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>

57 files changed, 531 insertions, 295 deletions

diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index 70c0e2b1936b..8da46d284e35 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -1286,7 +1286,6 @@ static int felix_parse_ports_node(struct felix *felix,
 		if (err < 0) {
 			dev_info(dev, "Unsupported PHY mode %s on port %d\n",
 				 phy_modes(phy_mode), port);
-			of_node_put(child);
 
 			/* Leave port_phy_modes[port] = 0, which is also
 			 * PHY_INTERFACE_MODE_NA. This will perform a
@@ -1786,16 +1785,15 @@ static int felix_change_mtu(struct dsa_switch *ds, int port, int new_mtu)
 {
 	struct ocelot *ocelot = ds->priv;
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
-	struct felix *felix = ocelot_to_felix(ocelot);
 
 	ocelot_port_set_maxlen(ocelot, port, new_mtu);
 
-	mutex_lock(&ocelot->tas_lock);
+	mutex_lock(&ocelot->fwd_domain_lock);
 
-	if (ocelot_port->taprio && felix->info->tas_guard_bands_update)
-		felix->info->tas_guard_bands_update(ocelot, port);
+	if (ocelot_port->taprio && ocelot->ops->tas_guard_bands_update)
+		ocelot->ops->tas_guard_bands_update(ocelot, port);
 
-	mutex_unlock(&ocelot->tas_lock);
+	mutex_unlock(&ocelot->fwd_domain_lock);
 
 	return 0;
 }
diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h
index 96008c046da5..1d4befe7cfe8 100644
--- a/drivers/net/dsa/ocelot/felix.h
+++ b/drivers/net/dsa/ocelot/felix.h
@@ -57,7 +57,6 @@ struct felix_info {
 	void	(*mdio_bus_free)(struct ocelot *ocelot);
 	int	(*port_setup_tc)(struct dsa_switch *ds, int port,
 				 enum tc_setup_type type, void *type_data);
-	void	(*tas_guard_bands_update)(struct ocelot *ocelot, int port);
 	void	(*port_sched_speed_set)(struct ocelot *ocelot, int port,
 					u32 speed);
 	void	(*phylink_mac_config)(struct ocelot *ocelot, int port,
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index bb39fedd46c7..1c113957fcf4 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -1209,15 +1209,17 @@ static u32 vsc9959_tas_tc_max_sdu(struct tc_taprio_qopt_offload *taprio, int tc)
 static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port)
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
+	struct ocelot_mm_state *mm = &ocelot->mm[port];
 	struct tc_taprio_qopt_offload *taprio;
 	u64 min_gate_len[OCELOT_NUM_TC];
+	u32 val, maxlen, add_frag_size;
+	u64 needed_min_frag_time_ps;
 	int speed, picos_per_byte;
 	u64 needed_bit_time_ps;
-	u32 val, maxlen;
 	u8 tas_speed;
 	int tc;
 
-	lockdep_assert_held(&ocelot->tas_lock);
+	lockdep_assert_held(&ocelot->fwd_domain_lock);
 
 	taprio = ocelot_port->taprio;
 
@@ -1253,14 +1255,21 @@ static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port)
 	 */
 	needed_bit_time_ps = (u64)(maxlen + 24) * picos_per_byte;
 
+	/* Preemptible TCs don't need to pass a full MTU, the port will
+	 * automatically emit a HOLD request when a preemptible TC gate closes
+	 */
+	val = ocelot_read_rix(ocelot, QSYS_PREEMPTION_CFG, port);
+	add_frag_size = QSYS_PREEMPTION_CFG_MM_ADD_FRAG_SIZE_X(val);
+	needed_min_frag_time_ps = picos_per_byte *
+		(u64)(24 + 2 * ethtool_mm_frag_size_add_to_min(add_frag_size));
+
 	dev_dbg(ocelot->dev,
-		"port %d: max frame size %d needs %llu ps at speed %d\n",
-		port, maxlen, needed_bit_time_ps, speed);
+		"port %d: max frame size %d needs %llu ps, %llu ps for mPackets at speed %d\n",
+		port, maxlen, needed_bit_time_ps, needed_min_frag_time_ps,
+		speed);
 
 	vsc9959_tas_min_gate_lengths(taprio, min_gate_len);
 
-	mutex_lock(&ocelot->fwd_domain_lock);
-
 	for (tc = 0; tc < OCELOT_NUM_TC; tc++) {
 		u32 requested_max_sdu = vsc9959_tas_tc_max_sdu(taprio, tc);
 		u64 remaining_gate_len_ps;
@@ -1269,7 +1278,9 @@ static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port)
 		remaining_gate_len_ps =
 			vsc9959_tas_remaining_gate_len_ps(min_gate_len[tc]);
 
-		if (remaining_gate_len_ps > needed_bit_time_ps) {
+		if ((mm->active_preemptible_tcs & BIT(tc)) ?
+		    remaining_gate_len_ps > needed_min_frag_time_ps :
+		    remaining_gate_len_ps > needed_bit_time_ps) {
 			/* Setting QMAXSDU_CFG to 0 disables oversized frame
 			 * dropping.
 			 */
@@ -1323,8 +1334,6 @@ static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port)
 	ocelot_write_rix(ocelot, maxlen, QSYS_PORT_MAX_SDU, port);
 
 	ocelot->ops->cut_through_fwd(ocelot);
-
-	mutex_unlock(&ocelot->fwd_domain_lock);
 }
 
 static void vsc9959_sched_speed_set(struct ocelot *ocelot, int port,
@@ -1351,7 +1360,7 @@ static void vsc9959_sched_speed_set(struct ocelot *ocelot, int port,
 		break;
 	}
 
-	mutex_lock(&ocelot->tas_lock);
+	mutex_lock(&ocelot->fwd_domain_lock);
 
 	ocelot_rmw_rix(ocelot,
 		       QSYS_TAG_CONFIG_LINK_SPEED(tas_speed),
@@ -1361,7 +1370,7 @@ static void vsc9959_sched_speed_set(struct ocelot *ocelot, int port,
 	if (ocelot_port->taprio)
 		vsc9959_tas_guard_bands_update(ocelot, port);
 
-	mutex_unlock(&ocelot->tas_lock);
+	mutex_unlock(&ocelot->fwd_domain_lock);
 }
 
 static void vsc9959_new_base_time(struct ocelot *ocelot, ktime_t base_time,
@@ -1409,7 +1418,7 @@ static int vsc9959_qos_port_tas_set(struct ocelot *ocelot, int port,
 	int ret, i;
 	u32 val;
 
-	mutex_lock(&ocelot->tas_lock);
+	mutex_lock(&ocelot->fwd_domain_lock);
 
 	if (taprio->cmd == TAPRIO_CMD_DESTROY) {
 		ocelot_port_mqprio(ocelot, port, &taprio->mqprio);
@@ -1421,7 +1430,7 @@ static int vsc9959_qos_port_tas_set(struct ocelot *ocelot, int port,
 
 		vsc9959_tas_guard_bands_update(ocelot, port);
 
-		mutex_unlock(&ocelot->tas_lock);
+		mutex_unlock(&ocelot->fwd_domain_lock);
 		return 0;
 	} else if (taprio->cmd != TAPRIO_CMD_REPLACE) {
 		ret = -EOPNOTSUPP;
@@ -1504,7 +1513,7 @@ static int vsc9959_qos_port_tas_set(struct ocelot *ocelot, int port,
 	ocelot_port->taprio = taprio_offload_get(taprio);
 	vsc9959_tas_guard_bands_update(ocelot, port);
 
-	mutex_unlock(&ocelot->tas_lock);
+	mutex_unlock(&ocelot->fwd_domain_lock);
 
 	return 0;
 
@@ -1512,7 +1521,7 @@ err_reset_tc:
 	taprio->mqprio.qopt.num_tc = 0;
 	ocelot_port_mqprio(ocelot, port, &taprio->mqprio);
 err_unlock:
-	mutex_unlock(&ocelot->tas_lock);
+	mutex_unlock(&ocelot->fwd_domain_lock);
 
 	return ret;
 }
@@ -1525,7 +1534,7 @@ static void vsc9959_tas_clock_adjust(struct ocelot *ocelot)
 	int port;
 	u32 val;
 
-	mutex_lock(&ocelot->tas_lock);
+	mutex_lock(&ocelot->fwd_domain_lock);
 
 	for (port = 0; port < ocelot->num_phys_ports; port++) {
 		ocelot_port = ocelot->ports[port];
@@ -1563,7 +1572,7 @@ static void vsc9959_tas_clock_adjust(struct ocelot *ocelot)
 			       QSYS_TAG_CONFIG_ENABLE,
 			       QSYS_TAG_CONFIG, port);
 	}
-	mutex_unlock(&ocelot->tas_lock);
+	mutex_unlock(&ocelot->fwd_domain_lock);
 }
 
 static int vsc9959_qos_port_cbs_set(struct dsa_switch *ds, int port,
@@ -1634,6 +1643,18 @@ static int vsc9959_qos_query_caps(struct tc_query_caps_base *base)
 	}
 }
 
+static int vsc9959_qos_port_mqprio(struct ocelot *ocelot, int port,
+				   struct tc_mqprio_qopt_offload *mqprio)
+{
+	int ret;
+
+	mutex_lock(&ocelot->fwd_domain_lock);
+	ret = ocelot_port_mqprio(ocelot, port, mqprio);
+	mutex_unlock(&ocelot->fwd_domain_lock);
+
+	return ret;
+}
+
 static int vsc9959_port_setup_tc(struct dsa_switch *ds, int port,
 				 enum tc_setup_type type,
 				 void *type_data)
@@ -1646,7 +1667,7 @@ static int vsc9959_port_setup_tc(struct dsa_switch *ds, int port,
 	case TC_SETUP_QDISC_TAPRIO:
 		return vsc9959_qos_port_tas_set(ocelot, port, type_data);
 	case TC_SETUP_QDISC_MQPRIO:
-		return ocelot_port_mqprio(ocelot, port, type_data);
+		return vsc9959_qos_port_mqprio(ocelot, port, type_data);
 	case TC_SETUP_QDISC_CBS:
 		return vsc9959_qos_port_cbs_set(ds, port, type_data);
 	default:
@@ -2591,6 +2612,7 @@ static const struct ocelot_ops vsc9959_ops = {
 	.cut_through_fwd	= vsc9959_cut_through_fwd,
 	.tas_clock_adjust	= vsc9959_tas_clock_adjust,
 	.update_stats		= vsc9959_update_stats,
+	.tas_guard_bands_update	= vsc9959_tas_guard_bands_update,
 };
 
 static const struct felix_info felix_info_vsc9959 = {
@@ -2616,7 +2638,6 @@ static const struct felix_info felix_info_vsc9959 = {
 	.port_modes		= vsc9959_port_modes,
 	.port_setup_tc		= vsc9959_port_setup_tc,
 	.port_sched_speed_set	= vsc9959_sched_speed_set,
-	.tas_guard_bands_update	= vsc9959_tas_guard_bands_update,
 };
 
 /* The INTB interrupt is shared between for PTP TX timestamp availability
diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c
index f7d7cfb2fd86..09b80644c11b 100644
--- a/drivers/net/dsa/qca/qca8k-8xxx.c
+++ b/drivers/net/dsa/qca/qca8k-8xxx.c
@@ -588,6 +588,9 @@ qca8k_phy_eth_busy_wait(struct qca8k_mgmt_eth_data *mgmt_eth_data,
 	bool ack;
 	int ret;
 
+	if (!skb)
+		return -ENOMEM;
+
 	reinit_completion(&mgmt_eth_data->rw_done);
 
 	/* Increment seq_num and set it in the copy pkt */
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index 451c3a1b6255..633b321d7fdd 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -35,6 +35,8 @@
 
 #define ENA_REGS_ADMIN_INTR_MASK 1
 
+#define ENA_MAX_BACKOFF_DELAY_EXP 16U
+
 #define ENA_MIN_ADMIN_POLL_US 100
 
 #define ENA_MAX_ADMIN_POLL_US 5000
@@ -536,6 +538,7 @@ static int ena_com_comp_status_to_errno(struct ena_com_admin_queue *admin_queue,
 
 static void ena_delay_exponential_backoff_us(u32 exp, u32 delay_us)
 {
+	exp = min_t(u32, exp, ENA_MAX_BACKOFF_DELAY_EXP);
 	delay_us = max_t(u32, ENA_MIN_ADMIN_POLL_US, delay_us);
 	delay_us = min_t(u32, delay_us * (1U << exp), ENA_MAX_ADMIN_POLL_US);
 	usleep_range(delay_us, 2 * delay_us);
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index 1761df8fb7f9..10c7c232cc4e 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -1492,8 +1492,6 @@ int bgmac_enet_probe(struct bgmac *bgmac)
 
 	bgmac->in_init = true;
 
-	bgmac_chip_intrs_off(bgmac);
-
 	net_dev->irq = bgmac->irq;
 	SET_NETDEV_DEV(net_dev, bgmac->dev);
 	dev_set_drvdata(bgmac->dev, bgmac);
@@ -1511,6 +1509,8 @@ int bgmac_enet_probe(struct bgmac *bgmac)
 	 */
 	bgmac_clk_enable(bgmac, 0);
 
+	bgmac_chip_intrs_off(bgmac);
+
 	/* This seems to be fixing IRQ by assigning OOB #6 to the core */
 	if (!(bgmac->feature_flags & BGMAC_FEAT_IDM_MASK)) {
 		if (bgmac->feature_flags & BGMAC_FEAT_IRQ_ID_OOB_6)
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 9939ccafb556..63a053dea819 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -355,7 +355,7 @@ struct bufdesc_ex {
 #define RX_RING_SIZE		(FEC_ENET_RX_FRPPG * FEC_ENET_RX_PAGES)
 #define FEC_ENET_TX_FRSIZE	2048
 #define FEC_ENET_TX_FRPPG	(PAGE_SIZE / FEC_ENET_TX_FRSIZE)
-#define TX_RING_SIZE		512	/* Must be power of two */
+#define TX_RING_SIZE		1024	/* Must be power of two */
 #define TX_RING_MOD_MASK	511	/*   for this to work */
 
 #define BD_ENET_RX_INT		0x00800000
@@ -544,10 +544,23 @@ enum {
 	XDP_STATS_TOTAL,
 };
 
+enum fec_txbuf_type {
+	FEC_TXBUF_T_SKB,
+	FEC_TXBUF_T_XDP_NDO,
+};
+
+struct fec_tx_buffer {
+	union {
+		struct sk_buff *skb;
+		struct xdp_frame *xdp;
+	};
+	enum fec_txbuf_type type;
+};
+
 struct fec_enet_priv_tx_q {
 	struct bufdesc_prop bd;
 	unsigned char *tx_bounce[TX_RING_SIZE];
-	struct  sk_buff *tx_skbuff[TX_RING_SIZE];
+	struct fec_tx_buffer tx_buf[TX_RING_SIZE];
 
 	unsigned short tx_stop_threshold;
 	unsigned short tx_wake_threshold;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 8fbe47703d47..ec9e4bdb0c06 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -397,7 +397,7 @@ static void fec_dump(struct net_device *ndev)
 			fec16_to_cpu(bdp->cbd_sc),
 			fec32_to_cpu(bdp->cbd_bufaddr),
 			fec16_to_cpu(bdp->cbd_datlen),
-			txq->tx_skbuff[index]);
+			txq->tx_buf[index].skb);
 		bdp = fec_enet_get_nextdesc(bdp, &txq->bd);
 		index++;
 	} while (bdp != txq->bd.base);
@@ -654,7 +654,7 @@ static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq,
 
 	index = fec_enet_get_bd_index(last_bdp, &txq->bd);
 	/* Save skb pointer */
-	txq->tx_skbuff[index] = skb;
+	txq->tx_buf[index].skb = skb;
 
 	/* Make sure the updates to rest of the descriptor are performed before
 	 * transferring ownership.
@@ -672,9 +672,7 @@ static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq,
 
 	skb_tx_timestamp(skb);
 
-	/* Make sure the update to bdp and tx_skbuff are performed before
-	 * txq->bd.cur.
-	 */
+	/* Make sure the update to bdp is performed before txq->bd.cur. */
 	wmb();
 	txq->bd.cur = bdp;
 
@@ -862,7 +860,7 @@ static int fec_enet_txq_submit_tso(struct fec_enet_priv_tx_q *txq,
 	}
 
 	/* Save skb pointer */
-	txq->tx_skbuff[index] = skb;
+	txq->tx_buf[index].skb = skb;
 
 	skb_tx_timestamp(skb);
 	txq->bd.cur = bdp;
@@ -952,16 +950,33 @@ static void fec_enet_bd_init(struct net_device *dev)
 		for (i = 0; i < txq->bd.ring_size; i++) {
 			/* Initialize the BD for every fragment in the page. */
 			bdp->cbd_sc = cpu_to_fec16(0);
-			if (bdp->cbd_bufaddr &&
-			    !IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr)))
-				dma_unmap_single(&fep->pdev->dev,
-						 fec32_to_cpu(bdp->cbd_bufaddr),
-						 fec16_to_cpu(bdp->cbd_datlen),
-						 DMA_TO_DEVICE);
-			if (txq->tx_skbuff[i]) {
-				dev_kfree_skb_any(txq->tx_skbuff[i]);
-				txq->tx_skbuff[i] = NULL;
+			if (txq->tx_buf[i].type == FEC_TXBUF_T_SKB) {
+				if (bdp->cbd_bufaddr &&
+				    !IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr)))
+					dma_unmap_single(&fep->pdev->dev,
+							 fec32_to_cpu(bdp->cbd_bufaddr),
+							 fec16_to_cpu(bdp->cbd_datlen),
+							 DMA_TO_DEVICE);
+				if (txq->tx_buf[i].skb) {
+					dev_kfree_skb_any(txq->tx_buf[i].skb);
+					txq->tx_buf[i].skb = NULL;
+				}
+			} else {
+				if (bdp->cbd_bufaddr)
+					dma_unmap_single(&fep->pdev->dev,
+							 fec32_to_cpu(bdp->cbd_bufaddr),
+							 fec16_to_cpu(bdp->cbd_datlen),
+							 DMA_TO_DEVICE);
+
+				if (txq->tx_buf[i].xdp) {
+					xdp_return_frame(txq->tx_buf[i].xdp);
+					txq->tx_buf[i].xdp = NULL;
+				}
+
+				/* restore default tx buffer type: FEC_TXBUF_T_SKB */
+				txq->tx_buf[i].type = FEC_TXBUF_T_SKB;
 			}
+
 			bdp->cbd_bufaddr = cpu_to_fec32(0);
 			bdp = fec_enet_get_nextdesc(bdp, &txq->bd);
 		}
@@ -1360,6 +1375,7 @@ static void
 fec_enet_tx_queue(struct net_device *ndev, u16 queue_id)
 {
 	struct	fec_enet_private *fep;
+	struct xdp_frame *xdpf;
 	struct bufdesc *bdp;
 	unsigned short status;
 	struct	sk_buff	*skb;
@@ -1387,16 +1403,31 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id)
 
 		index = fec_enet_get_bd_index(bdp, &txq->bd);
 
-		skb = txq->tx_skbuff[index];
-		txq->tx_skbuff[index] = NULL;
-		if (!IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr)))
-			dma_unmap_single(&fep->pdev->dev,
-					 fec32_to_cpu(bdp->cbd_bufaddr),
-					 fec16_to_cpu(bdp->cbd_datlen),
-					 DMA_TO_DEVICE);
-		bdp->cbd_bufaddr = cpu_to_fec32(0);
-		if (!skb)
-			goto skb_done;
+		if (txq->tx_buf[index].type == FEC_TXBUF_T_SKB) {
+			skb = txq->tx_buf[index].skb;
+			txq->tx_buf[index].skb = NULL;
+			if (bdp->cbd_bufaddr &&
+			    !IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr)))
+				dma_unmap_single(&fep->pdev->dev,
+						 fec32_to_cpu(bdp->cbd_bufaddr),
+						 fec16_to_cpu(bdp->cbd_datlen),
+						 DMA_TO_DEVICE);
+			bdp->cbd_bufaddr = cpu_to_fec32(0);
+			if (!skb)
+				goto tx_buf_done;
+		} else {
+			xdpf = txq->tx_buf[index].xdp;
+			if (bdp->cbd_bufaddr)
+				dma_unmap_single(&fep->pdev->dev,
+						 fec32_to_cpu(bdp->cbd_bufaddr),
+						 fec16_to_cpu(bdp->cbd_datlen),
+						 DMA_TO_DEVICE);
+			bdp->cbd_bufaddr = cpu_to_fec32(0);
+			if (!xdpf) {
+				txq->tx_buf[index].type = FEC_TXBUF_T_SKB;
+				goto tx_buf_done;
+			}
+		}
 
 		/* Check for errors. */
 		if (status & (BD_ENET_TX_HB | BD_ENET_TX_LC |
@@ -1415,21 +1446,11 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id)
 				ndev->stats.tx_carrier_errors++;
 		} else {
 			ndev->stats.tx_packets++;
-			ndev->stats.tx_bytes += skb->len;
-		}
-
-		/* NOTE: SKBTX_IN_PROGRESS being set does not imply it's we who
-		 * are to time stamp the packet, so we still need to check time
-		 * stamping enabled flag.
-		 */
-		if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS &&
-			     fep->hwts_tx_en) &&
-		    fep->bufdesc_ex) {
-			struct skb_shared_hwtstamps shhwtstamps;
-			struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp;
 
-			fec_enet_hwtstamp(fep, fec32_to_cpu(ebdp->ts), &shhwtstamps);
-			skb_tstamp_tx(skb, &shhwtstamps);
+			if (txq->tx_buf[index].type == FEC_TXBUF_T_SKB)
+				ndev->stats.tx_bytes += skb->len;
+			else
+				ndev->stats.tx_bytes += xdpf->len;
 		}
 
 		/* Deferred means some collisions occurred during transmit,
@@ -1438,10 +1459,32 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id)
 		if (status & BD_ENET_TX_DEF)
 			ndev->stats.collisions++;
 
-		/* Free the sk buffer associated with this last transmit */
-		dev_kfree_skb_any(skb);
-skb_done:
-		/* Make sure the update to bdp and tx_skbuff are performed
+		if (txq->tx_buf[index].type == FEC_TXBUF_T_SKB) {
+			/* NOTE: SKBTX_IN_PROGRESS being set does not imply it's we who
+			 * are to time stamp the packet, so we still need to check time
+			 * stamping enabled flag.
+			 */
+			if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS &&
+				     fep->hwts_tx_en) && fep->bufdesc_ex) {
+				struct skb_shared_hwtstamps shhwtstamps;
+				struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp;
+
+				fec_enet_hwtstamp(fep, fec32_to_cpu(ebdp->ts), &shhwtstamps);
+				skb_tstamp_tx(skb, &shhwtstamps);
+			}
+
+			/* Free the sk buffer associated with this last transmit */
+			dev_kfree_skb_any(skb);
+		} else {
+			xdp_return_frame(xdpf);
+
+			txq->tx_buf[index].xdp = NULL;
+			/* restore default tx buffer type: FEC_TXBUF_T_SKB */
+			txq->tx_buf[index].type = FEC_TXBUF_T_SKB;
+		}
+
+tx_buf_done:
+		/* Make sure the update to bdp and tx_buf are performed