Merge branch 'mk_eth_soc_fixes-perf-improvements'

Ilya Lipnitskiy says:

====================
mtk_eth_soc: fixes and performance improvements

Most of these changes come from OpenWrt where they have been present and
tested for months.

First three patches are bug fixes. The rest are performance
improvements. The last patch is a cleanup to use the iopoll.h macro for
busy-waiting instead of a custom loop.

v2:
 - Reverse christmas tree in "use iopoll.h macro for DMA init"
 - Use cond_resched() instead of iopoll.h macro in "reduce MDIO bus
   access latency"
 - Use napi_complete_done and rework NAPI callbacks in a new patch
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/mediatek/Kconfig

@@ -11,6 +11,7 @@ config NET_MEDIATEK_SOC
 	tristate "MediaTek SoC Gigabit Ethernet support"
 	depends on NET_DSA || !NET_DSA
 	select PHYLINK
+	select DIMLIB
 	help
 	  This driver supports the gigabit ethernet MACs in the
 	  MediaTek SoC family.

drivers/net/ethernet/mediatek/mtk_eth_soc.h

@@ -16,13 +16,14 @@
 #include <linux/refcount.h>
 #include <linux/phylink.h>
 #include <linux/rhashtable.h>
+#include <linux/dim.h>
 #include "mtk_ppe.h"
 
 #define MTK_QDMA_PAGE_SIZE	2048
 #define MTK_MAX_RX_LENGTH	1536
 #define MTK_MAX_RX_LENGTH_2K	2048
 #define MTK_TX_DMA_BUF_LEN	0x3fff
-#define MTK_DMA_SIZE		256
+#define MTK_DMA_SIZE		512
 #define MTK_NAPI_WEIGHT		64
 #define MTK_MAC_COUNT		2
 #define MTK_RX_ETH_HLEN		(ETH_HLEN + ETH_FCS_LEN)
@@ -137,13 +138,18 @@
 
 /* PDMA Delay Interrupt Register */
 #define MTK_PDMA_DELAY_INT		0xa0c
+#define MTK_PDMA_DELAY_RX_MASK		GENMASK(15, 0)
 #define MTK_PDMA_DELAY_RX_EN		BIT(15)
-#define MTK_PDMA_DELAY_RX_PINT		4
 #define MTK_PDMA_DELAY_RX_PINT_SHIFT	8
-#define MTK_PDMA_DELAY_RX_PTIME		4
-#define MTK_PDMA_DELAY_RX_DELAY		\
-	(MTK_PDMA_DELAY_RX_EN | MTK_PDMA_DELAY_RX_PTIME | \
-	(MTK_PDMA_DELAY_RX_PINT << MTK_PDMA_DELAY_RX_PINT_SHIFT))
+#define MTK_PDMA_DELAY_RX_PTIME_SHIFT	0
+
+#define MTK_PDMA_DELAY_TX_MASK		GENMASK(31, 16)
+#define MTK_PDMA_DELAY_TX_EN		BIT(31)
+#define MTK_PDMA_DELAY_TX_PINT_SHIFT	24
+#define MTK_PDMA_DELAY_TX_PTIME_SHIFT	16
+
+#define MTK_PDMA_DELAY_PINT_MASK	0x7f
+#define MTK_PDMA_DELAY_PTIME_MASK	0xff
 
 /* PDMA Interrupt Status Register */
 #define MTK_PDMA_INT_STATUS	0xa20
@@ -203,12 +209,12 @@
 #define MTK_RX_BT_32DWORDS	(3 << 11)
 #define MTK_NDP_CO_PRO		BIT(10)
 #define MTK_TX_WB_DDONE		BIT(6)
-#define MTK_DMA_SIZE_16DWORDS	(2 << 4)
+#define MTK_TX_BT_32DWORDS	(3 << 4)
 #define MTK_RX_DMA_BUSY		BIT(3)
 #define MTK_TX_DMA_BUSY		BIT(1)
 #define MTK_RX_DMA_EN		BIT(2)
 #define MTK_TX_DMA_EN		BIT(0)
-#define MTK_DMA_BUSY_TIMEOUT	HZ
+#define MTK_DMA_BUSY_TIMEOUT_US	1000000
 
 /* QDMA Reset Index Register */
 #define MTK_QDMA_RST_IDX	0x1A08
@@ -225,6 +231,7 @@
 /* QDMA Interrupt Status Register */
 #define MTK_QDMA_INT_STATUS	0x1A18
 #define MTK_RX_DONE_DLY		BIT(30)
+#define MTK_TX_DONE_DLY		BIT(28)
 #define MTK_RX_DONE_INT3	BIT(19)
 #define MTK_RX_DONE_INT2	BIT(18)
 #define MTK_RX_DONE_INT1	BIT(17)
@@ -234,8 +241,7 @@
 #define MTK_TX_DONE_INT1	BIT(1)
 #define MTK_TX_DONE_INT0	BIT(0)
 #define MTK_RX_DONE_INT		MTK_RX_DONE_DLY
-#define MTK_TX_DONE_INT		(MTK_TX_DONE_INT0 | MTK_TX_DONE_INT1 | \
-				 MTK_TX_DONE_INT2 | MTK_TX_DONE_INT3)
+#define MTK_TX_DONE_INT		MTK_TX_DONE_DLY
 
 /* QDMA Interrupt grouping registers */
 #define MTK_QDMA_INT_GRP1	0x1a20
@@ -301,6 +307,7 @@
 #define RX_DMA_LSO		BIT(30)
 #define RX_DMA_PLEN0(_x)	(((_x) & 0x3fff) << 16)
 #define RX_DMA_GET_PLEN0(_x)	(((_x) >> 16) & 0x3fff)
+#define RX_DMA_VTAG		BIT(15)
 
 /* QDMA descriptor rxd3 */
 #define RX_DMA_VID(_x)		((_x) & 0xfff)
@@ -635,6 +642,7 @@ struct mtk_tx_buf {
  * @phys:		The physical addr of tx_buf
  * @next_free:		Pointer to the next free descriptor
  * @last_free:		Pointer to the last free descriptor
+ * @last_free_ptr:	Hardware pointer value of the last free descriptor
  * @thresh:		The threshold of minimum amount of free descriptors
  * @free_count:		QDMA uses a linked list. Track how many free descriptors
  *			are present
@@ -645,6 +653,7 @@ struct mtk_tx_ring {
 	dma_addr_t phys;
 	struct mtk_tx_dma *next_free;
 	struct mtk_tx_dma *last_free;
+	u32 last_free_ptr;
 	u16 thresh;
 	atomic_t free_count;
 	int dma_size;
@@ -848,6 +857,7 @@ struct mtk_sgmii {
  * @page_lock:		Make sure that register operations are atomic
  * @tx_irq__lock:	Make sure that IRQ register operations are atomic
  * @rx_irq__lock:	Make sure that IRQ register operations are atomic
+ * @dim_lock:		Make sure that Net DIM operations are atomic
  * @dummy_dev:		we run 2 netdevs on 1 physical DMA ring and need a
  *			dummy for NAPI to work
  * @netdev:		The netdev instances
@@ -866,6 +876,14 @@ struct mtk_sgmii {
  * @rx_ring_qdma:	Pointer to the memory holding info about the QDMA RX ring
  * @tx_napi:		The TX NAPI struct
  * @rx_napi:		The RX NAPI struct
+ * @rx_events:		Net DIM RX event counter
+ * @rx_packets:		Net DIM RX packet counter
+ * @rx_bytes:		Net DIM RX byte counter
+ * @rx_dim:		Net DIM RX context
+ * @tx_events:		Net DIM TX event counter
+ * @tx_packets:		Net DIM TX packet counter
+ * @tx_bytes:		Net DIM TX byte counter
+ * @tx_dim:		Net DIM TX context
  * @scratch_ring:	Newer SoCs need memory for a second HW managed TX ring
  * @phy_scratch_ring:	physical address of scratch_ring
  * @scratch_head:	The scratch memory that scratch_ring points to.
@@ -910,6 +928,18 @@ struct mtk_eth {
 
 	const struct mtk_soc_data	*soc;
 
+	spinlock_t			dim_lock;
+
+	u32				rx_events;
+	u32				rx_packets;
+	u32				rx_bytes;
+	struct dim			rx_dim;
+
+	u32				tx_events;
+	u32				tx_packets;
+	u32				tx_bytes;
+	struct dim			tx_dim;
+
 	u32				tx_int_mask_reg;
 	u32				tx_int_status_reg;
 	u32				rx_dma_l4_valid;