[PATCH net-next v6 11/14] net: lan966x: add PCIe FDMA MTU change support

[Daniel Machon]

Add MTU change support for the PCIe FDMA path. When the MTU changes,
the contiguous ATU-mapped RX and TX buffers are reallocated with the
new size. On allocation failure, the existing buffers are reused
after being reset.

Cap the PCIe DCB ring at 256 (FDMA_PCI_DCB_MAX) to keep the entire
contiguous allocation under MAX_PAGE_ORDER at jumbo MTU, which 512
DCBs would overflow.

Tested-by: Herve Codina <herve.codina@xxxxxxxxxxx>
Signed-off-by: Daniel Machon <daniel.machon@xxxxxxxxxxxxx>
---
 .../ethernet/microchip/lan966x/lan966x_fdma_pci.c  | 168 ++++++++++++++++++++-
 1 file changed, 165 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma_pci.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma_pci.c
index f1f3c789d3a6..6cabbb8b47f2 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma_pci.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma_pci.c
@@ -1,8 +1,15 @@
 // SPDX-License-Identifier: GPL-2.0+
 
+#include <linux/mmzone.h>
+
 #include "fdma_api.h"
 #include "lan966x_main.h"
 
+/* Ring must fit in one MAX_PAGE_ORDER DMA block; 512 DCBs overflows
+ * at jumbo MTU.
+ */
+#define FDMA_PCI_DCB_MAX	256
+
 static int lan966x_fdma_pci_dataptr_cb(struct fdma *fdma, int dcb, int db,
 				       u64 *dataptr)
 {
@@ -341,7 +348,7 @@ static int lan966x_fdma_pci_init(struct lan966x *lan966x)
 	lan966x->rx.lan966x = lan966x;
 	lan966x->rx.max_mtu = lan966x_fdma_get_max_frame(lan966x);
 	rx_fdma->channel_id = FDMA_XTR_CHANNEL;
-	rx_fdma->n_dcbs = FDMA_DCB_MAX;
+	rx_fdma->n_dcbs = FDMA_PCI_DCB_MAX;
 	rx_fdma->n_dbs = FDMA_RX_DCB_MAX_DBS;
 	rx_fdma->priv = lan966x;
 	rx_fdma->db_size = FDMA_PCI_DB_SIZE(lan966x->rx.max_mtu);
@@ -351,7 +358,7 @@ static int lan966x_fdma_pci_init(struct lan966x *lan966x)
 
 	lan966x->tx.lan966x = lan966x;
 	tx_fdma->channel_id = FDMA_INJ_CHANNEL;
-	tx_fdma->n_dcbs = FDMA_DCB_MAX;
+	tx_fdma->n_dcbs = FDMA_PCI_DCB_MAX;
 	tx_fdma->n_dbs = FDMA_TX_DCB_MAX_DBS;
 	tx_fdma->priv = lan966x;
 	tx_fdma->db_size = FDMA_PCI_DB_SIZE(lan966x->rx.max_mtu);
@@ -374,9 +381,164 @@ static int lan966x_fdma_pci_init(struct lan966x *lan966x)
 	return 0;
 }
 
+/* Reset existing rx and tx buffers. */
+static void lan966x_fdma_pci_reset_mem(struct lan966x *lan966x)
+{
+	struct lan966x_rx *rx = &lan966x->rx;
+	struct lan966x_tx *tx = &lan966x->tx;
+
+	memset(rx->fdma.dcbs, 0, rx->fdma.size);
+	memset(tx->fdma.dcbs, 0, tx->fdma.size);
+
+	fdma_dcbs_init(&rx->fdma,
+		       FDMA_DCB_INFO_DATAL(rx->fdma.db_size - XDP_PACKET_HEADROOM),
+		       FDMA_DCB_STATUS_INTR);
+
+	fdma_dcbs_init(&tx->fdma,
+		       FDMA_DCB_INFO_DATAL(tx->fdma.db_size),
+		       FDMA_DCB_STATUS_DONE);
+
+	lan966x_fdma_llp_configure(lan966x,
+				   tx->fdma.atu_region->base_addr,
+				   tx->fdma.channel_id);
+	lan966x_fdma_llp_configure(lan966x,
+				   rx->fdma.atu_region->base_addr,
+				   rx->fdma.channel_id);
+}
+
+/* Wake all TX queues on every port (undoes lan966x_fdma_tx_disable_netdev). */
+static void lan966x_fdma_pci_wakeup_netdev(struct lan966x *lan966x)
+{
+	for (int i = 0; i < lan966x->num_phys_ports; ++i) {
+		struct lan966x_port *port = lan966x->ports[i];
+
+		if (port)
+			netif_tx_wake_all_queues(port->dev);
+	}
+}
+
+static int lan966x_fdma_pci_reload(struct lan966x *lan966x, int new_mtu)
+{
+	struct fdma tx_fdma_old = lan966x->tx.fdma;
+	struct fdma rx_fdma_old = lan966x->rx.fdma;
+	u32 old_mtu = lan966x->rx.max_mtu;
+	int err;
+
+	napi_disable(&lan966x->napi);
+	lan966x_fdma_tx_disable_netdev(lan966x);
+	lan966x_fdma_rx_disable(&lan966x->rx);
+	lan966x_fdma_tx_disable(&lan966x->tx);
+
+	lan966x->rx.max_mtu = new_mtu;
+
+	/* Must be NULL'ed in order to realloc them. */
+	lan966x->rx.fdma.atu_region = NULL;
+	lan966x->tx.fdma.atu_region = NULL;
+
+	lan966x->tx.fdma.db_size = FDMA_PCI_DB_SIZE(lan966x->rx.max_mtu);
+	lan966x->tx.fdma.size = fdma_get_size_contiguous(&lan966x->tx.fdma);
+	lan966x->rx.fdma.db_size = FDMA_PCI_DB_SIZE(lan966x->rx.max_mtu);
+	lan966x->rx.fdma.size = fdma_get_size_contiguous(&lan966x->rx.fdma);
+
+	err = lan966x_fdma_pci_rx_alloc(&lan966x->rx);
+	if (err)
+		goto restore;
+
+	err = lan966x_fdma_pci_tx_alloc(&lan966x->tx);
+	if (err) {
+		fdma_free_coherent_and_unmap(lan966x->dma_dev,
+					     &lan966x->rx.fdma);
+		goto restore;
+	}
+
+	/* Free and unmap old memory. */
+	fdma_free_coherent_and_unmap(lan966x->dma_dev, &rx_fdma_old);
+	fdma_free_coherent_and_unmap(lan966x->dma_dev, &tx_fdma_old);
+
+	napi_enable(&lan966x->napi);
+	lan966x_fdma_rx_start(&lan966x->rx);
+	lan966x_fdma_pci_wakeup_netdev(lan966x);
+
+	return err;
+restore:
+
+	/* No new buffers are allocated at this point. Use the old buffers,
+	 * but reset them before starting the FDMA again.
+	 */
+
+	memcpy(&lan966x->tx.fdma, &tx_fdma_old, sizeof(struct fdma));
+	memcpy(&lan966x->rx.fdma, &rx_fdma_old, sizeof(struct fdma));
+
+	lan966x->rx.max_mtu = old_mtu;
+
+	lan966x_fdma_pci_reset_mem(lan966x);
+
+	napi_enable(&lan966x->napi);
+	lan966x_fdma_rx_start(&lan966x->rx);
+	lan966x_fdma_pci_wakeup_netdev(lan966x);
+
+	return err;
+}
+
+static int __lan966x_fdma_pci_reload(struct lan966x *lan966x, int max_mtu)
+{
+	int err;
+	u32 val;
+
+	/* Disable the CPU port. */
+	lan_rmw(QSYS_SW_PORT_MODE_PORT_ENA_SET(0),
+		QSYS_SW_PORT_MODE_PORT_ENA,
+		lan966x, QSYS_SW_PORT_MODE(CPU_PORT));
+
+	/* Flush the CPU queues. */
+	readx_poll_timeout(lan966x_qsys_sw_status,
+			   lan966x,
+			   val,
+			   !(QSYS_SW_STATUS_EQ_AVAIL_GET(val)),
+			   READL_SLEEP_US, READL_TIMEOUT_US);
+
+	/* Add a sleep in case there are frames between the queues and the CPU
+	 * port
+	 */
+	usleep_range(USEC_PER_MSEC, 2 * USEC_PER_MSEC);
+
+	err = lan966x_fdma_pci_reload(lan966x, max_mtu);
+
+	/* Enable back the CPU port. */
+	lan_rmw(QSYS_SW_PORT_MODE_PORT_ENA_SET(1),
+		QSYS_SW_PORT_MODE_PORT_ENA,
+		lan966x, QSYS_SW_PORT_MODE(CPU_PORT));
+
+	return err;
+}
+
 static int lan966x_fdma_pci_resize(struct lan966x *lan966x)
 {
-	return -EOPNOTSUPP;
+	struct fdma rx_fdma;
+	int max_mtu;
+
+	max_mtu = lan966x_fdma_get_max_frame(lan966x);
+	if (max_mtu == lan966x->rx.max_mtu)
+		return 0;
+
+	/* rx and tx have n_dbs == 1, so both rings need the same contiguous
+	 * dma_alloc_coherent() block, which can't exceed MAX_PAGE_ORDER. The
+	 * allocation is padded to the ATU region granularity, so test the
+	 * padded size.
+	 */
+	rx_fdma = lan966x->rx.fdma;
+	rx_fdma.db_size = FDMA_PCI_DB_SIZE(max_mtu);
+	if (ALIGN(fdma_get_size_contiguous(&rx_fdma),
+		  FDMA_PCI_ATU_REGION_ALIGN) > (PAGE_SIZE << MAX_PAGE_ORDER))
+		return -ERANGE;
+
+	/* db_size is also handed to the FDMA in the 16-bit DCB DATAL field,
+	 * where a larger value would be silently truncated.
+	 */
+	if (rx_fdma.db_size > GENMASK(15, 0))
+		return -ERANGE;
+
+	return __lan966x_fdma_pci_reload(lan966x, max_mtu);
 }
 
 static void lan966x_fdma_pci_deinit(struct lan966x *lan966x)

-- 
2.34.1