Merge branch 'stmmac-next'

Jose Abreu says:

====================
net: stmmac: Improvements for -next

Misc improvements for stmmac.

Patch 1/6, fixes a sparse warning that was introduced in recent commit in
-next.

Patch 2/6, adds the Split Header support which is also available in XGMAC
cores and now in GMAC4+ with this patch.

Patch 3/6, adds the C45 support for MDIO transactions when using XGMAC cores.

Patch 4/6, removes the speed dependency on CBS callbacks so that it can be used
in XGMAC cores.

Patch 5/6, reworks the over-engineered stmmac_rx() function so that its easier
to read.

Patch 6/6, implements the UDP Segmentation Offload feature in GMAC4+ cores.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

11 files changed, 217 insertions, 81 deletions

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
index 07e97f45755d..2dc70d104161 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
@@ -14,6 +14,7 @@
 
 /*  MAC registers */
 #define GMAC_CONFIG			0x00000000
+#define GMAC_EXT_CONFIG			0x00000004
 #define GMAC_PACKET_FILTER		0x00000008
 #define GMAC_HASH_TAB(x)		(0x10 + (x) * 4)
 #define GMAC_VLAN_TAG			0x00000050
@@ -188,6 +189,11 @@ enum power_event {
 #define GMAC_CONFIG_TE			BIT(1)
 #define GMAC_CONFIG_RE			BIT(0)
 
+/* MAC extended config */
+#define GMAC_CONFIG_HDSMS		GENMASK(22, 20)
+#define GMAC_CONFIG_HDSMS_SHIFT		20
+#define GMAC_CONFIG_HDSMS_256		(0x2 << GMAC_CONFIG_HDSMS_SHIFT)
+
 /* MAC HW features0 bitmap */
 #define GMAC_HW_FEAT_SAVLANINS		BIT(27)
 #define GMAC_HW_FEAT_ADDMAC		BIT(18)
@@ -211,6 +217,7 @@ enum power_event {
 #define GMAC_HW_HASH_TB_SZ		GENMASK(25, 24)
 #define GMAC_HW_FEAT_AVSEL		BIT(20)
 #define GMAC_HW_TSOEN			BIT(18)
+#define GMAC_HW_FEAT_SPHEN		BIT(17)
 #define GMAC_HW_ADDR64			GENMASK(15, 14)
 #define GMAC_HW_TXFIFOSIZE		GENMASK(10, 6)
 #define GMAC_HW_RXFIFOSIZE		GENMASK(4, 0)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index a2ecab5dc8c8..40ca00e596dd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -733,7 +733,7 @@ static void dwmac4_set_mac_loopback(void __iomem *ioaddr, bool enable)
 }
 
 static void dwmac4_update_vlan_hash(struct mac_device_info *hw, u32 hash,
-				    u16 perfect_match, bool is_double)
+				    __le16 perfect_match, bool is_double)
 {
 	void __iomem *ioaddr = hw->pcsr;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
index 707ab5eba8da..3e14da69f378 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -83,9 +83,10 @@ static int dwmac4_wrback_get_rx_status(void *data, struct stmmac_extra_stats *x,
 	if (unlikely(rdes3 & RDES3_OWN))
 		return dma_own;
 
-	/* Verify rx error by looking at the last segment. */
-	if (likely(!(rdes3 & RDES3_LAST_DESCRIPTOR)))
+	if (unlikely(rdes3 & RDES3_CONTEXT_DESCRIPTOR))
 		return discard_frame;
+	if (likely(!(rdes3 & RDES3_LAST_DESCRIPTOR)))
+		return rx_not_ls;
 
 	if (unlikely(rdes3 & RDES3_ERROR_SUMMARY)) {
 		if (unlikely(rdes3 & RDES3_GIANT_PACKET))
@@ -188,7 +189,7 @@ static void dwmac4_set_tx_owner(struct dma_desc *p)
 
 static void dwmac4_set_rx_owner(struct dma_desc *p, int disable_rx_ic)
 {
-	p->des3 = cpu_to_le32(RDES3_OWN | RDES3_BUFFER1_VALID_ADDR);
+	p->des3 |= cpu_to_le32(RDES3_OWN | RDES3_BUFFER1_VALID_ADDR);
 
 	if (!disable_rx_ic)
 		p->des3 |= cpu_to_le32(RDES3_INT_ON_COMPLETION_EN);
@@ -492,6 +493,18 @@ static void dwmac4_set_vlan(struct dma_desc *p, u32 type)
 	p->des2 |= cpu_to_le32(type & TDES2_VLAN_TAG_MASK);
 }
 
+static int dwmac4_get_rx_header_len(struct dma_desc *p, unsigned int *len)
+{
+	*len = le32_to_cpu(p->des2) & RDES2_HL;
+	return 0;
+}
+
+static void dwmac4_set_sec_addr(struct dma_desc *p, dma_addr_t addr)
+{
+	p->des2 = cpu_to_le32(lower_32_bits(addr));
+	p->des3 = cpu_to_le32(upper_32_bits(addr) | RDES3_BUFFER2_VALID_ADDR);
+}
+
 const struct stmmac_desc_ops dwmac4_desc_ops = {
 	.tx_status = dwmac4_wrback_get_tx_status,
 	.rx_status = dwmac4_wrback_get_rx_status,
@@ -519,6 +532,8 @@ const struct stmmac_desc_ops dwmac4_desc_ops = {
 	.set_sarc = dwmac4_set_sarc,
 	.set_vlan_tag = dwmac4_set_vlan_tag,
 	.set_vlan = dwmac4_set_vlan,
+	.get_rx_header_len = dwmac4_get_rx_header_len,
+	.set_sec_addr = dwmac4_set_sec_addr,
 };
 
 const struct stmmac_mode_ops dwmac4_ring_mode_ops = {
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h
index 0d7b3bbcd5a7..6d92109dc9aa 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h
@@ -109,6 +109,7 @@
 #define RDES2_L4_FILTER_MATCH		BIT(28)
 #define RDES2_L3_L4_FILT_NB_MATCH_MASK	GENMASK(27, 26)
 #define RDES2_L3_L4_FILT_NB_MATCH_SHIFT	26
+#define RDES2_HL			GENMASK(9, 0)
 
 /* RDES3 (write back format) */
 #define RDES3_PACKET_SIZE_MASK		GENMASK(14, 0)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
index b24c89572745..36a0af8bf89f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
@@ -368,6 +368,7 @@ static void dwmac4_get_hw_feature(void __iomem *ioaddr,
 	dma_cap->hash_tb_sz = (hw_cap & GMAC_HW_HASH_TB_SZ) >> 24;
 	dma_cap->av = (hw_cap & GMAC_HW_FEAT_AVSEL) >> 20;
 	dma_cap->tsoen = (hw_cap & GMAC_HW_TSOEN) >> 18;
+	dma_cap->sphen = (hw_cap & GMAC_HW_FEAT_SPHEN) >> 17;
 
 	dma_cap->addr64 = (hw_cap & GMAC_HW_ADDR64) >> 14;
 	switch (dma_cap->addr64) {
@@ -460,6 +461,22 @@ static void dwmac4_set_bfsize(void __iomem *ioaddr, int bfsize, u32 chan)
 	writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan));
 }
 
+static void dwmac4_enable_sph(void __iomem *ioaddr, bool en, u32 chan)
+{
+	u32 value = readl(ioaddr + GMAC_EXT_CONFIG);
+
+	value &= ~GMAC_CONFIG_HDSMS;
+	value |= GMAC_CONFIG_HDSMS_256; /* Segment max 256 bytes */
+	writel(value, ioaddr + GMAC_EXT_CONFIG);
+
+	value = readl(ioaddr + DMA_CHAN_CONTROL(chan));
+	if (en)
+		value |= DMA_CONTROL_SPH;
+	else
+		value &= ~DMA_CONTROL_SPH;
+	writel(value, ioaddr + DMA_CHAN_CONTROL(chan));
+}
+
 const struct stmmac_dma_ops dwmac4_dma_ops = {
 	.reset = dwmac4_dma_reset,
 	.init = dwmac4_dma_init,
@@ -486,6 +503,7 @@ const struct stmmac_dma_ops dwmac4_dma_ops = {
 	.enable_tso = dwmac4_enable_tso,
 	.qmode = dwmac4_qmode,
 	.set_bfsize = dwmac4_set_bfsize,
+	.enable_sph = dwmac4_enable_sph,
 };
 
 const struct stmmac_dma_ops dwmac410_dma_ops = {
@@ -514,4 +532,5 @@ const struct stmmac_dma_ops dwmac410_dma_ops = {
 	.enable_tso = dwmac4_enable_tso,
 	.qmode = dwmac4_qmode,
 	.set_bfsize = dwmac4_set_bfsize,
+	.enable_sph = dwmac4_enable_sph,
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
index 5299fa1001a3..589931795847 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
@@ -110,6 +110,7 @@
 #define DMA_CHAN_STATUS(x)		(DMA_CHANX_BASE_ADDR(x) + 0x60)
 
 /* DMA Control X */
+#define DMA_CONTROL_SPH			BIT(24)
 #define DMA_CONTROL_MSS_MASK		GENMASK(13, 0)
 
 /* DMA Tx Channel X Control register defines */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index 9553d2bec1a7..082f5ee9e525 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -556,7 +556,7 @@ static int dwxgmac2_rss_configure(struct mac_device_info *hw,
 }
 
 static void dwxgmac2_update_vlan_hash(struct mac_device_info *hw, u32 hash,
-				      u16 perfect_match, bool is_double)
+				      __le16 perfect_match, bool is_double)
 {
 	void __iomem *ioaddr = hw->pcsr;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 1303d1e9a18f..509daeefdb79 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -357,7 +357,7 @@ struct stmmac_ops {
 			     struct stmmac_rss *cfg, u32 num_rxq);
 	/* VLAN */
 	void (*update_vlan_hash)(struct mac_device_info *hw, u32 hash,
-				 u16 perfect_match, bool is_double);
+				 __le16 perfect_match, bool is_double);
 	void (*enable_vlan)(struct mac_device_info *hw, u32 type);
 	/* TX Timestamp */
 	int (*get_mac_tx_timestamp)(struct mac_device_info *hw, u64 *ts);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 199c4f938bb2..39b4efd521f9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -36,6 +36,7 @@
 #endif /* CONFIG_DEBUG_FS */
 #include <linux/net_tstamp.h>
 #include <linux/phylink.h>
+#include <linux/udp.h>
 #include <net/pkt_cls.h>
 #include "stmmac_ptp.h"
 #include "stmmac.h"
@@ -2916,9 +2917,9 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 	u32 queue = skb_get_queue_mapping(skb);
 	struct stmmac_tx_queue *tx_q;
 	unsigned int first_entry;
+	u8 proto_hdr_len, hdr;
 	int tmp_pay_len = 0;
 	u32 pay_len, mss;
-	u8 proto_hdr_len;
 	dma_addr_t des;
 	bool has_vlan;
 	int i;
@@ -2926,7 +2927,13 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 	tx_q = &priv->tx_queue[queue];
 
 	/* Compute header lengths */
-	proto_hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+	if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) {
+		proto_hdr_len = skb_transport_offset(skb) + sizeof(struct udphdr);
+		hdr = sizeof(struct udphdr);
+	} else {
+		proto_hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+		hdr = tcp_hdrlen(skb);
+	}
 
 	/* Desc availability based on threshold should be enough safe */
 	if (unlikely(stmmac_tx_avail(priv, queue) <
@@ -2956,8 +2963,8 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	if (netif_msg_tx_queued(priv)) {
-		pr_info("%s: tcphdrlen %d, hdr_len %d, pay_len %d, mss %d\n",
-			__func__, tcp_hdrlen(skb), proto_hdr_len, pay_len, mss);
+		pr_info("%s: hdrlen %d, hdr_len %d, pay_len %d, mss %d\n",
+			__func__, hdr, proto_hdr_len, pay_len, mss);
 		pr_info("\tskb->len %d, skb->data_len %d\n", skb->len,
 			skb->data_len);
 	}
@@ -3071,7 +3078,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 			proto_hdr_len,
 			pay_len,
 			1, tx_q->tx_skbuff_dma[first_entry].last_segment,
-			tcp_hdrlen(skb) / 4, (skb->len - proto_hdr_len));
+			hdr / 4, (skb->len - proto_hdr_len));
 
 	/* If context desc is used to change MSS */
 	if (mss_desc) {
@@ -3130,6 +3137,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	int i, csum_insertion = 0, is_jumbo = 0;
 	u32 queue = skb_get_queue_mapping(skb);
 	int nfrags = skb_shinfo(skb)->nr_frags;
+	int gso = skb_shinfo(skb)->gso_type;
 	struct dma_desc *desc, *first;
 	struct stmmac_tx_queue *tx_q;
 	unsigned int first_entry;
@@ -3145,7 +3153,9 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	/* Manage oversized TCP frames for GMAC4 device */
 	if (skb_is_gso(skb) && priv->tso) {
-		if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))
+		if (gso & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))
+			return stmmac_tso_xmit(skb, dev);
+		if (priv->plat->has_gmac4 && (gso & SKB_GSO_UDP_L4))
 			return stmmac_tso_xmit(skb, dev);
 	}
 
@@ -3443,6 +3453,55 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue)
 	stmmac_set_rx_tail_ptr(priv, priv->ioaddr, rx_q->rx_tail_addr, queue);
 }
 
+static unsigned int stmmac_rx_buf1_len(struct stmmac_priv *priv,
+				       struct dma_desc *p,
+				       int status, unsigned int len)
+{
+	int ret, coe = priv->hw->rx_csum;
+	unsigned int plen = 0, hlen = 0;
+
+	/* Not first descriptor, buffer is always zero */
+	if (priv->sph && len)
+		return 0;
+
+	/* First descriptor, get split header length */
+	ret = stmmac_get_rx_header_len(priv, p, &hlen);
+	if (priv->sph && hlen) {
+		priv->xstats.rx_split_hdr_pkt_n++;
+		return hlen;
+	}
+
+	/* First descriptor, not last descriptor and not split header */
+	if (status & rx_not_ls)
+		return priv->dma_buf_sz;
+
+	plen = stmmac_get_rx_frame_len(priv, p, coe);
+
+	/* First descriptor and last descriptor and not split header */
+	return min_t(unsigned int, priv->dma_buf_sz, plen);
+}
+
+static unsigned int stmmac_rx_buf2_len(struct stmmac_priv *priv,
+				       struct dma_desc *p,
+				       int status, unsigned int len)
+{
+	int coe = priv->hw->rx_csum;
+	unsigned int plen = 0;
+
+	/* Not split header, buffer is not available */
+	if (!priv->sph)
+		return 0;
+
+	/* Not last descriptor */
+	if (status & rx_not_ls)
+		return priv->dma_buf_sz;
+
+	plen = stmmac_get_rx_frame_len(priv, p, coe);
+
+	/* Last descriptor */
+	return plen - len;
+}
+
 /**
  * stmmac_rx - manage the receive process
  * @priv: driver private structure
@@ -3472,11 +3531,10 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 		stmmac_display_ring(priv, rx_head, DMA_RX_SIZE, true);
 	}
 	while (count < limit) {
-		unsigned int hlen = 0, prev_len = 0;
+		unsigned int buf1_len = 0, buf2_len = 0;
 		enum pkt_hash_types hash_type;
 		struct stmmac_rx_buffer *buf;
 		struct dma_desc *np, *p;
-		unsigned int sec_len;
 		int entry;
 		u32 hash;
 
@@ -3495,7 +3553,8 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 			break;
 
 read_again:
-		sec_len = 0;
+		buf1_len = 0;
+		buf2_len = 0;
 		entry = next_entry;
 		buf = &rx_q->buf_pool[entry];
 
@@ -3520,7 +3579,6 @@ read_again:
 			np = rx_q->dma_rx + next_entry;
 
 		prefetch(np);
-		prefetch(page_address(buf->page));
 
 		if (priv->extend_desc)
 			stmmac_rx_extended_status(priv, &priv->dev->stats,
@@ -3537,69 +3595,61 @@ read_again:
 			goto read_again;
 		if (unlikely(error)) {
 			dev_kfree_skb(skb);
+			skb = NULL;
 			count++;
 			continue;
 		}
 
 		/* Buffer is good. Go on. */
 
-		if (likely(status & rx_not_ls)) {
-			len += priv->dma_buf_sz;
-		} else {
-			prev_len = len;
-			len = stmmac_get_rx_frame_len(priv, p, coe);
-
-			/* ACS is set; GMAC core strips PAD/FCS for IEEE 802.3
-			 * Type frames (LLC/LLC-SNAP)
-			 *
-			 * llc_snap is never checked in GMAC >= 4, so this ACS
-			 * feature is always disabled and packets need to be
-			 * stripped manually.
-			 */
-			if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00) ||
-			    unlikely(status != llc_snap))
-				len -= ETH_FCS_LEN;
+		prefetch(page_address(buf->page));
+		if (buf->sec_page)
+			prefetch(page_address(buf->sec_page));
+
+		buf1_len = stmmac_rx_buf1_len(priv, p, status, len);
+		len += buf1_len;
+		buf2_len = stmmac_rx_buf2_len(priv, p, status, len);
+		len += buf2_len;
+
+		/* ACS is set; GMAC core strips PAD/FCS for IEEE 802.3
+		 * Type frames (LLC/LLC-SNAP)
+		 *
+		 * llc_snap is never checked in GMAC >= 4, so this ACS
+		 * feature is always disabled and packets need to be
+		 * stripped manually.
+		 */
+		if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00) ||
+		    unlikely(status != llc_snap)) {
+			if (buf2_len)
+				buf2_len -= ETH_FCS_LEN;
+			else
+				buf1_len -= ETH_FCS_LEN;
+
+			len -= ETH_FCS_LEN;
 		}
 
 		if (!skb) {
-			int ret = stmmac_get_rx_header_len(priv, p, &hlen);
-
-			if (priv->sph && !ret && (hlen > 0)) {
-				sec_len = len;
-				if (!(status & rx_not_ls))
-					sec_len = sec_len - hlen;
-				len = hlen;
-
-				prefetch(page_address(buf->sec_page));
-				priv->xstats.rx_split_hdr_pkt_n++;
-			}
-
-			skb = napi_alloc_skb(&ch->rx_napi, len);
+			skb = napi_alloc_skb(&ch->rx_napi, buf1_len);
 			if (!skb) {
 				priv->dev->stats.rx_dropped++;
 				count++;
-				continue;
+				goto drain_data;
 			}
 
-			dma_sync_single_for_cpu(priv->device, buf->addr, len,
-						DMA_FROM_DEVICE);
+			dma_sync_single_for_cpu(priv->device, buf->addr,
+						buf1_len, DMA_FROM_DEVICE);
 			skb_copy_to_linear_data(skb, page_address(buf->page),
-						len);
-			skb_put(skb, len);
+						buf1_len);
+			skb_put(skb, buf1_len);
 
 			/* Data payload copied into SKB, page ready for recycle */
 			page_pool_recycle_direct(rx_q->page_pool, buf->page);
 			buf->page = NULL;
-		} else {
-			unsigned int buf_len = len - prev_len;
-
-			if (likely(status & rx_not_ls))
-				buf_len = priv->dma_buf_sz;
-
+		} else if (buf1_len) {
 			dma_sync_single_for_cpu(priv->device, buf->addr,
-						buf_len, DMA_FROM_DEVICE);
+						buf1_len, DMA_FROM_DEVICE);
 			skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
-					buf->page, 0, buf_len,
+					buf->page, 0, buf1_len,
 					priv->dma_buf_sz);
 
 			/* Data payload appended into SKB */
@@ -3607,22 +3657,23 @@ read_again:
 			buf->page = NULL;
 		}
 
-		if (sec_len > 0) {
+		if (buf2_len) {
 			dma_sync_single_for_cpu(priv->device, buf->sec_addr,
-						sec_len, DMA_FROM_DEVICE);
+						buf2_len, DMA_FROM_DEVICE);
 			skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
-					buf->sec_page, 0, sec_len,
+					buf->sec_page, 0, buf2_len,
 					priv->dma_buf_sz);
 
-			len += sec_len;
-
 			/* Data payload appended into SKB */
 			page_pool_release_page(rx_q->page_pool, buf->sec_page);
 			buf->sec_page = NULL;
 		}
 
+drain_data:
 		if (likely(status & rx_not_ls))
 			goto read_again;
+		if (!skb)
+			continue;
 
 		/* Got entire packet into SKB. Finish it. */
 
@@ -3640,13 +3691,14 @@ read_again:
 
 		skb_record_rx_queue(skb, queue);
 		napi_gro_receive(&ch->rx_napi, skb);
+		skb = NULL;
 
 		priv->dev->stats.rx_packets++;
 		priv->dev->stats.rx_bytes += len;
 		count++;
 	}
 
-	if (status & rx_not_ls) {
+	if (status & rx_not_ls || skb) {
 		rx_q->state_saved = true;
 		rx_q->state.skb = skb;
 		rx_q->state.error = error;
@@ -3994,11 +4046,13 @@ static int stmmac_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 static u16 stmmac_select_queue(struct net_device *dev, struct sk_buff *skb,
 			       struct net_device *sb_dev)
 {
-	if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) {
+	int gso = skb_shinfo(skb)->gso_type;
+
+	if (gso & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6 | SKB_GSO_UDP_L4)) {
 		/*
-		 * There is no way to determine the number of TSO
+		 * There is no way to determine the number of TSO/USO
 		 * capable Queues. Let's use always the Queue 0
-		 * because if TSO is supported then at least this
+		 * because if TSO/USO is supported then at least this
 		 * one will be capable.
 		 */
 		return 0;
@@ -4214,6 +4268,7 @@ static u32 stmmac_vid_crc32_le(__le16 vid_le)
 static int stmmac_vlan_update(struct stmmac_priv *priv, bool is_double)
 {
 	u32 crc, hash = 0;
+	__le16 pmatch = 0;
 	int count = 0;
 	u16 vid = 0;
 
@@ -4228,11 +4283,11 @@ static int stmmac_vlan_update(struct stmmac_priv *priv, bool is_double)
 		if (count > 2) /* VID = 0 always passes filter */
 			return -EOPNOTSUPP;
 
-		vid = cpu_to_le16(vid);
+		pmatch = cpu_to_le16(vid);
 		hash = 0;
 	}
 
-	return stmmac_update_vlan_hash(priv, priv->hw, hash, vid, is_double);
+	return stmmac_update_vlan_hash(priv, priv->hw, hash, pmatch, is_double);
 }
 
 static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid)
@@ -4512,6 +4567,8 @@ int stmmac_dvr_probe(struct device *device,
 
 	if ((priv->plat->tso_en) && (priv->dma_cap.tsoen)) {
 		ndev->hw_features |= NETIF_F_TSO | NETIF_F_TSO6;
+		if (priv->plat->has_gmac4)
+			ndev->hw_features |= NETIF_F_GSO_UDP_L4;
 		priv->tso = true;
 		dev_info(priv->device, "TSO feature enabled\n");
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index 40c42637ad75..cfe5d8b73142 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -41,20 +41,32 @@
 #define MII_XGMAC_BUSY			BIT(22)
 #define MII_XGMAC_MAX_C22ADDR		3
 #define MII_XGMAC_C22P_MASK		GENMASK(MII_XGMAC_MAX_C22ADDR, 0)
+#define MII_XGMAC_PA_SHIFT		16
+#define MII_XGMAC_DA_SHIFT		21
+
+static int stmmac_xgmac2_c45_format(struct stmmac_priv *priv, int phyaddr,
+				    int phyreg, u32 *hw_addr)
+{
+	u32 tmp;
+
+	/* Set port as Clause 45 */
+	tmp = readl(priv->ioaddr + XGMAC_MDIO_C22P);
+	tmp &= ~BIT(phyaddr);
+	writel(tmp, priv->ioaddr + XGMAC_MDIO_C22P);
+
+	*hw_addr = (phyaddr << MII_XGMAC_PA_SHIFT) | (phyreg & 0xffff);
+	*hw_addr |= (phyreg >> MII_DEVADDR_C45_SHIFT) << MII_XGMAC_DA_SHIFT;
+	return 0;
+}
 
 static int stmmac_xgmac2_c22_format(struct stmmac_priv *priv, int phyaddr,
 				    int phyreg, u32 *hw_addr)
 {
-	unsigned int mii_data = priv->hw->mii.data;
 	u32 tmp;
 
 	/* HW does not support C22 addr >= 4 */
 	if (phyaddr > MII_XGMAC_MAX_C22ADDR)
 		return -ENODEV;
-	/* Wait until any existing MII operation is complete */
-	if (readl_poll_timeout(priv->ioaddr + mii_data, tmp,
-			       !(tmp & MII_XGMAC_BUSY), 100, 10000))
-		return -EBUSY;
 
 	/* Set port as Clause 22 */
 	tmp = readl(priv->ioaddr + XGMAC_MDIO_C22P);
@@ -62,7 +74,7 @@ static int stmmac_xgmac2_c22_format(struct stmmac_priv *priv, int phyaddr,
 	tmp |= BIT(phyaddr);
 	writel(tmp, priv->ioaddr + XGMAC_MDIO_C22P);
 
-	*hw_addr = (phyaddr << 16) | (phyreg & 0x1f);
+	*hw_addr = (phyaddr << MII_XGMAC_PA_SHIFT) | (phyreg & 0x1f);
 	return 0;
 }
 
@@ -75,17 +87,28 @@ static int stmmac_xgmac2_mdio_read(struct mii_bus *bus, int phyaddr, int phyreg)
 	u32 tmp, addr, value = MII_XGMAC_BUSY;
 	int ret;
 
+	/* Wait until any existing MII operation is complete */
+	if (readl_poll_timeout(priv->ioaddr + mii_data, tmp,
+			       !(tmp & MII_XGMAC_BUSY), 100, 10000))
+		return -EBUSY;
+
 	if (phyreg & MII_ADDR_C45) {
-		return -EOPNOTSUPP;
+		phyreg &= ~MII_ADDR_C45;
+
+		ret = stmmac_xgmac2_c45_format(priv, phyaddr, phyreg, &addr);
+		if (ret)
+			return ret;
 	} else {
 		ret = stmmac_xgmac2_c22_format(priv, phyaddr, phyreg, &addr);
 		if (ret)
 			return ret;
+
+		value |= MII_XGMAC_SADDR;
 	}
 
 	value |= (priv->clk_csr << priv->hw->mii.clk_csr_shift)
 		& priv->hw->mii.clk_csr_mask;
-	value |= MII_XGMAC_SADDR | MII_XGMAC_READ;
+	value |= MII_XGMAC_READ;
 
 	/* Wait until any existing MII operation is complete */
 	if (readl_poll_timeout(priv->ioaddr + mii_data, tmp,
@@ -115,17 +138,28 @@ static int stmmac_xgmac2_mdio_write(struct mii_bus *bus, int phyaddr,
 	u32 addr, tmp, value = MII_XGMAC_BUSY;
 	int ret;
 
+	/* Wait until any existing MII operation is complete */
+	if (readl_poll_timeout(priv->ioaddr + mii_data, tmp,
+			       !(tmp & MII_XGMAC_BUSY), 100, 10000))
+		return -EBUSY;
+
 	if (phyreg & MII_ADDR_C45) {
-		return -EOPNOTSUPP;
+		phyreg &= ~MII_ADDR_C45;
+
+		ret = stmmac_xgmac2_c45_format(priv, phyaddr, phyreg, &addr);
+		if (ret)
+			return ret;
 	} else {
 		ret = stmmac_xgmac2_c22_format(priv, phyaddr, phyreg, &addr);
 		if (ret)
 			return ret;
+
+		value |= MII_XGMAC_SADDR;
 	}
 
 	value |= (priv->clk_csr << priv->hw->mii.clk_csr_shift)
 		& priv->hw->mii.clk_csr_mask;
-	value |= phydata | MII_XGMAC_SADDR;
+	value |= phydata;
 	value |= MII_XGMAC_WRITE;
 
 	/* Wait until any existing MII operation is complete */
@@ -363,6 +397,10 @@ int stmmac_mdio_register(struct net_device *ndev)
 		goto bus_register_fail;
 	}
 
+	/* Looks like we need a dummy read for XGMAC only and C45 PHYs */
+	if (priv->plat->has_xgmac)
+		stmmac_xgmac2_mdio_read(new_bus, 0, MII_ADDR_C45);
+
 	if (priv->plat->phy_node || mdio_node)
 		goto bus_register_done;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index f9a9a9d82233..7d972e0fd2b0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -321,8 +321,6 @@ static int tc_setup_cbs(struct stmmac_priv *priv,
 		return -EINVAL;
 	if (!priv->dma_cap.av)
 		return -EOPNOTSUPP;
-	if (priv->speed != SPEED_100 && priv->speed != SPEED_1000)
-		return -EOPNOTSUPP;
 
 	mode_to_use = priv->plat->tx_queues_cfg[queue].mode_to_use;
 	if (mode_to_use == MTL_QUEUE_DCB && qopt->enable) {