Merge tag 'vfs-6.6-merge-2' of ssh://gitolite.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull filesystem freezing updates from Darrick Wong:

New code for 6.6:

 * Allow the kernel to initiate a freeze of a filesystem.  The kernel
   and userspace can both hold a freeze on a filesystem at the same
   time; the freeze is not lifted until /both/ holders lift it.  This
   will enable us to fix a longstanding bug in XFS online fsck.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Message-Id: <20230822182604.GB11286@frogsfrogsfrogs>
Signed-off-by: Christian Brauner <brauner@kernel.org>

8 files changed, 178 insertions, 70 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 93979ab18bc1..19a5e7f3a075 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -5739,6 +5739,13 @@ ice_set_tx_maxrate(struct net_device *netdev, int queue_index, u32 maxrate)
 	q_handle = vsi->tx_rings[queue_index]->q_handle;
 	tc = ice_dcb_get_tc(vsi, queue_index);
 
+	vsi = ice_locate_vsi_using_queue(vsi, queue_index);
+	if (!vsi) {
+		netdev_err(netdev, "Invalid VSI for given queue %d\n",
+			   queue_index);
+		return -EINVAL;
+	}
+
 	/* Set BW back to default, when user set maxrate to 0 */
 	if (!maxrate)
 		status = ice_cfg_q_bw_dflt_lmt(vsi->port_info, vsi->idx, tc,
@@ -7872,10 +7879,10 @@ static int
 ice_validate_mqprio_qopt(struct ice_vsi *vsi,
 			 struct tc_mqprio_qopt_offload *mqprio_qopt)
 {
-	u64 sum_max_rate = 0, sum_min_rate = 0;
 	int non_power_of_2_qcount = 0;
 	struct ice_pf *pf = vsi->back;
 	int max_rss_q_cnt = 0;
+	u64 sum_min_rate = 0;
 	struct device *dev;
 	int i, speed;
 	u8 num_tc;
@@ -7891,6 +7898,7 @@ ice_validate_mqprio_qopt(struct ice_vsi *vsi,
 	dev = ice_pf_to_dev(pf);
 	vsi->ch_rss_size = 0;
 	num_tc = mqprio_qopt->qopt.num_tc;
+	speed = ice_get_link_speed_kbps(vsi);
 
 	for (i = 0; num_tc; i++) {
 		int qcount = mqprio_qopt->qopt.count[i];
@@ -7931,7 +7939,6 @@ ice_validate_mqprio_qopt(struct ice_vsi *vsi,
 		 */
 		max_rate = mqprio_qopt->max_rate[i];
 		max_rate = div_u64(max_rate, ICE_BW_KBPS_DIVISOR);
-		sum_max_rate += max_rate;
 
 		/* min_rate is minimum guaranteed rate and it can't be zero */
 		min_rate = mqprio_qopt->min_rate[i];
@@ -7944,6 +7951,12 @@ ice_validate_mqprio_qopt(struct ice_vsi *vsi,
 			return -EINVAL;
 		}
 
+		if (max_rate && max_rate > speed) {
+			dev_err(dev, "TC%d: max_rate(%llu Kbps) > link speed of %u Kbps\n",
+				i, max_rate, speed);
+			return -EINVAL;
+		}
+
 		iter_div_u64_rem(min_rate, ICE_MIN_BW_LIMIT, &rem);
 		if (rem) {
 			dev_err(dev, "TC%d: Min Rate not multiple of %u Kbps",
@@ -7981,12 +7994,6 @@ ice_validate_mqprio_qopt(struct ice_vsi *vsi,
 	    (mqprio_qopt->qopt.offset[i] + mqprio_qopt->qopt.count[i]))
 		return -EINVAL;
 
-	speed = ice_get_link_speed_kbps(vsi);
-	if (sum_max_rate && sum_max_rate > (u64)speed) {
-		dev_err(dev, "Invalid max Tx rate(%llu) Kbps > speed(%u) Kbps specified\n",
-			sum_max_rate, speed);
-		return -EINVAL;
-	}
 	if (sum_min_rate && sum_min_rate > (u64)speed) {
 		dev_err(dev, "Invalid min Tx rate(%llu) Kbps > speed (%u) Kbps specified\n",
 			sum_min_rate, speed);
diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
index b54052ef6050..4a34ef5f58d3 100644
--- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
@@ -750,17 +750,16 @@ exit:
 /**
  * ice_locate_vsi_using_queue - locate VSI using queue (forward to queue action)
  * @vsi: Pointer to VSI
- * @tc_fltr: Pointer to tc_flower_filter
+ * @queue: Queue index
  *
- * Locate the VSI using specified queue. When ADQ is not enabled, always
- * return input VSI, otherwise locate corresponding VSI based on per channel
- * offset and qcount
+ * Locate the VSI using specified "queue". When ADQ is not enabled,
+ * always return input VSI, otherwise locate corresponding
+ * VSI based on per channel "offset" and "qcount"
  */
-static struct ice_vsi *
-ice_locate_vsi_using_queue(struct ice_vsi *vsi,
-			   struct ice_tc_flower_fltr *tc_fltr)
+struct ice_vsi *
+ice_locate_vsi_using_queue(struct ice_vsi *vsi, int queue)
 {
-	int num_tc, tc, queue;
+	int num_tc, tc;
 
 	/* if ADQ is not active, passed VSI is the candidate VSI */
 	if (!ice_is_adq_active(vsi->back))
@@ -770,7 +769,6 @@ ice_locate_vsi_using_queue(struct ice_vsi *vsi,
 	 * upon queue number)
 	 */
 	num_tc = vsi->mqprio_qopt.qopt.num_tc;
-	queue = tc_fltr->action.fwd.q.queue;
 
 	for (tc = 0; tc < num_tc; tc++) {
 		int qcount = vsi->mqprio_qopt.qopt.count[tc];
@@ -812,6 +810,7 @@ ice_tc_forward_action(struct ice_vsi *vsi, struct ice_tc_flower_fltr *tc_fltr)
 	struct ice_pf *pf = vsi->back;
 	struct device *dev;
 	u32 tc_class;
+	int q;
 
 	dev = ice_pf_to_dev(pf);
 
@@ -840,7 +839,8 @@ ice_tc_forward_action(struct ice_vsi *vsi, struct ice_tc_flower_fltr *tc_fltr)
 		/* Determine destination VSI even though the action is
 		 * FWD_TO_QUEUE, because QUEUE is associated with VSI
 		 */
-		dest_vsi = tc_fltr->dest_vsi;
+		q = tc_fltr->action.fwd.q.queue;
+		dest_vsi = ice_locate_vsi_using_queue(vsi, q);
 		break;
 	default:
 		dev_err(dev,
@@ -1716,7 +1716,7 @@ ice_tc_forward_to_queue(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr,
 	/* If ADQ is configured, and the queue belongs to ADQ VSI, then prepare
 	 * ADQ switch filter
 	 */
-	ch_vsi = ice_locate_vsi_using_queue(vsi, fltr);
+	ch_vsi = ice_locate_vsi_using_queue(vsi, fltr->action.fwd.q.queue);
 	if (!ch_vsi)
 		return -EINVAL;
 	fltr->dest_vsi = ch_vsi;
diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.h b/drivers/net/ethernet/intel/ice/ice_tc_lib.h
index 8bbc1a62bdb1..65d387163a46 100644
--- a/drivers/net/ethernet/intel/ice/ice_tc_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.h
@@ -204,6 +204,7 @@ static inline int ice_chnl_dmac_fltr_cnt(struct ice_pf *pf)
 	return pf->num_dmac_chnl_fltrs;
 }
 
+struct ice_vsi *ice_locate_vsi_using_queue(struct ice_vsi *vsi, int queue);
 int
 ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi,
 		   struct flow_cls_offload *cls_flower);
diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 00a5ee487812..9db384f66a8e 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -14,6 +14,7 @@
 #include <linux/timecounter.h>
 #include <linux/net_tstamp.h>
 #include <linux/bitfield.h>
+#include <linux/hrtimer.h>
 
 #include "igc_hw.h"
 
@@ -101,6 +102,8 @@ struct igc_ring {
 	u32 start_time;
 	u32 end_time;
 	u32 max_sdu;
+	bool oper_gate_closed;		/* Operating gate. True if the TX Queue is closed */
+	bool admin_gate_closed;		/* Future gate. True if the TX Queue will be closed */
 
 	/* CBS parameters */
 	bool cbs_enable;                /* indicates if CBS is enabled */
@@ -160,6 +163,7 @@ struct igc_adapter {
 	struct timer_list watchdog_timer;
 	struct timer_list dma_err_timer;
 	struct timer_list phy_info_timer;
+	struct hrtimer hrtimer;
 
 	u32 wol;
 	u32 en_mng_pt;
@@ -184,10 +188,13 @@ struct igc_adapter {
 	u32 max_frame_size;
 	u32 min_frame_size;
 
+	int tc_setup_type;
 	ktime_t base_time;
 	ktime_t cycle_time;
-	bool qbv_enable;
+	bool taprio_offload_enable;
 	u32 qbv_config_change_errors;
+	bool qbv_transition;
+	unsigned int qbv_count;
 
 	/* OS defined structs */
 	struct pci_dev *pdev;
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 0e2cb00622d1..93bce729be76 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1708,6 +1708,8 @@ static int igc_ethtool_get_link_ksettings(struct net_device *netdev,
 	/* twisted pair */
 	cmd->base.port = PORT_TP;
 	cmd->base.phy_address = hw->phy.addr;
+	ethtool_link_ksettings_add_link_mode(cmd, supported, TP);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, TP);
 
 	/* advertising link modes */
 	if (hw->phy.autoneg_advertised & ADVERTISE_10_HALF)
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 019ce91c45aa..9f93f0f4f752 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -711,7 +711,6 @@ static void igc_configure_tx_ring(struct igc_adapter *adapter,
 	/* disable the queue */
 	wr32(IGC_TXDCTL(reg_idx), 0);
 	wrfl();
-	mdelay(10);
 
 	wr32(IGC_TDLEN(reg_idx),
 	     ring->count * sizeof(union igc_adv_tx_desc));
@@ -1017,7 +1016,7 @@ static __le32 igc_tx_launchtime(struct igc_ring *ring, ktime_t txtime,
 	ktime_t base_time = adapter->base_time;
 	ktime_t now = ktime_get_clocktai();
 	ktime_t baset_est, end_of_cycle;
-	u32 launchtime;
+	s32 launchtime;
 	s64 n;
 
 	n = div64_s64(ktime_sub_ns(now, base_time), cycle_time);
@@ -1030,7 +1029,7 @@ static __le32 igc_tx_launchtime(struct igc_ring *ring, ktime_t txtime,
 			*first_flag = true;
 			ring->last_ff_cycle = baset_est;
 
-			if (ktime_compare(txtime, ring->last_tx_cycle) > 0)
+			if (ktime_compare(end_of_cycle, ring->last_tx_cycle) > 0)
 				*insert_empty = true;
 		}
 	}
@@ -1573,16 +1572,12 @@ done:
 	first->bytecount = skb->len;
 	first->gso_segs = 1;
 
-	if (tx_ring->max_sdu > 0) {
-		u32 max_sdu = 0;
-
-		max_sdu = tx_ring->max_sdu +
-			  (skb_vlan_tagged(first->skb) ? VLAN_HLEN : 0);
+	if (adapter->qbv_transition || tx_ring->oper_gate_closed)
+		goto out_drop;
 
-		if (first->bytecount > max_sdu) {
-			adapter->stats.txdrop++;
-			goto out_drop;
-		}
+	if (tx_ring->max_sdu > 0 && first->bytecount > tx_ring->max_sdu) {
+		adapter->stats.txdrop++;
+		goto out_drop;
 	}
 
 	if (unlikely(test_bit(IGC_RING_FLAG_TX_HWTSTAMP, &tx_ring->flags) &&
@@ -3012,8 +3007,8 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget)
 		    time_after(jiffies, tx_buffer->time_stamp +
 		    (adapter->tx_timeout_factor * HZ)) &&
 		    !(rd32(IGC_STATUS) & IGC_STATUS_TXOFF) &&
-		    (rd32(IGC_TDH(tx_ring->reg_idx)) !=
-		     readl(tx_ring->tail))) {
+		    (rd32(IGC_TDH(tx_ring->reg_idx)) != readl(tx_ring->tail)) &&
+		    !tx_ring->oper_gate_closed) {
 			/* detected Tx unit hang */
 			netdev_err(tx_ring->netdev,
 				   "Detected Tx Unit Hang\n"
@@ -6102,7 +6097,10 @@ static int igc_tsn_clear_schedule(struct igc_adapter *adapter)
 
 	adapter->base_time = 0;
 	adapter->cycle_time = NSEC_PER_SEC;
+	adapter->taprio_offload_enable = false;
 	adapter->qbv_config_change_errors = 0;
+	adapter->qbv_transition = false;
+	adapter->qbv_count = 0;
 
 	for (i = 0; i < adapter->num_tx_queues; i++) {
 		struct igc_ring *ring = adapter->tx_ring[i];
@@ -6110,6 +6108,8 @@ static int igc_tsn_clear_schedule(struct igc_adapter *adapter)
 		ring->start_time = 0;
 		ring->end_time = NSEC_PER_SEC;
 		ring->max_sdu = 0;
+		ring->oper_gate_closed = false;
+		ring->admin_gate_closed = false;
 	}
 
 	return 0;
@@ -6121,27 +6121,20 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter,
 	bool queue_configured[IGC_MAX_TX_QUEUES] = { };
 	struct igc_hw *hw = &adapter->hw;
 	u32 start_time = 0, end_time = 0;
+	struct timespec64 now;
 	size_t n;
 	int i;
 
-	switch (qopt->cmd) {
-	case TAPRIO_CMD_REPLACE:
-		adapter->qbv_enable = true;
-		break;
-	case TAPRIO_CMD_DESTROY:
-		adapter->qbv_enable = false;
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-
-	if (!adapter->qbv_enable)
+	if (qopt->cmd == TAPRIO_CMD_DESTROY)
 		return igc_tsn_clear_schedule(adapter);
 
+	if (qopt->cmd != TAPRIO_CMD_REPLACE)
+		return -EOPNOTSUPP;
+
 	if (qopt->base_time < 0)
 		return -ERANGE;
 
-	if (igc_is_device_id_i225(hw) && adapter->base_time)
+	if (igc_is_device_id_i225(hw) && adapter->taprio_offload_enable)
 		return -EALREADY;
 
 	if (!validate_schedule(adapter, qopt))
@@ -6149,6 +6142,9 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter,
 
 	adapter->cycle_time = qopt->cycle_time;
 	adapter->base_time = qopt->base_time;
+	adapter->taprio_offload_enable = true;
+
+	igc_ptp_read(adapter, &now);
 
 	for (n = 0; n < qopt->num_entries; n++) {
 		struct tc_taprio_sched_entry *e = &qopt->entries[n];
@@ -6184,7 +6180,10 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter,
 				ring->start_time = start_time;
 			ring->end_time = end_time;
 
-			queue_configured[i] = true;
+			if (ring->start_time >= adapter->cycle_time)
+				queue_configured[i] = false;
+			else
+				queue_configured[i] = true;
 		}
 
 		start_time += e->interval;
@@ -6194,8 +6193,20 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter,
 	 * If not, set the start and end time to be end time.
 	 */
 	for (i = 0; i < adapter->num_tx_queues; i++) {
+		struct igc_ring *ring = adapter->tx_ring[i];
+
+		if (!is_base_time_past(qopt->base_time, &now)) {
+			ring->admin_gate_closed = false;
+		} else {
+			ring->oper_gate_closed = false;
+			ring->admin_gate_closed = false;
+		}
+
 		if (!queue_configured[i]) {
-			struct igc_ring *ring = adapter->tx_ring[i];
+			if (!is_base_time_past(qopt->base_time, &now))
+				ring->admin_gate_closed = true;
+			else
+				ring->oper_gate_closed = true;
 
 			ring->start_time = end_time;
 			ring->end_time = end_time;
@@ -6207,7 +6218,7 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter,
 		struct net_device *dev = adapter->netdev;
 
 		if (qopt->max_sdu[i])
-			ring->max_sdu = qopt->max_sdu[i] + dev->hard_header_len;
+			ring->max_sdu = qopt->max_sdu[i] + dev->hard_header_len - ETH_TLEN;
 		else
 			ring->max_sdu = 0;
 	}
@@ -6327,6 +6338,8 @@ static int igc_setup_tc(struct net_device *dev, enum tc_setup_type type,
 {
 	struct igc_adapter *adapter = netdev_priv(dev);
 
+	adapter->tc_setup_type = type;
+
 	switch (type) {
 	case TC_QUERY_CAPS:
 		return igc_tc_query_caps(adapter, type_data);
@@ -6574,6 +6587,27 @@ static const struct xdp_metadata_ops igc_xdp_metadata_ops = {
 	.xmo_rx_timestamp		= igc_xdp_rx_timestamp,
 };
 
+static enum hrtimer_restart igc_qbv_scheduling_timer(struct hrtimer *timer)
+{
+	struct igc_adapter *adapter = container_of(timer, struct igc_adapter,
+						   hrtimer);
+	unsigned int i;
+
+	adapter->qbv_transition = true;
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		struct igc_ring *tx_ring = adapter->tx_ring[i];
+
+		if (tx_ring->admin_gate_closed) {
+			tx_ring->admin_gate_closed = false;
+			tx_ring->oper_gate_closed = true;
+		} else {
+			tx_ring->oper_gate_closed = false;
+		}
+	}
+	adapter->qbv_transition = false;
+	return HRTIMER_NORESTART;
+}
+
 /**
  * igc_probe - Device Initialization Routine
  * @pdev: PCI device information struct
@@ -6752,6 +6786,9 @@ static int igc_probe(struct pci_dev *pdev,
 	INIT_WORK(&adapter->reset_task, igc_reset_task);
 	INIT_WORK(&adapter->watchdog_task, igc_watchdog_task);
 
+	hrtimer_init(&adapter->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	adapter->hrtimer.function = &igc_qbv_scheduling_timer;
+
 	/* Initialize link properties that are user-changeable */
 	adapter->fc_autoneg = true;
 	hw->mac.autoneg = true;
@@ -6855,6 +6892,7 @@ static void igc_remove(struct pci_dev *pdev)
 
 	cancel_work_sync(&adapter->reset_task);
 	cancel_work_sync(&adapter->watchdog_task);
+	hrtimer_cancel(&adapter->hrtimer);
 
 	/* Release control of h/w to f/w.  If f/w is AMT enabled, this
 	 * would have already happened in close and is redundant.
diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c
index 32ef112f8291..f0b979a70655 100644
--- a/drivers/net/ethernet/intel/igc/igc_ptp.c
+++ b/drivers/net/ethernet/intel/igc/igc_ptp.c
@@ -356,16 +356,35 @@ static int igc_ptp_feature_enable_i225(struct ptp_clock_info *ptp,
 			tsim &= ~IGC_TSICR_TT0;
 		}
 		if (on) {
+			struct timespec64 safe_start;
 			int i = rq->perout.index;
 
 			igc_pin_perout(igc, i, pin, use_freq);
-			igc->perout[i].start.tv_sec = rq->perout.start.sec;
+			igc_ptp_read(igc, &safe_start);
+
+			/* PPS output start time is triggered by Target time(TT)
+			 * register. Programming any past time value into TT
+			 * register will cause PPS to never start. Need to make
+			 * sure we program the TT register a time ahead in
+			 * future. There isn't a stringent need to fire PPS out
+			 * right away. Adding +2 seconds should take care of
+			 * corner cases. Let's say if the SYSTIML is close to
+			 * wrap up and the timer keeps ticking as we program the
+			 * register, adding +2seconds is safe bet.
+			 */
+			safe_start.tv_sec += 2;
+
+			if (rq->perout.start.sec < safe_start.tv_sec)
+				igc->perout[i].start.tv_sec = safe_start.tv_sec;
+			else
+				igc->perout[i].start.tv_sec = rq->perout.start.sec;
 			igc->perout[i].start.tv_nsec = rq->perout.start.nsec;
 			igc->perout[i].period.tv_sec = ts.tv_sec;
 			igc->perout[i].period.tv_nsec = ts.tv_nsec;
-			wr32(trgttimh, rq->perout.start.sec);
+			wr32(trgttimh, (u32)igc->perout[i].start.tv_sec);
 			/* For now, always select timer 0 as source. */
-			wr32(trgttiml, rq->perout.start.nsec | IGC_TT_IO_TIMER_SEL_SYSTIM0);
+			wr32(trgttiml, (u32)(igc->perout[i].start.tv_nsec |
+					     IGC_TT_IO_TIMER_SEL_SYSTIM0));
 			if (use_freq)
 				wr32(freqout, ns);
 			tsauxc |= tsauxc_mask;
diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c
index 94a2b0dfb54d..a9c08321aca9 100644
--- a/drivers/net/ethernet/intel/igc/igc_tsn.c
+++ b/drivers/net/ethernet/intel/igc/igc_tsn.c
@@ -37,7 +37,7 @@ static unsigned int igc_tsn_new_flags(struct igc_adapter *adapter)
 {
 	unsigned int new_flags = adapter->flags & ~IGC_FLAG_TSN_ANY_ENABLED;
 
-	if (adapter->qbv_enable)
+	if (adapter->taprio_offload_enable)
 		new_flags |= IGC_FLAG_TSN_QBV_ENABLED;
 
 	if (is_any_launchtime(adapter))
@@ -114,7 +114,6 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter)
 static int igc_tsn_enable_offload(struct igc_adapter *adapter)
 {
 	struct igc_hw *hw = &adapter->hw;
-	bool tsn_mode_reconfig = false;
 	u32 tqavctrl, baset_l, baset_h;
 	u32 sec, nsec, cycle;
 	ktime_t base_time, systim;
@@ -133,8 +132,28 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter)
 		wr32(IGC_STQT(i), ring->start_time);
 		wr32(IGC_ENDQT(i), ring->end_time);
 
-		txqctl |= IGC_TXQCTL_STRICT_CYCLE |
-			IGC_TXQCTL_STRICT_END;
+		if (adapter->taprio_offload_enable) {
+			/* If taprio_offload_enable is set we are in "taprio"
+			 * mode and we need to be strict about the
+			 * cycles: only transmit a packet if it can be
+			 * completed during that cycle.
+			 *
+			 * If taprio_offload_enable is NOT true when
+			 * enabling TSN offload, the cycle should have
+			 * no external effects, but is only used internally
+			 * to adapt the base time register after a second
+			 * has passed.
+			 *
+			 * Enabling strict mode in this case would
+			 * unnecessarily prevent the transmission of
+			 * certain packets (i.e. at the boundary of a
+			 * second) and thus interfere with the launchtime
+			 * feature that promises transmission at a
+			 * certain point in time.
+			 */
+			txqctl |= IGC_TXQCTL_STRICT_CYCLE |
+				IGC_TXQCTL_STRICT_END;
+		}
 
 		if (ring->launchtime_enable)
 			txqctl |= IGC_TXQCTL_QUEUE_MODE_LAUNCHT;
@@ -228,11 +247,10 @@ skip_cbs:
 
 	tqavctrl = rd32(IGC_TQAVCTRL) & ~IGC_TQAVCTRL_FUTSCDDIS;
 
-	if (tqavctrl & IGC_TQAVCTRL_TRANSMIT_MODE_TSN)
-		tsn_mode_reconfig = true;
-
 	tqavctrl |= IGC_TQAVCTRL_TRANSMIT_MODE_TSN | IGC_TQAVCTRL_ENHANCED_QAV;
 
+	adapter->qbv_count++;
+
 	cycle = adapter->cycle_time;
 	base_time = adapter->base_time;
 
@@ -249,17 +267,29 @@ skip_cbs:
 		 * Gate Control List (GCL) is running.
 		 */
 		if ((rd32(IGC_BASET_H) || rd32(IGC_BASET_L)) &&
-		    tsn_mode_reconfig)
+		    (adapter->tc_setup_type == TC_SETUP_QDISC_TAPRIO) &&
+		    (adapter->qbv_count > 1))
 			adapter->qbv_config_change_errors++;
 	} else {
-		/* According to datasheet section 7.5.2.9.3.3, FutScdDis bit
-		 * has to be configured before the cycle time and base time.
-		 * Tx won't hang if there is a GCL is already running,
-		 * so in this case we don't need to set FutScdDis.
-		 */
-		if (igc_is_device_id_i226(hw) &&
-		    !(rd32(IGC_BASET_H) || rd32(IGC_BASET_L)))
-			tqavctrl |= IGC_TQAVCTRL_FUTSCDDIS;
+		if (igc_is_device_id_i226(hw)) {
+			ktime_t adjust_time, expires_time;
+
+		       /* According to datasheet section 7.5.2.9.3.3, FutScdDis bit
+			* has to be configured before the cycle time and base time.
+			* Tx won't hang if a GCL is already running,
+			* so in this case we don't need to set FutScdDis.
+			*/
+			if (!(rd32(IGC_BASET_H) || rd32(IGC_BASET_L)))
+				tqavctrl |= IGC_TQAVCTRL_FUTSCDDIS;
+
+			nsec = rd32(IGC_SYSTIML);
+			sec = rd32(IGC_SYSTIMH);
+			systim = ktime_set(sec, nsec);
+
+			adjust_time = adapter->base_time;
+			expires_time = ktime_sub_ns(adjust_time, systim);
+			hrtimer_start(&adapter->hrtimer, expires_time, HRTIMER_MODE_REL);
+		}
 	}
 
 	wr32(IGC_TQAVCTRL, tqavctrl);
@@ -305,7 +335,11 @@ int igc_tsn_offload_apply(struct igc_adapter *adapter)
 {
 	struct igc_hw *hw = &adapter->hw;
 
-	if (netif_running(adapter->netdev) && igc_is_device_id_i225(hw)) {
+	/* Per I225/6 HW Design Section 7.5.2.1, transmit mode
+	 * cannot be changed dynamically. Require reset the adapter.
+	 */
+	if (netif_running(adapter->netdev) &&
+	    (igc_is_device_id_i225(hw) || !adapter->qbv_count)) {
 		schedule_work(&adapter->reset_task);
 		return 0;
 	}