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
  ...

1 files changed, 160 insertions, 50 deletions

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);