net: ethernet: ti: introduce am65x/j721e gigabit eth subsystem driver

The TI AM65x/J721E SoCs Gigabit Ethernet Switch subsystem (CPSW2G NUSS) has
two ports - One Ethernet port (port 1) with selectable RGMII and RMII
interfaces and an internal Communications Port Programming Interface (CPPI)
port (Host port 0) and with ALE in between. It also contains
 - Management Data Input/Output (MDIO) interface for physical layer device
(PHY) management;
 - Updated Address Lookup Engine (ALE) module;
 - (TBD) New version of Common platform time sync (CPTS) module.

On the TI am65x/J721E SoCs CPSW NUSS Ethernet subsystem into device MCU
domain named MCU_CPSW0.

Host Port 0 CPPI Packet Streaming Interface interface supports 8 TX
channels and one RX channels operating by TI am654 NAVSS Unified DMA
Peripheral Root Complex (UDMA-P) controller.

Introduced driver provides standard Linux net_device to user space and supports:
 - ifconfig up/down
 - MAC address configuration
 - ethtool operation:
   --driver
   --change
   --register-dump
   --negotiate phy
   --statistics
   --set-eee phy
   --show-ring
   --show-channels
   --set-channels
 - net_device ioctl mii-control
 - promisc mode

 - rx checksum offload for non-fragmented IPv4/IPv6 TCP/UDP packets.
   The CPSW NUSS can verify IPv4/IPv6 TCP/UDP packets checksum and fills
   csum information for each packet in psdata[2] word:
   - BIT(16) CHECKSUM_ERROR - indicates csum error
   - BIT(17) FRAGMENT -  indicates fragmented packet
   - BIT(18) TCP_UDP_N -  Indicates TCP packet was detected
   - BIT(19) IPV6_VALID,  BIT(20) IPV4_VALID - indicates IPv6/IPv4 packet
   - BIT(15, 0) CHECKSUM_ADD - This is the value that was summed
   during the checksum computation. This value is FFFFh for non fragmented
   IPV4/6 UDP/TCP packets with no checksum error.

   RX csum offload can be disabled:
	 ethtool -K <dev> rx-checksum on|off

 - tx checksum offload support for IPv4/IPv6 TCP/UDP packets (J721E only).
   TX csum HW offload  can be enabled/disabled:
	 ethtool -K <dev> tx-checksum-ip-generic on|off

 - multiq and switch between round robin/prio modes for cppi tx queues by
   using Netdev private flag "p0-rx-ptype-rrobin" to switch between
   Round Robin and Fixed priority modes:
	 # ethtool --show-priv-flags eth0
	 Private flags for eth0:
	 p0-rx-ptype-rrobin: on
	 # ethtool --set-priv-flags eth0 p0-rx-ptype-rrobin off

   Number of TX DMA channels can be changed using "ethtool -L eth0 tx <N>".

 - GRO support: the napi_gro_receive() and napi_complete_done() are used.
Signed-off-by: NGrygorii Strashko <grygorii.strashko@ti.com>
Tested-by: NMurali Karicheri <m-karicheri2@ti.com>
Tested-by: NPeter Ujfalusi <peter.ujfalusi@ti.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

drivers/net/ethernet/ti/Kconfig

@@ -6,7 +6,7 @@
 config NET_VENDOR_TI
 	bool "Texas Instruments (TI) devices"
 	default y
-	depends on PCI || EISA || AR7 || ARCH_DAVINCI || ARCH_OMAP2PLUS || ARCH_KEYSTONE
+	depends on PCI || EISA || AR7 || ARCH_DAVINCI || ARCH_OMAP2PLUS || ARCH_KEYSTONE || ARCH_K3
 	---help---
 	  If you have a network (Ethernet) card belonging to this class, say Y.
 
@@ -31,7 +31,7 @@ config TI_DAVINCI_EMAC
 
 config TI_DAVINCI_MDIO
 	tristate "TI DaVinci MDIO Support"
-	depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || ARCH_KEYSTONE || COMPILE_TEST
+	depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || ARCH_KEYSTONE || ARCH_K3 || COMPILE_TEST
 	select PHYLIB
 	---help---
 	  This driver supports TI's DaVinci MDIO module.
@@ -95,6 +95,21 @@ config TI_CPTS_MOD
 	imply PTP_1588_CLOCK
 	default m
 
+config TI_K3_AM65_CPSW_NUSS
+	tristate "TI K3 AM654x/J721E CPSW Ethernet driver"
+	depends on ARCH_K3 && OF && TI_K3_UDMA_GLUE_LAYER
+	select TI_DAVINCI_MDIO
+	imply PHY_TI_GMII_SEL
+	help
+	  This driver supports TI K3 AM654/J721E CPSW2G Ethernet SubSystem.
+	  The two-port Gigabit Ethernet MAC (MCU_CPSW0) subsystem provides
+	  Ethernet packet communication for the device: One Ethernet port
+	  (port 1) with selectable RGMII and RMII interfaces and an internal
+	  Communications Port Programming Interface (CPPI) port (port 0).
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called ti-am65-cpsw-nuss.
+
 config TI_KEYSTONE_NETCP
 	tristate "TI Keystone NETCP Core Support"
 	select TI_DAVINCI_MDIO

drivers/net/ethernet/ti/Makefile

@@ -23,3 +23,6 @@ obj-$(CONFIG_TI_KEYSTONE_NETCP) += keystone_netcp.o
 keystone_netcp-y := netcp_core.o cpsw_ale.o
 obj-$(CONFIG_TI_KEYSTONE_NETCP_ETHSS) += keystone_netcp_ethss.o
 keystone_netcp_ethss-y := netcp_ethss.o netcp_sgmii.o netcp_xgbepcsr.o cpsw_ale.o
+
+obj-$(CONFIG_TI_K3_AM65_CPSW_NUSS) += ti-am65-cpsw-nuss.o
+ti-am65-cpsw-nuss-y := am65-cpsw-nuss.o cpsw_sl.o am65-cpsw-ethtool.o cpsw_ale.o k3-cppi-desc-pool.o

drivers/net/ethernet/ti/am65-cpsw-nuss.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2020 Texas Instruments Incorporated - http://www.ti.com/
+ *
+ */
+
+#ifndef AM65_CPSW_NUSS_H_
+#define AM65_CPSW_NUSS_H_
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+
+#define HOST_PORT_NUM		0
+
+#define AM65_CPSW_MAX_TX_QUEUES	8
+#define AM65_CPSW_MAX_RX_QUEUES	1
+#define AM65_CPSW_MAX_RX_FLOWS	1
+
+struct am65_cpsw_slave_data {
+	bool				mac_only;
+	struct cpsw_sl			*mac_sl;
+	struct device_node		*phy_node;
+	struct phy_device		*phy;
+	phy_interface_t			phy_if;
+	struct phy			*ifphy;
+	bool				rx_pause;
+	bool				tx_pause;
+	u8				mac_addr[ETH_ALEN];
+};
+
+struct am65_cpsw_port {
+	struct am65_cpsw_common		*common;
+	struct net_device		*ndev;
+	const char			*name;
+	u32				port_id;
+	void __iomem			*port_base;
+	void __iomem			*stat_base;
+	bool				disabled;
+	struct am65_cpsw_slave_data	slave;
+};
+
+struct am65_cpsw_host {
+	struct am65_cpsw_common		*common;
+	void __iomem			*port_base;
+	void __iomem			*stat_base;
+};
+
+struct am65_cpsw_tx_chn {
+	struct napi_struct napi_tx;
+	struct am65_cpsw_common	*common;
+	struct k3_cppi_desc_pool *desc_pool;
+	struct k3_udma_glue_tx_channel *tx_chn;
+	int irq;
+	u32 id;
+	u32 descs_num;
+	char tx_chn_name[128];
+};
+
+struct am65_cpsw_rx_chn {
+	struct device *dev;
+	struct k3_cppi_desc_pool *desc_pool;
+	struct k3_udma_glue_rx_channel *rx_chn;
+	u32 descs_num;
+	int irq;
+};
+
+#define AM65_CPSW_QUIRK_I2027_NO_TX_CSUM BIT(0)
+
+struct am65_cpsw_pdata {
+	u32	quirks;
+};
+
+struct am65_cpsw_common {
+	struct device		*dev;
+	const struct am65_cpsw_pdata *pdata;
+
+	void __iomem		*ss_base;
+	void __iomem		*cpsw_base;
+
+	u32			port_num;
+	struct am65_cpsw_host   host;
+	struct am65_cpsw_port	*ports;
+	u32			disabled_ports_mask;
+
+	int			usage_count; /* number of opened ports */
+	struct cpsw_ale		*ale;
+	int			tx_ch_num;
+	u32			rx_flow_id_base;
+
+	struct am65_cpsw_tx_chn	tx_chns[AM65_CPSW_MAX_TX_QUEUES];
+	struct completion	tdown_complete;
+	atomic_t		tdown_cnt;
+
+	struct am65_cpsw_rx_chn	rx_chns;
+	struct napi_struct	napi_rx;
+
+	u32			nuss_ver;
+	u32			cpsw_ver;
+
+	bool			pf_p0_rx_ptype_rrobin;
+};
+
+struct am65_cpsw_ndev_stats {
+	u64 tx_packets;
+	u64 tx_bytes;
+	u64 rx_packets;
+	u64 rx_bytes;
+	struct u64_stats_sync syncp;
+};
+
+struct am65_cpsw_ndev_priv {
+	u32			msg_enable;
+	struct am65_cpsw_port	*port;
+	struct am65_cpsw_ndev_stats __percpu *stats;
+};
+
+#define am65_ndev_to_priv(ndev) \
+	((struct am65_cpsw_ndev_priv *)netdev_priv(ndev))
+#define am65_ndev_to_port(ndev) (am65_ndev_to_priv(ndev)->port)
+#define am65_ndev_to_common(ndev) (am65_ndev_to_port(ndev)->common)
+#define am65_ndev_to_slave(ndev) (&am65_ndev_to_port(ndev)->slave)
+
+#define am65_common_get_host(common) (&(common)->host)
+#define am65_common_get_port(common, id) (&(common)->ports[(id) - 1])
+
+#define am65_cpsw_napi_to_common(pnapi) \
+	container_of(pnapi, struct am65_cpsw_common, napi_rx)
+#define am65_cpsw_napi_to_tx_chn(pnapi) \
+	container_of(pnapi, struct am65_cpsw_tx_chn, napi_tx)
+
+#define AM65_CPSW_DRV_NAME "am65-cpsw-nuss"
+
+#define AM65_CPSW_IS_CPSW2G(common) ((common)->port_num == 1)
+
+extern const struct ethtool_ops am65_cpsw_ethtool_ops_slave;
+
+void am65_cpsw_nuss_adjust_link(struct net_device *ndev);
+void am65_cpsw_nuss_set_p0_ptype(struct am65_cpsw_common *common);
+void am65_cpsw_nuss_remove_tx_chns(struct am65_cpsw_common *common);
+int am65_cpsw_nuss_update_tx_chns(struct am65_cpsw_common *common, int num_tx);
+
+#endif /* AM65_CPSW_NUSS_H_ */

drivers/net/ethernet/ti/k3-cppi-desc-pool.c

+// SPDX-License-Identifier: GPL-2.0
+/* TI K3 CPPI5 descriptors pool API
+ *
+ * Copyright (C) 2020 Texas Instruments Incorporated - http://www.ti.com
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/genalloc.h>
+#include <linux/kernel.h>
+
+#include "k3-cppi-desc-pool.h"
+
+struct k3_cppi_desc_pool {
+	struct device		*dev;
+	dma_addr_t		dma_addr;
+	void			*cpumem;	/* dma_alloc map */
+	size_t			desc_size;
+	size_t			mem_size;
+	size_t			num_desc;
+	struct gen_pool		*gen_pool;
+};
+
+void k3_cppi_desc_pool_destroy(struct k3_cppi_desc_pool *pool)
+{
+	if (!pool)
+		return;
+
+	WARN(gen_pool_size(pool->gen_pool) != gen_pool_avail(pool->gen_pool),
+	     "k3_knav_desc_pool size %zu != avail %zu",
+	     gen_pool_size(pool->gen_pool),
+	     gen_pool_avail(pool->gen_pool));
+	if (pool->cpumem)
+		dma_free_coherent(pool->dev, pool->mem_size, pool->cpumem,
+				  pool->dma_addr);
+
+	gen_pool_destroy(pool->gen_pool);	/* frees pool->name */
+}
+
+struct k3_cppi_desc_pool *
+k3_cppi_desc_pool_create_name(struct device *dev, size_t size,
+			      size_t desc_size,
+			      const char *name)
+{
+	struct k3_cppi_desc_pool *pool;
+	const char *pool_name = NULL;
+	int ret = -ENOMEM;
+
+	pool = devm_kzalloc(dev, sizeof(*pool), GFP_KERNEL);
+	if (!pool)
+		return ERR_PTR(ret);
+
+	pool->dev = dev;
+	pool->desc_size	= roundup_pow_of_two(desc_size);
+	pool->num_desc	= size;
+	pool->mem_size	= pool->num_desc * pool->desc_size;
+
+	pool_name = kstrdup_const(name ? name : dev_name(pool->dev),
+				  GFP_KERNEL);
+	if (!pool_name)
+		return ERR_PTR(-ENOMEM);
+
+	pool->gen_pool = gen_pool_create(ilog2(pool->desc_size), -1);
+	if (IS_ERR(pool->gen_pool)) {
+		ret = PTR_ERR(pool->gen_pool);
+		dev_err(pool->dev, "pool create failed %d\n", ret);
+		kfree_const(pool_name);
+		goto gen_pool_create_fail;
+	}
+
+	pool->gen_pool->name = pool_name;
+
+	pool->cpumem = dma_alloc_coherent(pool->dev, pool->mem_size,
+					  &pool->dma_addr, GFP_KERNEL);
+
+	if (!pool->cpumem)
+		goto dma_alloc_fail;
+
+	ret = gen_pool_add_virt(pool->gen_pool, (unsigned long)pool->cpumem,
+				(phys_addr_t)pool->dma_addr, pool->mem_size,
+				-1);
+	if (ret < 0) {
+		dev_err(pool->dev, "pool add failed %d\n", ret);
+		goto gen_pool_add_virt_fail;
+	}
+
+	return pool;
+
+gen_pool_add_virt_fail:
+	dma_free_coherent(pool->dev, pool->mem_size, pool->cpumem,
+			  pool->dma_addr);
+dma_alloc_fail:
+	gen_pool_destroy(pool->gen_pool);	/* frees pool->name */
+gen_pool_create_fail:
+	devm_kfree(pool->dev, pool);
+	return ERR_PTR(ret);
+}
+
+dma_addr_t k3_cppi_desc_pool_virt2dma(struct k3_cppi_desc_pool *pool,
+				      void *addr)
+{
+	return addr ? pool->dma_addr + (addr - pool->cpumem) : 0;
+}
+
+void *k3_cppi_desc_pool_dma2virt(struct k3_cppi_desc_pool *pool, dma_addr_t dma)
+{
+	return dma ? pool->cpumem + (dma - pool->dma_addr) : NULL;
+}
+
+void *k3_cppi_desc_pool_alloc(struct k3_cppi_desc_pool *pool)
+{
+	return (void *)gen_pool_alloc(pool->gen_pool, pool->desc_size);
+}
+
+void k3_cppi_desc_pool_free(struct k3_cppi_desc_pool *pool, void *addr)
+{
+	gen_pool_free(pool->gen_pool, (unsigned long)addr, pool->desc_size);
+}
+
+size_t k3_cppi_desc_pool_avail(struct k3_cppi_desc_pool *pool)
+{
+	return gen_pool_avail(pool->gen_pool) / pool->desc_size;
+}

drivers/net/ethernet/ti/k3-cppi-desc-pool.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/* TI K3 CPPI5 descriptors pool
+ *
+ * Copyright (C) 2020 Texas Instruments Incorporated - http://www.ti.com
+ */
+
+#ifndef K3_CPPI_DESC_POOL_H_
+#define K3_CPPI_DESC_POOL_H_
+
+#include <linux/device.h>
+#include <linux/types.h>
+
+struct k3_cppi_desc_pool;
+
+void k3_cppi_desc_pool_destroy(struct k3_cppi_desc_pool *pool);
+struct k3_cppi_desc_pool *
+k3_cppi_desc_pool_create_name(struct device *dev, size_t size,
+			      size_t desc_size,
+			      const char *name);
+#define k3_cppi_desc_pool_create(dev, size, desc_size) \
+		k3_cppi_desc_pool_create_name(dev, size, desc_size, NULL)
+dma_addr_t
+k3_cppi_desc_pool_virt2dma(struct k3_cppi_desc_pool *pool, void *addr);
+void *
+k3_cppi_desc_pool_dma2virt(struct k3_cppi_desc_pool *pool, dma_addr_t dma);
+void *k3_cppi_desc_pool_alloc(struct k3_cppi_desc_pool *pool);
+void k3_cppi_desc_pool_free(struct k3_cppi_desc_pool *pool, void *addr);
+size_t k3_cppi_desc_pool_avail(struct k3_cppi_desc_pool *pool);
+
+#endif /* K3_CPPI_DESC_POOL_H_ */