net: stmmac: Rework coalesce timer and fix multi-queue races

This follows David Miller advice and tries to fix coalesce timer in
multi-queue scenarios.

We are now using per-queue coalesce values and per-queue TX timer.

Coalesce timer default values was changed to 1ms and the coalesce frames
to 25.

Tested in B2B setup between XGMAC2 and GMAC5.
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Fixes: 	ce736788 ("net: stmmac: adding multiple buffers for TX")
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: Neil Armstrong <narmstrong@baylibre.com>
Cc: Jerome Brunet <jbrunet@baylibre.com>
Cc: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

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

@@ -258,10 +258,10 @@ struct stmmac_safety_stats {
 #define MAX_DMA_RIWT		0xff
 #define MIN_DMA_RIWT		0x20
 /* Tx coalesce parameters */
-#define STMMAC_COAL_TX_TIMER	40000
+#define STMMAC_COAL_TX_TIMER	1000
 #define STMMAC_MAX_COAL_TX_TICK	100000
 #define STMMAC_TX_MAX_FRAMES	256
-#define STMMAC_TX_FRAMES	64
+#define STMMAC_TX_FRAMES	25
 
 /* Packets types */
 enum packets_types {

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

@@ -48,6 +48,8 @@ struct stmmac_tx_info {
 
 /* Frequently used values are kept adjacent for cache effect */
 struct stmmac_tx_queue {
+	u32 tx_count_frames;
+	struct timer_list txtimer;
 	u32 queue_index;
 	struct stmmac_priv *priv_data;
 	struct dma_extended_desc *dma_etx ____cacheline_aligned_in_smp;
@@ -73,7 +75,14 @@ struct stmmac_rx_queue {
 	u32 rx_zeroc_thresh;
 	dma_addr_t dma_rx_phy;
 	u32 rx_tail_addr;
+};
+
+struct stmmac_channel {
 	struct napi_struct napi ____cacheline_aligned_in_smp;
+	struct stmmac_priv *priv_data;
+	u32 index;
+	int has_rx;
+	int has_tx;
 };
 
 struct stmmac_tc_entry {
@@ -109,14 +118,12 @@ struct stmmac_pps_cfg {
 
 struct stmmac_priv {
 	/* Frequently used values are kept adjacent for cache effect */
-	u32 tx_count_frames;
 	u32 tx_coal_frames;
 	u32 tx_coal_timer;
 
 	int tx_coalesce;
 	int hwts_tx_en;
 	bool tx_path_in_lpi_mode;
-	struct timer_list txtimer;
 	bool tso;
 
 	unsigned int dma_buf_sz;
@@ -137,6 +144,9 @@ struct stmmac_priv {
 	/* TX Queue */
 	struct stmmac_tx_queue tx_queue[MTL_MAX_TX_QUEUES];
 
+	/* Generic channel for NAPI */
+	struct stmmac_channel channel[STMMAC_CH_MAX];
+
 	bool oldlink;
 	int speed;
 	int oldduplex;

include/linux/stmmac.h

@@ -30,6 +30,7 @@
 
 #define MTL_MAX_RX_QUEUES	8
 #define MTL_MAX_TX_QUEUES	8
+#define STMMAC_CH_MAX		8
 
 #define STMMAC_RX_COE_NONE	0
 #define STMMAC_RX_COE_TYPE1	1