17 files changed, 1790 insertions, 458 deletions

diff --git a/net/core/datagram.c b/net/core/datagram.c
index 57f3a6fcfc1e..4bf62b1afa3b 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -728,49 +728,6 @@ fault:
 	return -EFAULT;
 }
 
-__sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)
-{
-	__sum16 sum;
-
-	sum = csum_fold(skb_checksum(skb, 0, len, skb->csum));
-	if (likely(!sum)) {
-		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
-		    !skb->csum_complete_sw)
-			netdev_rx_csum_fault(skb->dev);
-	}
-	if (!skb_shared(skb))
-		skb->csum_valid = !sum;
-	return sum;
-}
-EXPORT_SYMBOL(__skb_checksum_complete_head);
-
-__sum16 __skb_checksum_complete(struct sk_buff *skb)
-{
-	__wsum csum;
-	__sum16 sum;
-
-	csum = skb_checksum(skb, 0, skb->len, 0);
-
-	/* skb->csum holds pseudo checksum */
-	sum = csum_fold(csum_add(skb->csum, csum));
-	if (likely(!sum)) {
-		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
-		    !skb->csum_complete_sw)
-			netdev_rx_csum_fault(skb->dev);
-	}
-
-	if (!skb_shared(skb)) {
-		/* Save full packet checksum */
-		skb->csum = csum;
-		skb->ip_summed = CHECKSUM_COMPLETE;
-		skb->csum_complete_sw = 1;
-		skb->csum_valid = !sum;
-	}
-
-	return sum;
-}
-EXPORT_SYMBOL(__skb_checksum_complete);
-
 /**
  *	skb_copy_and_csum_datagram_msg - Copy and checksum skb to user iovec.
  *	@skb: skbuff
@@ -810,7 +767,7 @@ int skb_copy_and_csum_datagram_msg(struct sk_buff *skb,
 
 		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
 		    !skb->csum_complete_sw)
-			netdev_rx_csum_fault(NULL);
+			netdev_rx_csum_fault(NULL, skb);
 	}
 	return 0;
 fault:
diff --git a/net/core/dev.c b/net/core/dev.c
index 722d50dbf8a4..1b5a4410be0e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -145,6 +145,7 @@
 #include <linux/sctp.h>
 #include <net/udp_tunnel.h>
 #include <linux/net_namespace.h>
+#include <linux/indirect_call_wrapper.h>
 
 #include "net-sysfs.h"
 
@@ -162,6 +163,9 @@ 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 netdev_notifier_info *info);
+static int call_netdevice_notifiers_extack(unsigned long val,
+					   struct net_device *dev,
+					   struct netlink_ext_ack *extack);
 static struct napi_struct *napi_by_id(unsigned int napi_id);
 
 /*
@@ -1361,7 +1365,7 @@ void netdev_notify_peers(struct net_device *dev)
 }
 EXPORT_SYMBOL(netdev_notify_peers);
 
-static int __dev_open(struct net_device *dev)
+static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 	int ret;
@@ -1377,7 +1381,7 @@ static int __dev_open(struct net_device *dev)
 	 */
 	netpoll_poll_disable(dev);
 
-	ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev);
+	ret = call_netdevice_notifiers_extack(NETDEV_PRE_UP, dev, extack);
 	ret = notifier_to_errno(ret);
 	if (ret)
 		return ret;
@@ -1406,7 +1410,8 @@ static int __dev_open(struct net_device *dev)
 
 /**
  *	dev_open	- prepare an interface for use.
- *	@dev:	device to open
+ *	@dev: device to open
+ *	@extack: netlink extended ack
  *
  *	Takes a device from down to up state. The device's private open
  *	function is invoked and then the multicast lists are loaded. Finally
@@ -1416,14 +1421,14 @@ static int __dev_open(struct net_device *dev)
  *	Calling this function on an active interface is a nop. On a failure
  *	a negative errno code is returned.
  */
-int dev_open(struct net_device *dev)
+int dev_open(struct net_device *dev, struct netlink_ext_ack *extack)
 {
 	int ret;
 
 	if (dev->flags & IFF_UP)
 		return 0;
 
-	ret = __dev_open(dev);
+	ret = __dev_open(dev, extack);
 	if (ret < 0)
 		return ret;
 
@@ -1585,6 +1590,7 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd)
 	N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN)
 	N(CVLAN_FILTER_PUSH_INFO) N(CVLAN_FILTER_DROP_INFO)
 	N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO)
+	N(PRE_CHANGEADDR)
 	}
 #undef N
 	return "UNKNOWN_NETDEV_EVENT";
@@ -1733,6 +1739,18 @@ static int call_netdevice_notifiers_info(unsigned long val,
 	return raw_notifier_call_chain(&netdev_chain, val, info);
 }
 
+static int call_netdevice_notifiers_extack(unsigned long val,
+					   struct net_device *dev,
+					   struct netlink_ext_ack *extack)
+{
+	struct netdev_notifier_info info = {
+		.dev = dev,
+		.extack = extack,
+	};
+
+	return call_netdevice_notifiers_info(val, &info);
+}
+
 /**
  *	call_netdevice_notifiers - call all network notifier blocks
  *      @val: value passed unmodified to notifier function
@@ -1744,11 +1762,7 @@ 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 = {
-		.dev = dev,
-	};
-
-	return call_netdevice_notifiers_info(val, &info);
+	return call_netdevice_notifiers_extack(val, dev, NULL);
 }
 EXPORT_SYMBOL(call_netdevice_notifiers);
 
@@ -3096,10 +3110,17 @@ EXPORT_SYMBOL(__skb_gso_segment);
 
 /* Take action when hardware reception checksum errors are detected. */
 #ifdef CONFIG_BUG
-void netdev_rx_csum_fault(struct net_device *dev)
+void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb)
 {
 	if (net_ratelimit()) {
 		pr_err("%s: hw csum failure\n", dev ? dev->name : "<unknown>");
+		if (dev)
+			pr_err("dev features: %pNF\n", &dev->features);
+		pr_err("skb len=%u data_len=%u pkt_type=%u gso_size=%u gso_type=%u nr_frags=%u ip_summed=%u csum=%x csum_complete_sw=%d csum_valid=%d csum_level=%u\n",
+		       skb->len, skb->data_len, skb->pkt_type,
+		       skb_shinfo(skb)->gso_size, skb_shinfo(skb)->gso_type,
+		       skb_shinfo(skb)->nr_frags, skb->ip_summed, skb->csum,
+		       skb->csum_complete_sw, skb->csum_valid, skb->csum_level);
 		dump_stack();
 	}
 }
@@ -4525,9 +4546,14 @@ static int netif_rx_internal(struct sk_buff *skb)
 
 int netif_rx(struct sk_buff *skb)
 {
+	int ret;
+
 	trace_netif_rx_entry(skb);
 
-	return netif_rx_internal(skb);
+	ret = netif_rx_internal(skb);
+	trace_netif_rx_exit(ret);
+
+	return ret;
 }
 EXPORT_SYMBOL(netif_rx);
 
@@ -4542,6 +4568,7 @@ int netif_rx_ni(struct sk_buff *skb)
 	if (local_softirq_pending())
 		do_softirq();
 	preempt_enable();
+	trace_netif_rx_ni_exit(err);
 
 	return err;
 }
@@ -4894,7 +4921,7 @@ skip_classify:
 		 * and set skb->priority like in vlan_do_receive()
 		 * For the time being, just ignore Priority Code Point
 		 */
-		skb->vlan_tci = 0;
+		__vlan_hwaccel_clear_tag(skb);
 	}
 
 	type = skb->protocol;
@@ -5227,9 +5254,14 @@ static void netif_receive_skb_list_internal(struct list_head *head)
  */
 int netif_receive_skb(struct sk_buff *skb)
 {
+	int ret;
+
 	trace_netif_receive_skb_entry(skb);
 
-	return netif_receive_skb_internal(skb);
+	ret = netif_receive_skb_internal(skb);
+	trace_netif_receive_skb_exit(ret);
+
+	return ret;
 }
 EXPORT_SYMBOL(netif_receive_skb);
 
@@ -5249,9 +5281,12 @@ void netif_receive_skb_list(struct list_head *head)
 
 	if (list_empty(head))
 		return;
-	list_for_each_entry(skb, head, list)
-		trace_netif_receive_skb_list_entry(skb);
+	if (trace_netif_receive_skb_list_entry_enabled()) {
+		list_for_each_entry(skb, head, list)
+			trace_netif_receive_skb_list_entry(skb);
+	}
 	netif_receive_skb_list_internal(head);
+	trace_netif_receive_skb_list_exit(0);
 }
 EXPORT_SYMBOL(netif_receive_skb_list);
 
@@ -5304,6 +5339,8 @@ static void flush_all_backlogs(void)
 	put_online_cpus();
 }
 
+INDIRECT_CALLABLE_DECLARE(int inet_gro_complete(struct sk_buff *, int));
+INDIRECT_CALLABLE_DECLARE(int ipv6_gro_complete(struct sk_buff *, int));
 static int napi_gro_complete(struct sk_buff *skb)
 {
 	struct packet_offload *ptype;
@@ -5323,7 +5360,9 @@ static int napi_gro_complete(struct sk_buff *skb)
 		if (ptype->type != type || !ptype->callbacks.gro_complete)
 			continue;
 
-		err = ptype->callbacks.gro_complete(skb, 0);
+		err = INDIRECT_CALL_INET(ptype->callbacks.gro_complete,
+					 ipv6_gro_complete, inet_gro_complete,
+					 skb, 0);
 		break;
 	}
 	rcu_read_unlock();
@@ -5362,11 +5401,13 @@ static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index,
  */
 void napi_gro_flush(struct napi_struct *napi, bool flush_old)
 {
-	u32 i;
+	unsigned long bitmask = napi->gro_bitmask;
+	unsigned int i, base = ~0U;
 
-	for (i = 0; i < GRO_HASH_BUCKETS; i++) {
-		if (test_bit(i, &napi->gro_bitmask))
-			__napi_gro_flush_chain(napi, i, flush_old);
+	while ((i = ffs(bitmask)) != 0) {
+		bitmask >>= i;
+		base += i;
+		__napi_gro_flush_chain(napi, base, flush_old);
 	}
 }
 EXPORT_SYMBOL(napi_gro_flush);
@@ -5391,7 +5432,9 @@ static struct list_head *gro_list_prepare(struct napi_struct *napi,
 		}
 
 		diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev;
-		diffs |= p->vlan_tci ^ skb->vlan_tci;
+		diffs |= skb_vlan_tag_present(p) ^ skb_vlan_tag_present(skb);
+		if (skb_vlan_tag_present(p))
+			diffs |= p->vlan_tci ^ skb->vlan_tci;
 		diffs |= skb_metadata_dst_cmp(p, skb);
 		diffs |= skb_metadata_differs(p, skb);
 		if (maclen == ETH_HLEN)
@@ -5466,6 +5509,10 @@ static void gro_flush_oldest(struct list_head *head)
 	napi_gro_complete(oldest);
 }
 
+INDIRECT_CALLABLE_DECLARE(struct sk_buff *inet_gro_receive(struct list_head *,
+							   struct sk_buff *));
+INDIRECT_CALLABLE_DECLARE(struct sk_buff *ipv6_gro_receive(struct list_head *,
+							   struct sk_buff *));
 static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
 	u32 hash = skb_get_hash_raw(skb) & (GRO_HASH_BUCKETS - 1);
@@ -5515,7 +5562,9 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 			NAPI_GRO_CB(skb)->csum_valid = 0;
 		}
 
-		pp = ptype->callbacks.gro_receive(gro_head, skb);
+		pp = INDIRECT_CALL_INET(ptype->callbacks.gro_receive,
+					ipv6_gro_receive, inet_gro_receive,
+					gro_head, skb);
 		break;
 	}
 	rcu_read_unlock();
@@ -5639,12 +5688,17 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
 
 gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
+	gro_result_t ret;
+
 	skb_mark_napi_id(skb, napi);
 	trace_napi_gro_receive_entry(skb);
 
 	skb_gro_reset_offset(skb);
 
-	return napi_skb_finish(dev_gro_receive(napi, skb), skb);
+	ret = napi_skb_finish(dev_gro_receive(napi, skb), skb);
+	trace_napi_gro_receive_exit(ret);
+
+	return ret;
 }
 EXPORT_SYMBOL(napi_gro_receive);
 
@@ -5657,7 +5711,7 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
 	__skb_pull(skb, skb_headlen(skb));
 	/* restore the reserve we had after netdev_alloc_skb_ip_align() */
 	skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN - skb_headroom(skb));
-	skb->vlan_tci = 0;
+	__vlan_hwaccel_clear_tag(skb);
 	skb->dev = napi->dev;
 	skb->skb_iif = 0;
 
@@ -5762,6 +5816,7 @@ static struct sk_buff *napi_frags_skb(struct napi_struct *napi)
 
 gro_result_t napi_gro_frags(struct napi_struct *napi)
 {
+	gro_result_t ret;
 	struct sk_buff *skb = napi_frags_skb(napi);
 
 	if (!skb)
@@ -5769,7 +5824,10 @@ gro_result_t napi_gro_frags(struct napi_struct *napi)
 
 	trace_napi_gro_frags_entry(skb);
 
-	return napi_frags_finish(napi, skb, dev_gro_receive(napi, skb));
+	ret = napi_frags_finish(napi, skb, dev_gro_receive(napi, skb));
+	trace_napi_gro_frags_exit(ret);
+
+	return ret;
 }
 EXPORT_SYMBOL(napi_gro_frags);
 
@@ -5785,10 +5843,11 @@ __sum16 __skb_gro_checksum_complete(struct sk_buff *skb)
 
 	/* NAPI_GRO_CB(skb)->csum holds pseudo checksum */
 	sum = csum_fold(csum_add(NAPI_GRO_CB(skb)->csum, wsum));
+	/* See comments in __skb_checksum_complete(). */
 	if (likely(!sum)) {
 		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
 		    !skb->csum_complete_sw)
-			netdev_rx_csum_fault(skb->dev);
+			netdev_rx_csum_fault(skb->dev, skb);
 	}
 
 	NAPI_GRO_CB(skb)->csum = wsum;
@@ -7467,7 +7526,8 @@ unsigned int dev_get_flags(const struct net_device *dev)
 }
 EXPORT_SYMBOL(dev_get_flags);
 
-int __dev_change_flags(struct net_device *dev, unsigned int flags)
+int __dev_change_flags(struct net_device *dev, unsigned int flags,
+		       struct netlink_ext_ack *extack)
 {
 	unsigned int old_flags = dev->flags;
 	int ret;
@@ -7504,7 +7564,7 @@ int __dev_change_flags(struct net_device *dev, unsigned int flags)
 		if (old_flags & IFF_UP)
 			__dev_close(dev);
 		else
-			ret = __dev_open(dev);
+			ret = __dev_open(dev, extack);
 	}
 
 	if ((flags ^ dev->gflags) & IFF_PROMISC) {
@@ -7564,16 +7624,18 @@ void __dev_notify_flags(struct net_device *dev, unsigned int old_flags,
  *	dev_change_flags - change device settings
  *	@dev: device
  *	@flags: device state flags
+ *	@extack: netlink extended ack
  *
  *	Change settings on device based state flags. The flags are
  *	in the userspace exported format.
  */
-int dev_change_flags(struct net_device *dev, unsigned int flags)
+int dev_change_flags(struct net_device *dev, unsigned int flags,
+		     struct netlink_ext_ack *extack)
 {
 	int ret;
 	unsigned int changes, old_flags = dev->flags, old_gflags = dev->gflags;
 
-	ret = __dev_change_flags(dev, flags);
+	ret = __dev_change_flags(dev, flags, extack);
 	if (ret < 0)
 		return ret;
 
@@ -7706,13 +7768,36 @@ void dev_set_group(struct net_device *dev, int new_group)
 EXPORT_SYMBOL(dev_set_group);
 
 /**
+ *	dev_pre_changeaddr_notify - Call NETDEV_PRE_CHANGEADDR.
+ *	@dev: device
+ *	@addr: new address
+ *	@extack: netlink extended ack
+ */
+int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr,
+			      struct netlink_ext_ack *extack)
+{
+	struct netdev_notifier_pre_changeaddr_info info = {
+		.info.dev = dev,
+		.info.extack = extack,
+		.dev_addr = addr,
+	};
+	int rc;
+
+	rc = call_netdevice_notifiers_info(NETDEV_PRE_CHANGEADDR, &info.info);
+	return notifier_to_errno(rc);
+}
+EXPORT_SYMBOL(dev_pre_changeaddr_notify);
+
+/**
  *	dev_set_mac_address - Change Media Access Control Address
  *	@dev: device
  *	@sa: new address
+ *	@extack: netlink extended ack
  *
  *	Change the hardware (MAC) address of the device
  */
-int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa)
+int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa,
+			struct netlink_ext_ack *extack)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 	int err;
@@ -7723,6 +7808,9 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa)
 		return -EINVAL;
 	if (!netif_device_present(dev))
 		return -ENODEV;
+	err = dev_pre_changeaddr_notify(dev, sa->sa_data, extack);
+	if (err)
+		return err;
 	err = ops->ndo_set_mac_address(dev, sa);
 	if (err)
 		return err;
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index d884d8f5f0e5..a6723b306717 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -278,6 +278,103 @@ int __hw_addr_sync_dev(struct netdev_hw_addr_list *list,
 EXPORT_SYMBOL(__hw_addr_sync_dev);
 
 /**
+ *  __hw_addr_ref_sync_dev - Synchronize device's multicast address list taking
+ *  into account references
+ *  @list: address list to synchronize
+ *  @dev:  device to sync
+ *  @sync: function to call if address or reference on it should be added
+ *  @unsync: function to call if address or some reference on it should removed
+ *
+ *  This function is intended to be called from the ndo_set_rx_mode
+ *  function of devices that require explicit address or references on it
+ *  add/remove notifications. The unsync function may be NULL in which case
+ *  the addresses or references on it requiring removal will simply be
+ *  removed without any notification to the device. That is responsibility of
+ *  the driver to identify and distribute address or references on it between
+ *  internal address tables.
+ **/
+int __hw_addr_ref_sync_dev(struct netdev_hw_addr_list *list,
+			   struct net_device *dev,
+			   int (*sync)(struct net_device *,
+				       const unsigned char *, int),
+			   int (*unsync)(struct net_device *,
+					 const unsigned char *, int))
+{
+	struct netdev_hw_addr *ha, *tmp;
+	int err, ref_cnt;
+
+	/* first go through and flush out any unsynced/stale entries */
+	list_for_each_entry_safe(ha, tmp, &list->list, list) {
+		/* sync if address is not used */
+		if ((ha->sync_cnt << 1) <= ha->refcount)
+			continue;
+
+		/* if fails defer unsyncing address */
+		ref_cnt = ha->refcount - ha->sync_cnt;
+		if (unsync && unsync(dev, ha->addr, ref_cnt))
+			continue;
+
+		ha->refcount = (ref_cnt << 1) + 1;
+		ha->sync_cnt = ref_cnt;
+		__hw_addr_del_entry(list, ha, false, false);
+	}
+
+	/* go through and sync updated/new entries to the list */
+	list_for_each_entry_safe(ha, tmp, &list->list, list) {
+		/* sync if address added or reused */
+		if ((ha->sync_cnt << 1) >= ha->refcount)
+			continue;
+
+		ref_cnt = ha->refcount - ha->sync_cnt;
+		err = sync(dev, ha->addr, ref_cnt);
+		if (err)
+			return err;
+
+		ha->refcount = ref_cnt << 1;
+		ha->sync_cnt = ref_cnt;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(__hw_addr_ref_sync_dev);
+
+/**
+ *  __hw_addr_ref_unsync_dev - Remove synchronized addresses and references on
+ *  it from device
+ *  @list: address list to remove synchronized addresses (references on it) from
+ *  @dev:  device to sync
+ *  @unsync: function to call if address and references on it should be removed
+ *
+ *  Remove all addresses that were added to the device by
+ *  __hw_addr_ref_sync_dev(). This function is intended to be called from the
+ *  ndo_stop or ndo_open functions on devices that require explicit address (or
+ *  references on it) add/remove notifications. If the unsync function pointer
+ *  is NULL then this function can be used to just reset the sync_cnt for the
+ *  addresses in the list.
+ **/
+void __hw_addr_ref_unsync_dev(struct netdev_hw_addr_list *list,
+			      struct net_device *dev,
+			      int (*unsync)(struct net_device *,
+					    const unsigned char *, int))
+{
+	struct netdev_hw_addr *ha, *tmp;
+
+	list_for_each_entry_safe(ha, tmp, &list->list, list) {
+		if (!ha->sync_cnt)
+			continue;
+
+		/* if fails defer unsyncing address */
+		if (unsync && unsync(dev, ha->addr, ha->sync_cnt))
+			continue;
+
+		ha->refcount -= ha->sync_cnt - 1;
+		ha->sync_cnt = 0;
+		__hw_addr_del_entry(list, ha, false, false);
+	}
+}
+EXPORT_SYMBOL(__hw_addr_ref_unsync_dev);
+
+/**
  *  __hw_addr_unsync_dev - Remove synchronized addresses from device
  *  @list: address list to remove synchronized addresses from
  *  @dev:  device to sync
@@ -401,6 +498,9 @@ int dev_addr_add(struct net_device *dev, const unsigned char *addr,
 
 	ASSERT_RTNL();
 
+	err = dev_pre_changeaddr_notify(dev, addr, NULL);
+	if (err)
+		return err;
 	err = __hw_addr_add(&dev->dev_addrs, addr, dev->addr_len, addr_type);
 	if (!err)
 		call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 90e8aa36881e..31380fd5a4e2 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -234,7 +234,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
 
 	switch (cmd) {
 	case SIOCSIFFLAGS:	/* Set interface flags */
-		return dev_change_flags(dev, ifr->ifr_flags);
+		return dev_change_flags(dev, ifr->ifr_flags, NULL);
 
 	case SIOCSIFMETRIC:	/* Set the metric on the interface
 				   (currently unused) */
@@ -246,7 +246,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
 	case SIOCSIFHWADDR:
 		if (dev->addr_len > sizeof(struct sockaddr))
 			return -EINVAL;
-		return dev_set_mac_address(dev, &ifr->ifr_hwaddr);
+		return dev_set_mac_address(dev, &ifr->ifr_hwaddr, NULL);
 
 	case SIOCSIFHWBROADCAST:
 		if (ifr->ifr_hwaddr.sa_family != dev->type)
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 3a4b29a13d31..abb0da9d7b4b 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -2692,6 +2692,11 @@ static const struct devlink_param devlink_param_generic[] = {
 		.name = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_NAME,
 		.type = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_TYPE,
 	},
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_FW_LOAD_POLICY,
+		.name = DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_NAME,
+		.type = DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_TYPE,
+	},
 };
 
 static int devlink_param_generic_verify(const struct devlink_param *param)
diff --git a/net/core/filter.c b/net/core/filter.c
index 8d2c629501e2..447dd1bad31f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -296,22 +296,18 @@ static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg,
 		break;
 
 	case SKF_AD_VLAN_TAG:
-	case SKF_AD_VLAN_TAG_PRESENT:
 		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
-		BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);
 
 		/* dst_reg = *(u16 *) (src_reg + offsetof(vlan_tci)) */
 		*insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg,
 				      offsetof(struct sk_buff, vlan_tci));
-		if (skb_field == SKF_AD_VLAN_TAG) {
-			*insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg,
-						~VLAN_TAG_PRESENT);
-		} else {
-			/* dst_reg >>= 12 */
-			*insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, 12);
-			/* dst_reg &= 1 */
+		break;
+	case SKF_AD_VLAN_TAG_PRESENT:
+		*insn++ = BPF_LDX_MEM(BPF_B, dst_reg, src_reg, PKT_VLAN_PRESENT_OFFSET());
+		if (PKT_VLAN_PRESENT_BIT)
+			*insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, PKT_VLAN_PRESENT_BIT);
+		if (PKT_VLAN_PRESENT_BIT < 7)
 			*insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, 1);
-		}
 		break;
 	}
 
@@ -467,7 +463,8 @@ static bool convert_bpf_ld_abs(struct sock_filter *fp, struct bpf_insn **insnp)
 		bool ldx_off_ok = offset <= S16_MAX;
 
 		*insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_H);
-		*insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset);
+		if (offset)
+			*insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset);
 		*insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP,
 				      size, 2 + endian + (!ldx_off_ok * 2));
 		if (ldx_off_ok) {
@@ -2428,6 +2425,174 @@ static const struct bpf_func_proto bpf_msg_push_data_proto = {
 	.arg4_type	= ARG_ANYTHING,
 };
 
+static void sk_msg_shift_left(struct sk_msg *msg, int i)
+{
+	int prev;
+
+	do {
+		prev = i;
+		sk_msg_iter_var_next(i);
+		msg->sg.data[prev] = msg->sg.data[i];
+	} while (i != msg->sg.end);
+
+	sk_msg_iter_prev(msg, end);
+}
+
+static void sk_msg_shift_right(struct sk_msg *msg, int i)
+{
+	struct scatterlist tmp, sge;
+
+	sk_msg_iter_next(msg, end);
+	sge = sk_msg_elem_cpy(msg, i);
+	sk_msg_iter_var_next(i);
+	tmp = sk_msg_elem_cpy(msg, i);
+
+	while (i != msg->sg.end) {
+		msg->sg.data[i] = sge;
+		sk_msg_iter_var_next(i);
+		sge = tmp;
+		tmp = sk_msg_elem_cpy(msg, i);
+	}
+}
+
+BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start,
+	   u32, len, u64, flags)
+{
+	u32 i = 0, l, space, offset = 0;
+	u64 last = start + len;
+	int pop;
+
+	if (unlikely(flags))
+		return -EINVAL;
+
+	/* First find the starting scatterlist element */
+	i = msg->sg.start;
+	do {
+		l = sk_msg_elem(msg, i)->length;
+
+		if (start < offset + l)
+			break;
+		offset += l;
+		sk_msg_iter_var_next(i);
+	} while (i != msg->sg.end);
+
+	/* Bounds checks: start and pop must be inside message */
+	if (start >= offset + l || last >= msg->sg.size)
+		return -EINVAL;
+
+	space = MAX_MSG_FRAGS - sk_msg_elem_used(msg);
+
+	pop = len;
+	/* --------------| offset
+	 * -| start      |-------- len -------|
+	 *
+	 *  |----- a ----|-------- pop -------|----- b ----|
+	 *  |______________________________________________| length
+	 *
+	 *
+	 * a:   region at front of scatter element to save
+	 * b:   region at back of scatter element to save when length > A + pop
+	 * pop: region to pop from element, same as input 'pop' here will be
+	 *      decremented below per iteration.
+	 *
+	 * Two top-level cases to handle when start != offset, first B is non
+	 * zero and second B is zero corresponding to when a pop includes more
+	 * than one element.
+	 *
+	 * Then if B is non-zero AND there is no space allocate space and
+	 * compact A, B regions into page. If there is space shift ring to
+	 * the rigth free'ing the next element in ring to place B, leaving
+	 * A untouched except to reduce length.
+	 */
+	if (start != offset) {
+		struct scatterlist *nsge, *sge = sk_msg_elem(msg, i);
+		int a = start;
+		int b = sge->length - pop - a;
+
+		sk_msg_iter_var_next(i);
+
+		if (pop < sge->length - a) {
+			if (space) {
+				sge->length = a;
+				sk_msg_shift_right(msg, i);
+				nsge = sk_msg_elem(msg, i);
+				get_page(sg_page(sge));
+				sg_set_page(nsge,
+					    sg_page(sge),
+					    b, sge->offset + pop + a);
+			} else {
+				struct page *page, *orig;
+				u8 *to, *from;
+
+				page = alloc_pages(__GFP_NOWARN |
+						   __GFP_COMP   | GFP_ATOMIC,
+						   get_order(a + b));
+				if (unlikely(!page))
+					return -ENOMEM;
+
+				sge->length = a;
+				orig = sg_page(sge);
+				from = sg_virt(sge);
+				to = page_address(page);
+				memcpy(to, from, a);
+				memcpy(to + a, from + a + pop, b);
+				sg_set_page(sge, page, a + b, 0);
+				put_page(orig);
+			}
+			pop = 0;
+		} else if (pop >= sge->length - a) {
+			sge->length = a;
+			pop -= (sge->length - a);
+		}
+	}
+
+	/* From above the current layout _must_ be as follows,
+	 *
+	 * -| offset
+	 * -| start
+	 *
+	 *  |---- pop ---|---------------- b ------------|
+	 *  |____________________________________________| length
+	 *
+	 * Offset and start of the current msg elem are equal because in the
+	 * previous case we handled offset != start and either consumed the
+	 * entire element and advanced to the next element OR pop == 0.
+	 *
+	 * Two cases to handle here are first pop is less than the length
+	 * leaving some remainder b above. Simply adjust the element's layout
+	 * in this case. Or pop >= length of the element so that b = 0. In this
+	 * case advance to next element decrementing pop.
+	 */
+	while (pop) {
+		struct scatterlist *sge = sk_msg_elem(msg, i);
+
+		if (pop < sge->length) {
+			sge->length -= pop;
+			sge->offset += pop;
+			pop = 0;
+		} else {
+			pop -= sge->length;
+			sk_msg_shift_left(msg, i);
+		}
+		sk_msg_iter_var_next(i);
+	}
+
+	sk_mem_uncharge(msg->sk, len - pop);
+	msg->sg.size -= (len - pop);
+	sk_msg_compute_data_pointers(msg);
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_msg_pop_data_proto = {
+	.func		= bpf_msg_pop_data,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb)
 {
 	return task_get_classid(skb);
@@ -3908,6 +4073,26 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = {
 	.arg1_type      = ARG_PTR_TO_CTX,
 };
 
+BPF_CALL_5(bpf_sockopt_event_output, struct bpf_sock_ops_kern *, bpf_sock,
+	   struct bpf_map *, map, u64, flags, void *, data, u64, size)
+{
+	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
+		return -EINVAL;
+
+	return bpf_event_output(map, flags, data, size, NULL, 0, NULL);
+}
+
+static const struct bpf_func_proto bpf_sockopt_event_output_proto =  {
+	.func		= bpf_sockopt_event_output,
+	.gpl_only       = true,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_CONST_MAP_PTR,
+	.arg3_type      = ARG_ANYTHING,
+	.arg4_type      = ARG_PTR_TO_MEM,
+	.arg5_type      = ARG_CONST_SIZE_OR_ZERO,
+};
+
 BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 	   int, level, int, optname, char *, optval, int, optlen)
 {
@@ -4825,37 +5010,31 @@ static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = {
 
 #ifdef CONFIG_INET
 static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
-			      struct sk_buff *skb, u8 family, u8 proto)
+			      int dif, int sdif, u8 family, u8 proto)
 {
 	bool refcounted = false;
 	struct sock *sk = NULL;
-	int dif = 0;
-
-	if (skb->dev)
-		dif = skb->dev->ifindex;
 
 	if (family == AF_INET) {
 		__be32 src4 = tuple->ipv4.saddr;
 		__be32 dst4 = tuple->ipv4.daddr;
-		int sdif = inet_sdif(skb);
 
 		if (proto == IPPROTO_TCP)
-			sk = __inet_lookup(net, &tcp_hashinfo, skb, 0,
+			sk = __inet_lookup(net, &tcp_hashinfo, NULL, 0,
 					   src4, tuple->ipv4.sport,
 					   dst4, tuple->ipv4.dport,
 					   dif, sdif, &refcounted);
 		else
 			sk = __udp4_lib_lookup(net, src4, tuple->ipv4.sport,
 					       dst4, tuple->ipv4.dport,
-					       dif, sdif, &udp_table, skb);
+					       dif, sdif, &udp_table, NULL);
 #if IS_ENABLED(CONFIG_IPV6)
 	} else {
 		struct in6_addr *src6 = (struct in6_addr *)&tuple->ipv6.saddr;
 		struct in6_addr *dst6 = (struct in6_addr *)&tuple->ipv6.daddr;
-		int sdif = inet6_sdif(skb);
 
 		if (proto == IPPROTO_TCP)
-			sk = __inet6_lookup(net, &tcp_hashinfo, skb, 0,
+			sk = __inet6_lookup(net, &tcp_hashinfo, NULL, 0,
 					    src6, tuple->ipv6.sport,
 					    dst6, ntohs(tuple->ipv6.dport),
 					    dif, sdif, &refcounted);
@@ -4864,7 +5043,7 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
 							    src6, tuple->ipv6.sport,
 							    dst6, tuple->ipv6.dport,
 							    dif, sdif,
-							    &udp_table, skb);
+							    &udp_table, NULL);
 #endif
 	}
 
@@ -4881,31 +5060,33 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
  * callers to satisfy BPF_CALL declarations.
  */
 static unsigned long
-bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
-	      u8 proto, u64 netns_id, u64 flags)
+__bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
+		struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id,
+		u64 flags)
 {
-	struct net *caller_net;
 	struct sock *sk = NULL;
 	u8 family = AF_UNSPEC;
 	struct net *net;
+	int sdif;
 
 	family = len == sizeof(tuple->ipv4) ? AF_INET : AF_INET6;
 	if (unlikely(family == AF_UNSPEC || flags ||
 		     !((s32)netns_id < 0 || netns_id <= S32_MAX)))
 		goto out;
 
-	if (skb->dev)
-		caller_net = dev_net(skb->dev);
+	if (family == AF_INET)
+		sdif = inet_sdif(skb);
 	else
-		caller_net = sock_net(skb->sk);
+		sdif = inet6_sdif(skb);
+
 	if ((s32)netns_id < 0) {
 		net = caller_net;
-		sk = sk_lookup(net, tuple, skb, family, proto);
+		sk = sk_lookup(net, tuple, ifindex, sdif, family, proto);
 	} else {
 		net = get_net_ns_by_id(caller_net, netns_id);
 		if (unlikely(!net))
 			goto out;
-		sk = sk_lookup(net, tuple, skb, family, proto);
+		sk = sk_lookup(net, tuple, ifindex, sdif, family, proto);
 		put_net(net);
 	}
 
@@ -4915,6 +5096,25 @@ out:
 	return (unsigned long) sk;
 }
 
+static unsigned long
+bpf_sk_lookup(struct sk_buff *skb, struct bpf