[PATCH net-next v7 11/14] net: lan966x: add PCIe FDMA MTU change support

[Daniel Machon]

Add MTU change support for the PCIe FDMA path: on an MTU change, the
contiguous ATU-mapped RX and TX buffers are reallocated at the new
size, falling back to the existing buffers on failure.

Cap the PCIe DCB ring at 256 (FDMA_PCI_DCB_MAX): 512 DCBs would
overflow MAX_PAGE_ORDER at jumbo MTU.

The ring must fit one MAX_PAGE_ORDER block after ATU padding, and
db_size is handed to the FDMA in the 16-bit DCB DATAL field.
Advertise the resulting limit in dev->max_mtu (FDMA_PCI_MAX_MTU)
when the FDMA is in use - a switch with no "fdma" interrupt named
uses the unconstrained register-based path instead, so the cap is
gated on lan966x->fdma, not lan966x_is_pci() alone. On a 4KB-page,
MAX_PAGE_ORDER=10 build this is MTU 15498; the overhead is shared
with lan966x_fdma_get_max_frame() via FDMA_OVERHEAD.

Skip the resize until lan966x_fdma_pci_init() has built the rings;
it runs after the netdevs register and sizes them from
DEV_MAC_MAXLEN_CFG, already programmed by the caller.

Tested-by: Herve Codina <herve.codina@xxxxxxxxxxx>
Signed-off-by: Daniel Machon <daniel.machon@xxxxxxxxxxxxx>
---
 .../net/ethernet/microchip/lan966x/lan966x_fdma.c  |   6 +-
 .../ethernet/microchip/lan966x/lan966x_fdma_pci.c  | 153 ++++++++++++++++++++-
 .../net/ethernet/microchip/lan966x/lan966x_main.c  |   3 +-
 .../net/ethernet/microchip/lan966x/lan966x_main.h  |  28 ++++
 4 files changed, 181 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
index 6fb2482eeb17..81103b94e36f 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
@@ -889,11 +889,7 @@ static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu)
 
 int lan966x_fdma_get_max_frame(struct lan966x *lan966x)
 {
-	return lan966x_fdma_get_max_mtu(lan966x) +
-	       IFH_LEN_BYTES +
-	       SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
-	       VLAN_HLEN * 2 +
-	       XDP_PACKET_HEADROOM;
+	return lan966x_fdma_get_max_mtu(lan966x) + FDMA_OVERHEAD;
 }
 
 static int __lan966x_fdma_reload(struct lan966x *lan966x, int max_mtu)
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma_pci.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma_pci.c
index 5d6902459f20..940425beec2f 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma_pci.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma_pci.c
@@ -358,7 +358,7 @@ 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);
@@ -368,7 +368,7 @@ 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);
@@ -391,9 +391,156 @@ 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);
+
+	/* Order matters: napi_enable() must precede the wakes, or a TX that
+	 * completes first clears FDMA_INTR_DB_ENA with nothing scheduled to
+	 * restore it, leaving RX dead until the next reload.
+	 */
+	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;
+	int max_mtu;
+
+	/* Nothing to resize until fdma_pci_init() has built the rings; it
+	 * sizes them from DEV_MAC_MAXLEN_CFG, which the caller already set.
+	 */
+	if (!lan966x->rx.lan966x)
+		return 0;
+
+	max_mtu = lan966x_fdma_get_max_frame(lan966x);
+	if (max_mtu == lan966x->rx.max_mtu)
+		return 0;
+
+	return __lan966x_fdma_pci_reload(lan966x, max_mtu);
 }
 
 static void lan966x_fdma_pci_deinit(struct lan966x *lan966x)
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
index c803619d83e2..2177e2bbfbd3 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
@@ -823,7 +823,8 @@ static int lan966x_probe_port(struct lan966x *lan966x, u32 p,
 	port->chip_port = p;
 	lan966x->ports[p] = port;
 
-	dev->max_mtu = ETH_MAX_MTU;
+	dev->max_mtu = lan966x_is_pci(lan966x) && lan966x->fdma ?
+		       FDMA_PCI_MAX_MTU : ETH_MAX_MTU;
 
 	dev->netdev_ops = &lan966x_port_netdev_ops;
 	dev->ethtool_ops = &lan966x_ethtool_ops;
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
index 16bc28c8f11f..1877f1916d71 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
@@ -7,6 +7,7 @@
 #include <linux/etherdevice.h>
 #include <linux/if_vlan.h>
 #include <linux/jiffies.h>
+#include <linux/mmzone.h>
 #include <linux/phy.h>
 #include <linux/phylink.h>
 #include <linux/ptp_clock_kernel.h>
@@ -87,6 +88,33 @@
 #define FDMA_INJ_CHANNEL		0
 #define FDMA_DCB_MAX			512
 
+/* Ring must fit in one MAX_PAGE_ORDER DMA block; 512 DCBs overflows
+ * at jumbo MTU.
+ */
+#define FDMA_PCI_DCB_MAX		256
+
+#define FDMA_OVERHEAD							\
+	(IFH_LEN_BYTES +						\
+	 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +		\
+	 VLAN_HLEN * 2 +						\
+	 XDP_PACKET_HEADROOM)
+
+/* Largest db_size keeping the ATU-padded ring inside one MAX_PAGE_ORDER
+ * block and within the 16-bit DCB DATAL field. Inverts ALIGN(x, R) <= L
+ * into x <= ALIGN_DOWN(L, R) to bound x directly.
+ */
+#define FDMA_PCI_DB_SIZE_MAX						\
+	MIN_T(u32,							\
+	      (ALIGN_DOWN(PAGE_SIZE << MAX_PAGE_ORDER,			\
+			  FDMA_PCI_ATU_REGION_ALIGN) -			\
+	       FDMA_PCI_DCB_MAX * sizeof(struct fdma_dcb)) /		\
+	      (FDMA_PCI_DCB_MAX * FDMA_RX_DCB_MAX_DBS),			\
+	      ALIGN_DOWN(GENMASK(15, 0), FDMA_PCI_DB_ALIGN))
+
+#define FDMA_PCI_MAX_MTU						\
+	(FDMA_PCI_DB_SIZE_MAX - FDMA_OVERHEAD -				\
+	 (ETH_HLEN + ETH_FCS_LEN))
+
 #define SE_IDX_QUEUE			0  /* 0-79 : Queue scheduler elements */
 #define SE_IDX_PORT			80 /* 80-89 : Port schedular elements */
 

-- 
2.34.1