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

Pull networking updates from David Miller:

 1) Seccomp BPF filters can now be JIT'd, from Alexei Starovoitov.

 2) Multiqueue support in xen-netback and xen-netfront, from Andrew J
    Benniston.

 3) Allow tweaking of aggregation settings in cdc_ncm driver, from Bjørn
    Mork.

 4) BPF now has a "random" opcode, from Chema Gonzalez.

 5) Add more BPF documentation and improve test framework, from Daniel
    Borkmann.

 6) Support TCP fastopen over ipv6, from Daniel Lee.

 7) Add software TSO helper functions and use them to support software
    TSO in mvneta and mv643xx_eth drivers.  From Ezequiel Garcia.

 8) Support software TSO in fec driver too, from Nimrod Andy.

 9) Add Broadcom SYSTEMPORT driver, from Florian Fainelli.

10) Handle broadcasts more gracefully over macvlan when there are large
    numbers of interfaces configured, from Herbert Xu.

11) Allow more control over fwmark used for non-socket based responses,
    from Lorenzo Colitti.

12) Do TCP congestion window limiting based upon measurements, from Neal
    Cardwell.

13) Support busy polling in SCTP, from Neal Horman.

14) Allow RSS key to be configured via ethtool, from Venkata Duvvuru.

15) Bridge promisc mode handling improvements from Vlad Yasevich.

16) Don't use inetpeer entries to implement ID generation any more, it
    performs poorly, from Eric Dumazet.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1522 commits)
  rtnetlink: fix userspace API breakage for iproute2 < v3.9.0
  tcp: fixing TLP's FIN recovery
  net: fec: Add software TSO support
  net: fec: Add Scatter/gather support
  net: fec: Increase buffer descriptor entry number
  net: fec: Factorize feature setting
  net: fec: Enable IP header hardware checksum
  net: fec: Factorize the .xmit transmit function
  bridge: fix compile error when compiling without IPv6 support
  bridge: fix smatch warning / potential null pointer dereference
  via-rhine: fix full-duplex with autoneg disable
  bnx2x: Enlarge the dorq threshold for VFs
  bnx2x: Check for UNDI in uncommon branch
  bnx2x: Fix 1G-baseT link
  bnx2x: Fix link for KR with swapped polarity lane
  sctp: Fix sk_ack_backlog wrap-around problem
  net/core: Add VF link state control policy
  net/fsl: xgmac_mdio is dependent on OF_MDIO
  net/fsl: Make xgmac_mdio read error message useful
  net_sched: drr: warn when qdisc is not work conserving
  ...

1 files changed, 198 insertions, 17 deletions

diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 640ba0e5831c..17cb912793fa 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -557,6 +557,23 @@ err_out:
 	return ret;
 }
 
+static int ethtool_copy_validate_indir(u32 *indir, void __user *useraddr,
+					struct ethtool_rxnfc *rx_rings,
+					u32 size)
+{
+	int i;
+
+	if (copy_from_user(indir, useraddr, size * sizeof(indir[0])))
+		return -EFAULT;
+
+	/* Validate ring indices */
+	for (i = 0; i < size; i++)
+		if (indir[i] >= rx_rings->data)
+			return -EINVAL;
+
+	return 0;
+}
+
 static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev,
 						     void __user *useraddr)
 {
@@ -565,7 +582,7 @@ static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev,
 	int ret;
 
 	if (!dev->ethtool_ops->get_rxfh_indir_size ||
-	    !dev->ethtool_ops->get_rxfh_indir)
+	    !dev->ethtool_ops->get_rxfh)
 		return -EOPNOTSUPP;
 	dev_size = dev->ethtool_ops->get_rxfh_indir_size(dev);
 	if (dev_size == 0)
@@ -591,7 +608,7 @@ static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev,
 	if (!indir)
 		return -ENOMEM;
 
-	ret = dev->ethtool_ops->get_rxfh_indir(dev, indir);
+	ret = dev->ethtool_ops->get_rxfh(dev, indir, NULL);
 	if (ret)
 		goto out;
 
@@ -613,8 +630,9 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev,
 	u32 *indir;
 	const struct ethtool_ops *ops = dev->ethtool_ops;
 	int ret;
+	u32 ringidx_offset = offsetof(struct ethtool_rxfh_indir, ring_index[0]);
 
-	if (!ops->get_rxfh_indir_size || !ops->set_rxfh_indir ||
+	if (!ops->get_rxfh_indir_size || !ops->set_rxfh ||
 	    !ops->get_rxnfc)
 		return -EOPNOTSUPP;
 
@@ -643,28 +661,184 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev,
 		for (i = 0; i < dev_size; i++)
 			indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data);
 	} else {
-		if (copy_from_user(indir,
-				  useraddr +
-				  offsetof(struct ethtool_rxfh_indir,
-					   ring_index[0]),
-				  dev_size * sizeof(indir[0]))) {
+		ret = ethtool_copy_validate_indir(indir,
+						  useraddr + ringidx_offset,
+						  &rx_rings,
+						  dev_size);
+		if (ret)
+			goto out;
+	}
+
+	ret = ops->set_rxfh(dev, indir, NULL);
+
+out:
+	kfree(indir);
+	return ret;
+}
+
+static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
+					       void __user *useraddr)
+{
+	int ret;
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+	u32 user_indir_size, user_key_size;
+	u32 dev_indir_size = 0, dev_key_size = 0;
+	struct ethtool_rxfh rxfh;
+	u32 total_size;
+	u32 indir_bytes;
+	u32 *indir = NULL;
+	u8 *hkey = NULL;
+	u8 *rss_config;
+
+	if (!(dev->ethtool_ops->get_rxfh_indir_size ||
+	      dev->ethtool_ops->get_rxfh_key_size) ||
+	      !dev->ethtool_ops->get_rxfh)
+		return -EOPNOTSUPP;
+
+	if (ops->get_rxfh_indir_size)
+		dev_indir_size = ops->get_rxfh_indir_size(dev);
+	if (ops->get_rxfh_key_size)
+		dev_key_size = ops->get_rxfh_key_size(dev);
+
+	if ((dev_key_size + dev_indir_size) == 0)
+		return -EOPNOTSUPP;
+
+	if (copy_from_user(&rxfh, useraddr, sizeof(rxfh)))
+		return -EFAULT;
+	user_indir_size = rxfh.indir_size;
+	user_key_size = rxfh.key_size;
+
+	/* Check that reserved fields are 0 for now */
+	if (rxfh.rss_context || rxfh.rsvd[0] || rxfh.rsvd[1])
+		return -EINVAL;
+
+	rxfh.indir_size = dev_indir_size;
+	rxfh.key_size = dev_key_size;
+	if (copy_to_user(useraddr, &rxfh, sizeof(rxfh)))
+		return -EFAULT;
+
+	/* If the user buffer size is 0, this is just a query for the
+	 * device table size and key size.  Otherwise, if the User size is
+	 * not equal to device table size or key size it's an error.
+	 */
+	if (!user_indir_size && !user_key_size)
+		return 0;
+
+	if ((user_indir_size && (user_indir_size != dev_indir_size)) ||
+	    (user_key_size && (user_key_size != dev_key_size)))
+		return -EINVAL;
+
+	indir_bytes = user_indir_size * sizeof(indir[0]);
+	total_size = indir_bytes + user_key_size;
+	rss_config = kzalloc(total_size, GFP_USER);
+	if (!rss_config)
+		return -ENOMEM;
+
+	if (user_indir_size)
+		indir = (u32 *)rss_config;
+
+	if (user_key_size)
+		hkey = rss_config + indir_bytes;
+
+	ret = dev->ethtool_ops->get_rxfh(dev, indir, hkey);
+	if (!ret) {
+		if (copy_to_user(useraddr +
+				 offsetof(struct ethtool_rxfh, rss_config[0]),
+				 rss_config, total_size))
 			ret = -EFAULT;
+	}
+
+	kfree(rss_config);
+
+	return ret;
+}
+
+static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
+					       void __user *useraddr)
+{
+	int ret;
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+	struct ethtool_rxnfc rx_rings;
+	struct ethtool_rxfh rxfh;
+	u32 dev_indir_size = 0, dev_key_size = 0, i;
+	u32 *indir = NULL, indir_bytes = 0;
+	u8 *hkey = NULL;
+	u8 *rss_config;
+	u32 rss_cfg_offset = offsetof(struct ethtool_rxfh, rss_config[0]);
+
+	if (!(ops->get_rxfh_indir_size || ops->get_rxfh_key_size) ||
+	    !ops->get_rxnfc || !ops->set_rxfh)
+		return -EOPNOTSUPP;
+
+	if (ops->get_rxfh_indir_size)
+		dev_indir_size = ops->get_rxfh_indir_size(dev);
+	if (ops->get_rxfh_key_size)
+		dev_key_size = dev->ethtool_ops->get_rxfh_key_size(dev);
+	if ((dev_key_size + dev_indir_size) == 0)
+		return -EOPNOTSUPP;
+
+	if (copy_from_user(&rxfh, useraddr, sizeof(rxfh)))
+		return -EFAULT;
+
+	/* Check that reserved fields are 0 for now */
+	if (rxfh.rss_context || rxfh.rsvd[0] || rxfh.rsvd[1])
+		return -EINVAL;
+
+	/* If either indir or hash key is valid, proceed further.
+	 * It is not valid to request that both be unchanged.
+	 */
+	if ((rxfh.indir_size &&
+	     rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE &&
+	     rxfh.indir_size != dev_indir_size) ||
+	    (rxfh.key_size && (rxfh.key_size != dev_key_size)) ||
+	    (rxfh.indir_size == ETH_RXFH_INDIR_NO_CHANGE &&
+	     rxfh.key_size == 0))
+		return -EINVAL;
+
+	if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE)
+		indir_bytes = dev_indir_size * sizeof(indir[0]);
+
+	rss_config = kzalloc(indir_bytes + rxfh.key_size, GFP_USER);
+	if (!rss_config)
+		return -ENOMEM;
+
+	rx_rings.cmd = ETHTOOL_GRXRINGS;
+	ret = ops->get_rxnfc(dev, &rx_rings, NULL);
+	if (ret)
+		goto out;
+
+	/* rxfh.indir_size == 0 means reset the indir table to default.
+	 * rxfh.indir_size == ETH_RXFH_INDIR_NO_CHANGE means leave it unchanged.
+	 */
+	if (rxfh.indir_size &&
+	    rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) {
+		indir = (u32 *)rss_config;
+		ret = ethtool_copy_validate_indir(indir,
+						  useraddr + rss_cfg_offset,
+						  &rx_rings,
+						  rxfh.indir_size);
+		if (ret)
 			goto out;
-		}
+	} else if (rxfh.indir_size == 0) {
+		indir = (u32 *)rss_config;
+		for (i = 0; i < dev_indir_size; i++)
+			indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data);
+	}
 
-		/* Validate ring indices */
-		for (i = 0; i < dev_size; i++) {
-			if (indir[i] >= rx_rings.data) {
-				ret = -EINVAL;
-				goto out;
-			}
+	if (rxfh.key_size) {
+		hkey = rss_config + indir_bytes;
+		if (copy_from_user(hkey,
+				   useraddr + rss_cfg_offset + indir_bytes,
+				   rxfh.key_size)) {
+			ret = -EFAULT;
+			goto out;
 		}
 	}
 
-	ret = ops->set_rxfh_indir(dev, indir);
+	ret = ops->set_rxfh(dev, indir, hkey);
 
 out:
-	kfree(indir);
+	kfree(rss_config);
 	return ret;
 }
 
@@ -1491,6 +1665,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
 	case ETHTOOL_GRXCLSRULE:
 	case ETHTOOL_GRXCLSRLALL:
 	case ETHTOOL_GRXFHINDIR:
+	case ETHTOOL_GRSSH:
 	case ETHTOOL_GFEATURES:
 	case ETHTOOL_GCHANNELS:
 	case ETHTOOL_GET_TS_INFO:
@@ -1628,6 +1803,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
 	case ETHTOOL_SRXFHINDIR:
 		rc = ethtool_set_rxfh_indir(dev, useraddr);
 		break;
+	case ETHTOOL_GRSSH:
+		rc = ethtool_get_rxfh(dev, useraddr);
+		break;
+	case ETHTOOL_SRSSH:
+		rc = ethtool_set_rxfh(dev, useraddr);
+		break;
 	case ETHTOOL_GFEATURES:
 		rc = ethtool_get_features(dev, useraddr);
 		break;