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

Pull networking updates from David Miller:

 1) Allow setting bluetooth L2CAP modes via socket option, from Luiz
    Augusto von Dentz.

 2) Add GSO partial support to igc, from Sasha Neftin.

 3) Several cleanups and improvements to r8169 from Heiner Kallweit.

 4) Add IF_OPER_TESTING link state and use it when ethtool triggers a
    device self-test. From Andrew Lunn.

 5) Start moving away from custom driver versions, use the globally
    defined kernel version instead, from Leon Romanovsky.

 6) Support GRO vis gro_cells in DSA layer, from Alexander Lobakin.

 7) Allow hard IRQ deferral during NAPI, from Eric Dumazet.

 8) Add sriov and vf support to hinic, from Luo bin.

 9) Support Media Redundancy Protocol (MRP) in the bridging code, from
    Horatiu Vultur.

10) Support netmap in the nft_nat code, from Pablo Neira Ayuso.

11) Allow UDPv6 encapsulation of ESP in the ipsec code, from Sabrina
    Dubroca. Also add ipv6 support for espintcp.

12) Lots of ReST conversions of the networking documentation, from Mauro
    Carvalho Chehab.

13) Support configuration of ethtool rxnfc flows in bcmgenet driver,
    from Doug Berger.

14) Allow to dump cgroup id and filter by it in inet_diag code, from
    Dmitry Yakunin.

15) Add infrastructure to export netlink attribute policies to
    userspace, from Johannes Berg.

16) Several optimizations to sch_fq scheduler, from Eric Dumazet.

17) Fallback to the default qdisc if qdisc init fails because otherwise
    a packet scheduler init failure will make a device inoperative. From
    Jesper Dangaard Brouer.

18) Several RISCV bpf jit optimizations, from Luke Nelson.

19) Correct the return type of the ->ndo_start_xmit() method in several
    drivers, it's netdev_tx_t but many drivers were using
    'int'. From Yunjian Wang.

20) Add an ethtool interface for PHY master/slave config, from Oleksij
    Rempel.

21) Add BPF iterators, from Yonghang Song.

22) Add cable test infrastructure, including ethool interfaces, from
    Andrew Lunn. Marvell PHY driver is the first to support this
    facility.

23) Remove zero-length arrays all over, from Gustavo A. R. Silva.

24) Calculate and maintain an explicit frame size in XDP, from Jesper
    Dangaard Brouer.

25) Add CAP_BPF, from Alexei Starovoitov.

26) Support terse dumps in the packet scheduler, from Vlad Buslov.

27) Support XDP_TX bulking in dpaa2 driver, from Ioana Ciornei.

28) Add devm_register_netdev(), from Bartosz Golaszewski.

29) Minimize qdisc resets, from Cong Wang.

30) Get rid of kernel_getsockopt and kernel_setsockopt in order to
    eliminate set_fs/get_fs calls. From Christoph Hellwig.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2517 commits)
  selftests: net: ip_defrag: ignore EPERM
  net_failover: fixed rollback in net_failover_open()
  Revert "tipc: Fix potential tipc_aead refcnt leak in tipc_crypto_rcv"
  Revert "tipc: Fix potential tipc_node refcnt leak in tipc_rcv"
  vmxnet3: allow rx flow hash ops only when rss is enabled
  hinic: add set_channels ethtool_ops support
  selftests/bpf: Add a default $(CXX) value
  tools/bpf: Don't use $(COMPILE.c)
  bpf, selftests: Use bpf_probe_read_kernel
  s390/bpf: Use bcr 0,%0 as tail call nop filler
  s390/bpf: Maintain 8-byte stack alignment
  selftests/bpf: Fix verifier test
  selftests/bpf: Fix sample_cnt shared between two threads
  bpf, selftests: Adapt cls_redirect to call csum_level helper
  bpf: Add csum_level helper for fixing up csum levels
  bpf: Fix up bpf_skb_adjust_room helper's skb csum setting
  sfc: add missing annotation for efx_ef10_try_update_nic_stats_vf()
  crypto/chtls: IPv6 support for inline TLS
  Crypto/chcr: Fixes a coccinile check error
  Crypto/chcr: Fixes compilations warnings
  ...

21 files changed, 1275 insertions, 785 deletions

diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index 756b63b6f7b3..d2c4d16dadba 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -625,7 +625,7 @@ static int bpf_sk_storage_map_alloc_check(union bpf_attr *attr)
 	    !attr->btf_key_type_id || !attr->btf_value_type_id)
 		return -EINVAL;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!bpf_capable())
 		return -EPERM;
 
 	if (attr->value_size > MAX_VALUE_SIZE)
@@ -978,7 +978,7 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs)
 	/* bpf_sk_storage_map is currently limited to CAP_SYS_ADMIN as
 	 * the map_alloc_check() side also does.
 	 */
-	if (!capable(CAP_SYS_ADMIN))
+	if (!bpf_capable())
 		return ERR_PTR(-EPERM);
 
 	nla_for_each_nested(nla, nla_stgs, rem) {
diff --git a/net/core/dev.c b/net/core/dev.c
index 2d8aceee4284..10684833f864 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -398,6 +398,74 @@ static RAW_NOTIFIER_HEAD(netdev_chain);
 DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
 EXPORT_PER_CPU_SYMBOL(softnet_data);
 
+#ifdef CONFIG_LOCKDEP
+/*
+ * register_netdevice() inits txq->_xmit_lock and sets lockdep class
+ * according to dev->type
+ */
+static const unsigned short netdev_lock_type[] = {
+	 ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25,
+	 ARPHRD_PRONET, ARPHRD_CHAOS, ARPHRD_IEEE802, ARPHRD_ARCNET,
+	 ARPHRD_APPLETLK, ARPHRD_DLCI, ARPHRD_ATM, ARPHRD_METRICOM,
+	 ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP,
+	 ARPHRD_CSLIP, ARPHRD_SLIP6, ARPHRD_CSLIP6, ARPHRD_RSRVD,
+	 ARPHRD_ADAPT, ARPHRD_ROSE, ARPHRD_X25, ARPHRD_HWX25,
+	 ARPHRD_PPP, ARPHRD_CISCO, ARPHRD_LAPB, ARPHRD_DDCMP,
+	 ARPHRD_RAWHDLC, ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD,
+	 ARPHRD_SKIP, ARPHRD_LOOPBACK, ARPHRD_LOCALTLK, ARPHRD_FDDI,
+	 ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE,
+	 ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET,
+	 ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL,
+	 ARPHRD_FCFABRIC, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM,
+	 ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE,
+	 ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE};
+
+static const char *const netdev_lock_name[] = {
+	"_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25",
+	"_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET",
+	"_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM",
+	"_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP",
+	"_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD",
+	"_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25",
+	"_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP",
+	"_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD",
+	"_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI",
+	"_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE",
+	"_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET",
+	"_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL",
+	"_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM",
+	"_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE",
+	"_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"};
+
+static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)];
+
+static inline unsigned short netdev_lock_pos(unsigned short dev_type)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(netdev_lock_type); i++)
+		if (netdev_lock_type[i] == dev_type)
+			return i;
+	/* the last key is used by default */
+	return ARRAY_SIZE(netdev_lock_type) - 1;
+}
+
+static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,
+						 unsigned short dev_type)
+{
+	int i;
+
+	i = netdev_lock_pos(dev_type);
+	lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i],
+				   netdev_lock_name[i]);
+}
+#else
+static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,
+						 unsigned short dev_type)
+{
+}
+#endif
+
 /*******************************************************************************
  *
  *		Protocol management and registration routines
@@ -4549,6 +4617,11 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 	xdp->data_meta = xdp->data;
 	xdp->data_end = xdp->data + hlen;
 	xdp->data_hard_start = skb->data - skb_headroom(skb);
+
+	/* SKB "head" area always have tailroom for skb_shared_info */
+	xdp->frame_sz  = (void *)skb_end_pointer(skb) - xdp->data_hard_start;
+	xdp->frame_sz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
 	orig_data_end = xdp->data_end;
 	orig_data = xdp->data;
 	eth = (struct ethhdr *)xdp->data;
@@ -4572,14 +4645,11 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 		skb_reset_network_header(skb);
 	}
 
-	/* check if bpf_xdp_adjust_tail was used. it can only "shrink"
-	 * pckt.
-	 */
-	off = orig_data_end - xdp->data_end;
+	/* check if bpf_xdp_adjust_tail was used */
+	off = xdp->data_end - orig_data_end;
 	if (off != 0) {
 		skb_set_tail_pointer(skb, xdp->data_end - xdp->data);
-		skb->len -= off;
-
+		skb->len += off; /* positive on grow, negative on shrink */
 	}
 
 	/* check if XDP changed eth hdr such SKB needs update */
@@ -5350,6 +5420,18 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
 	struct bpf_prog *new = xdp->prog;
 	int ret = 0;
 
+	if (new) {
+		u32 i;
+
+		/* generic XDP does not work with DEVMAPs that can
+		 * have a bpf_prog installed on an entry
+		 */
+		for (i = 0; i < new->aux->used_map_cnt; i++) {
+			if (dev_map_can_have_prog(new->aux->used_maps[i]))
+				return -EINVAL;
+		}
+	}
+
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		rcu_assign_pointer(dev->xdp_prog, new);
@@ -6237,7 +6319,8 @@ EXPORT_SYMBOL(__napi_schedule_irqoff);
 
 bool napi_complete_done(struct napi_struct *n, int work_done)
 {
-	unsigned long flags, val, new;
+	unsigned long flags, val, new, timeout = 0;
+	bool ret = true;
 
 	/*
 	 * 1) Don't let napi dequeue from the cpu poll list
@@ -6249,20 +6332,23 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 				 NAPIF_STATE_IN_BUSY_POLL)))
 		return false;
 
+	if (work_done) {
+		if (n->gro_bitmask)
+			timeout = READ_ONCE(n->dev->gro_flush_timeout);
+		n->defer_hard_irqs_count = READ_ONCE(n->dev->napi_defer_hard_irqs);
+	}
+	if (n->defer_hard_irqs_count > 0) {
+		n->defer_hard_irqs_count--;
+		timeout = READ_ONCE(n->dev->gro_flush_timeout);
+		if (timeout)
+			ret = false;
+	}
 	if (n->gro_bitmask) {
-		unsigned long timeout = 0;
-
-		if (work_done)
-			timeout = n->dev->gro_flush_timeout;
-
 		/* When the NAPI instance uses a timeout and keeps postponing
 		 * it, we need to bound somehow the time packets are kept in
 		 * the GRO layer
 		 */
 		napi_gro_flush(n, !!timeout);
-		if (timeout)
-			hrtimer_start(&n->timer, ns_to_ktime(timeout),
-				      HRTIMER_MODE_REL_PINNED);
 	}
 
 	gro_normal_list(n);
@@ -6294,7 +6380,10 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 		return false;
 	}
 
-	return true;
+	if (timeout)
+		hrtimer_start(&n->timer, ns_to_ktime(timeout),
+			      HRTIMER_MODE_REL_PINNED);
+	return ret;
 }
 EXPORT_SYMBOL(napi_complete_done);
 
@@ -6474,7 +6563,7 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
 	/* Note : we use a relaxed variant of napi_schedule_prep() not setting
 	 * NAPI_STATE_MISSED, since we do not react to a device IRQ.
 	 */
-	if (napi->gro_bitmask && !napi_disable_pending(napi) &&
+	if (!napi_disable_pending(napi) &&
 	    !test_and_set_bit(NAPI_STATE_SCHED, &napi->state))
 		__napi_schedule_irqoff(napi);
 
@@ -7796,6 +7885,28 @@ void netdev_bonding_info_change(struct net_device *dev,
 }
 EXPORT_SYMBOL(netdev_bonding_info_change);
 
+/**
+ * netdev_get_xmit_slave - Get the xmit slave of master device
+ * @skb: The packet
+ * @all_slaves: assume all the slaves are active
+ *
+ * The reference counters are not incremented so the caller must be
+ * careful with locks. The caller must hold RCU lock.
+ * %NULL is returned if no slave is found.
+ */
+
+struct net_device *netdev_get_xmit_slave(struct net_device *dev,
+					 struct sk_buff *skb,
+					 bool all_slaves)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+
+	if (!ops->ndo_get_xmit_slave)
+		return NULL;
+	return ops->ndo_get_xmit_slave(dev, skb, all_slaves);
+}
+EXPORT_SYMBOL(netdev_get_xmit_slave);
+
 static void netdev_adjacent_add_links(struct net_device *dev)
 {
 	struct netdev_adjacent *iter;
@@ -8736,6 +8847,12 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 			return -EINVAL;
 		}
 
+		if (prog->expected_attach_type == BPF_XDP_DEVMAP) {
+			NL_SET_ERR_MSG(extack, "BPF_XDP_DEVMAP programs can not be attached to a device");
+			bpf_prog_put(prog);
+			return -EINVAL;
+		}
+
 		/* prog->aux->id may be 0 for orphaned device-bound progs */
 		if (prog->aux->id && prog->aux->id == prog_id) {
 			bpf_prog_put(prog);
@@ -9148,6 +9265,11 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev,
 	else
 		netif_dormant_off(dev);
 
+	if (rootdev->operstate == IF_OPER_TESTING)
+		netif_testing_on(dev);
+	else
+		netif_testing_off(dev);
+
 	if (netif_carrier_ok(rootdev))
 		netif_carrier_on(dev);
 	else
@@ -9208,7 +9330,7 @@ static void netdev_init_one_queue(struct net_device *dev,
 {
 	/* Initialize queue lock */
 	spin_lock_init(&queue->_xmit_lock);
-	lockdep_set_class(&queue->_xmit_lock, &dev->qdisc_xmit_lock_key);
+	netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type);
 	queue->xmit_lock_owner = -1;
 	netdev_queue_numa_node_write(queue, NUMA_NO_NODE);
 	queue->dev = dev;
@@ -9255,22 +9377,6 @@ void netif_tx_stop_all_queues(struct net_device *dev)
 }
 EXPORT_SYMBOL(netif_tx_stop_all_queues);
 
-static void netdev_register_lockdep_key(struct net_device *dev)
-{
-	lockdep_register_key(&dev->qdisc_tx_busylock_key);
-	lockdep_register_key(&dev->qdisc_running_key);
-	lockdep_register_key(&dev->qdisc_xmit_lock_key);
-	lockdep_register_key(&dev->addr_list_lock_key);
-}
-
-static void netdev_unregister_lockdep_key(struct net_device *dev)
-{
-	lockdep_unregister_key(&dev->qdisc_tx_busylock_key);
-	lockdep_unregister_key(&dev->qdisc_running_key);
-	lockdep_unregister_key(&dev->qdisc_xmit_lock_key);
-	lockdep_unregister_key(&dev->addr_list_lock_key);
-}
-
 void netdev_update_lockdep_key(struct net_device *dev)
 {
 	lockdep_unregister_key(&dev->addr_list_lock_key);
@@ -9837,7 +9943,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 
 	dev_net_set(dev, &init_net);
 
-	netdev_register_lockdep_key(dev);
+	lockdep_register_key(&dev->addr_list_lock_key);
 
 	dev->gso_max_size = GSO_MAX_SIZE;
 	dev->gso_max_segs = GSO_MAX_SEGS;
@@ -9926,7 +10032,7 @@ void free_netdev(struct net_device *dev)
 	free_percpu(dev->xdp_bulkq);
 	dev->xdp_bulkq = NULL;
 
-	netdev_unregister_lockdep_key(dev);
+	lockdep_unregister_key(&dev->addr_list_lock_key);
 
 	/*  Compatibility with error handling in drivers */
 	if (dev->reg_state == NETREG_UNINITIALIZED) {
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 899edcee7dab..2cafbc808b09 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3716,24 +3716,26 @@ nla_put_failure:
 	return err;
 }
 
-static void devlink_nl_region_notify(struct devlink_region *region,
-				     struct devlink_snapshot *snapshot,
-				     enum devlink_command cmd)
+static struct sk_buff *
+devlink_nl_region_notify_build(struct devlink_region *region,
+			       struct devlink_snapshot *snapshot,
+			       enum devlink_command cmd, u32 portid, u32 seq)
 {
 	struct devlink *devlink = region->devlink;
 	struct sk_buff *msg;
 	void *hdr;
 	int err;
 
-	WARN_ON(cmd != DEVLINK_CMD_REGION_NEW && cmd != DEVLINK_CMD_REGION_DEL);
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg)
-		return;
+		return ERR_PTR(-ENOMEM);
 
-	hdr = genlmsg_put(msg, 0, 0, &devlink_nl_family, 0, cmd);
-	if (!hdr)
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, 0, cmd);
+	if (!hdr) {
+		err = -EMSGSIZE;
 		goto out_free_msg;
+	}
 
 	err = devlink_nl_put_handle(msg, devlink);
 	if (err)
@@ -3757,15 +3759,30 @@ static void devlink_nl_region_notify(struct devlink_region *region,
 	}
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
-				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
-
-	return;
+	return msg;
 
 out_cancel_msg:
 	genlmsg_cancel(msg, hdr);
 out_free_msg:
 	nlmsg_free(msg);
+	return ERR_PTR(err);
+}
+
+static void devlink_nl_region_notify(struct devlink_region *region,
+				     struct devlink_snapshot *snapshot,
+				     enum devlink_command cmd)
+{
+	struct devlink *devlink = region->devlink;
+	struct sk_buff *msg;
+
+	WARN_ON(cmd != DEVLINK_CMD_REGION_NEW && cmd != DEVLINK_CMD_REGION_DEL);
+
+	msg = devlink_nl_region_notify_build(region, snapshot, cmd, 0, 0);
+	if (IS_ERR(msg))
+		return;
+
+	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
+				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
 }
 
 /**
@@ -4069,6 +4086,8 @@ static int
 devlink_nl_cmd_region_new(struct sk_buff *skb, struct genl_info *info)
 {
 	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_snapshot *snapshot;
+	struct nlattr *snapshot_id_attr;
 	struct devlink_region *region;
 	const char *region_name;
 	u32 snapshot_id;
@@ -4080,11 +4099,6 @@ devlink_nl_cmd_region_new(struct sk_buff *skb, struct genl_info *info)
 		return -EINVAL;
 	}
 
-	if (!info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]) {
-		NL_SET_ERR_MSG_MOD(info->extack, "No snapshot id provided");
-		return -EINVAL;
-	}
-
 	region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]);
 	region = devlink_region_get_by_name(devlink, region_name);
 	if (!region) {
@@ -4102,16 +4116,25 @@ devlink_nl_cmd_region_new(struct sk_buff *skb, struct genl_info *info)
 		return -ENOSPC;
 	}
 
-	snapshot_id = nla_get_u32(info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]);
+	snapshot_id_attr = info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID];
+	if (snapshot_id_attr) {
+		snapshot_id = nla_get_u32(snapshot_id_attr);
 
-	if (devlink_region_snapshot_get_by_id(region, snapshot_id)) {
-		NL_SET_ERR_MSG_MOD(info->extack, "The requested snapshot id is already in use");
-		return -EEXIST;
-	}
+		if (devlink_region_snapshot_get_by_id(region, snapshot_id)) {
+			NL_SET_ERR_MSG_MOD(info->extack, "The requested snapshot id is already in use");
+			return -EEXIST;
+		}
 
-	err = __devlink_snapshot_id_insert(devlink, snapshot_id);
-	if (err)
-		return err;
+		err = __devlink_snapshot_id_insert(devlink, snapshot_id);
+		if (err)
+			return err;
+	} else {
+		err = __devlink_region_snapshot_id_get(devlink, &snapshot_id);
+		if (err) {
+			NL_SET_ERR_MSG_MOD(info->extack, "Failed to allocate a new snapshot id");
+			return err;
+		}
+	}
 
 	err = region->ops->snapshot(devlink, info->extack, &data);
 	if (err)
@@ -4121,6 +4144,27 @@ devlink_nl_cmd_region_new(struct sk_buff *skb, struct genl_info *info)
 	if (err)
 		goto err_snapshot_create;
 
+	if (!snapshot_id_attr) {
+		struct sk_buff *msg;
+
+		snapshot = devlink_region_snapshot_get_by_id(region,
+							     snapshot_id);
+		if (WARN_ON(!snapshot))
+			return -EINVAL;
+
+		msg = devlink_nl_region_notify_build(region, snapshot,
+						     DEVLINK_CMD_REGION_NEW,
+						     info->snd_portid,
+						     info->snd_seq);
+		err = PTR_ERR_OR_ZERO(msg);
+		if (err)
+			goto err_notify;
+
+		err = genlmsg_reply(msg, info);
+		if (err)
+			goto err_notify;
+	}
+
 	return 0;
 
 err_snapshot_create:
@@ -4128,6 +4172,10 @@ err_snapshot_create:
 err_snapshot_capture:
 	__devlink_snapshot_id_decrement(devlink, snapshot_id);
 	return err;
+
+err_notify:
+	devlink_region_snapshot_del(region, snapshot);
+	return err;
 }
 
 static int devlink_nl_cmd_region_read_chunk_fill(struct sk_buff *msg,
@@ -4167,7 +4215,6 @@ static int devlink_nl_region_read_snapshot_fill(struct sk_buff *skb,
 						struct nlattr **attrs,
 						u64 start_offset,
 						u64 end_offset,
-						bool dump,
 						u64 *new_offset)
 {
 	struct devlink_snapshot *snapshot;
@@ -4182,9 +4229,6 @@ static int devlink_nl_region_read_snapshot_fill(struct sk_buff *skb,
 	if (!snapshot)
 		return -EINVAL;
 
-	if (end_offset > region->size || dump)
-		end_offset = region->size;
-
 	while (curr_offset < end_offset) {
 		u32 data_size;
 		u8 *data;
@@ -4212,13 +4256,12 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
 					     struct netlink_callback *cb)
 {
 	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
-	u64 ret_offset, start_offset, end_offset = 0;
+	u64 ret_offset, start_offset, end_offset = U64_MAX;
 	struct nlattr **attrs = info->attrs;
 	struct devlink_region *region;
 	struct nlattr *chunks_attr;
 	const char *region_name;
 	struct devlink *devlink;
-	bool dump = true;
 	void *hdr;
 	int err;
 
@@ -4246,8 +4289,21 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
 		goto out_unlock;
 	}
 
+	if (attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR] &&
+	    attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]) {
+		if (!start_offset)
+			start_offset =
+				nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]);
+
+		end_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]);
+		end_offset += nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]);
+	}
+
+	if (end_offset > region->size)
+		end_offset = region->size;
+
 	/* return 0 if there is no further data to read */
-	if (start_offset >= region->size) {
+	if (start_offset == end_offset) {
 		err = 0;
 		goto out_unlock;
 	}
@@ -4274,27 +4330,10 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
 		goto nla_put_failure;
 	}
 
-	if (attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR] &&
-	    attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]) {
-		if (!start_offset)
-			start_offset =
-				nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]);
-
-		end_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]);
-		end_offset += nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]);
-		dump = false;
-
-		if (start_offset == end_offset) {
-			err = 0;
-			goto nla_put_failure;
-		}
-	}
-
 	err = devlink_nl_region_read_snapshot_fill(skb, devlink,
 						   region, attrs,
 						   start_offset,
-						   end_offset, dump,
-						   &ret_offset);
+						   end_offset, &ret_offset);
 
 	if (err && err != -EMSGSIZE)
 		goto nla_put_failure;
@@ -5830,7 +5869,8 @@ devlink_trap_action_get_from_info(struct genl_info *info,
 	val = nla_get_u8(info->attrs[DEVLINK_ATTR_TRAP_ACTION]);
 	switch (val) {
 	case DEVLINK_TRAP_ACTION_DROP: /* fall-through */
-	case DEVLINK_TRAP_ACTION_TRAP:
+	case DEVLINK_TRAP_ACTION_TRAP: /* fall-through */
+	case DEVLINK_TRAP_ACTION_MIRROR:
 		*p_trap_action = val;
 		break;
 	default:
@@ -8455,6 +8495,50 @@ static const struct devlink_trap devlink_trap_generic[] = {
 	DEVLINK_TRAP(OVERLAY_SMAC_MC, DROP),
 	DEVLINK_TRAP(INGRESS_FLOW_ACTION_DROP, DROP),
 	DEVLINK_TRAP(EGRESS_FLOW_ACTION_DROP, DROP),
+	DEVLINK_TRAP(STP, CONTROL),
+	DEVLINK_TRAP(LACP, CONTROL),
+	DEVLINK_TRAP(LLDP, CONTROL),
+	DEVLINK_TRAP(IGMP_QUERY, CONTROL),
+	DEVLINK_TRAP(IGMP_V1_REPORT, CONTROL),
+	DEVLINK_TRAP(IGMP_V2_REPORT, CONTROL),
+	DEVLINK_TRAP(IGMP_V3_REPORT, CONTROL),
+	DEVLINK_TRAP(IGMP_V2_LEAVE, CONTROL),
+	DEVLINK_TRAP(MLD_QUERY, CONTROL),
+	DEVLINK_TRAP(MLD_V1_REPORT, CONTROL),
+	DEVLINK_TRAP(MLD_V2_REPORT, CONTROL),
+	DEVLINK_TRAP(MLD_V1_DONE, CONTROL),
+	DEVLINK_TRAP(IPV4_DHCP, CONTROL),
+	DEVLINK_TRAP(IPV6_DHCP, CONTROL),
+	DEVLINK_TRAP(ARP_REQUEST, CONTROL),
+	DEVLINK_TRAP(ARP_RESPONSE, CONTROL),
+	DEVLINK_TRAP(ARP_OVERLAY, CONTROL),
+	DEVLINK_TRAP(IPV6_NEIGH_SOLICIT, CONTROL),
+	DEVLINK_TRAP(IPV6_NEIGH_ADVERT, CONTROL),
+	DEVLINK_TRAP(IPV4_BFD, CONTROL),
+	DEVLINK_TRAP(IPV6_BFD, CONTROL),
+	DEVLINK_TRAP(IPV4_OSPF, CONTROL),
+	DEVLINK_TRAP(IPV6_OSPF, CONTROL),
+	DEVLINK_TRAP(IPV4_BGP, CONTROL),
+	DEVLINK_TRAP(IPV6_BGP, CONTROL),
+	DEVLINK_TRAP(IPV4_VRRP, CONTROL),
+	DEVLINK_TRAP(IPV6_VRRP, CONTROL),
+	DEVLINK_TRAP(IPV4_PIM, CONTROL),
+	DEVLINK_TRAP(IPV6_PIM, CONTROL),
+	DEVLINK_TRAP(UC_LB, CONTROL),
+	DEVLINK_TRAP(LOCAL_ROUTE, CONTROL),
+	DEVLINK_TRAP(EXTERNAL_ROUTE, CONTROL),
+	DEVLINK_TRAP(IPV6_UC_DIP_LINK_LOCAL_SCOPE, CONTROL),
+	DEVLINK_TRAP(IPV6_DIP_ALL_NODES, CONTROL),
+	DEVLINK_TRAP(IPV6_DIP_ALL_ROUTERS, CONTROL),
+	DEVLINK_TRAP(IPV6_ROUTER_SOLICIT, CONTROL),
+	DEVLINK_TRAP(IPV6_ROUTER_ADVERT, CONTROL),
+	DEVLINK_TRAP(IPV6_REDIRECT, CONTROL),
+	DEVLINK_TRAP(IPV4_ROUTER_ALERT, CONTROL),
+	DEVLINK_TRAP(IPV6_ROUTER_ALERT, CONTROL),
+	DEVLINK_TRAP(PTP_EVENT, CONTROL),
+	DEVLINK_TRAP(PTP_GENERAL, CONTROL),
+	DEVLINK_TRAP(FLOW_ACTION_SAMPLE, CONTROL),
+	DEVLINK_TRAP(FLOW_ACTION_TRAP, CONTROL),
 };
 
 #define DEVLINK_TRAP_GROUP(_id)						      \
@@ -8466,9 +8550,28 @@ static const struct devlink_trap devlink_trap_generic[] = {
 static const struct devlink_trap_group devlink_trap_group_generic[] = {
 	DEVLINK_TRAP_GROUP(L2_DROPS),
 	DEVLINK_TRAP_GROUP(L3_DROPS),
+	DEVLINK_TRAP_GROUP(L3_EXCEPTIONS),
 	DEVLINK_TRAP_GROUP(BUFFER_DROPS),
 	DEVLINK_TRAP_GROUP(TUNNEL_DROPS),
 	DEVLINK_TRAP_GROUP(ACL_DROPS),
+	DEVLINK_TRAP_GROUP(STP),
+	DEVLINK_TRAP_GROUP(LACP),
+	DEVLINK_TRAP_GROUP(LLDP),
+	DEVLINK_TRAP_GROUP(MC_SNOOPING),
+	DEVLINK_TRAP_GROUP(DHCP),
+	DEVLINK_TRAP_GROUP(NEIGH_DISCOVERY),
+	DEVLINK_TRAP_GROUP(BFD),
+	DEVLINK_TRAP_GROUP(OSPF),
+	DEVLINK_TRAP_GROUP(BGP),
+	DEVLINK_TRAP_GROUP(VRRP),
+	DEVLINK_TRAP_GROUP(PIM),
+	DEVLINK_TRAP_GROUP(UC_LB),
+	DEVLINK_TRAP_GROUP(LOCAL_DELIVERY),
+	DEVLINK_TRAP_GROUP(IPV6),
+	DEVLINK_TRAP_GROUP(PTP_EVENT),
+	DEVLINK_TRAP_GROUP(PTP_GENERAL),
+	DEVLINK_TRAP_GROUP(ACL_SAMPLE),
+	DEVLINK_TRAP_GROUP(ACL_TRAP),
 };
 
 static int devlink_trap_generic_verify(const struct devlink_trap *trap)
@@ -8806,6 +8909,13 @@ void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb,
 	devlink_trap_stats_update(trap_item->stats, skb->len);
 	devlink_trap_stats_update(trap_item->group_item->stats, skb->len);
 
+	/* Control packets were not dropped by the device or encountered an
+	 * exception during forwarding and therefore should not be reported to
+	 * the kernel's drop monitor.
+	 */
+	if (trap_item->trap->type == DEVLINK_TRAP_TYPE_CONTROL)
+		return;
+
 	devlink_trap_report_metadata_fill(&hw_metadata, trap_item,
 					  in_devlink_port, fa_cookie);
 	net_dm_hw_report(skb, &hw_metadata);
diff --git a/net/core/dst.c b/net/core/dst.c
index 193af526e908..d6b6ced0d451 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -81,11 +81,11 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
 {
 	struct dst_entry *dst;
 
-	if (ops->gc && dst_entries_get_fast(ops) > ops->gc_thresh) {
+	if (ops->gc &&
+	    !(flags & DST_NOCOUNT) &&
+	    dst_entries_get_fast(ops) > ops->gc_thresh) {
 		if (ops->gc(ops)) {
-			printk_ratelimited(KERN_NOTICE "Route cache is full: "
-					   "consider increasing sysctl "
-					   "net.ipv[4|6].route.max_size.\n");
+			pr_notice_ratelimited("Route cache is full: consider increasing sysctl net.ipv6.route.max_size.\n");
 			return NULL;
 		}
 	}
diff --git a/net/core/filter.c b/net/core/filter.c
index 5cc9276f1023..d01a244b5087 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -256,17 +256,6 @@ BPF_CALL_2(bpf_skb_load_helper_32_no_cache, const struct sk_buff *, skb,
 					  offset);
 }
 
-BPF_CALL_0(bpf_get_raw_cpu_id)
-{
-	return raw_smp_processor_id();
-}
-
-static const struct bpf_func_proto bpf_get_raw_smp_processor_id_proto = {
-	.func		= bpf_get_raw_cpu_id,
-	.gpl_only	= false,
-	.ret_type	= RET_INTEGER,
-};
-
 static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg,
 			      struct bpf_insn *insn_buf)
 {
@@ -2026,6 +2015,40 @@ static const struct bpf_func_proto bpf_csum_update_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_2(bpf_csum_level, struct sk_buff *, skb, u64, level)
+{
+	/* The interface is to be used in combination with bpf_skb_adjust_room()
+	 * for encap/decap of packet headers when BPF_F_ADJ_ROOM_NO_CSUM_RESET
+	 * is passed as flags, for example.
+	 */
+	switch (level) {
+	case BPF_CSUM_LEVEL_INC:
+		__skb_incr_checksum_unnecessary(skb);
+		break;
+	case BPF_CSUM_LEVEL_DEC:
+		__skb_decr_checksum_unnecessary(skb);
+		break;
+	case BPF_CSUM_LEVEL_RESET:
+		__skb_reset_checksum_unnecessary(skb);
+		break;
+	case BPF_CSUM_LEVEL_QUERY:
+		return skb->ip_summed == CHECKSUM_UNNECESSARY ?
+		       skb->csum_level : -EACCES;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_csum_level_proto = {
+	.func		= bpf_csum_level,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+};
+
 static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb)
 {
 	return dev_forward_skb(dev, skb);
@@ -3124,7 +3147,8 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff,
 {
 	int ret;
 
-	if (flags & ~BPF_F_ADJ_ROOM_FIXED_GSO)
+	if (unlikely(flags & ~(BPF_F_ADJ_ROOM_FIXED_GSO |
+			       BPF_F_ADJ_ROOM_NO_CSUM_RESET)))
 		return -EINVAL;
 
 	if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) {
@@ -3174,7 +3198,8 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
 	u32 off;
 	int ret;
 
-	if (unlikely(flags & ~BPF_F_ADJ_ROOM_MASK))
+	if (unlikely(flags & ~(BPF_F_ADJ_ROOM_MASK |
+			       BPF_F_ADJ_ROOM_NO_CSUM_RESET)))
 		return -EINVAL;
 	if (unlikely(len_diff_abs > 0xfffU))
 		return -EFAULT;
@@ -3202,6 +3227,8 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
 
 	ret = shrink ? bpf_skb_net_shrink(skb, off, len_diff_abs, flags) :
 		       bpf_skb_net_grow(skb, off, len_diff_abs, flags);
+	if (!ret && !(flags & BPF_F_ADJ_ROOM_NO_CSUM_RESET))
+		__skb_reset_checksum_unnecessary(skb);
 
 	bpf_compute_data_pointers(skb);
 	return ret;
@@ -3422,15 +3449,26 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = {
 
 BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset)
 {
+	void *data_hard_end = xdp_data_hard_end(xdp); /* use xdp->frame_sz */
 	void *data_end = xdp->data_end + offset;
 
-	/* only shrinking is allowed for now. */
-	if (unlikely(offset >= 0))
+	/* Notice that xdp_data_hard_end have reserved some tailroom */
+	if (unlikely(data_end > data_hard_end))
+		return -EINVAL;
+
+	/* ALL drivers MUST init xdp->frame_sz, chicken check below */
+	if (unlikely(xdp->frame_sz > PAGE_SIZE)) {
+		WARN_ONCE(1, "Too BIG xdp->frame_sz = %d\n", xdp->frame_sz);
 		return -EINVAL;
+	}
 
 	if (unlikely(data_end < xdp->data + ETH_HLEN))
 		return -EINVAL;
 
+	/* Clear memory area on grow, can contain uninit kernel memory */
+	if (offset > 0)
+		memset(xdp->data_end, 0, offset);
+
 	xdp->data_end = data_end;
 
 	return 0;
@@ -4014,16 +4052,22 @@ static const struct bpf_func_proto bpf_skb_under_cgroup_proto = {
 };
 
 #ifdef CONFIG_SOCK_CGROUP_DATA
+static inline u64 __bpf_sk_cgroup_id(struct sock *sk)
+{
+	struct cgroup *cgrp;
+
+	cgr