Merge branch 'cpsw-mq'

Ivan Khoronzhuk says:

====================
net: ethernet: ti: cpsw: add cpdma multi-queue support

This series is intended to allow cpsw driver to use cpdma ability of
h/w shaper to send/receive data with up to 8 tx and 8 rx queues. This
series doesn't contain interface to configure h/w shaper itself, it
contains only multi-queue support part and ability to configure number
of tx/rx queues with ethtool, it also doesn't contain mapping of input
traffic to rx queues, as it can depend on usage and requires separate
interface for setup.

Default shaper mode - priority mode. The h/w shaper configuration will
be added with separate patch series. This series doesn't affect on net
throughput.

Tested on:
am572x-idk, 1Gbps link
am335-boneblack, 100Mbps link.

A simple example for splitting traffic on queues:

$ ethtool -l eth0

$ ethtool -L eth0 rx 8 tx 8

$ tc qdisc add dev eth0 root handle 1: multiq

$ tc filter add dev eth0 parent 1: protocol ip prio 1 u32 \
    match ip dst 172.22.39.12 \
    action skbedit queue_mapping 5

Based on: net-next/master
V3: https://lkml.org/lkml/2016/8/15/788

Since v3:
-changed arg to priv in fill_rx_channels in
  net: ethernet: ti: davinci_cpdma: split descs num between all channels
- added more comments to cpsw_set_channels

Since v2:
- added new patch to avoid warn while ctrl stop

  net: ethernet: ti: cpsw: add ethtool channels support
- enable ctrl in case at least one interface is running

Since v1:
- removed cpdam_check_free_desc function
- remove pm_runtime calls as they are used in begin/complete ethtool calls now
- removed change of driver version. it can be done later
- corrected setup of channels for dual_emac mode with ethtool
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

drivers/net/ethernet/ti/davinci_cpdma.c

@@ -104,6 +104,7 @@ struct cpdma_ctlr {
 	struct cpdma_desc_pool	*pool;
 	spinlock_t		lock;
 	struct cpdma_chan	*channels[2 * CPDMA_MAX_CHANNELS];
+	int chan_num;
 };
 
 struct cpdma_chan {
@@ -123,6 +124,13 @@ struct cpdma_chan {
 	int	int_set, int_clear, td;
 };
 
+#define tx_chan_num(chan)	(chan)
+#define rx_chan_num(chan)	((chan) + CPDMA_MAX_CHANNELS)
+#define is_rx_chan(chan)	((chan)->chan_num >= CPDMA_MAX_CHANNELS)
+#define is_tx_chan(chan)	(!is_rx_chan(chan))
+#define __chan_linear(chan_num)	((chan_num) & (CPDMA_MAX_CHANNELS - 1))
+#define chan_linear(chan)	__chan_linear((chan)->chan_num)
+
 /* The following make access to common cpdma_ctlr params more readable */
 #define dmaregs		params.dmaregs
 #define num_chan	params.num_chan
@@ -256,6 +264,7 @@ struct cpdma_ctlr *cpdma_ctlr_create(struct cpdma_params *params)
 	ctlr->state = CPDMA_STATE_IDLE;
 	ctlr->params = *params;
 	ctlr->dev = params->dev;
+	ctlr->chan_num = 0;
 	spin_lock_init(&ctlr->lock);
 
 	ctlr->pool = cpdma_desc_pool_create(ctlr->dev,
@@ -332,12 +341,14 @@ int cpdma_ctlr_stop(struct cpdma_ctlr *ctlr)
 	}
 
 	ctlr->state = CPDMA_STATE_TEARDOWN;
+	spin_unlock_irqrestore(&ctlr->lock, flags);
 
 	for (i = 0; i < ARRAY_SIZE(ctlr->channels); i++) {
 		if (ctlr->channels[i])
 			cpdma_chan_stop(ctlr->channels[i]);
 	}
 
+	spin_lock_irqsave(&ctlr->lock, flags);
 	dma_reg_write(ctlr, CPDMA_RXINTMASKCLEAR, 0xffffffff);
 	dma_reg_write(ctlr, CPDMA_TXINTMASKCLEAR, 0xffffffff);
 
@@ -399,13 +410,52 @@ void cpdma_ctlr_eoi(struct cpdma_ctlr *ctlr, u32 value)
 }
 EXPORT_SYMBOL_GPL(cpdma_ctlr_eoi);
 
+u32 cpdma_ctrl_rxchs_state(struct cpdma_ctlr *ctlr)
+{
+	return dma_reg_read(ctlr, CPDMA_RXINTSTATMASKED);
+}
+EXPORT_SYMBOL_GPL(cpdma_ctrl_rxchs_state);
+
+u32 cpdma_ctrl_txchs_state(struct cpdma_ctlr *ctlr)
+{
+	return dma_reg_read(ctlr, CPDMA_TXINTSTATMASKED);
+}
+EXPORT_SYMBOL_GPL(cpdma_ctrl_txchs_state);
+
+/**
+ * cpdma_chan_split_pool - Splits ctrl pool between all channels.
+ * Has to be called under ctlr lock
+ */
+static void cpdma_chan_split_pool(struct cpdma_ctlr *ctlr)
+{
+	struct cpdma_desc_pool *pool = ctlr->pool;
+	struct cpdma_chan *chan;
+	int ch_desc_num;
+	int i;
+
+	if (!ctlr->chan_num)
+		return;
+
+	/* calculate average size of pool slice */
+	ch_desc_num = pool->num_desc / ctlr->chan_num;
+
+	/* split ctlr pool */
+	for (i = 0; i < ARRAY_SIZE(ctlr->channels); i++) {
+		chan = ctlr->channels[i];
+		if (chan)
+			chan->desc_num = ch_desc_num;
+	}
+}
+
 struct cpdma_chan *cpdma_chan_create(struct cpdma_ctlr *ctlr, int chan_num,
-				     cpdma_handler_fn handler)
+				     cpdma_handler_fn handler, int rx_type)
 {
+	int offset = chan_num * 4;
 	struct cpdma_chan *chan;
-	int offset = (chan_num % CPDMA_MAX_CHANNELS) * 4;
 	unsigned long flags;
 
+	chan_num = rx_type ? rx_chan_num(chan_num) : tx_chan_num(chan_num);
+
 	if (__chan_linear(chan_num) >= ctlr->num_chan)
 		return NULL;
 
@@ -447,14 +497,25 @@ struct cpdma_chan *cpdma_chan_create(struct cpdma_ctlr *ctlr, int chan_num,
 	spin_lock_init(&chan->lock);
 
 	ctlr->channels[chan_num] = chan;
+	ctlr->chan_num++;
+
+	cpdma_chan_split_pool(ctlr);
+
 	spin_unlock_irqrestore(&ctlr->lock, flags);
 	return chan;
 }
 EXPORT_SYMBOL_GPL(cpdma_chan_create);
 
-int cpdma_chan_get_rx_buf_num(struct cpdma_ctlr *ctlr)
+int cpdma_chan_get_rx_buf_num(struct cpdma_chan *chan)
 {
-	return ctlr->pool->num_desc / 2;
+	unsigned long flags;
+	int desc_num;
+
+	spin_lock_irqsave(&chan->lock, flags);
+	desc_num = chan->desc_num;
+	spin_unlock_irqrestore(&chan->lock, flags);
+
+	return desc_num;
 }
 EXPORT_SYMBOL_GPL(cpdma_chan_get_rx_buf_num);
 
@@ -471,6 +532,10 @@ int cpdma_chan_destroy(struct cpdma_chan *chan)
 	if (chan->state != CPDMA_STATE_IDLE)
 		cpdma_chan_stop(chan);
 	ctlr->channels[chan->chan_num] = NULL;
+	ctlr->chan_num--;
+
+	cpdma_chan_split_pool(ctlr);
+
 	spin_unlock_irqrestore(&ctlr->lock, flags);
 	return 0;
 }

drivers/net/ethernet/ti/davinci_cpdma.h

@@ -17,13 +17,6 @@
 
 #define CPDMA_MAX_CHANNELS	BITS_PER_LONG
 
-#define tx_chan_num(chan)	(chan)
-#define rx_chan_num(chan)	((chan) + CPDMA_MAX_CHANNELS)
-#define is_rx_chan(chan)	((chan)->chan_num >= CPDMA_MAX_CHANNELS)
-#define is_tx_chan(chan)	(!is_rx_chan(chan))
-#define __chan_linear(chan_num)	((chan_num) & (CPDMA_MAX_CHANNELS - 1))
-#define chan_linear(chan)	__chan_linear((chan)->chan_num)
-
 #define CPDMA_RX_SOURCE_PORT(__status__)	((__status__ >> 16) & 0x7)
 
 #define CPDMA_EOI_RX_THRESH	0x0
@@ -79,8 +72,8 @@ int cpdma_ctlr_start(struct cpdma_ctlr *ctlr);
 int cpdma_ctlr_stop(struct cpdma_ctlr *ctlr);
 
 struct cpdma_chan *cpdma_chan_create(struct cpdma_ctlr *ctlr, int chan_num,
-				     cpdma_handler_fn handler);
-int cpdma_chan_get_rx_buf_num(struct cpdma_ctlr *ctlr);
+				     cpdma_handler_fn handler, int rx_type);
+int cpdma_chan_get_rx_buf_num(struct cpdma_chan *chan);
 int cpdma_chan_destroy(struct cpdma_chan *chan);
 int cpdma_chan_start(struct cpdma_chan *chan);
 int cpdma_chan_stop(struct cpdma_chan *chan);
@@ -94,6 +87,8 @@ int cpdma_chan_process(struct cpdma_chan *chan, int quota);
 int cpdma_ctlr_int_ctrl(struct cpdma_ctlr *ctlr, bool enable);
 void cpdma_ctlr_eoi(struct cpdma_ctlr *ctlr, u32 value);
 int cpdma_chan_int_ctrl(struct cpdma_chan *chan, bool enable);
+u32 cpdma_ctrl_rxchs_state(struct cpdma_ctlr *ctlr);
+u32 cpdma_ctrl_txchs_state(struct cpdma_ctlr *ctlr);
 bool cpdma_check_free_tx_desc(struct cpdma_chan *chan);
 
 enum cpdma_control {

drivers/net/ethernet/ti/davinci_emac.c

@@ -1870,10 +1870,10 @@ static int davinci_emac_probe(struct platform_device *pdev)
 		goto no_pdata;
 	}
 
-	priv->txchan = cpdma_chan_create(priv->dma, tx_chan_num(EMAC_DEF_TX_CH),
-				       emac_tx_handler);
-	priv->rxchan = cpdma_chan_create(priv->dma, rx_chan_num(EMAC_DEF_RX_CH),
-				       emac_rx_handler);
+	priv->txchan = cpdma_chan_create(priv->dma, EMAC_DEF_TX_CH,
+					 emac_tx_handler, 0);
+	priv->rxchan = cpdma_chan_create(priv->dma, EMAC_DEF_RX_CH,
+					 emac_rx_handler, 1);
 	if (WARN_ON(!priv->txchan || !priv->rxchan)) {
 		rc = -ENOMEM;
 		goto no_cpdma_chan;