Merge branch 'dsa-ACB-for-bcm_sf2-and-bcmsysport'

Florian Fainelli says:

====================
Enable ACB for bcm_sf2 and bcmsysport

This patch series enables Broadcom's Advanced Congestion Buffering mechanism
which requires cooperation between the CPU/Management Ethernet MAC controller
and the switch.

I took the notifier approach because ultimately the information we need to
carry to the master network device is DSA specific and I saw little room for
generalizing beyond what DSA requires. Chances are that this is highly specific
to the Broadcom HW as I don't know of any HW out there that supports something
nearly similar for similar or identical needs.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/dsa/bcm_sf2.c

@@ -205,6 +205,19 @@ static int bcm_sf2_port_setup(struct dsa_switch *ds, int port,
 	if (port == priv->moca_port)
 		bcm_sf2_port_intr_enable(priv, port);
 
+	/* Set per-queue pause threshold to 32 */
+	core_writel(priv, 32, CORE_TXQ_THD_PAUSE_QN_PORT(port));
+
+	/* Set ACB threshold to 24 */
+	for (i = 0; i < SF2_NUM_EGRESS_QUEUES; i++) {
+		reg = acb_readl(priv, ACB_QUEUE_CFG(port *
+						    SF2_NUM_EGRESS_QUEUES + i));
+		reg &= ~XOFF_THRESHOLD_MASK;
+		reg |= 24;
+		acb_writel(priv, reg, ACB_QUEUE_CFG(port *
+						    SF2_NUM_EGRESS_QUEUES + i));
+	}
+
 	return b53_enable_port(ds, port, phy);
 }
 
@@ -613,6 +626,20 @@ static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port,
 		status->pause = 1;
 }
 
+static void bcm_sf2_enable_acb(struct dsa_switch *ds)
+{
+	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
+	u32 reg;
+
+	/* Enable ACB globally */
+	reg = acb_readl(priv, ACB_CONTROL);
+	reg |= (ACB_FLUSH_MASK << ACB_FLUSH_SHIFT);
+	acb_writel(priv, reg, ACB_CONTROL);
+	reg &= ~(ACB_FLUSH_MASK << ACB_FLUSH_SHIFT);
+	reg |= ACB_EN | ACB_ALGORITHM;
+	acb_writel(priv, reg, ACB_CONTROL);
+}
+
 static int bcm_sf2_sw_suspend(struct dsa_switch *ds)
 {
 	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
@@ -655,6 +682,8 @@ static int bcm_sf2_sw_resume(struct dsa_switch *ds)
 			bcm_sf2_imp_setup(ds, port);
 	}
 
+	bcm_sf2_enable_acb(ds);
+
 	return 0;
 }
 
@@ -766,6 +795,7 @@ static int bcm_sf2_sw_setup(struct dsa_switch *ds)
 	}
 
 	bcm_sf2_sw_configure_vlan(ds);
+	bcm_sf2_enable_acb(ds);
 
 	return 0;
 }

drivers/net/dsa/bcm_sf2_regs.h

@@ -115,6 +115,24 @@ enum bcm_sf2_reg_offs {
 #define P7_IRQ_OFF			0
 #define P_IRQ_OFF(x)			((6 - (x)) * P_NUM_IRQ)
 
+/* Register set relative to 'ACB' */
+#define ACB_CONTROL			0x00
+#define  ACB_EN				(1 << 0)
+#define  ACB_ALGORITHM			(1 << 1)
+#define  ACB_FLUSH_SHIFT		2
+#define  ACB_FLUSH_MASK			0x3
+
+#define ACB_QUEUE_0_CFG			0x08
+#define  XOFF_THRESHOLD_MASK		0x7ff
+#define  XON_EN				(1 << 11)
+#define  TOTAL_XOFF_THRESHOLD_SHIFT	12
+#define  TOTAL_XOFF_THRESHOLD_MASK	0x7ff
+#define  TOTAL_XOFF_EN			(1 << 23)
+#define  TOTAL_XON_EN			(1 << 24)
+#define  PKTLEN_SHIFT			25
+#define  PKTLEN_MASK			0x3f
+#define ACB_QUEUE_CFG(x)		(ACB_QUEUE_0_CFG + ((x) * 0x4))
+
 /* Register set relative to 'CORE' */
 #define CORE_G_PCTL_PORT0		0x00000
 #define CORE_G_PCTL_PORT(x)		(CORE_G_PCTL_PORT0 + (x * 0x4))
@@ -237,6 +255,11 @@ enum bcm_sf2_reg_offs {
 #define CORE_PORT_VLAN_CTL_PORT(x)	(0xc400 + ((x) * 0x8))
 #define  PORT_VLAN_CTRL_MASK		0x1ff
 
+#define CORE_TXQ_THD_PAUSE_QN_PORT_0	0x2c80
+#define  TXQ_PAUSE_THD_MASK		0x7ff
+#define CORE_TXQ_THD_PAUSE_QN_PORT(x)	(CORE_TXQ_THD_PAUSE_QN_PORT_0 + \
+					(x) * 0x8)
+
 #define CORE_DEFAULT_1Q_TAG_P(x)	(0xd040 + ((x) * 8))
 #define  CFI_SHIFT			12
 #define  PRI_SHIFT			13

drivers/net/ethernet/broadcom/bcmsysport.c

@@ -1416,9 +1416,20 @@ static int bcm_sysport_init_tx_ring(struct bcm_sysport_priv *priv,
 	tdma_writel(priv, 0, TDMA_DESC_RING_COUNT(index));
 	tdma_writel(priv, 1, TDMA_DESC_RING_INTR_CONTROL(index));
 	tdma_writel(priv, 0, TDMA_DESC_RING_PROD_CONS_INDEX(index));
-	tdma_writel(priv, RING_IGNORE_STATUS, TDMA_DESC_RING_MAPPING(index));
+
+	/* Configure QID and port mapping */
+	reg = tdma_readl(priv, TDMA_DESC_RING_MAPPING(index));
+	reg &= ~(RING_QID_MASK | RING_PORT_ID_MASK << RING_PORT_ID_SHIFT);
+	reg |= ring->switch_queue & RING_QID_MASK;
+	reg |= ring->switch_port << RING_PORT_ID_SHIFT;
+	tdma_writel(priv, reg, TDMA_DESC_RING_MAPPING(index));
 	tdma_writel(priv, 0, TDMA_DESC_RING_PCP_DEI_VID(index));
 
+	/* Enable ACB algorithm 2 */
+	reg = tdma_readl(priv, TDMA_CONTROL);
+	reg |= tdma_control_bit(priv, ACB_ALGO);
+	tdma_writel(priv, reg, TDMA_CONTROL);
+
 	/* Do not use tdma_control_bit() here because TSB_SWAP1 collides
 	 * with the original definition of ACB_ALGO
 	 */
@@ -1447,8 +1458,9 @@ static int bcm_sysport_init_tx_ring(struct bcm_sysport_priv *priv,
 	napi_enable(&ring->napi);
 
 	netif_dbg(priv, hw, priv->netdev,
-		  "TDMA cfg, size=%d, desc_cpu=%p\n",
-		  ring->size, ring->desc_cpu);
+		  "TDMA cfg, size=%d, desc_cpu=%p switch q=%d,port=%d\n",
+		  ring->size, ring->desc_cpu, ring->switch_queue,
+		  ring->switch_port);
 
 	return 0;
 }
@@ -2011,6 +2023,92 @@ static const struct ethtool_ops bcm_sysport_ethtool_ops = {
 	.set_link_ksettings     = phy_ethtool_set_link_ksettings,
 };
 
+static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb,
+				    void *accel_priv,
+				    select_queue_fallback_t fallback)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	u16 queue = skb_get_queue_mapping(skb);
+	struct bcm_sysport_tx_ring *tx_ring;
+	unsigned int q, port;
+
+	if (!netdev_uses_dsa(dev))
+		return fallback(dev, skb);
+
+	/* DSA tagging layer will have configured the correct queue */
+	q = BRCM_TAG_GET_QUEUE(queue);
+	port = BRCM_TAG_GET_PORT(queue);
+	tx_ring = priv->ring_map[q + port * priv->per_port_num_tx_queues];
+
+	return tx_ring->index;
+}
+
+static int bcm_sysport_map_queues(struct net_device *dev,
+				  struct dsa_notifier_register_info *info)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	struct bcm_sysport_tx_ring *ring;
+	struct net_device *slave_dev;
+	unsigned int num_tx_queues;
+	unsigned int q, start, port;
+
+	/* We can't be setting up queue inspection for non directly attached
+	 * switches
+	 */
+	if (info->switch_number)
+		return 0;
+
+	port = info->port_number;
+	slave_dev = info->info.dev;
+
+	/* On SYSTEMPORT Lite we have twice as less queues, so we cannot do a
+	 * 1:1 mapping, we can only do a 2:1 mapping. By reducing the number of
+	 * per-port (slave_dev) network devices queue, we achieve just that.
+	 * This need to happen now before any slave network device is used such
+	 * it accurately reflects the number of real TX queues.
+	 */
+	if (priv->is_lite)
+		netif_set_real_num_tx_queues(slave_dev,
+					     slave_dev->num_tx_queues / 2);
+	num_tx_queues = slave_dev->real_num_tx_queues;
+
+	if (priv->per_port_num_tx_queues &&
+	    priv->per_port_num_tx_queues != num_tx_queues)
+		netdev_warn(slave_dev, "asymetric number of per-port queues\n");
+
+	priv->per_port_num_tx_queues = num_tx_queues;
+
+	start = find_first_zero_bit(&priv->queue_bitmap, dev->num_tx_queues);
+	for (q = 0; q < num_tx_queues; q++) {
+		ring = &priv->tx_rings[q + start];
+
+		/* Just remember the mapping actual programming done
+		 * during bcm_sysport_init_tx_ring
+		 */
+		ring->switch_queue = q;
+		ring->switch_port = port;
+		priv->ring_map[q + port * num_tx_queues] = ring;
+
+		/* Set all queues as being used now */
+		set_bit(q + start, &priv->queue_bitmap);
+	}
+
+	return 0;
+}
+
+static int bcm_sysport_dsa_notifier(struct notifier_block *unused,
+				    unsigned long event, void *ptr)
+{
+	struct dsa_notifier_register_info *info;
+
+	if (event != DSA_PORT_REGISTER)
+		return NOTIFY_DONE;
+
+	info = ptr;
+
+	return notifier_from_errno(bcm_sysport_map_queues(info->master, info));
+}
+
 static const struct net_device_ops bcm_sysport_netdev_ops = {
 	.ndo_start_xmit		= bcm_sysport_xmit,
 	.ndo_tx_timeout		= bcm_sysport_tx_timeout,
@@ -2023,6 +2121,7 @@ static const struct net_device_ops bcm_sysport_netdev_ops = {
 	.ndo_poll_controller	= bcm_sysport_poll_controller,
 #endif
 	.ndo_get_stats64	= bcm_sysport_get_stats64,
+	.ndo_select_queue	= bcm_sysport_select_queue,
 };
 
 #define REV_FMT	"v%2x.%02x"
@@ -2172,10 +2271,18 @@ static int bcm_sysport_probe(struct platform_device *pdev)
 
 	u64_stats_init(&priv->syncp);
 
+	priv->dsa_notifier.notifier_call = bcm_sysport_dsa_notifier;
+
+	ret = register_dsa_notifier(&priv->dsa_notifier);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to register DSA notifier\n");
+		goto err_deregister_fixed_link;
+	}
+
 	ret = register_netdev(dev);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to register net_device\n");
-		goto err_deregister_fixed_link;
+		goto err_deregister_notifier;
 	}
 
 	priv->rev = topctrl_readl(priv, REV_CNTL) & REV_MASK;
@@ -2188,6 +2295,8 @@ static int bcm_sysport_probe(struct platform_device *pdev)
 
 	return 0;
 
+err_deregister_notifier:
+	unregister_dsa_notifier(&priv->dsa_notifier);
 err_deregister_fixed_link:
 	if (of_phy_is_fixed_link(dn))
 		of_phy_deregister_fixed_link(dn);
@@ -2199,11 +2308,13 @@ err_free_netdev:
 static int bcm_sysport_remove(struct platform_device *pdev)
 {
 	struct net_device *dev = dev_get_drvdata(&pdev->dev);
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
 	struct device_node *dn = pdev->dev.of_node;
 
 	/* Not much to do, ndo_close has been called
 	 * and we use managed allocations
 	 */
+	unregister_dsa_notifier(&priv->dsa_notifier);
 	unregister_netdev(dev);
 	if (of_phy_is_fixed_link(dn))
 		of_phy_deregister_fixed_link(dn);

drivers/net/ethernet/broadcom/bcmsysport.h

@@ -404,7 +404,7 @@ struct bcm_rsb {
 #define  RING_CONS_INDEX_MASK		0xffff
 
 #define RING_MAPPING			0x14
-#define  RING_QID_MASK			0x3
+#define  RING_QID_MASK			0x7
 #define  RING_PORT_ID_SHIFT		3
 #define  RING_PORT_ID_MASK		0x7
 #define  RING_IGNORE_STATUS		(1 << 6)
@@ -712,6 +712,8 @@ struct bcm_sysport_tx_ring {
 	struct bcm_sysport_priv *priv;	/* private context backpointer */
 	unsigned long	packets;	/* packets statistics */
 	unsigned long	bytes;		/* bytes statistics */
+	unsigned int	switch_queue;	/* switch port queue number */
+	unsigned int	switch_port;	/* switch port queue number */
 };
 
 /* Driver private structure */
@@ -765,5 +767,12 @@ struct bcm_sysport_priv {
 
 	/* For atomic update generic 64bit value on 32bit Machine */
 	struct u64_stats_sync	syncp;
+
+	/* map information between switch port queues and local queues */
+	struct notifier_block	dsa_notifier;
+	unsigned int		per_port_num_tx_queues;
+	unsigned long		queue_bitmap;
+	struct bcm_sysport_tx_ring *ring_map[DSA_MAX_PORTS * 8];
+
 };
 #endif /* __BCM_SYSPORT_H */

include/net/dsa.h

@@ -471,4 +471,54 @@ static inline int dsa_switch_resume(struct dsa_switch *ds)
 }
 #endif /* CONFIG_PM_SLEEP */
 
+enum dsa_notifier_type {
+	DSA_PORT_REGISTER,
+	DSA_PORT_UNREGISTER,
+};
+
+struct dsa_notifier_info {
+	struct net_device *dev;
+};
+
+struct dsa_notifier_register_info {
+	struct dsa_notifier_info info;	/* must be first */
+	struct net_device *master;
+	unsigned int port_number;
+	unsigned int switch_number;
+};
+
+static inline struct net_device *
+dsa_notifier_info_to_dev(const struct dsa_notifier_info *info)
+{
+	return info->dev;
+}
+
+#if IS_ENABLED(CONFIG_NET_DSA)
+int register_dsa_notifier(struct notifier_block *nb);
+int unregister_dsa_notifier(struct notifier_block *nb);
+int call_dsa_notifiers(unsigned long val, struct net_device *dev,
+		       struct dsa_notifier_info *info);
+#else
+static inline int register_dsa_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline int unregister_dsa_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline int call_dsa_notifiers(unsigned long val, struct net_device *dev,
+				     struct dsa_notifier_info *info)
+{
+	return NOTIFY_DONE;
+}
+#endif
+
+/* Broadcom tag specific helpers to insert and extract queue/port number */
+#define BRCM_TAG_SET_PORT_QUEUE(p, q)	((p) << 8 | q)
+#define BRCM_TAG_GET_PORT(v)		((v) >> 8)
+#define BRCM_TAG_GET_QUEUE(v)		((v) & 0xff)
+
 #endif

net/dsa/dsa.c

@@ -14,6 +14,7 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/notifier.h>
 #include <linux/of.h>
 #include <linux/of_mdio.h>
 #include <linux/of_platform.h>
@@ -261,6 +262,28 @@ bool dsa_schedule_work(struct work_struct *work)
 	return queue_work(dsa_owq, work);
 }
 
+static ATOMIC_NOTIFIER_HEAD(dsa_notif_chain);
+
+int register_dsa_notifier(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_register(&dsa_notif_chain, nb);
+}
+EXPORT_SYMBOL_GPL(register_dsa_notifier);
+
+int unregister_dsa_notifier(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_unregister(&dsa_notif_chain, nb);
+}
+EXPORT_SYMBOL_GPL(unregister_dsa_notifier);
+
+int call_dsa_notifiers(unsigned long val, struct net_device *dev,
+		       struct dsa_notifier_info *info)
+{
+	info->dev = dev;
+	return atomic_notifier_call_chain(&dsa_notif_chain, val, info);
+}
+EXPORT_SYMBOL_GPL(call_dsa_notifiers);
+
 static int __init dsa_init_module(void)
 {
 	int rc;

net/dsa/slave.c

@@ -1116,6 +1116,7 @@ int dsa_slave_resume(struct net_device *slave_dev)
 
 int dsa_slave_create(struct dsa_port *port, const char *name)
 {
+	struct dsa_notifier_register_info rinfo = { };
 	struct dsa_switch *ds = port->ds;
 	struct net_device *master;
 	struct net_device *slave_dev;
@@ -1177,6 +1178,12 @@ int dsa_slave_create(struct dsa_port *port, const char *name)
 		goto out_free;
 	}
 
+	rinfo.info.dev = slave_dev;
+	rinfo.master = master;
+	rinfo.port_number = p->dp->index;
+	rinfo.switch_number = p->dp->ds->index;
+	call_dsa_notifiers(DSA_PORT_REGISTER, slave_dev, &rinfo.info);
+
 	ret = register_netdev(slave_dev);
 	if (ret) {
 		netdev_err(master, "error %d registering interface %s\n",
@@ -1200,6 +1207,7 @@ out_free:
 void dsa_slave_destroy(struct net_device *slave_dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(slave_dev);
+	struct dsa_notifier_register_info rinfo = { };
 	struct device_node *port_dn;
 
 	port_dn = p->dp->dn;
@@ -1211,6 +1219,11 @@ void dsa_slave_destroy(struct net_device *slave_dev)
 		if (of_phy_is_fixed_link(port_dn))
 			of_phy_deregister_fixed_link(port_dn);
 	}
+	rinfo.info.dev = slave_dev;
+	rinfo.master = p->dp->cpu_dp->netdev;
+	rinfo.port_number = p->dp->index;
+	rinfo.switch_number = p->dp->ds->index;
+	call_dsa_notifiers(DSA_PORT_UNREGISTER, slave_dev, &rinfo.info);
 	unregister_netdev(slave_dev);
 	free_percpu(p->stats64);
 	free_netdev(slave_dev);

net/dsa/tag_brcm.c

@@ -86,6 +86,12 @@ static struct sk_buff *brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev
 		brcm_tag[2] = BRCM_IG_DSTMAP2_MASK;
 	brcm_tag[3] = (1 << p->dp->index) & BRCM_IG_DSTMAP1_MASK;
 
+	/* Now tell the master network device about the desired output queue
+	 * as well
+	 */
+	skb_set_queue_mapping(skb, BRCM_TAG_SET_PORT_QUEUE(p->dp->index,
+							   queue));
+
 	return skb;
 }