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, 468 insertions, 0 deletions

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c
new file mode 100644
index 000000000..cbd06d9b9
--- /dev/null
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c
@@ -0,0 +1,468 @@
+/*
+ * cxgb4_ptp.c:Chelsio PTP support for T5/T6
+ *
+ * Copyright (c) 2003-2017 Chelsio Communications, Inc. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ * Written by: Atul Gupta (atul.gupta@chelsio.com)
+ */
+
+#include <linux/module.h>
+#include <linux/net_tstamp.h>
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/pps_kernel.h>
+#include <linux/ptp_clock_kernel.h>
+#include <linux/ptp_classify.h>
+#include <linux/udp.h>
+
+#include "cxgb4.h"
+#include "t4_hw.h"
+#include "t4_regs.h"
+#include "t4_msg.h"
+#include "t4fw_api.h"
+#include "cxgb4_ptp.h"
+
+/**
+ * cxgb4_ptp_is_ptp_tx - determine whether TX packet is PTP or not
+ * @skb: skb of outgoing ptp request
+ *
+ */
+bool cxgb4_ptp_is_ptp_tx(struct sk_buff *skb)
+{
+	struct udphdr *uh;
+
+	uh = udp_hdr(skb);
+	return skb->len >= PTP_MIN_LENGTH &&
+		skb->len <= PTP_IN_TRANSMIT_PACKET_MAXNUM &&
+		likely(skb->protocol == htons(ETH_P_IP)) &&
+		ip_hdr(skb)->protocol == IPPROTO_UDP &&
+		uh->dest == htons(PTP_EVENT_PORT);
+}
+
+bool is_ptp_enabled(struct sk_buff *skb, struct net_device *dev)
+{
+	struct port_info *pi;
+
+	pi = netdev_priv(dev);
+	return (pi->ptp_enable && cxgb4_xmit_with_hwtstamp(skb) &&
+		cxgb4_ptp_is_ptp_tx(skb));
+}
+
+/**
+ * cxgb4_ptp_is_ptp_rx - determine whether RX packet is PTP or not
+ * @skb: skb of incoming ptp request
+ *
+ */
+bool cxgb4_ptp_is_ptp_rx(struct sk_buff *skb)
+{
+	struct udphdr *uh = (struct udphdr *)(skb->data + ETH_HLEN +
+					      IPV4_HLEN(skb->data));
+
+	return  uh->dest == htons(PTP_EVENT_PORT) &&
+		uh->source == htons(PTP_EVENT_PORT);
+}
+
+/**
+ * cxgb4_ptp_read_hwstamp - read timestamp for TX event PTP message
+ * @adapter: board private structure
+ * @pi: port private structure
+ *
+ */
+void cxgb4_ptp_read_hwstamp(struct adapter *adapter, struct port_info *pi)
+{
+	struct skb_shared_hwtstamps *skb_ts = NULL;
+	u64 tx_ts;
+
+	skb_ts = skb_hwtstamps(adapter->ptp_tx_skb);
+
+	tx_ts = t4_read_reg(adapter,
+			    T5_PORT_REG(pi->port_id, MAC_PORT_TX_TS_VAL_LO));
+
+	tx_ts |= (u64)t4_read_reg(adapter,
+				  T5_PORT_REG(pi->port_id,
+					      MAC_PORT_TX_TS_VAL_HI)) << 32;
+	skb_ts->hwtstamp = ns_to_ktime(tx_ts);
+	skb_tstamp_tx(adapter->ptp_tx_skb, skb_ts);
+	dev_kfree_skb_any(adapter->ptp_tx_skb);
+	spin_lock(&adapter->ptp_lock);
+	adapter->ptp_tx_skb = NULL;
+	spin_unlock(&adapter->ptp_lock);
+}
+
+/**
+ * cxgb4_ptprx_timestamping - Enable Timestamp for RX PTP event message
+ * @pi: port private structure
+ * @port: pot number
+ * @mode: RX mode
+ *
+ */
+int cxgb4_ptprx_timestamping(struct port_info *pi, u8 port, u16 mode)
+{
+	struct adapter *adapter = pi->adapter;
+	struct fw_ptp_cmd c;
+	int err;
+
+	memset(&c, 0, sizeof(c));
+	c.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PTP_CMD) |
+				     FW_CMD_REQUEST_F |
+				     FW_CMD_WRITE_F |
+				     FW_PTP_CMD_PORTID_V(port));
+	c.retval_len16 = cpu_to_be32(FW_CMD_LEN16_V(sizeof(c) / 16));
+	c.u.init.sc = FW_PTP_SC_RXTIME_STAMP;
+	c.u.init.mode = cpu_to_be16(mode);
+
+	err = t4_wr_mbox(adapter, adapter->mbox, &c, sizeof(c), NULL);
+	if (err < 0)
+		dev_err(adapter->pdev_dev,
+			"PTP: %s error %d\n", __func__, -err);
+	return err;
+}
+
+int cxgb4_ptp_txtype(struct adapter *adapter, u8 port)
+{
+	struct fw_ptp_cmd c;
+	int err;
+
+	memset(&c, 0, sizeof(c));
+	c.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PTP_CMD) |
+				     FW_CMD_REQUEST_F |
+				     FW_CMD_WRITE_F |
+				     FW_PTP_CMD_PORTID_V(port));
+	c.retval_len16 = cpu_to_be32(FW_CMD_LEN16_V(sizeof(c) / 16));
+	c.u.init.sc = FW_PTP_SC_TX_TYPE;
+	c.u.init.mode = cpu_to_be16(PTP_TS_NONE);
+
+	err = t4_wr_mbox(adapter, adapter->mbox, &c, sizeof(c), NULL);
+	if (err < 0)
+		dev_err(adapter->pdev_dev,
+			"PTP: %s error %d\n", __func__, -err);
+
+	return err;
+}
+
+int cxgb4_ptp_redirect_rx_packet(struct adapter *adapter, struct port_info *pi)
+{
+	struct sge *s = &adapter->sge;
+	struct sge_eth_rxq *receive_q =  &s->ethrxq[pi->first_qset];
+	struct fw_ptp_cmd c;
+	int err;
+
+	memset(&c, 0, sizeof(c));
+	c.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PTP_CMD) |
+				     FW_CMD_REQUEST_F |
+				     FW_CMD_WRITE_F |
+				     FW_PTP_CMD_PORTID_V(pi->port_id));
+
+	c.retval_len16 = cpu_to_be32(FW_CMD_LEN16_V(sizeof(c) / 16));
+	c.u.init.sc = FW_PTP_SC_RDRX_TYPE;
+	c.u.init.txchan = pi->tx_chan;
+	c.u.init.absid = cpu_to_be16(receive_q->rspq.abs_id);
+
+	err = t4_wr_mbox(adapter, adapter->mbox, &c, sizeof(c), NULL);
+	if (err < 0)
+		dev_err(adapter->pdev_dev,
+			"PTP: %s error %d\n", __func__, -err);
+	return err;
+}
+
+/**
+ * cxgb4_ptp_adjfine - Adjust frequency of PHC cycle counter
+ * @ptp: ptp clock structure
+ * @scaled_ppm: Desired frequency in scaled parts per billion
+ *
+ * Adjust the frequency of the PHC cycle counter by the indicated amount from
+ * the base frequency.
+ *
+ * Scaled parts per million is ppm with a 16-bit binary fractional field.
+ */
+static int cxgb4_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
+{
+	struct adapter *adapter = (struct adapter *)container_of(ptp,
+				   struct adapter, ptp_clock_info);
+	s32 ppb = scaled_ppm_to_ppb(scaled_ppm);
+	struct fw_ptp_cmd c;
+	int err;
+
+	memset(&c, 0, sizeof(c));
+	c.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PTP_CMD) |
+				     FW_CMD_REQUEST_F |
+				     FW_CMD_WRITE_F |
+				     FW_PTP_CMD_PORTID_V(0));
+	c.retval_len16 = cpu_to_be32(FW_CMD_LEN16_V(sizeof(c) / 16));
+	c.u.ts.sc = FW_PTP_SC_ADJ_FREQ;
+	c.u.ts.sign = (ppb < 0) ? 1 : 0;
+	if (ppb < 0)
+		ppb = -ppb;
+	c.u.ts.ppb = cpu_to_be32(ppb);
+
+	err = t4_wr_mbox(adapter, adapter->mbox, &c, sizeof(c), NULL);
+	if (err < 0)
+		dev_err(adapter->pdev_dev,
+			"PTP: %s error %d\n", __func__, -err);
+
+	return err;
+}
+
+/**
+ * cxgb4_ptp_fineadjtime - Shift the time of the hardware clock
+ * @adapter: board private structure
+ * @delta: Desired change in nanoseconds
+ *
+ * Adjust the timer by resetting the timecounter structure.
+ */
+static int  cxgb4_ptp_fineadjtime(struct adapter *adapter, s64 delta)
+{
+	struct fw_ptp_cmd c;
+	int err;
+
+	memset(&c, 0, sizeof(c));
+	c.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PTP_CMD) |
+			     FW_CMD_REQUEST_F |
+			     FW_CMD_WRITE_F |
+			     FW_PTP_CMD_PORTID_V(0));
+	c.retval_len16 = cpu_to_be32(FW_CMD_LEN16_V(sizeof(c) / 16));
+	c.u.ts.sc = FW_PTP_SC_ADJ_FTIME;
+	c.u.ts.sign = (delta < 0) ? 1 : 0;
+	if (delta < 0)
+		delta = -delta;
+	c.u.ts.tm = cpu_to_be64(delta);
+
+	err = t4_wr_mbox(adapter, adapter->mbox, &c, sizeof(c), NULL);
+	if (err < 0)
+		dev_err(adapter->pdev_dev,
+			"PTP: %s error %d\n", __func__, -err);
+	return err;
+}
+
+/**
+ * cxgb4_ptp_adjtime - Shift the time of the hardware clock
+ * @ptp: ptp clock structure
+ * @delta: Desired change in nanoseconds
+ *
+ * Adjust the timer by resetting the timecounter structure.
+ */
+static int cxgb4_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+	struct adapter *adapter =
+		(struct adapter *)container_of(ptp, struct adapter,
+					       ptp_clock_info);
+	struct fw_ptp_cmd c;
+	s64 sign = 1;
+	int err;
+
+	if (delta < 0)
+		sign = -1;
+
+	if (delta * sign > PTP_CLOCK_MAX_ADJTIME) {
+		memset(&c, 0, sizeof(c));
+		c.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PTP_CMD) |
+					     FW_CMD_REQUEST_F |
+					     FW_CMD_WRITE_F |
+					     FW_PTP_CMD_PORTID_V(0));
+		c.retval_len16 = cpu_to_be32(FW_CMD_LEN16_V(sizeof(c) / 16));
+		c.u.ts.sc = FW_PTP_SC_ADJ_TIME;
+		c.u.ts.sign = (delta < 0) ? 1 : 0;
+		if (delta < 0)
+			delta = -delta;
+		c.u.ts.tm = cpu_to_be64(delta);
+
+		err = t4_wr_mbox(adapter, adapter->mbox, &c, sizeof(c), NULL);
+		if (err < 0)
+			dev_err(adapter->pdev_dev,
+				"PTP: %s error %d\n", __func__, -err);
+	} else {
+		err = cxgb4_ptp_fineadjtime(adapter, delta);
+	}
+
+	return err;
+}
+
+/**
+ * cxgb4_ptp_gettime - Reads the current time from the hardware clock
+ * @ptp: ptp clock structure
+ * @ts: timespec structure to hold the current time value
+ *
+ * Read the timecounter and return the correct value in ns after converting
+ * it into a struct timespec.
+ */
+static int cxgb4_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
+{
+	struct adapter *adapter = container_of(ptp, struct adapter,
+					       ptp_clock_info);
+	u64 ns;
+
+	ns = t4_read_reg(adapter, T5_PORT_REG(0, MAC_PORT_PTP_SUM_LO_A));
+	ns |= (u64)t4_read_reg(adapter,
+			       T5_PORT_REG(0, MAC_PORT_PTP_SUM_HI_A)) << 32;
+
+	/* convert to timespec*/
+	*ts = ns_to_timespec64(ns);
+	return 0;
+}
+
+/**
+ *  cxgb4_ptp_settime - Set the current time on the hardware clock
+ *  @ptp: ptp clock structure
+ *  @ts: timespec containing the new time for the cycle counter
+ *
+ *  Reset value to new base value instead of the kernel
+ *  wall timer value.
+ */
+static int cxgb4_ptp_settime(struct ptp_clock_info *ptp,
+			     const struct timespec64 *ts)
+{
+	struct adapter *adapter = (struct adapter *)container_of(ptp,
+				   struct adapter, ptp_clock_info);
+	struct fw_ptp_cmd c;
+	u64 ns;
+	int err;
+
+	memset(&c, 0, sizeof(c));
+	c.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PTP_CMD) |
+				     FW_CMD_REQUEST_F |
+				     FW_CMD_WRITE_F |
+				     FW_PTP_CMD_PORTID_V(0));
+	c.retval_len16 = cpu_to_be32(FW_CMD_LEN16_V(sizeof(c) / 16));
+	c.u.ts.sc = FW_PTP_SC_SET_TIME;
+
+	ns = timespec64_to_ns(ts);
+	c.u.ts.tm = cpu_to_be64(ns);
+
+	err =  t4_wr_mbox(adapter, adapter->mbox, &c, sizeof(c), NULL);
+	if (err < 0)
+		dev_err(adapter->pdev_dev,
+			"PTP: %s error %d\n", __func__, -err);
+
+	return err;
+}
+
+static void cxgb4_init_ptp_timer(struct adapter *adapter)
+{
+	struct fw_ptp_cmd c;
+	int err;
+
+	memset(&c, 0, sizeof(c));
+	c.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PTP_CMD) |
+				     FW_CMD_REQUEST_F |
+				     FW_CMD_WRITE_F |
+				     FW_PTP_CMD_PORTID_V(0));
+	c.retval_len16 = cpu_to_be32(FW_CMD_LEN16_V(sizeof(c) / 16));
+	c.u.scmd.sc = FW_PTP_SC_INIT_TIMER;
+
+	err = t4_wr_mbox(adapter, adapter->mbox, &c, sizeof(c), NULL);
+	if (err < 0)
+		dev_err(adapter->pdev_dev,
+			"PTP: %s error %d\n", __func__, -err);
+}
+
+/**
+ * cxgb4_ptp_enable - enable or disable an ancillary feature
+ * @ptp: ptp clock structure
+ * @request: Desired resource to enable or disable
+ * @on: Caller passes one to enable or zero to disable
+ *
+ * Enable (or disable) ancillary features of the PHC subsystem.
+ * Currently, no ancillary features are supported.
+ */
+static int cxgb4_ptp_enable(struct ptp_clock_info __always_unused *ptp,
+			    struct ptp_clock_request __always_unused *request,
+			    int __always_unused on)
+{
+	return -ENOTSUPP;
+}
+
+static const struct ptp_clock_info cxgb4_ptp_clock_info = {
+	.owner          = THIS_MODULE,
+	.name           = "cxgb4_clock",
+	.max_adj        = MAX_PTP_FREQ_ADJ,
+	.n_alarm        = 0,
+	.n_ext_ts       = 0,
+	.n_per_out      = 0,
+	.pps            = 0,
+	.adjfine        = cxgb4_ptp_adjfine,
+	.adjtime        = cxgb4_ptp_adjtime,
+	.gettime64      = cxgb4_ptp_gettime,
+	.settime64      = cxgb4_ptp_settime,
+	.enable         = cxgb4_ptp_enable,
+};
+
+/**
+ * cxgb4_ptp_init - initialize PTP for devices which support it
+ * @adapter: board private structure
+ *
+ * This function performs the required steps for enabling PTP support.
+ */
+void cxgb4_ptp_init(struct adapter *adapter)
+{
+	struct timespec64 now;
+	 /* no need to create a clock device if we already have one */
+	if (!IS_ERR_OR_NULL(adapter->ptp_clock))
+		return;
+
+	adapter->ptp_tx_skb = NULL;
+	adapter->ptp_clock_info = cxgb4_ptp_clock_info;
+	spin_lock_init(&adapter->ptp_lock);
+
+	adapter->ptp_clock = ptp_clock_register(&adapter->ptp_clock_info,
+						&adapter->pdev->dev);
+	if (IS_ERR_OR_NULL(adapter->ptp_clock)) {
+		adapter->ptp_clock = NULL;
+		dev_err(adapter->pdev_dev,
+			"PTP %s Clock registration has failed\n", __func__);
+		return;
+	}
+
+	now = ktime_to_timespec64(ktime_get_real());
+	cxgb4_init_ptp_timer(adapter);
+	if (cxgb4_ptp_settime(&adapter->ptp_clock_info, &now) < 0) {
+		ptp_clock_unregister(adapter->ptp_clock);
+		adapter->ptp_clock = NULL;
+	}
+}
+
+/**
+ * cxgb4_ptp_stop - disable PTP device and stop the overflow check
+ * @adapter: board private structure
+ *
+ * Stop the PTP support.
+ */
+void cxgb4_ptp_stop(struct adapter *adapter)
+{
+	if (adapter->ptp_tx_skb) {
+		dev_kfree_skb_any(adapter->ptp_tx_skb);
+		adapter->ptp_tx_skb = NULL;
+	}
+
+	if (adapter->ptp_clock) {
+		ptp_clock_unregister(adapter->ptp_clock);
+		adapter->ptp_clock = NULL;
+	}
+}