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, 1137 insertions, 0 deletions

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
new file mode 100644
index 000000000..9d5522647
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -0,0 +1,1137 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (c) 2018 Synopsys, Inc. and/or its affiliates.
+ * stmmac TC Handling (HW only)
+ */
+
+#include <net/pkt_cls.h>
+#include <net/tc_act/tc_gact.h>
+#include "common.h"
+#include "dwmac4.h"
+#include "dwmac5.h"
+#include "stmmac.h"
+
+static void tc_fill_all_pass_entry(struct stmmac_tc_entry *entry)
+{
+	memset(entry, 0, sizeof(*entry));
+	entry->in_use = true;
+	entry->is_last = true;
+	entry->is_frag = false;
+	entry->prio = ~0x0;
+	entry->handle = 0;
+	entry->val.match_data = 0x0;
+	entry->val.match_en = 0x0;
+	entry->val.af = 1;
+	entry->val.dma_ch_no = 0x0;
+}
+
+static struct stmmac_tc_entry *tc_find_entry(struct stmmac_priv *priv,
+					     struct tc_cls_u32_offload *cls,
+					     bool free)
+{
+	struct stmmac_tc_entry *entry, *first = NULL, *dup = NULL;
+	u32 loc = cls->knode.handle;
+	int i;
+
+	for (i = 0; i < priv->tc_entries_max; i++) {
+		entry = &priv->tc_entries[i];
+		if (!entry->in_use && !first && free)
+			first = entry;
+		if ((entry->handle == loc) && !free && !entry->is_frag)
+			dup = entry;
+	}
+
+	if (dup)
+		return dup;
+	if (first) {
+		first->handle = loc;
+		first->in_use = true;
+
+		/* Reset HW values */
+		memset(&first->val, 0, sizeof(first->val));
+	}
+
+	return first;
+}
+
+static int tc_fill_actions(struct stmmac_tc_entry *entry,
+			   struct stmmac_tc_entry *frag,
+			   struct tc_cls_u32_offload *cls)
+{
+	struct stmmac_tc_entry *action_entry = entry;
+	const struct tc_action *act;
+	struct tcf_exts *exts;
+	int i;
+
+	exts = cls->knode.exts;
+	if (!tcf_exts_has_actions(exts))
+		return -EINVAL;
+	if (frag)
+		action_entry = frag;
+
+	tcf_exts_for_each_action(i, act, exts) {
+		/* Accept */
+		if (is_tcf_gact_ok(act)) {
+			action_entry->val.af = 1;
+			break;
+		}
+		/* Drop */
+		if (is_tcf_gact_shot(act)) {
+			action_entry->val.rf = 1;
+			break;
+		}
+
+		/* Unsupported */
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int tc_fill_entry(struct stmmac_priv *priv,
+			 struct tc_cls_u32_offload *cls)
+{
+	struct stmmac_tc_entry *entry, *frag = NULL;
+	struct tc_u32_sel *sel = cls->knode.sel;
+	u32 off, data, mask, real_off, rem;
+	u32 prio = cls->common.prio << 16;
+	int ret;
+
+	/* Only 1 match per entry */
+	if (sel->nkeys <= 0 || sel->nkeys > 1)
+		return -EINVAL;
+
+	off = sel->keys[0].off << sel->offshift;
+	data = sel->keys[0].val;
+	mask = sel->keys[0].mask;
+
+	switch (ntohs(cls->common.protocol)) {
+	case ETH_P_ALL:
+		break;
+	case ETH_P_IP:
+		off += ETH_HLEN;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (off > priv->tc_off_max)
+		return -EINVAL;
+
+	real_off = off / 4;
+	rem = off % 4;
+
+	entry = tc_find_entry(priv, cls, true);
+	if (!entry)
+		return -EINVAL;
+
+	if (rem) {
+		frag = tc_find_entry(priv, cls, true);
+		if (!frag) {
+			ret = -EINVAL;
+			goto err_unuse;
+		}
+
+		entry->frag_ptr = frag;
+		entry->val.match_en = (mask << (rem * 8)) &
+			GENMASK(31, rem * 8);
+		entry->val.match_data = (data << (rem * 8)) &
+			GENMASK(31, rem * 8);
+		entry->val.frame_offset = real_off;
+		entry->prio = prio;
+
+		frag->val.match_en = (mask >> (rem * 8)) &
+			GENMASK(rem * 8 - 1, 0);
+		frag->val.match_data = (data >> (rem * 8)) &
+			GENMASK(rem * 8 - 1, 0);
+		frag->val.frame_offset = real_off + 1;
+		frag->prio = prio;
+		frag->is_frag = true;
+	} else {
+		entry->frag_ptr = NULL;
+		entry->val.match_en = mask;
+		entry->val.match_data = data;
+		entry->val.frame_offset = real_off;
+		entry->prio = prio;
+	}
+
+	ret = tc_fill_actions(entry, frag, cls);
+	if (ret)
+		goto err_unuse;
+
+	return 0;
+
+err_unuse:
+	if (frag)
+		frag->in_use = false;
+	entry->in_use = false;
+	return ret;
+}
+
+static void tc_unfill_entry(struct stmmac_priv *priv,
+			    struct tc_cls_u32_offload *cls)
+{
+	struct stmmac_tc_entry *entry;
+
+	entry = tc_find_entry(priv, cls, false);
+	if (!entry)
+		return;
+
+	entry->in_use = false;
+	if (entry->frag_ptr) {
+		entry = entry->frag_ptr;
+		entry->is_frag = false;
+		entry->in_use = false;
+	}
+}
+
+static int tc_config_knode(struct stmmac_priv *priv,
+			   struct tc_cls_u32_offload *cls)
+{
+	int ret;
+
+	ret = tc_fill_entry(priv, cls);
+	if (ret)
+		return ret;
+
+	ret = stmmac_rxp_config(priv, priv->hw->pcsr, priv->tc_entries,
+			priv->tc_entries_max);
+	if (ret)
+		goto err_unfill;
+
+	return 0;
+
+err_unfill:
+	tc_unfill_entry(priv, cls);
+	return ret;
+}
+
+static int tc_delete_knode(struct stmmac_priv *priv,
+			   struct tc_cls_u32_offload *cls)
+{
+	/* Set entry and fragments as not used */
+	tc_unfill_entry(priv, cls);
+
+	return stmmac_rxp_config(priv, priv->hw->pcsr, priv->tc_entries,
+				 priv->tc_entries_max);
+}
+
+static int tc_setup_cls_u32(struct stmmac_priv *priv,
+			    struct tc_cls_u32_offload *cls)
+{
+	switch (cls->command) {
+	case TC_CLSU32_REPLACE_KNODE:
+		tc_unfill_entry(priv, cls);
+		fallthrough;
+	case TC_CLSU32_NEW_KNODE:
+		return tc_config_knode(priv, cls);
+	case TC_CLSU32_DELETE_KNODE:
+		return tc_delete_knode(priv, cls);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int tc_rfs_init(struct stmmac_priv *priv)
+{
+	int i;
+
+	priv->rfs_entries_max[STMMAC_RFS_T_VLAN] = 8;
+	priv->rfs_entries_max[STMMAC_RFS_T_LLDP] = 1;
+	priv->rfs_entries_max[STMMAC_RFS_T_1588] = 1;
+
+	for (i = 0; i < STMMAC_RFS_T_MAX; i++)
+		priv->rfs_entries_total += priv->rfs_entries_max[i];
+
+	priv->rfs_entries = devm_kcalloc(priv->device,
+					 priv->rfs_entries_total,
+					 sizeof(*priv->rfs_entries),
+					 GFP_KERNEL);
+	if (!priv->rfs_entries)
+		return -ENOMEM;
+
+	dev_info(priv->device, "Enabled RFS Flow TC (entries=%d)\n",
+		 priv->rfs_entries_total);
+
+	return 0;
+}
+
+static int tc_init(struct stmmac_priv *priv)
+{
+	struct dma_features *dma_cap = &priv->dma_cap;
+	unsigned int count;
+	int ret, i;
+
+	if (dma_cap->l3l4fnum) {
+		priv->flow_entries_max = dma_cap->l3l4fnum;
+		priv->flow_entries = devm_kcalloc(priv->device,
+						  dma_cap->l3l4fnum,
+						  sizeof(*priv->flow_entries),
+						  GFP_KERNEL);
+		if (!priv->flow_entries)
+			return -ENOMEM;
+
+		for (i = 0; i < priv->flow_entries_max; i++)
+			priv->flow_entries[i].idx = i;
+
+		dev_info(priv->device, "Enabled L3L4 Flow TC (entries=%d)\n",
+			 priv->flow_entries_max);
+	}
+
+	ret = tc_rfs_init(priv);
+	if (ret)
+		return -ENOMEM;
+
+	if (!priv->plat->fpe_cfg) {
+		priv->plat->fpe_cfg = devm_kzalloc(priv->device,
+						   sizeof(*priv->plat->fpe_cfg),
+						   GFP_KERNEL);
+		if (!priv->plat->fpe_cfg)
+			return -ENOMEM;
+	} else {
+		memset(priv->plat->fpe_cfg, 0, sizeof(*priv->plat->fpe_cfg));
+	}
+
+	/* Fail silently as we can still use remaining features, e.g. CBS */
+	if (!dma_cap->frpsel)
+		return 0;
+
+	switch (dma_cap->frpbs) {
+	case 0x0:
+		priv->tc_off_max = 64;
+		break;
+	case 0x1:
+		priv->tc_off_max = 128;
+		break;
+	case 0x2:
+		priv->tc_off_max = 256;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (dma_cap->frpes) {
+	case 0x0:
+		count = 64;
+		break;
+	case 0x1:
+		count = 128;
+		break;
+	case 0x2:
+		count = 256;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Reserve one last filter which lets all pass */
+	priv->tc_entries_max = count;
+	priv->tc_entries = devm_kcalloc(priv->device,
+			count, sizeof(*priv->tc_entries), GFP_KERNEL);
+	if (!priv->tc_entries)
+		return -ENOMEM;
+
+	tc_fill_all_pass_entry(&priv->tc_entries[count - 1]);
+
+	dev_info(priv->device, "Enabling HW TC (entries=%d, max_off=%d)\n",
+			priv->tc_entries_max, priv->tc_off_max);
+
+	return 0;
+}
+
+static int tc_setup_cbs(struct stmmac_priv *priv,
+			struct tc_cbs_qopt_offload *qopt)
+{
+	u32 tx_queues_count = priv->plat->tx_queues_to_use;
+	u32 queue = qopt->queue;
+	u32 ptr, speed_div;
+	u32 mode_to_use;
+	u64 value;
+	int ret;
+
+	/* Queue 0 is not AVB capable */
+	if (queue <= 0 || queue >= tx_queues_count)
+		return -EINVAL;
+	if (!priv->dma_cap.av)
+		return -EOPNOTSUPP;
+
+	/* Port Transmit Rate and Speed Divider */
+	switch (priv->speed) {
+	case SPEED_10000:
+		ptr = 32;
+		speed_div = 10000000;
+		break;
+	case SPEED_5000:
+		ptr = 32;
+		speed_div = 5000000;
+		break;
+	case SPEED_2500:
+		ptr = 8;
+		speed_div = 2500000;
+		break;
+	case SPEED_1000:
+		ptr = 8;
+		speed_div = 1000000;
+		break;
+	case SPEED_100:
+		ptr = 4;
+		speed_div = 100000;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	mode_to_use = priv->plat->tx_queues_cfg[queue].mode_to_use;
+	if (mode_to_use == MTL_QUEUE_DCB && qopt->enable) {
+		ret = stmmac_dma_qmode(priv, priv->ioaddr, queue, MTL_QUEUE_AVB);
+		if (ret)
+			return ret;
+
+		priv->plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_AVB;
+	} else if (!qopt->enable) {
+		ret = stmmac_dma_qmode(priv, priv->ioaddr, queue,
+				       MTL_QUEUE_DCB);
+		if (ret)
+			return ret;
+
+		priv->plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB;
+	}
+
+	/* Final adjustments for HW */
+	value = div_s64(qopt->idleslope * 1024ll * ptr, speed_div);
+	priv->plat->tx_queues_cfg[queue].idle_slope = value & GENMASK(31, 0);
+
+	value = div_s64(-qopt->sendslope * 1024ll * ptr, speed_div);
+	priv->plat->tx_queues_cfg[queue].send_slope = value & GENMASK(31, 0);
+
+	value = qopt->hicredit * 1024ll * 8;
+	priv->plat->tx_queues_cfg[queue].high_credit = value & GENMASK(31, 0);
+
+	value = qopt->locredit * 1024ll * 8;
+	priv->plat->tx_queues_cfg[queue].low_credit = value & GENMASK(31, 0);
+
+	ret = stmmac_config_cbs(priv, priv->hw,
+				priv->plat->tx_queues_cfg[queue].send_slope,
+				priv->plat->tx_queues_cfg[queue].idle_slope,
+				priv->plat->tx_queues_cfg[queue].high_credit,
+				priv->plat->tx_queues_cfg[queue].low_credit,
+				queue);
+	if (ret)
+		return ret;
+
+	dev_info(priv->device, "CBS queue %d: send %d, idle %d, hi %d, lo %d\n",
+			queue, qopt->sendslope, qopt->idleslope,
+			qopt->hicredit, qopt->locredit);
+	return 0;
+}
+
+static int tc_parse_flow_actions(struct stmmac_priv *priv,
+				 struct flow_action *action,
+				 struct stmmac_flow_entry *entry,
+				 struct netlink_ext_ack *extack)
+{
+	struct flow_action_entry *act;
+	int i;
+
+	if (!flow_action_has_entries(action))
+		return -EINVAL;
+
+	if (!flow_action_basic_hw_stats_check(action, extack))
+		return -EOPNOTSUPP;
+
+	flow_action_for_each(i, act, action) {
+		switch (act->id) {
+		case FLOW_ACTION_DROP:
+			entry->action |= STMMAC_FLOW_ACTION_DROP;
+			return 0;
+		default:
+			break;
+		}
+	}
+
+	/* Nothing to do, maybe inverse filter ? */
+	return 0;
+}
+
+#define ETHER_TYPE_FULL_MASK	cpu_to_be16(~0)
+
+static int tc_add_basic_flow(struct stmmac_priv *priv,
+			     struct flow_cls_offload *cls,
+			     struct stmmac_flow_entry *entry)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(cls);
+	struct flow_dissector *dissector = rule->match.dissector;
+	struct flow_match_basic match;
+
+	/* Nothing to do here */
+	if (!dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_BASIC))
+		return -EINVAL;
+
+	flow_rule_match_basic(rule, &match);
+
+	entry->ip_proto = match.key->ip_proto;
+	return 0;
+}
+
+static int tc_add_ip4_flow(struct stmmac_priv *priv,
+			   struct flow_cls_offload *cls,
+			   struct stmmac_flow_entry *entry)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(cls);
+	struct flow_dissector *dissector = rule->match.dissector;
+	bool inv = entry->action & STMMAC_FLOW_ACTION_DROP;
+	struct flow_match_ipv4_addrs match;
+	u32 hw_match;
+	int ret;
+
+	/* Nothing to do here */
+	if (!dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS))
+		return -EINVAL;
+
+	flow_rule_match_ipv4_addrs(rule, &match);
+	hw_match = ntohl(match.key->src) & ntohl(match.mask->src);
+	if (hw_match) {
+		ret = stmmac_config_l3_filter(priv, priv->hw, entry->idx, true,
+					      false, true, inv, hw_match);
+		if (ret)
+			return ret;
+	}
+
+	hw_match = ntohl(match.key->dst) & ntohl(match.mask->dst);
+	if (hw_match) {
+		ret = stmmac_config_l3_filter(priv, priv->hw, entry->idx, true,
+					      false, false, inv, hw_match);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int tc_add_ports_flow(struct stmmac_priv *priv,
+			     struct flow_cls_offload *cls,
+			     struct stmmac_flow_entry *entry)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(cls);
+	struct flow_dissector *dissector = rule->match.dissector;
+	bool inv = entry->action & STMMAC_FLOW_ACTION_DROP;
+	struct flow_match_ports match;
+	u32 hw_match;
+	bool is_udp;
+	int ret;
+
+	/* Nothing to do here */
+	if (!dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_PORTS))
+		return -EINVAL;
+
+	switch (entry->ip_proto) {
+	case IPPROTO_TCP:
+		is_udp = false;
+		break;
+	case IPPROTO_UDP:
+		is_udp = true;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	flow_rule_match_ports(rule, &match);
+
+	hw_match = ntohs(match.key->src) & ntohs(match.mask->src);
+	if (hw_match) {
+		ret = stmmac_config_l4_filter(priv, priv->hw, entry->idx, true,
+					      is_udp, true, inv, hw_match);
+		if (ret)
+			return ret;
+	}
+
+	hw_match = ntohs(match.key->dst) & ntohs(match.mask->dst);
+	if (hw_match) {
+		ret = stmmac_config_l4_filter(priv, priv->hw, entry->idx, true,
+					      is_udp, false, inv, hw_match);
+		if (ret)
+			return ret;
+	}
+
+	entry->is_l4 = true;
+	return 0;
+}
+
+static struct stmmac_flow_entry *tc_find_flow(struct stmmac_priv *priv,
+					      struct flow_cls_offload *cls,
+					      bool get_free)
+{
+	int i;
+
+	for (i = 0; i < priv->flow_entries_max; i++) {
+		struct stmmac_flow_entry *entry = &priv->flow_entries[i];
+
+		if (entry->cookie == cls->cookie)
+			return entry;
+		if (get_free && (entry->in_use == false))
+			return entry;
+	}
+
+	return NULL;
+}
+
+static struct {
+	int (*fn)(struct stmmac_priv *priv, struct flow_cls_offload *cls,
+		  struct stmmac_flow_entry *entry);
+} tc_flow_parsers[] = {
+	{ .fn = tc_add_basic_flow },
+	{ .fn = tc_add_ip4_flow },
+	{ .fn = tc_add_ports_flow },
+};
+
+static int tc_add_flow(struct stmmac_priv *priv,
+		       struct flow_cls_offload *cls)
+{
+	struct stmmac_flow_entry *entry = tc_find_flow(priv, cls, false);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(cls);
+	int i, ret;
+
+	if (!entry) {
+		entry = tc_find_flow(priv, cls, true);
+		if (!entry)
+			return -ENOENT;
+	}
+
+	ret = tc_parse_flow_actions(priv, &rule->action, entry,
+				    cls->common.extack);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < ARRAY_SIZE(tc_flow_parsers); i++) {
+		ret = tc_flow_parsers[i].fn(priv, cls, entry);
+		if (!ret)
+			entry->in_use = true;
+	}
+
+	if (!entry->in_use)
+		return -EINVAL;
+
+	entry->cookie = cls->cookie;
+	return 0;
+}
+
+static int tc_del_flow(struct stmmac_priv *priv,
+		       struct flow_cls_offload *cls)
+{
+	struct stmmac_flow_entry *entry = tc_find_flow(priv, cls, false);
+	int ret;
+
+	if (!entry || !entry->in_use)
+		return -ENOENT;
+
+	if (entry->is_l4) {
+		ret = stmmac_config_l4_filter(priv, priv->hw, entry->idx, false,
+					      false, false, false, 0);
+	} else {
+		ret = stmmac_config_l3_filter(priv, priv->hw, entry->idx, false,
+					      false, false, false, 0);
+	}
+
+	entry->in_use = false;
+	entry->cookie = 0;
+	entry->is_l4 = false;
+	return ret;
+}
+
+static struct stmmac_rfs_entry *tc_find_rfs(struct stmmac_priv *priv,
+					    struct flow_cls_offload *cls,
+					    bool get_free)
+{
+	int i;
+
+	for (i = 0; i < priv->rfs_entries_total; i++) {
+		struct stmmac_rfs_entry *entry = &priv->rfs_entries[i];
+
+		if (entry->cookie == cls->cookie)
+			return entry;
+		if (get_free && entry->in_use == false)
+			return entry;
+	}
+
+	return NULL;
+}
+
+#define VLAN_PRIO_FULL_MASK (0x07)
+
+static int tc_add_vlan_flow(struct stmmac_priv *priv,
+			    struct flow_cls_offload *cls)
+{
+	struct stmmac_rfs_entry *entry = tc_find_rfs(priv, cls, false);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(cls);
+	struct flow_dissector *dissector = rule->match.dissector;
+	int tc = tc_classid_to_hwtc(priv->dev, cls->classid);
+	struct flow_match_vlan match;
+
+	if (!entry) {
+		entry = tc_find_rfs(priv, cls, true);
+		if (!entry)
+			return -ENOENT;
+	}
+
+	if (priv->rfs_entries_cnt[STMMAC_RFS_T_VLAN] >=
+	    priv->rfs_entries_max[STMMAC_RFS_T_VLAN])
+		return -ENOENT;
+
+	/* Nothing to do here */
+	if (!dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_VLAN))
+		return -EINVAL;
+
+	if (tc < 0) {
+		netdev_err(priv->dev, "Invalid traffic class\n");
+		return -EINVAL;
+	}
+
+	flow_rule_match_vlan(rule, &match);
+
+	if (match.mask->vlan_priority) {
+		u32 prio;
+
+		if (match.mask->vlan_priority != VLAN_PRIO_FULL_MASK) {
+			netdev_err(priv->dev, "Only full mask is supported for VLAN priority");
+			return -EINVAL;
+		}
+
+		prio = BIT(match.key->vlan_priority);
+		stmmac_rx_queue_prio(priv, priv->hw, prio, tc);
+
+		entry->in_use = true;
+		entry->cookie = cls->cookie;
+		entry->tc = tc;
+		entry->type = STMMAC_RFS_T_VLAN;
+		priv->rfs_entries_cnt[STMMAC_RFS_T_VLAN]++;
+	}
+
+	return 0;
+}
+
+static int tc_del_vlan_flow(struct stmmac_priv *priv,
+			    struct flow_cls_offload *cls)
+{
+	struct stmmac_rfs_entry *entry = tc_find_rfs(priv, cls, false);
+
+	if (!entry || !entry->in_use || entry->type != STMMAC_RFS_T_VLAN)
+		return -ENOENT;
+
+	stmmac_rx_queue_prio(priv, priv->hw, 0, entry->tc);
+
+	entry->in_use = false;
+	entry->cookie = 0;
+	entry->tc = 0;
+	entry->type = 0;
+
+	priv->rfs_entries_cnt[STMMAC_RFS_T_VLAN]--;
+
+	return 0;
+}
+
+static int tc_add_ethtype_flow(struct stmmac_priv *priv,
+			       struct flow_cls_offload *cls)
+{
+	struct stmmac_rfs_entry *entry = tc_find_rfs(priv, cls, false);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(cls);
+	struct flow_dissector *dissector = rule->match.dissector;
+	int tc = tc_classid_to_hwtc(priv->dev, cls->classid);
+	struct flow_match_basic match;
+
+	if (!entry) {
+		entry = tc_find_rfs(priv, cls, true);
+		if (!entry)
+			return -ENOENT;
+	}
+
+	/* Nothing to do here */
+	if (!dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_BASIC))
+		return -EINVAL;
+
+	if (tc < 0) {
+		netdev_err(priv->dev, "Invalid traffic class\n");
+		return -EINVAL;
+	}
+
+	flow_rule_match_basic(rule, &match);
+
+	if (match.mask->n_proto) {
+		u16 etype = ntohs(match.key->n_proto);
+
+		if (match.mask->n_proto != ETHER_TYPE_FULL_MASK) {
+			netdev_err(priv->dev, "Only full mask is supported for EthType filter");
+			return -EINVAL;
+		}
+		switch (etype) {
+		case ETH_P_LLDP:
+			if (priv->rfs_entries_cnt[STMMAC_RFS_T_LLDP] >=
+			    priv->rfs_entries_max[STMMAC_RFS_T_LLDP])
+				return -ENOENT;
+
+			entry->type = STMMAC_RFS_T_LLDP;
+			priv->rfs_entries_cnt[STMMAC_RFS_T_LLDP]++;
+
+			stmmac_rx_queue_routing(priv, priv->hw,
+						PACKET_DCBCPQ, tc);
+			break;
+		case ETH_P_1588:
+			if (priv->rfs_entries_cnt[STMMAC_RFS_T_1588] >=
+			    priv->rfs_entries_max[STMMAC_RFS_T_1588])
+				return -ENOENT;
+
+			entry->type = STMMAC_RFS_T_1588;
+			priv->rfs_entries_cnt[STMMAC_RFS_T_1588]++;
+
+			stmmac_rx_queue_routing(priv, priv->hw,
+						PACKET_PTPQ, tc);
+			break;
+		default:
+			netdev_err(priv->dev, "EthType(0x%x) is not supported", etype);
+			return -EINVAL;
+		}
+
+		entry->in_use = true;
+		entry->cookie = cls->cookie;
+		entry->tc = tc;
+		entry->etype = etype;
+
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static int tc_del_ethtype_flow(struct stmmac_priv *priv,
+			       struct flow_cls_offload *cls)
+{
+	struct stmmac_rfs_entry *entry = tc_find_rfs(priv, cls, false);
+
+	if (!entry || !entry->in_use ||
+	    entry->type < STMMAC_RFS_T_LLDP ||
+	    entry->type > STMMAC_RFS_T_1588)
+		return -ENOENT;
+
+	switch (entry->etype) {
+	case ETH_P_LLDP:
+		stmmac_rx_queue_routing(priv, priv->hw,
+					PACKET_DCBCPQ, 0);
+		priv->rfs_entries_cnt[STMMAC_RFS_T_LLDP]--;
+		break;
+	case ETH_P_1588:
+		stmmac_rx_queue_routing(priv, priv->hw,
+					PACKET_PTPQ, 0);
+		priv->rfs_entries_cnt[STMMAC_RFS_T_1588]--;
+		break;
+	default:
+		netdev_err(priv->dev, "EthType(0x%x) is not supported",
+			   entry->etype);
+		return -EINVAL;
+	}
+
+	entry->in_use = false;
+	entry->cookie = 0;
+	entry->tc = 0;
+	entry->etype = 0;
+	entry->type = 0;
+
+	return 0;
+}
+
+static int tc_add_flow_cls(struct stmmac_priv *priv,
+			   struct flow_cls_offload *cls)
+{
+	int ret;
+
+	ret = tc_add_flow(priv, cls);
+	if (!ret)
+		return ret;
+
+	ret = tc_add_ethtype_flow(priv, cls);
+	if (!ret)
+		return ret;
+
+	return tc_add_vlan_flow(priv, cls);
+}
+
+static int tc_del_flow_cls(struct stmmac_priv *priv,
+			   struct flow_cls_offload *cls)
+{
+	int ret;
+
+	ret = tc_del_flow(priv, cls);
+	if (!ret)
+		return ret;
+
+	ret = tc_del_ethtype_flow(priv, cls);
+	if (!ret)
+		return ret;
+
+	return tc_del_vlan_flow(priv, cls);
+}
+
+static int tc_setup_cls(struct stmmac_priv *priv,
+			struct flow_cls_offload *cls)
+{
+	int ret = 0;
+
+	/* When RSS is enabled, the filtering will be bypassed */
+	if (priv->rss.enable)
+		return -EBUSY;
+
+	switch (cls->command) {
+	case FLOW_CLS_REPLACE:
+		ret = tc_add_flow_cls(priv, cls);
+		break;
+	case FLOW_CLS_DESTROY:
+		ret = tc_del_flow_cls(priv, cls);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return ret;
+}
+
+struct timespec64 stmmac_calc_tas_basetime(ktime_t old_base_time,
+					   ktime_t current_time,
+					   u64 cycle_time)
+{
+	struct timespec64 time;
+
+	if (ktime_after(old_base_time, current_time)) {
+		time = ktime_to_timespec64(old_base_time);
+	} else {
+		s64 n;
+		ktime_t base_time;
+
+		n = div64_s64(ktime_sub_ns(current_time, old_base_time),
+			      cycle_time);
+		base_time = ktime_add_ns(old_base_time,
+					 (n + 1) * cycle_time);
+
+		time = ktime_to_timespec64(base_time);
+	}
+
+	return time;
+}
+
+static int tc_setup_taprio(struct stmmac_priv *priv,
+			   struct tc_taprio_qopt_offload *qopt)
+{
+	u32 size, wid = priv->dma_cap.estwid, dep = priv->dma_cap.estdep;
+	struct plat_stmmacenet_data *plat = priv->plat;
+	struct timespec64 time, current_time, qopt_time;
+	ktime_t current_time_ns;
+	bool fpe = false;
+	int i, ret = 0;
+	u64 ctr;
+
+	if (qopt->base_time < 0)
+		return -ERANGE;
+
+	if (!priv->dma_cap.estsel)
+		return -EOPNOTSUPP;
+
+	switch (wid) {
+	case 0x1:
+		wid = 16;
+		break;
+	case 0x2:
+		wid = 20;
+		break;
+	case 0x3:
+		wid = 24;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	switch (dep) {
+	case 0x1:
+		dep = 64;
+		break;
+	case 0x2:
+		dep = 128;
+		break;
+	case 0x3:
+		dep = 256;
+		break;
+	case 0x4:
+		dep = 512;
+		break;
+	case 0x5:
+		dep = 1024;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	if (!qopt->enable)
+		goto disable;
+	if (qopt->num_entries >= dep)
+		return -EINVAL;
+	if (!qopt->cycle_time)
+		return -ERANGE;
+
+	if (!plat->est) {
+		plat->est = devm_kzalloc(priv->device, sizeof(*plat->est),
+					 GFP_KERNEL);
+		if (!plat->est)
+			return -ENOMEM;
+
+		mutex_init(&priv->plat->est->lock);
+	} else {
+		memset(plat->est, 0, sizeof(*plat->est));
+	}
+
+	size = qopt->num_entries;
+
+	mutex_lock(&priv->plat->est->lock);
+	priv->plat->est->gcl_size = size;
+	priv->plat->est->enable = qopt->enable;
+	mutex_unlock(&priv->plat->est->lock);
+
+	for (i = 0; i < size; i++) {
+		s64 delta_ns = qopt->entries[i].interval;
+		u32 gates = qopt->entries[i].gate_mask;
+
+		if (delta_ns > GENMASK(wid, 0))
+			return -ERANGE;
+		if (gates > GENMASK(31 - wid, 0))
+			return -ERANGE;
+
+		switch (qopt->entries[i].command) {
+		case TC_TAPRIO_CMD_SET_GATES:
+			if (fpe)
+				return -EINVAL;
+			break;
+		case TC_TAPRIO_CMD_SET_AND_HOLD:
+			gates |= BIT(0);
+			fpe = true;
+			break;
+		case TC_TAPRIO_CMD_SET_AND_RELEASE:
+			gates &= ~BIT(0);
+			fpe = true;
+			break;
+		default:
+			return -EOPNOTSUPP;
+		}
+
+		priv->plat->est->gcl[i] = delta_ns | (gates << wid);
+	}
+
+	mutex_lock(&priv->plat->est->lock);
+	/* Adjust for real system time */
+	priv->ptp_clock_ops.gettime64(&priv->ptp_clock_ops, &current_time);
+	current_time_ns = timespec64_to_ktime(current_time);
+	time = stmmac_calc_tas_basetime(qopt->base_time, current_time_ns,
+					qopt->cycle_time);
+
+	priv->plat->est->btr[0] = (u32)time.tv_nsec;
+	priv->plat->est->btr[1] = (u32)time.tv_sec;
+
+	qopt_time = ktime_to_timespec64(qopt->base_time);
+	priv->plat->est->btr_reserve[0] = (u32)qopt_time.tv_nsec;
+	priv->plat->est->btr_reserve[1] = (u32)qopt_time.tv_sec;
+
+	ctr = qopt->cycle_time;
+	priv->plat->est->ctr[0] = do_div(ctr, NSEC_PER_SEC);
+	priv->plat->est->ctr[1] = (u32)ctr;
+
+	if (fpe && !priv->dma_cap.fpesel) {
+		mutex_unlock(&priv->plat->est->lock);
+		return -EOPNOTSUPP;
+	}
+
+	/* Actual FPE register configuration will be done after FPE handshake
+	 * is success.
+	 */
+	priv->plat->fpe_cfg->enable = fpe;
+
+	ret = stmmac_est_configure(priv, priv->ioaddr, priv->plat->est,
+				   priv->plat->clk_ptp_rate);
+	mutex_unlock(&priv->plat->est->lock);
+	if (ret) {
+		netdev_err(priv->dev, "failed to configure EST\n");
+		goto disable;
+	}
+
+	netdev_info(priv->dev, "configured EST\n");
+
+	if (fpe) {
+		stmmac_fpe_handshake(priv, true);
+		netdev_info(priv->dev, "start FPE handshake\n");
+	}
+
+	return 0;
+
+disable:
+	if (priv->plat->est) {
+		mutex_lock(&priv->plat->est->lock);
+		priv->plat->est->enable = false;
+		stmmac_est_configure(priv, priv->ioaddr, priv->plat->est,
+				     priv->plat->clk_ptp_rate);
+		mutex_unlock(&priv->plat->est->lock);
+	}
+
+	priv->plat->fpe_cfg->enable = false;
+	stmmac_fpe_configure(priv, priv->ioaddr,
+			     priv->plat->tx_queues_to_use,
+			     priv->plat->rx_queues_to_use,
+			     false);
+	netdev_info(priv->dev, "disabled FPE\n");
+
+	stmmac_fpe_handshake(priv, false);
+	netdev_info(priv->dev, "stop FPE handshake\n");
+
+	return ret;
+}
+
+static int tc_setup_etf(struct stmmac_priv *priv,
+			struct tc_etf_qopt_offload *qopt)
+{
+	if (!priv->dma_cap.tbssel)
+		return -EOPNOTSUPP;
+	if (qopt->queue >= priv->plat->tx_queues_to_use)
+		return -EINVAL;
+	if (!(priv->dma_conf.tx_queue[qopt->queue].tbs & STMMAC_TBS_AVAIL))
+		return -EINVAL;
+
+	if (qopt->enable)
+		priv->dma_conf.tx_queue[qopt->queue].tbs |= STMMAC_TBS_EN;
+	else
+		priv->dma_conf.tx_queue[qopt->queue].tbs &= ~STMMAC_TBS_EN;
+
+	netdev_info(priv->dev, "%s ETF for Queue %d\n",
+		    qopt->enable ? "enabled" : "disabled", qopt->queue);
+	return 0;
+}
+
+static int tc_query_caps(struct stmmac_priv *priv,
+			 struct tc_query_caps_base *base)
+{
+	switch (base->type) {
+	case TC_SETUP_QDISC_TAPRIO: {
+		struct tc_taprio_caps *caps = base->caps;
+
+		if (!priv->dma_cap.estsel)
+			return -EOPNOTSUPP;
+
+		caps->gate_mask_per_txq = true;
+
+		return 0;
+	}
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+const struct stmmac_tc_ops dwmac510_tc_ops = {
+	.init = tc_init,
+	.setup_cls_u32 = tc_setup_cls_u32,
+	.setup_cbs = tc_setup_cbs,
+	.setup_cls = tc_setup_cls,
+	.setup_taprio = tc_setup_taprio,
+	.setup_etf = tc_setup_etf,
+	.query_caps = tc_query_caps,
+};