_dbg(vif->dev,
+				   "Grant copy of header failed! status: %d pending_idx: %u ref: %u\n",
+				   (*gopp_copy)->status,
+				   pending_idx,
+				   (*gopp_copy)->source.u.ref);
 		xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_ERROR);
-	else
-		xenvif_grant_handle_set(vif, pending_idx , gop->handle);
-
-	/* Skip first skb fragment if it is on same page as header fragment. */
-	start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx);
+	}
 
 check_frags:
-	for (i = start; i < nr_frags; i++) {
+	for (i = 0; i < nr_frags; i++, gop_map++) {
 		int j, newerr;
 
 		pending_idx = frag_get_pending_idx(&shinfo->frags[i]);
-		tx_info = &vif->pending_tx_info[pending_idx];
 
 		/* Check error status: if okay then remember grant handle. */
-		newerr = (++gop)->status;
+		newerr = gop_map->status;
 
 		if (likely(!newerr)) {
-			xenvif_grant_handle_set(vif, pending_idx , gop->handle);
+			xenvif_grant_handle_set(vif,
+						pending_idx,
+						gop_map->handle);
 			/* Had a previous error? Invalidate this fragment. */
 			if (unlikely(err))
 				xenvif_idx_unmap(vif, pending_idx);
@@ -979,18 +983,20 @@ check_frags:
 		}
 
 		/* Error on this fragment: respond to client with an error. */
+		if (net_ratelimit())
+			netdev_dbg(vif->dev,
+				   "Grant map of %d. frag failed! status: %d pending_idx: %u ref: %u\n",
+				   i,
+				   gop_map->status,
+				   pending_idx,
+				   gop_map->ref);
 		xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_ERROR);
 
 		/* Not the first error? Preceding frags already invalidated. */
 		if (err)
 			continue;
-		/* First error: invalidate header and preceding fragments. */
-		if (!first_skb)
-			pending_idx = XENVIF_TX_CB(skb)->pending_idx;
-		else
-			pending_idx = XENVIF_TX_CB(skb)->pending_idx;
-		xenvif_idx_unmap(vif, pending_idx);
-		for (j = start; j < i; j++) {
+		/* First error: invalidate preceding fragments. */
+		for (j = 0; j < i; j++) {
 			pending_idx = frag_get_pending_idx(&shinfo->frags[j]);
 			xenvif_idx_unmap(vif, pending_idx);
 		}
@@ -1004,7 +1010,6 @@ check_frags:
 		skb = shinfo->frag_list;
 		shinfo = skb_shinfo(skb);
 		nr_frags = shinfo->nr_frags;
-		start = 0;
 
 		goto check_frags;
 	}
@@ -1015,15 +1020,13 @@ check_frags:
 	if (first_skb && err) {
 		int j;
 		shinfo = skb_shinfo(first_skb);
-		pending_idx = XENVIF_TX_CB(skb)->pending_idx;
-		start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx);
-		for (j = start; j < shinfo->nr_frags; j++) {
+		for (j = 0; j < shinfo->nr_frags; j++) {
 			pending_idx = frag_get_pending_idx(&shinfo->frags[j]);
 			xenvif_idx_unmap(vif, pending_idx);
 		}
 	}
 
-	*gopp = gop + 1;
+	*gopp_map = gop_map;
 	return err;
 }
 
@@ -1034,9 +1037,6 @@ static void xenvif_fill_frags(struct xenvif *vif, struct sk_buff *skb)
 	int i;
 	u16 prev_pending_idx = INVALID_PENDING_IDX;
 
-	if (skb_shinfo(skb)->destructor_arg)
-		prev_pending_idx = XENVIF_TX_CB(skb)->pending_idx;
-
 	for (i = 0; i < nr_frags; i++) {
 		skb_frag_t *frag = shinfo->frags + i;
 		struct xen_netif_tx_request *txp;
@@ -1046,10 +1046,10 @@ static void xenvif_fill_frags(struct xenvif *vif, struct sk_buff *skb)
 		pending_idx = frag_get_pending_idx(frag);
 
 		/* If this is not the first frag, chain it to the previous*/
-		if (unlikely(prev_pending_idx == INVALID_PENDING_IDX))
+		if (prev_pending_idx == INVALID_PENDING_IDX)
 			skb_shinfo(skb)->destructor_arg =
 				&callback_param(vif, pending_idx);
-		else if (likely(pending_idx != prev_pending_idx))
+		else
 			callback_param(vif, prev_pending_idx).ctx =
 				&callback_param(vif, pending_idx);
 
@@ -1189,7 +1189,10 @@ static bool tx_credit_exceeded(struct xenvif *vif, unsigned size)
 	return false;
 }
 
-static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget)
+static void xenvif_tx_build_gops(struct xenvif *vif,
+				     int budget,
+				     unsigned *copy_ops,
+				     unsigned *map_ops)
 {
 	struct gnttab_map_grant_ref *gop = vif->tx_map_ops, *request_gop;
 	struct sk_buff *skb;
@@ -1292,22 +1295,36 @@ static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget)
 			}
 		}
 
-		xenvif_tx_create_gop(vif, pending_idx, &txreq, gop);
-
-		gop++;
-
 		XENVIF_TX_CB(skb)->pending_idx = pending_idx;
 
 		__skb_put(skb, data_len);
+		vif->tx_copy_ops[*copy_ops].source.u.ref = txreq.gref;
+		vif->tx_copy_ops[*copy_ops].source.domid = vif->domid;
+		vif->tx_copy_ops[*copy_ops].source.offset = txreq.offset;
+
+		vif->tx_copy_ops[*copy_ops].dest.u.gmfn =
+			virt_to_mfn(skb->data);
+		vif->tx_copy_ops[*copy_ops].dest.domid = DOMID_SELF;
+		vif->tx_copy_ops[*copy_ops].dest.offset =
+			offset_in_page(skb->data);
+
+		vif->tx_copy_ops[*copy_ops].len = data_len;
+		vif->tx_copy_ops[*copy_ops].flags = GNTCOPY_source_gref;
+
+		(*copy_ops)++;
 
 		skb_shinfo(skb)->nr_frags = ret;
 		if (data_len < txreq.size) {
 			skb_shinfo(skb)->nr_frags++;
 			frag_set_pending_idx(&skb_shinfo(skb)->frags[0],
 					     pending_idx);
+			xenvif_tx_create_map_op(vif, pending_idx, &txreq, gop);
+			gop++;
 		} else {
 			frag_set_pending_idx(&skb_shinfo(skb)->frags[0],
 					     INVALID_PENDING_IDX);
+			memcpy(&vif->pending_tx_info[pending_idx].req, &txreq,
+			       sizeof(txreq));
 		}
 
 		vif->pending_cons++;
@@ -1324,11 +1341,13 @@ static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget)
 
 		vif->tx.req_cons = idx;
 
-		if ((gop-vif->tx_map_ops) >= ARRAY_SIZE(vif->tx_map_ops))
+		if (((gop-vif->tx_map_ops) >= ARRAY_SIZE(vif->tx_map_ops)) ||
+		    (*copy_ops >= ARRAY_SIZE(vif->tx_copy_ops)))
 			break;
 	}
 
-	return gop - vif->tx_map_ops;
+	(*map_ops) = gop - vif->tx_map_ops;
+	return;
 }
 
 /* Consolidate skb with a frag_list into a brand new one with local pages on
@@ -1399,7 +1418,8 @@ static int xenvif_handle_frag_list(struct xenvif *vif, struct sk_buff *skb)
 
 static int xenvif_tx_submit(struct xenvif *vif)
 {
-	struct gnttab_map_grant_ref *gop = vif->tx_map_ops;
+	struct gnttab_map_grant_ref *gop_map = vif->tx_map_ops;
+	struct gnttab_copy *gop_copy = vif->tx_copy_ops;
 	struct sk_buff *skb;
 	int work_done = 0;
 
@@ -1412,27 +1432,22 @@ static int xenvif_tx_submit(struct xenvif *vif)
 		txp = &vif->pending_tx_info[pending_idx].req;
 
 		/* Check the remap error code. */
-		if (unlikely(xenvif_tx_check_gop(vif, skb, &gop))) {
-			netdev_dbg(vif->dev, "netback grant failed.\n");
+		if (unlikely(xenvif_tx_check_gop(vif, skb, &gop_map, &gop_copy))) {
 			skb_shinfo(skb)->nr_frags = 0;
 			kfree_skb(skb);
 			continue;
 		}
 
 		data_len = skb->len;
-		memcpy(skb->data,
-		       (void *)(idx_to_kaddr(vif, pending_idx)|txp->offset),
-		       data_len);
 		callback_param(vif, pending_idx).ctx = NULL;
 		if (data_len < txp->size) {
 			/* Append the packet payload as a fragment. */
 			txp->offset += data_len;
 			txp->size -= data_len;
-			skb_shinfo(skb)->destructor_arg =
-				&callback_param(vif, pending_idx);
 		} else {
 			/* Schedule a response immediately. */
-			xenvif_idx_unmap(vif, pending_idx);
+			xenvif_idx_release(vif, pending_idx,
+					   XEN_NETIF_RSP_OKAY);
 		}
 
 		if (txp->flags & XEN_NETTXF_csum_blank)
@@ -1611,22 +1626,25 @@ static inline void xenvif_tx_dealloc_action(struct xenvif *vif)
 /* Called after netfront has transmitted */
 int xenvif_tx_action(struct xenvif *vif, int budget)
 {
-	unsigned nr_gops;
+	unsigned nr_mops, nr_cops = 0;
 	int work_done, ret;
 
 	if (unlikely(!tx_work_todo(vif)))
 		return 0;
 
-	nr_gops = xenvif_tx_build_gops(vif, budget);
+	xenvif_tx_build_gops(vif, budget, &nr_cops, &nr_mops);
 
-	if (nr_gops == 0)
+	if (nr_cops == 0)
 		return 0;
 
-	ret = gnttab_map_refs(vif->tx_map_ops,
-			      NULL,
-			      vif->pages_to_map,
-			      nr_gops);
-	BUG_ON(ret);
+	gnttab_batch_copy(vif->tx_copy_ops, nr_cops);
+	if (nr_mops != 0) {
+		ret = gnttab_map_refs(vif->tx_map_ops,
+				      NULL,
+				      vif->pages_to_map,
+				      nr_mops);
+		BUG_ON(ret);
+	}
 
 	work_done = xenvif_tx_submit(vif);