Merge branch 'net-stmmac-CPU-Performance-Improvements'

Jose Abreu says:

====================
net: stmmac: CPU Performance Improvements

CPU Performance improvements for stmmac. Please check bellow for results
before and after the series.

Patch 1/7, allows RX Interrupt on Completion to be disabled and only use the
RX HW Watchdog.

Patch 2/7, setups the default RX coalesce settings instead of using the
minimum value.

Patch 3/7 and 4/7, removes the uneeded computations for RX Flow Control
activation/de-activation, on some cases.

Patch 5/7, tunes-up the default coalesce settings.

Patch 6/7, re-works the TX coalesce timer activation logic.

Patch 7/7, removes the now uneeded TBU interrupt.

NetPerf UDP Results:
--------------------

Socket Message Elapsed Messages CPU Service
Size Size Time Okay Errors Throughput Util Demand
bytes bytes secs # # 10^6bits/sec % SS us/KB
--- XGMAC@2.5G: Before
212992 1400 10.00 2100620 0 2351.7 36.69 5.112
212992 10.00 2100539 2351.6 26.18 3.648
--- XGMAC@2.5G: After
212992 1400 10.00 2108972 0 2361.5 21.73 3.015
212992 10.00 2097038 2348.1 19.21 2.666

--- GMAC5@1G: Before
212992 1400 10.00 786000 0 880.2 34.71 12.923
212992 10.00 786000 880.2 23.42 8.719
--- GMAC5@1G: After
212992 1400 10.00 842648 0 943.7 14.12 4.903
212992 10.00 842648 943.7 12.73 4.418

Perf TCP Results on RX Path:
----------------------------
--- XGMAC@2.5G: Before
22.51% swapper [stmmac] [k] dwxgmac2_dma_interrupt
10.82% swapper [stmmac] [k] dwxgmac2_host_mtl_irq_status
5.21% swapper [stmmac] [k] dwxgmac2_host_irq_status
4.67% swapper [stmmac] [k] dwxgmac3_safety_feat_irq_status
3.63% swapper [kernel.kallsyms] [k] stack_trace_consume_entry
2.74% iperf3 [kernel.kallsyms] [k] copy_user_enhanced_fast_string
2.52% swapper [kernel.kallsyms] [k] update_stack_state
1.94% ksoftirqd/0 [stmmac] [k] dwxgmac2_dma_interrupt
1.45% iperf3 [kernel.kallsyms] [k] queued_spin_lock_slowpath
1.26% swapper [kernel.kallsyms] [k] create_object
--- XGMAC@2.5G: After
7.43% swapper [kernel.kallsyms] [k] stack_trace_consume_entry
5.86% swapper [stmmac] [k] dwxgmac2_dma_interrupt
5.68% swapper [kernel.kallsyms] [k] update_stack_state
4.71% iperf3 [kernel.kallsyms] [k] copy_user_enhanced_fast_string
2.88% swapper [kernel.kallsyms] [k] create_object
2.69% swapper [stmmac] [k] dwxgmac2_host_mtl_irq_status
2.61% swapper [stmmac] [k] stmmac_napi_poll_rx
2.52% swapper [kernel.kallsyms] [k] unwind_next_frame.part.4
1.48% swapper [kernel.kallsyms] [k] unwind_get_return_address
1.38% swapper [kernel.kallsyms] [k] arch_stack_walk

--- GMAC5@1G: Before
31.29% swapper [stmmac] [k] dwmac4_dma_interrupt
14.57% swapper [stmmac] [k] dwmac4_irq_mtl_status
10.66% swapper [stmmac] [k] dwmac4_irq_status
1.97% swapper [kernel.kallsyms] [k] stack_trace_consume_entry
1.73% iperf3 [kernel.kallsyms] [k] copy_user_enhanced_fast_string
1.59% swapper [kernel.kallsyms] [k] update_stack_state
1.15% iperf3 [kernel.kallsyms] [k] do_syscall_64
1.01% ksoftirqd/0 [stmmac] [k] dwmac4_dma_interrupt
0.89% swapper [kernel.kallsyms] [k] __default_send_IPI_dest_field
0.75% swapper [stmmac] [k] stmmac_napi_poll_rx
--- GMAC5@1G: After
6.70% swapper [kernel.kallsyms] [k] stack_trace_consume_entry
5.79% swapper [stmmac] [k] dwmac4_dma_interrupt
5.29% swapper [kernel.kallsyms] [k] update_stack_state
3.52% iperf3 [kernel.kallsyms] [k] copy_user_enhanced_fast_string
2.83% swapper [stmmac] [k] dwmac4_irq_mtl_status
2.62% swapper [kernel.kallsyms] [k] create_object
2.46% swapper [stmmac] [k] stmmac_napi_poll_rx
2.32% swapper [kernel.kallsyms] [k] unwind_next_frame.part.4
2.19% swapper [stmmac] [k] dwmac4_irq_status
1.39% swapper [kernel.kallsyms] [k] unwind_get_return_address
====================

Signed-off-by: David S. Miller <[e-mail]>

drivers/net/ethernet/stmicro/stmmac/common.h

···
 /* Max/Min RI Watchdog Timer count value */
 #define MAX_DMA_RIWT		0xff
 #define MIN_DMA_RIWT		0x10
+#define DEF_DMA_RIWT		0xa0
 /* Tx coalesce parameters */
 #define STMMAC_COAL_TX_TIMER	1000
 #define STMMAC_MAX_COAL_TX_TICK	100000
 #define STMMAC_TX_MAX_FRAMES	256
-#define STMMAC_TX_FRAMES	1
-#define STMMAC_RX_FRAMES	25
+#define STMMAC_TX_FRAMES	25
+#define STMMAC_RX_FRAMES	0
 
 /* Packets types */
 enum packets_types {

drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c

···
 			rfa = 0x01; /* Full-1.5K */
 			break;
 
-		case 8192:
-			rfd = 0x06; /* Full-4K */
-			rfa = 0x0a; /* Full-6K */
-			break;
-
-		case 16384:
-			rfd = 0x06; /* Full-4K */
-			rfa = 0x12; /* Full-10K */
-			break;
-
 		default:
-			rfd = 0x06; /* Full-4K */
-			rfa = 0x1e; /* Full-16K */
+			rfd = 0x07; /* Full-4.5K */
+			rfa = 0x04; /* Full-3K */
 			break;
 		}
 

drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h

···
 #define XGMAC_TBUE			BIT(2)
 #define XGMAC_TIE			BIT(0)
 #define XGMAC_DMA_INT_DEFAULT_EN	(XGMAC_NIE | XGMAC_AIE | XGMAC_RBUE | \
-					XGMAC_RIE | XGMAC_TBUE | XGMAC_TIE)
+					XGMAC_RIE | XGMAC_TIE)
 #define XGMAC_DMA_CH_Rx_WATCHDOG(x)	(0x0000313c + (0x80 * (x)))
 #define XGMAC_RWT			GENMASK(7, 0)
 #define XGMAC_DMA_CH_STATUS(x)		(0x00003160 + (0x80 * (x)))

drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c

···
 			rfa = 0x01; /* Full-1.5K */
 			break;
 
-		case 8192:
-			rfd = 0x06; /* Full-4K */
-			rfa = 0x0a; /* Full-6K */
-			break;
-
-		case 16384:
-			rfd = 0x06; /* Full-4K */
-			rfa = 0x12; /* Full-10K */
-			break;
-
 		default:
-			rfd = 0x06; /* Full-4K */
-			rfa = 0x1e; /* Full-16K */
+			rfd = 0x07; /* Full-4.5K */
+			rfa = 0x04; /* Full-3K */
 			break;
 		}
 

drivers/net/ethernet/stmicro/stmmac/stmmac_main.c

···
 	priv->tx_lpi_timer = STMMAC_DEFAULT_TWT_LS;
 
 	if (priv->use_riwt) {
-		ret = stmmac_rx_watchdog(priv, priv->ioaddr, MIN_DMA_RIWT, rx_cnt);
-		if (!ret)
-			priv->rx_riwt = MIN_DMA_RIWT;
+		if (!priv->rx_riwt)
+			priv->rx_riwt = DEF_DMA_RIWT;
+
+		ret = stmmac_rx_watchdog(priv, priv->ioaddr, priv->rx_riwt, rx_cnt);
 	}
 
 	if (priv->hw->pcs)
···
 	struct stmmac_priv *priv = netdev_priv(dev);
 	int nfrags = skb_shinfo(skb)->nr_frags;
 	u32 queue = skb_get_queue_mapping(skb);
+	unsigned int first_entry, tx_packets;
+	int tmp_pay_len = 0, first_tx;
 	struct stmmac_tx_queue *tx_q;
-	unsigned int first_entry;
 	u8 proto_hdr_len, hdr;
-	int tmp_pay_len = 0;
+	bool has_vlan, set_ic;
 	u32 pay_len, mss;
 	dma_addr_t des;
-	bool has_vlan;
 	int i;
 
 	tx_q = &priv->tx_queue[queue];
+	first_tx = tx_q->cur_tx;
 
 	/* Compute header lengths */
 	if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) {
···
 	tx_q->tx_skbuff[tx_q->cur_tx] = skb;
 
 	/* Manage tx mitigation */
-	tx_q->tx_count_frames += nfrags + 1;
-	if (likely(priv->tx_coal_frames > tx_q->tx_count_frames) &&
-	    !((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
-	      priv->hwts_tx_en)) {
-		stmmac_tx_timer_arm(priv, queue);
-	} else {
+	tx_packets = (tx_q->cur_tx + 1) - first_tx;
+	tx_q->tx_count_frames += tx_packets;
+
+	if ((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && priv->hwts_tx_en)
+		set_ic = true;
+	else if (!priv->tx_coal_frames)
+		set_ic = false;
+	else if (tx_packets > priv->tx_coal_frames)
+		set_ic = true;
+	else if ((tx_q->tx_count_frames % priv->tx_coal_frames) < tx_packets)
+		set_ic = true;
+	else
+		set_ic = false;
+
+	if (set_ic) {
 		desc = &tx_q->dma_tx[tx_q->cur_tx];
 		tx_q->tx_count_frames = 0;
 		stmmac_set_tx_ic(priv, desc);
 		priv->xstats.tx_set_ic_bit++;
+	} else {
+		stmmac_tx_timer_arm(priv, queue);
 	}
 
 	/* We've used all descriptors we need for this skb, however,
···
  */
 static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 {
+	unsigned int first_entry, tx_packets, enh_desc;
 	struct stmmac_priv *priv = netdev_priv(dev);
 	unsigned int nopaged_len = skb_headlen(skb);
 	int i, csum_insertion = 0, is_jumbo = 0;
···
 	int gso = skb_shinfo(skb)->gso_type;
 	struct dma_desc *desc, *first;
 	struct stmmac_tx_queue *tx_q;
-	unsigned int first_entry;
-	unsigned int enh_desc;
+	bool has_vlan, set_ic;
+	int entry, first_tx;
 	dma_addr_t des;
-	bool has_vlan;
-	int entry;
 
 	tx_q = &priv->tx_queue[queue];
+	first_tx = tx_q->cur_tx;
 
 	if (priv->tx_path_in_lpi_mode)
 		stmmac_disable_eee_mode(priv);
···
 	 * This approach takes care about the fragments: desc is the first
 	 * element in case of no SG.
 	 */
-	tx_q->tx_count_frames += nfrags + 1;
-	if (likely(priv->tx_coal_frames > tx_q->tx_count_frames) &&
-	    !((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
-	      priv->hwts_tx_en)) {
-		stmmac_tx_timer_arm(priv, queue);
-	} else {
+	tx_packets = (entry + 1) - first_tx;
+	tx_q->tx_count_frames += tx_packets;
+
+	if ((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && priv->hwts_tx_en)
+		set_ic = true;
+	else if (!priv->tx_coal_frames)
+		set_ic = false;
+	else if (tx_packets > priv->tx_coal_frames)
+		set_ic = true;
+	else if ((tx_q->tx_count_frames % priv->tx_coal_frames) < tx_packets)
+		set_ic = true;
+	else
+		set_ic = false;
+
+	if (set_ic) {
 		if (likely(priv->extend_desc))
 			desc = &tx_q->dma_etx[entry].basic;
 		else
···
 		tx_q->tx_count_frames = 0;
 		stmmac_set_tx_ic(priv, desc);
 		priv->xstats.tx_set_ic_bit++;
+	} else {
+		stmmac_tx_timer_arm(priv, queue);
 	}
 
 	/* We've used all descriptors we need for this skb, however,
···
 		rx_q->rx_count_frames += priv->rx_coal_frames;
 		if (rx_q->rx_count_frames > priv->rx_coal_frames)
 			rx_q->rx_count_frames = 0;
-		use_rx_wd = priv->use_riwt && rx_q->rx_count_frames;
+
+		use_rx_wd = !priv->rx_coal_frames;
+		use_rx_wd |= rx_q->rx_count_frames > 0;
+		if (!priv->use_riwt)
+			use_rx_wd = false;
 
 		dma_wmb();
 		stmmac_set_rx_owner(priv, p, use_rx_wd);