[PATCH net-next v6 8/9] net: bcmgenet: allow the MTU to be changed

[Nicolai Buchwitz]

The driver never sets dev->max_mtu, so the MTU is stuck at ETH_DATA_LEN.

One descriptor reaches as far as the packet ready threshold, so derive the
maximum from it. The threshold registers are 8 bit in units of 16 bytes and
want a multiple of the 256 byte burst size. A descriptor is one page and
also holds skb_shared_info behind the frame. On 4K pages the page is the
tighter limit and leaves 3564 bytes. That includes room for a VLAN tag so a
VLAN interface can run at the parent MTU. The MAC accepts a little more
than one descriptor holds, so a double tagged frame at that maximum is
dropped as fragmented until a later patch reassembles those.

The PHY keeps running across the change so the link stays up, with its
lock held so that a link event cannot enable the MAC while the registers
change. Two MTUs at or below ETH_DATA_LEN derive the same values, so a
change between them needs no restart at all.

Only a DMA that refuses to halt still takes the interface down, nothing is
left to run on then.

Suggested-by: Dave Stevenson <dave.stevenson@xxxxxxxxxxxxxxx>
Link: https://github.com/raspberrypi/linux/issues/5561
Signed-off-by: Nicolai Buchwitz <nb@xxxxxxxxxxx>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 88 ++++++++++++++++++++++++++
 1 file changed, 88 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index f6ed15bb1a91c..e42de63fac14d 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -84,6 +84,12 @@
 				      ENET_THLD_MAX * ENET_THLD_UNIT, \
 				      ENET_THLD_PAGE_LEN)
 
+/* Largest MTU that fits one descriptor, with room for a VLAN tag so a VLAN
+ * interface can use the parent MTU.
+ */
+#define ENET_MAX_MTU		(ENET_THLD_MAX_LEN - GENET_RBUF_ALIGN - \
+				 ETH_HLEN - VLAN_HLEN)
+
 /* Tx/Rx DMA register offset, skip 256 descriptors */
 #define WORDS_PER_BD(p)		(p->hw_params->words_per_bd)
 #define DMA_DESC_SIZE		(WORDS_PER_BD(priv) * sizeof(u32))
@@ -3965,6 +3971,81 @@ static int bcmgenet_change_carrier(struct net_device *dev, bool new_carrier)
 	return 0;
 }
 
+static int bcmgenet_change_mtu(struct net_device *dev, int new_mtu)
+{
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+	unsigned int old_mtu = dev->mtu;
+	struct bcmgenet_dma_set set;
+	int ret;
+
+	/* Below ETH_DATA_LEN everything is floored, so there is nothing to
+	 * reprogram. Same when a failed resume left the datapath down.
+	 */
+	if (!netif_running(dev) || !priv->tx_cbs ||
+	    max_t(unsigned int, old_mtu, ETH_DATA_LEN) ==
+	    max_t(unsigned int, new_mtu, ETH_DATA_LEN)) {
+		WRITE_ONCE(dev->mtu, new_mtu);
+		priv->rx_buf_len = bcmgenet_rx_buf_len(new_mtu);
+		return 0;
+	}
+
+	ret = bcmgenet_alloc_dma(priv, bcmgenet_rx_buf_len(new_mtu), &set);
+	if (ret)
+		return ret;
+
+	/* The watchdog trips on an idle queue once the rings are gone */
+	netif_device_detach(dev);
+
+	/* The PHY stays up, hold its lock. A link event would otherwise take
+	 * the MAC out of reset and enable it mid rewrite.
+	 */
+	mutex_lock(&dev->phydev->lock);
+	bcmgenet_netif_stop(dev, false);
+
+	WRITE_ONCE(dev->mtu, new_mtu);
+	priv->rx_buf_len = bcmgenet_rx_buf_len(new_mtu);
+	bcmgenet_set_mtu_regs(priv, new_mtu);
+
+	ret = bcmgenet_init_dma(priv, true, &set);
+	if (ret) {
+		/* Take it down here, or close and suspend tear it down twice */
+		netdev_err(dev, "failed to initialize DMA, closing\n");
+		WRITE_ONCE(dev->mtu, old_mtu);
+		priv->rx_buf_len = bcmgenet_rx_buf_len(old_mtu);
+		mutex_unlock(&dev->phydev->lock);
+		netif_close(dev);
+
+		/* __dev_open() refuses a detached device */
+		netif_device_attach(dev);
+		return ret;
+	}
+
+	bcmgenet_hfb_restore(priv);
+	bcmgenet_netif_start(dev, false);
+	mutex_unlock(&dev->phydev->lock);
+
+	/* bcmgenet_netif_start() only restores the link interrupt */
+	if (bcmgenet_has_mdio_intr(priv))
+		bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_MDIO_EVENT,
+					 INTRL2_CPU_MASK_CLEAR);
+
+	/* Interrupts were off, so a latched link event is lost. Internal PHYs
+	 * on v1-v4 are not polled either.
+	 */
+	phy_mac_interrupt(dev->phydev);
+
+	netif_device_attach(dev);
+
+	/* Filter updates that came in while the device was detached got
+	 * dropped. An IPv6 join does not hold RTNL.
+	 */
+	netif_addr_lock_bh(dev);
+	bcmgenet_set_rx_mode(dev);
+	netif_addr_unlock_bh(dev);
+
+	return 0;
+}
+
 static const struct net_device_ops bcmgenet_netdev_ops = {
 	.ndo_open		= bcmgenet_open,
 	.ndo_stop		= bcmgenet_close,
@@ -3976,6 +4057,7 @@ static const struct net_device_ops bcmgenet_netdev_ops = {
 	.ndo_set_features	= bcmgenet_set_features,
 	.ndo_get_stats64	= bcmgenet_get_stats64,
 	.ndo_change_carrier	= bcmgenet_change_carrier,
+	.ndo_change_mtu		= bcmgenet_change_mtu,
 };
 
 /* GENET hardware parameters/characteristics */
@@ -4329,8 +4411,14 @@ static int bcmgenet_probe(struct platform_device *pdev)
 	/* Mii wait queue */
 	init_waitqueue_head(&priv->wq);
 	bcmgenet_hfb_init(priv);
+
 	priv->rx_buf_len = bcmgenet_rx_buf_len(dev->mtu);
 	priv->tx_thld_len = bcmgenet_tx_pkt_rdy_thld(dev->mtu) * ENET_THLD_UNIT;
+
+	/* v1 cannot program the thresholds, so it stays at the default MTU */
+	if (!GENET_IS_V1(priv))
+		dev->max_mtu = ENET_MAX_MTU;
+
 	INIT_WORK(&priv->bcmgenet_irq_work, bcmgenet_irq_task);
 
 	priv->clk_wol = devm_clk_get_optional(&priv->pdev->dev, "enet-wol");

-- 
2.53.0