net/macb: add TX multiqueue support for gem

gem devices designed with multiqueue CANNOT work without this patch.

When probing a gem device, the driver must first prepare and enable the
peripheral clock before accessing I/O registers. The second step is to read the
MID register to find whether the device is a gem or an old macb IP.
For gem devices, it reads the Design Configuration Register 6 (DCFG6) to
compute to total number of queues, whereas macb devices always have a single
queue.
Only then it can call alloc_etherdev_mq() with the correct number of queues.
This is the reason why the order of some initializations has been changed in
macb_probe().
Eventually, the dedicated IRQ and TX ring buffer descriptors are initialized
for each queue.

For backward compatibility reasons, queue0 uses the legacy registers ISR, IER,
IDR, IMR, TBQP and RBQP. On the other hand, the other queues use new registers
ISR[1..7], IER[1..7], IDR[1..7], IMR[1..7], TBQP[1..7] and RBQP[1..7].
Except this hardware detail there is no real difference between queue0 and the
others. The driver hides that thanks to the struct macb_queue.
This structure allows us to share a common set of functions for all the queues.

Besides when a TX error occurs, the gem MUST be halted before writing any of
the TBQP registers to reset the relevant queue. An immediate side effect is
that the other queues too aren't processed anymore by the gem.
So macb_tx_error_task() calls netif_tx_stop_all_queues() to notify the Linux
network engine that all transmissions are stopped.

Also macb_tx_error_task() now calls spin_lock_irqsave() to prevent the
interrupt handlers of the other queues from running as each of them may wake
its associated queue up (please refer to macb_tx_interrupt()).

Finally, as all queues have previously been stopped, they should be restarted
calling netif_tx_start_all_queues() and setting the TSTART bit into the Network
Control Register. Before this patch, when dealing with a single queue, the
driver used to defer the reset of the faulting queue and the write of the
TSTART bit until the next call of macb_start_xmit().
As explained before, this bit is now set by macb_tx_error_task() too. That's
why the faulting queue MUST be reset by setting the TX_USED bit in its first
buffer descriptor before writing the TSTART bit.

Queue 0 always exits and is the lowest priority when other queues are available.
The higher the index of the queue is, the higher its priority is.

When transmitting frames, the TX queue is selected by the skb->queue_mapping
value. So queue discipline can be used to define the queue priority policy.
Signed-off-by: Cyrille Pitchen <cyrille.pitchen@atmel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/cadence/macb.h

@@ -12,6 +12,7 @@
 
 #define MACB_GREGS_NBR 16
 #define MACB_GREGS_VERSION 1
+#define MACB_MAX_QUEUES 8
 
 /* MACB register offsets */
 #define MACB_NCR				0x0000
@@ -89,6 +90,13 @@
 #define GEM_DCFG6				0x0294
 #define GEM_DCFG7				0x0298
 
+#define GEM_ISR(hw_q)				(0x0400 + ((hw_q) << 2))
+#define GEM_TBQP(hw_q)				(0x0440 + ((hw_q) << 2))
+#define GEM_RBQP(hw_q)				(0x0480 + ((hw_q) << 2))
+#define GEM_IER(hw_q)				(0x0600 + ((hw_q) << 2))
+#define GEM_IDR(hw_q)				(0x0620 + ((hw_q) << 2))
+#define GEM_IMR(hw_q)				(0x0640 + ((hw_q) << 2))
+
 /* Bitfields in NCR */
 #define MACB_LB_OFFSET				0
 #define MACB_LB_SIZE				1
@@ -376,6 +384,10 @@
 	__raw_readl((port)->regs + GEM_##reg)
 #define gem_writel(port, reg, value)			\
 	__raw_writel((value), (port)->regs + GEM_##reg)
+#define queue_readl(queue, reg)				\
+	__raw_readl((queue)->bp->regs + (queue)->reg)
+#define queue_writel(queue, reg, value)			\
+	__raw_writel((value), (queue)->bp->regs + (queue)->reg)
 
 /*
  * Conditional GEM/MACB macros.  These perform the operation to the correct
@@ -597,6 +609,23 @@ struct macb_config {
 	unsigned int		dma_burst_length;
 };
 
+struct macb_queue {
+	struct macb		*bp;
+	int			irq;
+
+	unsigned int		ISR;
+	unsigned int		IER;
+	unsigned int		IDR;
+	unsigned int		IMR;
+	unsigned int		TBQP;
+
+	unsigned int		tx_head, tx_tail;
+	struct macb_dma_desc	*tx_ring;
+	struct macb_tx_skb	*tx_skb;
+	dma_addr_t		tx_ring_dma;
+	struct work_struct	tx_error_task;
+};
+
 struct macb {
 	void __iomem		*regs;
 
@@ -607,9 +636,8 @@ struct macb {
 	void			*rx_buffers;
 	size_t			rx_buffer_size;
 
-	unsigned int		tx_head, tx_tail;
-	struct macb_dma_desc	*tx_ring;
-	struct macb_tx_skb	*tx_skb;
+	unsigned int		num_queues;
+	struct macb_queue	queues[MACB_MAX_QUEUES];
 
 	spinlock_t		lock;
 	struct platform_device	*pdev;
@@ -618,7 +646,6 @@ struct macb {
 	struct clk		*tx_clk;
 	struct net_device	*dev;
 	struct napi_struct	napi;
-	struct work_struct	tx_error_task;
 	struct net_device_stats	stats;
 	union {
 		struct macb_stats	macb;
@@ -626,7 +653,6 @@ struct macb {
 	}			hw_stats;
 
 	dma_addr_t		rx_ring_dma;
-	dma_addr_t		tx_ring_dma;
 	dma_addr_t		rx_buffers_dma;
 
 	struct macb_or_gem_ops	macbgem_ops;