Merge branch 'dsa-microchip-ptp'

Arun Ramadoss says:

====================
net: dsa: microchip: add PTP support for KSZ9563/KSZ8563 and LAN937x

KSZ9563/KSZ8563 and  LAN937x switch are capable for supporting IEEE 1588 PTP
protocol.  LAN937x has the same PTP register set similar to KSZ9563, hence the
implementation has been made common for the KSZ switches.  KSZ9563 does not
support two step timestamping but LAN937x supports both.  Tested the 1step &
2step p2p timestamping in LAN937x and p2p1step timestamping in KSZ9563.

This patch series is based on the Christian Eggers PTP support for KSZ9563.
Applied the Christian patch and updated as per the latest refactoring of KSZ
series code. The features added on top are PTP packet Interrupt
implementation based on nested handler, LAN937x two step timestamping and
programmable per_out pins.

Link: https://www.spinics.net/lists/netdev/msg705531.html

Patch v7 -> v8
- set skb->ip_summed = CHECKSUM_NONE after updating the checksum

Patch v6 -> v7
- Corrected the misplaced spaces and tabs
- Added mutex lock in do_aux_work
- Replaced 0/1 with false/true for ts_en
- SKB_TX_INPROGRESS flag is set before dsa_enqueue_skb
- Removed the fallthrough keyword
- pdelay_resp header correction is performed based on
  KSZ_SKB_CB(skb)->update_correction instead of clone

Patch v5 -> v6
- Rebased to latest net-next and renamed from RFC to patch net-next.

Patch v4 -> v5
- Replaced irq_domain_add_simple with irq_doamin_add_linear
- Used the helper diff_by_scaled_ppm() for adjfine.

Patch v3 -> v4
- removed IRQF_TRIGGER_FALLING from the request_threaded_irq of ptp msg
- addressed review comments on patch 10 periodic output
- added sign off in patch 6 & 9
- reverted to set PTP_1STEP bit for lan937x which is missed during v3 regression

Patch v2-> v3
- used port_rxtstamp for reconstructing the absolute timestamp instead of
tagger function pointer.
- Reverted to setting of 802.1As bit.

Patch v1 -> v2
- GPIO perout enable bit is different for LAN937x and KSZ9x. Added new patch
for configuring LAN937x programmable pins.
- PTP enabled in hardware based on both tx and rx timestamping of all the user
ports.
- Replaced setting of 802.1AS bit with P2P bit in PTP_MSG_CONF1 register.

RFC v2 -> Patch v1
- Changed the patch author based on past patch submission
- Changed the commit message prefix as net: dsa: microchip: ptp
Individual patch changes are listed in correspondig commits.

RFC v1 -> v2
- Added the p2p1step timestamping and conditional execution of 2 step for
  LAN937x only.
- Added the periodic output support
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

MAINTAINERS

@@ -13710,6 +13710,7 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml
 F:	Documentation/devicetree/bindings/net/dsa/microchip,lan937x.yaml
 F:	drivers/net/dsa/microchip/*
+F:	include/linux/dsa/ksz_common.h
 F:	include/linux/platform_data/microchip-ksz.h
 F:	net/dsa/tag_ksz.c
 

drivers/net/dsa/microchip/Kconfig

@@ -11,6 +11,7 @@ menuconfig NET_DSA_MICROCHIP_KSZ_COMMON
 config NET_DSA_MICROCHIP_KSZ9477_I2C
 	tristate "KSZ series I2C connected switch driver"
 	depends on NET_DSA_MICROCHIP_KSZ_COMMON && I2C
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select REGMAP_I2C
 	help
 	  Select to enable support for registering switches configured through I2C.
@@ -18,10 +19,20 @@ config NET_DSA_MICROCHIP_KSZ9477_I2C
 config NET_DSA_MICROCHIP_KSZ_SPI
 	tristate "KSZ series SPI connected switch driver"
 	depends on NET_DSA_MICROCHIP_KSZ_COMMON && SPI
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select REGMAP_SPI
 	help
 	  Select to enable support for registering switches configured through SPI.
 
+config NET_DSA_MICROCHIP_KSZ_PTP
+	bool "Support for the PTP clock on the KSZ9563/LAN937x Ethernet Switch"
+	depends on NET_DSA_MICROCHIP_KSZ_COMMON && PTP_1588_CLOCK
+	help
+	  Select to enable support for timestamping & PTP clock manipulation in
+	  KSZ8563/KSZ9563/LAN937x series of switches. KSZ9563/KSZ8563 supports
+	  only one step timestamping. LAN937x switch supports both one step and
+	  two step timestamping.
+
 config NET_DSA_MICROCHIP_KSZ8863_SMI
 	tristate "KSZ series SMI connected switch driver"
 	depends on NET_DSA_MICROCHIP_KSZ_COMMON

drivers/net/dsa/microchip/Makefile

@@ -4,6 +4,11 @@ ksz_switch-objs := ksz_common.o
 ksz_switch-objs += ksz9477.o
 ksz_switch-objs += ksz8795.o
 ksz_switch-objs += lan937x_main.o
+
+ifdef CONFIG_NET_DSA_MICROCHIP_KSZ_PTP
+ksz_switch-objs += ksz_ptp.o
+endif
+
 obj-$(CONFIG_NET_DSA_MICROCHIP_KSZ9477_I2C)	+= ksz9477_i2c.o
 obj-$(CONFIG_NET_DSA_MICROCHIP_KSZ_SPI)		+= ksz_spi.o
 obj-$(CONFIG_NET_DSA_MICROCHIP_KSZ8863_SMI)	+= ksz8863_smi.o

drivers/net/dsa/microchip/ksz_common.c

@@ -6,6 +6,7 @@
  */
 
 #include <linux/delay.h>
+#include <linux/dsa/ksz_common.h>
 #include <linux/export.h>
 #include <linux/gpio/consumer.h>
 #include <linux/kernel.h>
@@ -25,6 +26,7 @@
 #include <net/switchdev.h>
 
 #include "ksz_common.h"
+#include "ksz_ptp.h"
 #include "ksz8.h"
 #include "ksz9477.h"
 #include "lan937x.h"
@@ -2099,13 +2101,23 @@ static int ksz_setup(struct dsa_switch *ds)
 			ret = ksz_pirq_setup(dev, dp->index);
 			if (ret)
 				goto out_girq;
+
+			ret = ksz_ptp_irq_setup(ds, dp->index);
+			if (ret)
+				goto out_pirq;
 		}
 	}
 
+	ret = ksz_ptp_clock_register(ds);
+	if (ret) {
+		dev_err(dev->dev, "Failed to register PTP clock: %d\n", ret);
+		goto out_ptpirq;
+	}
+
 	ret = ksz_mdio_register(dev);
 	if (ret < 0) {
 		dev_err(dev->dev, "failed to register the mdio");
-		goto out_pirq;
+		goto out_ptp_clock_unregister;
 	}
 
 	/* start switch */
@@ -2114,6 +2126,12 @@ static int ksz_setup(struct dsa_switch *ds)
 
 	return 0;
 
+out_ptp_clock_unregister:
+	ksz_ptp_clock_unregister(ds);
+out_ptpirq:
+	if (dev->irq > 0)
+		dsa_switch_for_each_user_port(dp, dev->ds)
+			ksz_ptp_irq_free(ds, dp->index);
 out_pirq:
 	if (dev->irq > 0)
 		dsa_switch_for_each_user_port(dp, dev->ds)
@@ -2130,9 +2148,14 @@ static void ksz_teardown(struct dsa_switch *ds)
 	struct ksz_device *dev = ds->priv;
 	struct dsa_port *dp;
 
+	ksz_ptp_clock_unregister(ds);
+
 	if (dev->irq > 0) {
-		dsa_switch_for_each_user_port(dp, dev->ds)
+		dsa_switch_for_each_user_port(dp, dev->ds) {
+			ksz_ptp_irq_free(ds, dp->index);
+
 			ksz_irq_free(&dev->ports[dp->index].pirq);
+		}
 
 		ksz_irq_free(&dev->girq);
 	}
@@ -2517,6 +2540,17 @@ static enum dsa_tag_protocol ksz_get_tag_protocol(struct dsa_switch *ds,
 	return proto;
 }
 
+static int ksz_connect_tag_protocol(struct dsa_switch *ds,
+				    enum dsa_tag_protocol proto)
+{
+	struct ksz_tagger_data *tagger_data;
+
+	tagger_data = ksz_tagger_data(ds);
+	tagger_data->xmit_work_fn = ksz_port_deferred_xmit;
+
+	return 0;
+}
+
 static int ksz_port_vlan_filtering(struct dsa_switch *ds, int port,
 				   bool flag, struct netlink_ext_ack *extack)
 {
@@ -2932,6 +2966,7 @@ static int ksz_switch_detect(struct ksz_device *dev)
 
 static const struct dsa_switch_ops ksz_switch_ops = {
 	.get_tag_protocol	= ksz_get_tag_protocol,
+	.connect_tag_protocol   = ksz_connect_tag_protocol,
 	.get_phy_flags		= ksz_get_phy_flags,
 	.setup			= ksz_setup,
 	.teardown		= ksz_teardown,
@@ -2966,6 +3001,11 @@ static const struct dsa_switch_ops ksz_switch_ops = {
 	.get_pause_stats	= ksz_get_pause_stats,
 	.port_change_mtu	= ksz_change_mtu,
 	.port_max_mtu		= ksz_max_mtu,
+	.get_ts_info		= ksz_get_ts_info,
+	.port_hwtstamp_get	= ksz_hwtstamp_get,
+	.port_hwtstamp_set	= ksz_hwtstamp_set,
+	.port_txtstamp		= ksz_port_txtstamp,
+	.port_rxtstamp		= ksz_port_rxtstamp,
 };
 
 struct ksz_device *ksz_switch_alloc(struct device *base, void *priv)

drivers/net/dsa/microchip/ksz_common.h

@@ -15,9 +15,12 @@
 #include <net/dsa.h>
 #include <linux/irq.h>
 
+#include "ksz_ptp.h"
+
 #define KSZ_MAX_NUM_PORTS 8
 
 struct ksz_device;
+struct ksz_port;
 
 struct vlan_table {
 	u32 table[3];
@@ -81,6 +84,14 @@ struct ksz_irq {
 	struct ksz_device *dev;
 };
 
+struct ksz_ptp_irq {
+	struct ksz_port *port;
+	u16 ts_reg;
+	bool ts_en;
+	char name[16];
+	int num;
+};
+
 struct ksz_port {
 	bool remove_tag;		/* Remove Tag flag set, for ksz8795 only */
 	bool learning;
@@ -100,6 +111,15 @@ struct ksz_port {
 	struct ksz_device *ksz_dev;
 	struct ksz_irq pirq;
 	u8 num;
+#if IS_ENABLED(CONFIG_NET_DSA_MICROCHIP_KSZ_PTP)
+	struct hwtstamp_config tstamp_config;
+	bool hwts_tx_en;
+	bool hwts_rx_en;
+	struct ksz_irq ptpirq;
+	struct ksz_ptp_irq ptpmsg_irq[3];
+	ktime_t tstamp_msg;
+	struct completion tstamp_msg_comp;
+#endif
 };
 
 struct ksz_device {
@@ -140,6 +160,7 @@ struct ksz_device {
 	u16 port_mask;
 	struct mutex lock_irq;		/* IRQ Access */
 	struct ksz_irq girq;
+	struct ksz_ptp_data ptp_data;
 };
 
 /* List of supported models */
@@ -443,6 +464,32 @@ static inline int ksz_write32(struct ksz_device *dev, u32 reg, u32 value)
 	return ret;
 }
 
+static inline int ksz_rmw16(struct ksz_device *dev, u32 reg, u16 mask,
+			    u16 value)
+{
+	int ret;
+
+	ret = regmap_update_bits(dev->regmap[1], reg, mask, value);
+	if (ret)
+		dev_err(dev->dev, "can't rmw 16bit reg 0x%x: %pe\n", reg,
+			ERR_PTR(ret));
+
+	return ret;
+}
+
+static inline int ksz_rmw32(struct ksz_device *dev, u32 reg, u32 mask,
+			    u32 value)
+{
+	int ret;
+
+	ret = regmap_update_bits(dev->regmap[2], reg, mask, value);
+	if (ret)
+		dev_err(dev->dev, "can't rmw 32bit reg 0x%x: %pe\n", reg,
+			ERR_PTR(ret));
+
+	return ret;
+}
+
 static inline int ksz_write64(struct ksz_device *dev, u32 reg, u64 value)
 {
 	u32 val[2];
@@ -591,6 +638,7 @@ static inline int is_lan937x(struct ksz_device *dev)
 #define REG_PORT_INT_MASK		0x001F
 
 #define PORT_SRC_PHY_INT		1
+#define PORT_SRC_PTP_INT		2
 
 #define KSZ8795_HUGE_PACKET_SIZE	2000
 #define KSZ8863_HUGE_PACKET_SIZE	1916

drivers/net/dsa/microchip/ksz_ptp.c

+// SPDX-License-Identifier: GPL-2.0
+/* Microchip KSZ PTP Implementation
+ *
+ * Copyright (C) 2020 ARRI Lighting
+ * Copyright (C) 2022 Microchip Technology Inc.
+ */
+
+#include <linux/dsa/ksz_common.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+#include <linux/kernel.h>
+#include <linux/ptp_classify.h>
+#include <linux/ptp_clock_kernel.h>
+
+#include "ksz_common.h"
+#include "ksz_ptp.h"
+#include "ksz_ptp_reg.h"
+
+#define ptp_caps_to_data(d) container_of((d), struct ksz_ptp_data, caps)
+#define ptp_data_to_ksz_dev(d) container_of((d), struct ksz_device, ptp_data)
+#define work_to_xmit_work(w) \
+		container_of((w), struct ksz_deferred_xmit_work, work)
+
+/* Sub-nanoseconds-adj,max * sub-nanoseconds / 40ns * 1ns
+ * = (2^30-1) * (2 ^ 32) / 40 ns * 1 ns = 6249999
+ */
+#define KSZ_MAX_DRIFT_CORR 6249999
+#define KSZ_MAX_PULSE_WIDTH 125000000LL
+
+#define KSZ_PTP_INC_NS 40ULL  /* HW clock is incremented every 40 ns (by 40) */
+#define KSZ_PTP_SUBNS_BITS 32
+
+#define KSZ_PTP_INT_START 13
+
+static int ksz_ptp_tou_gpio(struct ksz_device *dev)
+{
+	int ret;
+
+	if (!is_lan937x(dev))
+		return 0;
+
+	ret = ksz_rmw32(dev, REG_PTP_CTRL_STAT__4, GPIO_OUT,
+			GPIO_OUT);
+	if (ret)
+		return ret;
+
+	ret = ksz_rmw32(dev, REG_SW_GLOBAL_LED_OVR__4, LED_OVR_1 | LED_OVR_2,
+			LED_OVR_1 | LED_OVR_2);
+	if (ret)
+		return ret;
+
+	return ksz_rmw32(dev, REG_SW_GLOBAL_LED_SRC__4,
+			 LED_SRC_PTP_GPIO_1 | LED_SRC_PTP_GPIO_2,
+			 LED_SRC_PTP_GPIO_1 | LED_SRC_PTP_GPIO_2);
+}
+
+static int ksz_ptp_tou_reset(struct ksz_device *dev, u8 unit)
+{
+	u32 data;
+	int ret;
+
+	/* Reset trigger unit (clears TRIGGER_EN, but not GPIOSTATx) */
+	ret = ksz_rmw32(dev, REG_PTP_CTRL_STAT__4, TRIG_RESET, TRIG_RESET);
+
+	data = FIELD_PREP(TRIG_DONE_M, BIT(unit));
+	ret = ksz_write32(dev, REG_PTP_TRIG_STATUS__4, data);
+	if (ret)
+		return ret;
+
+	data = FIELD_PREP(TRIG_INT_M, BIT(unit));
+	ret = ksz_write32(dev, REG_PTP_INT_STATUS__4, data);
+	if (ret)
+		return ret;
+
+	/* Clear reset and set GPIO direction */
+	return ksz_rmw32(dev, REG_PTP_CTRL_STAT__4, (TRIG_RESET | TRIG_ENABLE),
+			 0);
+}
+
+static int ksz_ptp_tou_pulse_verify(u64 pulse_ns)
+{
+	u32 data;
+
+	if (pulse_ns & 0x3)
+		return -EINVAL;
+
+	data = (pulse_ns / 8);
+	if (!FIELD_FIT(TRIG_PULSE_WIDTH_M, data))
+		return -ERANGE;
+
+	return 0;
+}
+
+static int ksz_ptp_tou_target_time_set(struct ksz_device *dev,
+				       struct timespec64 const *ts)
+{
+	int ret;
+
+	/* Hardware has only 32 bit */
+	if ((ts->tv_sec & 0xffffffff) != ts->tv_sec)
+		return -EINVAL;
+
+	ret = ksz_write32(dev, REG_TRIG_TARGET_NANOSEC, ts->tv_nsec);
+	if (ret)
+		return ret;
+
+	ret = ksz_write32(dev, REG_TRIG_TARGET_SEC, ts->tv_sec);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int ksz_ptp_tou_start(struct ksz_device *dev, u8 unit)
+{
+	u32 data;
+	int ret;
+
+	ret = ksz_rmw32(dev, REG_PTP_CTRL_STAT__4, TRIG_ENABLE, TRIG_ENABLE);
+	if (ret)
+		return ret;
+
+	/* Check error flag:
+	 * - the ACTIVE flag is NOT cleared an error!
+	 */
+	ret = ksz_read32(dev, REG_PTP_TRIG_STATUS__4, &data);
+	if (ret)
+		return ret;
+
+	if (FIELD_GET(TRIG_ERROR_M, data) & (1 << unit)) {
+		dev_err(dev->dev, "%s: Trigger unit%d error!\n", __func__,
+			unit);
+		ret = -EIO;
+		/* Unit will be reset on next access */
+		return ret;
+	}
+
+	return 0;
+}
+
+static int ksz_ptp_configure_perout(struct ksz_device *dev,
+				    u32 cycle_width_ns, u32 pulse_width_ns,
+				    struct timespec64 const *target_time,
+				    u8 index)
+{
+	u32 data;
+	int ret;
+
+	data = FIELD_PREP(TRIG_NOTIFY, 1) |
+		FIELD_PREP(TRIG_GPO_M, index) |
+		FIELD_PREP(TRIG_PATTERN_M, TRIG_POS_PERIOD);
+	ret = ksz_write32(dev, REG_TRIG_CTRL__4, data);
+	if (ret)
+		return ret;
+
+	ret = ksz_write32(dev, REG_TRIG_CYCLE_WIDTH, cycle_width_ns);
+	if (ret)
+		return ret;
+
+	/* Set cycle count 0 - Infinite */
+	ret = ksz_rmw32(dev, REG_TRIG_CYCLE_CNT, TRIG_CYCLE_CNT_M, 0);
+	if (ret)
+		return ret;
+
+	data = (pulse_width_ns / 8);
+	ret = ksz_write32(dev, REG_TRIG_PULSE_WIDTH__4, data);
+	if (ret)
+		return ret;
+
+	ret = ksz_ptp_tou_target_time_set(dev, target_time);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int ksz_ptp_enable_perout(struct ksz_device *dev,
+				 struct ptp_perout_request const *request,
+				 int on)
+{
+	struct ksz_ptp_data *ptp_data = &dev->ptp_data;
+	u64 req_pulse_width_ns;
+	u64 cycle_width_ns;
+	u64 pulse_width_ns;
+	int pin = 0;
+	u32 data32;
+	int ret;
+
+	if (request->flags & ~PTP_PEROUT_DUTY_CYCLE)
+		return -EOPNOTSUPP;
+
+	if (ptp_data->tou_mode != KSZ_PTP_TOU_PEROUT &&
+	    ptp_data->tou_mode != KSZ_PTP_TOU_IDLE)
+		return -EBUSY;
+
+	pin = ptp_find_pin(ptp_data->clock, PTP_PF_PEROUT, request->index);
+	if (pin < 0)
+		return -EINVAL;
+
+	data32 = FIELD_PREP(PTP_GPIO_INDEX, pin) |
+		 FIELD_PREP(PTP_TOU_INDEX, request->index);
+	ret = ksz_rmw32(dev, REG_PTP_UNIT_INDEX__4,
+			PTP_GPIO_INDEX | PTP_TOU_INDEX, data32);
+	if (ret)
+		return ret;
+
+	ret = ksz_ptp_tou_reset(dev, request->index);
+	if (ret)
+		return ret;
+
+	if (!on) {
+		ptp_data->tou_mode = KSZ_PTP_TOU_IDLE;
+		return 0;
+	}
+
+	ptp_data->perout_target_time_first.tv_sec  = request->start.sec;
+	ptp_data->perout_target_time_first.tv_nsec = request->start.nsec;
+
+	ptp_data->perout_period.tv_sec = request->period.sec;
+	ptp_data->perout_period.tv_nsec = request->period.nsec;
+
+	cycle_width_ns = timespec64_to_ns(&ptp_data->perout_period);
+	if ((cycle_width_ns & TRIG_CYCLE_WIDTH_M) != cycle_width_ns)
+		return -EINVAL;
+
+	if (request->flags & PTP_PEROUT_DUTY_CYCLE) {
+		pulse_width_ns = request->on.sec * NSEC_PER_SEC +
+			request->on.nsec;
+	} else {
+		/* Use a duty cycle of 50%. Maximum pulse width supported by the
+		 * hardware is a little bit more than 125 ms.
+		 */
+		req_pulse_width_ns = (request->period.sec * NSEC_PER_SEC +
+				      request->period.nsec) / 2;
+		pulse_width_ns = min_t(u64, req_pulse_width_ns,
+				       KSZ_MAX_PULSE_WIDTH);
+	}
+
+	ret = ksz_ptp_tou_pulse_verify(pulse_width_ns);
+	if (ret)
+		return ret;
+
+	ret = ksz_ptp_configure_perout(dev, cycle_width_ns, pulse_width_ns,
+				       &ptp_data->perout_target_time_first,
+				       pin);
+	if (ret)
+		return ret;
+
+	ret = ksz_ptp_tou_gpio(dev);
+	if (ret)
+		return ret;
+
+	ret = ksz_ptp_tou_start(dev, request->index);
+	if (ret)
+		return ret;
+
+	ptp_data->tou_mode = KSZ_PTP_TOU_PEROUT;
+
+	return 0;
+}
+
+static int ksz_ptp_enable_mode(struct ksz_device *dev)
+{
+	struct ksz_tagger_data *tagger_data = ksz_tagger_data(dev->ds);
+	struct ksz_ptp_data *ptp_data = &dev->ptp_data;
+	struct ksz_port *prt;
+	struct dsa_port *dp;
+	bool tag_en = false;
+	int ret;
+
+	dsa_switch_for_each_user_port(dp, dev->ds) {
+		prt = &dev->ports[dp->index];
+		if (prt->hwts_tx_en || prt->hwts_rx_en) {
+			tag_en = true;
+			break;
+		}
+	}
+
+	if (tag_en) {
+		ret = ptp_schedule_worker(ptp_data->clock, 0);
+		if (ret)
+			return ret;
+	} else {
+		ptp_cancel_worker_sync(ptp_data->clock);
+	}
+
+	tagger_data->hwtstamp_set_state(dev->ds, tag_en);
+
+	return ksz_rmw16(dev, REG_PTP_MSG_CONF1, PTP_ENABLE,
+			 tag_en ? PTP_ENABLE : 0);
+}
+
+/* The function is return back the capability of timestamping feature when
+ * requested through ethtool -T <interface> utility
+ */
+int ksz_get_ts_info(struct dsa_switch *ds, int port, struct ethtool_ts_info *ts)
+{
+	struct ksz_device *dev = ds->priv;
+	struct ksz_ptp_data *ptp_data;
+
+	ptp_data = &dev->ptp_data;
+
+	if (!ptp_data->clock)
+		return -ENODEV;
+
+	ts->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE |
+			      SOF_TIMESTAMPING_RX_HARDWARE |
+			      SOF_TIMESTAMPING_RAW_HARDWARE;
+
+	ts->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ONESTEP_P2P);
+
+	if (is_lan937x(dev))
+		ts->tx_types |= BIT(HWTSTAMP_TX_ON);
+
+	ts->rx_filters = BIT(HWTSTAMP_FILTER_NONE) |
+			 BIT(HWTSTAMP_FILTER_PTP_V2_L4_EVENT) |
+			 BIT(HWTSTAMP_FILTER_PTP_V2_L2_EVENT) |
+			 BIT(HWTSTAMP_FILTER_PTP_V2_EVENT);
+
+	ts->phc_index = ptp_clock_index(ptp_data->clock);
+
+	return 0;
+}
+
+int ksz_hwtstamp_get(struct dsa_switch *ds, int port, struct ifreq *ifr)
+{
+	struct ksz_device *dev = ds->priv;
+	struct hwtstamp_config *config;
+	struct ksz_port *prt;
+
+	prt = &dev->ports[port];
+	config = &prt->tstamp_config;
+
+	return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ?
+		-EFAULT : 0;
+}
+
+static int ksz_set_hwtstamp_config(struct ksz_device *dev,
+				   struct ksz_port *prt,
+				   struct hwtstamp_config *config)
+{
+	int ret;
+
+	if (config->flags)
+		return -EINVAL;
+
+	switch (config->tx_type) {
+	case HWTSTAMP_TX_OFF:
+		prt->ptpmsg_irq[KSZ_SYNC_MSG].ts_en  = false;
+		prt->ptpmsg_irq[KSZ_XDREQ_MSG].ts_en = false;
+		prt->ptpmsg_irq[KSZ_PDRES_MSG].ts_en = false;
+		prt->hwts_tx_en = false;
+		break;
+	case HWTSTAMP_TX_ONESTEP_P2P:
+		prt->ptpmsg_irq[KSZ_SYNC_MSG].ts_en  = false;
+		prt->ptpmsg_irq[KSZ_XDREQ_MSG].ts_en = true;
+		prt->ptpmsg_irq[KSZ_PDRES_MSG].ts_en = false;
+		prt->hwts_tx_en = true;
+
+		ret = ksz_rmw16(dev, REG_PTP_MSG_CONF1, PTP_1STEP, PTP_1STEP);
+		if (ret)
+			return ret;
+
+		break;
+	case HWTSTAMP_TX_ON:
+		if (!is_lan937x(dev))
+			return -ERANGE;
+
+		prt->ptpmsg_irq[KSZ_SYNC_MSG].ts_en  = true;
+		prt->ptpmsg_irq[KSZ_XDREQ_MSG].ts_en = true;
+		prt->ptpmsg_irq[KSZ_PDRES_MSG].ts_en = true;
+		prt->hwts_tx_en = true;
+
+		ret = ksz_rmw16(dev, REG_PTP_MSG_CONF1, PTP_1STEP, 0);
+		if (ret)
+			return ret;
+
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	switch (config->rx_filter) {
+	case HWTSTAMP_FILTER_NONE:
+		prt->hwts_rx_en = false;
+		break;
+	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+		config->rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
+		prt->hwts_rx_en = true;
+		break;
+	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+		config->rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
+		prt->hwts_rx_en = true;
+		break;
+	case HWTSTAMP_FILTER_PTP_V2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_SYNC:
+		config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+		prt->hwts_rx_en = true;
+		break;
+	default:
+		config->rx_filter = HWTSTAMP_FILTER_NONE;
+		return -ERANGE;
+	}
+
+	return ksz_ptp_enable_mode(dev);
+}
+
+int ksz_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr)
+{
+	struct ksz_device *dev = ds->priv;
+	struct hwtstamp_config config;
+	struct ksz_port *prt;
+	int ret;
+
+	prt = &dev->ports[port];
+
+	ret = copy_from_user(&config, ifr->ifr_data, sizeof(config));
+	if (ret)
+		return ret;
+
+	ret = ksz_set_hwtstamp_config(dev, prt, &config);
+	if (ret)
+		return ret;
+
+	memcpy(&prt->tstamp_config, &config, sizeof(config));
+
+	return copy_to_user(ifr->ifr_data, &config, sizeof(config));
+}
+
+static ktime_t ksz_tstamp_reconstruct(struct ksz_device *dev, ktime_t tstamp)
+{
+	struct timespec64 ptp_clock_time;
+	struct ksz_ptp_data *ptp_data;
+	struct timespec64 diff;
+	struct timespec64 ts;
+
+	ptp_data = &dev->ptp_data;
+	ts = ktime_to_timespec64(tstamp);
+
+	spin_lock_bh(&ptp_data->clock_lock);
+	ptp_clock_time = ptp_data->clock_time;
+	spin_unlock_bh(&ptp_data->clock_lock);
+
+	/* calculate full time from partial time stamp */
+	ts.tv_sec = (ptp_clock_time.tv_sec & ~3) | ts.tv_sec;
+
+	/* find nearest possible point in time */
+	diff = timespec64_sub(ts, ptp_clock_time);
+	if (diff.tv_sec > 2)
+		ts.tv_sec -= 4;
+	else if (diff.tv_sec < -2)
+		ts.tv_sec += 4;
+
+	return timespec64_to_ktime(ts);
+}
+
+bool ksz_port_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb,
+		       unsigned int type)
+{
+	struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb);
+	struct ksz_device *dev = ds->priv;
+	struct ptp_header *ptp_hdr;
+	struct ksz_port *prt;
+	u8 ptp_msg_type;
+	ktime_t tstamp;
+	s64 correction;
+
+	prt = &dev->ports[port];
+
+	tstamp = KSZ_SKB_CB(skb)->tstamp;
+	memset(hwtstamps, 0, sizeof(*hwtstamps));
+	hwtstamps->hwtstamp = ksz_tstamp_reconstruct(dev, tstamp);
+
+	if (prt->tstamp_config.tx_type != HWTSTAMP_TX_ONESTEP_P2P)
+		goto out;
+
+	ptp_hdr = ptp_parse_header(skb, type);
+	if (!ptp_hdr)
+		goto out;
+
+	ptp_msg_type = ptp_get_msgtype(ptp_hdr, type);
+	if (ptp_msg_type != PTP_MSGTYPE_PDELAY_REQ)
+		goto out;
+
+	/* Only subtract the partial time stamp from the correction field.  When
+	 * the hardware adds the egress time stamp to the correction field of
+	 * the PDelay_Resp message on tx, also only the partial time stamp will
+	 * be added.
+	 */
+	correction = (s64)get_unaligned_be64(&ptp_hdr->correction);
+	correction -= ktime_to_ns(tstamp) << 16;
+
+	ptp_header_update_correction(skb, type, ptp_hdr, correction);
+
+out:
+	return false;
+}
+
+void ksz_port_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb)
+{
+	struct ksz_device *dev = ds->priv;
+	struct ptp_header *hdr;
+	struct sk_buff *clone;
+	struct ksz_port *prt;
+	unsigned int type;
+	u8 ptp_msg_type;
+
+	prt = &dev->ports[port];
+
+	if (!prt->hwts_tx_en)
+		return;
+
+	type = ptp_classify_raw(skb);
+	if (type == PTP_CLASS_NONE)
+		return;
+
+	hdr = ptp_parse_header(skb, type);
+	if (!hdr)
+		return;
+
+	ptp_msg_type = ptp_get_msgtype(hdr, type);
+
+	switch (ptp_msg_type) {
+	case PTP_MSGTYPE_SYNC:
+		if (prt->tstamp_config.tx_type == HWTSTAMP_TX_ONESTEP_P2P)
+			return;
+		break;
+	case PTP_MSGTYPE_PDELAY_REQ:
+		break;
+	case PTP_MSGTYPE_PDELAY_RESP:
+		if (prt->tstamp_config.tx_type == HWTSTAMP_TX_ONESTEP_P2P) {
+			KSZ_SKB_CB(skb)->ptp_type = type;
+			KSZ_SKB_CB(skb)->update_correction = true;
+			return;
+		}
+		break;
+
+	default:
+		return;
+	}
+
+	clone = skb_clone_sk(skb);
+	if (!clone)
+		return;
+
+	/* caching the value to be used in tag_ksz.c */
+	KSZ_SKB_CB(skb)->clone = clone;
+}
+
+static void ksz_ptp_txtstamp_skb(struct ksz_device *dev,
+				 struct ksz_port *prt, struct sk_buff *skb)
+{
+	struct skb_shared_hwtstamps hwtstamps = {};
+	int ret;
+
+	/* timeout must include DSA master to transmit data, tstamp latency,
+	 * IRQ latency and time for reading the time stamp.
+	 */
+	ret = wait_for_completion_timeout(&prt->tstamp_msg_comp,
+					  msecs_to_jiffies(100));
+	if (!ret)
+		return;
+
+	hwtstamps.hwtstamp = prt->tstamp_msg;
+	skb_complete_tx_timestamp(skb, &hwtstamps);
+}
+
+void ksz_port_deferred_xmit(struct kthread_work *work)
+{
+	struct ksz_deferred_xmit_work *xmit_work = work_to_xmit_work(work);
+	struct sk_buff *clone, *skb = xmit_work->skb;
+	struct dsa_switch *ds = xmit_work->dp->ds;
+	struct ksz_device *dev = ds->priv;
+	struct ksz_port *prt;
+
+	prt = &dev->ports[xmit_work->dp->index];
+
+	clone = KSZ_SKB_CB(skb)->clone;
+
+	skb_shinfo(clone)->tx_flags |= SKBTX_IN_PROGRESS;
+
+	reinit_completion(&prt->tstamp_msg_comp);
+
+	dsa_enqueue_skb(skb, skb->dev);
+
+	ksz_ptp_txtstamp_skb(dev, prt, clone);
+
+	kfree(xmit_work);
+}
+
+static int _ksz_ptp_gettime(struct ksz_device *dev, struct timespec64 *ts)
+{
+	u32 nanoseconds;
+	u32 seconds;
+	u8 phase;
+	int ret;
+
+	/* Copy current PTP clock into shadow registers and read */
+	ret = ksz_rmw16(dev, REG_PTP_CLK_CTRL, PTP_READ_TIME, PTP_READ_TIME);
+	if (ret)
+		return ret;
+
+	ret = ksz_read8(dev, REG_PTP_RTC_SUB_NANOSEC__2, &phase);
+	if (ret)
+		return ret;
+
+	ret = ksz_read32(dev, REG_PTP_RTC_NANOSEC, &nanoseconds);
+	if (ret)
+		return ret;
+
+	ret = ksz_read32(dev, REG_PTP_RTC_SEC, &seconds);
+	if (ret)
+		return ret;
+
+	ts->tv_sec = seconds;
+	ts->tv_nsec = nanoseconds + phase * 8;
+
+	return 0;
+}
+
+static int ksz_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
+{
+	struct ksz_ptp_data *ptp_data = ptp_caps_to_data(ptp);
+	struct ksz_device *dev = ptp_data_to_ksz_dev(ptp_data);
+	int ret;
+
+	mutex_lock(&ptp_data->lock);
+	ret = _ksz_ptp_gettime(dev, ts);
+	mutex_unlock(&ptp_data->lock);
+
+	return ret;
+}
+
+static int ksz_ptp_restart_perout(struct ksz_device *dev)
+{
+	struct ksz_ptp_data *ptp_data = &dev->ptp_data;
+	s64 now_ns, first_ns, period_ns, next_ns;
+	struct ptp_perout_request request;
+	struct timespec64 next;
+	struct timespec64 now;
+	unsigned int count;
+	int ret;
+
+	dev_info(dev->dev, "Restarting periodic output signal\n");
+
+	ret = _ksz_ptp_gettime(dev, &now);
+	if (ret)
+		return ret;
+
+	now_ns = timespec64_to_ns(&now);
+	first_ns = timespec64_to_ns(&ptp_data->perout_target_time_first);
+
+	/* Calculate next perout event based on start time and period */
+	period_ns = timespec64_to_ns(&ptp_data->perout_period);
+
+	if (first_ns < now_ns) {
+		count = div_u64(now_ns - first_ns, period_ns);
+		next_ns = first_ns + count * period_ns;
+	} else {
+		next_ns = first_ns;
+	}
+
+	/* Ensure 100 ms guard time prior next event */
+	while (next_ns < now_ns + 100000000)
+		next_ns += period_ns;
+
+	/* Restart periodic output signal */
+	next = ns_to_timespec64(next_ns);
+	request.start.sec  = next.tv_sec;
+	request.start.nsec = next.tv_nsec;
+	request.period.sec  = ptp_data->perout_period.tv_sec;
+	request.period.nsec = ptp_data->perout_period.tv_nsec;
+	request.index = 0;
+	request.flags = 0;
+
+	return ksz_ptp_enable_perout(dev, &request, 1);
+}
+
+static int ksz_ptp_settime(struct ptp_clock_info *ptp,
+			   const struct timespec64 *ts)
+{
+	struct ksz_ptp_data *ptp_data = ptp_caps_to_data(ptp);
+	struct ksz_device *dev = ptp_data_to_ksz_dev(ptp_data);
+	int ret;
+
+	mutex_lock(&ptp_data->lock);
+
+	/* Write to shadow registers and Load PTP clock */
+	ret = ksz_write16(dev, REG_PTP_RTC_SUB_NANOSEC__2, PTP_RTC_0NS);
+	if (ret)
+		goto unlock;
+
+	ret = ksz_write32(dev, REG_PTP_RTC_NANOSEC, ts->tv_nsec);
+	if (ret)
+		goto unlock;
+
+	ret = ksz_write32(dev, REG_PTP_RTC_SEC, ts->tv_sec);
+	if (ret)
+		goto unlock;
+
+	ret = ksz_rmw16(dev, REG_PTP_CLK_CTRL, PTP_LOAD_TIME, PTP_LOAD_TIME);
+	if (ret)
+		goto unlock;
+
+	switch (ptp_data->tou_mode) {
+	case KSZ_PTP_TOU_IDLE:
+		break;
+
+	case KSZ_PTP_TOU_PEROUT:
+		ret = ksz_ptp_restart_perout(dev);
+		if (ret)
+			goto unlock;
+
+		break;
+	}
+
+	spin_lock_bh(&ptp_data->clock_lock);
+	ptp_data->clock_time = *ts;
+	spin_unlock_bh(&ptp_data->clock_lock);
+
+unlock:
+	mutex_unlock(&ptp_data->lock);
+
+	return ret;
+}
+
+static int ksz_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
+{
+	struct ksz_ptp_data *ptp_data = ptp_caps_to_data(ptp);
+	struct ksz_device *dev = ptp_data_to_ksz_dev(ptp_data);
+	u64 base, adj;
+	bool negative;
+	u32 data32;
+	int ret;
+
+	mutex_lock(&ptp_data->lock);
+
+	if (scaled_ppm) {
+		base = KSZ_PTP_INC_NS << KSZ_PTP_SUBNS_BITS;
+		negative = diff_by_scaled_ppm(base, scaled_ppm, &adj);
+
+		data32 = (u32)adj;
+		data32 &= PTP_SUBNANOSEC_M;
+		if (!negative)
+			data32 |= PTP_RATE_DIR;
+
+		ret = ksz_write32(dev, REG_PTP_SUBNANOSEC_RATE, data32);
+		if (ret)
+			goto unlock;
+
+		ret = ksz_rmw16(dev, REG_PTP_CLK_CTRL, PTP_CLK_ADJ_ENABLE,
+				PTP_CLK_ADJ_ENABLE);
+		if (ret)
+			goto unlock;
+	} else {
+		ret = ksz_rmw16(dev, REG_PTP_CLK_CTRL, PTP_CLK_ADJ_ENABLE, 0);
+		if (ret)
+			goto unlock;
+	}
+
+unlock:
+	mutex_unlock(&ptp_data->lock);
+	return ret;
+}
+
+static int ksz_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+	struct ksz_ptp_data *ptp_data = ptp_caps_to_data(ptp);
+	struct ksz_device *dev = ptp_data_to_ksz_dev(ptp_data);
+	struct timespec64 delta64 = ns_to_timespec64(delta);
+	s32 sec, nsec;
+	u16 data16;
+	int ret;
+
+	mutex_lock(&ptp_data->lock);
+
+	/* do not use ns_to_timespec64(),
+	 * both sec and nsec are subtracted by hw
+	 */
+	sec = div_s64_rem(delta, NSEC_PER_SEC, &nsec);
+
+	ret = ksz_write32(dev, REG_PTP_RTC_NANOSEC, abs(nsec));
+	if (ret)
+		goto unlock;
+
+	ret = ksz_write32(dev, REG_PTP_RTC_SEC, abs(sec));
+	if (ret)
+		goto unlock;
+
+	ret = ksz_read16(dev, REG_PTP_CLK_CTRL, &data16);
+	if (ret)
+		goto unlock;
+
+	data16 |= PTP_STEP_ADJ;
+
+	/* PTP_STEP_DIR -- 0: subtract, 1: add */
+	if (delta < 0)
+		data16 &= ~PTP_STEP_DIR;
+	else
+		data16 |= PTP_STEP_DIR;
+
+	ret = ksz_write16(dev, REG_PTP_CLK_CTRL, data16);
+	if (ret)
+		goto unlock;
+
+	switch (ptp_data->tou_mode) {
+	case KSZ_PTP_TOU_IDLE:
+		break;
+
+	case KSZ_PTP_TOU_PEROUT:
+		ret = ksz_ptp_restart_perout(dev);
+		if (ret)
+			goto unlock;
+
+		break;
+	}
+
+	spin_lock_bh(&ptp_data->clock_lock);
+	ptp_data->clock_time = timespec64_add(ptp_data->clock_time, delta64);
+	spin_unlock_bh(&ptp_data->clock_lock);
+
+unlock:
+	mutex_unlock(&ptp_data->lock);
+	return ret;
+}
+
+static int ksz_ptp_enable(struct ptp_clock_info *ptp,
+			  struct ptp_clock_request *req, int on)
+{
+	struct ksz_ptp_data *ptp_data = ptp_caps_to_data(ptp);
+	struct ksz_device *dev = ptp_data_to_ksz_dev(ptp_data);
+	int ret;
+
+	switch (req->type) {
+	case PTP_CLK_REQ_PEROUT:
+		mutex_lock(&ptp_data->lock);
+		ret = ksz_ptp_enable_perout(dev, &req->perout, on);
+		mutex_unlock(&ptp_data->lock);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return ret;
+}
+
+static int ksz_ptp_verify_pin(struct ptp_clock_info *ptp, unsigned int pin,
+			      enum ptp_pin_function func, unsigned int chan)
+{
+	int ret = 0;
+
+	switch (func) {
+	case PTP_PF_NONE:
+	case PTP_PF_PEROUT:
+		break;
+	default:
+		ret = -1;
+		break;
+	}
+
+	return ret;
+}
+
+/*  Function is pointer to the do_aux_work in the ptp_clock capability */
+static long ksz_ptp_do_aux_work(struct ptp_clock_info *ptp)
+{
+	struct ksz_ptp_data *ptp_data = ptp_caps_to_data(ptp);
+	struct ksz_device *dev = ptp_data_to_ksz_dev(ptp_data);
+	struct timespec64 ts;
+	int ret;
+
+	mutex_lock(&ptp_data->lock);
+	ret = _ksz_ptp_gettime(dev, &ts);
+	if (ret)
+		goto out;
+
+	spin_lock_bh(&ptp_data->clock_lock);
+	ptp_data->clock_time = ts;
+	spin_unlock_bh(&ptp_data->clock_lock);
+
+out:
+	mutex_unlock(&ptp_data->lock);
+
+	return HZ;  /* reschedule in 1 second */
+}
+
+static int ksz_ptp_start_clock(struct ksz_device *dev)
+{
+	struct ksz_ptp_data *ptp_data = &dev->ptp_data;
+	int ret;
+
+	ret = ksz_rmw16(dev, REG_PTP_CLK_CTRL, PTP_CLK_ENABLE, PTP_CLK_ENABLE);
+	if (ret)
+		return ret;
+
+	ptp_data->clock_time.tv_sec = 0;
+	ptp_data->clock_time.tv_nsec = 0;
+
+	return 0;
+}
+
+int ksz_ptp_clock_register(struct dsa_switch *ds)
+{
+	struct ksz_device *dev = ds->priv;
+	struct ksz_ptp_data *ptp_data;
+	int ret;
+	u8 i;
+
+	ptp_data = &dev->ptp_data;
+	mutex_init(&ptp_data->lock);
+	spin_lock_init(&ptp_data->clock_lock);
+
+	ptp_data->caps.owner		= THIS_MODULE;
+	snprintf(ptp_data->caps.name, 16, "Microchip Clock");
+	ptp_data->caps.max_adj		= KSZ_MAX_DRIFT_CORR;
+	ptp_data->caps.gettime64	= ksz_ptp_gettime;
+	ptp_data->caps.settime64	= ksz_ptp_settime;
+	ptp_data->caps.adjfine		= ksz_ptp_adjfine;
+	ptp_data->caps.adjtime		= ksz_ptp_adjtime;
+	ptp_data->caps.do_aux_work	= ksz_ptp_do_aux_work;
+	ptp_data->caps.enable		= ksz_ptp_enable;
+	ptp_data->caps.verify		= ksz_ptp_verify_pin;
+	ptp_data->caps.n_pins		= KSZ_PTP_N_GPIO;
+	ptp_data->caps.n_per_out	= 3;
+
+	ret = ksz_ptp_start_clock(dev);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < KSZ_PTP_N_GPIO; i++) {
+		struct ptp_pin_desc *ptp_pin = &ptp_data->pin_config[i];
+
+		snprintf(ptp_pin->name,
+			 sizeof(ptp_pin->name), "ksz_ptp_pin_%02d", i);
+		ptp_pin->index = i;
+		ptp_pin->func = PTP_PF_NONE;
+	}
+
+	ptp_data->caps.pin_config = ptp_data->pin_config;
+
+	/* Currently only P2P mode is supported. When 802_1AS bit is set, it
+	 * forwards all PTP packets to host port and none to other ports.
+	 */
+	ret = ksz_rmw16(dev, REG_PTP_MSG_CONF1, PTP_TC_P2P | PTP_802_1AS,
+			PTP_TC_P2P | PTP_802_1AS);
+	if (ret)
+		return ret;
+
+	ptp_data->clock = ptp_clock_register(&ptp_data->caps, dev->dev);
+	if (IS_ERR_OR_NULL(ptp_data->clock))
+		return PTR_ERR(ptp_data->clock);
+
+	return 0;
+}
+
+void ksz_ptp_clock_unregister(struct dsa_switch *ds)
+{
+	struct ksz_device *dev = ds->priv;
+	struct ksz_ptp_data *ptp_data;
+
+	ptp_data = &dev->ptp_data;
+
+	if (ptp_data->clock)
+		ptp_clock_unregister(ptp_data->clock);
+}
+
+static irqreturn_t ksz_ptp_msg_thread_fn(int irq, void *dev_id)
+{
+	struct ksz_ptp_irq *ptpmsg_irq = dev_id;
+	struct ksz_device *dev;
+	struct ksz_port *port;
+	u32 tstamp_raw;
+	ktime_t tstamp;
+	int ret;
+
+	port = ptpmsg_irq->port;
+	dev = port->ksz_dev;
+
+	if (ptpmsg_irq->ts_en) {
+		ret = ksz_read32(dev, ptpmsg_irq->ts_reg, &tstamp_raw);
+		if (ret)
+			return IRQ_NONE;
+
+		tstamp = ksz_decode_tstamp(tstamp_raw);
+
+		port->tstamp_msg = ksz_tstamp_reconstruct(dev, tstamp);
+
+		complete(&port->tstamp_msg_comp);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t ksz_ptp_irq_thread_fn(int irq, void *dev_id)
+{
+	struct ksz_irq *ptpirq = dev_id;
+	unsigned int nhandled = 0;
+	struct ksz_device *dev;
+	unsigned int sub_irq;
+	u16 data;
+	int ret;
+	u8 n;
+
+	dev = ptpirq->dev;
+
+	ret = ksz_read16(dev, ptpirq->reg_status, &data);
+	if (ret)
+		goto out;
+
+	/* Clear the interrupts W1C */
+	ret = ksz_write16(dev, ptpirq->reg_status, data);
+	if (ret)
+		return IRQ_NONE;
+
+	for (n = 0; n < ptpirq->nirqs; ++n) {
+		if (data & BIT(n + KSZ_PTP_INT_START)) {
+			sub_irq = irq_find_mapping(ptpirq->domain, n);
+			handle_nested_irq(sub_irq);
+			++nhandled;
+		}
+	}
+
+out:
+	return (nhandled > 0 ? IRQ_HANDLED : IRQ_NONE);
+}
+
+static void ksz_ptp_irq_mask(struct irq_data *d)
+{
+	struct ksz_irq *kirq = irq_data_get_irq_chip_data(d);
+
+	kirq->masked &= ~BIT(d->hwirq + KSZ_PTP_INT_START);
+}
+
+static void ksz_ptp_irq_unmask(struct irq_data *d)
+{
+	struct ksz_irq *kirq = irq_data_get_irq_chip_data(d);
+
+	kirq->masked |= BIT(d->hwirq + KSZ_PTP_INT_START);
+}
+
+static void ksz_ptp_irq_bus_lock(struct irq_data *d)
+{
+	struct ksz_irq *kirq  = irq_data_get_irq_chip_data(d);
+
+	mutex_lock(&kirq->dev->lock_irq);
+}
+
+static void ksz_ptp_irq_bus_sync_unlock(struct irq_data *d)
+{
+	struct ksz_irq *kirq  = irq_data_get_irq_chip_data(d);
+	struct ksz_device *dev = kirq->dev;
+	int ret;
+
+	ret = ksz_write16(dev, kirq->reg_mask, kirq->masked);
+	if (ret)
+		dev_err(dev->dev, "failed to change IRQ mask\n");
+
+	mutex_unlock(&dev->lock_irq);
+}
+
+static const struct irq_chip ksz_ptp_irq_chip = {
+	.name			= "ksz-irq",
+	.irq_mask		= ksz_ptp_irq_mask,
+	.irq_unmask		= ksz_ptp_irq_unmask,
+	.irq_bus_lock		= ksz_ptp_irq_bus_lock,
+	.irq_bus_sync_unlock	= ksz_ptp_irq_bus_sync_unlock,
+};
+
+static int ksz_ptp_irq_domain_map(struct irq_domain *d,
+				  unsigned int irq, irq_hw_number_t hwirq)
+{
+	irq_set_chip_data(irq, d->host_data);
+	irq_set_chip_and_handler(irq, &ksz_ptp_irq_chip, handle_level_irq);
+	irq_set_noprobe(irq);
+
+	return 0;
+}
+
+static const struct irq_domain_ops ksz_ptp_irq_domain_ops = {
+	.map	= ksz_ptp_irq_domain_map,
+	.xlate	= irq_domain_xlate_twocell,
+};
+
+static void ksz_ptp_msg_irq_free(struct ksz_port *port, u8 n)
+{
+	struct ksz_ptp_irq *ptpmsg_irq;
+
+	ptpmsg_irq = &port->ptpmsg_irq[n];
+
+	free_irq(ptpmsg_irq->num, ptpmsg_irq);
+	irq_dispose_mapping(ptpmsg_irq->num);
+}
+
+static int ksz_ptp_msg_irq_setup(struct ksz_port *port, u8 n)
+{
+	u16 ts_reg[] = {REG_PTP_PORT_PDRESP_TS, REG_PTP_PORT_XDELAY_TS,
+			REG_PTP_PORT_SYNC_TS};
+	static const char * const name[] = {"pdresp-msg", "xdreq-msg",
+					    "sync-msg"};
+	const struct ksz_dev_ops *ops = port->ksz_dev->dev_ops;
+	struct ksz_ptp_irq *ptpmsg_irq;
+
+	ptpmsg_irq = &port->ptpmsg_irq[n];
+
+	ptpmsg_irq->port = port;
+	ptpmsg_irq->ts_reg = ops->get_port_addr(port->num, ts_reg[n]);
+
+	snprintf(ptpmsg_irq->name, sizeof(ptpmsg_irq->name), name[n]);
+
+	ptpmsg_irq->num = irq_find_mapping(port->ptpirq.domain, n);
+	if (ptpmsg_irq->num < 0)
+		return ptpmsg_irq->num;
+
+	return request_threaded_irq(ptpmsg_irq->num, NULL,
+				    ksz_ptp_msg_thread_fn, IRQF_ONESHOT,
+				    ptpmsg_irq->name, ptpmsg_irq);
+}
+
+int ksz_ptp_irq_setup(struct dsa_switch *ds, u8 p)
+{
+	struct ksz_device *dev = ds->priv;
+	const struct ksz_dev_ops *ops = dev->dev_ops;
+	struct ksz_port *port = &dev->ports[p];
+	struct ksz_irq *ptpirq = &port->ptpirq;
+	int irq;
+	int ret;
+
+	ptpirq->dev = dev;
+	ptpirq->masked = 0;
+	ptpirq->nirqs = 3;
+	ptpirq->reg_mask = ops->get_port_addr(p, REG_PTP_PORT_TX_INT_ENABLE__2);
+	ptpirq->reg_status = ops->get_port_addr(p,
+						REG_PTP_PORT_TX_INT_STATUS__2);
+	snprintf(ptpirq->name, sizeof(ptpirq->name), "ptp-irq-%d", p);
+
+	init_completion(&port->tstamp_msg_comp);
+
+	ptpirq->domain = irq_domain_add_linear(dev->dev->of_node, ptpirq->nirqs,
+					       &ksz_ptp_irq_domain_ops, ptpirq);
+	if (!ptpirq->domain)
+		return -ENOMEM;
+
+	for (irq = 0; irq < ptpirq->nirqs; irq++)
+		irq_create_mapping(ptpirq->domain, irq);
+
+	ptpirq->irq_num = irq_find_mapping(port->pirq.domain, PORT_SRC_PTP_INT);
+	if (ptpirq->irq_num < 0) {
+		ret = ptpirq->irq_num;
+		goto out;
+	}
+
+	ret = request_threaded_irq(ptpirq->irq_num, NULL, ksz_ptp_irq_thread_fn,
+				   IRQF_ONESHOT, ptpirq->name, ptpirq);
+	if (ret)
+		goto out;
+
+	for (irq = 0; irq < ptpirq->nirqs; irq++) {
+		ret = ksz_ptp_msg_irq_setup(port, irq);
+		if (ret)
+			goto out_ptp_msg;
+	}
+
+	return 0;
+
+out_ptp_msg:
+	free_irq(ptpirq->irq_num, ptpirq);
+	while (irq--)
+		free_irq(port->ptpmsg_irq[irq].num, &port->ptpmsg_irq[irq]);
+out:
+	for (irq = 0; irq < ptpirq->nirqs; irq++)
+		irq_dispose_mapping(port->ptpmsg_irq[irq].num);
+
+	irq_domain_remove(ptpirq->domain);
+
+	return ret;
+}
+
+void ksz_ptp_irq_free(struct dsa_switch *ds, u8 p)
+{
+	struct ksz_device *dev = ds->priv;
+	struct ksz_port *port = &dev->ports[p];
+	struct ksz_irq *ptpirq = &port->ptpirq;
+	u8 n;
+
+	for (n = 0; n < ptpirq->nirqs; n++)
+		ksz_ptp_msg_irq_free(port, n);
+
+	free_irq(ptpirq->irq_num, ptpirq);
+	irq_dispose_mapping(ptpirq->irq_num);
+
+	irq_domain_remove(ptpirq->domain);
+}
+
+MODULE_AUTHOR("Christian Eggers <ceggers@arri.de>");
+MODULE_AUTHOR("Arun Ramadoss <arun.ramadoss@microchip.com>");
+MODULE_DESCRIPTION("PTP support for KSZ switch");
+MODULE_LICENSE("GPL");

drivers/net/dsa/microchip/ksz_ptp.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/* Microchip KSZ PTP Implementation
+ *
+ * Copyright (C) 2020 ARRI Lighting
+ * Copyright (C) 2022 Microchip Technology Inc.
+ */
+
+#ifndef _NET_DSA_DRIVERS_KSZ_PTP_H
+#define _NET_DSA_DRIVERS_KSZ_PTP_H
+
+#if IS_ENABLED(CONFIG_NET_DSA_MICROCHIP_KSZ_PTP)
+
+#include <linux/ptp_clock_kernel.h>
+
+#define KSZ_PTP_N_GPIO		2
+
+enum ksz_ptp_tou_mode {
+	KSZ_PTP_TOU_IDLE,
+	KSZ_PTP_TOU_PEROUT,
+};
+
+struct ksz_ptp_data {
+	struct ptp_clock_info caps;
+	struct ptp_clock *clock;
+	struct ptp_pin_desc pin_config[KSZ_PTP_N_GPIO];
+	/* Serializes all operations on the PTP hardware clock */
+	struct mutex lock;
+	/* lock for accessing the clock_time */
+	spinlock_t clock_lock;
+	struct timespec64 clock_time;
+	enum ksz_ptp_tou_mode tou_mode;
+	struct timespec64 perout_target_time_first;  /* start of first pulse */
+	struct timespec64 perout_period;
+};
+
+int ksz_ptp_clock_register(struct dsa_switch *ds);
+
+void ksz_ptp_clock_unregister(struct dsa_switch *ds);
+
+int ksz_get_ts_info(struct dsa_switch *ds, int port,
+		    struct ethtool_ts_info *ts);
+int ksz_hwtstamp_get(struct dsa_switch *ds, int port, struct ifreq *ifr);
+int ksz_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr);
+void ksz_port_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb);
+void ksz_port_deferred_xmit(struct kthread_work *work);
+bool ksz_port_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb,
+		       unsigned int type);
+int ksz_ptp_irq_setup(struct dsa_switch *ds, u8 p);
+void ksz_ptp_irq_free(struct dsa_switch *ds, u8 p);
+
+#else
+
+struct ksz_ptp_data {
+	/* Serializes all operations on the PTP hardware clock */
+	struct mutex lock;
+};
+
+static inline int ksz_ptp_clock_register(struct dsa_switch *ds)
+{
+	return 0;
+}
+
+static inline void ksz_ptp_clock_unregister(struct dsa_switch *ds) { }
+
+static inline int ksz_ptp_irq_setup(struct dsa_switch *ds, u8 p)
+{
+	return 0;
+}
+
+static inline void ksz_ptp_irq_free(struct dsa_switch *ds, u8 p) {}
+
+#define ksz_get_ts_info NULL
+
+#define ksz_hwtstamp_get NULL
+
+#define ksz_hwtstamp_set NULL
+
+#define ksz_port_rxtstamp NULL
+
+#define ksz_port_txtstamp NULL
+
+#define ksz_port_deferred_xmit NULL
+
+#endif	/* End of CONFIG_NET_DSA_MICROCHIP_KSZ_PTP */
+
+#endif

drivers/net/dsa/microchip/ksz_ptp_reg.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/* Microchip KSZ PTP register definitions
+ * Copyright (C) 2022 Microchip Technology Inc.
+ */
+
+#ifndef __KSZ_PTP_REGS_H
+#define __KSZ_PTP_REGS_H
+
+#define REG_SW_GLOBAL_LED_OVR__4	0x0120
+#define LED_OVR_2			BIT(1)
+#define LED_OVR_1			BIT(0)
+
+#define REG_SW_GLOBAL_LED_SRC__4	0x0128
+#define LED_SRC_PTP_GPIO_1		BIT(3)
+#define LED_SRC_PTP_GPIO_2		BIT(2)
+
+/* 5 - PTP Clock */
+#define REG_PTP_CLK_CTRL		0x0500
+
+#define PTP_STEP_ADJ			BIT(6)
+#define PTP_STEP_DIR			BIT(5)
+#define PTP_READ_TIME			BIT(4)
+#define PTP_LOAD_TIME			BIT(3)
+#define PTP_CLK_ADJ_ENABLE		BIT(2)
+#define PTP_CLK_ENABLE			BIT(1)
+#define PTP_CLK_RESET			BIT(0)
+
+#define REG_PTP_RTC_SUB_NANOSEC__2	0x0502
+
+#define PTP_RTC_SUB_NANOSEC_M		0x0007
+#define PTP_RTC_0NS			0x00
+
+#define REG_PTP_RTC_NANOSEC		0x0504
+
+#define REG_PTP_RTC_SEC			0x0508
+
+#define REG_PTP_SUBNANOSEC_RATE		0x050C
+
+#define PTP_SUBNANOSEC_M		0x3FFFFFFF
+#define PTP_RATE_DIR			BIT(31)
+#define PTP_TMP_RATE_ENABLE		BIT(30)
+
+#define REG_PTP_SUBNANOSEC_RATE_L	0x050E
+
+#define REG_PTP_RATE_DURATION		0x0510
+#define REG_PTP_RATE_DURATION_H		0x0510
+#define REG_PTP_RATE_DURATION_L		0x0512
+
+#define REG_PTP_MSG_CONF1		0x0514
+
+#define PTP_802_1AS			BIT(7)
+#define PTP_ENABLE			BIT(6)
+#define PTP_ETH_ENABLE			BIT(5)
+#define PTP_IPV4_UDP_ENABLE		BIT(4)
+#define PTP_IPV6_UDP_ENABLE		BIT(3)
+#define PTP_TC_P2P			BIT(2)
+#define PTP_MASTER			BIT(1)
+#define PTP_1STEP			BIT(0)
+
+#define REG_PTP_UNIT_INDEX__4		0x0520
+
+#define PTP_GPIO_INDEX			GENMASK(19, 16)
+#define PTP_TSI_INDEX			BIT(8)
+#define PTP_TOU_INDEX			GENMASK(1, 0)
+
+#define REG_PTP_TRIG_STATUS__4		0x0524
+
+#define TRIG_ERROR_M			GENMASK(18, 16)
+#define TRIG_DONE_M			GENMASK(2, 0)
+
+#define REG_PTP_INT_STATUS__4		0x0528
+
+#define TRIG_INT_M			GENMASK(18, 16)
+#define TS_INT_M			GENMASK(1, 0)
+
+#define REG_PTP_CTRL_STAT__4		0x052C
+
+#define GPIO_IN			BIT(7)
+#define GPIO_OUT			BIT(6)
+#define TS_INT_ENABLE			BIT(5)
+#define TRIG_ACTIVE			BIT(4)
+#define TRIG_ENABLE			BIT(3)
+#define TRIG_RESET			BIT(2)
+#define TS_ENABLE			BIT(1)
+#define TS_RESET			BIT(0)
+
+#define REG_TRIG_TARGET_NANOSEC	0x0530
+#define REG_TRIG_TARGET_SEC		0x0534
+
+#define REG_TRIG_CTRL__4		0x0538
+
+#define TRIG_CASCADE_ENABLE		BIT(31)
+#define TRIG_CASCADE_TAIL		BIT(30)
+#define TRIG_CASCADE_UPS_M		GENMASK(29, 26)
+#define TRIG_NOW			BIT(25)
+#define TRIG_NOTIFY			BIT(24)
+#define TRIG_EDGE			BIT(23)
+#define TRIG_PATTERN_M			GENMASK(22, 20)
+#define TRIG_NEG_EDGE			0
+#define TRIG_POS_EDGE			1
+#define TRIG_NEG_PULSE			2
+#define TRIG_POS_PULSE			3
+#define TRIG_NEG_PERIOD		4
+#define TRIG_POS_PERIOD		5
+#define TRIG_REG_OUTPUT		6
+#define TRIG_GPO_M			GENMASK(19, 16)
+#define TRIG_CASCADE_ITERATE_CNT_M	GENMASK(15, 0)
+
+#define REG_TRIG_CYCLE_WIDTH		0x053C
+#define TRIG_CYCLE_WIDTH_M		GENMASK(31, 0)
+
+#define REG_TRIG_CYCLE_CNT		0x0540
+
+#define TRIG_CYCLE_CNT_M		GENMASK(31, 16)
+#define TRIG_BIT_PATTERN_M		GENMASK(15, 0)
+
+#define REG_TRIG_ITERATE_TIME		0x0544
+
+#define REG_TRIG_PULSE_WIDTH__4	0x0548
+
+#define TRIG_PULSE_WIDTH_M		GENMASK(23, 0)
+
+/* Port PTP Register */
+#define REG_PTP_PORT_RX_DELAY__2	0x0C00
+#define REG_PTP_PORT_TX_DELAY__2	0x0C02
+#define REG_PTP_PORT_ASYM_DELAY__2	0x0C04
+
+#define REG_PTP_PORT_XDELAY_TS		0x0C08
+#define REG_PTP_PORT_SYNC_TS		0x0C0C
+#define REG_PTP_PORT_PDRESP_TS		0x0C10
+
+#define REG_PTP_PORT_TX_INT_STATUS__2	0x0C14
+#define REG_PTP_PORT_TX_INT_ENABLE__2	0x0C16
+
+#define PTP_PORT_SYNC_INT		BIT(15)
+#define PTP_PORT_XDELAY_REQ_INT		BIT(14)
+#define PTP_PORT_PDELAY_RESP_INT	BIT(13)
+#define KSZ_SYNC_MSG			2
+#define KSZ_XDREQ_MSG			1
+#define KSZ_PDRES_MSG			0
+
+#endif

include/linux/dsa/ksz_common.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/* Microchip switch tag common header
+ *
+ * Copyright (C) 2022 Microchip Technology Inc.
+ */
+
+#ifndef _NET_DSA_KSZ_COMMON_H_
+#define _NET_DSA_KSZ_COMMON_H_
+
+#include <net/dsa.h>
+
+/* All time stamps from the KSZ consist of 2 bits for seconds and 30 bits for
+ * nanoseconds. This is NOT the same as 32 bits for nanoseconds.
+ */
+#define KSZ_TSTAMP_SEC_MASK  GENMASK(31, 30)
+#define KSZ_TSTAMP_NSEC_MASK GENMASK(29, 0)
+
+static inline ktime_t ksz_decode_tstamp(u32 tstamp)
+{
+	u64 ns = FIELD_GET(KSZ_TSTAMP_SEC_MASK, tstamp) * NSEC_PER_SEC +
+		 FIELD_GET(KSZ_TSTAMP_NSEC_MASK, tstamp);
+
+	return ns_to_ktime(ns);
+}
+
+struct ksz_deferred_xmit_work {
+	struct dsa_port *dp;
+	struct sk_buff *skb;
+	struct kthread_work work;
+};
+
+struct ksz_tagger_data {
+	void (*xmit_work_fn)(struct kthread_work *work);
+	void (*hwtstamp_set_state)(struct dsa_switch *ds, bool on);
+};
+
+struct ksz_skb_cb {
+	struct sk_buff *clone;
+	unsigned int ptp_type;
+	bool update_correction;
+	u32 tstamp;
+};
+
+#define KSZ_SKB_CB(skb) \
+	((struct ksz_skb_cb *)((skb)->cb))
+
+static inline struct ksz_tagger_data *
+ksz_tagger_data(struct dsa_switch *ds)
+{
+	return ds->tagger_data;
+}
+
+#endif /* _NET_DSA_KSZ_COMMON_H_ */

include/linux/ptp_classify.h

@@ -10,8 +10,12 @@
 #ifndef _PTP_CLASSIFY_H_
 #define _PTP_CLASSIFY_H_
 
+#include <asm/unaligned.h>
 #include <linux/ip.h>
+#include <linux/ktime.h>
 #include <linux/skbuff.h>
+#include <linux/udp.h>
+#include <net/checksum.h>
 
 #define PTP_CLASS_NONE  0x00 /* not a PTP event message */
 #define PTP_CLASS_V1    0x01 /* protocol version 1 */
@@ -129,6 +133,69 @@ static inline u8 ptp_get_msgtype(const struct ptp_header *hdr,
 	return msgtype;
 }
 
+/**
+ * ptp_check_diff8 - Computes new checksum (when altering a 64-bit field)
+ * @old: old field value
+ * @new: new field value
+ * @oldsum: previous checksum
+ *
+ * This function can be used to calculate a new checksum when only a single
+ * field is changed. Similar as ip_vs_check_diff*() in ip_vs.h.
+ *
+ * Return: Updated checksum
+ */
+static inline __wsum ptp_check_diff8(__be64 old, __be64 new, __wsum oldsum)
+{
+	__be64 diff[2] = { ~old, new };
+
+	return csum_partial(diff, sizeof(diff), oldsum);
+}
+
+/**
+ * ptp_header_update_correction - Update PTP header's correction field
+ * @skb: packet buffer
+ * @type: type of the packet (see ptp_classify_raw())
+ * @hdr: ptp header
+ * @correction: new correction value
+ *
+ * This updates the correction field of a PTP header and updates the UDP
+ * checksum (if UDP is used as transport). It is needed for hardware capable of
+ * one-step P2P that does not already modify the correction field of Pdelay_Req
+ * event messages on ingress.
+ */
+static inline
+void ptp_header_update_correction(struct sk_buff *skb, unsigned int type,
+				  struct ptp_header *hdr, s64 correction)
+{
+	__be64 correction_old;
+	struct udphdr *uhdr;
+
+	/* previous correction value is required for checksum update. */
+	memcpy(&correction_old,  &hdr->correction, sizeof(correction_old));
+
+	/* write new correction value */
+	put_unaligned_be64((u64)correction, &hdr->correction);
+
+	switch (type & PTP_CLASS_PMASK) {
+	case PTP_CLASS_IPV4:
+	case PTP_CLASS_IPV6:
+		/* locate udp header */
+		uhdr = (struct udphdr *)((char *)hdr - sizeof(struct udphdr));
+		break;
+	default:
+		return;
+	}
+
+	/* update checksum */
+	uhdr->check = csum_fold(ptp_check_diff8(correction_old,
+						hdr->correction,
+						~csum_unfold(uhdr->check)));
+	if (!uhdr->check)
+		uhdr->check = CSUM_MANGLED_0;
+
+	skb->ip_summed = CHECKSUM_NONE;
+}
+
 /**
  * ptp_msg_is_sync - Evaluates whether the given skb is a PTP Sync message
  * @skb: packet buffer
@@ -166,5 +233,11 @@ static inline bool ptp_msg_is_sync(struct sk_buff *skb, unsigned int type)
 {
 	return false;
 }
+
+static inline
+void ptp_header_update_correction(struct sk_buff *skb, unsigned int type,
+				  struct ptp_header *hdr, s64 correction)
+{
+}
 #endif
 #endif /* _PTP_CLASSIFY_H_ */

net/dsa/tag_ksz.c

@@ -4,8 +4,10 @@
  * Copyright (c) 2017 Microchip Technology
  */
 
+#include <linux/dsa/ksz_common.h>
 #include <linux/etherdevice.h>
 #include <linux/list.h>
+#include <linux/ptp_classify.h>
 #include <net/dsa.h>
 
 #include "tag.h"
@@ -16,9 +18,71 @@
 #define LAN937X_NAME "lan937x"
 
 /* Typically only one byte is used for tail tag. */
+#define KSZ_PTP_TAG_LEN			4
 #define KSZ_EGRESS_TAG_LEN		1
 #define KSZ_INGRESS_TAG_LEN		1
 
+#define KSZ_HWTS_EN  0
+
+struct ksz_tagger_private {
+	struct ksz_tagger_data data; /* Must be first */
+	unsigned long state;
+	struct kthread_worker *xmit_worker;
+};
+
+static struct ksz_tagger_private *
+ksz_tagger_private(struct dsa_switch *ds)
+{
+	return ds->tagger_data;
+}
+
+static void ksz_hwtstamp_set_state(struct dsa_switch *ds, bool on)
+{
+	struct ksz_tagger_private *priv = ksz_tagger_private(ds);
+
+	if (on)
+		set_bit(KSZ_HWTS_EN, &priv->state);
+	else
+		clear_bit(KSZ_HWTS_EN, &priv->state);
+}
+
+static void ksz_disconnect(struct dsa_switch *ds)
+{
+	struct ksz_tagger_private *priv = ds->tagger_data;
+
+	kthread_destroy_worker(priv->xmit_worker);
+	kfree(priv);
+	ds->tagger_data = NULL;
+}
+
+static int ksz_connect(struct dsa_switch *ds)
+{
+	struct ksz_tagger_data *tagger_data;
+	struct kthread_worker *xmit_worker;
+	struct ksz_tagger_private *priv;
+	int ret;
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	xmit_worker = kthread_create_worker(0, "dsa%d:%d_xmit",
+					    ds->dst->index, ds->index);
+	if (IS_ERR(xmit_worker)) {
+		ret = PTR_ERR(xmit_worker);
+		kfree(priv);
+		return ret;
+	}
+
+	priv->xmit_worker = xmit_worker;
+	/* Export functions for switch driver use */
+	tagger_data = &priv->data;
+	tagger_data->hwtstamp_set_state = ksz_hwtstamp_set_state;
+	ds->tagger_data = priv;
+
+	return 0;
+}
+
 static struct sk_buff *ksz_common_rcv(struct sk_buff *skb,
 				      struct net_device *dev,
 				      unsigned int port, unsigned int len)
@@ -92,17 +156,20 @@ DSA_TAG_DRIVER(ksz8795_netdev_ops);
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ8795, KSZ8795_NAME);
 
 /*
- * For Ingress (Host -> KSZ9477), 2 bytes are added before FCS.
+ * For Ingress (Host -> KSZ9477), 2/6 bytes are added before FCS.
  * ---------------------------------------------------------------------------
- * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|tag1(1byte)|FCS(4bytes)
+ * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|ts(4bytes)|tag0(1byte)|tag1(1byte)|
+ * FCS(4bytes)
  * ---------------------------------------------------------------------------
+ * ts   : time stamp (Present only if PTP is enabled in the Hardware)
  * tag0 : Prioritization (not used now)
  * tag1 : each bit represents port (eg, 0x01=port1, 0x02=port2, 0x10=port5)
  *
- * For Egress (KSZ9477 -> Host), 1 byte is added before FCS.
+ * For Egress (KSZ9477 -> Host), 1/5 bytes is added before FCS.
  * ---------------------------------------------------------------------------
- * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|FCS(4bytes)
+ * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|ts(4bytes)|tag0(1byte)|FCS(4bytes)
  * ---------------------------------------------------------------------------
+ * ts   : time stamp (Present only if bit 7 of tag0 is set)
  * tag0 : zero-based value represents port
  *	  (eg, 0x00=port1, 0x02=port3, 0x06=port7)
  */
@@ -114,6 +181,91 @@ MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ8795, KSZ8795_NAME);
 #define KSZ9477_TAIL_TAG_OVERRIDE	BIT(9)
 #define KSZ9477_TAIL_TAG_LOOKUP		BIT(10)
 
+static void ksz_rcv_timestamp(struct sk_buff *skb, u8 *tag)
+{
+	u8 *tstamp_raw = tag - KSZ_PTP_TAG_LEN;
+	ktime_t tstamp;
+
+	tstamp = ksz_decode_tstamp(get_unaligned_be32(tstamp_raw));
+	KSZ_SKB_CB(skb)->tstamp = tstamp;
+}
+
+/* Time stamp tag *needs* to be inserted if PTP is enabled in hardware.
+ * Regardless of Whether it is a PTP frame or not.
+ */
+static void ksz_xmit_timestamp(struct dsa_port *dp, struct sk_buff *skb)
+{
+	struct ksz_tagger_private *priv;
+	struct ptp_header *ptp_hdr;
+	unsigned int ptp_type;
+	u32 tstamp_raw = 0;
+	s64 correction;
+
+	priv = ksz_tagger_private(dp->ds);
+
+	if (!test_bit(KSZ_HWTS_EN, &priv->state))
+		return;
+
+	if (!KSZ_SKB_CB(skb)->update_correction)
+		goto output_tag;
+
+	ptp_type = KSZ_SKB_CB(skb)->ptp_type;
+
+	ptp_hdr = ptp_parse_header(skb, ptp_type);
+	if (!ptp_hdr)
+		goto output_tag;
+
+	correction = (s64)get_unaligned_be64(&ptp_hdr->correction);
+
+	if (correction < 0) {
+		struct timespec64 ts;
+
+		ts = ns_to_timespec64(-correction >> 16);
+		tstamp_raw = ((ts.tv_sec & 3) << 30) | ts.tv_nsec;
+
+		/* Set correction field to 0 and update UDP checksum */
+		ptp_header_update_correction(skb, ptp_type, ptp_hdr, 0);
+	}
+
+output_tag:
+	put_unaligned_be32(tstamp_raw, skb_put(skb, KSZ_PTP_TAG_LEN));
+}
+
+/* Defer transmit if waiting for egress time stamp is required.  */
+static struct sk_buff *ksz_defer_xmit(struct dsa_port *dp, struct sk_buff *skb)
+{
+	struct ksz_tagger_data *tagger_data = ksz_tagger_data(dp->ds);
+	struct ksz_tagger_private *priv = ksz_tagger_private(dp->ds);
+	void (*xmit_work_fn)(struct kthread_work *work);
+	struct sk_buff *clone = KSZ_SKB_CB(skb)->clone;
+	struct ksz_deferred_xmit_work *xmit_work;
+	struct kthread_worker *xmit_worker;
+
+	if (!clone)
+		return skb;  /* no deferred xmit for this packet */
+
+	xmit_work_fn = tagger_data->xmit_work_fn;
+	xmit_worker = priv->xmit_worker;
+
+	if (!xmit_work_fn || !xmit_worker)
+		return NULL;
+
+	xmit_work = kzalloc(sizeof(*xmit_work), GFP_ATOMIC);
+	if (!xmit_work)
+		return NULL;
+
+	kthread_init_work(&xmit_work->work, xmit_work_fn);
+	/* Increase refcount so the kfree_skb in dsa_slave_xmit
+	 * won't really free the packet.
+	 */
+	xmit_work->dp = dp;
+	xmit_work->skb = skb_get(skb);
+
+	kthread_queue_work(xmit_worker, &xmit_work->work);
+
+	return NULL;
+}
+
 static struct sk_buff *ksz9477_xmit(struct sk_buff *skb,
 				    struct net_device *dev)
 {
@@ -126,6 +278,8 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb,
 		return NULL;
 
 	/* Tag encoding */
+	ksz_xmit_timestamp(dp, skb);
+
 	tag = skb_put(skb, KSZ9477_INGRESS_TAG_LEN);
 	addr = skb_mac_header(skb);
 
@@ -136,7 +290,7 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb,
 
 	*tag = cpu_to_be16(val);
 
-	return skb;
+	return ksz_defer_xmit(dp, skb);
 }
 
 static struct sk_buff *ksz9477_rcv(struct sk_buff *skb, struct net_device *dev)
@@ -147,8 +301,10 @@ static struct sk_buff *ksz9477_rcv(struct sk_buff *skb, struct net_device *dev)
 	unsigned int len = KSZ_EGRESS_TAG_LEN;
 
 	/* Extra 4-bytes PTP timestamp */
-	if (tag[0] & KSZ9477_PTP_TAG_INDICATION)
-		len += KSZ9477_PTP_TAG_LEN;
+	if (tag[0] & KSZ9477_PTP_TAG_INDICATION) {
+		ksz_rcv_timestamp(skb, tag);
+		len += KSZ_PTP_TAG_LEN;
+	}
 
 	return ksz_common_rcv(skb, dev, port, len);
 }
@@ -158,7 +314,9 @@ static const struct dsa_device_ops ksz9477_netdev_ops = {
 	.proto	= DSA_TAG_PROTO_KSZ9477,
 	.xmit	= ksz9477_xmit,
 	.rcv	= ksz9477_rcv,
-	.needed_tailroom = KSZ9477_INGRESS_TAG_LEN,
+	.connect = ksz_connect,
+	.disconnect = ksz_disconnect,
+	.needed_tailroom = KSZ9477_INGRESS_TAG_LEN + KSZ_PTP_TAG_LEN,
 };
 
 DSA_TAG_DRIVER(ksz9477_netdev_ops);
@@ -178,6 +336,8 @@ static struct sk_buff *ksz9893_xmit(struct sk_buff *skb,
 		return NULL;
 
 	/* Tag encoding */
+	ksz_xmit_timestamp(dp, skb);
+
 	tag = skb_put(skb, KSZ_INGRESS_TAG_LEN);
 	addr = skb_mac_header(skb);
 
@@ -186,7 +346,7 @@ static struct sk_buff *ksz9893_xmit(struct sk_buff *skb,
 	if (is_link_local_ether_addr(addr))
 		*tag |= KSZ9893_TAIL_TAG_OVERRIDE;
 
-	return skb;
+	return ksz_defer_xmit(dp, skb);
 }
 
 static const struct dsa_device_ops ksz9893_netdev_ops = {
@@ -194,23 +354,28 @@ static const struct dsa_device_ops ksz9893_netdev_ops = {
 	.proto	= DSA_TAG_PROTO_KSZ9893,
 	.xmit	= ksz9893_xmit,
 	.rcv	= ksz9477_rcv,
-	.needed_tailroom = KSZ_INGRESS_TAG_LEN,
+	.connect = ksz_connect,
+	.disconnect = ksz_disconnect,
+	.needed_tailroom = KSZ_INGRESS_TAG_LEN + KSZ_PTP_TAG_LEN,
 };
 
 DSA_TAG_DRIVER(ksz9893_netdev_ops);
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ9893, KSZ9893_NAME);
 
-/* For xmit, 2 bytes are added before FCS.
+/* For xmit, 2/6 bytes are added before FCS.
  * ---------------------------------------------------------------------------
- * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|tag1(1byte)|FCS(4bytes)
+ * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|ts(4bytes)|tag0(1byte)|tag1(1byte)|
+ * FCS(4bytes)
  * ---------------------------------------------------------------------------
+ * ts   : time stamp (Present only if PTP is enabled in the Hardware)
  * tag0 : represents tag override, lookup and valid
  * tag1 : each bit represents port (eg, 0x01=port1, 0x02=port2, 0x80=port8)
  *
- * For rcv, 1 byte is added before FCS.
+ * For rcv, 1/5 bytes is added before FCS.
  * ---------------------------------------------------------------------------
- * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|FCS(4bytes)
+ * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|ts(4bytes)|tag0(1byte)|FCS(4bytes)
  * ---------------------------------------------------------------------------
+ * ts   : time stamp (Present only if bit 7 of tag0 is set)
  * tag0 : zero-based value represents port
  *	  (eg, 0x00=port1, 0x02=port3, 0x07=port8)
  */
@@ -232,6 +397,8 @@ static struct sk_buff *lan937x_xmit(struct sk_buff *skb,
 	if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb))
 		return NULL;
 
+	ksz_xmit_timestamp(dp, skb);
+
 	tag = skb_put(skb, LAN937X_EGRESS_TAG_LEN);
 
 	val = BIT(dp->index);
@@ -244,7 +411,7 @@ static struct sk_buff *lan937x_xmit(struct sk_buff *skb,
 
 	put_unaligned_be16(val, tag);
 
-	return skb;
+	return ksz_defer_xmit(dp, skb);
 }
 
 static const struct dsa_device_ops lan937x_netdev_ops = {
@@ -252,7 +419,9 @@ static const struct dsa_device_ops lan937x_netdev_ops = {
 	.proto	= DSA_TAG_PROTO_LAN937X,
 	.xmit	= lan937x_xmit,
 	.rcv	= ksz9477_rcv,
-	.needed_tailroom = LAN937X_EGRESS_TAG_LEN,
+	.connect = ksz_connect,
+	.disconnect = ksz_disconnect,
+	.needed_tailroom = LAN937X_EGRESS_TAG_LEN + KSZ_PTP_TAG_LEN,
 };
 
 DSA_TAG_DRIVER(lan937x_netdev_ops);