1 files changed, 599 insertions, 209 deletions

diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index 8c351f100aca..2ba4c8795d60 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -1,22 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * TI Common Platform Time Sync
  *
  * Copyright (C) 2012 Richard Cochran <richardcochran@gmail.com>
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
+#include <linux/clk-provider.h>
 #include <linux/err.h>
 #include <linux/if.h>
 #include <linux/hrtimer.h>
@@ -26,17 +15,27 @@
 #include <linux/time.h>
 #include <linux/uaccess.h>
 #include <linux/workqueue.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
 
 #include "cpts.h"
 
-#ifdef CONFIG_TI_CPTS
+#define CPTS_SKB_TX_WORK_TIMEOUT 1 /* jiffies */
+#define CPTS_SKB_RX_TX_TMO 100 /*ms */
+#define CPTS_EVENT_RX_TX_TIMEOUT (100) /* ms */
 
-static struct sock_filter ptp_filter[] = {
-	PTP_FILTER
+struct cpts_skb_cb_data {
+	u32 skb_mtype_seqid;
+	unsigned long tmo;
 };
 
-#define cpts_read32(c, r)	__raw_readl(&c->reg->r)
-#define cpts_write32(c, v, r)	__raw_writel(v, &c->reg->r)
+#define cpts_read32(c, r)	readl_relaxed(&c->reg->r)
+#define cpts_write32(c, v, r)	writel_relaxed(v, &c->reg->r)
+
+static int cpts_event_port(struct cpts_event *event)
+{
+	return (event->high >> PORT_NUMBER_SHIFT) & PORT_NUMBER_MASK;
+}
 
 static int event_expired(struct cpts_event *event)
 {
@@ -61,147 +60,238 @@ static int cpts_fifo_pop(struct cpts *cpts, u32 *high, u32 *low)
 	return -1;
 }
 
+static int cpts_purge_events(struct cpts *cpts)
+{
+	struct list_head *this, *next;
+	struct cpts_event *event;
+	int removed = 0;
+
+	list_for_each_safe(this, next, &cpts->events) {
+		event = list_entry(this, struct cpts_event, list);
+		if (event_expired(event)) {
+			list_del_init(&event->list);
+			list_add(&event->list, &cpts->pool);
+			++removed;
+		}
+	}
+
+	if (removed)
+		dev_dbg(cpts->dev, "cpts: event pool cleaned up %d\n", removed);
+	return removed ? 0 : -1;
+}
+
+static void cpts_purge_txq(struct cpts *cpts)
+{
+	struct cpts_skb_cb_data *skb_cb;
+	struct sk_buff *skb, *tmp;
+	int removed = 0;
+
+	skb_queue_walk_safe(&cpts->txq, skb, tmp) {
+		skb_cb = (struct cpts_skb_cb_data *)skb->cb;
+		if (time_after(jiffies, skb_cb->tmo)) {
+			__skb_unlink(skb, &cpts->txq);
+			dev_consume_skb_any(skb);
+			++removed;
+		}
+	}
+
+	if (removed)
+		dev_dbg(cpts->dev, "txq cleaned up %d\n", removed);
+}
+
 /*
  * Returns zero if matching event type was found.
  */
 static int cpts_fifo_read(struct cpts *cpts, int match)
 {
+	struct ptp_clock_event pevent;
+	bool need_schedule = false;
+	struct cpts_event *event;
+	unsigned long flags;
 	int i, type = -1;
 	u32 hi, lo;
-	struct cpts_event *event;
+
+	spin_lock_irqsave(&cpts->lock, flags);
 
 	for (i = 0; i < CPTS_FIFO_DEPTH; i++) {
 		if (cpts_fifo_pop(cpts, &hi, &lo))
 			break;
-		if (list_empty(&cpts->pool)) {
-			pr_err("cpts: event pool is empty\n");
-			return -1;
+
+		if (list_empty(&cpts->pool) && cpts_purge_events(cpts)) {
+			dev_warn(cpts->dev, "cpts: event pool empty\n");
+			break;
 		}
+
 		event = list_first_entry(&cpts->pool, struct cpts_event, list);
-		event->tmo = jiffies + 2;
 		event->high = hi;
 		event->low = lo;
+		event->timestamp = timecounter_cyc2time(&cpts->tc, event->low);
 		type = event_type(event);
+
+		dev_dbg(cpts->dev, "CPTS_EV: %d high:%08X low:%08x\n",
+			type, event->high, event->low);
 		switch (type) {
 		case CPTS_EV_PUSH:
-		case CPTS_EV_RX:
+			WRITE_ONCE(cpts->cur_timestamp, lo);
+			timecounter_read(&cpts->tc);
+			if (cpts->mult_new) {
+				cpts->cc.mult = cpts->mult_new;
+				cpts->mult_new = 0;
+			}
+			if (!cpts->irq_poll)
+				complete(&cpts->ts_push_complete);
+			break;
 		case CPTS_EV_TX:
+		case CPTS_EV_RX:
+			event->tmo = jiffies +
+				msecs_to_jiffies(CPTS_EVENT_RX_TX_TIMEOUT);
+
 			list_del_init(&event->list);
 			list_add_tail(&event->list, &cpts->events);
+			need_schedule = true;
 			break;
 		case CPTS_EV_ROLL:
 		case CPTS_EV_HALF:
+			break;
 		case CPTS_EV_HW:
+			pevent.timestamp = event->timestamp;
+			pevent.type = PTP_CLOCK_EXTTS;
+			pevent.index = cpts_event_port(event) - 1;
+			ptp_clock_event(cpts->clock, &pevent);
 			break;
 		default:
-			pr_err("cpts: unknown event type\n");
+			dev_err(cpts->dev, "cpts: unknown event type\n");
 			break;
 		}
 		if (type == match)
 			break;
 	}
+
+	spin_unlock_irqrestore(&cpts->lock, flags);
+
+	if (!cpts->irq_poll && need_schedule)
+		ptp_schedule_worker(cpts->clock, 0);
+
 	return type == match ? 0 : -1;
 }
 
-static cycle_t cpts_systim_read(const struct cyclecounter *cc)
+void cpts_misc_interrupt(struct cpts *cpts)
+{
+	cpts_fifo_read(cpts, -1);
+}
+EXPORT_SYMBOL_GPL(cpts_misc_interrupt);
+
+static u64 cpts_systim_read(struct cyclecounter *cc)
 {
-	u64 val = 0;
-	struct cpts_event *event;
-	struct list_head *this, *next;
 	struct cpts *cpts = container_of(cc, struct cpts, cc);
 
+	return READ_ONCE(cpts->cur_timestamp);
+}
+
+static void cpts_update_cur_time(struct cpts *cpts, int match,
+				 struct ptp_system_timestamp *sts)
+{
+	unsigned long flags;
+
+	reinit_completion(&cpts->ts_push_complete);
+
+	/* use spin_lock_irqsave() here as it has to run very fast */
+	spin_lock_irqsave(&cpts->lock, flags);
+	ptp_read_system_prets(sts);
 	cpts_write32(cpts, TS_PUSH, ts_push);
-	if (cpts_fifo_read(cpts, CPTS_EV_PUSH))
-		pr_err("cpts: unable to obtain a time stamp\n");
+	cpts_read32(cpts, ts_push);
+	ptp_read_system_postts(sts);
+	spin_unlock_irqrestore(&cpts->lock, flags);
 
-	list_for_each_safe(this, next, &cpts->events) {
-		event = list_entry(this, struct cpts_event, list);
-		if (event_type(event) == CPTS_EV_PUSH) {
-			list_del_init(&event->list);
-			list_add(&event->list, &cpts->pool);
-			val = event->low;
-			break;
-		}
-	}
+	if (cpts->irq_poll && cpts_fifo_read(cpts, match) && match != -1)
+		dev_err(cpts->dev, "cpts: unable to obtain a time stamp\n");
 
-	return val;
+	if (!cpts->irq_poll &&
+	    !wait_for_completion_timeout(&cpts->ts_push_complete, HZ))
+		dev_err(cpts->dev, "cpts: obtain a time stamp timeout\n");
 }
 
 /* PTP clock operations */
 
-static int cpts_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
+static int cpts_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
 {
-	u64 adj;
-	u32 diff, mult;
-	int neg_adj = 0;
-	unsigned long flags;
 	struct cpts *cpts = container_of(ptp, struct cpts, info);
 
-	if (ppb < 0) {
-		neg_adj = 1;
-		ppb = -ppb;
-	}
-	mult = cpts->cc_mult;
-	adj = mult;
-	adj *= ppb;
-	diff = div_u64(adj, 1000000000ULL);
-
-	spin_lock_irqsave(&cpts->lock, flags);
-
-	timecounter_read(&cpts->tc);
+	mutex_lock(&cpts->ptp_clk_mutex);
 
-	cpts->cc.mult = neg_adj ? mult - diff : mult + diff;
+	cpts->mult_new = adjust_by_scaled_ppm(cpts->cc_mult, scaled_ppm);
 
-	spin_unlock_irqrestore(&cpts->lock, flags);
+	cpts_update_cur_time(cpts, CPTS_EV_PUSH, NULL);
 
+	mutex_unlock(&cpts->ptp_clk_mutex);
 	return 0;
 }
 
 static int cpts_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 {
-	s64 now;
-	unsigned long flags;
 	struct cpts *cpts = container_of(ptp, struct cpts, info);
 
-	spin_lock_irqsave(&cpts->lock, flags);
-	now = timecounter_read(&cpts->tc);
-	now += delta;
-	timecounter_init(&cpts->tc, &cpts->cc, now);
-	spin_unlock_irqrestore(&cpts->lock, flags);
+	mutex_lock(&cpts->ptp_clk_mutex);
+	timecounter_adjtime(&cpts->tc, delta);
+	mutex_unlock(&cpts->ptp_clk_mutex);
 
 	return 0;
 }
 
-static int cpts_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts)
+static int cpts_ptp_gettimeex(struct ptp_clock_info *ptp,
+			      struct timespec64 *ts,
+			      struct ptp_system_timestamp *sts)
 {
-	u64 ns;
-	u32 remainder;
-	unsigned long flags;
 	struct cpts *cpts = container_of(ptp, struct cpts, info);
+	u64 ns;
+
+	mutex_lock(&cpts->ptp_clk_mutex);
+
+	cpts_update_cur_time(cpts, CPTS_EV_PUSH, sts);
 
-	spin_lock_irqsave(&cpts->lock, flags);
 	ns = timecounter_read(&cpts->tc);
-	spin_unlock_irqrestore(&cpts->lock, flags);
+	mutex_unlock(&cpts->ptp_clk_mutex);
 
-	ts->tv_sec = div_u64_rem(ns, 1000000000, &remainder);
-	ts->tv_nsec = remainder;
+	*ts = ns_to_timespec64(ns);
 
 	return 0;
 }
 
 static int cpts_ptp_settime(struct ptp_clock_info *ptp,
-			    const struct timespec *ts)
+			    const struct timespec64 *ts)
 {
-	u64 ns;
-	unsigned long flags;
 	struct cpts *cpts = container_of(ptp, struct cpts, info);
+	u64 ns;
 
-	ns = ts->tv_sec * 1000000000ULL;
-	ns += ts->tv_nsec;
+	ns = timespec64_to_ns(ts);
 
-	spin_lock_irqsave(&cpts->lock, flags);
+	mutex_lock(&cpts->ptp_clk_mutex);
 	timecounter_init(&cpts->tc, &cpts->cc, ns);
-	spin_unlock_irqrestore(&cpts->lock, flags);
+	mutex_unlock(&cpts->ptp_clk_mutex);
+
+	return 0;
+}
+
+static int cpts_extts_enable(struct cpts *cpts, u32 index, int on)
+{
+	u32 v;
+
+	if (((cpts->hw_ts_enable & BIT(index)) >> index) == on)
+		return 0;
+
+	mutex_lock(&cpts->ptp_clk_mutex);
+
+	v = cpts_read32(cpts, control);
+	if (on) {
+		v |= BIT(8 + index);
+		cpts->hw_ts_enable |= BIT(index);
+	} else {
+		v &= ~BIT(8 + index);
+		cpts->hw_ts_enable &= ~BIT(index);
+	}
+	cpts_write32(cpts, v, control);
+
+	mutex_unlock(&cpts->ptp_clk_mutex);
 
 	return 0;
 }
@@ -209,107 +299,172 @@ static int cpts_ptp_settime(struct ptp_clock_info *ptp,
 static int cpts_ptp_enable(struct ptp_clock_info *ptp,
 			   struct ptp_clock_request *rq, int on)
 {
+	struct cpts *cpts = container_of(ptp, struct cpts, info);
+
+	switch (rq->type) {
+	case PTP_CLK_REQ_EXTTS:
+		return cpts_extts_enable(cpts, rq->extts.index, on);
+	default:
+		break;
+	}
+
 	return -EOPNOTSUPP;
 }
 
-static struct ptp_clock_info cpts_info = {
-	.owner		= THIS_MODULE,
-	.name		= "CTPS timer",
-	.max_adj	= 1000000,
-	.n_ext_ts	= 0,
-	.pps		= 0,
-	.adjfreq	= cpts_ptp_adjfreq,
-	.adjtime	= cpts_ptp_adjtime,
-	.gettime	= cpts_ptp_gettime,
-	.settime	= cpts_ptp_settime,
-	.enable		= cpts_ptp_enable,
-};
-
-static void cpts_overflow_check(struct work_struct *work)
+static bool cpts_match_tx_ts(struct cpts *cpts, struct cpts_event *event)
 {
-	struct timespec ts;
-	struct cpts *cpts = container_of(work, struct cpts, overflow_work.work);
+	struct sk_buff_head txq_list;
+	struct sk_buff *skb, *tmp;
+	unsigned long flags;
+	bool found = false;
+	u32 mtype_seqid;
+
+	mtype_seqid = event->high &
+		      ((MESSAGE_TYPE_MASK << MESSAGE_TYPE_SHIFT) |
+		       (SEQUENCE_ID_MASK << SEQUENCE_ID_SHIFT) |
+		       (EVENT_TYPE_MASK << EVENT_TYPE_SHIFT));
+
+	__skb_queue_head_init(&txq_list);
+
+	spin_lock_irqsave(&cpts->txq.lock, flags);
+	skb_queue_splice_init(&cpts->txq, &txq_list);
+	spin_unlock_irqrestore(&cpts->txq.lock, flags);
+
+	skb_queue_walk_safe(&txq_list, skb, tmp) {
+		struct skb_shared_hwtstamps ssh;
+		struct cpts_skb_cb_data *skb_cb =
+					(struct cpts_skb_cb_data *)skb->cb;
+
+		if (mtype_seqid == skb_cb->skb_mtype_seqid) {
+			memset(&ssh, 0, sizeof(ssh));
+			ssh.hwtstamp = ns_to_ktime(event->timestamp);
+			skb_tstamp_tx(skb, &ssh);
+			found = true;
+			__skb_unlink(skb, &txq_list);
+			dev_consume_skb_any(skb);
+			dev_dbg(cpts->dev, "match tx timestamp mtype_seqid %08x\n",
+				mtype_seqid);
+			break;
+		}
 
-	cpts_write32(cpts, CPTS_EN, control);
-	cpts_write32(cpts, TS_PEND_EN, int_enable);
-	cpts_ptp_gettime(&cpts->info, &ts);
-	pr_debug("cpts overflow check at %ld.%09lu\n", ts.tv_sec, ts.tv_nsec);
-	schedule_delayed_work(&cpts->overflow_work, CPTS_OVERFLOW_PERIOD);
-}
+		if (time_after(jiffies, skb_cb->tmo)) {
+			/* timeout any expired skbs over 1s */
+			dev_dbg(cpts->dev, "expiring tx timestamp from txq\n");
+			__skb_unlink(skb, &txq_list);
+			dev_consume_skb_any(skb);
+		}
+	}
 
-#define CPTS_REF_CLOCK_NAME "cpsw_cpts_rft_clk"
+	spin_lock_irqsave(&cpts->txq.lock, flags);
+	skb_queue_splice(&txq_list, &cpts->txq);
+	spin_unlock_irqrestore(&cpts->txq.lock, flags);
 
-static void cpts_clk_init(struct cpts *cpts)
+	return found;
+}
+
+static void cpts_process_events(struct cpts *cpts)
 {
-	cpts->refclk = clk_get(NULL, CPTS_REF_CLOCK_NAME);
-	if (IS_ERR(cpts->refclk)) {
-		pr_err("Failed to clk_get %s\n", CPTS_REF_CLOCK_NAME);
-		cpts->refclk = NULL;
-		return;
+	struct list_head *this, *next;
+	struct cpts_event *event;
+	LIST_HEAD(events_free);
+	unsigned long flags;
+	LIST_HEAD(events);
+
+	spin_lock_irqsave(&cpts->lock, flags);
+	list_splice_init(&cpts->events, &events);
+	spin_unlock_irqrestore(&cpts->lock, flags);
+
+	list_for_each_safe(this, next, &events) {
+		event = list_entry(this, struct cpts_event, list);
+		if (cpts_match_tx_ts(cpts, event) ||
+		    time_after(jiffies, event->tmo)) {
+			list_del_init(&event->list);
+			list_add(&event->list, &events_free);
+		}
 	}
-	clk_prepare_enable(cpts->refclk);
+
+	spin_lock_irqsave(&cpts->lock, flags);
+	list_splice_tail(&events, &cpts->events);
+	list_splice_tail(&events_free, &cpts->pool);
+	spin_unlock_irqrestore(&cpts->lock, flags);
 }
 
-static void cpts_clk_release(struct cpts *cpts)
+static long cpts_overflow_check(struct ptp_clock_info *ptp)
 {
-	clk_disable(cpts->refclk);
-	clk_put(cpts->refclk);
+	struct cpts *cpts = container_of(ptp, struct cpts, info);
+	unsigned long delay = cpts->ov_check_period;
+	unsigned long flags;
+	u64 ns;
+
+	mutex_lock(&cpts->ptp_clk_mutex);
+
+	cpts_update_cur_time(cpts, -1, NULL);
+	ns = timecounter_read(&cpts->tc);
+
+	cpts_process_events(cpts);
+
+	spin_lock_irqsave(&cpts->txq.lock, flags);
+	if (!skb_queue_empty(&cpts->txq)) {
+		cpts_purge_txq(cpts);
+		if (!skb_queue_empty(&cpts->txq))
+			delay = CPTS_SKB_TX_WORK_TIMEOUT;
+	}
+	spin_unlock_irqrestore(&cpts->txq.lock, flags);
+
+	dev_dbg(cpts->dev, "cpts overflow check at %lld\n", ns);
+	mutex_unlock(&cpts->ptp_clk_mutex);
+	return (long)delay;
 }
 
-static int cpts_match(struct sk_buff *skb, unsigned int ptp_class,
-		      u16 ts_seqid, u8 ts_msgtype)
+static const struct ptp_clock_info cpts_info = {
+	.owner		= THIS_MODULE,
+	.name		= "CTPS timer",
+	.max_adj	= 1000000,
+	.n_ext_ts	= 0,
+	.n_pins		= 0,
+	.pps		= 0,
+	.adjfine	= cpts_ptp_adjfine,
+	.adjtime	= cpts_ptp_adjtime,
+	.gettimex64	= cpts_ptp_gettimeex,
+	.settime64	= cpts_ptp_settime,
+	.enable		= cpts_ptp_enable,
+	.do_aux_work	= cpts_overflow_check,
+};
+
+static int cpts_skb_get_mtype_seqid(struct sk_buff *skb, u32 *mtype_seqid)
 {
-	u16 *seqid;
-	unsigned int offset;
-	u8 *msgtype, *data = skb->data;
+	unsigned int ptp_class = ptp_classify_raw(skb);
+	struct ptp_header *hdr;
+	u8 msgtype;
+	u16 seqid;
 
-	switch (ptp_class) {
-	case PTP_CLASS_V1_IPV4:
-	case PTP_CLASS_V2_IPV4:
-		offset = ETH_HLEN + IPV4_HLEN(data) + UDP_HLEN;
-		break;
-	case PTP_CLASS_V1_IPV6:
-	case PTP_CLASS_V2_IPV6:
-		offset = OFF_PTP6;
-		break;
-	case PTP_CLASS_V2_L2:
-		offset = ETH_HLEN;
-		break;
-	case PTP_CLASS_V2_VLAN:
-		offset = ETH_HLEN + VLAN_HLEN;
-		break;
-	default:
+	if (ptp_class == PTP_CLASS_NONE)
 		return 0;
-	}
 
-	if (skb->len + ETH_HLEN < offset + OFF_PTP_SEQUENCE_ID + sizeof(*seqid))
+	hdr = ptp_parse_header(skb, ptp_class);
+	if (!hdr)
 		return 0;
 
-	if (unlikely(ptp_class & PTP_CLASS_V1))
-		msgtype = data + offset + OFF_PTP_CONTROL;
-	else
-		msgtype = data + offset;
+	msgtype = ptp_get_msgtype(hdr, ptp_class);
+	seqid	= ntohs(hdr->sequence_id);
 
-	seqid = (u16 *)(data + offset + OFF_PTP_SEQUENCE_ID);
+	*mtype_seqid  = (msgtype & MESSAGE_TYPE_MASK) << MESSAGE_TYPE_SHIFT;
+	*mtype_seqid |= (seqid & SEQUENCE_ID_MASK) << SEQUENCE_ID_SHIFT;
 
-	return (ts_msgtype == (*msgtype & 0xf) && ts_seqid == ntohs(*seqid));
+	return 1;
 }
 
-static u64 cpts_find_ts(struct cpts *cpts, struct sk_buff *skb, int ev_type)
+static u64 cpts_find_ts(struct cpts *cpts, struct sk_buff *skb,
+			int ev_type, u32 skb_mtype_seqid)
 {
-	u64 ns = 0;
-	struct cpts_event *event;
 	struct list_head *this, *next;
-	unsigned int class = sk_run_filter(skb, ptp_filter);
+	struct cpts_event *event;
 	unsigned long flags;
-	u16 seqid;
-	u8 mtype;
-
-	if (class == PTP_CLASS_NONE)
-		return 0;
+	u32 mtype_seqid;
+	u64 ns = 0;
 
+	cpts_fifo_read(cpts, -1);
 	spin_lock_irqsave(&cpts->lock, flags);
-	cpts_fifo_read(cpts, CPTS_EV_PUSH);
 	list_for_each_safe(this, next, &cpts->events) {
 		event = list_entry(this, struct cpts_event, list);
 		if (event_expired(event)) {
@@ -317,11 +472,14 @@ static u64 cpts_find_ts(struct cpts *cpts, struct sk_buff *skb, int ev_type)
 			list_add(&event->list, &cpts->pool);
 			continue;
 		}
-		mtype = (event->high >> MESSAGE_TYPE_SHIFT) & MESSAGE_TYPE_MASK;
-		seqid = (event->high >> SEQUENCE_ID_SHIFT) & SEQUENCE_ID_MASK;
-		if (ev_type == event_type(event) &&
-		    cpts_match(skb, class, seqid, mtype)) {
-			ns = timecounter_cyc2time(&cpts->tc, event->low);
+
+		mtype_seqid = event->high &
+			      ((MESSAGE_TYPE_MASK << MESSAGE_TYPE_SHIFT) |
+			       (SEQUENCE_ID_MASK << SEQUENCE_ID_SHIFT) |
+			       (EVENT_TYPE_MASK << EVENT_TYPE_SHIFT));
+
+		if (mtype_seqid == skb_mtype_seqid) {
+			ns = event->timestamp;
 			list_del_init(&event->list);
 			list_add(&event->list, &cpts->pool);
 			break;
@@ -334,91 +492,323 @@ static u64 cpts_find_ts(struct cpts *cpts, struct sk_buff *skb, int ev_type)
 
 void cpts_rx_timestamp(struct cpts *cpts, struct sk_buff *skb)
 {
-	u64 ns;
+	struct cpts_skb_cb_data *skb_cb = (struct cpts_skb_cb_data *)skb->cb;
 	struct skb_shared_hwtstamps *ssh;
+	int ret;
+	u64 ns;
 
-	if (!cpts->rx_enable)
+	/* cpts_rx_timestamp() is called before eth_type_trans(), so
+	 * skb MAC Hdr properties are not configured yet. Hence need to
+	 * reset skb MAC header here
+	 */
+	skb_reset_mac_header(skb);
+	ret = cpts_skb_get_mtype_seqid(skb, &skb_cb->skb_mtype_seqid);
+	if (!ret)
 		return;
-	ns = cpts_find_ts(cpts, skb, CPTS_EV_RX);
+
+	skb_cb->skb_mtype_seqid |= (CPTS_EV_RX << EVENT_TYPE_SHIFT);
+
+	dev_dbg(cpts->dev, "%s mtype seqid %08x\n",
+		__func__, skb_cb->skb_mtype_seqid);
+
+	ns = cpts_find_ts(cpts, skb, CPTS_EV_RX, skb_cb->skb_mtype_seqid);
 	if (!ns)
 		return;
 	ssh = skb_hwtstamps(skb);
 	memset(ssh, 0, sizeof(*ssh));
 	ssh->hwtstamp = ns_to_ktime(ns);
 }
+EXPORT_SYMBOL_GPL(cpts_rx_timestamp);
 
 void cpts_tx_timestamp(struct cpts *cpts, struct sk_buff *skb)
 {
-	u64 ns;
-	struct skb_shared_hwtstamps ssh;
+	struct cpts_skb_cb_data *skb_cb = (struct cpts_skb_cb_data *)skb->cb;
+	int ret;
 
 	if (!(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS))
 		return;
-	ns = cpts_find_ts(cpts, skb, CPTS_EV_TX);
-	if (!ns)
+
+	ret = cpts_skb_get_mtype_seqid(skb, &skb_cb->skb_mtype_seqid);
+	if (!ret)
 		return;
-	memset(&ssh, 0, sizeof(ssh));
-	ssh.hwtstamp = ns_to_ktime(ns);
-	skb_tstamp_tx(skb, &ssh);
-}
 
-#endif /*CONFIG_TI_CPTS*/
+	skb_cb->skb_mtype_seqid |= (CPTS_EV_TX << EVENT_TYPE_SHIFT);
 
-int cpts_register(struct device *dev, struct cpts *cpts,
-		  u32 mult, u32 shift)
-{
-#ifdef CONFIG_TI_CPTS
-	int err, i;
-	unsigned long flags;
+	dev_dbg(cpts->dev, "%s mtype seqid %08x\n",
+		__func__, skb_cb->skb_mtype_seqid);
 
-	if (ptp_filter_init(ptp_filter, ARRAY_SIZE(ptp_filter))) {
-		pr_err("cpts: bad ptp filter\n");
-		return -EINVAL;
-	}
-	cpts->info = cpts_info;
-	cpts->clock = ptp_clock_register(&cpts->info, dev);
-	if (IS_ERR(cpts->clock)) {
-		err = PTR_ERR(cpts->clock);
-		cpts->clock = NULL;
-		return err;
-	}
-	spin_lock_init(&cpts->lock);
+	/* Always defer TX TS processing to PTP worker */
+	skb_get(skb);
+	/* get the timestamp for timeouts */
+	skb_cb->tmo = jiffies + msecs_to_jiffies(CPTS_SKB_RX_TX_TMO);
+	skb_queue_tail(&cpts->txq, skb);
+	ptp_schedule_worker(cpts->clock, 0);
+}
+EXPORT_SYMBOL_GPL(cpts_tx_timestamp);
 
-	cpts->cc.read = cpts_systim_read;
-	cpts->cc.mask = CLOCKSOURCE_MASK(32);
-	cpts->cc_mult = mult;
-	cpts->cc.mult = mult;
-	cpts->cc.shift = shift;
+int cpts_register(struct cpts *cpts)
+{
+	int err, i;
 
+	skb_queue_head_init(&cpts->txq);
 	INIT_LIST_HEAD(&cpts->events);
 	INIT_LIST_HEAD(&cpts->pool);
 	for (i = 0; i < CPTS_MAX_EVENTS; i++)
 		list_add(&cpts->pool_data[i].list, &cpts->pool);
 
-	cpts_clk_init(cpts);
+	err = clk_enable(cpts->refclk);
+	if (err)
+		return err;
+
 	cpts_write32(cpts, CPTS_EN, control);
 	cpts_write32(cpts, TS_PEND_EN, int_enable);
 
-	spin_lock_irqsave(&cpts->lock, flags);
-	timecounter_init(&cpts->tc, &cpts->cc, ktime_to_ns(ktime_get_real()));
-	spin_unlock_irqrestore(&cpts->lock, flags);
-
-	INIT_DELAYED_WORK(&cpts->overflow_work, cpts_overflow_check);
-	schedule_delayed_work(&cpts->overflow_work, CPTS_OVERFLOW_PERIOD);
+	timecounter_init(&cpts->tc, &cpts->cc, ktime_get_real_ns());
 
+	cpts->clock = ptp_clock_register(&cpts->info, cpts->dev);
+	if (IS_ERR(cpts->clock)) {
+		err = PTR_ERR(cpts->clock);
+		cpts->clock = NULL;
+		goto err_ptp;
+	}
 	cpts->phc_index = ptp_clock_index(cpts->clock);
-#endif
+
+	ptp_schedule_worker(cpts->clock, cpts->ov_check_period);
 	return 0;
+
+err_ptp:
+	clk_disable(cpts->refclk);
+	return err;
 }
+EXPORT_SYMBOL_GPL(cpts_register);
 
 void cpts_unregister(struct cpts *cpts)
 {
-#ifdef CONFIG_TI_CPTS
-	if (cpts->clock) {
-		ptp_clock_unregister(cpts->clock);
-		cancel_delayed_work_sync(&cpts->overflow_work);
+	if (WARN_ON(!cpts->clock))
+		return;
+
+	ptp_clock_unregister(cpts->clock);
+	cpts->clock = NULL;
+	cpts->phc_index = -1;
+
+	cpts_write32(cpts, 0, int_enable);
+	cpts_write32(cpts, 0, control);
+
+	/* Drop all packet */
+	skb_queue_purge(&cpts->txq);
+
+	clk_disable(cpts->refclk);
+}
+EXPORT_SYMBOL_GPL(cpts_unregister);
+
+static void cpts_calc_mult_shift(struct cpts *cpts)
+{
+	u64 frac, maxsec, ns;
+	u32 freq;
+
+	freq = clk_get_rate(cpts->refclk);
+
+	/* Calc the maximum number of seconds which we can run before
+	 * wrapping around.
+	 */
+	maxsec = cpts->cc.mask;
+	do_div(maxsec, freq);
+	/* limit conversation rate to 10 sec as higher values will produce
+	 * too small mult factors and so reduce the conversion accuracy
+	 */
+	if (maxsec > 10)
+		maxsec = 10;
+
+	/* Calc overflow check period (maxsec / 2) */
+	cpts->ov_check_period = (HZ * maxsec) / 2;
+	dev_info(cpts->dev, "cpts: overflow check period %lu (jiffies)\n",
+		 cpts->ov_check_period);
+
+	if (cpts->cc.mult || cpts->cc.shift)
+		return;
+
+	clocks_calc_mult_shift(&cpts->cc.mult, &cpts->cc.shift,
+			       freq, NSEC_PER_SEC, maxsec);
+
+	frac = 0;
+	ns = cyclecounter_cyc2ns(&cpts->cc, freq, cpts->cc.mask, &frac);
+
+	dev_info(cpts->dev,
+		 "CPTS: ref_clk_freq:%u calc_mult:%u calc_shift:%u error:%lld nsec/sec\n",
+		 freq, cpts->cc.mult, cpts->cc.shift, (ns - NSEC_PER_SEC));
+}
+
+static void cpts_clk_unregister(void *clk)
+{
+	clk_hw_unregister_mux(clk);
+}
+
+static void cpts_clk_del_provider(void *np)
+{
+	of_clk_del_provider(np);
+}
+
+static int cpts_of_mux_clk_setup(struct cpts *cpts, struct device_node *node)
+{
+	struct device_node *refclk_np;
+	const char **parent_names;
+	unsigned int num_parents;
+	struct clk_hw *clk_hw;
+	int ret = -EINVAL;
+	u32 *mux_table;
+
+	refclk_np = of_get_child_by_name(node, "cpts-refclk-mux");
+	if (!refclk_np)
+		/* refclk selection supported not for all SoCs */
+		return 0;
+
+	num_parents = of_clk_get_parent_count(refclk_np);
+	if (num_parents < 1) {
+		dev_err(cpts->dev, "mux-clock %s must have parents\n",
+			refclk_np->name);
+		goto mux_fail;
+	}
+
+	parent_names = devm_kcalloc(cpts->dev, num_parents,
+				    sizeof(*parent_names), GFP_KERNEL);
+
+	mux_table = devm_kcalloc(cpts->dev, num_parents, sizeof(*mux_table),
+				 GFP_KERNEL);
+	if (!mux_table || !parent_names) {
+		ret = -ENOMEM;
+		goto mux_fail;
+	}
+
+	of_clk_parent_fill(refclk_np, parent_names, num_parents);
+
+	ret = of_property_read_variable_u32_array(refclk_np, "ti,mux-tbl",
+						  mux_table,
+						  num_parents, num_parents);
+	if (ret < 0)
+		goto mux_fail;
+
+	clk_hw = clk_hw_register_mux_table(cpts->dev, refclk_np->name,
+					   parent_names, num_parents,
+					   0,
+					   &cpts->reg->rftclk_sel, 0, 0x1F,
+					   0, mux_table, NULL);
+	if (IS_ERR(clk_hw)) {
+		ret = PTR_ERR(clk_hw);
+		goto mux_fail;
 	}
-	if (cpts->refclk)
-		cpts_clk_release(cpts);
-#endif
+
+	ret = devm_add_action_or_reset(cpts->dev, cpts_clk_unregister, clk_hw);
+	if (ret) {
+		dev_err(cpts->dev, "add clkmux unreg action %d", ret);
+		goto mux_fail;
+	}
+
+	ret = of_clk_add_hw_provider(refclk_np, of_clk_hw_simple_get, clk_hw);
+	if (ret)
+		goto mux_fail;
+
+	ret = devm_add_action_or_reset(cpts->dev, cpts_clk_del_provider,
+				       refclk_np);
+	if (ret) {
+		dev_err(cpts->dev, "add clkmux provider unreg action %d", ret);
+		goto mux_fail;
+	}
+
+	return ret;
+
+mux_fail:
+	of_node_put(refclk_np);
+	return ret;
 }
+
+static int cpts_of_parse(struct cpts *cpts, struct device_node *node)
+{
+	int ret = -EINVAL;
+	u32 prop;
+
+	if (!of_property_read_u32(node, "cpts_clock_mult", &prop))
+		cpts->cc.mult = prop;
+
+	if (!of_property_read_u32(node, "cpts_clock_shift", &prop))
+		cpts->cc.shift = prop;
+
+	if ((cpts->cc.mult && !cpts->cc.shift) ||
+	    (!cpts->cc.mult && cpts->cc.shift))
+		goto of_error;
+
+	return cpts_of_mux_clk_setup(cpts, node);
+
+of_error:
+	dev_err(cpts->dev, "CPTS: Missing property in the DT.\n");
+	return ret;
+}
+
+struct cpts *cpts_create(struct device *dev, void __iomem *regs,
+			 struct device_node *node, u32 n_ext_ts)
+{
+	struct cpts *cpts;
+	int ret;
+
+	cpts = devm_kzalloc(dev, sizeof(*cpts), GFP_KERNEL);
+	if (!cpts)
+		return ERR_PTR(-ENOMEM);
+
+	cpts->dev = dev;
+	cpts->reg = (struct cpsw_cpts __iomem *)regs;
+	cpts->irq_poll = true;
+	spin_lock_init(&cpts->lock);
+	mutex_init(&cpts->ptp_clk_mutex);
+	init_completion(&cpts->ts_push_complete);
+
+	ret = cpts_of_parse(cpts, node);
+	if (ret)
+		return ERR_PTR(ret);
+
+	cpts->refclk = devm_get_clk_from_child(dev, node, "cpts");
+	if (IS_ERR(cpts->refclk))
+		/* try get clk from dev node for compatibility */
+		cpts->refclk = devm_clk_get(dev, "cpts");
+
+	if (IS_ERR(cpts->refclk)) {
+		dev_err(dev, "Failed to get cpts refclk %ld\n",
+			PTR_ERR(cpts->refclk));
+		return ERR_CAST(cpts->refclk);
+	}
+
+	ret = clk_prepare(cpts->refclk);
+	if (ret)
+		return ERR_PTR(ret);
+
+	cpts->cc.read = cpts_systim_read;
+	cpts->cc.mask = CLOCKSOURCE_MASK(32);
+	cpts->info = cpts_info;
+	cpts->phc_index = -1;
+
+	if (n_ext_ts)
+		cpts->info.n_ext_ts = n_ext_ts;
+
+	cpts_calc_mult_shift(cpts);
+	/* save cc.mult original value as it can be modified
+	 * by cpts_ptp_adjfine().
+	 */
+	cpts->cc_mult = cpts->cc.mult;
+
+	return cpts;
+}
+EXPORT_SYMBOL_GPL(cpts_create);
+
+void cpts_release(struct cpts *cpts)
+{
+	if (!cpts)
+		return;
+
+	if (WARN_ON(!cpts->refclk))
+		return;
+
+	clk_unprepare(cpts->refclk);
+}
+EXPORT_SYMBOL_GPL(cpts_release);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("TI CPTS driver");
+MODULE_AUTHOR("Richard Cochran <richardcochran@gmail.com>");