From 2f657a600409f1961d67642fe384a9d4be71d36a Mon Sep 17 00:00:00 2001
From: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Date: Fri, 29 Sep 2017 17:19:20 -0400
Subject: net: dsa: change dsa_ptr for a dsa_port

With DSA, a master net device (CPU facing interface) has a dsa_ptr
pointer to which hangs a dsa_switch_tree. This is not correct because a
master interface is wired to a dedicated switch port, and because we can
theoretically have several master interfaces pointing to several CPU
ports of the same switch fabric.

Change the master interface's dsa_ptr for the CPU dsa_port pointer.
This is a step towards supporting multiple CPU ports.

Signed-off-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux/netdevice.h')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index f535779d9dc1..e1d6ef130611 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -55,7 +55,7 @@
 struct netpoll_info;
 struct device;
 struct phy_device;
-struct dsa_switch_tree;
+struct dsa_port;
 
 /* 802.11 specific */
 struct wireless_dev;
@@ -1752,7 +1752,7 @@ struct net_device {
 	struct vlan_info __rcu	*vlan_info;
 #endif
 #if IS_ENABLED(CONFIG_NET_DSA)
-	struct dsa_switch_tree	*dsa_ptr;
+	struct dsa_port		*dsa_ptr;
 #endif
 #if IS_ENABLED(CONFIG_TIPC)
 	struct tipc_bearer __rcu *tipc_ptr;
-- 
cgit v1.2.3


From 6c5570016b972d9b1f0f6c2dca9cc0422b1f92bf Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 2 Oct 2017 23:50:05 +0200
Subject: net: core: decouple ifalias get/set from rtnl lock

Device alias can be set by either rtnetlink (rtnl is held) or sysfs.

rtnetlink hold the rtnl mutex, sysfs acquires it for this purpose.
Add an extra mutex for it and use rcu to protect concurrent accesses.

This allows the sysfs path to not take rtnl and would later allow
to not hold it when dumping ifalias.

Based on suggestion from Eric Dumazet.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  8 +++++++-
 net/core/dev.c            | 52 +++++++++++++++++++++++++++++++++++------------
 net/core/net-sysfs.c      | 17 ++++++++--------
 net/core/rtnetlink.c      | 13 ++++++++++--
 4 files changed, 65 insertions(+), 25 deletions(-)

(limited to 'include/linux/netdevice.h')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index e1d6ef130611..d04424cfffba 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -826,6 +826,11 @@ struct xfrmdev_ops {
 };
 #endif
 
+struct dev_ifalias {
+	struct rcu_head rcuhead;
+	char ifalias[];
+};
+
 /*
  * This structure defines the management hooks for network devices.
  * The following hooks can be defined; unless noted otherwise, they are
@@ -1632,7 +1637,7 @@ enum netdev_priv_flags {
 struct net_device {
 	char			name[IFNAMSIZ];
 	struct hlist_node	name_hlist;
-	char 			*ifalias;
+	struct dev_ifalias	__rcu *ifalias;
 	/*
 	 *	I/O specific fields
 	 *	FIXME: Merge these and struct ifmap into one
@@ -3275,6 +3280,7 @@ void __dev_notify_flags(struct net_device *, unsigned int old_flags,
 			unsigned int gchanges);
 int dev_change_name(struct net_device *, const char *);
 int dev_set_alias(struct net_device *, const char *, size_t);
+int dev_get_alias(const struct net_device *, char *, size_t);
 int dev_change_net_namespace(struct net_device *, struct net *, const char *);
 int __dev_set_mtu(struct net_device *, int);
 int dev_set_mtu(struct net_device *, int);
diff --git a/net/core/dev.c b/net/core/dev.c
index e350c768d4b5..1770097cfd86 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -188,6 +188,8 @@ static struct napi_struct *napi_by_id(unsigned int napi_id);
 DEFINE_RWLOCK(dev_base_lock);
 EXPORT_SYMBOL(dev_base_lock);
 
+static DEFINE_MUTEX(ifalias_mutex);
+
 /* protects napi_hash addition/deletion and napi_gen_id */
 static DEFINE_SPINLOCK(napi_hash_lock);
 
@@ -1265,29 +1267,53 @@ rollback:
  */
 int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
 {
-	char *new_ifalias;
-
-	ASSERT_RTNL();
+	struct dev_ifalias *new_alias = NULL;
 
 	if (len >= IFALIASZ)
 		return -EINVAL;
 
-	if (!len) {
-		kfree(dev->ifalias);
-		dev->ifalias = NULL;
-		return 0;
+	if (len) {
+		new_alias = kmalloc(sizeof(*new_alias) + len + 1, GFP_KERNEL);
+		if (!new_alias)
+			return -ENOMEM;
+
+		memcpy(new_alias->ifalias, alias, len);
+		new_alias->ifalias[len] = 0;
 	}
 
-	new_ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL);
-	if (!new_ifalias)
-		return -ENOMEM;
-	dev->ifalias = new_ifalias;
-	memcpy(dev->ifalias, alias, len);
-	dev->ifalias[len] = 0;
+	mutex_lock(&ifalias_mutex);
+	rcu_swap_protected(dev->ifalias, new_alias,
+			   mutex_is_locked(&ifalias_mutex));
+	mutex_unlock(&ifalias_mutex);
+
+	if (new_alias)
+		kfree_rcu(new_alias, rcuhead);
 
 	return len;
 }
 
+/**
+ *	dev_get_alias - get ifalias of a device
+ *	@dev: device
+ *	@alias: buffer to store name of ifalias
+ *	@len: size of buffer
+ *
+ *	get ifalias for a device.  Caller must make sure dev cannot go
+ *	away,  e.g. rcu read lock or own a reference count to device.
+ */
+int dev_get_alias(const struct net_device *dev, char *name, size_t len)
+{
+	const struct dev_ifalias *alias;
+	int ret = 0;
+
+	rcu_read_lock();
+	alias = rcu_dereference(dev->ifalias);
+	if (alias)
+		ret = snprintf(name, len, "%s", alias->ifalias);
+	rcu_read_unlock();
+
+	return ret;
+}
 
 /**
  *	netdev_features_change - device changes features
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 927a6dcbad96..51d5836d8fb9 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -391,10 +391,7 @@ static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr,
 	if (len >  0 && buf[len - 1] == '\n')
 		--count;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
 	ret = dev_set_alias(netdev, buf, count);
-	rtnl_unlock();
 
 	return ret < 0 ? ret : len;
 }
@@ -403,13 +400,12 @@ static ssize_t ifalias_show(struct device *dev,
 			    struct device_attribute *attr, char *buf)
 {
 	const struct net_device *netdev = to_net_dev(dev);
+	char tmp[IFALIASZ];
 	ssize_t ret = 0;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
-	if (netdev->ifalias)
-		ret = sprintf(buf, "%s\n", netdev->ifalias);
-	rtnl_unlock();
+	ret = dev_get_alias(netdev, tmp, sizeof(tmp));
+	if (ret > 0)
+		ret = sprintf(buf, "%s\n", tmp);
 	return ret;
 }
 static DEVICE_ATTR_RW(ifalias);
@@ -1488,7 +1484,10 @@ static void netdev_release(struct device *d)
 
 	BUG_ON(dev->reg_state != NETREG_RELEASED);
 
-	kfree(dev->ifalias);
+	/* no need to wait for rcu grace period:
+	 * device is dead and about to be freed.
+	 */
+	kfree(rcu_access_pointer(dev->ifalias));
 	netdev_freemem(dev);
 }
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index e6955da0d58d..3961f87cdc76 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1366,6 +1366,16 @@ static int nla_put_iflink(struct sk_buff *skb, const struct net_device *dev)
 	return nla_put_u32(skb, IFLA_LINK, ifindex);
 }
 
+static noinline_for_stack int nla_put_ifalias(struct sk_buff *skb,
+					      struct net_device *dev)
+{
+	char buf[IFALIASZ];
+	int ret;
+
+	ret = dev_get_alias(dev, buf, sizeof(buf));
+	return ret > 0 ? nla_put_string(skb, IFLA_IFALIAS, buf) : 0;
+}
+
 static int rtnl_fill_link_netnsid(struct sk_buff *skb,
 				  const struct net_device *dev)
 {
@@ -1425,8 +1435,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 	    nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) ||
 	    (dev->qdisc &&
 	     nla_put_string(skb, IFLA_QDISC, dev->qdisc->ops->id)) ||
-	    (dev->ifalias &&
-	     nla_put_string(skb, IFLA_IFALIAS, dev->ifalias)) ||
+	    nla_put_ifalias(skb, dev) ||
 	    nla_put_u32(skb, IFLA_CARRIER_CHANGES,
 			atomic_read(&dev->carrier_changes)) ||
 	    nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down))
-- 
cgit v1.2.3


From 51d0c04795a4b5d9a188336884887a9d394a94b0 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 4 Oct 2017 17:48:45 -0700
Subject: net: Add extack to netdev_notifier_info

Add netlink_ext_ack to netdev_notifier_info to allow notifier
handlers to return errors to userspace.

Clean up the initialization in dev.c such that extack is easily
added in subsequent patches where relevant. Specifically, remove
the init call in call_netdevice_notifiers_info and have callers
initalize on stack when info is declared.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 10 +++++-
 net/core/dev.c            | 79 ++++++++++++++++++++++++++++-------------------
 2 files changed, 56 insertions(+), 33 deletions(-)

(limited to 'include/linux/netdevice.h')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d04424cfffba..05fcaba4b0d9 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2309,7 +2309,8 @@ int register_netdevice_notifier(struct notifier_block *nb);
 int unregister_netdevice_notifier(struct notifier_block *nb);
 
 struct netdev_notifier_info {
-	struct net_device *dev;
+	struct net_device	*dev;
+	struct netlink_ext_ack	*extack;
 };
 
 struct netdev_notifier_change_info {
@@ -2334,6 +2335,7 @@ static inline void netdev_notifier_info_init(struct netdev_notifier_info *info,
 					     struct net_device *dev)
 {
 	info->dev = dev;
+	info->extack = NULL;
 }
 
 static inline struct net_device *
@@ -2342,6 +2344,12 @@ netdev_notifier_info_to_dev(const struct netdev_notifier_info *info)
 	return info->dev;
 }
 
+static inline struct netlink_ext_ack *
+netdev_notifier_info_to_extack(const struct netdev_notifier_info *info)
+{
+	return info->extack;
+}
+
 int call_netdevice_notifiers(unsigned long val, struct net_device *dev);
 
 
diff --git a/net/core/dev.c b/net/core/dev.c
index bffc75429184..e27a6bc0ac4d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -163,7 +163,6 @@ static struct list_head offload_base __read_mostly;
 
 static int netif_rx_internal(struct sk_buff *skb);
 static int call_netdevice_notifiers_info(unsigned long val,
-					 struct net_device *dev,
 					 struct netdev_notifier_info *info);
 static struct napi_struct *napi_by_id(unsigned int napi_id);
 
@@ -1339,10 +1338,11 @@ EXPORT_SYMBOL(netdev_features_change);
 void netdev_state_change(struct net_device *dev)
 {
 	if (dev->flags & IFF_UP) {
-		struct netdev_notifier_change_info change_info;
+		struct netdev_notifier_change_info change_info = {
+			.info.dev = dev,
+		};
 
-		change_info.flags_changed = 0;
-		call_netdevice_notifiers_info(NETDEV_CHANGE, dev,
+		call_netdevice_notifiers_info(NETDEV_CHANGE,
 					      &change_info.info);
 		rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
 	}
@@ -1563,9 +1563,10 @@ EXPORT_SYMBOL(dev_disable_lro);
 static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val,
 				   struct net_device *dev)
 {
-	struct netdev_notifier_info info;
+	struct netdev_notifier_info info = {
+		.dev = dev,
+	};
 
-	netdev_notifier_info_init(&info, dev);
 	return nb->notifier_call(nb, val, &info);
 }
 
@@ -1690,11 +1691,9 @@ EXPORT_SYMBOL(unregister_netdevice_notifier);
  */
 
 static int call_netdevice_notifiers_info(unsigned long val,
-					 struct net_device *dev,
 					 struct netdev_notifier_info *info)
 {
 	ASSERT_RTNL();
-	netdev_notifier_info_init(info, dev);
 	return raw_notifier_call_chain(&netdev_chain, val, info);
 }
 
@@ -1709,9 +1708,11 @@ static int call_netdevice_notifiers_info(unsigned long val,
 
 int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
 {
-	struct netdev_notifier_info info;
+	struct netdev_notifier_info info = {
+		.dev = dev,
+	};
 
-	return call_netdevice_notifiers_info(val, dev, &info);
+	return call_netdevice_notifiers_info(val, &info);
 }
 EXPORT_SYMBOL(call_netdevice_notifiers);
 
@@ -6278,7 +6279,15 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 				   struct net_device *upper_dev, bool master,
 				   void *upper_priv, void *upper_info)
 {
-	struct netdev_notifier_changeupper_info changeupper_info;
+	struct netdev_notifier_changeupper_info changeupper_info = {
+		.info = {
+			.dev = dev,
+		},
+		.upper_dev = upper_dev,
+		.master = master,
+		.linking = true,
+		.upper_info = upper_info,
+	};
 	int ret = 0;
 
 	ASSERT_RTNL();
@@ -6296,12 +6305,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 	if (master && netdev_master_upper_dev_get(dev))
 		return -EBUSY;
 
-	changeupper_info.upper_dev = upper_dev;
-	changeupper_info.master = master;
-	changeupper_info.linking = true;
-	changeupper_info.upper_info = upper_info;
-
-	ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev,
+	ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER,
 					    &changeupper_info.info);
 	ret = notifier_to_errno(ret);
 	if (ret)
@@ -6312,7 +6316,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 	if (ret)
 		return ret;
 
-	ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev,
+	ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER,
 					    &changeupper_info.info);
 	ret = notifier_to_errno(ret);
 	if (ret)
@@ -6376,20 +6380,24 @@ EXPORT_SYMBOL(netdev_master_upper_dev_link);
 void netdev_upper_dev_unlink(struct net_device *dev,
 			     struct net_device *upper_dev)
 {
-	struct netdev_notifier_changeupper_info changeupper_info;
+	struct netdev_notifier_changeupper_info changeupper_info = {
+		.info = {
+			.dev = dev,
+		},
+		.upper_dev = upper_dev,
+		.linking = false,
+	};
 
 	ASSERT_RTNL();
 
-	changeupper_info.upper_dev = upper_dev;
 	changeupper_info.master = netdev_master_upper_dev_get(dev) == upper_dev;
-	changeupper_info.linking = false;
 
-	call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev,
+	call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER,
 				      &changeupper_info.info);
 
 	__netdev_adjacent_dev_unlink_neighbour(dev, upper_dev);
 
-	call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev,
+	call_netdevice_notifiers_info(NETDEV_CHANGEUPPER,
 				      &changeupper_info.info);
 }
 EXPORT_SYMBOL(netdev_upper_dev_unlink);
@@ -6405,11 +6413,13 @@ EXPORT_SYMBOL(netdev_upper_dev_unlink);
 void netdev_bonding_info_change(struct net_device *dev,
 				struct netdev_bonding_info *bonding_info)
 {
-	struct netdev_notifier_bonding_info	info;
+	struct netdev_notifier_bonding_info info = {
+		.info.dev = dev,
+	};
 
 	memcpy(&info.bonding_info, bonding_info,
 	       sizeof(struct netdev_bonding_info));
-	call_netdevice_notifiers_info(NETDEV_BONDING_INFO, dev,
+	call_netdevice_notifiers_info(NETDEV_BONDING_INFO,
 				      &info.info);
 }
 EXPORT_SYMBOL(netdev_bonding_info_change);
@@ -6535,11 +6545,13 @@ EXPORT_SYMBOL(dev_get_nest_level);
 void netdev_lower_state_changed(struct net_device *lower_dev,
 				void *lower_state_info)
 {
-	struct netdev_notifier_changelowerstate_info changelowerstate_info;
+	struct netdev_notifier_changelowerstate_info changelowerstate_info = {
+		.info.dev = lower_dev,
+	};
 
 	ASSERT_RTNL();
 	changelowerstate_info.lower_state_info = lower_state_info;
-	call_netdevice_notifiers_info(NETDEV_CHANGELOWERSTATE, lower_dev,
+	call_netdevice_notifiers_info(NETDEV_CHANGELOWERSTATE,
 				      &changelowerstate_info.info);
 }
 EXPORT_SYMBOL(netdev_lower_state_changed);
@@ -6830,11 +6842,14 @@ void __dev_notify_flags(struct net_device *dev, unsigned int old_flags,
 
 	if (dev->flags & IFF_UP &&
 	    (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) {
-		struct netdev_notifier_change_info change_info;
-
-		change_info.flags_changed = changes;
-		call_netdevice_notifiers_info(NETDEV_CHANGE, dev,
-					      &change_info.info);
+		struct netdev_notifier_change_info change_info = {
+			.info = {
+				.dev = dev,
+			},
+			.flags_changed = changes,
+		};
+
+		call_netdevice_notifiers_info(NETDEV_CHANGE, &change_info.info);
 	}
 }
 
-- 
cgit v1.2.3


From 33eaf2a6eb48ebf00374aaaf4b1b43f9950dcbe4 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 4 Oct 2017 17:48:46 -0700
Subject: net: Add extack to ndo_add_slave

Pass extack to do_set_master and down to ndo_add_slave

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c    |  5 +++--
 drivers/net/bonding/bond_options.c |  2 +-
 drivers/net/team/team.c            |  3 ++-
 drivers/net/vrf.c                  |  3 ++-
 include/linux/netdevice.h          |  3 ++-
 include/net/bonding.h              |  3 ++-
 net/batman-adv/soft-interface.c    |  3 ++-
 net/bridge/br_device.c             |  3 ++-
 net/core/rtnetlink.c               | 10 ++++++----
 9 files changed, 22 insertions(+), 13 deletions(-)

(limited to 'include/linux/netdevice.h')

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index b19dc033fb36..78feb94a36db 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1328,7 +1328,8 @@ void bond_lower_state_changed(struct slave *slave)
 }
 
 /* enslave device <slave> to bond device <master> */
-int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
+int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
+		 struct netlink_ext_ack *extack)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 	const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
@@ -3492,7 +3493,7 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd
 	switch (cmd) {
 	case BOND_ENSLAVE_OLD:
 	case SIOCBONDENSLAVE:
-		res = bond_enslave(bond_dev, slave_dev);
+		res = bond_enslave(bond_dev, slave_dev, NULL);
 		break;
 	case BOND_RELEASE_OLD:
 	case SIOCBONDRELEASE:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 5931aa2fe997..8a9b085c2a98 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -1383,7 +1383,7 @@ static int bond_option_slaves_set(struct bonding *bond,
 	switch (command[0]) {
 	case '+':
 		netdev_dbg(bond->dev, "Adding slave %s\n", dev->name);
-		ret = bond_enslave(bond->dev, dev);
+		ret = bond_enslave(bond->dev, dev, NULL);
 		break;
 
 	case '-':
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index ae53e899259f..4359d45aa131 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1914,7 +1914,8 @@ static int team_netpoll_setup(struct net_device *dev,
 }
 #endif
 
-static int team_add_slave(struct net_device *dev, struct net_device *port_dev)
+static int team_add_slave(struct net_device *dev, struct net_device *port_dev,
+			  struct netlink_ext_ack *extack)
 {
 	struct team *team = netdev_priv(dev);
 	int err;
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index cc18b7b11612..4a082ef53533 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -788,7 +788,8 @@ err:
 	return ret;
 }
 
-static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev)
+static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev,
+			 struct netlink_ext_ack *extack)
 {
 	if (netif_is_l3_master(port_dev) || netif_is_l3_slave(port_dev))
 		return -EINVAL;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 05fcaba4b0d9..368a5064a487 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1246,7 +1246,8 @@ struct net_device_ops {
 						     u32 flow_id);
 #endif
 	int			(*ndo_add_slave)(struct net_device *dev,
-						 struct net_device *slave_dev);
+						 struct net_device *slave_dev,
+						 struct netlink_ext_ack *extack);
 	int			(*ndo_del_slave)(struct net_device *dev,
 						 struct net_device *slave_dev);
 	netdev_features_t	(*ndo_fix_features)(struct net_device *dev,
diff --git a/include/net/bonding.h b/include/net/bonding.h
index b2e68657a216..2860cc66c2bb 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -596,7 +596,8 @@ void bond_destroy_sysfs(struct bond_net *net);
 void bond_prepare_sysfs_group(struct bonding *bond);
 int bond_sysfs_slave_add(struct slave *slave);
 void bond_sysfs_slave_del(struct slave *slave);
-int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev);
+int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
+		 struct netlink_ext_ack *extack);
 int bond_release(struct net_device *bond_dev, struct net_device *slave_dev);
 u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb);
 int bond_set_carrier(struct bonding *bond);
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index c2c986746d0b..e7d5fbb6ad53 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -867,7 +867,8 @@ free_bat_counters:
  * Return: 0 if successful or error otherwise.
  */
 static int batadv_softif_slave_add(struct net_device *dev,
-				   struct net_device *slave_dev)
+				   struct net_device *slave_dev,
+				   struct netlink_ext_ack *extack)
 {
 	struct batadv_hard_iface *hard_iface;
 	struct net *net = dev_net(dev);
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index f6b6a92f1c48..cb0131d70ab1 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -320,7 +320,8 @@ void br_netpoll_disable(struct net_bridge_port *p)
 
 #endif
 
-static int br_add_slave(struct net_device *dev, struct net_device *slave_dev)
+static int br_add_slave(struct net_device *dev, struct net_device *slave_dev,
+			struct netlink_ext_ack *extack)
 
 {
 	struct net_bridge *br = netdev_priv(dev);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 1ee98b1369d5..c5ee429bcce9 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1957,7 +1957,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 	return err;
 }
 
-static int do_set_master(struct net_device *dev, int ifindex)
+static int do_set_master(struct net_device *dev, int ifindex,
+			 struct netlink_ext_ack *extack)
 {
 	struct net_device *upper_dev = netdev_master_upper_dev_get(dev);
 	const struct net_device_ops *ops;
@@ -1982,7 +1983,7 @@ static int do_set_master(struct net_device *dev, int ifindex)
 			return -EINVAL;
 		ops = upper_dev->netdev_ops;
 		if (ops->ndo_add_slave) {
-			err = ops->ndo_add_slave(upper_dev, dev);
+			err = ops->ndo_add_slave(upper_dev, dev, extack);
 			if (err)
 				return err;
 		} else {
@@ -2115,7 +2116,7 @@ static int do_setlink(const struct sk_buff *skb,
 	}
 
 	if (tb[IFLA_MASTER]) {
-		err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]));
+		err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), extack);
 		if (err)
 			goto errout;
 		status |= DO_SETLINK_MODIFIED;
@@ -2753,7 +2754,8 @@ replay:
 				goto out_unregister;
 		}
 		if (tb[IFLA_MASTER]) {
-			err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]));
+			err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]),
+					    extack);
 			if (err)
 				goto out_unregister;
 		}
-- 
cgit v1.2.3


From 42ab19ee90292993370a30ad242599d75a3b749e Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 4 Oct 2017 17:48:47 -0700
Subject: net: Add extack to upper device linking

Add extack arg to netdev_upper_dev_link and netdev_master_upper_dev_link

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c                    |  7 ++++---
 drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c |  2 +-
 drivers/net/hyperv/netvsc_drv.c                    |  2 +-
 drivers/net/ipvlan/ipvlan_main.c                   |  2 +-
 drivers/net/macsec.c                               |  2 +-
 drivers/net/macvlan.c                              |  7 ++++---
 drivers/net/macvtap.c                              |  2 +-
 drivers/net/team/team.c                            |  2 +-
 drivers/net/usb/qmi_wwan.c                         |  2 +-
 drivers/net/vrf.c                                  |  7 ++++---
 include/linux/if_macvlan.h                         |  3 ++-
 include/linux/netdevice.h                          |  6 ++++--
 net/8021q/vlan.c                                   |  6 +++---
 net/8021q/vlan.h                                   |  2 +-
 net/8021q/vlan_netlink.c                           |  2 +-
 net/batman-adv/hard-interface.c                    |  2 +-
 net/bridge/br_if.c                                 |  2 +-
 net/core/dev.c                                     | 15 ++++++++++-----
 net/openvswitch/vport-netdev.c                     |  3 ++-
 19 files changed, 44 insertions(+), 32 deletions(-)

(limited to 'include/linux/netdevice.h')

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 78feb94a36db..bc92307c2082 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1217,14 +1217,15 @@ static enum netdev_lag_tx_type bond_lag_tx_type(struct bonding *bond)
 	}
 }
 
-static int bond_master_upper_dev_link(struct bonding *bond, struct slave *slave)
+static int bond_master_upper_dev_link(struct bonding *bond, struct slave *slave,
+				      struct netlink_ext_ack *extack)
 {
 	struct netdev_lag_upper_info lag_upper_info;
 	int err;
 
 	lag_upper_info.tx_type = bond_lag_tx_type(bond);
 	err = netdev_master_upper_dev_link(slave->dev, bond->dev, slave,
-					   &lag_upper_info);
+					   &lag_upper_info, extack);
 	if (err)
 		return err;
 	rtmsg_ifinfo(RTM_NEWLINK, slave->dev, IFF_SLAVE, GFP_KERNEL);
@@ -1710,7 +1711,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 		goto err_detach;
 	}
 
-	res = bond_master_upper_dev_link(bond, new_slave);
+	res = bond_master_upper_dev_link(bond, new_slave, extack);
 	if (res) {
 		netdev_dbg(bond_dev, "Error %d calling bond_master_upper_dev_link\n", res);
 		goto err_unregister;
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
index 98f22551eb45..1af326a60cbb 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
@@ -178,7 +178,7 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev,
 	if (err)
 		goto err1;
 
-	err = netdev_master_upper_dev_link(dev, real_dev, NULL, NULL);
+	err = netdev_master_upper_dev_link(dev, real_dev, NULL, NULL, extack);
 	if (err)
 		goto err2;
 
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index f300ae61c6c6..dfb986421ec6 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -1748,7 +1748,7 @@ static int netvsc_vf_join(struct net_device *vf_netdev,
 		goto rx_handler_failed;
 	}
 
-	ret = netdev_upper_dev_link(vf_netdev, ndev);
+	ret = netdev_upper_dev_link(vf_netdev, ndev, NULL);
 	if (ret != 0) {
 		netdev_err(vf_netdev,
 			   "can not set master device %s (err = %d)\n",
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index c74893c1e620..57c3856bab05 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -584,7 +584,7 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev,
 	if (err < 0)
 		goto remove_ida;
 
-	err = netdev_upper_dev_link(phy_dev, dev);
+	err = netdev_upper_dev_link(phy_dev, dev, extack);
 	if (err) {
 		goto unregister_netdev;
 	}
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 98e4deaa3a6a..ccbe4eaffe4d 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -3244,7 +3244,7 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
 				       &macsec_netdev_addr_lock_key,
 				       macsec_get_nest_level(dev));
 
-	err = netdev_upper_dev_link(real_dev, dev);
+	err = netdev_upper_dev_link(real_dev, dev, extack);
 	if (err < 0)
 		goto unregister;
 
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 1ffe77e95d46..858bd66511a2 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -1344,7 +1344,8 @@ static int macvlan_changelink_sources(struct macvlan_dev *vlan, u32 mode,
 }
 
 int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
-			   struct nlattr *tb[], struct nlattr *data[])
+			   struct nlattr *tb[], struct nlattr *data[],
+			   struct netlink_ext_ack *extack)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
 	struct macvlan_port *port;
@@ -1433,7 +1434,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
 		goto destroy_macvlan_port;
 
 	dev->priv_flags |= IFF_MACVLAN;
-	err = netdev_upper_dev_link(lowerdev, dev);
+	err = netdev_upper_dev_link(lowerdev, dev, extack);
 	if (err)
 		goto unregister_netdev;
 
@@ -1456,7 +1457,7 @@ static int macvlan_newlink(struct net *src_net, struct net_device *dev,
 			   struct nlattr *tb[], struct nlattr *data[],
 			   struct netlink_ext_ack *extack)
 {
-	return macvlan_common_newlink(src_net, dev, tb, data);
+	return macvlan_common_newlink(src_net, dev, tb, data, extack);
 }
 
 void macvlan_dellink(struct net_device *dev, struct list_head *head)
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index c2d0ea2fb019..f62aea2fcfa9 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -105,7 +105,7 @@ static int macvtap_newlink(struct net *src_net, struct net_device *dev,
 	/* Don't put anything that may fail after macvlan_common_newlink
 	 * because we can't undo what it does.
 	 */
-	err = macvlan_common_newlink(src_net, dev, tb, data);
+	err = macvlan_common_newlink(src_net, dev, tb, data, extack);
 	if (err) {
 		netdev_rx_handler_unregister(dev);
 		return err;
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 4359d45aa131..a468439969df 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1112,7 +1112,7 @@ static int team_upper_dev_link(struct team *team, struct team_port *port)
 
 	lag_upper_info.tx_type = team->mode->lag_tx_type;
 	err = netdev_master_upper_dev_link(port->dev, team->dev, NULL,
-					   &lag_upper_info);
+					   &lag_upper_info, NULL);
 	if (err)
 		return err;
 	port->dev->priv_flags |= IFF_TEAM_PORT;
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 8c3733608271..db7279d5b250 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -221,7 +221,7 @@ static int qmimux_register_device(struct net_device *real_dev, u8 mux_id)
 	/* Account for reference in struct qmimux_priv_priv */
 	dev_hold(real_dev);
 
-	err = netdev_upper_dev_link(real_dev, new_dev);
+	err = netdev_upper_dev_link(real_dev, new_dev, NULL);
 	if (err)
 		goto out_unregister_netdev;
 
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 4a082ef53533..77d0655a0250 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -764,7 +764,8 @@ static void cycle_netdev(struct net_device *dev)
 	}
 }
 
-static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev)
+static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev,
+			    struct netlink_ext_ack *extack)
 {
 	int ret;
 
@@ -775,7 +776,7 @@ static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev)
 		return -EOPNOTSUPP;
 
 	port_dev->priv_flags |= IFF_L3MDEV_SLAVE;
-	ret = netdev_master_upper_dev_link(port_dev, dev, NULL, NULL);
+	ret = netdev_master_upper_dev_link(port_dev, dev, NULL, NULL, extack);
 	if (ret < 0)
 		goto err;
 
@@ -794,7 +795,7 @@ static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev,
 	if (netif_is_l3_master(port_dev) || netif_is_l3_slave(port_dev))
 		return -EINVAL;
 
-	return do_vrf_add_slave(dev, port_dev);
+	return do_vrf_add_slave(dev, port_dev, extack);
 }
 
 /* inverse of do_vrf_add_slave */
diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h
index c9ec1343d187..10e319f41fb1 100644
--- a/include/linux/if_macvlan.h
+++ b/include/linux/if_macvlan.h
@@ -72,7 +72,8 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan,
 extern void macvlan_common_setup(struct net_device *dev);
 
 extern int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
-				  struct nlattr *tb[], struct nlattr *data[]);
+				  struct nlattr *tb[], struct nlattr *data[],
+				  struct netlink_ext_ack *extack);
 
 extern void macvlan_count_rx(const struct macvlan_dev *vlan,
 			     unsigned int len, bool success,
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 368a5064a487..31bb3010c69b 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3919,10 +3919,12 @@ void *netdev_adjacent_get_private(struct list_head *adj_list);
 void *netdev_lower_get_first_private_rcu(struct net_device *dev);
 struct net_device *netdev_master_upper_dev_get(struct net_device *dev);
 struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev);
-int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev);
+int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev,
+			  struct netlink_ext_ack *extack);
 int netdev_master_upper_dev_link(struct net_device *dev,
 				 struct net_device *upper_dev,
-				 void *upper_priv, void *upper_info);
+				 void *upper_priv, void *upper_info,
+				 struct netlink_ext_ack *extack);
 void netdev_upper_dev_unlink(struct net_device *dev,
 			     struct net_device *upper_dev);
 void netdev_adjacent_rename_links(struct net_device *dev, char *oldname);
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 9649579b5b9f..71c3e045505b 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -138,7 +138,7 @@ int vlan_check_real_dev(struct net_device *real_dev,
 	return 0;
 }
 
-int register_vlan_dev(struct net_device *dev)
+int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack)
 {
 	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	struct net_device *real_dev = vlan->real_dev;
@@ -174,7 +174,7 @@ int register_vlan_dev(struct net_device *dev)
 	if (err < 0)
 		goto out_uninit_mvrp;
 
-	err = netdev_upper_dev_link(real_dev, dev);
+	err = netdev_upper_dev_link(real_dev, dev, extack);
 	if (err)
 		goto out_unregister_netdev;
 
@@ -270,7 +270,7 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id)
 	vlan->flags = VLAN_FLAG_REORDER_HDR;
 
 	new_dev->rtnl_link_ops = &vlan_link_ops;
-	err = register_vlan_dev(new_dev);
+	err = register_vlan_dev(new_dev, NULL);
 	if (err < 0)
 		goto out_free_newdev;
 
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index df8bd65dd370..94f8eed9f9b3 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h
@@ -107,7 +107,7 @@ void vlan_dev_get_realdev_name(const struct net_device *dev, char *result);
 int vlan_check_real_dev(struct net_device *real_dev,
 			__be16 protocol, u16 vlan_id);
 void vlan_setup(struct net_device *dev);
-int register_vlan_dev(struct net_device *dev);
+int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack);
 void unregister_vlan_dev(struct net_device *dev, struct list_head *head);
 bool vlan_dev_inherit_address(struct net_device *dev,
 			      struct net_device *real_dev);
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index 5e831de3103e..6e7c5a6a7930 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -160,7 +160,7 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev,
 	if (err < 0)
 		return err;
 
-	return register_vlan_dev(dev);
+	return register_vlan_dev(dev, extack);
 }
 
 static inline size_t vlan_qos_map_size(unsigned int n)
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index e348f76ea8c1..f7b413b9297e 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -738,7 +738,7 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
 	bat_priv = netdev_priv(hard_iface->soft_iface);
 
 	ret = netdev_master_upper_dev_link(hard_iface->net_dev,
-					   soft_iface, NULL, NULL);
+					   soft_iface, NULL, NULL, NULL);
 	if (ret)
 		goto err_dev;
 
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index f3aef22931ab..0a3fd727048d 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -540,7 +540,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
 
 	dev->priv_flags |= IFF_BRIDGE_PORT;
 
-	err = netdev_master_upper_dev_link(dev, br->dev, NULL, NULL);
+	err = netdev_master_upper_dev_link(dev, br->dev, NULL, NULL, NULL);
 	if (err)
 		goto err5;
 
diff --git a/net/core/dev.c b/net/core/dev.c
index e27a6bc0ac4d..fcddccb6be41 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6277,11 +6277,13 @@ static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev,
 
 static int __netdev_upper_dev_link(struct net_device *dev,
 				   struct net_device *upper_dev, bool master,
-				   void *upper_priv, void *upper_info)
+				   void *upper_priv, void *upper_info,
+				   struct netlink_ext_ack *extack)
 {
 	struct netdev_notifier_changeupper_info changeupper_info = {
 		.info = {
 			.dev = dev,
+			.extack = extack,
 		},
 		.upper_dev = upper_dev,
 		.master = master,
@@ -6341,9 +6343,11 @@ rollback:
  * returns zero.
  */
 int netdev_upper_dev_link(struct net_device *dev,
-			  struct net_device *upper_dev)
+			  struct net_device *upper_dev,
+			  struct netlink_ext_ack *extack)
 {
-	return __netdev_upper_dev_link(dev, upper_dev, false, NULL, NULL);
+	return __netdev_upper_dev_link(dev, upper_dev, false,
+				       NULL, NULL, extack);
 }
 EXPORT_SYMBOL(netdev_upper_dev_link);
 
@@ -6362,10 +6366,11 @@ EXPORT_SYMBOL(netdev_upper_dev_link);
  */
 int netdev_master_upper_dev_link(struct net_device *dev,
 				 struct net_device *upper_dev,
-				 void *upper_priv, void *upper_info)
+				 void *upper_priv, void *upper_info,
+				 struct netlink_ext_ack *extack)
 {
 	return __netdev_upper_dev_link(dev, upper_dev, true,
-				       upper_priv, upper_info);
+				       upper_priv, upper_info, extack);
 }
 EXPORT_SYMBOL(netdev_master_upper_dev_link);
 
diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c
index 0389398fa4ab..2e5e7a41d8ef 100644
--- a/net/openvswitch/vport-netdev.c
+++ b/net/openvswitch/vport-netdev.c
@@ -108,7 +108,8 @@ struct vport *ovs_netdev_link(struct vport *vport, const char *name)
 
 	rtnl_lock();
 	err = netdev_master_upper_dev_link(vport->dev,
-					   get_dpdev(vport->dp), NULL, NULL);
+					   get_dpdev(vport->dp),
+					   NULL, NULL, NULL);
 	if (err)
 		goto error_unlock;
 
-- 
cgit v1.2.3


From 0ad646c81b2182f7fa67ec0c8c825e0ee165696d Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Fri, 13 Oct 2017 11:58:53 -0700
Subject: tun: call dev_get_valid_name() before register_netdevice()

register_netdevice() could fail early when we have an invalid
dev name, in which case ->ndo_uninit() is not called. For tun
device, this is a problem because a timer etc. are already
initialized and it expects ->ndo_uninit() to clean them up.

We could move these initializations into a ->ndo_init() so
that register_netdevice() knows better, however this is still
complicated due to the logic in tun_detach().

Therefore, I choose to just call dev_get_valid_name() before
register_netdevice(), which is quicker and much easier to audit.
And for this specific case, it is already enough.

Fixes: 96442e42429e ("tuntap: choose the txq based on rxq")
Reported-by: Dmitry Alexeev <avekceeb@gmail.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c         | 3 +++
 include/linux/netdevice.h | 3 +++
 net/core/dev.c            | 6 +++---
 3 files changed, 9 insertions(+), 3 deletions(-)

(limited to 'include/linux/netdevice.h')

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 5ce580f413b9..e21bf90b819f 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2027,6 +2027,9 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 
 		if (!dev)
 			return -ENOMEM;
+		err = dev_get_valid_name(net, dev, name);
+		if (err)
+			goto err_free_dev;
 
 		dev_net_set(dev, net);
 		dev->rtnl_link_ops = &tun_link_ops;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index f535779d9dc1..2eaac7d75af4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3694,6 +3694,9 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 				    unsigned char name_assign_type,
 				    void (*setup)(struct net_device *),
 				    unsigned int txqs, unsigned int rxqs);
+int dev_get_valid_name(struct net *net, struct net_device *dev,
+		       const char *name);
+
 #define alloc_netdev(sizeof_priv, name, name_assign_type, setup) \
 	alloc_netdev_mqs(sizeof_priv, name, name_assign_type, setup, 1, 1)
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 588b473194a8..11596a302a26 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1147,9 +1147,8 @@ static int dev_alloc_name_ns(struct net *net,
 	return ret;
 }
 
-static int dev_get_valid_name(struct net *net,
-			      struct net_device *dev,
-			      const char *name)
+int dev_get_valid_name(struct net *net, struct net_device *dev,
+		       const char *name)
 {
 	BUG_ON(!net);
 
@@ -1165,6 +1164,7 @@ static int dev_get_valid_name(struct net *net,
 
 	return 0;
 }
+EXPORT_SYMBOL(dev_get_valid_name);
 
 /**
  *	dev_change_name - change name of a device
-- 
cgit v1.2.3


From 1c601d829ab0d7ac3ac44853f83db2206afe67fc Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Mon, 16 Oct 2017 12:19:39 +0200
Subject: bpf: cpumap xdp_buff to skb conversion and allocation

This patch makes cpumap functional, by adding SKB allocation and
invoking the network stack on the dequeuing CPU.

For constructing the SKB on the remote CPU, the xdp_buff in converted
into a struct xdp_pkt, and it mapped into the top headroom of the
packet, to avoid allocating separate mem.  For now, struct xdp_pkt is
just a cpumap internal data structure, with info carried between
enqueue to dequeue.

If a driver doesn't have enough headroom it is simply dropped, with
return code -EOVERFLOW.  This will be picked up the xdp tracepoint
infrastructure, to allow users to catch this.

V2: take into account xdp->data_meta

V4:
 - Drop busypoll tricks, keeping it more simple.
 - Skip RPS and Generic-XDP-recursive-reinjection, suggested by Alexei

V5: correct RCU read protection around __netif_receive_skb_core.

V6: Setting TASK_RUNNING vs TASK_INTERRUPTIBLE based on talk with Rik van Riel

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |   1 +
 kernel/bpf/cpumap.c       | 152 +++++++++++++++++++++++++++++++++++++++-------
 net/core/dev.c            |  27 ++++++++
 3 files changed, 158 insertions(+), 22 deletions(-)

(limited to 'include/linux/netdevice.h')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 31bb3010c69b..bf014afcb914 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3260,6 +3260,7 @@ int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb);
 int netif_rx(struct sk_buff *skb);
 int netif_rx_ni(struct sk_buff *skb);
 int netif_receive_skb(struct sk_buff *skb);
+int netif_receive_skb_core(struct sk_buff *skb);
 gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb);
 void napi_gro_flush(struct napi_struct *napi, bool flush_old);
 struct sk_buff *napi_get_frags(struct napi_struct *napi);
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 768da6a2c265..ee7adf4352dd 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -25,6 +25,9 @@
 #include <linux/kthread.h>
 #include <linux/capability.h>
 
+#include <linux/netdevice.h>   /* netif_receive_skb_core */
+#include <linux/etherdevice.h> /* eth_type_trans */
+
 /* General idea: XDP packets getting XDP redirected to another CPU,
  * will maximum be stored/queued for one driver ->poll() call.  It is
  * guaranteed that setting flush bit and flush operation happen on
@@ -179,6 +182,92 @@ static void cpu_map_kthread_stop(struct work_struct *work)
 	kthread_stop(rcpu->kthread);
 }
 
+/* For now, xdp_pkt is a cpumap internal data structure, with info
+ * carried between enqueue to dequeue. It is mapped into the top
+ * headroom of the packet, to avoid allocating separate mem.
+ */
+struct xdp_pkt {
+	void *data;
+	u16 len;
+	u16 headroom;
+	u16 metasize;
+	struct net_device *dev_rx;
+};
+
+/* Convert xdp_buff to xdp_pkt */
+static struct xdp_pkt *convert_to_xdp_pkt(struct xdp_buff *xdp)
+{
+	struct xdp_pkt *xdp_pkt;
+	int metasize;
+	int headroom;
+
+	/* Assure headroom is available for storing info */
+	headroom = xdp->data - xdp->data_hard_start;
+	metasize = xdp->data - xdp->data_meta;
+	metasize = metasize > 0 ? metasize : 0;
+	if ((headroom - metasize) < sizeof(*xdp_pkt))
+		return NULL;
+
+	/* Store info in top of packet */
+	xdp_pkt = xdp->data_hard_start;
+
+	xdp_pkt->data = xdp->data;
+	xdp_pkt->len  = xdp->data_end - xdp->data;
+	xdp_pkt->headroom = headroom - sizeof(*xdp_pkt);
+	xdp_pkt->metasize = metasize;
+
+	return xdp_pkt;
+}
+
+struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
+				  struct xdp_pkt *xdp_pkt)
+{
+	unsigned int frame_size;
+	void *pkt_data_start;
+	struct sk_buff *skb;
+
+	/* build_skb need to place skb_shared_info after SKB end, and
+	 * also want to know the memory "truesize".  Thus, need to
+	 * know the memory frame size backing xdp_buff.
+	 *
+	 * XDP was designed to have PAGE_SIZE frames, but this
+	 * assumption is not longer true with ixgbe and i40e.  It
+	 * would be preferred to set frame_size to 2048 or 4096
+	 * depending on the driver.
+	 *   frame_size = 2048;
+	 *   frame_len  = frame_size - sizeof(*xdp_pkt);
+	 *
+	 * Instead, with info avail, skb_shared_info in placed after
+	 * packet len.  This, unfortunately fakes the truesize.
+	 * Another disadvantage of this approach, the skb_shared_info
+	 * is not at a fixed memory location, with mixed length
+	 * packets, which is bad for cache-line hotness.
+	 */
+	frame_size = SKB_DATA_ALIGN(xdp_pkt->len) + xdp_pkt->headroom +
+		SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
+	pkt_data_start = xdp_pkt->data - xdp_pkt->headroom;
+	skb = build_skb(pkt_data_start, frame_size);
+	if (!skb)
+		return NULL;
+
+	skb_reserve(skb, xdp_pkt->headroom);
+	__skb_put(skb, xdp_pkt->len);
+	if (xdp_pkt->metasize)
+		skb_metadata_set(skb, xdp_pkt->metasize);
+
+	/* Essential SKB info: protocol and skb->dev */
+	skb->protocol = eth_type_trans(skb, xdp_pkt->dev_rx);
+
+	/* Optional SKB info, currently missing:
+	 * - HW checksum info		(skb->ip_summed)
+	 * - HW RX hash			(skb_set_hash)
+	 * - RX ring dev queue index	(skb_record_rx_queue)
+	 */
+
+	return skb;
+}
+
 static int cpu_map_kthread_run(void *data)
 {
 	struct bpf_cpu_map_entry *rcpu = data;
@@ -191,15 +280,45 @@ static int cpu_map_kthread_run(void *data)
 	 * kthread_stop signal until queue is empty.
 	 */
 	while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) {
+		unsigned int processed = 0, drops = 0;
 		struct xdp_pkt *xdp_pkt;
 
-		schedule();
-		/* Do work */
-		while ((xdp_pkt = ptr_ring_consume(rcpu->queue))) {
-			/* For now just "refcnt-free" */
-			page_frag_free(xdp_pkt);
+		/* Release CPU reschedule checks */
+		if (__ptr_ring_empty(rcpu->queue)) {
+			__set_current_state(TASK_INTERRUPTIBLE);
+			schedule();
+		} else {
+			cond_resched();
+		}
+		__set_current_state(TASK_RUNNING);
+
+		/* Process packets in rcpu->queue */
+		local_bh_disable();
+		/*
+		 * The bpf_cpu_map_entry is single consumer, with this
+		 * kthread CPU pinned. Lockless access to ptr_ring
+		 * consume side valid as no-resize allowed of queue.
+		 */
+		while ((xdp_pkt = __ptr_ring_consume(rcpu->queue))) {
+			struct sk_buff *skb;
+			int ret;
+
+			skb = cpu_map_build_skb(rcpu, xdp_pkt);
+			if (!skb) {
+				page_frag_free(xdp_pkt);
+				continue;
+			}
+
+			/* Inject into network stack */
+			ret = netif_receive_skb_core(skb);
+			if (ret == NET_RX_DROP)
+				drops++;
+
+			/* Limit BH-disable period */
+			if (++processed == 8)
+				break;
 		}
-		__set_current_state(TASK_INTERRUPTIBLE);
+		local_bh_enable(); /* resched point, may call do_softirq() */
 	}
 	__set_current_state(TASK_RUNNING);
 
@@ -490,13 +609,6 @@ static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
 	return 0;
 }
 
-/* Notice: Will change in later patch */
-struct xdp_pkt {
-	void *data;
-	u16 len;
-	u16 headroom;
-};
-
 /* Runs under RCU-read-side, plus in softirq under NAPI protection.
  * Thus, safe percpu variable access.
  */
@@ -524,17 +636,13 @@ int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
 		    struct net_device *dev_rx)
 {
 	struct xdp_pkt *xdp_pkt;
-	int headroom;
 
-	/* For now this is just used as a void pointer to data_hard_start.
-	 * Followup patch will generalize this.
-	 */
-	xdp_pkt = xdp->data_hard_start;
+	xdp_pkt = convert_to_xdp_pkt(xdp);
+	if (!xdp_pkt)
+		return -EOVERFLOW;
 
-	/* Fake writing into xdp_pkt->data to measure overhead */
-	headroom = xdp->data - xdp->data_hard_start;
-	if (headroom < sizeof(*xdp_pkt))
-		xdp_pkt->data = xdp->data;
+	/* Info needed when constructing SKB on remote CPU */
+	xdp_pkt->dev_rx = dev_rx;
 
 	bq_enqueue(rcpu, xdp_pkt);
 	return 0;
diff --git a/net/core/dev.c b/net/core/dev.c
index d2b20e73080e..cf5894f0e6eb 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4492,6 +4492,33 @@ out:
 	return ret;
 }
 
+/**
+ *	netif_receive_skb_core - special purpose version of netif_receive_skb
+ *	@skb: buffer to process
+ *
+ *	More direct receive version of netif_receive_skb().  It should
+ *	only be used by callers that have a need to skip RPS and Generic XDP.
+ *	Caller must also take care of handling if (page_is_)pfmemalloc.
+ *
+ *	This function may only be called from softirq context and interrupts
+ *	should be enabled.
+ *
+ *	Return values (usually ignored):
+ *	NET_RX_SUCCESS: no congestion
+ *	NET_RX_DROP: packet was dropped
+ */
+int netif_receive_skb_core(struct sk_buff *skb)
+{
+	int ret;
+
+	rcu_read_lock();
+	ret = __netif_receive_skb_core(skb, false);
+	rcu_read_unlock();
+
+	return ret;
+}
+EXPORT_SYMBOL(netif_receive_skb_core);
+
 static int __netif_receive_skb(struct sk_buff *skb)
 {
 	int ret;
-- 
cgit v1.2.3


From 8c4083b30e56fc71b0e94c26374b32d95d5ea461 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Thu, 19 Oct 2017 15:50:29 +0200
Subject: net: sched: add block bind/unbind notif. and extended block_get/put

Introduce new type of ndo_setup_tc message to propage binding/unbinding
of a block to driver. Call this ndo whenever qdisc gets/puts a block.
Alongside with this, there's need to propagate binder type from qdisc
code down to the notifier. So introduce extended variants of
block_get/put in order to pass this info.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  1 +
 include/net/pkt_cls.h     | 40 +++++++++++++++++++++++++++++++++
 net/sched/cls_api.c       | 56 ++++++++++++++++++++++++++++++++++++++++++++---
 3 files changed, 94 insertions(+), 3 deletions(-)

(limited to 'include/linux/netdevice.h')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index bf014afcb914..4de5b08ee0fb 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -775,6 +775,7 @@ enum tc_setup_type {
 	TC_SETUP_CLSFLOWER,
 	TC_SETUP_CLSMATCHALL,
 	TC_SETUP_CLSBPF,
+	TC_SETUP_BLOCK,
 };
 
 /* These structures hold the attributes of xdp state that are being passed
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 49a143e0fe65..41bc7d774047 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -17,13 +17,27 @@ struct tcf_walker {
 int register_tcf_proto_ops(struct tcf_proto_ops *ops);
 int unregister_tcf_proto_ops(struct tcf_proto_ops *ops);
 
+enum tcf_block_binder_type {
+	TCF_BLOCK_BINDER_TYPE_UNSPEC,
+};
+
+struct tcf_block_ext_info {
+	enum tcf_block_binder_type binder_type;
+};
+
 #ifdef CONFIG_NET_CLS
 struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index,
 				bool create);
 void tcf_chain_put(struct tcf_chain *chain);
 int tcf_block_get(struct tcf_block **p_block,
 		  struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q);
+int tcf_block_get_ext(struct tcf_block **p_block,
+		      struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q,
+		      struct tcf_block_ext_info *ei);
 void tcf_block_put(struct tcf_block *block);
+void tcf_block_put_ext(struct tcf_block *block,
+		       struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q,
+		       struct tcf_block_ext_info *ei);
 
 static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
 {
@@ -46,10 +60,25 @@ int tcf_block_get(struct tcf_block **p_block,
 	return 0;
 }
 
+static inline
+int tcf_block_get_ext(struct tcf_block **p_block,
+		      struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q,
+		      struct tcf_block_ext_info *ei)
+{
+	return 0;
+}
+
 static inline void tcf_block_put(struct tcf_block *block)
 {
 }
 
+static inline
+void tcf_block_put_ext(struct tcf_block *block,
+		       struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q,
+		       struct tcf_block_ext_info *ei)
+{
+}
+
 static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
 {
 	return NULL;
@@ -434,6 +463,17 @@ tcf_match_indev(struct sk_buff *skb, int ifindex)
 int tc_setup_cb_call(struct tcf_exts *exts, enum tc_setup_type type,
 		     void *type_data, bool err_stop);
 
+enum tc_block_command {
+	TC_BLOCK_BIND,
+	TC_BLOCK_UNBIND,
+};
+
+struct tc_block_offload {
+	enum tc_block_command command;
+	enum tcf_block_binder_type binder_type;
+	struct tcf_block *block;
+};
+
 struct tc_cls_common_offload {
 	u32 chain_index;
 	__be16 protocol;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 2e8e87fd9d97..92dce26d10e3 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -240,8 +240,36 @@ tcf_chain_filter_chain_ptr_set(struct tcf_chain *chain,
 	chain->p_filter_chain = p_filter_chain;
 }
 
-int tcf_block_get(struct tcf_block **p_block,
-		  struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q)
+static void tcf_block_offload_cmd(struct tcf_block *block, struct Qdisc *q,
+				  struct tcf_block_ext_info *ei,
+				  enum tc_block_command command)
+{
+	struct net_device *dev = q->dev_queue->dev;
+	struct tc_block_offload bo = {};
+
+	if (!tc_can_offload(dev))
+		return;
+	bo.command = command;
+	bo.binder_type = ei->binder_type;
+	bo.block = block;
+	dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo);
+}
+
+static void tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q,
+				   struct tcf_block_ext_info *ei)
+{
+	tcf_block_offload_cmd(block, q, ei, TC_BLOCK_BIND);
+}
+
+static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q,
+				     struct tcf_block_ext_info *ei)
+{
+	tcf_block_offload_cmd(block, q, ei, TC_BLOCK_UNBIND);
+}
+
+int tcf_block_get_ext(struct tcf_block **p_block,
+		      struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q,
+		      struct tcf_block_ext_info *ei)
 {
 	struct tcf_block *block = kzalloc(sizeof(*block), GFP_KERNEL);
 	struct tcf_chain *chain;
@@ -259,6 +287,7 @@ int tcf_block_get(struct tcf_block **p_block,
 	tcf_chain_filter_chain_ptr_set(chain, p_filter_chain);
 	block->net = qdisc_net(q);
 	block->q = q;
+	tcf_block_offload_bind(block, q, ei);
 	*p_block = block;
 	return 0;
 
@@ -266,15 +295,28 @@ err_chain_create:
 	kfree(block);
 	return err;
 }
+EXPORT_SYMBOL(tcf_block_get_ext);
+
+int tcf_block_get(struct tcf_block **p_block,
+		  struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q)
+{
+	struct tcf_block_ext_info ei = {0, };
+
+	return tcf_block_get_ext(p_block, p_filter_chain, q, &ei);
+}
 EXPORT_SYMBOL(tcf_block_get);
 
-void tcf_block_put(struct tcf_block *block)
+void tcf_block_put_ext(struct tcf_block *block,
+		       struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q,
+		       struct tcf_block_ext_info *ei)
 {
 	struct tcf_chain *chain, *tmp;
 
 	if (!block)
 		return;
 
+	tcf_block_offload_unbind(block, q, ei);
+
 	/* XXX: Standalone actions are not allowed to jump to any chain, and
 	 * bound actions should be all removed after flushing. However,
 	 * filters are destroyed in RCU callbacks, we have to hold the chains
@@ -302,6 +344,14 @@ void tcf_block_put(struct tcf_block *block)
 		tcf_chain_put(chain);
 	kfree(block);
 }
+EXPORT_SYMBOL(tcf_block_put_ext);
+
+void tcf_block_put(struct tcf_block *block)
+{
+	struct tcf_block_ext_info ei = {0, };
+
+	tcf_block_put_ext(block, NULL, block->q, &ei);
+}
 EXPORT_SYMBOL(tcf_block_put);
 
 /* Main classifier routine: scans classifier chain attached
-- 
cgit v1.2.3


From 3d0bd028ffb4a4915cb64cfa0d2cee1578cc0321 Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Mon, 16 Oct 2017 18:01:27 -0700
Subject: net/sched: Add support for HW offloading for CBS

This adds support for offloading the CBS algorithm to the controller,
if supported. Drivers wanting to support CBS offload must implement
the .ndo_setup_tc callback and handle the TC_SETUP_CBS (introduced
here) type.

Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Tested-by: Henrik Austad <henrik@austad.us>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 include/linux/netdevice.h |   1 +
 include/net/pkt_sched.h   |   9 ++++
 net/sched/sch_cbs.c       | 104 ++++++++++++++++++++++++++++++++++++++++------
 3 files changed, 102 insertions(+), 12 deletions(-)

(limited to 'include/linux/netdevice.h')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 6c7960c8338a..5e02f79b2110 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -776,6 +776,7 @@ enum tc_setup_type {
 	TC_SETUP_CLSMATCHALL,
 	TC_SETUP_CLSBPF,
 	TC_SETUP_BLOCK,
+	TC_SETUP_CBS,
 };
 
 /* These structures hold the attributes of xdp state that are being passed
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index b8ecafce4ba1..02f2db26e30c 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -140,4 +140,13 @@ static inline struct net *qdisc_net(struct Qdisc *q)
 	return dev_net(q->dev_queue->dev);
 }
 
+struct tc_cbs_qopt_offload {
+	u8 enable;
+	s32 queue;
+	s32 hicredit;
+	s32 locredit;
+	s32 idleslope;
+	s32 sendslope;
+};
+
 #endif
diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index 0e85133c5653..bdb533b7fb8c 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -68,6 +68,8 @@
 #define BYTES_PER_KBIT (1000LL / 8)
 
 struct cbs_sched_data {
+	bool offload;
+	int queue;
 	s64 port_rate; /* in bytes/s */
 	s64 last; /* timestamp in ns */
 	s64 credits; /* in bytes */
@@ -80,6 +82,11 @@ struct cbs_sched_data {
 	struct sk_buff *(*dequeue)(struct Qdisc *sch);
 };
 
+static int cbs_enqueue_offload(struct sk_buff *skb, struct Qdisc *sch)
+{
+	return qdisc_enqueue_tail(skb, sch);
+}
+
 static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct cbs_sched_data *q = qdisc_priv(sch);
@@ -169,6 +176,11 @@ static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch)
 	return skb;
 }
 
+static struct sk_buff *cbs_dequeue_offload(struct Qdisc *sch)
+{
+	return qdisc_dequeue_head(sch);
+}
+
 static struct sk_buff *cbs_dequeue(struct Qdisc *sch)
 {
 	struct cbs_sched_data *q = qdisc_priv(sch);
@@ -180,14 +192,66 @@ static const struct nla_policy cbs_policy[TCA_CBS_MAX + 1] = {
 	[TCA_CBS_PARMS]	= { .len = sizeof(struct tc_cbs_qopt) },
 };
 
+static void cbs_disable_offload(struct net_device *dev,
+				struct cbs_sched_data *q)
+{
+	struct tc_cbs_qopt_offload cbs = { };
+	const struct net_device_ops *ops;
+	int err;
+
+	if (!q->offload)
+		return;
+
+	q->enqueue = cbs_enqueue_soft;
+	q->dequeue = cbs_dequeue_soft;
+
+	ops = dev->netdev_ops;
+	if (!ops->ndo_setup_tc)
+		return;
+
+	cbs.queue = q->queue;
+	cbs.enable = 0;
+
+	err = ops->ndo_setup_tc(dev, TC_SETUP_CBS, &cbs);
+	if (err < 0)
+		pr_warn("Couldn't disable CBS offload for queue %d\n",
+			cbs.queue);
+}
+
+static int cbs_enable_offload(struct net_device *dev, struct cbs_sched_data *q,
+			      const struct tc_cbs_qopt *opt)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+	struct tc_cbs_qopt_offload cbs = { };
+	int err;
+
+	if (!ops->ndo_setup_tc)
+		return -EOPNOTSUPP;
+
+	cbs.queue = q->queue;
+
+	cbs.enable = 1;
+	cbs.hicredit = opt->hicredit;
+	cbs.locredit = opt->locredit;
+	cbs.idleslope = opt->idleslope;
+	cbs.sendslope = opt->sendslope;
+
+	err = ops->ndo_setup_tc(dev, TC_SETUP_CBS, &cbs);
+	if (err < 0)
+		return err;
+
+	q->enqueue = cbs_enqueue_offload;
+	q->dequeue = cbs_dequeue_offload;
+
+	return 0;
+}
+
 static int cbs_change(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct cbs_sched_data *q = qdisc_priv(sch);
 	struct net_device *dev = qdisc_dev(sch);
 	struct nlattr *tb[TCA_CBS_MAX + 1];
-	struct ethtool_link_ksettings ecmd;
 	struct tc_cbs_qopt *qopt;
-	s64 link_speed;
 	int err;
 
 	err = nla_parse_nested(tb, TCA_CBS_MAX, opt, cbs_policy, NULL);
@@ -199,23 +263,30 @@ static int cbs_change(struct Qdisc *sch, struct nlattr *opt)
 
 	qopt = nla_data(tb[TCA_CBS_PARMS]);
 
-	if (qopt->offload)
-		return -EOPNOTSUPP;
+	if (!qopt->offload) {
+		struct ethtool_link_ksettings ecmd;
+		s64 link_speed;
 
-	if (!__ethtool_get_link_ksettings(dev, &ecmd))
-		link_speed = ecmd.base.speed;
-	else
-		link_speed = SPEED_1000;
+		if (!__ethtool_get_link_ksettings(dev, &ecmd))
+			link_speed = ecmd.base.speed;
+		else
+			link_speed = SPEED_1000;
 
-	q->port_rate = link_speed * 1000 * BYTES_PER_KBIT;
+		q->port_rate = link_speed * 1000 * BYTES_PER_KBIT;
 
-	q->enqueue = cbs_enqueue_soft;
-	q->dequeue = cbs_dequeue_soft;
+		cbs_disable_offload(dev, q);
+	} else {
+		err = cbs_enable_offload(dev, q, qopt);
+		if (err < 0)
+			return err;
+	}
 
+	/* Everything went OK, save the parameters used. */
 	q->hicredit = qopt->hicredit;
 	q->locredit = qopt->locredit;
 	q->idleslope = qopt->idleslope * BYTES_PER_KBIT;
 	q->sendslope = qopt->sendslope * BYTES_PER_KBIT;
+	q->offload = qopt->offload;
 
 	return 0;
 }
@@ -223,10 +294,16 @@ static int cbs_change(struct Qdisc *sch, struct nlattr *opt)
 static int cbs_init(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct cbs_sched_data *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
 
 	if (!opt)
 		return -EINVAL;
 
+	q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0);
+
+	q->enqueue = cbs_enqueue_soft;
+	q->dequeue = cbs_dequeue_soft;
+
 	qdisc_watchdog_init(&q->watchdog, sch);
 
 	return cbs_change(sch, opt);
@@ -235,8 +312,11 @@ static int cbs_init(struct Qdisc *sch, struct nlattr *opt)
 static void cbs_destroy(struct Qdisc *sch)
 {
 	struct cbs_sched_data *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
 
 	qdisc_watchdog_cancel(&q->watchdog);
+
+	cbs_disable_offload(dev, q);
 }
 
 static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb)
@@ -253,7 +333,7 @@ static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb)
 	opt.locredit = q->locredit;
 	opt.sendslope = div64_s64(q->sendslope, BYTES_PER_KBIT);
 	opt.idleslope = div64_s64(q->idleslope, BYTES_PER_KBIT);
-	opt.offload = 0;
+	opt.offload = q->offload;
 
 	if (nla_put(skb, TCA_CBS_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
-- 
cgit v1.2.3


From 46209401f8f6116bd0b2c2d14a63958e83ffca0b Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Fri, 3 Nov 2017 11:46:25 +0100
Subject: net: core: introduce mini_Qdisc and eliminate usage of tp->q for
 clsact fastpath

In sch_handle_egress and sch_handle_ingress tp->q is used only in order
to update stats. So stats and filter list are the only things that are
needed in clsact qdisc fastpath processing. Introduce new mini_Qdisc
struct to hold those items. Also, introduce a helper to swap the
mini_Qdisc structures in case filter list head changes.

This removes need for tp->q usage without added overhead.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  9 ++++++---
 include/net/sch_generic.h | 32 ++++++++++++++++++++++++++++++++
 net/core/dev.c            | 21 +++++++++++----------
 net/sched/sch_generic.c   | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 net/sched/sch_ingress.c   | 19 ++++++++++++++-----
 5 files changed, 109 insertions(+), 18 deletions(-)

(limited to 'include/linux/netdevice.h')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5e02f79b2110..7de7656550c2 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1559,6 +1559,8 @@ enum netdev_priv_flags {
  *
  *	@rx_handler:		handler for received packets
  *	@rx_handler_data: 	XXX: need comments on this one
+ *	@miniq_ingress:		ingress/clsact qdisc specific data for
+ *				ingress processing
  *	@ingress_queue:		XXX: need comments on this one
  *	@broadcast:		hw bcast address
  *
@@ -1576,7 +1578,8 @@ enum netdev_priv_flags {
  *	@tx_global_lock: 	XXX: need comments on this one
  *
  *	@xps_maps:	XXX: need comments on this one
- *
+ *	@miniq_egress:		clsact qdisc specific data for
+ *				egress processing
  *	@watchdog_timeo:	Represents the timeout that is used by
  *				the watchdog (see dev_watchdog())
  *	@watchdog_timer:	List of timers
@@ -1795,7 +1798,7 @@ struct net_device {
 	void __rcu		*rx_handler_data;
 
 #ifdef CONFIG_NET_CLS_ACT
-	struct tcf_proto __rcu  *ingress_cl_list;
+	struct mini_Qdisc __rcu	*miniq_ingress;
 #endif
 	struct netdev_queue __rcu *ingress_queue;
 #ifdef CONFIG_NETFILTER_INGRESS
@@ -1826,7 +1829,7 @@ struct net_device {
 	struct xps_dev_maps __rcu *xps_maps;
 #endif
 #ifdef CONFIG_NET_CLS_ACT
-	struct tcf_proto __rcu  *egress_cl_list;
+	struct mini_Qdisc __rcu	*miniq_egress;
 #endif
 
 	/* These may be needed for future network-power-down code. */
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index f230269e0bfb..c64e62c9450a 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -904,4 +904,36 @@ static inline void psched_ratecfg_getrate(struct tc_ratespec *res,
 	res->linklayer = (r->linklayer & TC_LINKLAYER_MASK);
 }
 
+/* Mini Qdisc serves for specific needs of ingress/clsact Qdisc.
+ * The fast path only needs to access filter list and to update stats
+ */
+struct mini_Qdisc {
+	struct tcf_proto *filter_list;
+	struct gnet_stats_basic_cpu __percpu *cpu_bstats;
+	struct gnet_stats_queue	__percpu *cpu_qstats;
+	struct rcu_head rcu;
+};
+
+static inline void mini_qdisc_bstats_cpu_update(struct mini_Qdisc *miniq,
+						const struct sk_buff *skb)
+{
+	bstats_cpu_update(this_cpu_ptr(miniq->cpu_bstats), skb);
+}
+
+static inline void mini_qdisc_qstats_cpu_drop(struct mini_Qdisc *miniq)
+{
+	this_cpu_inc(miniq->cpu_qstats->drops);
+}
+
+struct mini_Qdisc_pair {
+	struct mini_Qdisc miniq1;
+	struct mini_Qdisc miniq2;
+	struct mini_Qdisc __rcu **p_miniq;
+};
+
+void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp,
+			  struct tcf_proto *tp_head);
+void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc,
+			  struct mini_Qdisc __rcu **p_miniq);
+
 #endif
diff --git a/net/core/dev.c b/net/core/dev.c
index 24ac9083bc13..1423cf4d695c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3274,22 +3274,22 @@ EXPORT_SYMBOL(dev_loopback_xmit);
 static struct sk_buff *
 sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
 {
-	struct tcf_proto *cl = rcu_dereference_bh(dev->egress_cl_list);
+	struct mini_Qdisc *miniq = rcu_dereference_bh(dev->miniq_egress);
 	struct tcf_result cl_res;
 
-	if (!cl)
+	if (!miniq)
 		return skb;
 
 	/* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */
-	qdisc_bstats_cpu_update(cl->q, skb);
+	mini_qdisc_bstats_cpu_update(miniq, skb);
 
-	switch (tcf_classify(skb, cl, &cl_res, false)) {
+	switch (tcf_classify(skb, miniq->filter_list, &cl_res, false)) {
 	case TC_ACT_OK:
 	case TC_ACT_RECLASSIFY:
 		skb->tc_index = TC_H_MIN(cl_res.classid);
 		break;
 	case TC_ACT_SHOT:
-		qdisc_qstats_cpu_drop(cl->q);
+		mini_qdisc_qstats_cpu_drop(miniq);
 		*ret = NET_XMIT_DROP;
 		kfree_skb(skb);
 		return NULL;
@@ -4189,7 +4189,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 		   struct net_device *orig_dev)
 {
 #ifdef CONFIG_NET_CLS_ACT
-	struct tcf_proto *cl = rcu_dereference_bh(skb->dev->ingress_cl_list);
+	struct mini_Qdisc *miniq = rcu_dereference_bh(skb->dev->miniq_ingress);
 	struct tcf_result cl_res;
 
 	/* If there's at least one ingress present somewhere (so
@@ -4197,8 +4197,9 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 	 * that are not configured with an ingress qdisc will bail
 	 * out here.
 	 */
-	if (!cl)
+	if (!miniq)
 		return skb;
+
 	if (*pt_prev) {
 		*ret = deliver_skb(skb, *pt_prev, orig_dev);
 		*pt_prev = NULL;
@@ -4206,15 +4207,15 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 
 	qdisc_skb_cb(skb)->pkt_len = skb->len;
 	skb->tc_at_ingress = 1;
-	qdisc_bstats_cpu_update(cl->q, skb);
+	mini_qdisc_bstats_cpu_update(miniq, skb);
 
-	switch (tcf_classify(skb, cl, &cl_res, false)) {
+	switch (tcf_classify(skb, miniq->filter_list, &cl_res, false)) {
 	case TC_ACT_OK:
 	case TC_ACT_RECLASSIFY:
 		skb->tc_index = TC_H_MIN(cl_res.classid);
 		break;
 	case TC_ACT_SHOT:
-		qdisc_qstats_cpu_drop(cl->q);
+		mini_qdisc_qstats_cpu_drop(miniq);
 		kfree_skb(skb);
 		return NULL;
 	case TC_ACT_STOLEN:
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index aa74aa42b5d7..3839cbbdc32b 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -1024,3 +1024,49 @@ void psched_ratecfg_precompute(struct psched_ratecfg *r,
 	}
 }
 EXPORT_SYMBOL(psched_ratecfg_precompute);
+
+static void mini_qdisc_rcu_func(struct rcu_head *head)
+{
+}
+
+void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp,
+			  struct tcf_proto *tp_head)
+{
+	struct mini_Qdisc *miniq_old = rtnl_dereference(*miniqp->p_miniq);
+	struct mini_Qdisc *miniq;
+
+	if (!tp_head) {
+		RCU_INIT_POINTER(*miniqp->p_miniq, NULL);
+		return;
+	}
+
+	miniq = !miniq_old || miniq_old == &miniqp->miniq2 ?
+		&miniqp->miniq1 : &miniqp->miniq2;
+
+	/* We need to make sure that readers won't see the miniq
+	 * we are about to modify. So wait until previous call_rcu_bh callback
+	 * is done.
+	 */
+	rcu_barrier_bh();
+	miniq->filter_list = tp_head;
+	rcu_assign_pointer(*miniqp->p_miniq, miniq);
+
+	if (miniq_old)
+		/* This is counterpart of the rcu barrier above. We need to
+		 * block potential new user of miniq_old until all readers
+		 * are not seeing it.
+		 */
+		call_rcu_bh(&miniq_old->rcu, mini_qdisc_rcu_func);
+}
+EXPORT_SYMBOL(mini_qdisc_pair_swap);
+
+void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc,
+			  struct mini_Qdisc __rcu **p_miniq)
+{
+	miniqp->miniq1.cpu_bstats = qdisc->cpu_bstats;
+	miniqp->miniq1.cpu_qstats = qdisc->cpu_qstats;
+	miniqp->miniq2.cpu_bstats = qdisc->cpu_bstats;
+	miniqp->miniq2.cpu_qstats = qdisc->cpu_qstats;
+	miniqp->p_miniq = p_miniq;
+}
+EXPORT_SYMBOL(mini_qdisc_pair_init);
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index 811845815b8c..5ecc38f35d47 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -21,6 +21,7 @@
 struct ingress_sched_data {
 	struct tcf_block *block;
 	struct tcf_block_ext_info block_info;
+	struct mini_Qdisc_pair miniqp;
 };
 
 static struct Qdisc *ingress_leaf(struct Qdisc *sch, unsigned long arg)
@@ -56,9 +57,9 @@ static struct tcf_block *ingress_tcf_block(struct Qdisc *sch, unsigned long cl)
 
 static void clsact_chain_head_change(struct tcf_proto *tp_head, void *priv)
 {
-	struct tcf_proto __rcu **p_filter_chain = priv;
+	struct mini_Qdisc_pair *miniqp = priv;
 
-	rcu_assign_pointer(*p_filter_chain, tp_head);
+	mini_qdisc_pair_swap(miniqp, tp_head);
 }
 
 static int ingress_init(struct Qdisc *sch, struct nlattr *opt)
@@ -67,9 +68,11 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt)
 	struct net_device *dev = qdisc_dev(sch);
 	int err;
 
+	mini_qdisc_pair_init(&q->miniqp, sch, &dev->miniq_ingress);
+
 	q->block_info.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
 	q->block_info.chain_head_change = clsact_chain_head_change;
-	q->block_info.chain_head_change_priv = &dev->ingress_cl_list;
+	q->block_info.chain_head_change_priv = &q->miniqp;
 
 	err = tcf_block_get_ext(&q->block, sch, &q->block_info);
 	if (err)
@@ -128,6 +131,8 @@ struct clsact_sched_data {
 	struct tcf_block *egress_block;
 	struct tcf_block_ext_info ingress_block_info;
 	struct tcf_block_ext_info egress_block_info;
+	struct mini_Qdisc_pair miniqp_ingress;
+	struct mini_Qdisc_pair miniqp_egress;
 };
 
 static unsigned long clsact_find(struct Qdisc *sch, u32 classid)
@@ -167,17 +172,21 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt)
 	struct net_device *dev = qdisc_dev(sch);
 	int err;
 
+	mini_qdisc_pair_init(&q->miniqp_ingress, sch, &dev->miniq_ingress);
+
 	q->ingress_block_info.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
 	q->ingress_block_info.chain_head_change = clsact_chain_head_change;
-	q->ingress_block_info.chain_head_change_priv = &dev->ingress_cl_list;
+	q->ingress_block_info.chain_head_change_priv = &q->miniqp_ingress;
 
 	err = tcf_block_get_ext(&q->ingress_block, sch, &q->ingress_block_info);
 	if (err)
 		return err;
 
+	mini_qdisc_pair_init(&q->miniqp_egress, sch, &dev->miniq_egress);
+
 	q->egress_block_info.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS;
 	q->egress_block_info.chain_head_change = clsact_chain_head_change;
-	q->egress_block_info.chain_head_change_priv = &dev->egress_cl_list;
+	q->egress_block_info.chain_head_change_priv = &q->miniqp_egress;
 
 	err = tcf_block_get_ext(&q->egress_block, sch, &q->egress_block_info);
 	if (err)
-- 
cgit v1.2.3


From f4e63525ee35f9c02e9f51f90571718363e9a9a9 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 3 Nov 2017 13:56:16 -0700
Subject: net: bpf: rename ndo_xdp to ndo_bpf

ndo_xdp is a control path callback for setting up XDP in the
driver.  We can reuse it for other forms of communication
between the eBPF stack and the drivers.  Rename the callback
and associated structures and definitions.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c          |  2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c      |  2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h      |  2 +-
 drivers/net/ethernet/cavium/thunder/nicvf_main.c   |  4 +--
 drivers/net/ethernet/intel/i40e/i40e_main.c        |  6 ++--
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c      |  4 +--
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c     |  6 ++--
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |  4 +--
 .../net/ethernet/netronome/nfp/nfp_net_common.c    |  4 +--
 drivers/net/ethernet/qlogic/qede/qede.h            |  2 +-
 drivers/net/ethernet/qlogic/qede/qede_filter.c     |  2 +-
 drivers/net/ethernet/qlogic/qede/qede_main.c       |  4 +--
 drivers/net/tun.c                                  |  4 +--
 drivers/net/virtio_net.c                           |  4 +--
 include/linux/netdevice.h                          | 23 ++++++++-------
 net/core/dev.c                                     | 34 +++++++++++-----------
 net/core/rtnetlink.c                               |  4 +--
 17 files changed, 56 insertions(+), 55 deletions(-)

(limited to 'include/linux/netdevice.h')

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 4e3d569bf32e..96416f5d97f3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7775,7 +7775,7 @@ static const struct net_device_ops bnxt_netdev_ops = {
 #endif
 	.ndo_udp_tunnel_add	= bnxt_udp_tunnel_add,
 	.ndo_udp_tunnel_del	= bnxt_udp_tunnel_del,
-	.ndo_xdp		= bnxt_xdp,
+	.ndo_bpf		= bnxt_xdp,
 	.ndo_bridge_getlink	= bnxt_bridge_getlink,
 	.ndo_bridge_setlink	= bnxt_bridge_setlink,
 	.ndo_get_phys_port_name = bnxt_get_phys_port_name
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 06ce63c00821..261e5847557a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -208,7 +208,7 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
 	return 0;
 }
 
-int bnxt_xdp(struct net_device *dev, struct netdev_xdp *xdp)
+int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	int rc;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
index 12a5ad66b564..414b748038ca 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
@@ -16,6 +16,6 @@ void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts);
 bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 		 struct page *page, u8 **data_ptr, unsigned int *len,
 		 u8 *event);
-int bnxt_xdp(struct net_device *dev, struct netdev_xdp *xdp);
+int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp);
 
 #endif
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 71989e180289..a063c36c4c58 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -1741,7 +1741,7 @@ static int nicvf_xdp_setup(struct nicvf *nic, struct bpf_prog *prog)
 	return 0;
 }
 
-static int nicvf_xdp(struct net_device *netdev, struct netdev_xdp *xdp)
+static int nicvf_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
 {
 	struct nicvf *nic = netdev_priv(netdev);
 
@@ -1774,7 +1774,7 @@ static const struct net_device_ops nicvf_netdev_ops = {
 	.ndo_tx_timeout         = nicvf_tx_timeout,
 	.ndo_fix_features       = nicvf_fix_features,
 	.ndo_set_features       = nicvf_set_features,
-	.ndo_xdp		= nicvf_xdp,
+	.ndo_bpf		= nicvf_xdp,
 };
 
 static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index dfecaeda0654..05b94d87a6c3 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -11648,12 +11648,12 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi,
 }
 
 /**
- * i40e_xdp - implements ndo_xdp for i40e
+ * i40e_xdp - implements ndo_bpf for i40e
  * @dev: netdevice
  * @xdp: XDP command
  **/
 static int i40e_xdp(struct net_device *dev,
-		    struct netdev_xdp *xdp)
+		    struct netdev_bpf *xdp)
 {
 	struct i40e_netdev_priv *np = netdev_priv(dev);
 	struct i40e_vsi *vsi = np->vsi;
@@ -11705,7 +11705,7 @@ static const struct net_device_ops i40e_netdev_ops = {
 	.ndo_features_check	= i40e_features_check,
 	.ndo_bridge_getlink	= i40e_ndo_bridge_getlink,
 	.ndo_bridge_setlink	= i40e_ndo_bridge_setlink,
-	.ndo_xdp		= i40e_xdp,
+	.ndo_bpf		= i40e_xdp,
 };
 
 /**
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 507977994a03..e5dcb25be398 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -10004,7 +10004,7 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
 	return 0;
 }
 
-static int ixgbe_xdp(struct net_device *dev, struct netdev_xdp *xdp)
+static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(dev);
 
@@ -10113,7 +10113,7 @@ static const struct net_device_ops ixgbe_netdev_ops = {
 	.ndo_udp_tunnel_add	= ixgbe_add_udp_tunnel_port,
 	.ndo_udp_tunnel_del	= ixgbe_del_udp_tunnel_port,
 	.ndo_features_check	= ixgbe_features_check,
-	.ndo_xdp		= ixgbe_xdp,
+	.ndo_bpf		= ixgbe_xdp,
 	.ndo_xdp_xmit		= ixgbe_xdp_xmit,
 	.ndo_xdp_flush		= ixgbe_xdp_flush,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index d611df2f274d..736a6ccaf05e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2916,7 +2916,7 @@ static u32 mlx4_xdp_query(struct net_device *dev)
 	return prog_id;
 }
 
-static int mlx4_xdp(struct net_device *dev, struct netdev_xdp *xdp)
+static int mlx4_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
@@ -2958,7 +2958,7 @@ static const struct net_device_ops mlx4_netdev_ops = {
 	.ndo_udp_tunnel_del	= mlx4_en_del_vxlan_port,
 	.ndo_features_check	= mlx4_en_features_check,
 	.ndo_set_tx_maxrate	= mlx4_en_set_tx_maxrate,
-	.ndo_xdp		= mlx4_xdp,
+	.ndo_bpf		= mlx4_xdp,
 };
 
 static const struct net_device_ops mlx4_netdev_ops_master = {
@@ -2995,7 +2995,7 @@ static const struct net_device_ops mlx4_netdev_ops_master = {
 	.ndo_udp_tunnel_del	= mlx4_en_del_vxlan_port,
 	.ndo_features_check	= mlx4_en_features_check,
 	.ndo_set_tx_maxrate	= mlx4_en_set_tx_maxrate,
-	.ndo_xdp		= mlx4_xdp,
+	.ndo_bpf		= mlx4_xdp,
 };
 
 struct mlx4_en_bond {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 28ae00b3eb88..3b7b7bb84eb0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3831,7 +3831,7 @@ static u32 mlx5e_xdp_query(struct net_device *dev)
 	return prog_id;
 }
 
-static int mlx5e_xdp(struct net_device *dev, struct netdev_xdp *xdp)
+static int mlx5e_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
@@ -3883,7 +3883,7 @@ static const struct net_device_ops mlx5e_netdev_ops = {
 	.ndo_rx_flow_steer	 = mlx5e_rx_flow_steer,
 #endif
 	.ndo_tx_timeout          = mlx5e_tx_timeout,
-	.ndo_xdp		 = mlx5e_xdp,
+	.ndo_bpf		 = mlx5e_xdp,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller     = mlx5e_netpoll,
 #endif
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 185a3dd35a3f..f6c6ad4e8a59 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -3378,7 +3378,7 @@ nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog, u32 flags,
 	return 0;
 }
 
-static int nfp_net_xdp(struct net_device *netdev, struct netdev_xdp *xdp)
+static int nfp_net_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
 
@@ -3441,7 +3441,7 @@ const struct net_device_ops nfp_net_netdev_ops = {
 	.ndo_get_phys_port_name	= nfp_port_get_phys_port_name,
 	.ndo_udp_tunnel_add	= nfp_net_add_vxlan_port,
 	.ndo_udp_tunnel_del	= nfp_net_del_vxlan_port,
-	.ndo_xdp		= nfp_net_xdp,
+	.ndo_bpf		= nfp_net_xdp,
 };
 
 /**
diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index adb700512baa..a3a70ade411f 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -503,7 +503,7 @@ void qede_fill_rss_params(struct qede_dev *edev,
 void qede_udp_tunnel_add(struct net_device *dev, struct udp_tunnel_info *ti);
 void qede_udp_tunnel_del(struct net_device *dev, struct udp_tunnel_info *ti);
 
-int qede_xdp(struct net_device *dev, struct netdev_xdp *xdp);
+int qede_xdp(struct net_device *dev, struct netdev_bpf *xdp);
 
 #ifdef CONFIG_DCB
 void qede_set_dcbnl_ops(struct net_device *ndev);
diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
index f79e36e4060a..c1a0708a7d7c 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_filter.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -1065,7 +1065,7 @@ static int qede_xdp_set(struct qede_dev *edev, struct bpf_prog *prog)
 	return 0;
 }
 
-int qede_xdp(struct net_device *dev, struct netdev_xdp *xdp)
+int qede_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	struct qede_dev *edev = netdev_priv(dev);
 
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index e5ee9f274a71..8f9b3eb82137 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -556,7 +556,7 @@ static const struct net_device_ops qede_netdev_ops = {
 	.ndo_udp_tunnel_add = qede_udp_tunnel_add,
 	.ndo_udp_tunnel_del = qede_udp_tunnel_del,
 	.ndo_features_check = qede_features_check,
-	.ndo_xdp = qede_xdp,
+	.ndo_bpf = qede_xdp,
 #ifdef CONFIG_RFS_ACCEL
 	.ndo_rx_flow_steer = qede_rx_flow_steer,
 #endif
@@ -594,7 +594,7 @@ static const struct net_device_ops qede_netdev_vf_xdp_ops = {
 	.ndo_udp_tunnel_add = qede_udp_tunnel_add,
 	.ndo_udp_tunnel_del = qede_udp_tunnel_del,
 	.ndo_features_check = qede_features_check,
-	.ndo_xdp = qede_xdp,
+	.ndo_bpf = qede_xdp,
 };
 
 /* -------------------------------------------------------------------------
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 8125956f62a1..1a326b697221 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1141,7 +1141,7 @@ static u32 tun_xdp_query(struct net_device *dev)
 	return 0;
 }
 
-static int tun_xdp(struct net_device *dev, struct netdev_xdp *xdp)
+static int tun_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
@@ -1185,7 +1185,7 @@ static const struct net_device_ops tap_netdev_ops = {
 	.ndo_features_check	= passthru_features_check,
 	.ndo_set_rx_headroom	= tun_set_headroom,
 	.ndo_get_stats64	= tun_net_get_stats64,
-	.ndo_xdp		= tun_xdp,
+	.ndo_bpf		= tun_xdp,
 };
 
 static void tun_flow_init(struct tun_struct *tun)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index fc059f193e7d..edf984406ba0 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2088,7 +2088,7 @@ static u32 virtnet_xdp_query(struct net_device *dev)
 	return 0;
 }
 
-static int virtnet_xdp(struct net_device *dev, struct netdev_xdp *xdp)
+static int virtnet_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
@@ -2115,7 +2115,7 @@ static const struct net_device_ops virtnet_netdev = {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = virtnet_netpoll,
 #endif
-	.ndo_xdp		= virtnet_xdp,
+	.ndo_bpf		= virtnet_xdp,
 	.ndo_xdp_xmit		= virtnet_xdp_xmit,
 	.ndo_xdp_flush		= virtnet_xdp_flush,
 	.ndo_features_check	= passthru_features_check,
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7de7656550c2..9af9feaaeb64 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -779,10 +779,10 @@ enum tc_setup_type {
 	TC_SETUP_CBS,
 };
 
-/* These structures hold the attributes of xdp state that are being passed
- * to the netdevice through the xdp op.
+/* These structures hold the attributes of bpf state that are being passed
+ * to the netdevice through the bpf op.
  */
-enum xdp_netdev_command {
+enum bpf_netdev_command {
 	/* Set or clear a bpf program used in the earliest stages of packet
 	 * rx. The prog will have been loaded as BPF_PROG_TYPE_XDP. The callee
 	 * is responsible for calling bpf_prog_put on any old progs that are
@@ -801,8 +801,8 @@ enum xdp_netdev_command {
 
 struct netlink_ext_ack;
 
-struct netdev_xdp {
-	enum xdp_netdev_command command;
+struct netdev_bpf {
+	enum bpf_netdev_command command;
 	union {
 		/* XDP_SETUP_PROG */
 		struct {
@@ -1124,9 +1124,10 @@ struct dev_ifalias {
  *	appropriate rx headroom value allows avoiding skb head copy on
  *	forward. Setting a negative value resets the rx headroom to the
  *	default value.
- * int (*ndo_xdp)(struct net_device *dev, struct netdev_xdp *xdp);
+ * int (*ndo_bpf)(struct net_device *dev, struct netdev_bpf *bpf);
  *	This function is used to set or query state related to XDP on the
- *	netdevice. See definition of enum xdp_netdev_command for details.
+ *	netdevice and manage BPF offload. See definition of
+ *	enum bpf_netdev_command for details.
  * int (*ndo_xdp_xmit)(struct net_device *dev, struct xdp_buff *xdp);
  *	This function is used to submit a XDP packet for transmit on a
  *	netdevice.
@@ -1315,8 +1316,8 @@ struct net_device_ops {
 						       struct sk_buff *skb);
 	void			(*ndo_set_rx_headroom)(struct net_device *dev,
 						       int needed_headroom);
-	int			(*ndo_xdp)(struct net_device *dev,
-					   struct netdev_xdp *xdp);
+	int			(*ndo_bpf)(struct net_device *dev,
+					   struct netdev_bpf *bpf);
 	int			(*ndo_xdp_xmit)(struct net_device *dev,
 						struct xdp_buff *xdp);
 	void			(*ndo_xdp_flush)(struct net_device *dev);
@@ -3311,10 +3312,10 @@ struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *d
 struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 				    struct netdev_queue *txq, int *ret);
 
-typedef int (*xdp_op_t)(struct net_device *dev, struct netdev_xdp *xdp);
+typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf);
 int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 		      int fd, u32 flags);
-u8 __dev_xdp_attached(struct net_device *dev, xdp_op_t xdp_op, u32 *prog_id);
+u8 __dev_xdp_attached(struct net_device *dev, bpf_op_t xdp_op, u32 *prog_id);
 
 int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
 int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
diff --git a/net/core/dev.c b/net/core/dev.c
index 1423cf4d695c..10cde58d3275 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4545,7 +4545,7 @@ static int __netif_receive_skb(struct sk_buff *skb)
 	return ret;
 }
 
-static int generic_xdp_install(struct net_device *dev, struct netdev_xdp *xdp)
+static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	struct bpf_prog *old = rtnl_dereference(dev->xdp_prog);
 	struct bpf_prog *new = xdp->prog;
@@ -7090,26 +7090,26 @@ int dev_change_proto_down(struct net_device *dev, bool proto_down)
 }
 EXPORT_SYMBOL(dev_change_proto_down);
 
-u8 __dev_xdp_attached(struct net_device *dev, xdp_op_t xdp_op, u32 *prog_id)
+u8 __dev_xdp_attached(struct net_device *dev, bpf_op_t bpf_op, u32 *prog_id)
 {
-	struct netdev_xdp xdp;
+	struct netdev_bpf xdp;
 
 	memset(&xdp, 0, sizeof(xdp));
 	xdp.command = XDP_QUERY_PROG;
 
 	/* Query must always succeed. */
-	WARN_ON(xdp_op(dev, &xdp) < 0);
+	WARN_ON(bpf_op(dev, &xdp) < 0);
 	if (prog_id)
 		*prog_id = xdp.prog_id;
 
 	return xdp.prog_attached;
 }
 
-static int dev_xdp_install(struct net_device *dev, xdp_op_t xdp_op,
+static int dev_xdp_install(struct net_device *dev, bpf_op_t bpf_op,
 			   struct netlink_ext_ack *extack, u32 flags,
 			   struct bpf_prog *prog)
 {
-	struct netdev_xdp xdp;
+	struct netdev_bpf xdp;
 
 	memset(&xdp, 0, sizeof(xdp));
 	if (flags & XDP_FLAGS_HW_MODE)
@@ -7120,7 +7120,7 @@ static int dev_xdp_install(struct net_device *dev, xdp_op_t xdp_op,
 	xdp.flags = flags;
 	xdp.prog = prog;
 
-	return xdp_op(dev, &xdp);
+	return bpf_op(dev, &xdp);
 }
 
 /**
@@ -7137,24 +7137,24 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 	struct bpf_prog *prog = NULL;
-	xdp_op_t xdp_op, xdp_chk;
+	bpf_op_t bpf_op, bpf_chk;
 	int err;
 
 	ASSERT_RTNL();
 
-	xdp_op = xdp_chk = ops->ndo_xdp;
-	if (!xdp_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE)))
+	bpf_op = bpf_chk = ops->ndo_bpf;
+	if (!bpf_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE)))
 		return -EOPNOTSUPP;
-	if (!xdp_op || (flags & XDP_FLAGS_SKB_MODE))
-		xdp_op = generic_xdp_install;
-	if (xdp_op == xdp_chk)
-		xdp_chk = generic_xdp_install;
+	if (!bpf_op || (flags & XDP_FLAGS_SKB_MODE))
+		bpf_op = generic_xdp_install;
+	if (bpf_op == bpf_chk)
+		bpf_chk = generic_xdp_install;
 
 	if (fd >= 0) {
-		if (xdp_chk && __dev_xdp_attached(dev, xdp_chk, NULL))
+		if (bpf_chk && __dev_xdp_attached(dev, bpf_chk, NULL))
 			return -EEXIST;
 		if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) &&
-		    __dev_xdp_attached(dev, xdp_op, NULL))
+		    __dev_xdp_attached(dev, bpf_op, NULL))
 			return -EBUSY;
 
 		prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP);
@@ -7162,7 +7162,7 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 			return PTR_ERR(prog);
 	}
 
-	err = dev_xdp_install(dev, xdp_op, extack, flags, prog);
+	err = dev_xdp_install(dev, bpf_op, extack, flags, prog);
 	if (err < 0 && prog)
 		bpf_prog_put(prog);
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 8a8c51937edf..dc5ad84ac096 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1270,10 +1270,10 @@ static u8 rtnl_xdp_attached_mode(struct net_device *dev, u32 *prog_id)
 		*prog_id = generic_xdp_prog->aux->id;
 		return XDP_ATTACHED_SKB;
 	}
-	if (!ops->ndo_xdp)
+	if (!ops->ndo_bpf)
 		return XDP_ATTACHED_NONE;
 
-	return __dev_xdp_attached(dev, ops->ndo_xdp, prog_id);
+	return __dev_xdp_attached(dev, ops->ndo_bpf, prog_id);
 }
 
 static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev)
-- 
cgit v1.2.3


From ab3f0063c48c26c927851b6767824e35a716d878 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 3 Nov 2017 13:56:17 -0700
Subject: bpf: offload: add infrastructure for loading programs for a specific
 netdev

The fact that we don't know which device the program is going
to be used on is quite limiting in current eBPF infrastructure.
We have to reverse or limit the changes which kernel makes to
the loaded bytecode if we want it to be offloaded to a networking
device.  We also have to invent new APIs for debugging and
troubleshooting support.

Make it possible to load programs for a specific netdev.  This
helps us to bring the debug information closer to the core
eBPF infrastructure (e.g. we will be able to reuse the verifer
log in device JIT).  It allows device JITs to perform translation
on the original bytecode.

__bpf_prog_get() when called to get a reference for an attachment
point will now refuse to give it if program has a device assigned.
Following patches will add a version of that function which passes
the expected netdev in. @type argument in __bpf_prog_get() is
renamed to attach_type to make it clearer that it's only set on
attachment.

All calls to ndo_bpf are protected by rtnl, only verifier callbacks
are not.  We need a wait queue to make sure netdev doesn't get
destroyed while verifier is still running and calling its driver.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/bpf.h          |  36 +++++++++
 include/linux/bpf_verifier.h |  10 +++
 include/linux/netdevice.h    |  14 ++++
 include/uapi/linux/bpf.h     |   1 +
 kernel/bpf/Makefile          |   1 +
 kernel/bpf/core.c            |  10 ++-
 kernel/bpf/offload.c         | 182 +++++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/syscall.c         |  17 +++-
 kernel/bpf/verifier.c        |  15 +++-
 9 files changed, 278 insertions(+), 8 deletions(-)
 create mode 100644 kernel/bpf/offload.c

(limited to 'include/linux/netdevice.h')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 520aeebe0d93..e45d43f9ec92 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -15,6 +15,7 @@
 #include <linux/err.h>
 #include <linux/rbtree_latch.h>
 #include <linux/numa.h>
+#include <linux/wait.h>
 
 struct perf_event;
 struct bpf_prog;
@@ -182,6 +183,16 @@ struct bpf_verifier_ops {
 				  struct bpf_prog *prog, u32 *target_size);
 };
 
+struct bpf_dev_offload {
+	struct bpf_prog		*prog;
+	struct net_device	*netdev;
+	void			*dev_priv;
+	struct list_head	offloads;
+	bool			dev_state;
+	bool			verifier_running;
+	wait_queue_head_t	verifier_done;
+};
+
 struct bpf_prog_aux {
 	atomic_t refcnt;
 	u32 used_map_cnt;
@@ -199,6 +210,7 @@ struct bpf_prog_aux {
 #ifdef CONFIG_SECURITY
 	void *security;
 #endif
+	struct bpf_dev_offload *offload;
 	union {
 		struct work_struct work;
 		struct rcu_head	rcu;
@@ -317,6 +329,7 @@ extern const struct file_operations bpf_prog_fops;
 #undef BPF_PROG_TYPE
 #undef BPF_MAP_TYPE
 
+extern const struct bpf_prog_ops bpf_offload_prog_ops;
 extern const struct bpf_verifier_ops tc_cls_act_analyzer_ops;
 extern const struct bpf_verifier_ops xdp_analyzer_ops;
 
@@ -491,6 +504,29 @@ static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu,
 }
 #endif /* CONFIG_BPF_SYSCALL */
 
+int bpf_prog_offload_compile(struct bpf_prog *prog);
+void bpf_prog_offload_destroy(struct bpf_prog *prog);
+
+#if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL)
+int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr);
+
+static inline bool bpf_prog_is_dev_bound(struct bpf_prog_aux *aux)
+{
+	return aux->offload;
+}
+#else
+static inline int bpf_prog_offload_init(struct bpf_prog *prog,
+					union bpf_attr *attr)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline bool bpf_prog_is_dev_bound(struct bpf_prog_aux *aux)
+{
+	return false;
+}
+#endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */
+
 #if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL)
 struct sock  *__sock_map_lookup_elem(struct bpf_map *map, u32 key);
 int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type);
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 3b0976aaac75..e45011dbc02d 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -153,6 +153,7 @@ struct bpf_verifier_env {
 	struct bpf_verifier_state *cur_state; /* current verifier state */
 	struct bpf_verifier_state_list **explored_states; /* search pruning optimization */
 	const struct bpf_ext_analyzer_ops *analyzer_ops; /* external analyzer ops */
+	const struct bpf_ext_analyzer_ops *dev_ops; /* device analyzer ops */
 	void *analyzer_priv; /* pointer to external analyzer's private data */
 	struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */
 	u32 used_map_cnt;		/* number of used maps */
@@ -169,6 +170,15 @@ static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env)
 	return env->cur_state->regs;
 }
 
+#if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL)
+int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env);
+#else
+int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
 int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops,
 		 void *priv);
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9af9feaaeb64..fda527ccb263 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -797,8 +797,13 @@ enum bpf_netdev_command {
 	 * is equivalent to XDP_ATTACHED_DRV.
 	 */
 	XDP_QUERY_PROG,
+	/* BPF program for offload callbacks, invoked at program load time. */
+	BPF_OFFLOAD_VERIFIER_PREP,
+	BPF_OFFLOAD_TRANSLATE,
+	BPF_OFFLOAD_DESTROY,
 };
 
+struct bpf_ext_analyzer_ops;
 struct netlink_ext_ack;
 
 struct netdev_bpf {
@@ -815,6 +820,15 @@ struct netdev_bpf {
 			u8 prog_attached;
 			u32 prog_id;
 		};
+		/* BPF_OFFLOAD_VERIFIER_PREP */
+		struct {
+			struct bpf_prog *prog;
+			const struct bpf_ext_analyzer_ops *ops; /* callee set */
+		} verifier;
+		/* BPF_OFFLOAD_TRANSLATE, BPF_OFFLOAD_DESTROY */
+		struct {
+			struct bpf_prog *prog;
+		} offload;
 	};
 };
 
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index a9820677c2ff..80d191a93fb0 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -260,6 +260,7 @@ union bpf_attr {
 		__u32		kern_version;	/* checked when prog_type=kprobe */
 		__u32		prog_flags;
 		char		prog_name[BPF_OBJ_NAME_LEN];
+		__u32		prog_target_ifindex;	/* ifindex of netdev to prep for */
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 16e95c8e749e..e691da0b3bab 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -7,6 +7,7 @@ obj-$(CONFIG_BPF_SYSCALL) += disasm.o
 ifeq ($(CONFIG_NET),y)
 obj-$(CONFIG_BPF_SYSCALL) += devmap.o
 obj-$(CONFIG_BPF_SYSCALL) += cpumap.o
+obj-$(CONFIG_BPF_SYSCALL) += offload.o
 ifeq ($(CONFIG_STREAM_PARSER),y)
 obj-$(CONFIG_BPF_SYSCALL) += sockmap.o
 endif
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 7fe448799d76..8a6c37762330 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1380,7 +1380,13 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 	 * valid program, which in this case would simply not
 	 * be JITed, but falls back to the interpreter.
 	 */
-	fp = bpf_int_jit_compile(fp);
+	if (!bpf_prog_is_dev_bound(fp->aux)) {
+		fp = bpf_int_jit_compile(fp);
+	} else {
+		*err = bpf_prog_offload_compile(fp);
+		if (*err)
+			return fp;
+	}
 	bpf_prog_lock_ro(fp);
 
 	/* The tail call compatibility check can only be done at
@@ -1549,6 +1555,8 @@ static void bpf_prog_free_deferred(struct work_struct *work)
 	struct bpf_prog_aux *aux;
 
 	aux = container_of(work, struct bpf_prog_aux, work);
+	if (bpf_prog_is_dev_bound(aux))
+		bpf_prog_offload_destroy(aux->prog);
 	bpf_jit_free(aux->prog);
 }
 
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
new file mode 100644
index 000000000000..5553e0e2f8b1
--- /dev/null
+++ b/kernel/bpf/offload.c
@@ -0,0 +1,182 @@
+#include <linux/bpf.h>
+#include <linux/bpf_verifier.h>
+#include <linux/bug.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/printk.h>
+#include <linux/rtnetlink.h>
+
+/* protected by RTNL */
+static LIST_HEAD(bpf_prog_offload_devs);
+
+int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr)
+{
+	struct net *net = current->nsproxy->net_ns;
+	struct bpf_dev_offload *offload;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (attr->prog_flags)
+		return -EINVAL;
+
+	offload = kzalloc(sizeof(*offload), GFP_USER);
+	if (!offload)
+		return -ENOMEM;
+
+	offload->prog = prog;
+	init_waitqueue_head(&offload->verifier_done);
+
+	rtnl_lock();
+	offload->netdev = __dev_get_by_index(net, attr->prog_target_ifindex);
+	if (!offload->netdev) {
+		rtnl_unlock();
+		kfree(offload);
+		return -EINVAL;
+	}
+
+	prog->aux->offload = offload;
+	list_add_tail(&offload->offloads, &bpf_prog_offload_devs);
+	rtnl_unlock();
+
+	return 0;
+}
+
+static int __bpf_offload_ndo(struct bpf_prog *prog, enum bpf_netdev_command cmd,
+			     struct netdev_bpf *data)
+{
+	struct net_device *netdev = prog->aux->offload->netdev;
+
+	ASSERT_RTNL();
+
+	if (!netdev)
+		return -ENODEV;
+	if (!netdev->netdev_ops->ndo_bpf)
+		return -EOPNOTSUPP;
+
+	data->command = cmd;
+
+	return netdev->netdev_ops->ndo_bpf(netdev, data);
+}
+
+int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env)
+{
+	struct netdev_bpf data = {};
+	int err;
+
+	data.verifier.prog = env->prog;
+
+	rtnl_lock();
+	err = __bpf_offload_ndo(env->prog, BPF_OFFLOAD_VERIFIER_PREP, &data);
+	if (err)
+		goto exit_unlock;
+
+	env->dev_ops = data.verifier.ops;
+
+	env->prog->aux->offload->dev_state = true;
+	env->prog->aux->offload->verifier_running = true;
+exit_unlock:
+	rtnl_unlock();
+	return err;
+}
+
+static void __bpf_prog_offload_destroy(struct bpf_prog *prog)
+{
+	struct bpf_dev_offload *offload = prog->aux->offload;
+	struct netdev_bpf data = {};
+
+	data.offload.prog = prog;
+
+	if (offload->verifier_running)
+		wait_event(offload->verifier_done, !offload->verifier_running);
+
+	if (offload->dev_state)
+		WARN_ON(__bpf_offload_ndo(prog, BPF_OFFLOAD_DESTROY, &data));
+
+	offload->dev_state = false;
+	list_del_init(&offload->offloads);
+	offload->netdev = NULL;
+}
+
+void bpf_prog_offload_destroy(struct bpf_prog *prog)
+{
+	struct bpf_dev_offload *offload = prog->aux->offload;
+
+	offload->verifier_running = false;
+	wake_up(&offload->verifier_done);
+
+	rtnl_lock();
+	__bpf_prog_offload_destroy(prog);
+	rtnl_unlock();
+
+	kfree(offload);
+}
+
+static int bpf_prog_offload_translate(struct bpf_prog *prog)
+{
+	struct bpf_dev_offload *offload = prog->aux->offload;
+	struct netdev_bpf data = {};
+	int ret;
+
+	data.offload.prog = prog;
+
+	offload->verifier_running = false;
+	wake_up(&offload->verifier_done);
+
+	rtnl_lock();
+	ret = __bpf_offload_ndo(prog, BPF_OFFLOAD_TRANSLATE, &data);
+	rtnl_unlock();
+
+	return ret;
+}
+
+static unsigned int bpf_prog_warn_on_exec(const void *ctx,
+					  const struct bpf_insn *insn)
+{
+	WARN(1, "attempt to execute device eBPF program on the host!");
+	return 0;
+}
+
+int bpf_prog_offload_compile(struct bpf_prog *prog)
+{
+	prog->bpf_func = bpf_prog_warn_on_exec;
+
+	return bpf_prog_offload_translate(prog);
+}
+
+const struct bpf_prog_ops bpf_offload_prog_ops = {
+};
+
+static int bpf_offload_notification(struct notifier_block *notifier,
+				    ulong event, void *ptr)
+{
+	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+	struct bpf_dev_offload *offload, *tmp;
+
+	ASSERT_RTNL();
+
+	switch (event) {
+	case NETDEV_UNREGISTER:
+		list_for_each_entry_safe(offload, tmp, &bpf_prog_offload_devs,
+					 offloads) {
+			if (offload->netdev == netdev)
+				__bpf_prog_offload_destroy(offload->prog);
+		}
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block bpf_offload_notifier = {
+	.notifier_call = bpf_offload_notification,
+};
+
+static int __init bpf_offload_init(void)
+{
+	register_netdevice_notifier(&bpf_offload_notifier);
+	return 0;
+}
+
+subsys_initcall(bpf_offload_init);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 323be2473c4b..1574b9f0f24e 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -824,7 +824,10 @@ static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog)
 	if (type >= ARRAY_SIZE(bpf_prog_types) || !bpf_prog_types[type])
 		return -EINVAL;
 
-	prog->aux->ops = bpf_prog_types[type];
+	if (!bpf_prog_is_dev_bound(prog->aux))
+		prog->aux->ops = bpf_prog_types[type];
+	else
+		prog->aux->ops = &bpf_offload_prog_ops;
 	prog->type = type;
 	return 0;
 }
@@ -1054,7 +1057,7 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog)
 }
 EXPORT_SYMBOL_GPL(bpf_prog_inc_not_zero);
 
-static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *type)
+static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type)
 {
 	struct fd f = fdget(ufd);
 	struct bpf_prog *prog;
@@ -1062,7 +1065,7 @@ static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *type)
 	prog = ____bpf_prog_get(f);
 	if (IS_ERR(prog))
 		return prog;
-	if (type && prog->type != *type) {
+	if (attach_type && (prog->type != *attach_type || prog->aux->offload)) {
 		prog = ERR_PTR(-EINVAL);
 		goto out;
 	}
@@ -1089,7 +1092,7 @@ struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type)
 EXPORT_SYMBOL_GPL(bpf_prog_get_type);
 
 /* last field in 'union bpf_attr' used by this command */
-#define	BPF_PROG_LOAD_LAST_FIELD prog_name
+#define	BPF_PROG_LOAD_LAST_FIELD prog_target_ifindex
 
 static int bpf_prog_load(union bpf_attr *attr)
 {
@@ -1152,6 +1155,12 @@ static int bpf_prog_load(union bpf_attr *attr)
 	atomic_set(&prog->aux->refcnt, 1);
 	prog->gpl_compatible = is_gpl ? 1 : 0;
 
+	if (attr->prog_target_ifindex) {
+		err = bpf_prog_offload_init(prog, attr);
+		if (err)
+			goto free_prog;
+	}
+
 	/* find program type: socket_filter vs tracing_filter */
 	err = find_prog_type(type, prog);
 	if (err < 0)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 04357ad5a812..51aabb32ad67 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3736,10 +3736,13 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 static int ext_analyzer_insn_hook(struct bpf_verifier_env *env,
 				  int insn_idx, int prev_insn_idx)
 {
-	if (!env->analyzer_ops || !env->analyzer_ops->insn_hook)
-		return 0;
+	if (env->analyzer_ops && env->analyzer_ops->insn_hook)
+		return env->analyzer_ops->insn_hook(env, insn_idx,
+						    prev_insn_idx);
+	if (env->dev_ops && env->dev_ops->insn_hook)
+		return env->dev_ops->insn_hook(env, insn_idx, prev_insn_idx);
 
-	return env->analyzer_ops->insn_hook(env, insn_idx, prev_insn_idx);
+	return 0;
 }
 
 static int do_check(struct bpf_verifier_env *env)
@@ -4516,6 +4519,12 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
 	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
 		env->strict_alignment = true;
 
+	if (env->prog->aux->offload) {
+		ret = bpf_prog_offload_verifier_prep(env);
+		if (ret)
+			goto err_unlock;
+	}
+
 	ret = replace_map_fd_with_map_ptr(env);
 	if (ret < 0)
 		goto skip_full_check;
-- 
cgit v1.2.3


From 602f3baf22188aad24b9a58be3209ab774b97d74 Mon Sep 17 00:00:00 2001
From: Nogah Frankel <nogahf@mellanox.com>
Date: Mon, 6 Nov 2017 07:23:41 +0100
Subject: net_sch: red: Add offload ability to RED qdisc

Add the ability to offload RED qdisc by using ndo_setup_tc.
There are four commands for RED offloading:
* TC_RED_SET: handles set and change.
* TC_RED_DESTROY: handle qdisc destroy.
* TC_RED_STATS: update the qdiscs counters (given as reference)
* TC_RED_XSTAT: returns red xstats.

Whether RED is being offloaded is being determined every time dump action
is being called because parent change of this qdisc could change its
offload state but doesn't require any RED function to be called.

Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h      |  1 +
 include/net/pkt_cls.h          | 30 ++++++++++++++++
 include/uapi/linux/pkt_sched.h |  1 +
 net/sched/sch_red.c            | 79 ++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 111 insertions(+)

(limited to 'include/linux/netdevice.h')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index fda527ccb263..71968a2ca9f3 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -777,6 +777,7 @@ enum tc_setup_type {
 	TC_SETUP_CLSBPF,
 	TC_SETUP_BLOCK,
 	TC_SETUP_CBS,
+	TC_SETUP_QDISC_RED,
 };
 
 /* These structures hold the attributes of bpf state that are being passed
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 98fef3221227..03c208d3c922 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -703,4 +703,34 @@ struct tc_cookie {
 	u8  *data;
 	u32 len;
 };
+
+enum tc_red_command {
+	TC_RED_REPLACE,
+	TC_RED_DESTROY,
+	TC_RED_STATS,
+	TC_RED_XSTATS,
+};
+
+struct tc_red_qopt_offload_params {
+	u32 min;
+	u32 max;
+	u32 probability;
+	bool is_ecn;
+};
+struct tc_red_qopt_offload_stats {
+	struct gnet_stats_basic_packed *bstats;
+	struct gnet_stats_queue *qstats;
+};
+
+struct tc_red_qopt_offload {
+	enum tc_red_command command;
+	u32 handle;
+	u32 parent;
+	union {
+		struct tc_red_qopt_offload_params set;
+		struct tc_red_qopt_offload_stats stats;
+		struct red_stats *xstats;
+	};
+};
+
 #endif
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 5002562868cc..6a2c5ea7e9c4 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -256,6 +256,7 @@ struct tc_red_qopt {
 #define TC_RED_ECN		1
 #define TC_RED_HARDDROP		2
 #define TC_RED_ADAPTATIVE	4
+#define TC_RED_OFFLOADED	8
 };
 
 struct tc_red_xstats {
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index fdfdb56aaae2..007dd8ef8aac 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -19,6 +19,7 @@
 #include <linux/kernel.h>
 #include <linux/skbuff.h>
 #include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
 #include <net/inet_ecn.h>
 #include <net/red.h>
 
@@ -148,11 +149,37 @@ static void red_reset(struct Qdisc *sch)
 	red_restart(&q->vars);
 }
 
+static int red_offload(struct Qdisc *sch, bool enable)
+{
+	struct red_sched_data *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
+	struct tc_red_qopt_offload opt = {
+		.handle = sch->handle,
+		.parent = sch->parent,
+	};
+
+	if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc)
+		return -EOPNOTSUPP;
+
+	if (enable) {
+		opt.command = TC_RED_REPLACE;
+		opt.set.min = q->parms.qth_min >> q->parms.Wlog;
+		opt.set.max = q->parms.qth_max >> q->parms.Wlog;
+		opt.set.probability = q->parms.max_P;
+		opt.set.is_ecn = red_use_ecn(q);
+	} else {
+		opt.command = TC_RED_DESTROY;
+	}
+
+	return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED, &opt);
+}
+
 static void red_destroy(struct Qdisc *sch)
 {
 	struct red_sched_data *q = qdisc_priv(sch);
 
 	del_timer_sync(&q->adapt_timer);
+	red_offload(sch, false);
 	qdisc_destroy(q->qdisc);
 }
 
@@ -219,6 +246,7 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt)
 		red_start_of_idle_period(&q->vars);
 
 	sch_tree_unlock(sch);
+	red_offload(sch, true);
 	return 0;
 }
 
@@ -244,6 +272,33 @@ static int red_init(struct Qdisc *sch, struct nlattr *opt)
 	return red_change(sch, opt);
 }
 
+static int red_dump_offload(struct Qdisc *sch, struct tc_red_qopt *opt)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct tc_red_qopt_offload hw_stats = {
+		.handle = sch->handle,
+		.parent = sch->parent,
+		.command = TC_RED_STATS,
+		.stats.bstats = &sch->bstats,
+		.stats.qstats = &sch->qstats,
+	};
+	int err;
+
+	opt->flags &= ~TC_RED_OFFLOADED;
+	if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc)
+		return 0;
+
+	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED,
+					    &hw_stats);
+	if (err == -EOPNOTSUPP)
+		return 0;
+
+	if (!err)
+		opt->flags |= TC_RED_OFFLOADED;
+
+	return err;
+}
+
 static int red_dump(struct Qdisc *sch, struct sk_buff *skb)
 {
 	struct red_sched_data *q = qdisc_priv(sch);
@@ -257,8 +312,13 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb)
 		.Plog		= q->parms.Plog,
 		.Scell_log	= q->parms.Scell_log,
 	};
+	int err;
 
 	sch->qstats.backlog = q->qdisc->qstats.backlog;
+	err = red_dump_offload(sch, &opt);
+	if (err)
+		goto nla_put_failure;
+
 	opts = nla_nest_start(skb, TCA_OPTIONS);
 	if (opts == NULL)
 		goto nla_put_failure;
@@ -275,6 +335,7 @@ nla_put_failure:
 static int red_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
 {
 	struct red_sched_data *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
 	struct tc_red_xstats st = {
 		.early	= q->stats.prob_drop + q->stats.forced_drop,
 		.pdrop	= q->stats.pdrop,
@@ -282,6 +343,24 @@ static int red_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
 		.marked	= q->stats.prob_mark + q->stats.forced_mark,
 	};
 
+	if (tc_can_offload(dev) &&  dev->netdev_ops->ndo_setup_tc) {
+		struct red_stats hw_stats = {0};
+		struct tc_red_qopt_offload hw_stats_request = {
+			.handle = sch->handle,
+			.parent = sch->parent,
+			.command = TC_RED_XSTATS,
+			.xstats = &hw_stats,
+		};
+		if (!dev->netdev_ops->ndo_setup_tc(dev,
+						   TC_SETUP_QDISC_RED,
+						   &hw_stats_request)) {
+			st.early += hw_stats.prob_drop + hw_stats.forced_drop;
+			st.pdrop += hw_stats.pdrop;
+			st.other += hw_stats.other;
+			st.marked += hw_stats.prob_mark + hw_stats.forced_mark;
+		}
+	}
+
 	return gnet_stats_copy_app(d, &st, sizeof(st));
 }
 
-- 
cgit v1.2.3


From 575ed7d39e2fbe602a3894bc766a8cb49af83bd3 Mon Sep 17 00:00:00 2001
From: Nogah Frankel <nogahf@mellanox.com>
Date: Mon, 6 Nov 2017 07:23:42 +0100
Subject: net_sch: mqprio: Change TC_SETUP_MQPRIO to TC_SETUP_QDISC_MQPRIO

Change TC_SETUP_MQPRIO to TC_SETUP_QDISC_MQPRIO to match the new
convention.

Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-drv.c               | 2 +-
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c        | 2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt.c              | 2 +-
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c         | 2 +-
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c | 2 +-
 drivers/net/ethernet/intel/fm10k/fm10k_netdev.c        | 2 +-
 drivers/net/ethernet/intel/i40e/i40e_main.c            | 2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c          | 2 +-
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c         | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c      | 2 +-
 drivers/net/ethernet/sfc/falcon/tx.c                   | 2 +-
 drivers/net/ethernet/sfc/tx.c                          | 2 +-
 drivers/net/ethernet/ti/netcp_core.c                   | 2 +-
 include/linux/netdevice.h                              | 2 +-
 net/sched/sch_mqprio.c                                 | 5 +++--
 15 files changed, 17 insertions(+), 16 deletions(-)

(limited to 'include/linux/netdevice.h')

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 3d53153ce751..a74a8fbad53a 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -2206,7 +2206,7 @@ static int xgbe_setup_tc(struct net_device *netdev, enum tc_setup_type type,
 	struct tc_mqprio_qopt *mqprio = type_data;
 	u8 tc;
 
-	if (type != TC_SETUP_MQPRIO)
+	if (type != TC_SETUP_QDISC_MQPRIO)
 		return -EOPNOTSUPP;
 
 	mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 1216c1f1e052..4c739d5355d2 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -4289,7 +4289,7 @@ int __bnx2x_setup_tc(struct net_device *dev, enum tc_setup_type type,
 {
 	struct tc_mqprio_qopt *mqprio = type_data;
 
-	if (type != TC_SETUP_MQPRIO)
+	if (type != TC_SETUP_QDISC_MQPRIO)
 		return -EOPNOTSUPP;
 
 	mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 96416f5d97f3..e5472e5ae7b2 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7388,7 +7388,7 @@ static int bnxt_setup_tc(struct net_device *dev, enum tc_setup_type type,
 	switch (type) {
 	case TC_SETUP_BLOCK:
 		return bnxt_setup_tc_block(dev, type_data);
-	case TC_SETUP_MQPRIO: {
+	case TC_SETUP_QDISC_MQPRIO: {
 		struct tc_mqprio_qopt *mqprio = type_data;
 
 		mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index ebc55b6a6349..784dbf5a3e12 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -351,7 +351,7 @@ static int dpaa_setup_tc(struct net_device *net_dev, enum tc_setup_type type,
 	u8 num_tc;
 	int i;
 
-	if (type != TC_SETUP_MQPRIO)
+	if (type != TC_SETUP_QDISC_MQPRIO)
 		return -EOPNOTSUPP;
 
 	mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
index 2a0af11c9b59..59415090ff0f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
@@ -1252,7 +1252,7 @@ out:
 static int hns3_nic_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			     void *type_data)
 {
-	if (type != TC_SETUP_MQPRIO)
+	if (type != TC_SETUP_QDISC_MQPRIO)
 		return -EOPNOTSUPP;
 
 	return hns3_setup_tc(dev, type_data);
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
index 81e4425f0529..adc62fb38c49 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
@@ -1389,7 +1389,7 @@ static int __fm10k_setup_tc(struct net_device *dev, enum tc_setup_type type,
 {
 	struct tc_mqprio_qopt *mqprio = type_data;
 
-	if (type != TC_SETUP_MQPRIO)
+	if (type != TC_SETUP_QDISC_MQPRIO)
 		return -EOPNOTSUPP;
 
 	mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 05b94d87a6c3..17e6f64299cf 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -7550,7 +7550,7 @@ static int __i40e_setup_tc(struct net_device *netdev, enum tc_setup_type type,
 			   void *type_data)
 {
 	switch (type) {
-	case TC_SETUP_MQPRIO:
+	case TC_SETUP_QDISC_MQPRIO:
 		return i40e_setup_tc(netdev, type_data);
 	case TC_SETUP_BLOCK:
 		return i40e_setup_tc_block(netdev, type_data);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index e5dcb25be398..6eaca8366ac8 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -9431,7 +9431,7 @@ static int __ixgbe_setup_tc(struct net_device *dev, enum tc_setup_type type,
 	switch (type) {
 	case TC_SETUP_BLOCK:
 		return ixgbe_setup_tc_block(dev, type_data);
-	case TC_SETUP_MQPRIO:
+	case TC_SETUP_QDISC_MQPRIO:
 		return ixgbe_setup_tc_mqprio(dev, type_data);
 	default:
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 736a6ccaf05e..99051a294fa6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -135,7 +135,7 @@ static int __mlx4_en_setup_tc(struct net_device *dev, enum tc_setup_type type,
 {
 	struct tc_mqprio_qopt *mqprio = type_data;
 
-	if (type != TC_SETUP_MQPRIO)
+	if (type != TC_SETUP_QDISC_MQPRIO)
 		return -EOPNOTSUPP;
 
 	if (mqprio->num_tc && mqprio->num_tc != MLX4_EN_NUM_UP_HIGH)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index f877f2f5f2a5..5d5d2e50e4bf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3146,7 +3146,7 @@ int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type,
 	case TC_SETUP_BLOCK:
 		return mlx5e_setup_tc_block(dev, type_data);
 #endif
-	case TC_SETUP_MQPRIO:
+	case TC_SETUP_QDISC_MQPRIO:
 		return mlx5e_setup_tc_mqprio(dev, type_data);
 	default:
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/sfc/falcon/tx.c b/drivers/net/ethernet/sfc/falcon/tx.c
index 6a75f4140a4b..1b978d69e702 100644
--- a/drivers/net/ethernet/sfc/falcon/tx.c
+++ b/drivers/net/ethernet/sfc/falcon/tx.c
@@ -435,7 +435,7 @@ int ef4_setup_tc(struct net_device *net_dev, enum tc_setup_type type,
 	unsigned tc, num_tc;
 	int rc;
 
-	if (type != TC_SETUP_MQPRIO)
+	if (type != TC_SETUP_QDISC_MQPRIO)
 		return -EOPNOTSUPP;
 
 	num_tc = mqprio->num_tc;
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index 32bf1fecf864..ea27b8a7f465 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -663,7 +663,7 @@ int efx_setup_tc(struct net_device *net_dev, enum tc_setup_type type,
 	unsigned tc, num_tc;
 	int rc;
 
-	if (type != TC_SETUP_MQPRIO)
+	if (type != TC_SETUP_QDISC_MQPRIO)
 		return -EOPNOTSUPP;
 
 	num_tc = mqprio->num_tc;
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index 437d36289786..15e2e3031d36 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -1887,7 +1887,7 @@ static int netcp_setup_tc(struct net_device *dev, enum tc_setup_type type,
 	/* setup tc must be called under rtnl lock */
 	ASSERT_RTNL();
 
-	if (type != TC_SETUP_MQPRIO)
+	if (type != TC_SETUP_QDISC_MQPRIO)
 		return -EOPNOTSUPP;
 
 	mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 71968a2ca9f3..703885aed856 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -770,7 +770,7 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
 				       struct sk_buff *skb);
 
 enum tc_setup_type {
-	TC_SETUP_MQPRIO,
+	TC_SETUP_QDISC_MQPRIO,
 	TC_SETUP_CLSU32,
 	TC_SETUP_CLSFLOWER,
 	TC_SETUP_CLSMATCHALL,
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 4d5ed45123f0..b85885a9d8a1 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -50,7 +50,8 @@ static void mqprio_destroy(struct Qdisc *sch)
 		switch (priv->mode) {
 		case TC_MQPRIO_MODE_DCB:
 		case TC_MQPRIO_MODE_CHANNEL:
-			dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_MQPRIO,
+			dev->netdev_ops->ndo_setup_tc(dev,
+						      TC_SETUP_QDISC_MQPRIO,
 						      &mqprio);
 			break;
 		default:
@@ -265,7 +266,7 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt)
 			return -EINVAL;
 		}
 		err = dev->netdev_ops->ndo_setup_tc(dev,
-						    TC_SETUP_MQPRIO,
+						    TC_SETUP_QDISC_MQPRIO,
 						    &mqprio);
 		if (err)
 			return err;
-- 
cgit v1.2.3


From 8521db4c7e155d12fb280686c0552e47f77e9110 Mon Sep 17 00:00:00 2001
From: Nogah Frankel <nogahf@mellanox.com>
Date: Mon, 6 Nov 2017 07:23:43 +0100
Subject: net_sch: cbs: Change TC_SETUP_CBS to TC_SETUP_QDISC_CBS

Change TC_SETUP_CBS to TC_SETUP_QDISC_CBS to match the new convention..

Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/igb/igb_main.c | 2 +-
 include/linux/netdevice.h                 | 2 +-
 net/sched/sch_cbs.c                       | 4 ++--
 3 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux/netdevice.h')

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index e22bce7cdacd..43cf39527660 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -2488,7 +2488,7 @@ static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type,
 	struct igb_adapter *adapter = netdev_priv(dev);
 
 	switch (type) {
-	case TC_SETUP_CBS:
+	case TC_SETUP_QDISC_CBS:
 		return igb_offload_cbs(adapter, type_data);
 
 	default:
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 703885aed856..30f0f2928808 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -776,7 +776,7 @@ enum tc_setup_type {
 	TC_SETUP_CLSMATCHALL,
 	TC_SETUP_CLSBPF,
 	TC_SETUP_BLOCK,
-	TC_SETUP_CBS,
+	TC_SETUP_QDISC_CBS,
 	TC_SETUP_QDISC_RED,
 };
 
diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index bdb533b7fb8c..7a72980c1509 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -212,7 +212,7 @@ static void cbs_disable_offload(struct net_device *dev,
 	cbs.queue = q->queue;
 	cbs.enable = 0;
 
-	err = ops->ndo_setup_tc(dev, TC_SETUP_CBS, &cbs);
+	err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_CBS, &cbs);
 	if (err < 0)
 		pr_warn("Couldn't disable CBS offload for queue %d\n",
 			cbs.queue);
@@ -236,7 +236,7 @@ static int cbs_enable_offload(struct net_device *dev, struct cbs_sched_data *q,
 	cbs.idleslope = opt->idleslope;
 	cbs.sendslope = opt->sendslope;
 
-	err = ops->ndo_setup_tc(dev, TC_SETUP_CBS, &cbs);
+	err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_CBS, &cbs);
 	if (err < 0)
 		return err;
 
-- 
cgit v1.2.3


From 375ef2b1f0d0b43b0d36ffdd521637ff59b0c13c Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Sun, 17 Sep 2017 13:43:58 +0300
Subject: net: Introduce netdev_*_once functions

Extend the net device error logging with netdev_*_once macros.
netdev_*_once are the equivalents of the dev_*_once macros which are
useful for messages that should only be logged once.

Also add netdev_WARN_ONCE, which is the "once" extension for the already
existing netdev_WARN macro.

Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 include/linux/netdevice.h | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

(limited to 'include/linux/netdevice.h')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 30f0f2928808..79518ede3170 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4336,6 +4336,31 @@ void netdev_notice(const struct net_device *dev, const char *format, ...);
 __printf(2, 3)
 void netdev_info(const struct net_device *dev, const char *format, ...);
 
+#define netdev_level_once(level, dev, fmt, ...)			\
+do {								\
+	static bool __print_once __read_mostly;			\
+								\
+	if (!__print_once) {					\
+		__print_once = true;				\
+		netdev_printk(level, dev, fmt, ##__VA_ARGS__);	\
+	}							\
+} while (0)
+
+#define netdev_emerg_once(dev, fmt, ...) \
+	netdev_level_once(KERN_EMERG, dev, fmt, ##__VA_ARGS__)
+#define netdev_alert_once(dev, fmt, ...) \
+	netdev_level_once(KERN_ALERT, dev, fmt, ##__VA_ARGS__)
+#define netdev_crit_once(dev, fmt, ...) \
+	netdev_level_once(KERN_CRIT, dev, fmt, ##__VA_ARGS__)
+#define netdev_err_once(dev, fmt, ...) \
+	netdev_level_once(KERN_ERR, dev, fmt, ##__VA_ARGS__)
+#define netdev_warn_once(dev, fmt, ...) \
+	netdev_level_once(KERN_WARNING, dev, fmt, ##__VA_ARGS__)
+#define netdev_notice_once(dev, fmt, ...) \
+	netdev_level_once(KERN_NOTICE, dev, fmt, ##__VA_ARGS__)
+#define netdev_info_once(dev, fmt, ...) \
+	netdev_level_once(KERN_INFO, dev, fmt, ##__VA_ARGS__)
+
 #define MODULE_ALIAS_NETDEV(device) \
 	MODULE_ALIAS("netdev-" device)
 
@@ -4376,6 +4401,10 @@ do {								\
 	WARN(1, "netdevice: %s%s\n" format, netdev_name(dev),	\
 	     netdev_reg_state(dev), ##args)
 
+#define netdev_WARN_ONCE(dev, condition, format, arg...)		\
+	WARN_ONCE(1, "netdevice: %s%s\n" format, netdev_name(dev)	\
+		  netdev_reg_state(dev), ##args)
+
 /* netif printk helpers, similar to netdev_printk */
 
 #define netif_printk(priv, type, level, dev, fmt, args...)	\
-- 
cgit v1.2.3


From 54985120a1c461b74f9510e5d730971f2a2383b1 Mon Sep 17 00:00:00 2001
From: Girish Moodalbail <girish.moodalbail@oracle.com>
Date: Tue, 7 Nov 2017 11:32:11 -0800
Subject: net: fix incorrect comment with regard to VLAN packet handling

The commit bcc6d4790361 ("net: vlan: make non-hw-accel rx path similar
to hw-accel") unified accel and non-accel path for VLAN RX. With that
fix we do not register any packet_type handler for VLANs anymore, so fix
the incorrect comment.

Signed-off-by: Girish Moodalbail <girish.moodalbail@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 8 --------
 1 file changed, 8 deletions(-)

(limited to 'include/linux/netdevice.h')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 79518ede3170..6b274bfe489f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4479,15 +4479,7 @@ do {								\
  *	Why 16. Because with 16 the only overlap we get on a hash of the
  *	low nibble of the protocol value is RARP/SNAP/X.25.
  *
- *      NOTE:  That is no longer true with the addition of VLAN tags.  Not
- *             sure which should go first, but I bet it won't make much
- *             difference if we are running VLANs.  The good news is that
- *             this protocol won't be in the list unless compiled in, so
- *             the average user (w/out VLANs) will not be adversely affected.
- *             --BLG
- *
  *		0800	IP
- *		8100    802.1Q VLAN
  *		0001	802.3
  *		0002	AX.25
  *		0004	802.2
-- 
cgit v1.2.3


From 0c19f846d582af919db66a5914a0189f9f92c936 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Tue, 21 Nov 2017 10:22:25 -0500
Subject: net: accept UFO datagrams from tuntap and packet

Tuntap and similar devices can inject GSO packets. Accept type
VIRTIO_NET_HDR_GSO_UDP, even though not generating UFO natively.

Processes are expected to use feature negotiation such as TUNSETOFFLOAD
to detect supported offload types and refrain from injecting other
packets. This process breaks down with live migration: guest kernels
do not renegotiate flags, so destination hosts need to expose all
features that the source host does.

Partially revert the UFO removal from 182e0b6b5846~1..d9d30adf5677.
This patch introduces nearly(*) no new code to simplify verification.
It brings back verbatim tuntap UFO negotiation, VIRTIO_NET_HDR_GSO_UDP
insertion and software UFO segmentation.

It does not reinstate protocol stack support, hardware offload
(NETIF_F_UFO), SKB_GSO_UDP tunneling in SKB_GSO_SOFTWARE or reception
of VIRTIO_NET_HDR_GSO_UDP packets in tuntap.

To support SKB_GSO_UDP reappearing in the stack, also reinstate
logic in act_csum and openvswitch. Achieve equivalence with v4.13 HEAD
by squashing in commit 939912216fa8 ("net: skb_needs_check() removes
CHECKSUM_UNNECESSARY check for tx.") and reverting commit 8d63bee643f1
("net: avoid skb_warn_bad_offload false positives on UFO").

(*) To avoid having to bring back skb_shinfo(skb)->ip6_frag_id,
ipv6_proxy_select_ident is changed to return a __be32 and this is
assigned directly to the frag_hdr. Also, SKB_GSO_UDP is inserted
at the end of the enum to minimize code churn.

Tested
  Booted a v4.13 guest kernel with QEMU. On a host kernel before this
  patch `ethtool -k eth0` shows UFO disabled. After the patch, it is
  enabled, same as on a v4.13 host kernel.

  A UFO packet sent from the guest appears on the tap device:
    host:
      nc -l -p -u 8000 &
      tcpdump -n -i tap0

    guest:
      dd if=/dev/zero of=payload.txt bs=1 count=2000
      nc -u 192.16.1.1 8000 < payload.txt

  Direct tap to tap transmission of VIRTIO_NET_HDR_GSO_UDP succeeds,
  packets arriving fragmented:

    ./with_tap_pair.sh ./tap_send_ufo tap0 tap1
    (from https://github.com/wdebruij/kerneltools/tree/master/tests)

Changes
  v1 -> v2
    - simplified set_offload change (review comment)
    - documented test procedure

Link: http://lkml.kernel.org/r/<CAF=yD-LuUeDuL9YWPJD9ykOZ0QCjNeznPDr6whqZ9NGMNF12Mw@mail.gmail.com>
Fixes: fb652fdfe837 ("macvlan/macvtap: Remove NETIF_F_UFO advertisement.")
Reported-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tap.c               |  2 +-
 drivers/net/tun.c               |  2 +
 include/linux/netdev_features.h |  4 +-
 include/linux/netdevice.h       |  1 +
 include/linux/skbuff.h          |  2 +
 include/linux/virtio_net.h      |  5 ++-
 include/net/ipv6.h              |  1 +
 net/core/dev.c                  |  3 +-
 net/ipv4/af_inet.c              | 12 +++++-
 net/ipv4/udp_offload.c          | 49 ++++++++++++++++++++++--
 net/ipv6/output_core.c          | 31 +++++++++++++++
 net/ipv6/udp_offload.c          | 85 +++++++++++++++++++++++++++++++++++++++--
 net/openvswitch/datapath.c      | 14 +++++++
 net/openvswitch/flow.c          |  6 ++-
 net/sched/act_csum.c            |  6 +++
 15 files changed, 209 insertions(+), 14 deletions(-)

(limited to 'include/linux/netdevice.h')

diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index b13890953ebb..e9489b88407c 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -1077,7 +1077,7 @@ static long tap_ioctl(struct file *file, unsigned int cmd,
 	case TUNSETOFFLOAD:
 		/* let the user check for future flags */
 		if (arg & ~(TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 |
-			    TUN_F_TSO_ECN))
+			    TUN_F_TSO_ECN | TUN_F_UFO))
 			return -EINVAL;
 
 		rtnl_lock();
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 5a2ea78a008f..6a7bde9bc4b2 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2370,6 +2370,8 @@ static int set_offload(struct tun_struct *tun, unsigned long arg)
 				features |= NETIF_F_TSO6;
 			arg &= ~(TUN_F_TSO4|TUN_F_TSO6);
 		}
+
+		arg &= ~TUN_F_UFO;
 	}
 
 	/* This gives the user a way to test for new features in future by
diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index dc8b4896b77b..b1b0ca7ccb2b 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -54,8 +54,9 @@ enum {
 	NETIF_F_GSO_TUNNEL_REMCSUM_BIT, /* ... TUNNEL with TSO & REMCSUM */
 	NETIF_F_GSO_SCTP_BIT,		/* ... SCTP fragmentation */
 	NETIF_F_GSO_ESP_BIT,		/* ... ESP with TSO */
+	NETIF_F_GSO_UDP_BIT,		/* ... UFO, deprecated except tuntap */
 	/**/NETIF_F_GSO_LAST =		/* last bit, see GSO_MASK */
-		NETIF_F_GSO_ESP_BIT,
+		NETIF_F_GSO_UDP_BIT,
 
 	NETIF_F_FCOE_CRC_BIT,		/* FCoE CRC32 */
 	NETIF_F_SCTP_CRC_BIT,		/* SCTP checksum offload */
@@ -132,6 +133,7 @@ enum {
 #define NETIF_F_GSO_TUNNEL_REMCSUM __NETIF_F(GSO_TUNNEL_REMCSUM)
 #define NETIF_F_GSO_SCTP	__NETIF_F(GSO_SCTP)
 #define NETIF_F_GSO_ESP		__NETIF_F(GSO_ESP)
+#define NETIF_F_GSO_UDP		__NETIF_F(GSO_UDP)
 #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER)
 #define NETIF_F_HW_VLAN_STAG_RX	__NETIF_F(HW_VLAN_STAG_RX)
 #define NETIF_F_HW_VLAN_STAG_TX	__NETIF_F(HW_VLAN_STAG_TX)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 6b274bfe489f..ef789e1d679e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4140,6 +4140,7 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 	BUILD_BUG_ON(SKB_GSO_TUNNEL_REMCSUM != (NETIF_F_GSO_TUNNEL_REMCSUM >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_SCTP    != (NETIF_F_GSO_SCTP >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_ESP != (NETIF_F_GSO_ESP >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_GSO_UDP >> NETIF_F_GSO_SHIFT));
 
 	return (features & feature) == feature;
 }
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ed06e1c28fc7..bc486ef23f20 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -568,6 +568,8 @@ enum {
 	SKB_GSO_SCTP = 1 << 14,
 
 	SKB_GSO_ESP = 1 << 15,
+
+	SKB_GSO_UDP = 1 << 16,
 };
 
 #if BITS_PER_LONG > 32
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 210034c896e3..f144216febc6 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -9,7 +9,7 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 					const struct virtio_net_hdr *hdr,
 					bool little_endian)
 {
-	unsigned short gso_type = 0;
+	unsigned int gso_type = 0;
 
 	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
@@ -19,6 +19,9 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 		case VIRTIO_NET_HDR_GSO_TCPV6:
 			gso_type = SKB_GSO_TCPV6;
 			break;
+		case VIRTIO_NET_HDR_GSO_UDP:
+			gso_type = SKB_GSO_UDP;
+			break;
 		default:
 			return -EINVAL;
 		}
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index ec14f0d5a3a1..f73797e2fa60 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -767,6 +767,7 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add
 __be32 ipv6_select_ident(struct net *net,
 			 const struct in6_addr *daddr,
 			 const struct in6_addr *saddr);
+__be32 ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb);
 
 int ip6_dst_hoplimit(struct dst_entry *dst);
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 8ee29f4f5fa9..bbba19112f02 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2746,7 +2746,8 @@ EXPORT_SYMBOL(skb_mac_gso_segment);
 static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path)
 {
 	if (tx_path)
-		return skb->ip_summed != CHECKSUM_PARTIAL;
+		return skb->ip_summed != CHECKSUM_PARTIAL &&
+		       skb->ip_summed != CHECKSUM_UNNECESSARY;
 
 	return skb->ip_summed == CHECKSUM_NONE;
 }
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index ce4aa827be05..f00499a46927 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1223,9 +1223,10 @@ EXPORT_SYMBOL(inet_sk_rebuild_header);
 struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 				 netdev_features_t features)
 {
-	bool fixedid = false, gso_partial, encap;
+	bool udpfrag = false, fixedid = false, gso_partial, encap;
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	const struct net_offload *ops;
+	unsigned int offset = 0;
 	struct iphdr *iph;
 	int proto, tot_len;
 	int nhoff;
@@ -1260,6 +1261,7 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 	segs = ERR_PTR(-EPROTONOSUPPORT);
 
 	if (!skb->encapsulation || encap) {
+		udpfrag = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP);
 		fixedid = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID);
 
 		/* fixed ID is invalid if DF bit is not set */
@@ -1279,7 +1281,13 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 	skb = segs;
 	do {
 		iph = (struct iphdr *)(skb_mac_header(skb) + nhoff);
-		if (skb_is_gso(skb)) {
+		if (udpfrag) {
+			iph->frag_off = htons(offset >> 3);
+			if (skb->next)
+				iph->frag_off |= htons(IP_MF);
+			offset += skb->len - nhoff - ihl;
+			tot_len = skb->len - nhoff;
+		} else if (skb_is_gso(skb)) {
 			if (!fixedid) {
 				iph->id = htons(id);
 				id += skb_shinfo(skb)->gso_segs;
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index e360d55be555..01801b77bd0d 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -187,16 +187,57 @@ out_unlock:
 }
 EXPORT_SYMBOL(skb_udp_tunnel_segment);
 
-static struct sk_buff *udp4_tunnel_segment(struct sk_buff *skb,
-					   netdev_features_t features)
+static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
+					 netdev_features_t features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	unsigned int mss;
+	__wsum csum;
+	struct udphdr *uh;
+	struct iphdr *iph;
 
 	if (skb->encapsulation &&
 	    (skb_shinfo(skb)->gso_type &
-	     (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM)))
+	     (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))) {
 		segs = skb_udp_tunnel_segment(skb, features, false);
+		goto out;
+	}
+
+	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
+		goto out;
+
+	mss = skb_shinfo(skb)->gso_size;
+	if (unlikely(skb->len <= mss))
+		goto out;
+
+	/* Do software UFO. Complete and fill in the UDP checksum as
+	 * HW cannot do checksum of UDP packets sent as multiple
+	 * IP fragments.
+	 */
 
+	uh = udp_hdr(skb);
+	iph = ip_hdr(skb);
+
+	uh->check = 0;
+	csum = skb_checksum(skb, 0, skb->len, 0);
+	uh->check = udp_v4_check(skb->len, iph->saddr, iph->daddr, csum);
+	if (uh->check == 0)
+		uh->check = CSUM_MANGLED_0;
+
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+	/* If there is no outer header we can fake a checksum offload
+	 * due to the fact that we have already done the checksum in
+	 * software prior to segmenting the frame.
+	 */
+	if (!skb->encap_hdr_csum)
+		features |= NETIF_F_HW_CSUM;
+
+	/* Fragment the skb. IP headers of the fragments are updated in
+	 * inet_gso_segment()
+	 */
+	segs = skb_segment(skb, features);
+out:
 	return segs;
 }
 
@@ -330,7 +371,7 @@ static int udp4_gro_complete(struct sk_buff *skb, int nhoff)
 
 static const struct net_offload udpv4_offload = {
 	.callbacks = {
-		.gso_segment = udp4_tunnel_segment,
+		.gso_segment = udp4_ufo_fragment,
 		.gro_receive  =	udp4_gro_receive,
 		.gro_complete =	udp4_gro_complete,
 	},
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index 4a7e5ffa5108..4fe7c90962dd 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -31,6 +31,37 @@ static u32 __ipv6_select_ident(struct net *net, u32 hashrnd,
 	return id;
 }
 
+/* This function exists only for tap drivers that must support broken
+ * clients requesting UFO without specifying an IPv6 fragment ID.
+ *
+ * This is similar to ipv6_select_ident() but we use an independent hash
+ * seed to limit information leakage.
+ *
+ * The network header must be set before calling this.
+ */
+__be32 ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb)
+{
+	static u32 ip6_proxy_idents_hashrnd __read_mostly;
+	struct in6_addr buf[2];
+	struct in6_addr *addrs;
+	u32 id;
+
+	addrs = skb_header_pointer(skb,
+				   skb_network_offset(skb) +
+				   offsetof(struct ipv6hdr, saddr),
+				   sizeof(buf), buf);
+	if (!addrs)
+		return 0;
+
+	net_get_random_once(&ip6_proxy_idents_hashrnd,
+			    sizeof(ip6_proxy_idents_hashrnd));
+
+	id = __ipv6_select_ident(net, ip6_proxy_idents_hashrnd,
+				 &addrs[1], &addrs[0]);
+	return htonl(id);
+}
+EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident);
+
 __be32 ipv6_select_ident(struct net *net,
 			 const struct in6_addr *daddr,
 			 const struct in6_addr *saddr)
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 455fd4e39333..a0f89ad76f9d 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -17,15 +17,94 @@
 #include <net/ip6_checksum.h>
 #include "ip6_offload.h"
 
-static struct sk_buff *udp6_tunnel_segment(struct sk_buff *skb,
-					   netdev_features_t features)
+static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
+					 netdev_features_t features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	unsigned int mss;
+	unsigned int unfrag_ip6hlen, unfrag_len;
+	struct frag_hdr *fptr;
+	u8 *packet_start, *prevhdr;
+	u8 nexthdr;
+	u8 frag_hdr_sz = sizeof(struct frag_hdr);
+	__wsum csum;
+	int tnl_hlen;
+	int err;
+
+	mss = skb_shinfo(skb)->gso_size;
+	if (unlikely(skb->len <= mss))
+		goto out;
 
 	if (skb->encapsulation && skb_shinfo(skb)->gso_type &
 	    (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))
 		segs = skb_udp_tunnel_segment(skb, features, true);
+	else {
+		const struct ipv6hdr *ipv6h;
+		struct udphdr *uh;
+
+		if (!pskb_may_pull(skb, sizeof(struct udphdr)))
+			goto out;
+
+		/* Do software UFO. Complete and fill in the UDP checksum as HW cannot
+		 * do checksum of UDP packets sent as multiple IP fragments.
+		 */
+
+		uh = udp_hdr(skb);
+		ipv6h = ipv6_hdr(skb);
+
+		uh->check = 0;
+		csum = skb_checksum(skb, 0, skb->len, 0);
+		uh->check = udp_v6_check(skb->len, &ipv6h->saddr,
+					  &ipv6h->daddr, csum);
+		if (uh->check == 0)
+			uh->check = CSUM_MANGLED_0;
+
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+		/* If there is no outer header we can fake a checksum offload
+		 * due to the fact that we have already done the checksum in
+		 * software prior to segmenting the frame.
+		 */
+		if (!skb->encap_hdr_csum)
+			features |= NETIF_F_HW_CSUM;
+
+		/* Check if there is enough headroom to insert fragment header. */
+		tnl_hlen = skb_tnl_header_len(skb);
+		if (skb->mac_header < (tnl_hlen + frag_hdr_sz)) {
+			if (gso_pskb_expand_head(skb, tnl_hlen + frag_hdr_sz))
+				goto out;
+		}
+
+		/* Find the unfragmentable header and shift it left by frag_hdr_sz
+		 * bytes to insert fragment header.
+		 */
+		err = ip6_find_1stfragopt(skb, &prevhdr);
+		if (err < 0)
+			return ERR_PTR(err);
+		unfrag_ip6hlen = err;
+		nexthdr = *prevhdr;
+		*prevhdr = NEXTHDR_FRAGMENT;
+		unfrag_len = (skb_network_header(skb) - skb_mac_header(skb)) +
+			     unfrag_ip6hlen + tnl_hlen;
+		packet_start = (u8 *) skb->head + SKB_GSO_CB(skb)->mac_offset;
+		memmove(packet_start-frag_hdr_sz, packet_start, unfrag_len);
+
+		SKB_GSO_CB(skb)->mac_offset -= frag_hdr_sz;
+		skb->mac_header -= frag_hdr_sz;
+		skb->network_header -= frag_hdr_sz;
+
+		fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen);
+		fptr->nexthdr = nexthdr;
+		fptr->reserved = 0;
+		fptr->identification = ipv6_proxy_select_ident(dev_net(skb->dev), skb);
+
+		/* Fragment the skb. ipv6 header and the remaining fields of the
+		 * fragment header are updated in ipv6_gso_segment()
+		 */
+		segs = skb_segment(skb, features);
+	}
 
+out:
 	return segs;
 }
 
@@ -75,7 +154,7 @@ static int udp6_gro_complete(struct sk_buff *skb, int nhoff)
 
 static const struct net_offload udpv6_offload = {
 	.callbacks = {
-		.gso_segment	=	udp6_tunnel_segment,
+		.gso_segment	=	udp6_ufo_fragment,
 		.gro_receive	=	udp6_gro_receive,
 		.gro_complete	=	udp6_gro_complete,
 	},
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 0dab33fb9844..99cfafc2a139 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -308,6 +308,8 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 			     const struct dp_upcall_info *upcall_info,
 				 uint32_t cutlen)
 {
+	unsigned short gso_type = skb_shinfo(skb)->gso_type;
+	struct sw_flow_key later_key;
 	struct sk_buff *segs, *nskb;
 	int err;
 
@@ -318,9 +320,21 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 	if (segs == NULL)
 		return -EINVAL;
 
+	if (gso_type & SKB_GSO_UDP) {
+		/* The initial flow key extracted by ovs_flow_key_extract()
+		 * in this case is for a first fragment, so we need to
+		 * properly mark later fragments.
+		 */
+		later_key = *key;
+		later_key.ip.frag = OVS_FRAG_TYPE_LATER;
+	}
+
 	/* Queue all of the segments. */
 	skb = segs;
 	do {
+		if (gso_type & SKB_GSO_UDP && skb != segs)
+			key = &later_key;
+
 		err = queue_userspace_packet(dp, skb, key, upcall_info, cutlen);
 		if (err)
 			break;
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 864ddb1e3642..dbe2379329c5 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -631,7 +631,8 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 			key->ip.frag = OVS_FRAG_TYPE_LATER;
 			return 0;
 		}
-		if (nh->frag_off & htons(IP_MF))
+		if (nh->frag_off & htons(IP_MF) ||
+			skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
 			key->ip.frag = OVS_FRAG_TYPE_FIRST;
 		else
 			key->ip.frag = OVS_FRAG_TYPE_NONE;
@@ -747,6 +748,9 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 
 		if (key->ip.frag == OVS_FRAG_TYPE_LATER)
 			return 0;
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+			key->ip.frag = OVS_FRAG_TYPE_FIRST;
+
 		/* Transport layer. */
 		if (key->ip.proto == NEXTHDR_TCP) {
 			if (tcphdr_ok(skb)) {
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 1c40caadcff9..d836f998117b 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -229,6 +229,9 @@ static int tcf_csum_ipv4_udp(struct sk_buff *skb, unsigned int ihl,
 	const struct iphdr *iph;
 	u16 ul;
 
+	if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+		return 1;
+
 	/*
 	 * Support both UDP and UDPLITE checksum algorithms, Don't use
 	 * udph->len to get the real length without any protocol check,
@@ -282,6 +285,9 @@ static int tcf_csum_ipv6_udp(struct sk_buff *skb, unsigned int ihl,
 	const struct ipv6hdr *ip6h;
 	u16 ul;
 
+	if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+		return 1;
+
 	/*
 	 * Support both UDP and UDPLITE checksum algorithms, Don't use
 	 * udph->len to get the real length without any protocol check,
-- 
cgit v1.2.3