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, 620 insertions, 0 deletions

diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
new file mode 100644
index 000000000..77d288d38
--- /dev/null
+++ b/net/sched/act_pedit.c
@@ -0,0 +1,620 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * net/sched/act_pedit.c	Generic packet editor
+ *
+ * Authors:	Jamal Hadi Salim (2002-4)
+ */
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/skbuff.h>
+#include <linux/rtnetlink.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <net/netlink.h>
+#include <net/pkt_sched.h>
+#include <linux/tc_act/tc_pedit.h>
+#include <net/tc_act/tc_pedit.h>
+#include <uapi/linux/tc_act/tc_pedit.h>
+#include <net/pkt_cls.h>
+#include <net/tc_wrapper.h>
+
+static struct tc_action_ops act_pedit_ops;
+
+static const struct nla_policy pedit_policy[TCA_PEDIT_MAX + 1] = {
+	[TCA_PEDIT_PARMS]	= { .len = sizeof(struct tc_pedit) },
+	[TCA_PEDIT_KEYS_EX]   = { .type = NLA_NESTED },
+};
+
+static const struct nla_policy pedit_key_ex_policy[TCA_PEDIT_KEY_EX_MAX + 1] = {
+	[TCA_PEDIT_KEY_EX_HTYPE]  = { .type = NLA_U16 },
+	[TCA_PEDIT_KEY_EX_CMD]	  = { .type = NLA_U16 },
+};
+
+static struct tcf_pedit_key_ex *tcf_pedit_keys_ex_parse(struct nlattr *nla,
+							u8 n)
+{
+	struct tcf_pedit_key_ex *keys_ex;
+	struct tcf_pedit_key_ex *k;
+	const struct nlattr *ka;
+	int err = -EINVAL;
+	int rem;
+
+	if (!nla)
+		return NULL;
+
+	keys_ex = kcalloc(n, sizeof(*k), GFP_KERNEL);
+	if (!keys_ex)
+		return ERR_PTR(-ENOMEM);
+
+	k = keys_ex;
+
+	nla_for_each_nested(ka, nla, rem) {
+		struct nlattr *tb[TCA_PEDIT_KEY_EX_MAX + 1];
+
+		if (!n) {
+			err = -EINVAL;
+			goto err_out;
+		}
+		n--;
+
+		if (nla_type(ka) != TCA_PEDIT_KEY_EX) {
+			err = -EINVAL;
+			goto err_out;
+		}
+
+		err = nla_parse_nested_deprecated(tb, TCA_PEDIT_KEY_EX_MAX,
+						  ka, pedit_key_ex_policy,
+						  NULL);
+		if (err)
+			goto err_out;
+
+		if (!tb[TCA_PEDIT_KEY_EX_HTYPE] ||
+		    !tb[TCA_PEDIT_KEY_EX_CMD]) {
+			err = -EINVAL;
+			goto err_out;
+		}
+
+		k->htype = nla_get_u16(tb[TCA_PEDIT_KEY_EX_HTYPE]);
+		k->cmd = nla_get_u16(tb[TCA_PEDIT_KEY_EX_CMD]);
+
+		if (k->htype > TCA_PEDIT_HDR_TYPE_MAX ||
+		    k->cmd > TCA_PEDIT_CMD_MAX) {
+			err = -EINVAL;
+			goto err_out;
+		}
+
+		k++;
+	}
+
+	if (n) {
+		err = -EINVAL;
+		goto err_out;
+	}
+
+	return keys_ex;
+
+err_out:
+	kfree(keys_ex);
+	return ERR_PTR(err);
+}
+
+static int tcf_pedit_key_ex_dump(struct sk_buff *skb,
+				 struct tcf_pedit_key_ex *keys_ex, int n)
+{
+	struct nlattr *keys_start = nla_nest_start_noflag(skb,
+							  TCA_PEDIT_KEYS_EX);
+
+	if (!keys_start)
+		goto nla_failure;
+	for (; n > 0; n--) {
+		struct nlattr *key_start;
+
+		key_start = nla_nest_start_noflag(skb, TCA_PEDIT_KEY_EX);
+		if (!key_start)
+			goto nla_failure;
+
+		if (nla_put_u16(skb, TCA_PEDIT_KEY_EX_HTYPE, keys_ex->htype) ||
+		    nla_put_u16(skb, TCA_PEDIT_KEY_EX_CMD, keys_ex->cmd))
+			goto nla_failure;
+
+		nla_nest_end(skb, key_start);
+
+		keys_ex++;
+	}
+
+	nla_nest_end(skb, keys_start);
+
+	return 0;
+nla_failure:
+	nla_nest_cancel(skb, keys_start);
+	return -EINVAL;
+}
+
+static void tcf_pedit_cleanup_rcu(struct rcu_head *head)
+{
+	struct tcf_pedit_parms *parms =
+		container_of(head, struct tcf_pedit_parms, rcu);
+
+	kfree(parms->tcfp_keys_ex);
+	kfree(parms->tcfp_keys);
+
+	kfree(parms);
+}
+
+static int tcf_pedit_init(struct net *net, struct nlattr *nla,
+			  struct nlattr *est, struct tc_action **a,
+			  struct tcf_proto *tp, u32 flags,
+			  struct netlink_ext_ack *extack)
+{
+	struct tc_action_net *tn = net_generic(net, act_pedit_ops.net_id);
+	bool bind = flags & TCA_ACT_FLAGS_BIND;
+	struct tcf_chain *goto_ch = NULL;
+	struct tcf_pedit_parms *oparms, *nparms;
+	struct nlattr *tb[TCA_PEDIT_MAX + 1];
+	struct tc_pedit *parm;
+	struct nlattr *pattr;
+	struct tcf_pedit *p;
+	int ret = 0, err;
+	int i, ksize;
+	u32 index;
+
+	if (!nla) {
+		NL_SET_ERR_MSG_MOD(extack, "Pedit requires attributes to be passed");
+		return -EINVAL;
+	}
+
+	err = nla_parse_nested_deprecated(tb, TCA_PEDIT_MAX, nla,
+					  pedit_policy, NULL);
+	if (err < 0)
+		return err;
+
+	pattr = tb[TCA_PEDIT_PARMS];
+	if (!pattr)
+		pattr = tb[TCA_PEDIT_PARMS_EX];
+	if (!pattr) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing required TCA_PEDIT_PARMS or TCA_PEDIT_PARMS_EX pedit attribute");
+		return -EINVAL;
+	}
+
+	parm = nla_data(pattr);
+	if (!parm->nkeys) {
+		NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed");
+		return -EINVAL;
+	}
+	ksize = parm->nkeys * sizeof(struct tc_pedit_key);
+	if (nla_len(pattr) < sizeof(*parm) + ksize) {
+		NL_SET_ERR_MSG_ATTR(extack, pattr, "Length of TCA_PEDIT_PARMS or TCA_PEDIT_PARMS_EX pedit attribute is invalid");
+		return -EINVAL;
+	}
+
+	nparms = kzalloc(sizeof(*nparms), GFP_KERNEL);
+	if (!nparms)
+		return -ENOMEM;
+
+	nparms->tcfp_keys_ex =
+		tcf_pedit_keys_ex_parse(tb[TCA_PEDIT_KEYS_EX], parm->nkeys);
+	if (IS_ERR(nparms->tcfp_keys_ex)) {
+		ret = PTR_ERR(nparms->tcfp_keys_ex);
+		goto out_free;
+	}
+
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
+	if (!err) {
+		ret = tcf_idr_create_from_flags(tn, index, est, a,
+						&act_pedit_ops, bind, flags);
+		if (ret) {
+			tcf_idr_cleanup(tn, index);
+			goto out_free_ex;
+		}
+		ret = ACT_P_CREATED;
+	} else if (err > 0) {
+		if (bind)
+			goto out_free;
+		if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
+			ret = -EEXIST;
+			goto out_release;
+		}
+	} else {
+		ret = err;
+		goto out_free_ex;
+	}
+
+	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
+	if (err < 0) {
+		ret = err;
+		goto out_release;
+	}
+
+	nparms->tcfp_off_max_hint = 0;
+	nparms->tcfp_flags = parm->flags;
+	nparms->tcfp_nkeys = parm->nkeys;
+
+	nparms->tcfp_keys = kmalloc(ksize, GFP_KERNEL);
+	if (!nparms->tcfp_keys) {
+		ret = -ENOMEM;
+		goto put_chain;
+	}
+
+	memcpy(nparms->tcfp_keys, parm->keys, ksize);
+
+	for (i = 0; i < nparms->tcfp_nkeys; ++i) {
+		u32 cur = nparms->tcfp_keys[i].off;
+
+		/* sanitize the shift value for any later use */
+		nparms->tcfp_keys[i].shift = min_t(size_t,
+						   BITS_PER_TYPE(int) - 1,
+						   nparms->tcfp_keys[i].shift);
+
+		/* The AT option can read a single byte, we can bound the actual
+		 * value with uchar max.
+		 */
+		cur += (0xff & nparms->tcfp_keys[i].offmask) >> nparms->tcfp_keys[i].shift;
+
+		/* Each key touches 4 bytes starting from the computed offset */
+		nparms->tcfp_off_max_hint =
+			max(nparms->tcfp_off_max_hint, cur + 4);
+	}
+
+	p = to_pedit(*a);
+
+	spin_lock_bh(&p->tcf_lock);
+	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
+	oparms = rcu_replace_pointer(p->parms, nparms, 1);
+	spin_unlock_bh(&p->tcf_lock);
+
+	if (oparms)
+		call_rcu(&oparms->rcu, tcf_pedit_cleanup_rcu);
+
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
+
+	return ret;
+
+put_chain:
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
+out_release:
+	tcf_idr_release(*a, bind);
+out_free_ex:
+	kfree(nparms->tcfp_keys_ex);
+out_free:
+	kfree(nparms);
+	return ret;
+}
+
+static void tcf_pedit_cleanup(struct tc_action *a)
+{
+	struct tcf_pedit *p = to_pedit(a);
+	struct tcf_pedit_parms *parms;
+
+	parms = rcu_dereference_protected(p->parms, 1);
+
+	if (parms)
+		call_rcu(&parms->rcu, tcf_pedit_cleanup_rcu);
+}
+
+static bool offset_valid(struct sk_buff *skb, int offset)
+{
+	if (offset > 0 && offset > skb->len)
+		return false;
+
+	if  (offset < 0 && -offset > skb_headroom(skb))
+		return false;
+
+	return true;
+}
+
+static int pedit_skb_hdr_offset(struct sk_buff *skb,
+				enum pedit_header_type htype, int *hoffset)
+{
+	int ret = -EINVAL;
+
+	switch (htype) {
+	case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH:
+		if (skb_mac_header_was_set(skb)) {
+			*hoffset = skb_mac_offset(skb);
+			ret = 0;
+		}
+		break;
+	case TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK:
+	case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4:
+	case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6:
+		*hoffset = skb_network_offset(skb);
+		ret = 0;
+		break;
+	case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP:
+	case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP:
+		if (skb_transport_header_was_set(skb)) {
+			*hoffset = skb_transport_offset(skb);
+			ret = 0;
+		}
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+TC_INDIRECT_SCOPE int tcf_pedit_act(struct sk_buff *skb,
+				    const struct tc_action *a,
+				    struct tcf_result *res)
+{
+	enum pedit_header_type htype = TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK;
+	enum pedit_cmd cmd = TCA_PEDIT_KEY_EX_CMD_SET;
+	struct tcf_pedit *p = to_pedit(a);
+	struct tcf_pedit_key_ex *tkey_ex;
+	struct tcf_pedit_parms *parms;
+	struct tc_pedit_key *tkey;
+	u32 max_offset;
+	int i;
+
+	parms = rcu_dereference_bh(p->parms);
+
+	max_offset = (skb_transport_header_was_set(skb) ?
+		      skb_transport_offset(skb) :
+		      skb_network_offset(skb)) +
+		     parms->tcfp_off_max_hint;
+	if (skb_ensure_writable(skb, min(skb->len, max_offset)))
+		goto done;
+
+	tcf_lastuse_update(&p->tcf_tm);
+	tcf_action_update_bstats(&p->common, skb);
+
+	tkey = parms->tcfp_keys;
+	tkey_ex = parms->tcfp_keys_ex;
+
+	for (i = parms->tcfp_nkeys; i > 0; i--, tkey++) {
+		int offset = tkey->off;
+		u32 *ptr, hdata;
+		int hoffset;
+		u32 val;
+		int rc;
+
+		if (tkey_ex) {
+			htype = tkey_ex->htype;
+			cmd = tkey_ex->cmd;
+
+			tkey_ex++;
+		}
+
+		rc = pedit_skb_hdr_offset(skb, htype, &hoffset);
+		if (rc) {
+			pr_info("tc action pedit bad header type specified (0x%x)\n",
+				htype);
+			goto bad;
+		}
+
+		if (tkey->offmask) {
+			u8 *d, _d;
+
+			if (!offset_valid(skb, hoffset + tkey->at)) {
+				pr_info("tc action pedit 'at' offset %d out of bounds\n",
+					hoffset + tkey->at);
+				goto bad;
+			}
+			d = skb_header_pointer(skb, hoffset + tkey->at,
+					       sizeof(_d), &_d);
+			if (!d)
+				goto bad;
+			offset += (*d & tkey->offmask) >> tkey->shift;
+		}
+
+		if (offset % 4) {
+			pr_info("tc action pedit offset must be on 32 bit boundaries\n");
+			goto bad;
+		}
+
+		if (!offset_valid(skb, hoffset + offset)) {
+			pr_info("tc action pedit offset %d out of bounds\n",
+				hoffset + offset);
+			goto bad;
+		}
+
+		ptr = skb_header_pointer(skb, hoffset + offset,
+					 sizeof(hdata), &hdata);
+		if (!ptr)
+			goto bad;
+		/* just do it, baby */
+		switch (cmd) {
+		case TCA_PEDIT_KEY_EX_CMD_SET:
+			val = tkey->val;
+			break;
+		case TCA_PEDIT_KEY_EX_CMD_ADD:
+			val = (*ptr + tkey->val) & ~tkey->mask;
+			break;
+		default:
+			pr_info("tc action pedit bad command (%d)\n",
+				cmd);
+			goto bad;
+		}
+
+		*ptr = ((*ptr & tkey->mask) ^ val);
+		if (ptr == &hdata)
+			skb_store_bits(skb, hoffset + offset, ptr, 4);
+	}
+
+	goto done;
+
+bad:
+	tcf_action_inc_overlimit_qstats(&p->common);
+done:
+	return p->tcf_action;
+}
+
+static void tcf_pedit_stats_update(struct tc_action *a, u64 bytes, u64 packets,
+				   u64 drops, u64 lastuse, bool hw)
+{
+	struct tcf_pedit *d = to_pedit(a);
+	struct tcf_t *tm = &d->tcf_tm;
+
+	tcf_action_update_stats(a, bytes, packets, drops, hw);
+	tm->lastuse = max_t(u64, tm->lastuse, lastuse);
+}
+
+static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a,
+			  int bind, int ref)
+{
+	unsigned char *b = skb_tail_pointer(skb);
+	struct tcf_pedit *p = to_pedit(a);
+	struct tcf_pedit_parms *parms;
+	struct tc_pedit *opt;
+	struct tcf_t t;
+	int s;
+
+	spin_lock_bh(&p->tcf_lock);
+	parms = rcu_dereference_protected(p->parms, 1);
+	s = struct_size(opt, keys, parms->tcfp_nkeys);
+
+	opt = kzalloc(s, GFP_ATOMIC);
+	if (unlikely(!opt)) {
+		spin_unlock_bh(&p->tcf_lock);
+		return -ENOBUFS;
+	}
+
+	memcpy(opt->keys, parms->tcfp_keys,
+	       flex_array_size(opt, keys, parms->tcfp_nkeys));
+	opt->index = p->tcf_index;
+	opt->nkeys = parms->tcfp_nkeys;
+	opt->flags = parms->tcfp_flags;
+	opt->action = p->tcf_action;
+	opt->refcnt = refcount_read(&p->tcf_refcnt) - ref;
+	opt->bindcnt = atomic_read(&p->tcf_bindcnt) - bind;
+
+	if (parms->tcfp_keys_ex) {
+		if (tcf_pedit_key_ex_dump(skb, parms->tcfp_keys_ex,
+					  parms->tcfp_nkeys))
+			goto nla_put_failure;
+
+		if (nla_put(skb, TCA_PEDIT_PARMS_EX, s, opt))
+			goto nla_put_failure;
+	} else {
+		if (nla_put(skb, TCA_PEDIT_PARMS, s, opt))
+			goto nla_put_failure;
+	}
+
+	tcf_tm_dump(&t, &p->tcf_tm);
+	if (nla_put_64bit(skb, TCA_PEDIT_TM, sizeof(t), &t, TCA_PEDIT_PAD))
+		goto nla_put_failure;
+	spin_unlock_bh(&p->tcf_lock);
+
+	kfree(opt);
+	return skb->len;
+
+nla_put_failure:
+	spin_unlock_bh(&p->tcf_lock);
+	nlmsg_trim(skb, b);
+	kfree(opt);
+	return -1;
+}
+
+static int tcf_pedit_offload_act_setup(struct tc_action *act, void *entry_data,
+				       u32 *index_inc, bool bind,
+				       struct netlink_ext_ack *extack)
+{
+	if (bind) {
+		struct flow_action_entry *entry = entry_data;
+		int k;
+
+		for (k = 0; k < tcf_pedit_nkeys(act); k++) {
+			switch (tcf_pedit_cmd(act, k)) {
+			case TCA_PEDIT_KEY_EX_CMD_SET:
+				entry->id = FLOW_ACTION_MANGLE;
+				break;
+			case TCA_PEDIT_KEY_EX_CMD_ADD:
+				entry->id = FLOW_ACTION_ADD;
+				break;
+			default:
+				NL_SET_ERR_MSG_MOD(extack, "Unsupported pedit command offload");
+				return -EOPNOTSUPP;
+			}
+			entry->mangle.htype = tcf_pedit_htype(act, k);
+			entry->mangle.mask = tcf_pedit_mask(act, k);
+			entry->mangle.val = tcf_pedit_val(act, k);
+			entry->mangle.offset = tcf_pedit_offset(act, k);
+			entry->hw_stats = tc_act_hw_stats(act->hw_stats);
+			entry++;
+		}
+		*index_inc = k;
+	} else {
+		struct flow_offload_action *fl_action = entry_data;
+		u32 cmd = tcf_pedit_cmd(act, 0);
+		int k;
+
+		switch (cmd) {
+		case TCA_PEDIT_KEY_EX_CMD_SET:
+			fl_action->id = FLOW_ACTION_MANGLE;
+			break;
+		case TCA_PEDIT_KEY_EX_CMD_ADD:
+			fl_action->id = FLOW_ACTION_ADD;
+			break;
+		default:
+			NL_SET_ERR_MSG_MOD(extack, "Unsupported pedit command offload");
+			return -EOPNOTSUPP;
+		}
+
+		for (k = 1; k < tcf_pedit_nkeys(act); k++) {
+			if (cmd != tcf_pedit_cmd(act, k)) {
+				NL_SET_ERR_MSG_MOD(extack, "Unsupported pedit command offload");
+				return -EOPNOTSUPP;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static struct tc_action_ops act_pedit_ops = {
+	.kind		=	"pedit",
+	.id		=	TCA_ID_PEDIT,
+	.owner		=	THIS_MODULE,
+	.act		=	tcf_pedit_act,
+	.stats_update	=	tcf_pedit_stats_update,
+	.dump		=	tcf_pedit_dump,
+	.cleanup	=	tcf_pedit_cleanup,
+	.init		=	tcf_pedit_init,
+	.offload_act_setup =	tcf_pedit_offload_act_setup,
+	.size		=	sizeof(struct tcf_pedit),
+};
+
+static __net_init int pedit_init_net(struct net *net)
+{
+	struct tc_action_net *tn = net_generic(net, act_pedit_ops.net_id);
+
+	return tc_action_net_init(net, tn, &act_pedit_ops);
+}
+
+static void __net_exit pedit_exit_net(struct list_head *net_list)
+{
+	tc_action_net_exit(net_list, act_pedit_ops.net_id);
+}
+
+static struct pernet_operations pedit_net_ops = {
+	.init = pedit_init_net,
+	.exit_batch = pedit_exit_net,
+	.id   = &act_pedit_ops.net_id,
+	.size = sizeof(struct tc_action_net),
+};
+
+MODULE_AUTHOR("Jamal Hadi Salim(2002-4)");
+MODULE_DESCRIPTION("Generic Packet Editor actions");
+MODULE_LICENSE("GPL");
+
+static int __init pedit_init_module(void)
+{
+	return tcf_register_action(&act_pedit_ops, &pedit_net_ops);
+}
+
+static void __exit pedit_cleanup_module(void)
+{
+	tcf_unregister_action(&act_pedit_ops, &pedit_net_ops);
+}
+
+module_init(pedit_init_module);
+module_exit(pedit_cleanup_module);