net: cadence: macb: implement EEE TX LPI support

commit 0cc425f upstream

The GEM MAC has hardware LPI registers (NCR bit 19: TXLPIEN) but no
built-in idle timer, so asserting TXLPIEN blocks all TX immediately
with no automatic wake. A software idle timer is required, as noted
in Microchip documentation (section 40.6.19): "It is best to use
firmware to control LPI."

Implement phylink managed EEE using the mac_enable_tx_lpi and
mac_disable_tx_lpi callbacks:

- macb_tx_lpi_set(): sets or clears TXLPIEN; requires bp->lock to be
  held by the caller (asserted with lockdep_assert_held). Returns bool
  indicating whether the register actually changed, avoiding redundant
  writes and unnecessary udelay on the xmit fast path.

- macb_tx_lpi_work_fn(): delayed_work handler that enters LPI if all
  TX queues are idle and EEE is still active. Takes bp->lock with
  irqsave before calling macb_tx_lpi_set().

- macb_tx_lpi_schedule(): arms the work timer using the LPI timer
  value provided by phylink (default 250 ms). Called from
  macb_tx_complete() after each TX drain so the idle countdown
  restarts whenever the ring goes quiet.

- macb_tx_lpi_wake(): called from macb_start_xmit() under bp->lock,
  immediately before TSTART. Returns early if eee_active is false to
  avoid a register read on the common path when EEE is disabled.
  Clears TXLPIEN and applies a 50 us udelay for PHY wake (IEEE
  802.3az Tw_sys_tx is 16.5 us for 1000BASE-T / 30 us for
  100BASE-TX; GEM has no hardware enforcement). Only delays when
  TXLPIEN was actually set. The delay is placed after tx_head is
  advanced so the work_fn's queue-idle check sees a non-empty ring
  and cannot race back into LPI before the frame is transmitted.

- mac_enable_tx_lpi: stores the timer and sets eee_active under
  bp->lock, then defers the first LPI entry by 1 second per IEEE
  802.3az section 22.7a.

- mac_disable_tx_lpi: cancels the work (sync, without the lock to
  avoid deadlock with the work_fn), then takes bp->lock to clear
  eee_active and deassert TXLPIEN.

Populate phylink_config lpi_interfaces (MII, GMII, RGMII variants)
and lpi_capabilities (MAC_100FD | MAC_1000FD) so phylink can
negotiate EEE with the PHY and call the callbacks appropriately.
Set lpi_timer_default to 250000 us and eee_enabled_default to true.

Reviewed-by: Claudiu Beznea <claudiu.beznea@tuxon.dev>
Reviewed-by: Théo Lebrun <theo.lebrun@bootlin.com>
Signed-off-by: Nicolai Buchwitz <nb@tipi-net.de>

Author: nbuchwitz

drivers/net/ethernet/cadence/macb.h

@@ -315,6 +315,8 @@
 #define MACB_IRXFCS_SIZE	1
 
 /* GEM specific NCR bitfields. */
+#define GEM_TXLPIEN_OFFSET		19
+#define GEM_TXLPIEN_SIZE		1
 #define GEM_ENABLE_HS_MAC_OFFSET	31
 #define GEM_ENABLE_HS_MAC_SIZE		1
 
@@ -790,6 +792,7 @@
 #define MACB_CAPS_NEED_TSUCLK			0x00000400
 #define MACB_CAPS_QUEUE_DISABLE			0x00000800
 #define MACB_CAPS_QBV				0x00001000
+#define MACB_CAPS_EEE				0x00002000
 #define MACB_CAPS_PCS				0x01000000
 #define MACB_CAPS_HIGH_SPEED			0x02000000
 #define MACB_CAPS_CLK_HW_CHG			0x04000000
@@ -1403,6 +1406,11 @@ struct macb {
 
 	struct work_struct	hresp_err_bh_work;
 
+	/* EEE / LPI state */
+	bool			eee_active;
+	struct delayed_work	tx_lpi_work;
+	u32			tx_lpi_timer;
+
 	int	rx_bd_rd_prefetch;
 	int	tx_bd_rd_prefetch;
 

drivers/net/ethernet/cadence/macb_main.c

@@ -9,6 +9,7 @@
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/crc32.h>
+#include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/kernel.h>
@@ -642,6 +643,107 @@ static const struct phylink_pcs_ops macb_phylink_pcs_ops = {
 	.pcs_config = macb_pcs_config,
 };
 
+static bool macb_tx_lpi_set(struct macb *bp, bool enable)
+{
+	u32 old, ncr;
+
+	lockdep_assert_held(&bp->lock);
+
+	ncr = macb_readl(bp, NCR);
+	old = ncr;
+	if (enable)
+		ncr |= GEM_BIT(TXLPIEN);
+	else
+		ncr &= ~GEM_BIT(TXLPIEN);
+	if (old != ncr)
+		macb_writel(bp, NCR, ncr);
+
+	return old != ncr;
+}
+
+static bool macb_tx_all_queues_idle(struct macb *bp)
+{
+	struct macb_queue *queue;
+	unsigned int q;
+
+	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
+		if (READ_ONCE(queue->tx_head) != READ_ONCE(queue->tx_tail))
+			return false;
+	}
+	return true;
+}
+
+static void macb_tx_lpi_work_fn(struct work_struct *work)
+{
+	struct macb *bp = container_of(work, struct macb, tx_lpi_work.work);
+	unsigned long flags;
+
+	spin_lock_irqsave(&bp->lock, flags);
+	if (bp->eee_active && macb_tx_all_queues_idle(bp))
+		macb_tx_lpi_set(bp, true);
+	spin_unlock_irqrestore(&bp->lock, flags);
+}
+
+static void macb_tx_lpi_schedule(struct macb *bp)
+{
+	if (bp->eee_active)
+		mod_delayed_work(system_wq, &bp->tx_lpi_work,
+				 usecs_to_jiffies(bp->tx_lpi_timer));
+}
+
+/* Wake from LPI before transmitting. The MAC must deassert TXLPIEN
+ * and wait for the PHY to exit LPI before any frame can be sent.
+ * IEEE 802.3az Tw_sys is ~17us for 1000BASE-T, ~30us for 100BASE-TX;
+ * we use a conservative 50us.
+ */
+static void macb_tx_lpi_wake(struct macb *bp)
+{
+	lockdep_assert_held(&bp->lock);
+
+	if (!bp->eee_active)
+		return;
+
+	if (!macb_tx_lpi_set(bp, false))
+		return;
+
+	cancel_delayed_work(&bp->tx_lpi_work);
+	udelay(50);
+}
+
+static void macb_mac_disable_tx_lpi(struct phylink_config *config)
+{
+	struct net_device *ndev = to_net_dev(config->dev);
+	struct macb *bp = netdev_priv(ndev);
+	unsigned long flags;
+
+	cancel_delayed_work_sync(&bp->tx_lpi_work);
+
+	spin_lock_irqsave(&bp->lock, flags);
+	bp->eee_active = false;
+	macb_tx_lpi_set(bp, false);
+	spin_unlock_irqrestore(&bp->lock, flags);
+}
+
+static int macb_mac_enable_tx_lpi(struct phylink_config *config, u32 timer,
+				  bool tx_clk_stop)
+{
+	struct net_device *ndev = to_net_dev(config->dev);
+	struct macb *bp = netdev_priv(ndev);
+	unsigned long flags;
+
+	spin_lock_irqsave(&bp->lock, flags);
+	bp->tx_lpi_timer = timer;
+	bp->eee_active = true;
+	spin_unlock_irqrestore(&bp->lock, flags);
+
+	/* Defer initial LPI entry by 1 second after link-up per
+	 * IEEE 802.3az section 22.7a.
+	 */
+	mod_delayed_work(system_wq, &bp->tx_lpi_work, msecs_to_jiffies(1000));
+
+	return 0;
+}
+
 static void macb_mac_config(struct phylink_config *config, unsigned int mode,
 			    const struct phylink_link_state *state)
 {
@@ -806,6 +908,8 @@ static const struct phylink_mac_ops macb_phylink_ops = {
 	.mac_config = macb_mac_config,
 	.mac_link_down = macb_mac_link_down,
 	.mac_link_up = macb_mac_link_up,
+	.mac_disable_tx_lpi = macb_mac_disable_tx_lpi,
+	.mac_enable_tx_lpi = macb_mac_enable_tx_lpi,
 };
 
 static bool macb_phy_handle_exists(struct device_node *dn)
@@ -901,6 +1005,18 @@ static int macb_mii_probe(struct net_device *dev)
 		}
 	}
 
+	/* Configure EEE LPI if supported */
+	if (bp->caps & MACB_CAPS_EEE) {
+		__set_bit(PHY_INTERFACE_MODE_MII,
+			  bp->phylink_config.lpi_interfaces);
+		__set_bit(PHY_INTERFACE_MODE_GMII,
+			  bp->phylink_config.lpi_interfaces);
+		phy_interface_set_rgmii(bp->phylink_config.lpi_interfaces);
+		bp->phylink_config.lpi_capabilities = MAC_100FD | MAC_1000FD;
+		bp->phylink_config.lpi_timer_default = 250000;
+		bp->phylink_config.eee_enabled_default = true;
+	}
+
 	bp->phylink = phylink_create(&bp->phylink_config, bp->pdev->dev.fwnode,
 				     bp->phy_interface, &macb_phylink_ops);
 	if (IS_ERR(bp->phylink)) {
@@ -1302,6 +1418,9 @@ static int macb_tx_complete(struct macb_queue *queue, int budget)
 		netif_wake_subqueue(bp->dev, queue_index);
 	spin_unlock_irqrestore(&queue->tx_ptr_lock, flags);
 
+	if (packets)
+		macb_tx_lpi_schedule(bp);
+
 	return packets;
 }
 
@@ -2411,6 +2530,7 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			     skb->len);
 
 	spin_lock(&bp->lock);
+	macb_tx_lpi_wake(bp);
 
 	/* TSTART write might get dropped, so make the IRQ retrigger a buffer read */
 	if (macb_readl(bp, TSR) & MACB_BIT(TGO))
@@ -3108,6 +3228,8 @@ static int macb_close(struct net_device *dev)
 		netdev_tx_reset_queue(netdev_get_tx_queue(dev, q));
 	}
 
+	cancel_delayed_work_sync(&bp->tx_lpi_work);
+
 	phylink_stop(bp->phylink);
 	phylink_disconnect_phy(bp->phylink);
 
@@ -5746,6 +5868,7 @@ static int macb_probe(struct platform_device *pdev)
 	}
 
 	INIT_WORK(&bp->hresp_err_bh_work, macb_hresp_error_task);
+	INIT_DELAYED_WORK(&bp->tx_lpi_work, macb_tx_lpi_work_fn);
 
 	netdev_info(dev, "Cadence %s rev 0x%08x at 0x%08lx irq %d (%pM)\n",
 		    macb_is_gem(bp) ? "GEM" : "MACB", macb_readl(bp, MID),
@@ -5790,6 +5913,7 @@ static void macb_remove(struct platform_device *pdev)
 		mdiobus_free(bp->mii_bus);
 
 		device_set_wakeup_enable(&bp->pdev->dev, 0);
+		cancel_delayed_work_sync(&bp->tx_lpi_work);
 		cancel_work_sync(&bp->hresp_err_bh_work);
 		pm_runtime_disable(&pdev->dev);
 		pm_runtime_dont_use_autosuspend(&pdev->dev);