Merge tag 'net-next-6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Paolo Abeni:
 "Core:

   - Allow live renaming when an interface is up

   - Add retpoline wrappers for tc, improving considerably the
     performances of complex queue discipline configurations

   - Add inet drop monitor support

   - A few GRO performance improvements

   - Add infrastructure for atomic dev stats, addressing long standing
     data races

   - De-duplicate common code between OVS and conntrack offloading
     infrastructure

   - A bunch of UBSAN_BOUNDS/FORTIFY_SOURCE improvements

   - Netfilter: introduce packet parser for tunneled packets

   - Replace IPVS timer-based estimators with kthreads to scale up the
     workload with the number of available CPUs

   - Add the helper support for connection-tracking OVS offload

  BPF:

   - Support for user defined BPF objects: the use case is to allocate
     own objects, build own object hierarchies and use the building
     blocks to build own data structures flexibly, for example, linked
     lists in BPF

   - Make cgroup local storage available to non-cgroup attached BPF
     programs

   - Avoid unnecessary deadlock detection and failures wrt BPF task
     storage helpers

   - A relevant bunch of BPF verifier fixes and improvements

   - Veristat tool improvements to support custom filtering, sorting,
     and replay of results

   - Add LLVM disassembler as default library for dumping JITed code

   - Lots of new BPF documentation for various BPF maps

   - Add bpf_rcu_read_{,un}lock() support for sleepable programs

   - Add RCU grace period chaining to BPF to wait for the completion of
     access from both sleepable and non-sleepable BPF programs

   - Add support storing struct task_struct objects as kptrs in maps

   - Improve helper UAPI by explicitly defining BPF_FUNC_xxx integer
     values

   - Add libbpf *_opts API-variants for bpf_*_get_fd_by_id() functions

  Protocols:

   - TCP: implement Protective Load Balancing across switch links

   - TCP: allow dynamically disabling TCP-MD5 static key, reverting back
     to fast[er]-path

   - UDP: Introduce optional per-netns hash lookup table

   - IPv6: simplify and cleanup sockets disposal

   - Netlink: support different type policies for each generic netlink
     operation

   - MPTCP: add MSG_FASTOPEN and FastOpen listener side support

   - MPTCP: add netlink notification support for listener sockets events

   - SCTP: add VRF support, allowing sctp sockets binding to VRF devices

   - Add bridging MAC Authentication Bypass (MAB) support

   - Extensions for Ethernet VPN bridging implementation to better
     support multicast scenarios

   - More work for Wi-Fi 7 support, comprising conversion of all the
     existing drivers to internal TX queue usage

   - IPSec: introduce a new offload type (packet offload) allowing
     complete header processing and crypto offloading

   - IPSec: extended ack support for more descriptive XFRM error
     reporting

   - RXRPC: increase SACK table size and move processing into a
     per-local endpoint kernel thread, reducing considerably the
     required locking

   - IEEE 802154: synchronous send frame and extended filtering support,
     initial support for scanning available 15.4 networks

   - Tun: bump the link speed from 10Mbps to 10Gbps

   - Tun/VirtioNet: implement UDP segmentation offload support

  Driver API:

   - PHY/SFP: improve power level switching between standard level 1 and
     the higher power levels

   - New API for netdev <-> devlink_port linkage

   - PTP: convert existing drivers to new frequency adjustment
     implementation

   - DSA: add support for rx offloading

   - Autoload DSA tagging driver when dynamically changing protocol

   - Add new PCP and APPTRUST attributes to Data Center Bridging

   - Add configuration support for 800Gbps link speed

   - Add devlink port function attribute to enable/disable RoCE and
     migratable

   - Extend devlink-rate to support strict prioriry and weighted fair
     queuing

   - Add devlink support to directly reading from region memory

   - New device tree helper to fetch MAC address from nvmem

   - New big TCP helper to simplify temporary header stripping

  New hardware / drivers:

   - Ethernet:
      - Marvel Octeon CNF95N and CN10KB Ethernet Switches
      - Marvel Prestera AC5X Ethernet Switch
      - WangXun 10 Gigabit NIC
      - Motorcomm yt8521 Gigabit Ethernet
      - Microchip ksz9563 Gigabit Ethernet Switch
      - Microsoft Azure Network Adapter
      - Linux Automation 10Base-T1L adapter

   - PHY:
      - Aquantia AQR112 and AQR412
      - Motorcomm YT8531S

   - PTP:
      - Orolia ART-CARD

   - WiFi:
      - MediaTek Wi-Fi 7 (802.11be) devices
      - RealTek rtw8821cu, rtw8822bu, rtw8822cu and rtw8723du USB
        devices

   - Bluetooth:
      - Broadcom BCM4377/4378/4387 Bluetooth chipsets
      - Realtek RTL8852BE and RTL8723DS
      - Cypress.CYW4373A0 WiFi + Bluetooth combo device

  Drivers:

   - CAN:
      - gs_usb: bus error reporting support
      - kvaser_usb: listen only and bus error reporting support

   - Ethernet NICs:
      - Intel (100G):
         - extend action skbedit to RX queue mapping
         - implement devlink-rate support
         - support direct read from memory
      - nVidia/Mellanox (mlx5):
         - SW steering improvements, increasing rules update rate
         - Support for enhanced events compression
         - extend H/W offload packet manipulation capabilities
         - implement IPSec packet offload mode
      - nVidia/Mellanox (mlx4):
         - better big TCP support
      - Netronome Ethernet NICs (nfp):
         - IPsec offload support
         - add support for multicast filter
      - Broadcom:
         - RSS and PTP support improvements
      - AMD/SolarFlare:
         - netlink extened ack improvements
         - add basic flower matches to offload, and related stats
      - Virtual NICs:
         - ibmvnic: introduce affinity hint support
      - small / embedded:
         - FreeScale fec: add initial XDP support
         - Marvel mv643xx_eth: support MII/GMII/RGMII modes for Kirkwood
         - TI am65-cpsw: add suspend/resume support
         - Mediatek MT7986: add RX wireless wthernet dispatch support
         - Realtek 8169: enable GRO software interrupt coalescing per
           default

   - Ethernet high-speed switches:
      - Microchip (sparx5):
         - add support for Sparx5 TC/flower H/W offload via VCAP
      - Mellanox mlxsw:
         - add 802.1X and MAC Authentication Bypass offload support
         - add ip6gre support

   - Embedded Ethernet switches:
      - Mediatek (mtk_eth_soc):
         - improve PCS implementation, add DSA untag support
         - enable flow offload support
      - Renesas:
         - add rswitch R-Car Gen4 gPTP support
      - Microchip (lan966x):
         - add full XDP support
         - add TC H/W offload via VCAP
         - enable PTP on bridge interfaces
      - Microchip (ksz8):
         - add MTU support for KSZ8 series

   - Qualcomm 802.11ax WiFi (ath11k):
      - support configuring channel dwell time during scan

   - MediaTek WiFi (mt76):
      - enable Wireless Ethernet Dispatch (WED) offload support
      - add ack signal support
      - enable coredump support
      - remain_on_channel support

   - Intel WiFi (iwlwifi):
      - enable Wi-Fi 7 Extremely High Throughput (EHT) PHY capabilities
      - 320 MHz channels support

   - RealTek WiFi (rtw89):
      - new dynamic header firmware format support
      - wake-over-WLAN support"

* tag 'net-next-6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2002 commits)
  ipvs: fix type warning in do_div() on 32 bit
  net: lan966x: Remove a useless test in lan966x_ptp_add_trap()
  net: ipa: add IPA v4.7 support
  dt-bindings: net: qcom,ipa: Add SM6350 compatible
  bnxt: Use generic HBH removal helper in tx path
  IPv6/GRO: generic helper to remove temporary HBH/jumbo header in driver
  selftests: forwarding: Add bridge MDB test
  selftests: forwarding: Rename bridge_mdb test
  bridge: mcast: Support replacement of MDB port group entries
  bridge: mcast: Allow user space to specify MDB entry routing protocol
  bridge: mcast: Allow user space to add (*, G) with a source list and filter mode
  bridge: mcast: Add support for (*, G) with a source list and filter mode
  bridge: mcast: Avoid arming group timer when (S, G) corresponds to a source
  bridge: mcast: Add a flag for user installed source entries
  bridge: mcast: Expose __br_multicast_del_group_src()
  bridge: mcast: Expose br_multicast_new_group_src()
  bridge: mcast: Add a centralized error path
  bridge: mcast: Place netlink policy before validation functions
  bridge: mcast: Split (*, G) and (S, G) addition into different functions
  bridge: mcast: Do not derive entry type from its filter mode
  ...

2 files changed, 407 insertions, 130 deletions

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 7a401d94463a..bca2a470ccad 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -812,6 +812,17 @@ static int netlink_release(struct socket *sock)
 	}
 
 	sock_prot_inuse_add(sock_net(sk), &netlink_proto, -1);
+
+	/* Because struct net might disappear soon, do not keep a pointer. */
+	if (!sk->sk_net_refcnt && sock_net(sk) != &init_net) {
+		__netns_tracker_free(sock_net(sk), &sk->ns_tracker, false);
+		/* Because of deferred_put_nlk_sk and use of work queue,
+		 * it is possible  netns will be freed before this socket.
+		 */
+		sock_net_set(sk, &init_net);
+		__netns_tracker_alloc(&init_net, &sk->ns_tracker,
+				      false, GFP_KERNEL);
+	}
 	call_rcu(&nlk->rcu, deferred_put_nlk_sk);
 	return 0;
 }
@@ -2488,19 +2499,24 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
 		flags |= NLM_F_ACK_TLVS;
 
 	skb = nlmsg_new(payload + tlvlen, GFP_KERNEL);
-	if (!skb) {
-		NETLINK_CB(in_skb).sk->sk_err = ENOBUFS;
-		sk_error_report(NETLINK_CB(in_skb).sk);
-		return;
-	}
+	if (!skb)
+		goto err_skb;
 
 	rep = nlmsg_put(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq,
-			NLMSG_ERROR, payload, flags);
+			NLMSG_ERROR, sizeof(*errmsg), flags);
+	if (!rep)
+		goto err_bad_put;
 	errmsg = nlmsg_data(rep);
 	errmsg->error = err;
-	unsafe_memcpy(&errmsg->msg, nlh, payload > sizeof(*errmsg)
-					 ? nlh->nlmsg_len : sizeof(*nlh),
-		      /* Bounds checked by the skb layer. */);
+	errmsg->msg = *nlh;
+
+	if (!(flags & NLM_F_CAPPED)) {
+		if (!nlmsg_append(skb, nlmsg_len(nlh)))
+			goto err_bad_put;
+
+		memcpy(nlmsg_data(&errmsg->msg), nlmsg_data(nlh),
+		       nlmsg_len(nlh));
+	}
 
 	if (tlvlen)
 		netlink_ack_tlv_fill(in_skb, skb, nlh, err, extack);
@@ -2508,6 +2524,14 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
 	nlmsg_end(skb, rep);
 
 	nlmsg_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid);
+
+	return;
+
+err_bad_put:
+	nlmsg_free(skb);
+err_skb:
+	NETLINK_CB(in_skb).sk->sk_err = ENOBUFS;
+	sk_error_report(NETLINK_CB(in_skb).sk);
 }
 EXPORT_SYMBOL(netlink_ack);
 
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 3e16527beb91..600993c80050 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -101,6 +101,17 @@ genl_op_fill_in_reject_policy(const struct genl_family *family,
 	op->maxattr = 1;
 }
 
+static void
+genl_op_fill_in_reject_policy_split(const struct genl_family *family,
+				    struct genl_split_ops *op)
+{
+	if (op->policy)
+		return;
+
+	op->policy = genl_policy_reject_all;
+	op->maxattr = 1;
+}
+
 static const struct genl_family *genl_family_find_byid(unsigned int id)
 {
 	return idr_find(&genl_fam_idr, id);
@@ -118,10 +129,15 @@ static const struct genl_family *genl_family_find_byname(char *name)
 	return NULL;
 }
 
-static int genl_get_cmd_cnt(const struct genl_family *family)
-{
-	return family->n_ops + family->n_small_ops;
-}
+struct genl_op_iter {
+	const struct genl_family *family;
+	struct genl_split_ops doit;
+	struct genl_split_ops dumpit;
+	int cmd_idx;
+	int entry_idx;
+	u32 cmd;
+	u8 flags;
+};
 
 static void genl_op_from_full(const struct genl_family *family,
 			      unsigned int i, struct genl_ops *op)
@@ -181,24 +197,187 @@ static int genl_get_cmd_small(u32 cmd, const struct genl_family *family,
 	return -ENOENT;
 }
 
-static int genl_get_cmd(u32 cmd, const struct genl_family *family,
-			struct genl_ops *op)
+static void genl_op_from_split(struct genl_op_iter *iter)
 {
-	if (!genl_get_cmd_full(cmd, family, op))
-		return 0;
-	return genl_get_cmd_small(cmd, family, op);
+	const struct genl_family *family = iter->family;
+	int i, cnt = 0;
+
+	i = iter->entry_idx - family->n_ops - family->n_small_ops;
+
+	if (family->split_ops[i + cnt].flags & GENL_CMD_CAP_DO) {
+		iter->doit = family->split_ops[i + cnt];
+		genl_op_fill_in_reject_policy_split(family, &iter->doit);
+		cnt++;
+	} else {
+		memset(&iter->doit, 0, sizeof(iter->doit));
+	}
+
+	if (i + cnt < family->n_split_ops &&
+	    family->split_ops[i + cnt].flags & GENL_CMD_CAP_DUMP) {
+		iter->dumpit = family->split_ops[i + cnt];
+		genl_op_fill_in_reject_policy_split(family, &iter->dumpit);
+		cnt++;
+	} else {
+		memset(&iter->dumpit, 0, sizeof(iter->dumpit));
+	}
+
+	WARN_ON(!cnt);
+	iter->entry_idx += cnt;
 }
 
-static void genl_get_cmd_by_index(unsigned int i,
-				  const struct genl_family *family,
-				  struct genl_ops *op)
+static int
+genl_get_cmd_split(u32 cmd, u8 flag, const struct genl_family *family,
+		   struct genl_split_ops *op)
 {
-	if (i < family->n_ops)
-		genl_op_from_full(family, i, op);
-	else if (i < family->n_ops + family->n_small_ops)
-		genl_op_from_small(family, i - family->n_ops, op);
-	else
-		WARN_ON_ONCE(1);
+	int i;
+
+	for (i = 0; i < family->n_split_ops; i++)
+		if (family->split_ops[i].cmd == cmd &&
+		    family->split_ops[i].flags & flag) {
+			*op = family->split_ops[i];
+			return 0;
+		}
+
+	return -ENOENT;
+}
+
+static int
+genl_cmd_full_to_split(struct genl_split_ops *op,
+		       const struct genl_family *family,
+		       const struct genl_ops *full, u8 flags)
+{
+	if ((flags & GENL_CMD_CAP_DO && !full->doit) ||
+	    (flags & GENL_CMD_CAP_DUMP && !full->dumpit)) {
+		memset(op, 0, sizeof(*op));
+		return -ENOENT;
+	}
+
+	if (flags & GENL_CMD_CAP_DUMP) {
+		op->start	= full->start;
+		op->dumpit	= full->dumpit;
+		op->done	= full->done;
+	} else {
+		op->pre_doit	= family->pre_doit;
+		op->doit	= full->doit;
+		op->post_doit	= family->post_doit;
+	}
+
+	if (flags & GENL_CMD_CAP_DUMP &&
+	    full->validate & GENL_DONT_VALIDATE_DUMP) {
+		op->policy	= NULL;
+		op->maxattr	= 0;
+	} else {
+		op->policy	= full->policy;
+		op->maxattr	= full->maxattr;
+	}
+
+	op->cmd			= full->cmd;
+	op->internal_flags	= full->internal_flags;
+	op->flags		= full->flags;
+	op->validate		= full->validate;
+
+	/* Make sure flags include the GENL_CMD_CAP_DO / GENL_CMD_CAP_DUMP */
+	op->flags		|= flags;
+
+	return 0;
+}
+
+/* Must make sure that op is initialized to 0 on failure */
+static int
+genl_get_cmd(u32 cmd, u8 flags, const struct genl_family *family,
+	     struct genl_split_ops *op)
+{
+	struct genl_ops full;
+	int err;
+
+	err = genl_get_cmd_full(cmd, family, &full);
+	if (err == -ENOENT)
+		err = genl_get_cmd_small(cmd, family, &full);
+	/* Found one of legacy forms */
+	if (err == 0)
+		return genl_cmd_full_to_split(op, family, &full, flags);
+
+	err = genl_get_cmd_split(cmd, flags, family, op);
+	if (err)
+		memset(op, 0, sizeof(*op));
+	return err;
+}
+
+/* For policy dumping only, get ops of both do and dump.
+ * Fail if both are missing, genl_get_cmd() will zero-init in case of failure.
+ */
+static int
+genl_get_cmd_both(u32 cmd, const struct genl_family *family,
+		  struct genl_split_ops *doit, struct genl_split_ops *dumpit)
+{
+	int err1, err2;
+
+	err1 = genl_get_cmd(cmd, GENL_CMD_CAP_DO, family, doit);
+	err2 = genl_get_cmd(cmd, GENL_CMD_CAP_DUMP, family, dumpit);
+
+	return err1 && err2 ? -ENOENT : 0;
+}
+
+static bool
+genl_op_iter_init(const struct genl_family *family, struct genl_op_iter *iter)
+{
+	iter->family = family;
+	iter->cmd_idx = 0;
+	iter->entry_idx = 0;
+
+	iter->flags = 0;
+
+	return iter->family->n_ops +
+		iter->family->n_small_ops +
+		iter->family->n_split_ops;
+}
+
+static bool genl_op_iter_next(struct genl_op_iter *iter)
+{
+	const struct genl_family *family = iter->family;
+	bool legacy_op = true;
+	struct genl_ops op;
+
+	if (iter->entry_idx < family->n_ops) {
+		genl_op_from_full(family, iter->entry_idx, &op);
+	} else if (iter->entry_idx < family->n_ops + family->n_small_ops) {
+		genl_op_from_small(family, iter->entry_idx - family->n_ops,
+				   &op);
+	} else if (iter->entry_idx <
+		   family->n_ops + family->n_small_ops + family->n_split_ops) {
+		legacy_op = false;
+		/* updates entry_idx */
+		genl_op_from_split(iter);
+	} else {
+		return false;
+	}
+
+	iter->cmd_idx++;
+
+	if (legacy_op) {
+		iter->entry_idx++;
+
+		genl_cmd_full_to_split(&iter->doit, family,
+				       &op, GENL_CMD_CAP_DO);
+		genl_cmd_full_to_split(&iter->dumpit, family,
+				       &op, GENL_CMD_CAP_DUMP);
+	}
+
+	iter->cmd = iter->doit.cmd | iter->dumpit.cmd;
+	iter->flags = iter->doit.flags | iter->dumpit.flags;
+
+	return true;
+}
+
+static void
+genl_op_iter_copy(struct genl_op_iter *dst, struct genl_op_iter *src)
+{
+	*dst = *src;
+}
+
+static unsigned int genl_op_iter_idx(struct genl_op_iter *iter)
+{
+	return iter->cmd_idx;
 }
 
 static int genl_allocate_reserve_groups(int n_groups, int *first_id)
@@ -366,31 +545,72 @@ static void genl_unregister_mc_groups(const struct genl_family *family)
 	}
 }
 
+static bool genl_split_op_check(const struct genl_split_ops *op)
+{
+	if (WARN_ON(hweight8(op->flags & (GENL_CMD_CAP_DO |
+					  GENL_CMD_CAP_DUMP)) != 1))
+		return true;
+	return false;
+}
+
 static int genl_validate_ops(const struct genl_family *family)
 {
-	int i, j;
+	struct genl_op_iter i, j;
+	unsigned int s;
 
 	if (WARN_ON(family->n_ops && !family->ops) ||
-	    WARN_ON(family->n_small_ops && !family->small_ops))
+	    WARN_ON(family->n_small_ops && !family->small_ops) ||
+	    WARN_ON(family->n_split_ops && !family->split_ops))
 		return -EINVAL;
 
-	for (i = 0; i < genl_get_cmd_cnt(family); i++) {
-		struct genl_ops op;
-
-		genl_get_cmd_by_index(i, family, &op);
-		if (op.dumpit == NULL && op.doit == NULL)
+	for (genl_op_iter_init(family, &i); genl_op_iter_next(&i); ) {
+		if (!(i.flags & (GENL_CMD_CAP_DO | GENL_CMD_CAP_DUMP)))
 			return -EINVAL;
-		if (WARN_ON(op.cmd >= family->resv_start_op && op.validate))
+
+		if (WARN_ON(i.cmd >= family->resv_start_op &&
+			    (i.doit.validate || i.dumpit.validate)))
 			return -EINVAL;
-		for (j = i + 1; j < genl_get_cmd_cnt(family); j++) {
-			struct genl_ops op2;
 
-			genl_get_cmd_by_index(j, family, &op2);
-			if (op.cmd == op2.cmd)
+		genl_op_iter_copy(&j, &i);
+		while (genl_op_iter_next(&j)) {
+			if (i.cmd == j.cmd)
 				return -EINVAL;
 		}
 	}
 
+	if (family->n_split_ops) {
+		if (genl_split_op_check(&family->split_ops[0]))
+			return -EINVAL;
+	}
+
+	for (s = 1; s < family->n_split_ops; s++) {
+		const struct genl_split_ops *a, *b;
+
+		a = &family->split_ops[s - 1];
+		b = &family->split_ops[s];
+
+		if (genl_split_op_check(b))
+			return -EINVAL;
+
+		/* Check sort order */
+		if (a->cmd < b->cmd)
+			continue;
+
+		if (a->internal_flags != b->internal_flags ||
+		    ((a->flags ^ b->flags) & ~(GENL_CMD_CAP_DO |
+					       GENL_CMD_CAP_DUMP))) {
+			WARN_ON(1);
+			return -EINVAL;
+		}
+
+		if ((a->flags & GENL_CMD_CAP_DO) &&
+		    (b->flags & GENL_CMD_CAP_DUMP))
+			continue;
+
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -544,7 +764,7 @@ static struct nlattr **
 genl_family_rcv_msg_attrs_parse(const struct genl_family *family,
 				struct nlmsghdr *nlh,
 				struct netlink_ext_ack *extack,
-				const struct genl_ops *ops,
+				const struct genl_split_ops *ops,
 				int hdrlen,
 				enum genl_validate_flags no_strict_flag)
 {
@@ -580,22 +800,21 @@ struct genl_start_context {
 	const struct genl_family *family;
 	struct nlmsghdr *nlh;
 	struct netlink_ext_ack *extack;
-	const struct genl_ops *ops;
+	const struct genl_split_ops *ops;
 	int hdrlen;
 };
 
 static int genl_start(struct netlink_callback *cb)
 {
 	struct genl_start_context *ctx = cb->data;
-	const struct genl_ops *ops = ctx->ops;
+	const struct genl_split_ops *ops;
 	struct genl_dumpit_info *info;
 	struct nlattr **attrs = NULL;
 	int rc = 0;
 
-	if (ops->validate & GENL_DONT_VALIDATE_DUMP)
-		goto no_attrs;
-
-	if (ctx->nlh->nlmsg_len < nlmsg_msg_size(ctx->hdrlen))
+	ops = ctx->ops;
+	if (!(ops->validate & GENL_DONT_VALIDATE_DUMP) &&
+	    ctx->nlh->nlmsg_len < nlmsg_msg_size(ctx->hdrlen))
 		return -EINVAL;
 
 	attrs = genl_family_rcv_msg_attrs_parse(ctx->family, ctx->nlh, ctx->extack,
@@ -604,7 +823,6 @@ static int genl_start(struct netlink_callback *cb)
 	if (IS_ERR(attrs))
 		return PTR_ERR(attrs);
 
-no_attrs:
 	info = genl_dumpit_info_alloc();
 	if (!info) {
 		genl_family_rcv_msg_attrs_free(attrs);
@@ -633,7 +851,7 @@ no_attrs:
 
 static int genl_lock_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 {
-	const struct genl_ops *ops = &genl_dumpit_info(cb)->op;
+	const struct genl_split_ops *ops = &genl_dumpit_info(cb)->op;
 	int rc;
 
 	genl_lock();
@@ -645,7 +863,7 @@ static int genl_lock_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 static int genl_lock_done(struct netlink_callback *cb)
 {
 	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
-	const struct genl_ops *ops = &info->op;
+	const struct genl_split_ops *ops = &info->op;
 	int rc = 0;
 
 	if (ops->done) {
@@ -661,7 +879,7 @@ static int genl_lock_done(struct netlink_callback *cb)
 static int genl_parallel_done(struct netlink_callback *cb)
 {
 	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
-	const struct genl_ops *ops = &info->op;
+	const struct genl_split_ops *ops = &info->op;
 	int rc = 0;
 
 	if (ops->done)
@@ -675,15 +893,12 @@ static int genl_family_rcv_msg_dumpit(const struct genl_family *family,
 				      struct sk_buff *skb,
 				      struct nlmsghdr *nlh,
 				      struct netlink_ext_ack *extack,
-				      const struct genl_ops *ops,
+				      const struct genl_split_ops *ops,
 				      int hdrlen, struct net *net)
 {
 	struct genl_start_context ctx;
 	int err;
 
-	if (!ops->dumpit)
-		return -EOPNOTSUPP;
-
 	ctx.family = family;
 	ctx.nlh = nlh;
 	ctx.extack = extack;
@@ -721,16 +936,13 @@ static int genl_family_rcv_msg_doit(const struct genl_family *family,
 				    struct sk_buff *skb,
 				    struct nlmsghdr *nlh,
 				    struct netlink_ext_ack *extack,
-				    const struct genl_ops *ops,
+				    const struct genl_split_ops *ops,
 				    int hdrlen, struct net *net)
 {
 	struct nlattr **attrbuf;
 	struct genl_info info;
 	int err;
 
-	if (!ops->doit)
-		return -EOPNOTSUPP;
-
 	attrbuf = genl_family_rcv_msg_attrs_parse(family, nlh, extack,
 						  ops, hdrlen,
 						  GENL_DONT_VALIDATE_STRICT);
@@ -747,16 +959,16 @@ static int genl_family_rcv_msg_doit(const struct genl_family *family,
 	genl_info_net_set(&info, net);
 	memset(&info.user_ptr, 0, sizeof(info.user_ptr));
 
-	if (family->pre_doit) {
-		err = family->pre_doit(ops, skb, &info);
+	if (ops->pre_doit) {
+		err = ops->pre_doit(ops, skb, &info);
 		if (err)
 			goto out;
 	}
 
 	err = ops->doit(skb, &info);
 
-	if (family->post_doit)
-		family->post_doit(ops, skb, &info);
+	if (ops->post_doit)
+		ops->post_doit(ops, skb, &info);
 
 out:
 	genl_family_rcv_msg_attrs_free(attrbuf);
@@ -801,8 +1013,9 @@ static int genl_family_rcv_msg(const struct genl_family *family,
 {
 	struct net *net = sock_net(skb->sk);
 	struct genlmsghdr *hdr = nlmsg_data(nlh);
-	struct genl_ops op;
+	struct genl_split_ops op;
 	int hdrlen;
+	u8 flags;
 
 	/* this family doesn't exist in this netns */
 	if (!family->netnsok && !net_eq(net, &init_net))
@@ -815,7 +1028,9 @@ static int genl_family_rcv_msg(const struct genl_family *family,
 	if (genl_header_check(family, nlh, hdr, extack))
 		return -EINVAL;
 
-	if (genl_get_cmd(hdr->cmd, family, &op))
+	flags = (nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP ?
+		GENL_CMD_CAP_DUMP : GENL_CMD_CAP_DO;
+	if (genl_get_cmd(hdr->cmd, flags, family, &op))
 		return -EOPNOTSUPP;
 
 	if ((op.flags & GENL_ADMIN_PERM) &&
@@ -826,7 +1041,7 @@ static int genl_family_rcv_msg(const struct genl_family *family,
 	    !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
-	if ((nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP)
+	if (flags & GENL_CMD_CAP_DUMP)
 		return genl_family_rcv_msg_dumpit(family, skb, nlh, extack,
 						  &op, hdrlen, net);
 	else
@@ -871,6 +1086,7 @@ static struct genl_family genl_ctrl;
 static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq,
 			  u32 flags, struct sk_buff *skb, u8 cmd)
 {
+	struct genl_op_iter i;
 	void *hdr;
 
 	hdr = genlmsg_put(skb, portid, seq, &genl_ctrl, flags, cmd);
@@ -884,33 +1100,26 @@ static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq,
 	    nla_put_u32(skb, CTRL_ATTR_MAXATTR, family->maxattr))
 		goto nla_put_failure;
 
-	if (genl_get_cmd_cnt(family)) {
+	if (genl_op_iter_init(family, &i)) {
 		struct nlattr *nla_ops;
-		int i;
 
 		nla_ops = nla_nest_start_noflag(skb, CTRL_ATTR_OPS);
 		if (nla_ops == NULL)
 			goto nla_put_failure;
 
-		for (i = 0; i < genl_get_cmd_cnt(family); i++) {
+		while (genl_op_iter_next(&i)) {
 			struct nlattr *nest;
-			struct genl_ops op;
 			u32 op_flags;
 
-			genl_get_cmd_by_index(i, family, &op);
-			op_flags = op.flags;
-			if (op.dumpit)
-				op_flags |= GENL_CMD_CAP_DUMP;
-			if (op.doit)
-				op_flags |= GENL_CMD_CAP_DO;
-			if (op.policy)
+			op_flags = i.flags;
+			if (i.doit.policy || i.dumpit.policy)
 				op_flags |= GENL_CMD_CAP_HASPOL;
 
-			nest = nla_nest_start_noflag(skb, i + 1);
+			nest = nla_nest_start_noflag(skb, genl_op_iter_idx(&i));
 			if (nest == NULL)
 				goto nla_put_failure;
 
-			if (nla_put_u32(skb, CTRL_ATTR_OP_ID, op.cmd) ||
+			if (nla_put_u32(skb, CTRL_ATTR_OP_ID, i.cmd) ||
 			    nla_put_u32(skb, CTRL_ATTR_OP_FLAGS, op_flags))
 				goto nla_put_failure;
 
@@ -1163,10 +1372,10 @@ static int genl_ctrl_event(int event, const struct genl_family *family,
 struct ctrl_dump_policy_ctx {
 	struct netlink_policy_dump_state *state;
 	const struct genl_family *rt;
-	unsigned int opidx;
+	struct genl_op_iter *op_iter;
 	u32 op;
 	u16 fam_id;
-	u8 policies:1,
+	u8 dump_map:1,
 	   single_op:1;
 };
 
@@ -1183,8 +1392,8 @@ static int ctrl_dumppolicy_start(struct netlink_callback *cb)
 	struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx;
 	struct nlattr **tb = info->attrs;
 	const struct genl_family *rt;
-	struct genl_ops op;
-	int err, i;
+	struct genl_op_iter i;
+	int err;
 
 	BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx));
 
@@ -1208,40 +1417,73 @@ static int ctrl_dumppolicy_start(struct netlink_callback *cb)
 	ctx->rt = rt;
 
 	if (tb[CTRL_ATTR_OP]) {
+		struct genl_split_ops doit, dump;
+
 		ctx->single_op = true;
 		ctx->op = nla_get_u32(tb[CTRL_ATTR_OP]);
 
-		err = genl_get_cmd(ctx->op, rt, &op);
+		err = genl_get_cmd_both(ctx->op, rt, &doit, &dump);
 		if (err) {
 			NL_SET_BAD_ATTR(cb->extack, tb[CTRL_ATTR_OP]);
 			return err;
 		}
 
-		if (!op.policy)
+		if (doit.policy) {
+			err = netlink_policy_dump_add_policy(&ctx->state,
+							     doit.policy,
+							     doit.maxattr);
+			if (err)
+				goto err_free_state;
+		}
+		if (dump.policy) {
+			err = netlink_policy_dump_add_policy(&ctx->state,
+							     dump.policy,
+							     dump.maxattr);
+			if (err)
+				goto err_free_state;
+		}
+
+		if (!ctx->state)
 			return -ENODATA;
 
-		return netlink_policy_dump_add_policy(&ctx->state, op.policy,
-						      op.maxattr);
+		ctx->dump_map = 1;
+		return 0;
 	}
 
-	for (i = 0; i < genl_get_cmd_cnt(rt); i++) {
-		genl_get_cmd_by_index(i, rt, &op);
+	ctx->op_iter = kmalloc(sizeof(*ctx->op_iter), GFP_KERNEL);
+	if (!ctx->op_iter)
+		return -ENOMEM;
 
-		if (op.policy) {
+	genl_op_iter_init(rt, ctx->op_iter);
+	ctx->dump_map = genl_op_iter_next(ctx->op_iter);
+
+	for (genl_op_iter_init(rt, &i); genl_op_iter_next(&i); ) {
+		if (i.doit.policy) {
 			err = netlink_policy_dump_add_policy(&ctx->state,
-							     op.policy,
-							     op.maxattr);
+							     i.doit.policy,
+							     i.doit.maxattr);
+			if (err)
+				goto err_free_state;
+		}
+		if (i.dumpit.policy) {
+			err = netlink_policy_dump_add_policy(&ctx->state,
+							     i.dumpit.policy,
+							     i.dumpit.maxattr);
 			if (err)
 				goto err_free_state;
 		}
 	}
 
-	if (!ctx->state)
-		return -ENODATA;
+	if (!ctx->state) {
+		err = -ENODATA;
+		goto err_free_op_iter;
+	}
 	return 0;
 
 err_free_state:
 	netlink_policy_dump_free(ctx->state);
+err_free_op_iter:
+	kfree(ctx->op_iter);
 	return err;
 }
 
@@ -1265,7 +1507,8 @@ static void *ctrl_dumppolicy_prep(struct sk_buff *skb,
 
 static int ctrl_dumppolicy_put_op(struct sk_buff *skb,
 				  struct netlink_callback *cb,
-			          struct genl_ops *op)
+				  struct genl_split_ops *doit,
+				  struct genl_split_ops *dumpit)
 {
 	struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx;
 	struct nlattr *nest_pol, *nest_op;
@@ -1273,10 +1516,7 @@ static int ctrl_dumppolicy_put_op(struct sk_buff *skb,
 	int idx;
 
 	/* skip if we have nothing to show */
-	if (!op->policy)
-		return 0;
-	if (!op->doit &&
-	    (!op->dumpit || op->validate & GENL_DONT_VALIDATE_DUMP))
+	if (!doit->policy && !dumpit->policy)
 		return 0;
 
 	hdr = ctrl_dumppolicy_prep(skb, cb);
@@ -1287,21 +1527,26 @@ static int ctrl_dumppolicy_put_op(struct sk_buff *skb,
 	if (!nest_pol)
 		goto err;
 
-	nest_op = nla_nest_start(skb, op->cmd);
+	nest_op = nla_nest_start(skb, doit->cmd);
 	if (!nest_op)
 		goto err;
 
-	/* for now both do/dump are always the same */
-	idx = netlink_policy_dump_get_policy_idx(ctx->state,
-						 op->policy,
-						 op->maxattr);
+	if (doit->policy) {
+		idx = netlink_policy_dump_get_policy_idx(ctx->state,
+							 doit->policy,
+							 doit->maxattr);
 
-	if (op->doit && nla_put_u32(skb, CTRL_ATTR_POLICY_DO, idx))
-		goto err;
+		if (nla_put_u32(skb, CTRL_ATTR_POLICY_DO, idx))
+			goto err;
+	}
+	if (dumpit->policy) {
+		idx = netlink_policy_dump_get_policy_idx(ctx->state,
+							 dumpit->policy,
+							 dumpit->maxattr);
 
-	if (op->dumpit && !(op->validate & GENL_DONT_VALIDATE_DUMP) &&
-	    nla_put_u32(skb, CTRL_ATTR_POLICY_DUMP, idx))
-		goto err;
+		if (nla_put_u32(skb, CTRL_ATTR_POLICY_DUMP, idx))
+			goto err;
+	}
 
 	nla_nest_end(skb, nest_op);
 	nla_nest_end(skb, nest_pol);
@@ -1318,31 +1563,29 @@ static int ctrl_dumppolicy(struct sk_buff *skb, struct netlink_callback *cb)
 	struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx;
 	void *hdr;
 
-	if (!ctx->policies) {
-		while (ctx->opidx < genl_get_cmd_cnt(ctx->rt)) {
-			struct genl_ops op;
+	if (ctx->dump_map) {
+		if (ctx->single_op) {
+			struct genl_split_ops doit, dumpit;
 
-			if (ctx->single_op) {
-				int err;
+			if (WARN_ON(genl_get_cmd_both(ctx->op, ctx->rt,
+						      &doit, &dumpit)))
+				return -ENOENT;
 
-				err = genl_get_cmd(ctx->op, ctx->rt, &op);
-				if (WARN_ON(err))
-					return skb->len;
+			if (ctrl_dumppolicy_put_op(skb, cb, &doit, &dumpit))
+				return skb->len;
 
-				/* break out of the loop after this one */
-				ctx->opidx = genl_get_cmd_cnt(ctx->rt);
-			} else {
-				genl_get_cmd_by_index(ctx->opidx, ctx->rt, &op);
-			}
+			/* done with the per-op policy index list */
+			ctx->dump_map = 0;
+		}
 
-			if (ctrl_dumppolicy_put_op(skb, cb, &op))
+		while (ctx->dump_map) {
+			if (ctrl_dumppolicy_put_op(skb, cb,
+						   &ctx->op_iter->doit,
+						   &ctx->op_iter->dumpit))
 				return skb->len;
 
-			ctx->opidx++;
+			ctx->dump_map = genl_op_iter_next(ctx->op_iter);
 		}
-
-		/* completed with the per-op policy index list */
-		ctx->policies = true;
 	}
 
 	while (netlink_policy_dump_loop(ctx->state)) {
@@ -1375,18 +1618,27 @@ static int ctrl_dumppolicy_done(struct netlink_callback *cb)
 {
 	struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx;
 
+	kfree(ctx->op_iter);
 	netlink_policy_dump_free(ctx->state);
 	return 0;
 }
 
-static const struct genl_ops genl_ctrl_ops[] = {
+static const struct genl_split_ops genl_ctrl_ops[] = {
 	{
 		.cmd		= CTRL_CMD_GETFAMILY,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
 		.policy		= ctrl_policy_family,
 		.maxattr	= ARRAY_SIZE(ctrl_policy_family) - 1,
 		.doit		= ctrl_getfamily,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= CTRL_CMD_GETFAMILY,
+		.validate	= GENL_DONT_VALIDATE_DUMP,
+		.policy		= ctrl_policy_family,
+		.maxattr	= ARRAY_SIZE(ctrl_policy_family) - 1,
 		.dumpit		= ctrl_dumpfamily,
+		.flags		= GENL_CMD_CAP_DUMP,
 	},
 	{
 		.cmd		= CTRL_CMD_GETPOLICY,
@@ -1395,6 +1647,7 @@ static const struct genl_ops genl_ctrl_ops[] = {
 		.start		= ctrl_dumppolicy_start,
 		.dumpit		= ctrl_dumppolicy,
 		.done		= ctrl_dumppolicy_done,
+		.flags		= GENL_CMD_CAP_DUMP,
 	},
 };
 
@@ -1404,8 +1657,8 @@ static const struct genl_multicast_group genl_ctrl_groups[] = {
 
 static struct genl_family genl_ctrl __ro_after_init = {
 	.module = THIS_MODULE,
-	.ops = genl_ctrl_ops,
-	.n_ops = ARRAY_SIZE(genl_ctrl_ops),
+	.split_ops = genl_ctrl_ops,
+	.n_split_ops = ARRAY_SIZE(genl_ctrl_ops),
 	.resv_start_op = CTRL_CMD_GETPOLICY + 1,
 	.mcgrps = genl_ctrl_groups,
 	.n_mcgrps = ARRAY_SIZE(genl_ctrl_groups),