[PATCH] intel ixp2000 network driver

The way the hardware and firmware work is that there is one shared RX
queue and IRQ for a number of different network interfaces.  Due to this,
we would like to process received packets for every interface in the same
NAPI poll handler, so we need a pseudo-device to schedule polling on.

What the driver currently does is that it always schedules polling for
the first network interface in the list, and processes packets for every
interface in the poll handler for that first interface -- however, this
scheme breaks down if the first network interface happens to not be up,
since netif_rx_schedule_prep() checks netif_running().

sky2 apparently has the same issue, and Stephen Hemminger suggested a
way to work around this: create a variant of netif_rx_schedule_prep()
that does not check netif_running().  I implemented this locally and
called it netif_rx_schedule_prep_notup(), and it seems to work well,
but it's something that probably not everyone would be happy with.

The ixp2000 is an ARM CPU with a high-speed network interface in the
CPU itself (full duplex 4Gb/s or 10Gb/s depending on the IXP model.)
The CPU package also contains 8 or 16 (again depending on the IXP
model) 'microengines', which are somewhat primitive but very fast
and efficient processor cores which can be used to offload various
things from the main CPU.

This driver makes the high-speed network interface in the CPU visible
and usable as a regular linux network device.  Currently, it only
supports the Radisys ENP2611 IXP board, but adding support for other
board types should be fairly easy.

Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org>
Signed-off-by: Jeff Garzik <jgarzik@pobox.com>

1 files changed, 404 insertions, 0 deletions

diff --git a/drivers/net/ixp2000/ixpdev.c b/drivers/net/ixp2000/ixpdev.c
new file mode 100644
index 000000000000..216aad1911e6
--- /dev/null
+++ b/drivers/net/ixp2000/ixpdev.c
@@ -0,0 +1,404 @@
+/*
+ * IXP2000 MSF network device driver
+ * Copyright (C) 2004, 2005 Lennert Buytenhek <buytenh@wantstofly.org>
+ * Dedicated to Marija Kulikova.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/init.h>
+#include <linux/moduleparam.h>
+#include <asm/arch/uengine.h>
+#include <asm/mach-types.h>
+#include <asm/io.h>
+#include "ixp2400_rx.ucode"
+#include "ixp2400_tx.ucode"
+#include "ixpdev_priv.h"
+#include "ixpdev.h"
+
+static int nds_count;
+static struct net_device **nds;
+static int nds_open;
+static void (*set_port_admin_status)(int port, int up);
+
+static struct ixpdev_rx_desc * const rx_desc =
+	(struct ixpdev_rx_desc *)(IXP2000_SRAM0_VIRT_BASE + RX_BUF_DESC_BASE);
+static struct ixpdev_tx_desc * const tx_desc =
+	(struct ixpdev_tx_desc *)(IXP2000_SRAM0_VIRT_BASE + TX_BUF_DESC_BASE);
+static int tx_pointer;
+
+
+static int ixpdev_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct ixpdev_priv *ip = netdev_priv(dev);
+	struct ixpdev_tx_desc *desc;
+	int entry;
+
+	if (unlikely(skb->len > PAGE_SIZE)) {
+		/* @@@ Count drops.  */
+		dev_kfree_skb(skb);
+		return 0;
+	}
+
+	entry = tx_pointer;
+	tx_pointer = (tx_pointer + 1) % TX_BUF_COUNT;
+
+	desc = tx_desc + entry;
+	desc->pkt_length = skb->len;
+	desc->channel = ip->channel;
+
+	skb_copy_and_csum_dev(skb, phys_to_virt(desc->buf_addr));
+	dev_kfree_skb(skb);
+
+	ixp2000_reg_write(RING_TX_PENDING,
+		TX_BUF_DESC_BASE + (entry * sizeof(struct ixpdev_tx_desc)));
+
+	dev->trans_start = jiffies;
+
+	local_irq_disable();
+	ip->tx_queue_entries++;
+	if (ip->tx_queue_entries == TX_BUF_COUNT_PER_CHAN)
+		netif_stop_queue(dev);
+	local_irq_enable();
+
+	return 0;
+}
+
+
+static int ixpdev_rx(struct net_device *dev, int *budget)
+{
+	while (*budget > 0) {
+		struct ixpdev_rx_desc *desc;
+		struct sk_buff *skb;
+		void *buf;
+		u32 _desc;
+
+		_desc = ixp2000_reg_read(RING_RX_DONE);
+		if (_desc == 0)
+			return 0;
+
+		desc = rx_desc +
+			((_desc - RX_BUF_DESC_BASE) / sizeof(struct ixpdev_rx_desc));
+		buf = phys_to_virt(desc->buf_addr);
+
+		if (desc->pkt_length < 4 || desc->pkt_length > PAGE_SIZE) {
+			printk(KERN_ERR "ixp2000: rx err, length %d\n",
+					desc->pkt_length);
+			goto err;
+		}
+
+		if (desc->channel < 0 || desc->channel >= nds_count) {
+			printk(KERN_ERR "ixp2000: rx err, channel %d\n",
+					desc->channel);
+			goto err;
+		}
+
+		/* @@@ Make FCS stripping configurable.  */
+		desc->pkt_length -= 4;
+
+		if (unlikely(!netif_running(nds[desc->channel])))
+			goto err;
+
+		skb = dev_alloc_skb(desc->pkt_length + 2);
+		if (likely(skb != NULL)) {
+			skb->dev = nds[desc->channel];
+			skb_reserve(skb, 2);
+			eth_copy_and_sum(skb, buf, desc->pkt_length, 0);
+			skb_put(skb, desc->pkt_length);
+			skb->protocol = eth_type_trans(skb, skb->dev);
+
+			skb->dev->last_rx = jiffies;
+
+			netif_receive_skb(skb);
+		}
+
+err:
+		ixp2000_reg_write(RING_RX_PENDING, _desc);
+		dev->quota--;
+		(*budget)--;
+	}
+
+	return 1;
+}
+
+/* dev always points to nds[0].  */
+static int ixpdev_poll(struct net_device *dev, int *budget)
+{
+	/* @@@ Have to stop polling when nds[0] is administratively
+	 * downed while we are polling.  */
+	do {
+		ixp2000_reg_write(IXP2000_IRQ_THD_RAW_STATUS_A_0, 0x00ff);
+
+		if (ixpdev_rx(dev, budget))
+			return 1;
+	} while (ixp2000_reg_read(IXP2000_IRQ_THD_RAW_STATUS_A_0) & 0x00ff);
+
+	netif_rx_complete(dev);
+	ixp2000_reg_write(IXP2000_IRQ_THD_ENABLE_SET_A_0, 0x00ff);
+
+	return 0;
+}
+
+/* @@@ Ugly hack.  */
+static inline int netif_rx_schedule_prep_notup(struct net_device *dev)
+{
+	return !test_and_set_bit(__LINK_STATE_RX_SCHED, &dev->state);
+}
+
+static void ixpdev_tx_complete(void)
+{
+	int channel;
+	u32 wake;
+
+	wake = 0;
+	while (1) {
+		struct ixpdev_priv *ip;
+		u32 desc;
+		int entry;
+
+		desc = ixp2000_reg_read(RING_TX_DONE);
+		if (desc == 0)
+			break;
+
+		/* @@@ Check whether entries come back in order.  */
+		entry = (desc - TX_BUF_DESC_BASE) / sizeof(struct ixpdev_tx_desc);
+		channel = tx_desc[entry].channel;
+
+		if (channel < 0 || channel >= nds_count) {
+			printk(KERN_ERR "ixp2000: txcomp channel index "
+					"out of bounds (%d, %.8i, %d)\n",
+					channel, (unsigned int)desc, entry);
+			continue;
+		}
+
+		ip = netdev_priv(nds[channel]);
+		if (ip->tx_queue_entries == TX_BUF_COUNT_PER_CHAN)
+			wake |= 1 << channel;
+		ip->tx_queue_entries--;
+	}
+
+	for (channel = 0; wake != 0; channel++) {
+		if (wake & (1 << channel)) {
+			netif_wake_queue(nds[channel]);
+			wake &= ~(1 << channel);
+		}
+	}
+}
+
+static irqreturn_t ixpdev_interrupt(int irq, void *dev_id, struct pt_regs *regs)
+{
+	u32 status;
+
+	status = ixp2000_reg_read(IXP2000_IRQ_THD_STATUS_A_0);
+	if (status == 0)
+		return IRQ_NONE;
+
+	/*
+	 * Any of the eight receive units signaled RX?
+	 */
+	if (status & 0x00ff) {
+		ixp2000_reg_wrb(IXP2000_IRQ_THD_ENABLE_CLEAR_A_0, 0x00ff);
+		if (likely(netif_rx_schedule_prep_notup(nds[0]))) {
+			__netif_rx_schedule(nds[0]);
+		} else {
+			printk(KERN_CRIT "ixp2000: irq while polling!!\n");
+		}
+	}
+
+	/*
+	 * Any of the eight transmit units signaled TXdone?
+	 */
+	if (status & 0xff00) {
+		ixp2000_reg_wrb(IXP2000_IRQ_THD_RAW_STATUS_A_0, 0xff00);
+		ixpdev_tx_complete();
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int ixpdev_open(struct net_device *dev)
+{
+	struct ixpdev_priv *ip = netdev_priv(dev);
+	int err;
+
+	if (!nds_open++) {
+		err = request_irq(IRQ_IXP2000_THDA0, ixpdev_interrupt,
+					SA_SHIRQ, "ixp2000_eth", nds);
+		if (err) {
+			nds_open--;
+			return err;
+		}
+
+		ixp2000_reg_write(IXP2000_IRQ_THD_ENABLE_SET_A_0, 0xffff);
+	}
+
+	set_port_admin_status(ip->channel, 1);
+	netif_start_queue(dev);
+
+	return 0;
+}
+
+static int ixpdev_close(struct net_device *dev)
+{
+	struct ixpdev_priv *ip = netdev_priv(dev);
+
+	netif_stop_queue(dev);
+	set_port_admin_status(ip->channel, 0);
+
+	if (!--nds_open) {
+		ixp2000_reg_write(IXP2000_IRQ_THD_ENABLE_CLEAR_A_0, 0xffff);
+		free_irq(IRQ_IXP2000_THDA0, nds);
+	}
+
+	return 0;
+}
+
+struct net_device *ixpdev_alloc(int channel, int sizeof_priv)
+{
+	struct net_device *dev;
+	struct ixpdev_priv *ip;
+
+	dev = alloc_etherdev(sizeof_priv);
+	if (dev == NULL)
+		return NULL;
+
+	dev->hard_start_xmit = ixpdev_xmit;
+	dev->poll = ixpdev_poll;
+	dev->open = ixpdev_open;
+	dev->stop = ixpdev_close;
+
+	dev->features |= NETIF_F_SG | NETIF_F_HW_CSUM;
+	dev->weight = 64;
+
+	ip = netdev_priv(dev);
+	ip->channel = channel;
+	ip->tx_queue_entries = 0;
+
+	return dev;
+}
+
+int ixpdev_init(int __nds_count, struct net_device **__nds,
+		void (*__set_port_admin_status)(int port, int up))
+{
+	int i;
+	int err;
+
+	if (RX_BUF_COUNT > 192 || TX_BUF_COUNT > 192) {
+		static void __too_many_rx_or_tx_buffers(void);
+		__too_many_rx_or_tx_buffers();
+	}
+
+	nds_count = __nds_count;
+	nds = __nds;
+	set_port_admin_status = __set_port_admin_status;
+
+	for (i = 0; i < nds_count; i++) {
+		err = register_netdev(nds[i]);
+		if (err) {
+			while (--i >= 0)
+				unregister_netdev(nds[i]);
+			goto err_out;
+		}
+	}
+
+	for (i = 0; i < RX_BUF_COUNT; i++) {
+		void *buf;
+
+		buf = (void *)get_zeroed_page(GFP_KERNEL);
+		if (buf == NULL) {
+			err = -ENOMEM;
+			while (--i >= 0)
+				free_page((unsigned long)phys_to_virt(rx_desc[i].buf_addr));
+			goto err_unregister;
+		}
+		rx_desc[i].buf_addr = virt_to_phys(buf);
+		rx_desc[i].buf_length = PAGE_SIZE;
+	}
+
+	/* @@@ Maybe we shouldn't be preallocating TX buffers.  */
+	for (i = 0; i < TX_BUF_COUNT; i++) {
+		void *buf;
+
+		buf = (void *)get_zeroed_page(GFP_KERNEL);
+		if (buf == NULL) {
+			err = -ENOMEM;
+			while (--i >= 0)
+				free_page((unsigned long)phys_to_virt(tx_desc[i].buf_addr));
+			goto err_free_rx;
+		}
+		tx_desc[i].buf_addr = virt_to_phys(buf);
+	}
+
+	/* 256 entries, ring status set means 'empty', base address 0x0000.  */
+	ixp2000_reg_write(RING_RX_PENDING_BASE, 0x44000000);
+	ixp2000_reg_write(RING_RX_PENDING_HEAD, 0x00000000);
+	ixp2000_reg_write(RING_RX_PENDING_TAIL, 0x00000000);
+
+	/* 256 entries, ring status set means 'full', base address 0x0400.  */
+	ixp2000_reg_write(RING_RX_DONE_BASE, 0x40000400);
+	ixp2000_reg_write(RING_RX_DONE_HEAD, 0x00000000);
+	ixp2000_reg_write(RING_RX_DONE_TAIL, 0x00000000);
+
+	for (i = 0; i < RX_BUF_COUNT; i++) {
+		ixp2000_reg_write(RING_RX_PENDING,
+			RX_BUF_DESC_BASE + (i * sizeof(struct ixpdev_rx_desc)));
+	}
+
+	ixp2000_uengine_load(0, &ixp2400_rx);
+	ixp2000_uengine_start_contexts(0, 0xff);
+
+
+	/* 256 entries, ring status set means 'empty', base address 0x0800.  */
+	ixp2000_reg_write(RING_TX_PENDING_BASE, 0x44000800);
+	ixp2000_reg_write(RING_TX_PENDING_HEAD, 0x00000000);
+	ixp2000_reg_write(RING_TX_PENDING_TAIL, 0x00000000);
+
+	/* 256 entries, ring status set means 'full', base address 0x0c00.  */
+	ixp2000_reg_write(RING_TX_DONE_BASE, 0x40000c00);
+	ixp2000_reg_write(RING_TX_DONE_HEAD, 0x00000000);
+	ixp2000_reg_write(RING_TX_DONE_TAIL, 0x00000000);
+
+	ixp2000_uengine_load(1, &ixp2400_tx);
+	ixp2000_uengine_start_contexts(1, 0xff);
+
+	return 0;
+
+err_free_rx:
+	for (i = 0; i < RX_BUF_COUNT; i++)
+		free_page((unsigned long)phys_to_virt(rx_desc[i].buf_addr));
+
+err_unregister:
+	for (i = 0; i < nds_count; i++)
+		unregister_netdev(nds[i]);
+
+err_out:
+	return err;
+} 
+
+void ixpdev_deinit(void)
+{
+	int i;
+
+	/* @@@ Flush out pending packets.  */
+
+	ixp2000_uengine_stop_contexts(1, 0xff);
+	ixp2000_uengine_stop_contexts(0, 0xff);
+	ixp2000_uengine_reset(0x3);
+
+	for (i = 0; i < TX_BUF_COUNT; i++)
+		free_page((unsigned long)phys_to_virt(tx_desc[i].buf_addr));
+
+	for (i = 0; i < RX_BUF_COUNT; i++)
+		free_page((unsigned long)phys_to_virt(rx_desc[i].buf_addr));
+
+	for (i = 0; i < nds_count; i++)
+		unregister_netdev(nds[i]);
+}