Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 550 insertions, 0 deletions

diff --git a/net/sched/ematch.c b/net/sched/ematch.c
new file mode 100644
index 000000000..5c1235e60
--- /dev/null
+++ b/net/sched/ematch.c
@@ -0,0 +1,550 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * net/sched/ematch.c		Extended Match API
+ *
+ * Authors:	Thomas Graf <tgraf@suug.ch>
+ *
+ * ==========================================================================
+ *
+ * An extended match (ematch) is a small classification tool not worth
+ * writing a full classifier for. Ematches can be interconnected to form
+ * a logic expression and get attached to classifiers to extend their
+ * functionatlity.
+ *
+ * The userspace part transforms the logic expressions into an array
+ * consisting of multiple sequences of interconnected ematches separated
+ * by markers. Precedence is implemented by a special ematch kind
+ * referencing a sequence beyond the marker of the current sequence
+ * causing the current position in the sequence to be pushed onto a stack
+ * to allow the current position to be overwritten by the position referenced
+ * in the special ematch. Matching continues in the new sequence until a
+ * marker is reached causing the position to be restored from the stack.
+ *
+ * Example:
+ *          A AND (B1 OR B2) AND C AND D
+ *
+ *              ------->-PUSH-------
+ *    -->--    /         -->--      \   -->--
+ *   /     \  /         /     \      \ /     \
+ * +-------+-------+-------+-------+-------+--------+
+ * | A AND | B AND | C AND | D END | B1 OR | B2 END |
+ * +-------+-------+-------+-------+-------+--------+
+ *                    \                      /
+ *                     --------<-POP---------
+ *
+ * where B is a virtual ematch referencing to sequence starting with B1.
+ *
+ * ==========================================================================
+ *
+ * How to write an ematch in 60 seconds
+ * ------------------------------------
+ *
+ *   1) Provide a matcher function:
+ *      static int my_match(struct sk_buff *skb, struct tcf_ematch *m,
+ *                          struct tcf_pkt_info *info)
+ *      {
+ *      	struct mydata *d = (struct mydata *) m->data;
+ *
+ *      	if (...matching goes here...)
+ *      		return 1;
+ *      	else
+ *      		return 0;
+ *      }
+ *
+ *   2) Fill out a struct tcf_ematch_ops:
+ *      static struct tcf_ematch_ops my_ops = {
+ *      	.kind = unique id,
+ *      	.datalen = sizeof(struct mydata),
+ *      	.match = my_match,
+ *      	.owner = THIS_MODULE,
+ *      };
+ *
+ *   3) Register/Unregister your ematch:
+ *      static int __init init_my_ematch(void)
+ *      {
+ *      	return tcf_em_register(&my_ops);
+ *      }
+ *
+ *      static void __exit exit_my_ematch(void)
+ *      {
+ *      	tcf_em_unregister(&my_ops);
+ *      }
+ *
+ *      module_init(init_my_ematch);
+ *      module_exit(exit_my_ematch);
+ *
+ *   4) By now you should have two more seconds left, barely enough to
+ *      open up a beer to watch the compilation going.
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/rtnetlink.h>
+#include <linux/skbuff.h>
+#include <net/pkt_cls.h>
+
+static LIST_HEAD(ematch_ops);
+static DEFINE_RWLOCK(ematch_mod_lock);
+
+static struct tcf_ematch_ops *tcf_em_lookup(u16 kind)
+{
+	struct tcf_ematch_ops *e = NULL;
+
+	read_lock(&ematch_mod_lock);
+	list_for_each_entry(e, &ematch_ops, link) {
+		if (kind == e->kind) {
+			if (!try_module_get(e->owner))
+				e = NULL;
+			read_unlock(&ematch_mod_lock);
+			return e;
+		}
+	}
+	read_unlock(&ematch_mod_lock);
+
+	return NULL;
+}
+
+/**
+ * tcf_em_register - register an extended match
+ *
+ * @ops: ematch operations lookup table
+ *
+ * This function must be called by ematches to announce their presence.
+ * The given @ops must have kind set to a unique identifier and the
+ * callback match() must be implemented. All other callbacks are optional
+ * and a fallback implementation is used instead.
+ *
+ * Returns -EEXISTS if an ematch of the same kind has already registered.
+ */
+int tcf_em_register(struct tcf_ematch_ops *ops)
+{
+	int err = -EEXIST;
+	struct tcf_ematch_ops *e;
+
+	if (ops->match == NULL)
+		return -EINVAL;
+
+	write_lock(&ematch_mod_lock);
+	list_for_each_entry(e, &ematch_ops, link)
+		if (ops->kind == e->kind)
+			goto errout;
+
+	list_add_tail(&ops->link, &ematch_ops);
+	err = 0;
+errout:
+	write_unlock(&ematch_mod_lock);
+	return err;
+}
+EXPORT_SYMBOL(tcf_em_register);
+
+/**
+ * tcf_em_unregister - unregister and extended match
+ *
+ * @ops: ematch operations lookup table
+ *
+ * This function must be called by ematches to announce their disappearance
+ * for examples when the module gets unloaded. The @ops parameter must be
+ * the same as the one used for registration.
+ *
+ * Returns -ENOENT if no matching ematch was found.
+ */
+void tcf_em_unregister(struct tcf_ematch_ops *ops)
+{
+	write_lock(&ematch_mod_lock);
+	list_del(&ops->link);
+	write_unlock(&ematch_mod_lock);
+}
+EXPORT_SYMBOL(tcf_em_unregister);
+
+static inline struct tcf_ematch *tcf_em_get_match(struct tcf_ematch_tree *tree,
+						  int index)
+{
+	return &tree->matches[index];
+}
+
+
+static int tcf_em_validate(struct tcf_proto *tp,
+			   struct tcf_ematch_tree_hdr *tree_hdr,
+			   struct tcf_ematch *em, struct nlattr *nla, int idx)
+{
+	int err = -EINVAL;
+	struct tcf_ematch_hdr *em_hdr = nla_data(nla);
+	int data_len = nla_len(nla) - sizeof(*em_hdr);
+	void *data = (void *) em_hdr + sizeof(*em_hdr);
+	struct net *net = tp->chain->block->net;
+
+	if (!TCF_EM_REL_VALID(em_hdr->flags))
+		goto errout;
+
+	if (em_hdr->kind == TCF_EM_CONTAINER) {
+		/* Special ematch called "container", carries an index
+		 * referencing an external ematch sequence.
+		 */
+		u32 ref;
+
+		if (data_len < sizeof(ref))
+			goto errout;
+		ref = *(u32 *) data;
+
+		if (ref >= tree_hdr->nmatches)
+			goto errout;
+
+		/* We do not allow backward jumps to avoid loops and jumps
+		 * to our own position are of course illegal.
+		 */
+		if (ref <= idx)
+			goto errout;
+
+
+		em->data = ref;
+	} else {
+		/* Note: This lookup will increase the module refcnt
+		 * of the ematch module referenced. In case of a failure,
+		 * a destroy function is called by the underlying layer
+		 * which automatically releases the reference again, therefore
+		 * the module MUST not be given back under any circumstances
+		 * here. Be aware, the destroy function assumes that the
+		 * module is held if the ops field is non zero.
+		 */
+		em->ops = tcf_em_lookup(em_hdr->kind);
+
+		if (em->ops == NULL) {
+			err = -ENOENT;
+#ifdef CONFIG_MODULES
+			__rtnl_unlock();
+			request_module("ematch-kind-%u", em_hdr->kind);
+			rtnl_lock();
+			em->ops = tcf_em_lookup(em_hdr->kind);
+			if (em->ops) {
+				/* We dropped the RTNL mutex in order to
+				 * perform the module load. Tell the caller
+				 * to replay the request.
+				 */
+				module_put(em->ops->owner);
+				em->ops = NULL;
+				err = -EAGAIN;
+			}
+#endif
+			goto errout;
+		}
+
+		/* ematch module provides expected length of data, so we
+		 * can do a basic sanity check.
+		 */
+		if (em->ops->datalen && data_len < em->ops->datalen)
+			goto errout;
+
+		if (em->ops->change) {
+			err = -EINVAL;
+			if (em_hdr->flags & TCF_EM_SIMPLE)
+				goto errout;
+			err = em->ops->change(net, data, data_len, em);
+			if (err < 0)
+				goto errout;
+		} else if (data_len > 0) {
+			/* ematch module doesn't provide an own change
+			 * procedure and expects us to allocate and copy
+			 * the ematch data.
+			 *
+			 * TCF_EM_SIMPLE may be specified stating that the
+			 * data only consists of a u32 integer and the module
+			 * does not expected a memory reference but rather
+			 * the value carried.
+			 */
+			if (em_hdr->flags & TCF_EM_SIMPLE) {
+				if (em->ops->datalen > 0)
+					goto errout;
+				if (data_len < sizeof(u32))
+					goto errout;
+				em->data = *(u32 *) data;
+			} else {
+				void *v = kmemdup(data, data_len, GFP_KERNEL);
+				if (v == NULL) {
+					err = -ENOBUFS;
+					goto errout;
+				}
+				em->data = (unsigned long) v;
+			}
+			em->datalen = data_len;
+		}
+	}
+
+	em->matchid = em_hdr->matchid;
+	em->flags = em_hdr->flags;
+	em->net = net;
+
+	err = 0;
+errout:
+	return err;
+}
+
+static const struct nla_policy em_policy[TCA_EMATCH_TREE_MAX + 1] = {
+	[TCA_EMATCH_TREE_HDR]	= { .len = sizeof(struct tcf_ematch_tree_hdr) },
+	[TCA_EMATCH_TREE_LIST]	= { .type = NLA_NESTED },
+};
+
+/**
+ * tcf_em_tree_validate - validate ematch config TLV and build ematch tree
+ *
+ * @tp: classifier kind handle
+ * @nla: ematch tree configuration TLV
+ * @tree: destination ematch tree variable to store the resulting
+ *        ematch tree.
+ *
+ * This function validates the given configuration TLV @nla and builds an
+ * ematch tree in @tree. The resulting tree must later be copied into
+ * the private classifier data using tcf_em_tree_change(). You MUST NOT
+ * provide the ematch tree variable of the private classifier data directly,
+ * the changes would not be locked properly.
+ *
+ * Returns a negative error code if the configuration TLV contains errors.
+ */
+int tcf_em_tree_validate(struct tcf_proto *tp, struct nlattr *nla,
+			 struct tcf_ematch_tree *tree)
+{
+	int idx, list_len, matches_len, err;
+	struct nlattr *tb[TCA_EMATCH_TREE_MAX + 1];
+	struct nlattr *rt_match, *rt_hdr, *rt_list;
+	struct tcf_ematch_tree_hdr *tree_hdr;
+	struct tcf_ematch *em;
+
+	memset(tree, 0, sizeof(*tree));
+	if (!nla)
+		return 0;
+
+	err = nla_parse_nested_deprecated(tb, TCA_EMATCH_TREE_MAX, nla,
+					  em_policy, NULL);
+	if (err < 0)
+		goto errout;
+
+	err = -EINVAL;
+	rt_hdr = tb[TCA_EMATCH_TREE_HDR];
+	rt_list = tb[TCA_EMATCH_TREE_LIST];
+
+	if (rt_hdr == NULL || rt_list == NULL)
+		goto errout;
+
+	tree_hdr = nla_data(rt_hdr);
+	memcpy(&tree->hdr, tree_hdr, sizeof(*tree_hdr));
+
+	rt_match = nla_data(rt_list);
+	list_len = nla_len(rt_list);
+	matches_len = tree_hdr->nmatches * sizeof(*em);
+
+	tree->matches = kzalloc(matches_len, GFP_KERNEL);
+	if (tree->matches == NULL)
+		goto errout;
+
+	/* We do not use nla_parse_nested here because the maximum
+	 * number of attributes is unknown. This saves us the allocation
+	 * for a tb buffer which would serve no purpose at all.
+	 *
+	 * The array of rt attributes is parsed in the order as they are
+	 * provided, their type must be incremental from 1 to n. Even
+	 * if it does not serve any real purpose, a failure of sticking
+	 * to this policy will result in parsing failure.
+	 */
+	for (idx = 0; nla_ok(rt_match, list_len); idx++) {
+		err = -EINVAL;
+
+		if (rt_match->nla_type != (idx + 1))
+			goto errout_abort;
+
+		if (idx >= tree_hdr->nmatches)
+			goto errout_abort;
+
+		if (nla_len(rt_match) < sizeof(struct tcf_ematch_hdr))
+			goto errout_abort;
+
+		em = tcf_em_get_match(tree, idx);
+
+		err = tcf_em_validate(tp, tree_hdr, em, rt_match, idx);
+		if (err < 0)
+			goto errout_abort;
+
+		rt_match = nla_next(rt_match, &list_len);
+	}
+
+	/* Check if the number of matches provided by userspace actually
+	 * complies with the array of matches. The number was used for
+	 * the validation of references and a mismatch could lead to
+	 * undefined references during the matching process.
+	 */
+	if (idx != tree_hdr->nmatches) {
+		err = -EINVAL;
+		goto errout_abort;
+	}
+
+	err = 0;
+errout:
+	return err;
+
+errout_abort:
+	tcf_em_tree_destroy(tree);
+	return err;
+}
+EXPORT_SYMBOL(tcf_em_tree_validate);
+
+/**
+ * tcf_em_tree_destroy - destroy an ematch tree
+ *
+ * @tree: ematch tree to be deleted
+ *
+ * This functions destroys an ematch tree previously created by
+ * tcf_em_tree_validate()/tcf_em_tree_change(). You must ensure that
+ * the ematch tree is not in use before calling this function.
+ */
+void tcf_em_tree_destroy(struct tcf_ematch_tree *tree)
+{
+	int i;
+
+	if (tree->matches == NULL)
+		return;
+
+	for (i = 0; i < tree->hdr.nmatches; i++) {
+		struct tcf_ematch *em = tcf_em_get_match(tree, i);
+
+		if (em->ops) {
+			if (em->ops->destroy)
+				em->ops->destroy(em);
+			else if (!tcf_em_is_simple(em))
+				kfree((void *) em->data);
+			module_put(em->ops->owner);
+		}
+	}
+
+	tree->hdr.nmatches = 0;
+	kfree(tree->matches);
+	tree->matches = NULL;
+}
+EXPORT_SYMBOL(tcf_em_tree_destroy);
+
+/**
+ * tcf_em_tree_dump - dump ematch tree into a rtnl message
+ *
+ * @skb: skb holding the rtnl message
+ * @tree: ematch tree to be dumped
+ * @tlv: TLV type to be used to encapsulate the tree
+ *
+ * This function dumps a ematch tree into a rtnl message. It is valid to
+ * call this function while the ematch tree is in use.
+ *
+ * Returns -1 if the skb tailroom is insufficient.
+ */
+int tcf_em_tree_dump(struct sk_buff *skb, struct tcf_ematch_tree *tree, int tlv)
+{
+	int i;
+	u8 *tail;
+	struct nlattr *top_start;
+	struct nlattr *list_start;
+
+	top_start = nla_nest_start_noflag(skb, tlv);
+	if (top_start == NULL)
+		goto nla_put_failure;
+
+	if (nla_put(skb, TCA_EMATCH_TREE_HDR, sizeof(tree->hdr), &tree->hdr))
+		goto nla_put_failure;
+
+	list_start = nla_nest_start_noflag(skb, TCA_EMATCH_TREE_LIST);
+	if (list_start == NULL)
+		goto nla_put_failure;
+
+	tail = skb_tail_pointer(skb);
+	for (i = 0; i < tree->hdr.nmatches; i++) {
+		struct nlattr *match_start = (struct nlattr *)tail;
+		struct tcf_ematch *em = tcf_em_get_match(tree, i);
+		struct tcf_ematch_hdr em_hdr = {
+			.kind = em->ops ? em->ops->kind : TCF_EM_CONTAINER,
+			.matchid = em->matchid,
+			.flags = em->flags
+		};
+
+		if (nla_put(skb, i + 1, sizeof(em_hdr), &em_hdr))
+			goto nla_put_failure;
+
+		if (em->ops && em->ops->dump) {
+			if (em->ops->dump(skb, em) < 0)
+				goto nla_put_failure;
+		} else if (tcf_em_is_container(em) || tcf_em_is_simple(em)) {
+			u32 u = em->data;
+			nla_put_nohdr(skb, sizeof(u), &u);
+		} else if (em->datalen > 0)
+			nla_put_nohdr(skb, em->datalen, (void *) em->data);
+
+		tail = skb_tail_pointer(skb);
+		match_start->nla_len = tail - (u8 *)match_start;
+	}
+
+	nla_nest_end(skb, list_start);
+	nla_nest_end(skb, top_start);
+
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+EXPORT_SYMBOL(tcf_em_tree_dump);
+
+static inline int tcf_em_match(struct sk_buff *skb, struct tcf_ematch *em,
+			       struct tcf_pkt_info *info)
+{
+	int r = em->ops->match(skb, em, info);
+
+	return tcf_em_is_inverted(em) ? !r : r;
+}
+
+/* Do not use this function directly, use tcf_em_tree_match instead */
+int __tcf_em_tree_match(struct sk_buff *skb, struct tcf_ematch_tree *tree,
+			struct tcf_pkt_info *info)
+{
+	int stackp = 0, match_idx = 0, res = 0;
+	struct tcf_ematch *cur_match;
+	int stack[CONFIG_NET_EMATCH_STACK];
+
+proceed:
+	while (match_idx < tree->hdr.nmatches) {
+		cur_match = tcf_em_get_match(tree, match_idx);
+
+		if (tcf_em_is_container(cur_match)) {
+			if (unlikely(stackp >= CONFIG_NET_EMATCH_STACK))
+				goto stack_overflow;
+
+			stack[stackp++] = match_idx;
+			match_idx = cur_match->data;
+			goto proceed;
+		}
+
+		res = tcf_em_match(skb, cur_match, info);
+
+		if (tcf_em_early_end(cur_match, res))
+			break;
+
+		match_idx++;
+	}
+
+pop_stack:
+	if (stackp > 0) {
+		match_idx = stack[--stackp];
+		cur_match = tcf_em_get_match(tree, match_idx);
+
+		if (tcf_em_is_inverted(cur_match))
+			res = !res;
+
+		if (tcf_em_early_end(cur_match, res)) {
+			goto pop_stack;
+		} else {
+			match_idx++;
+			goto proceed;
+		}
+	}
+
+	return res;
+
+stack_overflow:
+	net_warn_ratelimited("tc ematch: local stack overflow, increase NET_EMATCH_STACK\n");
+	return -1;
+}
+EXPORT_SYMBOL(__tcf_em_tree_match);