Merge tag 'mlx5e-updates-2018-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5e-updates-2018-06-28

mlx5e netdevice driver updates:

- Boris Pismenny added the support for UDP GSO in the first two patches.
  Impressive performance numbers are included in the commit message,
  @Line rate with ~half of the cpu utilization compared to non offload
  or no GSO at all.

- From Tariq Toukan:
  - Convert large order kzalloc allocations to kvzalloc.
  - Added performance diagnostic statistics to several places in data path.

From Saeed and Eran,
  - Update NIC HW stats on demand only, this is to eliminate the background
    thread needed to update some HW statistics in the driver cache in
    order to report error and drop counters from HW in ndo_get_stats.
====================

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

13 files changed, 252 insertions, 48 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 9efbf193ad5a..d923f2f58608 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -14,8 +14,8 @@ mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
 		fpga/ipsec.o fpga/tls.o
 
 mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
-		en_tx.o en_rx.o en_dim.o en_txrx.o en_stats.o vxlan.o \
-		en_arfs.o en_fs_ethtool.o en_selftest.o en/port.o
+		en_tx.o en_rx.o en_dim.o en_txrx.o en_accel/rxtx.o en_stats.o  \
+		vxlan.o en_arfs.o en_fs_ethtool.o en_selftest.o en/port.o
 
 mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index eb9eb7aa953a..e2b7586ed7a0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -137,7 +137,6 @@ struct page_pool;
 #define MLX5E_MAX_NUM_CHANNELS         (MLX5E_INDIR_RQT_SIZE >> 1)
 #define MLX5E_MAX_NUM_SQS              (MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC)
 #define MLX5E_TX_CQ_POLL_BUDGET        128
-#define MLX5E_UPDATE_STATS_INTERVAL    200 /* msecs */
 #define MLX5E_SQ_RECOVER_MIN_INTERVAL  500 /* msecs */
 
 #define MLX5E_UMR_WQE_INLINE_SZ \
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
index f20074dbef32..39a5d13ba459 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
@@ -34,12 +34,11 @@
 #ifndef __MLX5E_EN_ACCEL_H__
 #define __MLX5E_EN_ACCEL_H__
 
-#ifdef CONFIG_MLX5_ACCEL
-
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 #include "en_accel/ipsec_rxtx.h"
 #include "en_accel/tls_rxtx.h"
+#include "en_accel/rxtx.h"
 #include "en.h"
 
 static inline struct sk_buff *mlx5e_accel_handle_tx(struct sk_buff *skb,
@@ -64,9 +63,13 @@ static inline struct sk_buff *mlx5e_accel_handle_tx(struct sk_buff *skb,
 	}
 #endif
 
+	if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) {
+		skb = mlx5e_udp_gso_handle_tx_skb(dev, sq, skb, wqe, pi);
+		if (unlikely(!skb))
+			return NULL;
+	}
+
 	return skb;
 }
 
-#endif /* CONFIG_MLX5_ACCEL */
-
 #endif /* __MLX5E_EN_ACCEL_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.c
new file mode 100644
index 000000000000..7b7ec3998e84
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.c
@@ -0,0 +1,109 @@
+#include "en_accel/rxtx.h"
+
+static void mlx5e_udp_gso_prepare_last_skb(struct sk_buff *skb,
+					   struct sk_buff *nskb,
+					   int remaining)
+{
+	int bytes_needed = remaining, remaining_headlen, remaining_page_offset;
+	int headlen = skb_transport_offset(skb) + sizeof(struct udphdr);
+	int payload_len = remaining + sizeof(struct udphdr);
+	int k = 0, i, j;
+
+	skb_copy_bits(skb, 0, nskb->data, headlen);
+	nskb->dev = skb->dev;
+	skb_reset_mac_header(nskb);
+	skb_set_network_header(nskb, skb_network_offset(skb));
+	skb_set_transport_header(nskb, skb_transport_offset(skb));
+	skb_set_tail_pointer(nskb, headlen);
+
+	/* How many frags do we need? */
+	for (i = skb_shinfo(skb)->nr_frags - 1; i >= 0; i--) {
+		bytes_needed -= skb_frag_size(&skb_shinfo(skb)->frags[i]);
+		k++;
+		if (bytes_needed <= 0)
+			break;
+	}
+
+	/* Fill the first frag and split it if necessary */
+	j = skb_shinfo(skb)->nr_frags - k;
+	remaining_page_offset = -bytes_needed;
+	skb_fill_page_desc(nskb, 0,
+			   skb_shinfo(skb)->frags[j].page.p,
+			   skb_shinfo(skb)->frags[j].page_offset + remaining_page_offset,
+			   skb_shinfo(skb)->frags[j].size - remaining_page_offset);
+
+	skb_frag_ref(skb, j);
+
+	/* Fill the rest of the frags */
+	for (i = 1; i < k; i++) {
+		j = skb_shinfo(skb)->nr_frags - k + i;
+
+		skb_fill_page_desc(nskb, i,
+				   skb_shinfo(skb)->frags[j].page.p,
+				   skb_shinfo(skb)->frags[j].page_offset,
+				   skb_shinfo(skb)->frags[j].size);
+		skb_frag_ref(skb, j);
+	}
+	skb_shinfo(nskb)->nr_frags = k;
+
+	remaining_headlen = remaining - skb->data_len;
+
+	/* headlen contains remaining data? */
+	if (remaining_headlen > 0)
+		skb_copy_bits(skb, skb->len - remaining, nskb->data + headlen,
+			      remaining_headlen);
+	nskb->len = remaining + headlen;
+	nskb->data_len =  payload_len - sizeof(struct udphdr) +
+		max_t(int, 0, remaining_headlen);
+	nskb->protocol = skb->protocol;
+	if (nskb->protocol == htons(ETH_P_IP)) {
+		ip_hdr(nskb)->id = htons(ntohs(ip_hdr(nskb)->id) +
+					 skb_shinfo(skb)->gso_segs);
+		ip_hdr(nskb)->tot_len =
+			htons(payload_len + sizeof(struct iphdr));
+	} else {
+		ipv6_hdr(nskb)->payload_len = htons(payload_len);
+	}
+	udp_hdr(nskb)->len = htons(payload_len);
+	skb_shinfo(nskb)->gso_size = 0;
+	nskb->ip_summed = skb->ip_summed;
+	nskb->csum_start = skb->csum_start;
+	nskb->csum_offset = skb->csum_offset;
+	nskb->queue_mapping = skb->queue_mapping;
+}
+
+/* might send skbs and update wqe and pi */
+struct sk_buff *mlx5e_udp_gso_handle_tx_skb(struct net_device *netdev,
+					    struct mlx5e_txqsq *sq,
+					    struct sk_buff *skb,
+					    struct mlx5e_tx_wqe **wqe,
+					    u16 *pi)
+{
+	int payload_len = skb_shinfo(skb)->gso_size + sizeof(struct udphdr);
+	int headlen = skb_transport_offset(skb) + sizeof(struct udphdr);
+	int remaining = (skb->len - headlen) % skb_shinfo(skb)->gso_size;
+	struct sk_buff *nskb;
+
+	if (skb->protocol == htons(ETH_P_IP))
+		ip_hdr(skb)->tot_len = htons(payload_len + sizeof(struct iphdr));
+	else
+		ipv6_hdr(skb)->payload_len = htons(payload_len);
+	udp_hdr(skb)->len = htons(payload_len);
+	if (!remaining)
+		return skb;
+
+	sq->stats->udp_seg_rem++;
+	nskb = alloc_skb(max_t(int, headlen, headlen + remaining - skb->data_len), GFP_ATOMIC);
+	if (unlikely(!nskb)) {
+		sq->stats->dropped++;
+		return NULL;
+	}
+
+	mlx5e_udp_gso_prepare_last_skb(skb, nskb, remaining);
+
+	skb_shinfo(skb)->gso_segs--;
+	pskb_trim(skb, skb->len - remaining);
+	mlx5e_sq_xmit(sq, skb, *wqe, *pi);
+	mlx5e_sq_fetch_wqe(sq, wqe, pi);
+	return nskb;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.h
new file mode 100644
index 000000000000..ed42699a78b3
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.h
@@ -0,0 +1,14 @@
+
+#ifndef __MLX5E_EN_ACCEL_RX_TX_H__
+#define __MLX5E_EN_ACCEL_RX_TX_H__
+
+#include <linux/skbuff.h>
+#include "en.h"
+
+struct sk_buff *mlx5e_udp_gso_handle_tx_skb(struct net_device *netdev,
+					    struct mlx5e_txqsq *sq,
+					    struct sk_buff *skb,
+					    struct mlx5e_tx_wqe **wqe,
+					    u16 *pi);
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 134f20a182b5..ba9ae05efe09 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -270,12 +270,9 @@ void mlx5e_update_stats_work(struct work_struct *work)
 	struct delayed_work *dwork = to_delayed_work(work);
 	struct mlx5e_priv *priv = container_of(dwork, struct mlx5e_priv,
 					       update_stats_work);
+
 	mutex_lock(&priv->state_lock);
-	if (test_bit(MLX5E_STATE_OPENED, &priv->state)) {
-		priv->profile->update_stats(priv);
-		queue_delayed_work(priv->wq, dwork,
-				   msecs_to_jiffies(MLX5E_UPDATE_STATS_INTERVAL));
-	}
+	priv->profile->update_stats(priv);
 	mutex_unlock(&priv->state_lock);
 }
 
@@ -352,8 +349,8 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq,
 {
 	int wq_sz = mlx5_wq_ll_get_size(&rq->mpwqe.wq);
 
-	rq->mpwqe.info = kcalloc_node(wq_sz, sizeof(*rq->mpwqe.info),
-				      GFP_KERNEL, cpu_to_node(c->cpu));
+	rq->mpwqe.info = kvzalloc_node(wq_sz * sizeof(*rq->mpwqe.info),
+				       GFP_KERNEL, cpu_to_node(c->cpu));
 	if (!rq->mpwqe.info)
 		return -ENOMEM;
 
@@ -670,7 +667,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 err_free:
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		kfree(rq->mpwqe.info);
+		kvfree(rq->mpwqe.info);
 		mlx5_core_destroy_mkey(mdev, &rq->umr_mkey);
 		break;
 	default: /* MLX5_WQ_TYPE_CYCLIC */
@@ -702,7 +699,7 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq)
 
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		kfree(rq->mpwqe.info);
+		kvfree(rq->mpwqe.info);
 		mlx5_core_destroy_mkey(rq->mdev, &rq->umr_mkey);
 		break;
 	default: /* MLX5_WQ_TYPE_CYCLIC */
@@ -965,15 +962,15 @@ static void mlx5e_close_rq(struct mlx5e_rq *rq)
 
 static void mlx5e_free_xdpsq_db(struct mlx5e_xdpsq *sq)
 {
-	kfree(sq->db.di);
+	kvfree(sq->db.di);
 }
 
 static int mlx5e_alloc_xdpsq_db(struct mlx5e_xdpsq *sq, int numa)
 {
 	int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
 
-	sq->db.di = kcalloc_node(wq_sz, sizeof(*sq->db.di),
-				     GFP_KERNEL, numa);
+	sq->db.di = kvzalloc_node(sizeof(*sq->db.di) * wq_sz,
+				  GFP_KERNEL, numa);
 	if (!sq->db.di) {
 		mlx5e_free_xdpsq_db(sq);
 		return -ENOMEM;
@@ -1024,15 +1021,15 @@ static void mlx5e_free_xdpsq(struct mlx5e_xdpsq *sq)
 
 static void mlx5e_free_icosq_db(struct mlx5e_icosq *sq)
 {
-	kfree(sq->db.ico_wqe);
+	kvfree(sq->db.ico_wqe);
 }
 
 static int mlx5e_alloc_icosq_db(struct mlx5e_icosq *sq, int numa)
 {
 	u8 wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
 
-	sq->db.ico_wqe = kcalloc_node(wq_sz, sizeof(*sq->db.ico_wqe),
-				      GFP_KERNEL, numa);
+	sq->db.ico_wqe = kvzalloc_node(sizeof(*sq->db.ico_wqe) * wq_sz,
+				       GFP_KERNEL, numa);
 	if (!sq->db.ico_wqe)
 		return -ENOMEM;
 
@@ -1077,8 +1074,8 @@ static void mlx5e_free_icosq(struct mlx5e_icosq *sq)
 
 static void mlx5e_free_txqsq_db(struct mlx5e_txqsq *sq)
 {
-	kfree(sq->db.wqe_info);
-	kfree(sq->db.dma_fifo);
+	kvfree(sq->db.wqe_info);
+	kvfree(sq->db.dma_fifo);
 }
 
 static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa)
@@ -1086,10 +1083,10 @@ static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa)
 	int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
 	int df_sz = wq_sz * MLX5_SEND_WQEBB_NUM_DS;
 
-	sq->db.dma_fifo = kcalloc_node(df_sz, sizeof(*sq->db.dma_fifo),
-					   GFP_KERNEL, numa);
-	sq->db.wqe_info = kcalloc_node(wq_sz, sizeof(*sq->db.wqe_info),
-					   GFP_KERNEL, numa);
+	sq->db.dma_fifo = kvzalloc_node(df_sz * sizeof(*sq->db.dma_fifo),
+					GFP_KERNEL, numa);
+	sq->db.wqe_info = kvzalloc_node(wq_sz * sizeof(*sq->db.wqe_info),
+					GFP_KERNEL, numa);
 	if (!sq->db.dma_fifo || !sq->db.wqe_info) {
 		mlx5e_free_txqsq_db(sq);
 		return -ENOMEM;
@@ -1893,7 +1890,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	int err;
 	int eqn;
 
-	c = kzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
+	c = kvzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
 	if (!c)
 		return -ENOMEM;
 
@@ -1979,7 +1976,7 @@ err_close_icosq_cq:
 
 err_napi_del:
 	netif_napi_del(&c->napi);
-	kfree(c);
+	kvfree(c);
 
 	return err;
 }
@@ -2018,7 +2015,7 @@ static void mlx5e_close_channel(struct mlx5e_channel *c)
 	mlx5e_close_cq(&c->icosq.cq);
 	netif_napi_del(&c->napi);
 
-	kfree(c);
+	kvfree(c);
 }
 
 #define DEFAULT_FRAG_SIZE (2048)
@@ -2276,7 +2273,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv,
 	chs->num = chs->params.num_channels;
 
 	chs->c = kcalloc(chs->num, sizeof(struct mlx5e_channel *), GFP_KERNEL);
-	cparam = kzalloc(sizeof(struct mlx5e_channel_param), GFP_KERNEL);
+	cparam = kvzalloc(sizeof(struct mlx5e_channel_param), GFP_KERNEL);
 	if (!chs->c || !cparam)
 		goto err_free;
 
@@ -2287,7 +2284,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv,
 			goto err_close_channels;
 	}
 
-	kfree(cparam);
+	kvfree(cparam);
 	return 0;
 
 err_close_channels:
@@ -2296,7 +2293,7 @@ err_close_channels:
 
 err_free:
 	kfree(chs->c);
-	kfree(cparam);
+	kvfree(cparam);
 	chs->num = 0;
 	return err;
 }
@@ -3405,6 +3402,9 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	struct mlx5e_vport_stats *vstats = &priv->stats.vport;
 	struct mlx5e_pport_stats *pstats = &priv->stats.pport;
 
+	/* update HW stats in background for next time */
+	queue_delayed_work(priv->wq, &priv->update_stats_work, 0);
+
 	if (mlx5e_is_uplink_rep(priv)) {
 		stats->rx_packets = PPORT_802_3_GET(pstats, a_frames_received_ok);
 		stats->rx_bytes   = PPORT_802_3_GET(pstats, a_octets_received_ok);
@@ -4592,6 +4592,9 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	netdev->features         |= NETIF_F_HIGHDMA;
 	netdev->features         |= NETIF_F_HW_VLAN_STAG_FILTER;
 
+	netdev->features         |= NETIF_F_GSO_UDP_L4;
+	netdev->hw_features      |= NETIF_F_GSO_UDP_L4;
+
 	netdev->priv_flags       |= IFF_UNICAST_FLT;
 
 	mlx5e_set_netdev_dev_addr(netdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 3f2fe95e01d9..7db7552b7e3f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -893,6 +893,9 @@ mlx5e_rep_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 
+	/* update HW stats in background for next time */
+	queue_delayed_work(priv->wq, &priv->update_stats_work, 0);
+
 	memcpy(stats, &priv->stats.vf_vport, sizeof(*stats));
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index d3a1dd20e41d..f763a6aebc2d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -487,7 +487,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 
 	sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR;
 	sq->pc += MLX5E_UMR_WQEBBS;
-	mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &umr_wqe->ctrl);
+	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &umr_wqe->ctrl);
 
 	return 0;
 
@@ -601,6 +601,8 @@ bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
 
 	if (!rq->mpwqe.umr_in_progress)
 		mlx5e_alloc_rx_mpwqe(rq, wq->head);
+	else
+		rq->stats->congst_umr += mlx5_wq_ll_missing(wq) > 2;
 
 	return false;
 }
@@ -1261,7 +1263,10 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	}
 
 	if (unlikely(mpwrq_is_filler_cqe(cqe))) {
-		rq->stats->mpwqe_filler++;
+		struct mlx5e_rq_stats *stats = rq->stats;
+
+		stats->mpwqe_filler_cqes++;
+		stats->mpwqe_filler_strides += cstrides;
 		goto mpwrq_cqe_out;
 	}
 
@@ -1383,6 +1388,8 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 		} while (!last_wqe);
 	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
 
+	rq->stats->xdp_tx_cqe += i;
+
 	mlx5_cqwq_update_db_record(&cq->wq);
 
 	/* ensure cq space is freed before enabling more cqes */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 1646859974ce..c0507fada0be 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -44,6 +44,7 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_packets) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_bytes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_added_vlan_packets) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_nop) },
 
 #ifdef CONFIG_MLX5_EN_TLS
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_ooo) },
@@ -59,6 +60,7 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary_inner) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_drop) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_cqe) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_full) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_none) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial) },
@@ -67,10 +69,13 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_dropped) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xmit_more) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_recover) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_udp_seg_rem) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqe_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_wqe_err) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler_cqes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler_strides) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_buff_alloc_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_blks) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_pkts) },
@@ -80,6 +85,11 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_empty) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_busy) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_waive) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_congst_umr) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_events) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_poll) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_arm) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_aff_change) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_eq_rearm) },
 };
 
@@ -133,9 +143,11 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner;
 		s->rx_xdp_drop += rq_stats->xdp_drop;
 		s->rx_xdp_tx += rq_stats->xdp_tx;
+		s->rx_xdp_tx_cqe  += rq_stats->xdp_tx_cqe;
 		s->rx_xdp_tx_full += rq_stats->xdp_tx_full;
 		s->rx_wqe_err   += rq_stats->wqe_err;
-		s->rx_mpwqe_filler += rq_stats->mpwqe_filler;
+		s->rx_mpwqe_filler_cqes    += rq_stats->mpwqe_filler_cqes;
+		s->rx_mpwqe_filler_strides += rq_stats->mpwqe_filler_strides;
 		s->rx_buff_alloc_err += rq_stats->buff_alloc_err;
 		s->rx_cqe_compress_blks += rq_stats->cqe_compress_blks;
 		s->rx_cqe_compress_pkts += rq_stats->cqe_compress_pkts;
@@ -145,6 +157,11 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->rx_cache_empty += rq_stats->cache_empty;
 		s->rx_cache_busy  += rq_stats->cache_busy;
 		s->rx_cache_waive += rq_stats->cache_waive;
+		s->rx_congst_umr  += rq_stats->congst_umr;
+		s->ch_events      += ch_stats->events;
+		s->ch_poll        += ch_stats->poll;
+		s->ch_arm         += ch_stats->arm;
+		s->ch_aff_change  += ch_stats->aff_change;
 		s->ch_eq_rearm += ch_stats->eq_rearm;
 
 		for (j = 0; j < priv->max_opened_tc; j++) {
@@ -157,8 +174,10 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 			s->tx_tso_inner_packets	+= sq_stats->tso_inner_packets;
 			s->tx_tso_inner_bytes	+= sq_stats->tso_inner_bytes;
 			s->tx_added_vlan_packets += sq_stats->added_vlan_packets;
+			s->tx_nop               += sq_stats->nop;
 			s->tx_queue_stopped	+= sq_stats->stopped;
 			s->tx_queue_wake	+= sq_stats->wake;
+			s->tx_udp_seg_rem	+= sq_stats->udp_seg_rem;
 			s->tx_queue_dropped	+= sq_stats->dropped;
 			s->tx_cqe_err		+= sq_stats->cqe_err;
 			s->tx_recover		+= sq_stats->recover;
@@ -170,6 +189,7 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 			s->tx_tls_ooo		+= sq_stats->tls_ooo;
 			s->tx_tls_resync_bytes	+= sq_stats->tls_resync_bytes;
 #endif
+			s->tx_cqes		+= sq_stats->cqes;
 		}
 	}
 
@@ -1107,12 +1127,14 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_drop) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx_cqe) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx_full) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_bytes) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, removed_vlan_packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, wqe_err) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler_cqes) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler_strides) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, buff_alloc_err) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_blks) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) },
@@ -1122,6 +1144,7 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_empty) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_busy) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_waive) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, congst_umr) },
 };
 
 static const struct counter_desc sq_stats_desc[] = {
@@ -1140,11 +1163,16 @@ static const struct counter_desc sq_stats_desc[] = {
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, dropped) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, xmit_more) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, recover) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, cqes) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, wake) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, cqe_err) },
 };
 
 static const struct counter_desc ch_stats_desc[] = {
+	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, events) },
+	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, poll) },
+	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, arm) },
+	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, aff_change) },
 	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, eq_rearm) },
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 643153bb3607..fc3f66003edd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -61,6 +61,7 @@ struct mlx5e_sw_stats {
 	u64 tx_tso_inner_packets;
 	u64 tx_tso_inner_bytes;
 	u64 tx_added_vlan_packets;
+	u64 tx_nop;
 	u64 rx_lro_packets;
 	u64 rx_lro_bytes;
 	u64 rx_removed_vlan_packets;
@@ -70,6 +71,7 @@ struct mlx5e_sw_stats {
 	u64 rx_csum_unnecessary_inner;
 	u64 rx_xdp_drop;
 	u64 rx_xdp_tx;
+	u64 rx_xdp_tx_cqe;
 	u64 rx_xdp_tx_full;
 	u64 tx_csum_none;
 	u64 tx_csum_partial;
@@ -78,10 +80,13 @@ struct mlx5e_sw_stats {
 	u64 tx_queue_dropped;
 	u64 tx_xmit_more;
 	u64 tx_recover;
+	u64 tx_cqes;
 	u64 tx_queue_wake;
+	u64 tx_udp_seg_rem;
 	u64 tx_cqe_err;
 	u64 rx_wqe_err;
-	u64 rx_mpwqe_filler;
+	u64 rx_mpwqe_filler_cqes;
+	u64 rx_mpwqe_filler_strides;
 	u64 rx_buff_alloc_err;
 	u64 rx_cqe_compress_blks;
 	u64 rx_cqe_compress_pkts;
@@ -91,6 +96,11 @@ struct mlx5e_sw_stats {
 	u64 rx_cache_empty;
 	u64 rx_cache_busy;
 	u64 rx_cache_waive;
+	u64 rx_congst_umr;
+	u64 ch_events;
+	u64 ch_poll;
+	u64 ch_arm;
+	u64 ch_aff_change;
 	u64 ch_eq_rearm;
 
 #ifdef CONFIG_MLX5_EN_TLS
@@ -169,9 +179,11 @@ struct mlx5e_rq_stats {
 	u64 removed_vlan_packets;
 	u64 xdp_drop;
 	u64 xdp_tx;
+	u64 xdp_tx_cqe;
 	u64 xdp_tx_full;
 	u64 wqe_err;
-	u64 mpwqe_filler;
+	u64 mpwqe_filler_cqes;
+	u64 mpwqe_filler_strides;
 	u64 buff_alloc_err;
 	u64 cqe_compress_blks;
 	u64 cqe_compress_pkts;
@@ -181,6 +193,7 @@ struct mlx5e_rq_stats {
 	u64 cache_empty;
 	u64 cache_busy;
 	u64 cache_waive;
+	u64 congst_umr;
 };
 
 struct mlx5e_sq_stats {
@@ -196,6 +209,7 @@ struct mlx5e_sq_stats {
 	u64 csum_partial_inner;
 	u64 added_vlan_packets;
 	u64 nop;
+	u64 udp_seg_rem;
 #ifdef CONFIG_MLX5_EN_TLS
 	u64 tls_ooo;
 	u64 tls_resync_bytes;
@@ -206,11 +220,16 @@ struct mlx5e_sq_stats {
 	u64 dropped;
 	u64 recover;
 	/* dirtied @completion */
-	u64 wake ____cacheline_aligned_in_smp;
+	u64 cqes ____cacheline_aligned_in_smp;
+	u64 wake;
 	u64 cqe_err;
 };
 
 struct mlx5e_ch_stats {
+	u64 events;
+	u64 poll;
+	u64 arm;
+	u64 aff_change;
 	u64 eq_rearm;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index f29deb44bf3b..f0739dae7b56 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -228,7 +228,10 @@ mlx5e_tx_get_gso_ihs(struct mlx5e_txqsq *sq, struct sk_buff *skb)
 		stats->tso_inner_packets++;
 		stats->tso_inner_bytes += skb->len - ihs;
 	} else {
-		ihs = skb_transport_offset(skb) + tcp_hdrlen(skb);
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
+			ihs = skb_transport_offset(skb) + sizeof(struct udphdr);
+		else
+			ihs = skb_transport_offset(skb) + tcp_hdrlen(skb);
 		stats->tso_packets++;
 		stats->tso_bytes += skb->len - ihs;
 	}
@@ -443,12 +446,11 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 	sq = priv->txq2sq[skb_get_queue_mapping(skb)];
 	mlx5e_sq_fetch_wqe(sq, &wqe, &pi);
 
-#ifdef CONFIG_MLX5_ACCEL
 	/* might send skbs and update wqe and pi */
 	skb = mlx5e_accel_handle_tx(skb, sq, dev, &wqe, &pi);
 	if (unlikely(!skb))
 		return NETDEV_TX_OK;
-#endif
+
 	return mlx5e_sq_xmit(sq, skb, wqe, pi);
 }
 
@@ -466,6 +468,7 @@ static void mlx5e_dump_error_cqe(struct mlx5e_txqsq *sq,
 
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 {
+	struct mlx5e_sq_stats *stats;
 	struct mlx5e_txqsq *sq;
 	struct mlx5_cqe64 *cqe;
 	u32 dma_fifo_cc;
@@ -483,6 +486,8 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 	if (!cqe)
 		return false;
 
+	stats = sq->stats;
+
 	npkts = 0;
 	nbytes = 0;
 
@@ -511,7 +516,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 				queue_work(cq->channel->priv->wq,
 					   &sq->recover.recover_work);
 			}
-			sq->stats->cqe_err++;
+			stats->cqe_err++;
 		}
 
 		do {
@@ -556,6 +561,8 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 
 	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
 
+	stats->cqes += i;
+
 	mlx5_cqwq_update_db_record(&cq->wq);
 
 	/* ensure cq space is freed before enabling more cqes */
@@ -571,7 +578,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 				   MLX5E_SQ_STOP_ROOM) &&
 	    !test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) {
 		netif_tx_wake_queue(sq->txq);
-		sq->stats->wake++;
+		stats->wake++;
 	}
 
 	return (i == MLX5E_TX_CQ_POLL_BUDGET);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index 1b17f682693b..4e1f99a98d5d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -74,10 +74,13 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 {
 	struct mlx5e_channel *c = container_of(napi, struct mlx5e_channel,
 					       napi);
+	struct mlx5e_ch_stats *ch_stats = c->stats;
 	bool busy = false;
 	int work_done = 0;
 	int i;
 
+	ch_stats->poll++;
+
 	for (i = 0; i < c->num_tc; i++)
 		busy |= mlx5e_poll_tx_cq(&c->sq[i].cq, budget);
 
@@ -94,6 +97,7 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	if (busy) {
 		if (likely(mlx5e_channel_no_affinity_change(c)))
 			return budget;
+		ch_stats->aff_change++;
 		if (budget && work_done == budget)
 			work_done--;
 	}
@@ -101,6 +105,8 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	if (unlikely(!napi_complete_done(napi, work_done)))
 		return work_done;
 
+	ch_stats->arm++;
+
 	for (i = 0; i < c->num_tc; i++) {
 		mlx5e_handle_tx_dim(&c->sq[i]);
 		mlx5e_cq_arm(&c->sq[i].cq);
@@ -118,8 +124,9 @@ void mlx5e_completion_event(struct mlx5_core_cq *mcq)
 {
 	struct mlx5e_cq *cq = container_of(mcq, struct mlx5e_cq, mcq);
 
-	cq->event_ctr++;
 	napi_schedule(cq->napi);
+	cq->event_ctr++;
+	cq->channel->stats->events++;
 }
 
 void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
index 0b47126815b6..2bd4c3184eba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
@@ -229,6 +229,11 @@ static inline int mlx5_wq_ll_is_empty(struct mlx5_wq_ll *wq)
 	return !wq->cur_sz;
 }
 
+static inline int mlx5_wq_ll_missing(struct mlx5_wq_ll *wq)
+{
+	return wq->fbc.sz_m1 - wq->cur_sz;
+}
+
 static inline void *mlx5_wq_ll_get_wqe(struct mlx5_wq_ll *wq, u16 ix)
 {
 	return mlx5_frag_buf_get_wqe(&wq->fbc, ix);