net: fec: change data structure to support multiqueue

This patch just change data structure to support multi-queue.
Only 1 queue enabled.

Ethernet multiqueue mechanism can improve performance in SMP system.
For single hw queue, multiqueue can balance cpu loading.
For multi hw queues, multiple cores can process network packets in parallel,
and refer the article for the detail advantage for multiqueue:
http://vger.kernel.org/~davem/davem_nyc09.pdfSigned-off-by: Fugang Duan <B38611@freescale.com>
Signed-off-by: Frank Li <frank.li@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/freescale/fec.h

@@ -27,8 +27,8 @@
  */
 #define FEC_IEVENT		0x004 /* Interrupt event reg */
 #define FEC_IMASK		0x008 /* Interrupt mask reg */
-#define FEC_R_DES_ACTIVE	0x010 /* Receive descriptor reg */
-#define FEC_X_DES_ACTIVE	0x014 /* Transmit descriptor reg */
+#define FEC_R_DES_ACTIVE_0	0x010 /* Receive descriptor reg */
+#define FEC_X_DES_ACTIVE_0	0x014 /* Transmit descriptor reg */
 #define FEC_ECNTRL		0x024 /* Ethernet control reg */
 #define FEC_MII_DATA		0x040 /* MII manage frame reg */
 #define FEC_MII_SPEED		0x044 /* MII speed control reg */
@@ -45,14 +45,26 @@
 #define FEC_X_WMRK		0x144 /* FIFO transmit water mark */
 #define FEC_R_BOUND		0x14c /* FIFO receive bound reg */
 #define FEC_R_FSTART		0x150 /* FIFO receive start reg */
-#define FEC_R_DES_START		0x180 /* Receive descriptor ring */
-#define FEC_X_DES_START		0x184 /* Transmit descriptor ring */
+#define FEC_R_DES_START_1	0x160 /* Receive descriptor ring 1 */
+#define FEC_X_DES_START_1	0x164 /* Transmit descriptor ring 1 */
+#define FEC_R_DES_START_2	0x16c /* Receive descriptor ring 2 */
+#define FEC_X_DES_START_2	0x170 /* Transmit descriptor ring 2 */
+#define FEC_R_DES_START_0	0x180 /* Receive descriptor ring */
+#define FEC_X_DES_START_0	0x184 /* Transmit descriptor ring */
 #define FEC_R_BUFF_SIZE		0x188 /* Maximum receive buff size */
 #define FEC_R_FIFO_RSFL		0x190 /* Receive FIFO section full threshold */
 #define FEC_R_FIFO_RSEM		0x194 /* Receive FIFO section empty threshold */
 #define FEC_R_FIFO_RAEM		0x198 /* Receive FIFO almost empty threshold */
 #define FEC_R_FIFO_RAFL		0x19c /* Receive FIFO almost full threshold */
 #define FEC_RACC		0x1C4 /* Receive Accelerator function */
+#define FEC_RCMR_1		0x1c8 /* Receive classification match ring 1 */
+#define FEC_RCMR_2		0x1cc /* Receive classification match ring 2 */
+#define FEC_DMA_CFG_1		0x1d8 /* DMA class configuration for ring 1 */
+#define FEC_DMA_CFG_2		0x1dc /* DMA class Configuration for ring 2 */
+#define FEC_R_DES_ACTIVE_1	0x1e0 /* Rx descriptor active for ring 1 */
+#define FEC_X_DES_ACTIVE_1	0x1e4 /* Tx descriptor active for ring 1 */
+#define FEC_R_DES_ACTIVE_2	0x1e8 /* Rx descriptor active for ring 2 */
+#define FEC_X_DES_ACTIVE_2	0x1ec /* Tx descriptor active for ring 2 */
 #define FEC_MIIGSK_CFGR		0x300 /* MIIGSK Configuration reg */
 #define FEC_MIIGSK_ENR		0x308 /* MIIGSK Enable reg */
 
@@ -233,6 +245,43 @@ struct bufdesc_ex {
 /* This device has up to three irqs on some platforms */
 #define FEC_IRQ_NUM		3
 
+/* Maximum number of queues supported
+ * ENET with AVB IP can support up to 3 independent tx queues and rx queues.
+ * User can point the queue number that is less than or equal to 3.
+ */
+#define FEC_ENET_MAX_TX_QS	3
+#define FEC_ENET_MAX_RX_QS	3
+
+#define FEC_R_DES_START(X)	((X == 1) ? FEC_R_DES_START_1 : \
+				((X == 2) ? \
+					FEC_R_DES_START_2 : FEC_R_DES_START_0))
+#define FEC_X_DES_START(X)	((X == 1) ? FEC_X_DES_START_1 : \
+				((X == 2) ? \
+					FEC_X_DES_START_2 : FEC_X_DES_START_0))
+#define FEC_R_DES_ACTIVE(X)	((X == 1) ? FEC_R_DES_ACTIVE_1 : \
+				((X == 2) ? \
+				   FEC_R_DES_ACTIVE_2 : FEC_R_DES_ACTIVE_0))
+#define FEC_X_DES_ACTIVE(X)	((X == 1) ? FEC_X_DES_ACTIVE_1 : \
+				((X == 2) ? \
+				   FEC_X_DES_ACTIVE_2 : FEC_X_DES_ACTIVE_0))
+
+#define FEC_DMA_CFG(X)		((X == 2) ? FEC_DMA_CFG_2 : FEC_DMA_CFG_1)
+
+#define DMA_CLASS_EN		(1 << 16)
+#define FEC_RCMR(X)		((X == 2) ? FEC_RCMR_2 : FEC_RCMR_1)
+#define IDLE_SLOPE_MASK		0xFFFF
+#define IDLE_SLOPE_1		0x200 /* BW fraction: 0.5 */
+#define IDLE_SLOPE_2		0x200 /* BW fraction: 0.5 */
+#define IDLE_SLOPE(X)		((X == 1) ? (IDLE_SLOPE_1 & IDLE_SLOPE_MASK) : \
+				(IDLE_SLOPE_2 & IDLE_SLOPE_MASK))
+#define RCMR_MATCHEN            (0x1 << 16)
+#define RCMR_CMP_CFG(v, n)	((v & 0x7) <<  (n << 2))
+#define RCMR_CMP_1		(RCMR_CMP_CFG(0, 0) | RCMR_CMP_CFG(1, 1) | \
+				RCMR_CMP_CFG(2, 2) | RCMR_CMP_CFG(3, 3))
+#define RCMR_CMP_2		(RCMR_CMP_CFG(4, 0) | RCMR_CMP_CFG(5, 1) | \
+				RCMR_CMP_CFG(6, 2) | RCMR_CMP_CFG(7, 3))
+#define RCMR_CMP(X)		((X == 1) ? RCMR_CMP_1 : RCMR_CMP_2)
+
 /* The number of Tx and Rx buffers.  These are allocated from the page
  * pool.  The code may assume these are power of two, so it it best
  * to keep them that size.
@@ -256,6 +305,35 @@ struct bufdesc_ex {
 #define FLAG_RX_CSUM_ENABLED	(BD_ENET_RX_ICE | BD_ENET_RX_PCR)
 #define FLAG_RX_CSUM_ERROR	(BD_ENET_RX_ICE | BD_ENET_RX_PCR)
 
+struct fec_enet_priv_tx_q {
+	int index;
+	unsigned char *tx_bounce[TX_RING_SIZE];
+	struct  sk_buff *tx_skbuff[TX_RING_SIZE];
+
+	dma_addr_t	bd_dma;
+	struct bufdesc	*tx_bd_base;
+	uint tx_ring_size;
+
+	unsigned short tx_stop_threshold;
+	unsigned short tx_wake_threshold;
+
+	struct bufdesc	*cur_tx;
+	struct bufdesc	*dirty_tx;
+	char *tso_hdrs;
+	dma_addr_t tso_hdrs_dma;
+};
+
+struct fec_enet_priv_rx_q {
+	int index;
+	struct  sk_buff *rx_skbuff[RX_RING_SIZE];
+
+	dma_addr_t	bd_dma;
+	struct bufdesc	*rx_bd_base;
+	uint rx_ring_size;
+
+	struct bufdesc	*cur_rx;
+};
+
 /* The FEC buffer descriptors track the ring buffers.  The rx_bd_base and
  * tx_bd_base always point to the base of the buffer descriptors.  The
  * cur_rx and cur_tx point to the currently available buffer.
@@ -280,29 +358,18 @@ struct fec_enet_private {
 	struct mutex ptp_clk_mutex;
 
 	/* The saved address of a sent-in-place packet/buffer, for skfree(). */
-	unsigned char *tx_bounce[TX_RING_SIZE];
-	struct	sk_buff *tx_skbuff[TX_RING_SIZE];
-	struct	sk_buff *rx_skbuff[RX_RING_SIZE];
+	struct fec_enet_priv_tx_q *tx_queue[FEC_ENET_MAX_TX_QS];
+	struct fec_enet_priv_rx_q *rx_queue[FEC_ENET_MAX_RX_QS];
 
-	/* CPM dual port RAM relative addresses */
-	dma_addr_t	bd_dma;
-	/* Address of Rx and Tx buffers */
-	struct bufdesc	*rx_bd_base;
-	struct bufdesc	*tx_bd_base;
-	/* The next free ring entry */
-	struct bufdesc	*cur_rx, *cur_tx;
-	/* The ring entries to be free()ed */
-	struct bufdesc	*dirty_tx;
+	unsigned int total_tx_ring_size;
+	unsigned int total_rx_ring_size;
 
-	unsigned short bufdesc_size;
-	unsigned short tx_ring_size;
-	unsigned short rx_ring_size;
-	unsigned short tx_stop_threshold;
-	unsigned short tx_wake_threshold;
+	unsigned long work_tx;
+	unsigned long work_rx;
+	unsigned long work_ts;
+	unsigned long work_mdio;
 
-	/* Software TSO */
-	char *tso_hdrs;
-	dma_addr_t tso_hdrs_dma;
+	unsigned short bufdesc_size;
 
 	struct	platform_device *pdev;