openwrt-xburst/target/linux/ixp4xx/patches-2.6.23/200-npe_driver.patch

diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 4de432e..c4c810b 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -61,6 +61,7 @@ extern int root_mountflags;
 extern void _stext, _text, _etext, __data_start, _edata, _end;
 
 unsigned int processor_id;
+EXPORT_SYMBOL(processor_id);
 unsigned int __machine_arch_type;
 EXPORT_SYMBOL(__machine_arch_type);
 
diff --git a/arch/arm/mach-ixp4xx/Kconfig b/arch/arm/mach-ixp4xx/Kconfig
index 61b2dfc..e774447 100644
--- a/arch/arm/mach-ixp4xx/Kconfig
+++ b/arch/arm/mach-ixp4xx/Kconfig
@@ -189,6 +189,20 @@ config IXP4XX_INDIRECT_PCI
 	  need to use the indirect method instead. If you don't know
 	  what you need, leave this option unselected.
 
+config IXP4XX_QMGR
+	tristate "IXP4xx Queue Manager support"
+	help
+	  This driver supports IXP4xx built-in hardware queue manager
+	  and is automatically selected by Ethernet and HSS drivers.
+
+config IXP4XX_NPE
+	tristate "IXP4xx Network Processor Engine support"
+	select HOTPLUG
+	select FW_LOADER
+	help
+	  This driver supports IXP4xx built-in network coprocessors
+	  and is automatically selected by Ethernet and HSS drivers.
+
 endmenu
 
 endif
diff --git a/arch/arm/mach-ixp4xx/Makefile b/arch/arm/mach-ixp4xx/Makefile
index 77e00ad..4bb97e1 100644
--- a/arch/arm/mach-ixp4xx/Makefile
+++ b/arch/arm/mach-ixp4xx/Makefile
@@ -30,3 +30,5 @@ obj-$(CONFIG_MACH_GATEWAY7001)	+= gateway7001-setup.o
 obj-$(CONFIG_MACH_WG302V2)	+= wg302v2-setup.o
 
 obj-$(CONFIG_PCI)		+= $(obj-pci-$(CONFIG_PCI)) common-pci.o
+obj-$(CONFIG_IXP4XX_QMGR)	+= ixp4xx_qmgr.o
+obj-$(CONFIG_IXP4XX_NPE)	+= ixp4xx_npe.o
diff --git a/arch/arm/mach-ixp4xx/ixdp425-setup.c b/arch/arm/mach-ixp4xx/ixdp425-setup.c
index d5008d8..10b41c6 100644
--- a/arch/arm/mach-ixp4xx/ixdp425-setup.c
+++ b/arch/arm/mach-ixp4xx/ixdp425-setup.c
@@ -177,6 +177,31 @@ static struct platform_device ixdp425_uart = {
 	.resource		= ixdp425_uart_resources
 };
 
+/* Built-in 10/100 Ethernet MAC interfaces */
+static struct eth_plat_info ixdp425_plat_eth[] = {
+	{
+		.phy		= 0,
+		.rxq		= 3,
+		.txreadyq	= 20,
+	}, {
+		.phy		= 1,
+		.rxq		= 4,
+		.txreadyq	= 21,
+	}
+};
+
+static struct platform_device ixdp425_eth[] = {
+	{
+		.name			= "ixp4xx_eth",
+		.id			= IXP4XX_ETH_NPEB,
+		.dev.platform_data	= ixdp425_plat_eth,
+	}, {
+		.name			= "ixp4xx_eth",
+		.id			= IXP4XX_ETH_NPEC,
+		.dev.platform_data	= ixdp425_plat_eth + 1,
+	}
+};
+
 static struct platform_device *ixdp425_devices[] __initdata = {
 	&ixdp425_i2c_controller,
 	&ixdp425_flash,
@@ -184,7 +209,9 @@ static struct platform_device *ixdp425_devices[] __initdata = {
     defined(CONFIG_MTD_NAND_PLATFORM_MODULE)
 	&ixdp425_flash_nand,
 #endif
-	&ixdp425_uart
+	&ixdp425_uart,
+	&ixdp425_eth[0],
+	&ixdp425_eth[1],
 };
 
 static void __init ixdp425_init(void)
diff --git a/arch/arm/mach-ixp4xx/ixp4xx_npe.c b/arch/arm/mach-ixp4xx/ixp4xx_npe.c
new file mode 100644
index 0000000..83c137e
--- /dev/null
+++ b/arch/arm/mach-ixp4xx/ixp4xx_npe.c
@@ -0,0 +1,741 @@
+/*
+ * Intel IXP4xx Network Processor Engine driver for Linux
+ *
+ * Copyright (C) 2007 Krzysztof Halasa <khc@pm.waw.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ *
+ * The code is based on publicly available information:
+ * - Intel IXP4xx Developer's Manual and other e-papers
+ * - Intel IXP400 Access Library Software (BSD license)
+ * - previous works by Christian Hohnstaedt <chohnstaedt@innominate.com>
+ *   Thanks, Christian.
+ */
+
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/firmware.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <asm/arch/npe.h>
+
+#define DEBUG_MSG			0
+#define DEBUG_FW			0
+
+#define NPE_COUNT			3
+#define MAX_RETRIES			1000	/* microseconds */
+#define NPE_42X_DATA_SIZE		0x800	/* in dwords */
+#define NPE_46X_DATA_SIZE		0x1000
+#define NPE_A_42X_INSTR_SIZE		0x1000
+#define NPE_B_AND_C_42X_INSTR_SIZE	0x800
+#define NPE_46X_INSTR_SIZE		0x1000
+#define REGS_SIZE			0x1000
+
+#define NPE_PHYS_REG			32
+
+#define FW_MAGIC			0xFEEDF00D
+#define FW_BLOCK_TYPE_INSTR		0x0
+#define FW_BLOCK_TYPE_DATA		0x1
+#define FW_BLOCK_TYPE_EOF		0xF
+
+/* NPE exec status (read) and command (write) */
+#define CMD_NPE_STEP			0x01
+#define CMD_NPE_START			0x02
+#define CMD_NPE_STOP			0x03
+#define CMD_NPE_CLR_PIPE		0x04
+#define CMD_CLR_PROFILE_CNT		0x0C
+#define CMD_RD_INS_MEM			0x10 /* instruction memory */
+#define CMD_WR_INS_MEM			0x11
+#define CMD_RD_DATA_MEM			0x12 /* data memory */
+#define CMD_WR_DATA_MEM			0x13
+#define CMD_RD_ECS_REG			0x14 /* exec access register */
+#define CMD_WR_ECS_REG			0x15
+
+#define STAT_RUN			0x80000000
+#define STAT_STOP			0x40000000
+#define STAT_CLEAR			0x20000000
+#define STAT_ECS_K			0x00800000 /* pipeline clean */
+
+#define NPE_STEVT			0x1B
+#define NPE_STARTPC			0x1C
+#define NPE_REGMAP			0x1E
+#define NPE_CINDEX			0x1F
+
+#define INSTR_WR_REG_SHORT		0x0000C000
+#define INSTR_WR_REG_BYTE		0x00004000
+#define INSTR_RD_FIFO			0x0F888220
+#define INSTR_RESET_MBOX		0x0FAC8210
+
+#define ECS_BG_CTXT_REG_0		0x00 /* Background Executing Context */
+#define ECS_BG_CTXT_REG_1		0x01 /*		Stack level */
+#define ECS_BG_CTXT_REG_2		0x02
+#define ECS_PRI_1_CTXT_REG_0		0x04 /* Priority 1 Executing Context */
+#define ECS_PRI_1_CTXT_REG_1		0x05 /*		Stack level */
+#define ECS_PRI_1_CTXT_REG_2		0x06
+#define ECS_PRI_2_CTXT_REG_0		0x08 /* Priority 2 Executing Context */
+#define ECS_PRI_2_CTXT_REG_1		0x09 /*		Stack level */
+#define ECS_PRI_2_CTXT_REG_2		0x0A
+#define ECS_DBG_CTXT_REG_0		0x0C /* Debug Executing Context */
+#define ECS_DBG_CTXT_REG_1		0x0D /*		Stack level */
+#define ECS_DBG_CTXT_REG_2		0x0E
+#define ECS_INSTRUCT_REG		0x11 /* NPE Instruction Register */
+
+#define ECS_REG_0_ACTIVE		0x80000000 /* all levels */
+#define ECS_REG_0_NEXTPC_MASK		0x1FFF0000 /* BG/PRI1/PRI2 levels */
+#define ECS_REG_0_LDUR_BITS		8
+#define ECS_REG_0_LDUR_MASK		0x00000700 /* all levels */
+#define ECS_REG_1_CCTXT_BITS		16
+#define ECS_REG_1_CCTXT_MASK		0x000F0000 /* all levels */
+#define ECS_REG_1_SELCTXT_BITS		0
+#define ECS_REG_1_SELCTXT_MASK		0x0000000F /* all levels */
+#define ECS_DBG_REG_2_IF		0x00100000 /* debug level */
+#define ECS_DBG_REG_2_IE		0x00080000 /* debug level */
+
+/* NPE watchpoint_fifo register bit */
+#define WFIFO_VALID			0x80000000
+
+/* NPE messaging_status register bit definitions */
+#define MSGSTAT_OFNE	0x00010000 /* OutFifoNotEmpty */
+#define MSGSTAT_IFNF	0x00020000 /* InFifoNotFull */
+#define MSGSTAT_OFNF	0x00040000 /* OutFifoNotFull */
+#define MSGSTAT_IFNE	0x00080000 /* InFifoNotEmpty */
+#define MSGSTAT_MBINT	0x00100000 /* Mailbox interrupt */
+#define MSGSTAT_IFINT	0x00200000 /* InFifo interrupt */
+#define MSGSTAT_OFINT	0x00400000 /* OutFifo interrupt */
+#define MSGSTAT_WFINT	0x00800000 /* WatchFifo interrupt */
+
+/* NPE messaging_control register bit definitions */
+#define MSGCTL_OUT_FIFO			0x00010000 /* enable output FIFO */
+#define MSGCTL_IN_FIFO			0x00020000 /* enable input FIFO */
+#define MSGCTL_OUT_FIFO_WRITE		0x01000000 /* enable FIFO + WRITE */
+#define MSGCTL_IN_FIFO_WRITE		0x02000000
+
+/* NPE mailbox_status value for reset */
+#define RESET_MBOX_STAT			0x0000F0F0
+
+const char *npe_names[] = { "NPE-A", "NPE-B", "NPE-C" };
+
+#define print_npe(pri, npe, fmt, ...)					\
+	printk(pri "%s: " fmt, npe_name(npe), ## __VA_ARGS__)
+
+#if DEBUG_MSG
+#define debug_msg(npe, fmt, ...)					\
+	print_npe(KERN_DEBUG, npe, fmt, ## __VA_ARGS__)
+#else
+#define debug_msg(npe, fmt, ...)
+#endif
+
+static struct {
+	u32 reg, val;
+} ecs_reset[] = {
+	{ ECS_BG_CTXT_REG_0,	0xA0000000 },
+	{ ECS_BG_CTXT_REG_1,	0x01000000 },
+	{ ECS_BG_CTXT_REG_2,	0x00008000 },
+	{ ECS_PRI_1_CTXT_REG_0,	0x20000080 },
+	{ ECS_PRI_1_CTXT_REG_1,	0x01000000 },
+	{ ECS_PRI_1_CTXT_REG_2,	0x00008000 },
+	{ ECS_PRI_2_CTXT_REG_0,	0x20000080 },
+	{ ECS_PRI_2_CTXT_REG_1,	0x01000000 },
+	{ ECS_PRI_2_CTXT_REG_2,	0x00008000 },
+	{ ECS_DBG_CTXT_REG_0,	0x20000000 },
+	{ ECS_DBG_CTXT_REG_1,	0x00000000 },
+	{ ECS_DBG_CTXT_REG_2,	0x001E0000 },
+	{ ECS_INSTRUCT_REG,	0x1003C00F },
+};
+
+static struct npe npe_tab[NPE_COUNT] = {
+	{
+		.id	= 0,
+		.regs	= (struct npe_regs __iomem *)IXP4XX_NPEA_BASE_VIRT,
+		.regs_phys = IXP4XX_NPEA_BASE_PHYS,
+	}, {
+		.id	= 1,
+		.regs	= (struct npe_regs __iomem *)IXP4XX_NPEB_BASE_VIRT,
+		.regs_phys = IXP4XX_NPEB_BASE_PHYS,
+	}, {
+		.id	= 2,
+		.regs	= (struct npe_regs __iomem *)IXP4XX_NPEC_BASE_VIRT,
+		.regs_phys = IXP4XX_NPEC_BASE_PHYS,
+	}
+};
+
+int npe_running(struct npe *npe)
+{
+	return (__raw_readl(&npe->regs->exec_status_cmd) & STAT_RUN) != 0;
+}
+
+static void npe_cmd_write(struct npe *npe, u32 addr, int cmd, u32 data)
+{
+	__raw_writel(data, &npe->regs->exec_data);
+	__raw_writel(addr, &npe->regs->exec_addr);
+	__raw_writel(cmd, &npe->regs->exec_status_cmd);
+}
+
+static u32 npe_cmd_read(struct npe *npe, u32 addr, int cmd)
+{
+	__raw_writel(addr, &npe->regs->exec_addr);
+	__raw_writel(cmd, &npe->regs->exec_status_cmd);
+	/* Iintroduce extra read cycles after issuing read command to NPE
+	   so that we read the register after the NPE has updated it.
+	   This is to overcome race condition between XScale and NPE */
+	__raw_readl(&npe->regs->exec_data);
+	__raw_readl(&npe->regs->exec_data);
+	return __raw_readl(&npe->regs->exec_data);
+}
+
+static void npe_clear_active(struct npe *npe, u32 reg)
+{
+	u32 val = npe_cmd_read(npe, reg, CMD_RD_ECS_REG);
+	npe_cmd_write(npe, reg, CMD_WR_ECS_REG, val & ~ECS_REG_0_ACTIVE);
+}
+
+static void npe_start(struct npe *npe)
+{
+	/* ensure only Background Context Stack Level is active */
+	npe_clear_active(npe, ECS_PRI_1_CTXT_REG_0);
+	npe_clear_active(npe, ECS_PRI_2_CTXT_REG_0);
+	npe_clear_active(npe, ECS_DBG_CTXT_REG_0);
+
+	__raw_writel(CMD_NPE_CLR_PIPE, &npe->regs->exec_status_cmd);
+	__raw_writel(CMD_NPE_START, &npe->regs->exec_status_cmd);
+}
+
+static void npe_stop(struct npe *npe)
+{
+	__raw_writel(CMD_NPE_STOP, &npe->regs->exec_status_cmd);
+	__raw_writel(CMD_NPE_CLR_PIPE, &npe->regs->exec_status_cmd); /*FIXME?*/
+}
+
+static int __must_check npe_debug_instr(struct npe *npe, u32 instr, u32 ctx,
+					u32 ldur)
+{
+	u32 wc;
+	int i;
+
+	/* set the Active bit, and the LDUR, in the debug level */
+	npe_cmd_write(npe, ECS_DBG_CTXT_REG_0, CMD_WR_ECS_REG,
+		      ECS_REG_0_ACTIVE | (ldur << ECS_REG_0_LDUR_BITS));
+
+	/* set CCTXT at ECS DEBUG L3 to specify in which context to execute
+	   the instruction, and set SELCTXT at ECS DEBUG Level to specify
+	   which context store to access.
+	   Debug ECS Level Reg 1 has form 0x000n000n, where n = context number
+	*/
+	npe_cmd_write(npe, ECS_DBG_CTXT_REG_1, CMD_WR_ECS_REG,
+		      (ctx << ECS_REG_1_CCTXT_BITS) |
+		      (ctx << ECS_REG_1_SELCTXT_BITS));
+
+	/* clear the pipeline */
+	__raw_writel(CMD_NPE_CLR_PIPE, &npe->regs->exec_status_cmd);
+
+	/* load NPE instruction into the instruction register */
+	npe_cmd_write(npe, ECS_INSTRUCT_REG, CMD_WR_ECS_REG, instr);
+
+	/* we need this value later to wait for completion of NPE execution
+	   step */
+	wc = __raw_readl(&npe->regs->watch_count);
+
+	/* issue a Step One command via the Execution Control register */
+	__raw_writel(CMD_NPE_STEP, &npe->regs->exec_status_cmd);
+
+	/* Watch Count register increments when NPE completes an instruction */
+	for (i = 0; i < MAX_RETRIES; i++) {
+		if (wc != __raw_readl(&npe->regs->watch_count))
+			return 0;
+		udelay(1);
+	}
+
+	print_npe(KERN_ERR, npe, "reset: npe_debug_instr(): timeout\n");
+	return -ETIMEDOUT;
+}
+
+static int __must_check npe_logical_reg_write8(struct npe *npe, u32 addr,
+					       u8 val, u32 ctx)
+{
+	/* here we build the NPE assembler instruction: mov8 d0, #0 */
+	u32 instr = INSTR_WR_REG_BYTE |	/* OpCode */
+		addr << 9 |		/* base Operand */
+		(val & 0x1F) << 4 |	/* lower 5 bits to immediate data */
+		(val & ~0x1F) << (18 - 5);/* higher 3 bits to CoProc instr. */
+	return npe_debug_instr(npe, instr, ctx, 1); /* execute it */
+}
+
+static int __must_check npe_logical_reg_write16(struct npe *npe, u32 addr,
+						u16 val, u32 ctx)
+{
+	/* here we build the NPE assembler instruction: mov16 d0, #0 */
+	u32 instr = INSTR_WR_REG_SHORT | /* OpCode */
+		addr << 9 |		/* base Operand */
+		(val & 0x1F) << 4 |	/* lower 5 bits to immediate data */
+		(val & ~0x1F) << (18 - 5);/* higher 11 bits to CoProc instr. */
+	return npe_debug_instr(npe, instr, ctx, 1); /* execute it */
+}
+
+static int __must_check npe_logical_reg_write32(struct npe *npe, u32 addr,
+						u32 val, u32 ctx)
+{
+	/* write in 16 bit steps first the high and then the low value */
+	if (npe_logical_reg_write16(npe, addr, val >> 16, ctx))
+		return -ETIMEDOUT;
+	return npe_logical_reg_write16(npe, addr + 2, val & 0xFFFF, ctx);
+}
+
+static int npe_reset(struct npe *npe)
+{
+	u32 val, ctl, exec_count, ctx_reg2;
+	int i;
+
+	ctl = (__raw_readl(&npe->regs->messaging_control) | 0x3F000000) &
+		0x3F3FFFFF;
+
+	/* disable parity interrupt */
+	__raw_writel(ctl & 0x3F00FFFF, &npe->regs->messaging_control);
+
+	/* pre exec - debug instruction */
+	/* turn off the halt bit by clearing Execution Count register. */
+	exec_count = __raw_readl(&npe->regs->exec_count);
+	__raw_writel(0, &npe->regs->exec_count);
+	/* ensure that IF and IE are on (temporarily), so that we don't end up
+	   stepping forever */
+	ctx_reg2 = npe_cmd_read(npe, ECS_DBG_CTXT_REG_2, CMD_RD_ECS_REG);
+	npe_cmd_write(npe, ECS_DBG_CTXT_REG_2, CMD_WR_ECS_REG, ctx_reg2 |
+		      ECS_DBG_REG_2_IF | ECS_DBG_REG_2_IE);
+
+	/* clear the FIFOs */
+	while (__raw_readl(&npe->regs->watchpoint_fifo) & WFIFO_VALID)
+		;
+	while (__raw_readl(&npe->regs->messaging_status) & MSGSTAT_OFNE)
+		/* read from the outFIFO until empty */
+		print_npe(KERN_DEBUG, npe, "npe_reset: read FIFO = 0x%X\n",
+			  __raw_readl(&npe->regs->in_out_fifo));
+
+	while (__raw_readl(&npe->regs->messaging_status) & MSGSTAT_IFNE)
+		/* step execution of the NPE intruction to read inFIFO using
+		   the Debug Executing Context stack */
+		if (npe_debug_instr(npe, INSTR_RD_FIFO, 0, 0))
+			return -ETIMEDOUT;
+
+	/* reset the mailbox reg from the XScale side */
+	__raw_writel(RESET_MBOX_STAT, &npe->regs->mailbox_status);
+	/* from NPE side */
+	if (npe_debug_instr(npe, INSTR_RESET_MBOX, 0, 0))
+		return -ETIMEDOUT;
+
+	/* Reset the physical registers in the NPE register file */
+	for (val = 0; val < NPE_PHYS_REG; val++) {
+		if (npe_logical_reg_write16(npe, NPE_REGMAP, val >> 1, 0))
+			return -ETIMEDOUT;
+		/* address is either 0 or 4 */
+		if (npe_logical_reg_write32(npe, (val & 1) * 4, 0, 0))
+			return -ETIMEDOUT;
+	}
+
+	/* Reset the context store = each context's Context Store registers */
+
+	/* Context 0 has no STARTPC. Instead, this value is used to set NextPC
+	   for Background ECS, to set where NPE starts executing code */
+	val = npe_cmd_read(npe, ECS_BG_CTXT_REG_0, CMD_RD_ECS_REG);
+	val &= ~ECS_REG_0_NEXTPC_MASK;
+	val |= (0 /* NextPC */ << 16) & ECS_REG_0_NEXTPC_MASK;
+	npe_cmd_write(npe, ECS_BG_CTXT_REG_0, CMD_WR_ECS_REG, val);
+
+	for (i = 0; i < 16; i++) {
+		if (i) {	/* Context 0 has no STEVT nor STARTPC */
+			/* STEVT = off, 0x80 */
+			if (npe_logical_reg_write8(npe, NPE_STEVT, 0x80, i))
+				return -ETIMEDOUT;
+			if (npe_logical_reg_write16(npe, NPE_STARTPC, 0, i))
+				return -ETIMEDOUT;
+		}
+		/* REGMAP = d0->p0, d8->p2, d16->p4 */
+		if (npe_logical_reg_write16(npe, NPE_REGMAP, 0x820, i))
+			return -ETIMEDOUT;
+		if (npe_logical_reg_write8(npe, NPE_CINDEX, 0, i))
+			return -ETIMEDOUT;
+	}
+
+	/* post exec */
+	/* clear active bit in debug level */
+	npe_cmd_write(npe, ECS_DBG_CTXT_REG_0, CMD_WR_ECS_REG, 0);
+	/* clear the pipeline */
+	__raw_writel(CMD_NPE_CLR_PIPE, &npe->regs->exec_status_cmd);
+	/* restore previous values */
+	__raw_writel(exec_count, &npe->regs->exec_count);
+	npe_cmd_write(npe, ECS_DBG_CTXT_REG_2, CMD_WR_ECS_REG, ctx_reg2);
+
+	/* write reset values to Execution Context Stack registers */
+	for (val = 0; val < ARRAY_SIZE(ecs_reset); val++)
+		npe_cmd_write(npe, ecs_reset[val].reg, CMD_WR_ECS_REG,
+			      ecs_reset[val].val);
+
+	/* clear the profile counter */
+	__raw_writel(CMD_CLR_PROFILE_CNT, &npe->regs->exec_status_cmd);
+
+	__raw_writel(0, &npe->regs->exec_count);
+	__raw_writel(0, &npe->regs->action_points[0]);
+	__raw_writel(0, &npe->regs->action_points[1]);
+	__raw_writel(0, &npe->regs->action_points[2]);
+	__raw_writel(0, &npe->regs->action_points[3]);
+	__raw_writel(0, &npe->regs->watch_count);
+
+	val = ixp4xx_read_feature_bits();
+	/* reset the NPE */
+	ixp4xx_write_feature_bits(val &
+				  ~(IXP4XX_FEATURE_RESET_NPEA << npe->id));
+	for (i = 0; i < MAX_RETRIES; i++) {
+		if (!(ixp4xx_read_feature_bits() &
+		      (IXP4XX_FEATURE_RESET_NPEA << npe->id)))
+			break;	/* reset completed */
+		udelay(1);
+	}
+	if (i == MAX_RETRIES)
+		return -ETIMEDOUT;
+
+	/* deassert reset */
+	ixp4xx_write_feature_bits(val |
+				  (IXP4XX_FEATURE_RESET_NPEA << npe->id));
+	for (i = 0; i < MAX_RETRIES; i++) {
+		if (ixp4xx_read_feature_bits() &
+		    (IXP4XX_FEATURE_RESET_NPEA << npe->id))
+			break;	/* NPE is back alive */
+		udelay(1);
+	}
+	if (i == MAX_RETRIES)
+		return -ETIMEDOUT;
+
+	npe_stop(npe);
+
+	/* restore NPE configuration bus Control Register - parity settings */
+	__raw_writel(ctl, &npe->regs->messaging_control);
+	return 0;
+}
+
+
+int npe_send_message(struct npe *npe, const void *msg, const char *what)
+{
+	const u32 *send = msg;
+	int cycles = 0;
+
+	debug_msg(npe, "Trying to send message %s [%08X:%08X]\n",
+		  what, send[0], send[1]);
+
+	if (__raw_readl(&npe->regs->messaging_status) & MSGSTAT_IFNE) {
+		debug_msg(npe, "NPE input FIFO not empty\n");
+		return -EIO;
+	}
+
+	__raw_writel(send[0], &npe->regs->in_out_fifo);
+
+	if (!(__raw_readl(&npe->regs->messaging_status) & MSGSTAT_IFNF)) {
+		debug_msg(npe, "NPE input FIFO full\n");
+		return -EIO;
+	}
+
+	__raw_writel(send[1], &npe->regs->in_out_fifo);
+
+	while ((cycles < MAX_RETRIES) &&
+	       (__raw_readl(&npe->regs->messaging_status) & MSGSTAT_IFNE)) {
+		udelay(1);
+		cycles++;
+	}
+
+	if (cycles == MAX_RETRIES) {
+		debug_msg(npe, "Timeout sending message\n");
+		return -ETIMEDOUT;
+	}
+
+	debug_msg(npe, "Sending a message took %i cycles\n", cycles);
+	return 0;
+}
+
+int npe_recv_message(struct npe *npe, void *msg, const char *what)
+{
+	u32 *recv = msg;
+	int cycles = 0, cnt = 0;
+
+	debug_msg(npe, "Trying to receive message %s\n", what);
+
+	while (cycles < MAX_RETRIES) {
+		if (__raw_readl(&npe->regs->messaging_status) & MSGSTAT_OFNE) {
+			recv[cnt++] = __raw_readl(&npe->regs->in_out_fifo);
+			if (cnt == 2)
+				break;
+		} else {
+			udelay(1);
+			cycles++;
+		}
+	}
+
+	switch(cnt) {
+	case 1:
+		debug_msg(npe, "Received [%08X]\n", recv[0]);
+		break;
+	case 2:
+		debug_msg(npe, "Received [%08X:%08X]\n", recv[0], recv[1]);
+		break;
+	}
+
+	if (cycles == MAX_RETRIES) {
+		debug_msg(npe, "Timeout waiting for message\n");
+		return -ETIMEDOUT;
+	}
+
+	debug_msg(npe, "Receiving a message took %i cycles\n", cycles);
+	return 0;
+}
+
+int npe_send_recv_message(struct npe *npe, void *msg, const char *what)
+{
+	int result;
+	u32 *send = msg, recv[2];
+
+	if ((result = npe_send_message(npe, msg, what)) != 0)
+		return result;
+	if ((result = npe_recv_message(npe, recv, what)) != 0)
+		return result;
+
+	if ((recv[0] != send[0]) || (recv[1] != send[1])) {
+		debug_msg(npe, "Message %s: unexpected message received\n",
+			  what);
+		return -EIO;
+	}
+	return 0;
+}
+
+
+int npe_load_firmware(struct npe *npe, const char *name, struct device *dev)
+{
+	const struct firmware *fw_entry;
+
+	struct dl_block {
+		u32 type;
+		u32 offset;
+	} *blk;
+
+	struct dl_image {
+		u32 magic;
+		u32 id;
+		u32 size;
+		union {
+			u32 data[0];
+			struct dl_block blocks[0];
+		};
+	} *image;
+
+	struct dl_codeblock {
+		u32 npe_addr;
+		u32 size;
+		u32 data[0];
+	} *cb;
+
+	int i, j, err, data_size, instr_size, blocks, table_end;
+	u32 cmd;
+
+	if ((err = request_firmware(&fw_entry, name, dev)) != 0)
+		return err;
+
+	err = -EINVAL;
+	if (fw_entry->size < sizeof(struct dl_image)) {
+		print_npe(KERN_ERR, npe, "incomplete firmware file\n");
+		goto err;
+	}
+	image = (struct dl_image*)fw_entry->data;
+
+#if DEBUG_FW
+	print_npe(KERN_DEBUG, npe, "firmware: %08X %08X %08X (0x%X bytes)\n",
+		  image->magic, image->id, image->size, image->size * 4);
+#endif
+
+	if (image->magic == swab32(FW_MAGIC)) { /* swapped file */
+		image->id = swab32(image->id);
+		image->size = swab32(image->size);
+	} else if (image->magic != FW_MAGIC) {
+		print_npe(KERN_ERR, npe, "bad firmware file magic: 0x%X\n",
+			  image->magic);
+		goto err;
+	}
+	if ((image->size * 4 + sizeof(struct dl_image)) != fw_entry->size) {
+		print_npe(KERN_ERR, npe,
+			  "inconsistent size of firmware file\n");
+		goto err;
+	}
+	if (((image->id >> 24) & 0xF /* NPE ID */) != npe->id) {
+		print_npe(KERN_ERR, npe, "firmware file NPE ID mismatch\n");
+		goto err;
+	}
+	if (image->magic == swab32(FW_MAGIC))
+		for (i = 0; i < image->size; i++)
+			image->data[i] = swab32(image->data[i]);
+
+	if (!cpu_is_ixp46x() && ((image->id >> 28) & 0xF /* device ID */)) {
+		print_npe(KERN_INFO, npe, "IXP46x firmware ignored on "
+			  "IXP42x\n");
+		goto err;
+	}
+
+	if (npe_running(npe)) {
+		print_npe(KERN_INFO, npe, "unable to load firmware, NPE is "
+			  "already running\n");
+		err = -EBUSY;
+		goto err;
+	}
+#if 0
+	npe_stop(npe);
+	npe_reset(npe);
+#endif
+
+	print_npe(KERN_INFO, npe, "firmware functionality 0x%X, "
+		  "revision 0x%X:%X\n", (image->id >> 16) & 0xFF,
+		  (image->id >> 8) & 0xFF, image->id & 0xFF);
+
+	if (!cpu_is_ixp46x()) {
+		if (!npe->id)
+			instr_size = NPE_A_42X_INSTR_SIZE;
+		else
+			instr_size = NPE_B_AND_C_42X_INSTR_SIZE;
+		data_size = NPE_42X_DATA_SIZE;
+	} else {
+		instr_size = NPE_46X_INSTR_SIZE;
+		data_size = NPE_46X_DATA_SIZE;
+	}
+
+	for (blocks = 0; blocks * sizeof(struct dl_block) / 4 < image->size;
+	     blocks++)
+		if (image->blocks[blocks].type == FW_BLOCK_TYPE_EOF)
+			break;
+	if (blocks * sizeof(struct dl_block) / 4 >= image->size) {
+		print_npe(KERN_INFO, npe, "firmware EOF block marker not "
+			  "found\n");
+		goto err;
+	}
+
+#if DEBUG_FW
+	print_npe(KERN_DEBUG, npe, "%i firmware blocks found\n", blocks);
+#endif
+
+	table_end = blocks * sizeof(struct dl_block) / 4 + 1 /* EOF marker */;
+	for (i = 0, blk = image->blocks; i < blocks; i++, blk++) {
+		if (blk->offset > image->size - sizeof(struct dl_codeblock) / 4
+		    || blk->offset < table_end) {
+			print_npe(KERN_INFO, npe, "invalid offset 0x%X of "
+				  "firmware block #%i\n", blk->offset, i);
+			goto err;
+		}
+
+		cb = (struct dl_codeblock*)&image->data[blk->offset];
+		if (blk->type == FW_BLOCK_TYPE_INSTR) {
+			if (cb->npe_addr + cb->size > instr_size)
+				goto too_big;
+			cmd = CMD_WR_INS_MEM;
+		} else if (blk->type == FW_BLOCK_TYPE_DATA) {
+			if (cb->npe_addr + cb->size > data_size)
+				goto too_big;
+			cmd = CMD_WR_DATA_MEM;
+		} else {
+			print_npe(KERN_INFO, npe, "invalid firmware block #%i "
+				  "type 0x%X\n", i, blk->type);
+			goto err;
+		}
+		if (blk->offset + sizeof(*cb) / 4 + cb->size > image->size) {
+			print_npe(KERN_INFO, npe, "firmware block #%i doesn't "
+				  "fit in firmware image: type %c, start 0x%X,"
+				  " length 0x%X\n", i,
+				  blk->type == FW_BLOCK_TYPE_INSTR ? 'I' : 'D',
+				  cb->npe_addr, cb->size);
+			goto err;
+		}
+
+		for (j = 0; j < cb->size; j++)
+			npe_cmd_write(npe, cb->npe_addr + j, cmd, cb->data[j]);
+	}
+
+	npe_start(npe);
+	if (!npe_running(npe))
+		print_npe(KERN_ERR, npe, "unable to start\n");
+	release_firmware(fw_entry);
+	return 0;
+
+too_big:
+	print_npe(KERN_INFO, npe, "firmware block #%i doesn't fit in NPE "
+		  "memory: type %c, start 0x%X, length 0x%X\n", i,
+		  blk->type == FW_BLOCK_TYPE_INSTR ? 'I' : 'D',
+		  cb->npe_addr, cb->size);
+err:
+	release_firmware(fw_entry);
+	return err;
+}
+
+
+struct npe *npe_request(int id)
+{
+	if (id < NPE_COUNT)
+		if (npe_tab[id].valid)
+			if (try_module_get(THIS_MODULE))
+				return &npe_tab[id];
+	return NULL;
+}
+
+void npe_release(struct npe *npe)
+{
+	module_put(THIS_MODULE);
+}
+
+
+static int __init npe_init_module(void)
+{
+
+	int i, found = 0;
+
+	for (i = 0; i < NPE_COUNT; i++) {
+		struct npe *npe = &npe_tab[i];
+		if (!(ixp4xx_read_feature_bits() &
+		      (IXP4XX_FEATURE_RESET_NPEA << i)))
+			continue; /* NPE already disabled or not present */
+		if (!(npe->mem_res = request_mem_region(npe->regs_phys,
+							REGS_SIZE,
+							npe_name(npe)))) {
+			print_npe(KERN_ERR, npe,
+				  "failed to request memory region\n");
+			continue;
+		}
+
+		if (npe_reset(npe))
+			continue;
+		npe->valid = 1;
+		found++;
+	}
+
+	if (!found)
+		return -ENOSYS;
+	return 0;
+}
+
+static void __exit npe_cleanup_module(void)
+{
+	int i;
+
+	for (i = 0; i < NPE_COUNT; i++)
+		if (npe_tab[i].mem_res) {
+			npe_reset(&npe_tab[i]);
+			release_resource(npe_tab[i].mem_res);
+		}
+}
+
+module_init(npe_init_module);
+module_exit(npe_cleanup_module);
+
+MODULE_AUTHOR("Krzysztof Halasa");
+MODULE_LICENSE("GPL v2");
+
+EXPORT_SYMBOL(npe_names);
+EXPORT_SYMBOL(npe_running);
+EXPORT_SYMBOL(npe_request);
+EXPORT_SYMBOL(npe_release);
+EXPORT_SYMBOL(npe_load_firmware);
+EXPORT_SYMBOL(npe_send_message);
+EXPORT_SYMBOL(npe_recv_message);
+EXPORT_SYMBOL(npe_send_recv_message);
diff --git a/arch/arm/mach-ixp4xx/ixp4xx_qmgr.c b/arch/arm/mach-ixp4xx/ixp4xx_qmgr.c
new file mode 100644
index 0000000..e833013
--- /dev/null
+++ b/arch/arm/mach-ixp4xx/ixp4xx_qmgr.c
@@ -0,0 +1,274 @@
+/*
+ * Intel IXP4xx Queue Manager driver for Linux
+ *
+ * Copyright (C) 2007 Krzysztof Halasa <khc@pm.waw.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ */
+
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <asm/arch/qmgr.h>
+
+#define DEBUG		0
+
+struct qmgr_regs __iomem *qmgr_regs;
+static struct resource *mem_res;
+static spinlock_t qmgr_lock;
+static u32 used_sram_bitmap[4]; /* 128 16-dword pages */
+static void (*irq_handlers[HALF_QUEUES])(void *pdev);
+static void *irq_pdevs[HALF_QUEUES];
+
+void qmgr_set_irq(unsigned int queue, int src,
+		  void (*handler)(void *pdev), void *pdev)
+{
+	u32 __iomem *reg = &qmgr_regs->irqsrc[queue / 8]; /* 8 queues / u32 */
+	int bit = (queue % 8) * 4; /* 3 bits + 1 reserved bit per queue */
+	unsigned long flags;
+
+	src &= 7;
+	spin_lock_irqsave(&qmgr_lock, flags);
+	__raw_writel((__raw_readl(reg) & ~(7 << bit)) | (src << bit), reg);
+	irq_handlers[queue] = handler;
+	irq_pdevs[queue] = pdev;
+	spin_unlock_irqrestore(&qmgr_lock, flags);
+}
+
+
+static irqreturn_t qmgr_irq1(int irq, void *pdev)
+{
+	int i;
+	u32 val = __raw_readl(&qmgr_regs->irqstat[0]);
+	__raw_writel(val, &qmgr_regs->irqstat[0]); /* ACK */
+
+	for (i = 0; i < HALF_QUEUES; i++)
+		if (val & (1 << i))
+			irq_handlers[i](irq_pdevs[i]);
+
+	return val ? IRQ_HANDLED : 0;
+}
+
+
+void qmgr_enable_irq(unsigned int queue)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&qmgr_lock, flags);
+	__raw_writel(__raw_readl(&qmgr_regs->irqen[0]) | (1 << queue),
+		     &qmgr_regs->irqen[0]);
+	spin_unlock_irqrestore(&qmgr_lock, flags);
+}
+
+void qmgr_disable_irq(unsigned int queue)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&qmgr_lock, flags);
+	__raw_writel(__raw_readl(&qmgr_regs->irqen[0]) & ~(1 << queue),
+		     &qmgr_regs->irqen[0]);
+	spin_unlock_irqrestore(&qmgr_lock, flags);
+}
+
+static inline void shift_mask(u32 *mask)
+{
+	mask[3] = mask[3] << 1 | mask[2] >> 31;
+	mask[2] = mask[2] << 1 | mask[1] >> 31;
+	mask[1] = mask[1] << 1 | mask[0] >> 31;
+	mask[0] <<= 1;
+}
+
+int qmgr_request_queue(unsigned int queue, unsigned int len /* dwords */,
+		       unsigned int nearly_empty_watermark,
+		       unsigned int nearly_full_watermark)
+{
+	u32 cfg, addr = 0, mask[4]; /* in 16-dwords */
+	int err;
+
+	if (queue >= HALF_QUEUES)
+		return -ERANGE;
+
+	if ((nearly_empty_watermark | nearly_full_watermark) & ~7)
+		return -EINVAL;
+
+	switch (len) {
+	case  16:
+		cfg = 0 << 24;
+		mask[0] = 0x1;
+		break;
+	case  32:
+		cfg = 1 << 24;
+		mask[0] = 0x3;
+		break;
+	case  64:
+		cfg = 2 << 24;
+		mask[0] = 0xF;
+		break;
+	case 128:
+		cfg = 3 << 24;
+		mask[0] = 0xFF;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	cfg |= nearly_empty_watermark << 26;
+	cfg |= nearly_full_watermark << 29;
+	len /= 16;		/* in 16-dwords: 1, 2, 4 or 8 */
+	mask[1] = mask[2] = mask[3] = 0;
+
+	if (!try_module_get(THIS_MODULE))
+		return -ENODEV;
+
+	spin_lock_irq(&qmgr_lock);
+	if (__raw_readl(&qmgr_regs->sram[queue])) {
+		err = -EBUSY;
+		goto err;
+	}
+
+	while (1) {
+		if (!(used_sram_bitmap[0] & mask[0]) &&
+		    !(used_sram_bitmap[1] & mask[1]) &&
+		    !(used_sram_bitmap[2] & mask[2]) &&
+		    !(used_sram_bitmap[3] & mask[3]))
+			break; /* found free space */
+
+		addr++;
+		shift_mask(mask);
+		if (addr + len > ARRAY_SIZE(qmgr_regs->sram)) {
+			printk(KERN_ERR "qmgr: no free SRAM space for"
+			       " queue %i\n", queue);
+			err = -ENOMEM;
+			goto err;
+		}
+	}
+
+	used_sram_bitmap[0] |= mask[0];
+	used_sram_bitmap[1] |= mask[1];
+	used_sram_bitmap[2] |= mask[2];
+	used_sram_bitmap[3] |= mask[3];
+	__raw_writel(cfg | (addr << 14), &qmgr_regs->sram[queue]);
+	spin_unlock_irq(&qmgr_lock);
+
+#if DEBUG
+	printk(KERN_DEBUG "qmgr: requested queue %i, addr = 0x%02X\n",
+	       queue, addr);
+#endif
+	return 0;
+
+err:
+	spin_unlock_irq(&qmgr_lock);
+	module_put(THIS_MODULE);
+	return err;
+}
+
+void qmgr_release_queue(unsigned int queue)
+{
+	u32 cfg, addr, mask[4];
+
+	BUG_ON(queue >= HALF_QUEUES); /* not in valid range */
+
+	spin_lock_irq(&qmgr_lock);
+	cfg = __raw_readl(&qmgr_regs->sram[queue]);
+	addr = (cfg >> 14) & 0xFF;
+
+	BUG_ON(!addr);		/* not requested */
+
+	switch ((cfg >> 24) & 3) {
+	case 0: mask[0] = 0x1; break;
+	case 1: mask[0] = 0x3; break;
+	case 2: mask[0] = 0xF; break;
+	case 3: mask[0] = 0xFF; break;
+	}
+
+	while (addr--)
+		shift_mask(mask);
+
+	__raw_writel(0, &qmgr_regs->sram[queue]);
+
+	used_sram_bitmap[0] &= ~mask[0];
+	used_sram_bitmap[1] &= ~mask[1];
+	used_sram_bitmap[2] &= ~mask[2];
+	used_sram_bitmap[3] &= ~mask[3];
+	irq_handlers[queue] = NULL; /* catch IRQ bugs */
+	spin_unlock_irq(&qmgr_lock);
+
+	module_put(THIS_MODULE);
+#if DEBUG
+	printk(KERN_DEBUG "qmgr: released queue %i\n", queue);
+#endif
+}
+
+static int qmgr_init(void)
+{
+	int i, err;
+	mem_res = request_mem_region(IXP4XX_QMGR_BASE_PHYS,
+				     IXP4XX_QMGR_REGION_SIZE,
+				     "IXP4xx Queue Manager");
+	if (mem_res == NULL)
+		return -EBUSY;
+
+	qmgr_regs = ioremap(IXP4XX_QMGR_BASE_PHYS, IXP4XX_QMGR_REGION_SIZE);
+	if (qmgr_regs == NULL) {
+		err = -ENOMEM;
+		goto error_map;
+	}
+
+	/* reset qmgr registers */
+	for (i = 0; i < 4; i++) {
+		__raw_writel(0x33333333, &qmgr_regs->stat1[i]);
+		__raw_writel(0, &qmgr_regs->irqsrc[i]);
+	}
+	for (i = 0; i < 2; i++) {
+		__raw_writel(0, &qmgr_regs->stat2[i]);
+		__raw_writel(0xFFFFFFFF, &qmgr_regs->irqstat[i]); /* clear */
+		__raw_writel(0, &qmgr_regs->irqen[i]);
+	}
+
+	for (i = 0; i < QUEUES; i++)
+		__raw_writel(0, &qmgr_regs->sram[i]);
+
+	err = request_irq(IRQ_IXP4XX_QM1, qmgr_irq1, 0,
+			  "IXP4xx Queue Manager", NULL);
+	if (err) {
+		printk(KERN_ERR "qmgr: failed to request IRQ%i\n",
+		       IRQ_IXP4XX_QM1);
+		goto error_irq;
+	}
+
+	used_sram_bitmap[0] = 0xF; /* 4 first pages reserved for config */
+	spin_lock_init(&qmgr_lock);
+
+	printk(KERN_INFO "IXP4xx Queue Manager initialized.\n");
+	return 0;
+
+error_irq:
+	iounmap(qmgr_regs);
+error_map:
+	release_mem_region(IXP4XX_QMGR_BASE_PHYS, IXP4XX_QMGR_REGION_SIZE);
+	return err;
+}
+
+static void qmgr_remove(void)
+{
+	free_irq(IRQ_IXP4XX_QM1, NULL);
+	synchronize_irq(IRQ_IXP4XX_QM1);
+	iounmap(qmgr_regs);
+	release_mem_region(IXP4XX_QMGR_BASE_PHYS, IXP4XX_QMGR_REGION_SIZE);
+}
+
+module_init(qmgr_init);
+module_exit(qmgr_remove);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Krzysztof Halasa");
+
+EXPORT_SYMBOL(qmgr_regs);
+EXPORT_SYMBOL(qmgr_set_irq);
+EXPORT_SYMBOL(qmgr_enable_irq);
+EXPORT_SYMBOL(qmgr_disable_irq);
+EXPORT_SYMBOL(qmgr_request_queue);
+EXPORT_SYMBOL(qmgr_release_queue);
diff --git a/drivers/net/arm/Kconfig b/drivers/net/arm/Kconfig
index f9cc2b6..9274d3f 100644
--- a/drivers/net/arm/Kconfig
+++ b/drivers/net/arm/Kconfig
@@ -47,3 +47,13 @@ config EP93XX_ETH
 	help
 	  This is a driver for the ethernet hardware included in EP93xx CPUs.
 	  Say Y if you are building a kernel for EP93xx based devices.
+
+config IXP4XX_ETH
+	tristate "IXP4xx Ethernet support"
+	depends on NET_ETHERNET && ARM && ARCH_IXP4XX
+	select IXP4XX_NPE
+	select IXP4XX_QMGR
+	select MII
+	help
+	  Say Y here if you want to use built-in Ethernet ports
+	  on IXP4xx processor.
diff --git a/drivers/net/arm/Makefile b/drivers/net/arm/Makefile
index a4c8682..7c812ac 100644
--- a/drivers/net/arm/Makefile
+++ b/drivers/net/arm/Makefile
@@ -9,3 +9,4 @@ obj-$(CONFIG_ARM_ETHER3)	+= ether3.o
 obj-$(CONFIG_ARM_ETHER1)	+= ether1.o
 obj-$(CONFIG_ARM_AT91_ETHER)	+= at91_ether.o
 obj-$(CONFIG_EP93XX_ETH)	+= ep93xx_eth.o
+obj-$(CONFIG_IXP4XX_ETH)	+= ixp4xx_eth.o
diff --git a/drivers/net/arm/ixp4xx_eth.c b/drivers/net/arm/ixp4xx_eth.c
new file mode 100644
index 0000000..2c23f50
--- /dev/null
+++ b/drivers/net/arm/ixp4xx_eth.c
@@ -0,0 +1,1259 @@
+/*
+ * Intel IXP4xx Ethernet driver for Linux
+ *
+ * Copyright (C) 2007 Krzysztof Halasa <khc@pm.waw.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ *
+ * Ethernet port config (0x00 is not present on IXP42X):
+ *
+ * logical port		0x00		0x10		0x20
+ * NPE			0 (NPE-A)	1 (NPE-B)	2 (NPE-C)
+ * physical PortId	2		0		1
+ * TX queue		23		24		25
+ * RX-free queue	26		27		28
+ * TX-done queue is always 31, per-port RX and TX-ready queues are configurable
+ *
+ *
+ * Queue entries:
+ * bits 0 -> 1	- NPE ID (RX and TX-done)
+ * bits 0 -> 2	- priority (TX, per 802.1D)
+ * bits 3 -> 4	- port ID (user-set?)
+ * bits 5 -> 31	- physical descriptor address
+ */
+
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/etherdevice.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/mii.h>
+#include <linux/platform_device.h>
+#include <asm/arch/npe.h>
+#include <asm/arch/qmgr.h>
+
+#define DEBUG_QUEUES		0
+#define DEBUG_DESC		0
+#define DEBUG_RX		0
+#define DEBUG_TX		0
+#define DEBUG_PKT_BYTES		0
+#define DEBUG_MDIO		0
+#define DEBUG_CLOSE		0
+
+#define DRV_NAME		"ixp4xx_eth"
+
+#define MAX_NPES		3
+
+#define RX_DESCS		64 /* also length of all RX queues */
+#define TX_DESCS		16 /* also length of all TX queues */
+#define TXDONE_QUEUE_LEN	64 /* dwords */
+
+#define POOL_ALLOC_SIZE		(sizeof(struct desc) * (RX_DESCS + TX_DESCS))
+#define REGS_SIZE		0x1000
+#define MAX_MRU			1536 /* 0x600 */
+
+#define MDIO_INTERVAL		(3 * HZ)
+#define MAX_MDIO_RETRIES	100 /* microseconds, typically 30 cycles */
+#define MAX_MII_RESET_RETRIES	100 /* mdio_read() cycles, typically 4 */
+#define MAX_CLOSE_WAIT		1000 /* microseconds, typically 2-3 cycles */
+
+#define NPE_ID(port_id)		((port_id) >> 4)
+#define PHYSICAL_ID(port_id)	((NPE_ID(port_id) + 2) % 3)
+#define TX_QUEUE(port_id)	(NPE_ID(port_id) + 23)
+#define RXFREE_QUEUE(port_id)	(NPE_ID(port_id) + 26)
+#define TXDONE_QUEUE		31
+
+/* TX Control Registers */
+#define TX_CNTRL0_TX_EN		0x01
+#define TX_CNTRL0_HALFDUPLEX	0x02
+#define TX_CNTRL0_RETRY		0x04
+#define TX_CNTRL0_PAD_EN	0x08
+#define TX_CNTRL0_APPEND_FCS	0x10
+#define TX_CNTRL0_2DEFER	0x20
+#define TX_CNTRL0_RMII		0x40 /* reduced MII */
+#define TX_CNTRL1_RETRIES	0x0F /* 4 bits */
+
+/* RX Control Registers */
+#define RX_CNTRL0_RX_EN		0x01
+#define RX_CNTRL0_PADSTRIP_EN	0x02
+#define RX_CNTRL0_SEND_FCS	0x04
+#define RX_CNTRL0_PAUSE_EN	0x08
+#define RX_CNTRL0_LOOP_EN	0x10
+#define RX_CNTRL0_ADDR_FLTR_EN	0x20
+#define RX_CNTRL0_RX_RUNT_EN	0x40
+#define RX_CNTRL0_BCAST_DIS	0x80
+#define RX_CNTRL1_DEFER_EN	0x01
+
+/* Core Control Register */
+#define CORE_RESET		0x01
+#define CORE_RX_FIFO_FLUSH	0x02
+#define CORE_TX_FIFO_FLUSH	0x04
+#define CORE_SEND_JAM		0x08
+#define CORE_MDC_EN		0x10 /* MDIO using NPE-B ETH-0 only */
+
+#define DEFAULT_TX_CNTRL0	(TX_CNTRL0_TX_EN | TX_CNTRL0_RETRY |	\
+				 TX_CNTRL0_PAD_EN | TX_CNTRL0_APPEND_FCS | \
+				 TX_CNTRL0_2DEFER)
+#define DEFAULT_RX_CNTRL0	RX_CNTRL0_RX_EN
+#define DEFAULT_CORE_CNTRL	CORE_MDC_EN
+
+
+/* NPE message codes */
+#define NPE_GETSTATUS			0x00
+#define NPE_EDB_SETPORTADDRESS		0x01
+#define NPE_EDB_GETMACADDRESSDATABASE	0x02
+#define NPE_EDB_SETMACADDRESSSDATABASE	0x03
+#define NPE_GETSTATS			0x04
+#define NPE_RESETSTATS			0x05
+#define NPE_SETMAXFRAMELENGTHS		0x06
+#define NPE_VLAN_SETRXTAGMODE		0x07
+#define NPE_VLAN_SETDEFAULTRXVID	0x08
+#define NPE_VLAN_SETPORTVLANTABLEENTRY	0x09
+#define NPE_VLAN_SETPORTVLANTABLERANGE	0x0A
+#define NPE_VLAN_SETRXQOSENTRY		0x0B
+#define NPE_VLAN_SETPORTIDEXTRACTIONMODE 0x0C
+#define NPE_STP_SETBLOCKINGSTATE	0x0D
+#define NPE_FW_SETFIREWALLMODE		0x0E
+#define NPE_PC_SETFRAMECONTROLDURATIONID 0x0F
+#define NPE_PC_SETAPMACTABLE		0x11
+#define NPE_SETLOOPBACK_MODE		0x12
+#define NPE_PC_SETBSSIDTABLE		0x13
+#define NPE_ADDRESS_FILTER_CONFIG	0x14
+#define NPE_APPENDFCSCONFIG		0x15
+#define NPE_NOTIFY_MAC_RECOVERY_DONE	0x16
+#define NPE_MAC_RECOVERY_START		0x17
+
+
+#ifdef __ARMEB__
+typedef struct sk_buff buffer_t;
+#define free_buffer dev_kfree_skb
+#define free_buffer_irq dev_kfree_skb_irq
+#else
+typedef void buffer_t;
+#define free_buffer kfree
+#define free_buffer_irq kfree
+#endif
+
+struct eth_regs {
+	u32 tx_control[2], __res1[2];		/* 000 */
+	u32 rx_control[2], __res2[2];		/* 010 */
+	u32 random_seed, __res3[3];		/* 020 */
+	u32 partial_empty_threshold, __res4;	/* 030 */
+	u32 partial_full_threshold, __res5;	/* 038 */
+	u32 tx_start_bytes, __res6[3];		/* 040 */
+	u32 tx_deferral, rx_deferral,__res7[2];	/* 050 */
+	u32 tx_2part_deferral[2], __res8[2];	/* 060 */
+	u32 slot_time, __res9[3];		/* 070 */
+	u32 mdio_command[4];			/* 080 */
+	u32 mdio_status[4];			/* 090 */
+	u32 mcast_mask[6], __res10[2];		/* 0A0 */
+	u32 mcast_addr[6], __res11[2];		/* 0C0 */
+	u32 int_clock_threshold, __res12[3];	/* 0E0 */
+	u32 hw_addr[6], __res13[61];		/* 0F0 */
+	u32 core_control;			/* 1FC */
+};
+
+struct port {
+	struct resource *mem_res;
+	struct eth_regs __iomem *regs;
+	struct npe *npe;
+	struct net_device *netdev;
+	struct net_device_stats stat;
+	struct mii_if_info mii;
+	struct delayed_work mdio_thread;
+	struct eth_plat_info *plat;
+	buffer_t *rx_buff_tab[RX_DESCS], *tx_buff_tab[TX_DESCS];
+	struct desc *desc_tab;	/* coherent */
+	u32 desc_tab_phys;
+	int id;			/* logical port ID */
+	u16 mii_bmcr;
+};
+
+/* NPE message structure */
+struct msg {
+#ifdef __ARMEB__
+	u8 cmd, eth_id, byte2, byte3;
+	u8 byte4, byte5, byte6, byte7;
+#else
+	u8 byte3, byte2, eth_id, cmd;
+	u8 byte7, byte6, byte5, byte4;
+#endif
+};
+
+/* Ethernet packet descriptor */
+struct desc {
+	u32 next;		/* pointer to next buffer, unused */
+
+#ifdef __ARMEB__
+	u16 buf_len;		/* buffer length */
+	u16 pkt_len;		/* packet length */
+	u32 data;		/* pointer to data buffer in RAM */
+	u8 dest_id;
+	u8 src_id;
+	u16 flags;
+	u8 qos;
+	u8 padlen;
+	u16 vlan_tci;
+#else
+	u16 pkt_len;		/* packet length */
+	u16 buf_len;		/* buffer length */
+	u32 data;		/* pointer to data buffer in RAM */
+	u16 flags;
+	u8 src_id;
+	u8 dest_id;
+	u16 vlan_tci;
+	u8 padlen;
+	u8 qos;
+#endif
+
+#ifdef __ARMEB__
+	u8 dst_mac_0, dst_mac_1, dst_mac_2, dst_mac_3;
+	u8 dst_mac_4, dst_mac_5, src_mac_0, src_mac_1;
+	u8 src_mac_2, src_mac_3, src_mac_4, src_mac_5;
+#else
+	u8 dst_mac_3, dst_mac_2, dst_mac_1, dst_mac_0;
+	u8 src_mac_1, src_mac_0, dst_mac_5, dst_mac_4;
+	u8 src_mac_5, src_mac_4, src_mac_3, src_mac_2;
+#endif
+};
+
+
+#define rx_desc_phys(port, n)	((port)->desc_tab_phys +		\
+				 (n) * sizeof(struct desc))
+#define rx_desc_ptr(port, n)	(&(port)->desc_tab[n])
+
+#define tx_desc_phys(port, n)	((port)->desc_tab_phys +		\
+				 ((n) + RX_DESCS) * sizeof(struct desc))
+#define tx_desc_ptr(port, n)	(&(port)->desc_tab[(n) + RX_DESCS])
+
+#ifndef __ARMEB__
+static inline void memcpy_swab32(u32 *dest, u32 *src, int cnt)
+{
+	int i;
+	for (i = 0; i < cnt; i++)
+		dest[i] = swab32(src[i]);
+}
+#endif
+
+static spinlock_t mdio_lock;
+static struct eth_regs __iomem *mdio_regs; /* mdio command and status only */
+static int ports_open;
+static struct port *npe_port_tab[MAX_NPES];
+static struct dma_pool *dma_pool;
+
+
+static u16 mdio_cmd(struct net_device *dev, int phy_id, int location,
+		    int write, u16 cmd)
+{
+	int cycles = 0;
+
+	if (__raw_readl(&mdio_regs->mdio_command[3]) & 0x80) {
+		printk(KERN_ERR "%s: MII not ready to transmit\n", dev->name);
+		return 0;
+	}
+
+	if (write) {
+		__raw_writel(cmd & 0xFF, &mdio_regs->mdio_command[0]);
+		__raw_writel(cmd >> 8, &mdio_regs->mdio_command[1]);
+	}
+	__raw_writel(((phy_id << 5) | location) & 0xFF,
+		     &mdio_regs->mdio_command[2]);
+	__raw_writel((phy_id >> 3) | (write << 2) | 0x80 /* GO */,
+		     &mdio_regs->mdio_command[3]);
+
+	while ((cycles < MAX_MDIO_RETRIES) &&
+	       (__raw_readl(&mdio_regs->mdio_command[3]) & 0x80)) {
+		udelay(1);
+		cycles++;
+	}
+
+	if (cycles == MAX_MDIO_RETRIES) {
+		printk(KERN_ERR "%s: MII write failed\n", dev->name);
+		return 0;
+	}
+
+#if DEBUG_MDIO
+	printk(KERN_DEBUG "%s: mdio_cmd() took %i cycles\n", dev->name,
+	       cycles);
+#endif
+
+	if (write)
+		return 0;
+
+	if (__raw_readl(&mdio_regs->mdio_status[3]) & 0x80) {
+		printk(KERN_ERR "%s: MII read failed\n", dev->name);
+		return 0;
+	}
+
+	return (__raw_readl(&mdio_regs->mdio_status[0]) & 0xFF) |
+		(__raw_readl(&mdio_regs->mdio_status[1]) << 8);
+}
+
+static int mdio_read(struct net_device *dev, int phy_id, int location)
+{
+	unsigned long flags;
+	u16 val;
+
+	spin_lock_irqsave(&mdio_lock, flags);
+	val = mdio_cmd(dev, phy_id, location, 0, 0);
+	spin_unlock_irqrestore(&mdio_lock, flags);
+	return val;
+}
+
+static void mdio_write(struct net_device *dev, int phy_id, int location,
+		       int val)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&mdio_lock, flags);
+	mdio_cmd(dev, phy_id, location, 1, val);
+	spin_unlock_irqrestore(&mdio_lock, flags);
+}
+
+static void phy_reset(struct net_device *dev, int phy_id)
+{
+	struct port *port = netdev_priv(dev);
+	int cycles = 0;
+
+	mdio_write(dev, phy_id, MII_BMCR, port->mii_bmcr | BMCR_RESET);
+	
+	while (cycles < MAX_MII_RESET_RETRIES) {
+		if (!(mdio_read(dev, phy_id, MII_BMCR) & BMCR_RESET)) {
+#if DEBUG_MDIO
+			printk(KERN_DEBUG "%s: phy_reset() took %i cycles\n",
+			       dev->name, cycles);
+#endif
+			return;
+		}
+		udelay(1);
+		cycles++;
+	}
+
+	printk(KERN_ERR "%s: MII reset failed\n", dev->name);
+}
+
+static void eth_set_duplex(struct port *port)
+{
+	if (port->mii.full_duplex)
+		__raw_writel(DEFAULT_TX_CNTRL0 & ~TX_CNTRL0_HALFDUPLEX,
+			     &port->regs->tx_control[0]);
+	else
+		__raw_writel(DEFAULT_TX_CNTRL0 | TX_CNTRL0_HALFDUPLEX,
+			     &port->regs->tx_control[0]);
+}
+
+
+static void phy_check_media(struct port *port, int init)
+{
+	if (mii_check_media(&port->mii, 1, init))
+		eth_set_duplex(port);
+	if (port->mii.force_media) { /* mii_check_media() doesn't work */
+		struct net_device *dev = port->netdev;
+		int cur_link = mii_link_ok(&port->mii);
+		int prev_link = netif_carrier_ok(dev);
+
+		if (!prev_link && cur_link) {
+			printk(KERN_INFO "%s: link up\n", dev->name);
+			netif_carrier_on(dev);
+		} else if (prev_link && !cur_link) {
+			printk(KERN_INFO "%s: link down\n", dev->name);
+			netif_carrier_off(dev);
+		}
+	}
+}
+
+
+static void mdio_thread(struct work_struct *work)
+{
+	struct port *port = container_of(work, struct port, mdio_thread.work);
+
+	phy_check_media(port, 0);
+	schedule_delayed_work(&port->mdio_thread, MDIO_INTERVAL);
+}
+
+
+static inline void debug_pkt(struct net_device *dev, const char *func,
+			     u8 *data, int len)
+{
+#if DEBUG_PKT_BYTES
+	int i;
+
+	printk(KERN_DEBUG "%s: %s(%i) ", dev->name, func, len);
+	for (i = 0; i < len; i++) {
+		if (i >= DEBUG_PKT_BYTES)
+			break;
+		printk("%s%02X",
+		       ((i == 6) || (i == 12) || (i >= 14)) ? " " : "",
+		       data[i]);
+	}
+	printk("\n");
+#endif
+}
+
+
+static inline void debug_desc(u32 phys, struct desc *desc)
+{
+#if DEBUG_DESC
+	printk(KERN_DEBUG "%X: %X %3X %3X %08X %2X < %2X %4X %X"
+	       " %X %X %02X%02X%02X%02X%02X%02X < %02X%02X%02X%02X%02X%02X\n",
+	       phys, desc->next, desc->buf_len, desc->pkt_len,
+	       desc->data, desc->dest_id, desc->src_id, desc->flags,
+	       desc->qos, desc->padlen, desc->vlan_tci,
+	       desc->dst_mac_0, desc->dst_mac_1, desc->dst_mac_2,
+	       desc->dst_mac_3, desc->dst_mac_4, desc->dst_mac_5,
+	       desc->src_mac_0, desc->src_mac_1, desc->src_mac_2,
+	       desc->src_mac_3, desc->src_mac_4, desc->src_mac_5);
+#endif
+}
+
+static inline void debug_queue(unsigned int queue, int is_get, u32 phys)
+{
+#if DEBUG_QUEUES
+	static struct {
+		int queue;
+		char *name;
+	} names[] = {
+		{ TX_QUEUE(0x10), "TX#0 " },
+		{ TX_QUEUE(0x20), "TX#1 " },
+		{ TX_QUEUE(0x00), "TX#2 " },
+		{ RXFREE_QUEUE(0x10), "RX-free#0 " },
+		{ RXFREE_QUEUE(0x20), "RX-free#1 " },
+		{ RXFREE_QUEUE(0x00), "RX-free#2 " },
+		{ TXDONE_QUEUE, "TX-done " },
+	};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(names); i++)
+		if (names[i].queue == queue)
+			break;
+
+	printk(KERN_DEBUG "Queue %i %s%s %X\n", queue,
+	       i < ARRAY_SIZE(names) ? names[i].name : "",
+	       is_get ? "->" : "<-", phys);
+#endif
+}
+
+static inline u32 queue_get_entry(unsigned int queue)
+{
+	u32 phys = qmgr_get_entry(queue);
+	debug_queue(queue, 1, phys);
+	return phys;
+}
+
+static inline int queue_get_desc(unsigned int queue, struct port *port,
+				 int is_tx)
+{
+	u32 phys, tab_phys, n_desc;
+	struct desc *tab;
+
+	if (!(phys = queue_get_entry(queue)))
+		return -1;
+
+	phys &= ~0x1F; /* mask out non-address bits */
+	tab_phys = is_tx ? tx_desc_phys(port, 0) : rx_desc_phys(port, 0);
+	tab = is_tx ? tx_desc_ptr(port, 0) : rx_desc_ptr(port, 0);
+	n_desc = (phys - tab_phys) / sizeof(struct desc);
+	BUG_ON(n_desc >= (is_tx ? TX_DESCS : RX_DESCS));
+	debug_desc(phys, &tab[n_desc]);
+	BUG_ON(tab[n_desc].next);
+	return n_desc;
+}
+
+static inline void queue_put_desc(unsigned int queue, u32 phys,
+				  struct desc *desc)
+{
+	debug_queue(queue, 0, phys);
+	debug_desc(phys, desc);
+	BUG_ON(phys & 0x1F);
+	qmgr_put_entry(queue, phys);
+	BUG_ON(qmgr_stat_overflow(queue));
+}
+
+
+static inline void dma_unmap_tx(struct port *port, struct desc *desc)
+{
+#ifdef __ARMEB__
+	dma_unmap_single(&port->netdev->dev, desc->data,
+			 desc->buf_len, DMA_TO_DEVICE);
+#else
+	dma_unmap_single(&port->netdev->dev, desc->data & ~3,
+			 ALIGN((desc->data & 3) + desc->buf_len, 4),
+			 DMA_TO_DEVICE);
+#endif
+}
+
+
+static void eth_rx_irq(void *pdev)
+{
+	struct net_device *dev = pdev;
+	struct port *port = netdev_priv(dev);
+
+#if DEBUG_RX
+	printk(KERN_DEBUG "%s: eth_rx_irq\n", dev->name);
+#endif
+	qmgr_disable_irq(port->plat->rxq);
+	netif_rx_schedule(dev);
+}
+
+static int eth_poll(struct net_device *dev, int *budget)
+{
+	struct port *port = netdev_priv(dev);
+	unsigned int rxq = port->plat->rxq, rxfreeq = RXFREE_QUEUE(port->id);
+	int quota = dev->quota, received = 0;
+
+#if DEBUG_RX
+	printk(KERN_DEBUG "%s: eth_poll\n", dev->name);
+#endif
+
+	while (quota) {
+		struct sk_buff *skb;
+		struct desc *desc;
+		int n;
+#ifdef __ARMEB__
+		struct sk_buff *temp;
+		u32 phys;
+#endif
+
+		if ((n = queue_get_desc(rxq, port, 0)) < 0) {
+			dev->quota -= received;	/* No packet received */
+			*budget -= received;
+			received = 0;
+#if DEBUG_RX
+			printk(KERN_DEBUG "%s: eth_poll netif_rx_complete\n",
+			       dev->name);
+#endif
+			netif_rx_complete(dev);
+			qmgr_enable_irq(rxq);
+			if (!qmgr_stat_empty(rxq) &&
+			    netif_rx_reschedule(dev, 0)) {
+#if DEBUG_RX
+				printk(KERN_DEBUG "%s: eth_poll"
+				       " netif_rx_reschedule successed\n",
+				       dev->name);
+#endif
+				qmgr_disable_irq(rxq);
+				continue;
+			}
+#if DEBUG_RX
+			printk(KERN_DEBUG "%s: eth_poll all done\n",
+			       dev->name);
+#endif
+			return 0; /* all work done */
+		}
+
+		desc = rx_desc_ptr(port, n);
+
+#ifdef __ARMEB__
+		if ((skb = netdev_alloc_skb(dev, MAX_MRU)) != NULL) {
+			phys = dma_map_single(&dev->dev, skb->data,
+					      MAX_MRU, DMA_FROM_DEVICE);
+			if (dma_mapping_error(phys)) {
+				dev_kfree_skb(skb);
+				skb = NULL;
+			}
+		}
+#else
+		skb = netdev_alloc_skb(dev, desc->pkt_len);
+#endif
+
+		if (!skb) {
+			port->stat.rx_dropped++;
+			/* put the desc back on RX-ready queue */
+			desc->buf_len = MAX_MRU;
+			desc->pkt_len = 0;
+			queue_put_desc(rxfreeq, rx_desc_phys(port, n), desc);
+			continue;
+		}
+
+		/* process received frame */
+#ifdef __ARMEB__
+		temp = skb;
+		skb = port->rx_buff_tab[n];
+		dma_unmap_single(&dev->dev, desc->data,
+				 MAX_MRU, DMA_FROM_DEVICE);
+#else
+		dma_sync_single(&dev->dev, desc->data,
+				MAX_MRU, DMA_FROM_DEVICE);
+		memcpy_swab32((u32 *)skb->data, (u32 *)port->rx_buff_tab[n],
+			      ALIGN(desc->pkt_len, 4) / 4);
+#endif
+		skb_put(skb, desc->pkt_len);
+
+		debug_pkt(dev, "eth_poll", skb->data, skb->len);
+
+		skb->protocol = eth_type_trans(skb, dev);
+		dev->last_rx = jiffies;
+		port->stat.rx_packets++;
+		port->stat.rx_bytes += skb->len;
+		netif_receive_skb(skb);
+
+		/* put the new buffer on RX-free queue */
+#ifdef __ARMEB__
+		port->rx_buff_tab[n] = temp;
+		desc->data = phys;
+#endif
+		desc->buf_len = MAX_MRU;
+		desc->pkt_len = 0;
+		queue_put_desc(rxfreeq, rx_desc_phys(port, n), desc);
+		quota--;
+		received++;
+	}
+	dev->quota -= received;
+	*budget -= received;
+#if DEBUG_RX
+	printk(KERN_DEBUG "eth_poll(): end, not all work done\n");
+#endif
+	return 1;		/* not all work done */
+}
+
+
+static void eth_txdone_irq(void *unused)
+{
+	u32 phys;
+
+#if DEBUG_TX
+	printk(KERN_DEBUG DRV_NAME ": eth_txdone_irq\n");
+#endif
+	while ((phys = queue_get_entry(TXDONE_QUEUE)) != 0) {
+		u32 npe_id, n_desc;
+		struct port *port;
+		struct desc *desc;
+		int start;
+
+		npe_id = phys & 3;
+		BUG_ON(npe_id >= MAX_NPES);
+		port = npe_port_tab[npe_id];
+		BUG_ON(!port);
+		phys &= ~0x1F; /* mask out non-address bits */
+		n_desc = (phys - tx_desc_phys(port, 0)) / sizeof(struct desc);
+		BUG_ON(n_desc >= TX_DESCS);
+		desc = tx_desc_ptr(port, n_desc);
+		debug_desc(phys, desc);
+
+		if (port->tx_buff_tab[n_desc]) { /* not the draining packet */
+			port->stat.tx_packets++;
+			port->stat.tx_bytes += desc->pkt_len;
+
+			dma_unmap_tx(port, desc);
+#if DEBUG_TX
+			printk(KERN_DEBUG "%s: eth_txdone_irq free %p\n",
+			       port->netdev->name, port->tx_buff_tab[n_desc]);
+#endif
+			free_buffer_irq(port->tx_buff_tab[n_desc]);
+			port->tx_buff_tab[n_desc] = NULL;
+		}
+
+		start = qmgr_stat_empty(port->plat->txreadyq);
+		queue_put_desc(port->plat->txreadyq, phys, desc);
+		if (start) {
+#if DEBUG_TX
+			printk(KERN_DEBUG "%s: eth_txdone_irq xmit ready\n",
+			       port->netdev->name);
+#endif
+			netif_wake_queue(port->netdev);
+		}
+	}
+}
+
+static int eth_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct port *port = netdev_priv(dev);
+	unsigned int txreadyq = port->plat->txreadyq;
+	int len, offset, bytes, n;
+	void *mem;
+	u32 phys;
+	struct desc *desc;
+
+#if DEBUG_TX
+	printk(KERN_DEBUG "%s: eth_xmit\n", dev->name);
+#endif
+
+	if (unlikely(skb->len > MAX_MRU)) {
+		dev_kfree_skb(skb);
+		port->stat.tx_errors++;
+		return NETDEV_TX_OK;
+	}
+
+	debug_pkt(dev, "eth_xmit", skb->data, skb->len);
+
+	len = skb->len;
+#ifdef __ARMEB__
+	offset = 0; /* no need to keep alignment */
+	bytes = len;
+	mem = skb->data;
+#else
+	offset = (int)skb->data & 3; /* keep 32-bit alignment */
+	bytes = ALIGN(offset + len, 4);
+	if (!(mem = kmalloc(bytes, GFP_ATOMIC))) {
+		dev_kfree_skb(skb);
+		port->stat.tx_dropped++;
+		return NETDEV_TX_OK;
+	}
+	memcpy_swab32(mem, (u32 *)((int)skb->data & ~3), bytes / 4);
+	dev_kfree_skb(skb);
+#endif
+
+	phys = dma_map_single(&dev->dev, mem, bytes, DMA_TO_DEVICE);
+	if (dma_mapping_error(phys)) {
+#ifdef __ARMEB__
+		dev_kfree_skb(skb);
+#else
+		kfree(mem);
+#endif
+		port->stat.tx_dropped++;
+		return NETDEV_TX_OK;
+	}
+
+	n = queue_get_desc(txreadyq, port, 1);
+	BUG_ON(n < 0);
+	desc = tx_desc_ptr(port, n);
+
+#ifdef __ARMEB__
+	port->tx_buff_tab[n] = skb;
+#else
+	port->tx_buff_tab[n] = mem;
+#endif
+	desc->data = phys + offset;
+	desc->buf_len = desc->pkt_len = len;
+
+	/* NPE firmware pads short frames with zeros internally */
+	wmb();
+	queue_put_desc(TX_QUEUE(port->id), tx_desc_phys(port, n), desc);
+	dev->trans_start = jiffies;
+
+	if (qmgr_stat_empty(txreadyq)) {
+#if DEBUG_TX
+		printk(KERN_DEBUG "%s: eth_xmit queue full\n", dev->name);
+#endif
+		netif_stop_queue(dev);
+		/* we could miss TX ready interrupt */
+		if (!qmgr_stat_empty(txreadyq)) {
+#if DEBUG_TX
+			printk(KERN_DEBUG "%s: eth_xmit ready again\n",
+			       dev->name);
+#endif
+			netif_wake_queue(dev);
+		}
+	}
+
+#if DEBUG_TX
+	printk(KERN_DEBUG "%s: eth_xmit end\n", dev->name);
+#endif
+	return NETDEV_TX_OK;
+}
+
+
+static struct net_device_stats *eth_stats(struct net_device *dev)
+{
+	struct port *port = netdev_priv(dev);
+	return &port->stat;
+}
+
+static void eth_set_mcast_list(struct net_device *dev)
+{
+	struct port *port = netdev_priv(dev);
+	struct dev_mc_list *mclist = dev->mc_list;
+	u8 diffs[ETH_ALEN], *addr;
+	int cnt = dev->mc_count, i;
+
+	if ((dev->flags & IFF_PROMISC) || !mclist || !cnt) {
+		__raw_writel(DEFAULT_RX_CNTRL0 & ~RX_CNTRL0_ADDR_FLTR_EN,
+			     &port->regs->rx_control[0]);
+		return;
+	}
+
+	memset(diffs, 0, ETH_ALEN);
+	addr = mclist->dmi_addr; /* first MAC address */
+
+	while (--cnt && (mclist = mclist->next))
+		for (i = 0; i < ETH_ALEN; i++)
+			diffs[i] |= addr[i] ^ mclist->dmi_addr[i];
+
+	for (i = 0; i < ETH_ALEN; i++) {
+		__raw_writel(addr[i], &port->regs->mcast_addr[i]);
+		__raw_writel(~diffs[i], &port->regs->mcast_mask[i]);
+	}
+
+	__raw_writel(DEFAULT_RX_CNTRL0 | RX_CNTRL0_ADDR_FLTR_EN,
+		     &port->regs->rx_control[0]);
+}
+
+
+static int eth_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
+{
+	struct port *port = netdev_priv(dev);
+	unsigned int duplex_chg;
+	int err;
+
+	if (!netif_running(dev))
+		return -EINVAL;
+	err = generic_mii_ioctl(&port->mii, if_mii(req), cmd, &duplex_chg);
+	if (duplex_chg)
+		eth_set_duplex(port);
+	return err;
+}
+
+
+static int request_queues(struct port *port)
+{
+	int err;
+
+	err = qmgr_request_queue(RXFREE_QUEUE(port->id), RX_DESCS, 0, 0);
+	if (err)
+		return err;
+
+	err = qmgr_request_queue(port->plat->rxq, RX_DESCS, 0, 0);
+	if (err)
+		goto rel_rxfree;
+
+	err = qmgr_request_queue(TX_QUEUE(port->id), TX_DESCS, 0, 0);
+	if (err)
+		goto rel_rx;
+
+	err = qmgr_request_queue(port->plat->txreadyq, TX_DESCS, 0, 0);
+	if (err)
+		goto rel_tx;
+
+	/* TX-done queue handles skbs sent out by the NPEs */
+	if (!ports_open) {
+		err = qmgr_request_queue(TXDONE_QUEUE, TXDONE_QUEUE_LEN, 0, 0);
+		if (err)
+			goto rel_txready;
+	}
+	return 0;
+
+rel_txready:
+	qmgr_release_queue(port->plat->txreadyq);
+rel_tx:
+	qmgr_release_queue(TX_QUEUE(port->id));
+rel_rx:
+	qmgr_release_queue(port->plat->rxq);
+rel_rxfree:
+	qmgr_release_queue(RXFREE_QUEUE(port->id));
+	printk(KERN_DEBUG "%s: unable to request hardware queues\n",
+	       port->netdev->name);
+	return err;
+}
+
+static void release_queues(struct port *port)
+{
+	qmgr_release_queue(RXFREE_QUEUE(port->id));
+	qmgr_release_queue(port->plat->rxq);
+	qmgr_release_queue(TX_QUEUE(port->id));
+	qmgr_release_queue(port->plat->txreadyq);
+
+	if (!ports_open)
+		qmgr_release_queue(TXDONE_QUEUE);
+}
+
+static int init_queues(struct port *port)
+{
+	int i;
+
+	if (!ports_open)
+		if (!(dma_pool = dma_pool_create(DRV_NAME, NULL,
+						 POOL_ALLOC_SIZE, 32, 0)))
+			return -ENOMEM;
+
+	if (!(port->desc_tab = dma_pool_alloc(dma_pool, GFP_KERNEL,
+					      &port->desc_tab_phys)))
+		return -ENOMEM;
+	memset(port->desc_tab, 0, POOL_ALLOC_SIZE);
+	memset(port->rx_buff_tab, 0, sizeof(port->rx_buff_tab)); /* tables */
+	memset(port->tx_buff_tab, 0, sizeof(port->tx_buff_tab));
+
+	/* Setup RX buffers */
+	for (i = 0; i < RX_DESCS; i++) {
+		struct desc *desc = rx_desc_ptr(port, i);
+		buffer_t *buff;
+		void *data;
+#ifdef __ARMEB__
+		if (!(buff = netdev_alloc_skb(port->netdev, MAX_MRU)))
+			return -ENOMEM;
+		data = buff->data;
+#else
+		if (!(buff = kmalloc(MAX_MRU, GFP_KERNEL)))
+			return -ENOMEM;
+		data = buff;
+#endif
+		desc->buf_len = MAX_MRU;
+		desc->data = dma_map_single(&port->netdev->dev, data,
+					    MAX_MRU, DMA_FROM_DEVICE);
+		if (dma_mapping_error(desc->data)) {
+			free_buffer(buff);
+			return -EIO;
+		}
+		port->rx_buff_tab[i] = buff;
+	}
+
+	return 0;
+}
+
+static void destroy_queues(struct port *port)
+{
+	int i;
+
+	if (port->desc_tab) {
+		for (i = 0; i < RX_DESCS; i++) {
+			struct desc *desc = rx_desc_ptr(port, i);
+			buffer_t *buff = port->rx_buff_tab[i];
+			if (buff) {
+				dma_unmap_single(&port->netdev->dev,
+						 desc->data, MAX_MRU,
+						 DMA_FROM_DEVICE);
+				free_buffer(buff);
+			}
+		}
+		for (i = 0; i < TX_DESCS; i++) {
+			struct desc *desc = tx_desc_ptr(port, i);
+			buffer_t *buff = port->tx_buff_tab[i];
+			if (buff) {
+				dma_unmap_tx(port, desc);
+				free_buffer(buff);
+			}
+		}
+		dma_pool_free(dma_pool, port->desc_tab, port->desc_tab_phys);
+		port->desc_tab = NULL;
+	}
+
+	if (!ports_open && dma_pool) {
+		dma_pool_destroy(dma_pool);
+		dma_pool = NULL;
+	}
+}
+
+static int eth_open(struct net_device *dev)
+{
+	struct port *port = netdev_priv(dev);
+	struct npe *npe = port->npe;
+	struct msg msg;
+	int i, err;
+
+	if (!npe_running(npe)) {
+		err = npe_load_firmware(npe, npe_name(npe), &dev->dev);
+		if (err)
+			return err;
+
+		if (npe_recv_message(npe, &msg, "ETH_GET_STATUS")) {
+			printk(KERN_ERR "%s: %s not responding\n", dev->name,
+			       npe_name(npe));
+			return -EIO;
+		}
+	}
+
+	mdio_write(dev, port->plat->phy, MII_BMCR, port->mii_bmcr);
+
+	memset(&msg, 0, sizeof(msg));
+	msg.cmd = NPE_VLAN_SETRXQOSENTRY;
+	msg.eth_id = port->id;
+	msg.byte5 = port->plat->rxq | 0x80;
+	msg.byte7 = port->plat->rxq << 4;
+	for (i = 0; i < 8; i++) {
+		msg.byte3 = i;
+		if (npe_send_recv_message(port->npe, &msg, "ETH_SET_RXQ"))
+			return -EIO;
+	}
+
+	msg.cmd = NPE_EDB_SETPORTADDRESS;
+	msg.eth_id = PHYSICAL_ID(port->id);
+	msg.byte2 = dev->dev_addr[0];
+	msg.byte3 = dev->dev_addr[1];
+	msg.byte4 = dev->dev_addr[2];
+	msg.byte5 = dev->dev_addr[3];
+	msg.byte6 = dev->dev_addr[4];
+	msg.byte7 = dev->dev_addr[5];
+	if (npe_send_recv_message(port->npe, &msg, "ETH_SET_MAC"))
+		return -EIO;
+
+	memset(&msg, 0, sizeof(msg));
+	msg.cmd = NPE_FW_SETFIREWALLMODE;
+	msg.eth_id = port->id;
+	if (npe_send_recv_message(port->npe, &msg, "ETH_SET_FIREWALL_MODE"))
+		return -EIO;
+
+	if ((err = request_queues(port)) != 0)
+		return err;
+
+	if ((err = init_queues(port)) != 0) {
+		destroy_queues(port);
+		release_queues(port);
+		return err;
+	}
+
+	for (i = 0; i < ETH_ALEN; i++)
+		__raw_writel(dev->dev_addr[i], &port->regs->hw_addr[i]);
+	__raw_writel(0x08, &port->regs->random_seed);
+	__raw_writel(0x12, &port->regs->partial_empty_threshold);
+	__raw_writel(0x30, &port->regs->partial_full_threshold);
+	__raw_writel(0x08, &port->regs->tx_start_bytes);
+	__raw_writel(0x15, &port->regs->tx_deferral);
+	__raw_writel(0x08, &port->regs->tx_2part_deferral[0]);
+	__raw_writel(0x07, &port->regs->tx_2part_deferral[1]);
+	__raw_writel(0x80, &port->regs->slot_time);
+	__raw_writel(0x01, &port->regs->int_clock_threshold);
+
+	/* Populate queues with buffers, no failure after this point */
+	for (i = 0; i < TX_DESCS; i++)
+		queue_put_desc(port->plat->txreadyq,
+			       tx_desc_phys(port, i), tx_desc_ptr(port, i));
+
+	for (i = 0; i < RX_DESCS; i++)
+		queue_put_desc(RXFREE_QUEUE(port->id),
+			       rx_desc_phys(port, i), rx_desc_ptr(port, i));
+
+	__raw_writel(TX_CNTRL1_RETRIES, &port->regs->tx_control[1]);
+	__raw_writel(DEFAULT_TX_CNTRL0, &port->regs->tx_control[0]);
+	__raw_writel(0, &port->regs->rx_control[1]);
+	__raw_writel(DEFAULT_RX_CNTRL0, &port->regs->rx_control[0]);
+
+	phy_check_media(port, 1);
+	eth_set_mcast_list(dev);
+	netif_start_queue(dev);
+	schedule_delayed_work(&port->mdio_thread, MDIO_INTERVAL);
+
+	qmgr_set_irq(port->plat->rxq, QUEUE_IRQ_SRC_NOT_EMPTY,
+		     eth_rx_irq, dev);
+	if (!ports_open) {
+		qmgr_set_irq(TXDONE_QUEUE, QUEUE_IRQ_SRC_NOT_EMPTY,
+			     eth_txdone_irq, NULL);
+		qmgr_enable_irq(TXDONE_QUEUE);
+	}
+	ports_open++;
+	netif_rx_schedule(dev); /* we may already have RX data, enables IRQ */
+	return 0;
+}
+
+static int eth_close(struct net_device *dev)
+{
+	struct port *port = netdev_priv(dev);
+	struct msg msg;
+	int buffs = RX_DESCS; /* allocated RX buffers */
+	int i;
+
+	ports_open--;
+	qmgr_disable_irq(port->plat->rxq);
+	netif_stop_queue(dev);
+
+	while (queue_get_desc(RXFREE_QUEUE(port->id), port, 0) >= 0)
+		buffs--;
+
+	memset(&msg, 0, sizeof(msg));
+	msg.cmd = NPE_SETLOOPBACK_MODE;
+	msg.eth_id = port->id;
+	msg.byte3 = 1;
+	if (npe_send_recv_message(port->npe, &msg, "ETH_ENABLE_LOOPBACK"))
+		printk(KERN_CRIT "%s: unable to enable loopback\n", dev->name);
+
+	i = 0;
+	do {			/* drain RX buffers */
+		while (queue_get_desc(port->plat->rxq, port, 0) >= 0)
+			buffs--;
+		if (!buffs)
+			break;
+		if (qmgr_stat_empty(TX_QUEUE(port->id))) {
+			/* we have to inject some packet */
+			struct desc *desc;
+			u32 phys;
+			int n = queue_get_desc(port->plat->txreadyq, port, 1);
+			BUG_ON(n < 0);
+			desc = tx_desc_ptr(port, n);
+			phys = tx_desc_phys(port, n);
+			desc->buf_len = desc->pkt_len = 1;
+			wmb();
+			queue_put_desc(TX_QUEUE(port->id), phys, desc);
+		}
+		udelay(1);
+	} while (++i < MAX_CLOSE_WAIT);
+
+	if (buffs)
+		printk(KERN_CRIT "%s: unable to drain RX queue, %i buffer(s)"
+		       " left in NPE\n", dev->name, buffs);
+#if DEBUG_CLOSE
+	if (!buffs)
+		printk(KERN_DEBUG "Draining RX queue took %i cycles\n", i);
+#endif
+
+	buffs = TX_DESCS;
+	while (queue_get_desc(TX_QUEUE(port->id), port, 1) >= 0)
+		buffs--; /* cancel TX */
+
+	i = 0;
+	do {
+		while (queue_get_desc(port->plat->txreadyq, port, 1) >= 0)
+			buffs--;
+		if (!buffs)
+			break;
+	} while (++i < MAX_CLOSE_WAIT);
+
+	if (buffs)
+		printk(KERN_CRIT "%s: unable to drain TX queue, %i buffer(s) "
+		       "left in NPE\n", dev->name, buffs);
+#if DEBUG_CLOSE
+	if (!buffs)
+		printk(KERN_DEBUG "Draining TX queues took %i cycles\n", i);
+#endif
+
+	msg.byte3 = 0;
+	if (npe_send_recv_message(port->npe, &msg, "ETH_DISABLE_LOOPBACK"))
+		printk(KERN_CRIT "%s: unable to disable loopback\n",
+		       dev->name);
+
+	port->mii_bmcr = mdio_read(dev, port->plat->phy, MII_BMCR) &
+		~(BMCR_RESET | BMCR_PDOWN); /* may have been altered */
+	mdio_write(dev, port->plat->phy, MII_BMCR,
+		   port->mii_bmcr | BMCR_PDOWN);
+
+	if (!ports_open)
+		qmgr_disable_irq(TXDONE_QUEUE);
+	cancel_rearming_delayed_work(&port->mdio_thread);
+	destroy_queues(port);
+	release_queues(port);
+	return 0;
+}
+
+static int __devinit eth_init_one(struct platform_device *pdev)
+{
+	struct port *port;
+	struct net_device *dev;
+	struct eth_plat_info *plat = pdev->dev.platform_data;
+	u32 regs_phys;
+	int err;
+
+	if (!(dev = alloc_etherdev(sizeof(struct port))))
+		return -ENOMEM;
+
+	SET_MODULE_OWNER(dev);
+	SET_NETDEV_DEV(dev, &pdev->dev);
+	port = netdev_priv(dev);
+	port->netdev = dev;
+	port->id = pdev->id;
+
+	switch (port->id) {
+	case IXP4XX_ETH_NPEA:
+		port->regs = (struct eth_regs __iomem *)IXP4XX_EthA_BASE_VIRT;
+		regs_phys  = IXP4XX_EthA_BASE_PHYS;
+		break;
+	case IXP4XX_ETH_NPEB:
+		port->regs = (struct eth_regs __iomem *)IXP4XX_EthB_BASE_VIRT;
+		regs_phys  = IXP4XX_EthB_BASE_PHYS;
+		break;
+	case IXP4XX_ETH_NPEC:
+		port->regs = (struct eth_regs __iomem *)IXP4XX_EthC_BASE_VIRT;
+		regs_phys  = IXP4XX_EthC_BASE_PHYS;
+		break;
+	default:
+		err = -ENOSYS;
+		goto err_free;
+	}
+
+	dev->open = eth_open;
+	dev->hard_start_xmit = eth_xmit;
+	dev->poll = eth_poll;
+	dev->stop = eth_close;
+	dev->get_stats = eth_stats;
+	dev->do_ioctl = eth_ioctl;
+	dev->set_multicast_list = eth_set_mcast_list;
+	dev->weight = 16;
+	dev->tx_queue_len = 100;
+
+	if (!(port->npe = npe_request(NPE_ID(port->id)))) {
+		err = -EIO;
+		goto err_free;
+	}
+
+	if (register_netdev(dev)) {
+		err = -EIO;
+		goto err_npe_rel;
+	}
+
+	port->mem_res = request_mem_region(regs_phys, REGS_SIZE, dev->name);
+	if (!port->mem_res) {
+		err = -EBUSY;
+		goto err_unreg;
+	}
+
+	port->plat = plat;
+	npe_port_tab[NPE_ID(port->id)] = port;
+	memcpy(dev->dev_addr, plat->hwaddr, ETH_ALEN);
+
+	platform_set_drvdata(pdev, dev);
+
+	__raw_writel(DEFAULT_CORE_CNTRL | CORE_RESET,
+		     &port->regs->core_control);
+	udelay(50);
+	__raw_writel(DEFAULT_CORE_CNTRL, &port->regs->core_control);
+	udelay(50);
+
+	port->mii.dev = dev;
+	port->mii.mdio_read = mdio_read;
+	port->mii.mdio_write = mdio_write;
+	port->mii.phy_id = plat->phy;
+	port->mii.phy_id_mask = 0x1F;
+	port->mii.reg_num_mask = 0x1F;
+
+	printk(KERN_INFO "%s: MII PHY %i on %s\n", dev->name, plat->phy,
+	       npe_name(port->npe));
+
+	phy_reset(dev, plat->phy);
+	port->mii_bmcr = mdio_read(dev, plat->phy, MII_BMCR) &
+		~(BMCR_RESET | BMCR_PDOWN);
+	mdio_write(dev, plat->phy, MII_BMCR, port->mii_bmcr | BMCR_PDOWN);
+
+	INIT_DELAYED_WORK(&port->mdio_thread, mdio_thread);
+	return 0;
+
+err_unreg:
+	unregister_netdev(dev);
+err_npe_rel:
+	npe_release(port->npe);
+err_free:
+	free_netdev(dev);
+	return err;
+}
+
+static int __devexit eth_remove_one(struct platform_device *pdev)
+{
+	struct net_device *dev = platform_get_drvdata(pdev);
+	struct port *port = netdev_priv(dev);
+
+	unregister_netdev(dev);
+	npe_port_tab[NPE_ID(port->id)] = NULL;
+	platform_set_drvdata(pdev, NULL);
+	npe_release(port->npe);
+	release_resource(port->mem_res);
+	free_netdev(dev);
+	return 0;
+}
+
+static struct platform_driver drv = {
+	.driver.name	= DRV_NAME,
+	.probe		= eth_init_one,
+	.remove		= eth_remove_one,
+};
+
+static int __init eth_init_module(void)
+{
+	if (!(ixp4xx_read_feature_bits() & IXP4XX_FEATURE_NPEB_ETH0))
+		return -ENOSYS;
+
+	/* All MII PHY accesses use NPE-B Ethernet registers */
+	spin_lock_init(&mdio_lock);
+	mdio_regs = (struct eth_regs __iomem *)IXP4XX_EthB_BASE_VIRT;
+	__raw_writel(DEFAULT_CORE_CNTRL, &mdio_regs->core_control);
+
+	return platform_driver_register(&drv);
+}
+
+static void __exit eth_cleanup_module(void)
+{
+	platform_driver_unregister(&drv);
+}
+
+MODULE_AUTHOR("Krzysztof Halasa");
+MODULE_DESCRIPTION("Intel IXP4xx Ethernet driver");
+MODULE_LICENSE("GPL v2");
+module_init(eth_init_module);
+module_exit(eth_cleanup_module);
diff --git a/drivers/net/wan/Kconfig b/drivers/net/wan/Kconfig
index a3df09e..94e7aa7 100644
--- a/drivers/net/wan/Kconfig
+++ b/drivers/net/wan/Kconfig
@@ -334,6 +334,15 @@ config DSCC4_PCI_RST
 
 	  Say Y if your card supports this feature.
 
+config IXP4XX_HSS
+	tristate "IXP4xx HSS (synchronous serial port) support"
+	depends on HDLC && ARM && ARCH_IXP4XX
+	select IXP4XX_NPE
+	select IXP4XX_QMGR
+	help
+	  Say Y here if you want to use built-in HSS ports
+	  on IXP4xx processor.
+
 config DLCI
 	tristate "Frame Relay DLCI support"
 	---help---
diff --git a/drivers/net/wan/Makefile b/drivers/net/wan/Makefile
index d61fef3..1b1d116 100644
--- a/drivers/net/wan/Makefile
+++ b/drivers/net/wan/Makefile
@@ -42,6 +42,7 @@ obj-$(CONFIG_C101)		+= c101.o
 obj-$(CONFIG_WANXL)		+= wanxl.o
 obj-$(CONFIG_PCI200SYN)		+= pci200syn.o
 obj-$(CONFIG_PC300TOO)		+= pc300too.o
+obj-$(CONFIG_IXP4XX_HSS)	+= ixp4xx_hss.o
 
 clean-files := wanxlfw.inc
 $(obj)/wanxl.o:	$(obj)/wanxlfw.inc
diff --git a/drivers/net/wan/ixp4xx_hss.c b/drivers/net/wan/ixp4xx_hss.c
new file mode 100644
index 0000000..c4cdace
--- /dev/null
+++ b/drivers/net/wan/ixp4xx_hss.c
@@ -0,0 +1,1270 @@
+/*
+ * Intel IXP4xx HSS (synchronous serial port) driver for Linux
+ *
+ * Copyright (C) 2007 Krzysztof Halasa <khc@pm.waw.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/hdlc.h>
+#include <linux/platform_device.h>
+#include <asm/arch/npe.h>
+#include <asm/arch/qmgr.h>
+
+#define DEBUG_QUEUES		0
+#define DEBUG_DESC		0
+#define DEBUG_RX		0
+#define DEBUG_TX		0
+#define DEBUG_PKT_BYTES		0
+#define DEBUG_CLOSE		0
+
+#define DRV_NAME		"ixp4xx_hss"
+
+#define PKT_EXTRA_FLAGS		0 /* orig 1 */
+#define FRAME_SYNC_OFFSET	0 /* unused, channelized only */
+#define FRAME_SYNC_SIZE		1024
+#define PKT_NUM_PIPES		1 /* 1, 2 or 4 */
+#define PKT_PIPE_FIFO_SIZEW	4 /* total 4 dwords per HSS */
+
+#define RX_DESCS		16 /* also length of all RX queues */
+#define TX_DESCS		16 /* also length of all TX queues */
+
+#define POOL_ALLOC_SIZE		(sizeof(struct desc) * (RX_DESCS + TX_DESCS))
+#define RX_SIZE			(HDLC_MAX_MRU + 4) /* NPE needs more space */
+#define MAX_CLOSE_WAIT		1000 /* microseconds */
+
+/* Queue IDs */
+#define HSS0_CHL_RXTRIG_QUEUE	12	/* orig size = 32 dwords */
+#define HSS0_PKT_RX_QUEUE	13	/* orig size = 32 dwords */
+#define HSS0_PKT_TX0_QUEUE	14	/* orig size = 16 dwords */
+#define HSS0_PKT_TX1_QUEUE	15
+#define HSS0_PKT_TX2_QUEUE	16
+#define HSS0_PKT_TX3_QUEUE	17
+#define HSS0_PKT_RXFREE0_QUEUE	18	/* orig size = 16 dwords */
+#define HSS0_PKT_RXFREE1_QUEUE	19
+#define HSS0_PKT_RXFREE2_QUEUE	20
+#define HSS0_PKT_RXFREE3_QUEUE	21
+#define HSS0_PKT_TXDONE_QUEUE	22	/* orig size = 64 dwords */
+
+#define HSS1_CHL_RXTRIG_QUEUE	10
+#define HSS1_PKT_RX_QUEUE	0
+#define HSS1_PKT_TX0_QUEUE	5
+#define HSS1_PKT_TX1_QUEUE	6
+#define HSS1_PKT_TX2_QUEUE	7
+#define HSS1_PKT_TX3_QUEUE	8
+#define HSS1_PKT_RXFREE0_QUEUE	1
+#define HSS1_PKT_RXFREE1_QUEUE	2
+#define HSS1_PKT_RXFREE2_QUEUE	3
+#define HSS1_PKT_RXFREE3_QUEUE	4
+#define HSS1_PKT_TXDONE_QUEUE	9
+
+#define NPE_PKT_MODE_HDLC		0
+#define NPE_PKT_MODE_RAW		1
+#define NPE_PKT_MODE_56KMODE		2
+#define NPE_PKT_MODE_56KENDIAN_MSB	4
+
+/* PKT_PIPE_HDLC_CFG_WRITE flags */
+#define PKT_HDLC_IDLE_ONES		0x1 /* default = flags */
+#define PKT_HDLC_CRC_32			0x2 /* default = CRC-16 */
+#define PKT_HDLC_MSB_ENDIAN		0x4 /* default = LE */
+
+
+/* hss_config, PCRs */
+/* Frame sync sampling, default = active low */
+#define PCR_FRM_SYNC_ACTIVE_HIGH	0x40000000
+#define PCR_FRM_SYNC_FALLINGEDGE	0x80000000
+#define PCR_FRM_SYNC_RISINGEDGE		0xC0000000
+
+/* Frame sync pin: input (default) or output generated off a given clk edge */
+#define PCR_FRM_SYNC_OUTPUT_FALLING	0x20000000
+#define PCR_FRM_SYNC_OUTPUT_RISING	0x30000000
+
+/* Frame and data clock sampling on edge, default = falling */
+#define PCR_FCLK_EDGE_RISING		0x08000000
+#define PCR_DCLK_EDGE_RISING		0x04000000
+
+/* Clock direction, default = input */
+#define PCR_SYNC_CLK_DIR_OUTPUT		0x02000000
+
+/* Generate/Receive frame pulses, default = enabled */
+#define PCR_FRM_PULSE_DISABLED		0x01000000
+
+ /* Data rate is full (default) or half the configured clk speed */
+#define PCR_HALF_CLK_RATE		0x00200000
+
+/* Invert data between NPE and HSS FIFOs? (default = no) */
+#define PCR_DATA_POLARITY_INVERT	0x00100000
+
+/* TX/RX endianness, default = LSB */
+#define PCR_MSB_ENDIAN			0x00080000
+
+/* Normal (default) / open drain mode (TX only) */
+#define PCR_TX_PINS_OPEN_DRAIN		0x00040000
+
+/* No framing bit transmitted and expected on RX? (default = framing bit) */
+#define PCR_SOF_NO_FBIT			0x00020000
+
+/* Drive data pins? */
+#define PCR_TX_DATA_ENABLE		0x00010000
+
+/* Voice 56k type: drive the data pins low (default), high, high Z */
+#define PCR_TX_V56K_HIGH		0x00002000
+#define PCR_TX_V56K_HIGH_IMP		0x00004000
+
+/* Unassigned type: drive the data pins low (default), high, high Z */
+#define PCR_TX_UNASS_HIGH		0x00000800
+#define PCR_TX_UNASS_HIGH_IMP		0x00001000
+
+/* T1 @ 1.544MHz only: Fbit dictated in FIFO (default) or high Z */
+#define PCR_TX_FB_HIGH_IMP		0x00000400
+
+/* 56k data endiannes - which bit unused: high (default) or low */
+#define PCR_TX_56KE_BIT_0_UNUSED	0x00000200
+
+/* 56k data transmission type: 32/8 bit data (default) or 56K data */
+#define PCR_TX_56KS_56K_DATA		0x00000100
+
+/* hss_config, cCR */
+/* Number of packetized clients, default = 1 */
+#define CCR_NPE_HFIFO_2_HDLC		0x04000000
+#define CCR_NPE_HFIFO_3_OR_4HDLC	0x08000000
+
+/* default = no loopback */
+#define CCR_LOOPBACK			0x02000000
+
+/* HSS number, default = 0 (first) */
+#define CCR_SECOND_HSS			0x01000000
+
+
+/* hss_config, clkCR: main:10, num:10, denom:12 */
+#define CLK42X_SPEED_EXP	((0x3FF << 22) | (  2 << 12) |   15) /*65 KHz*/
+
+#define CLK42X_SPEED_512KHZ	((  130 << 22) | (  2 << 12) |   15)
+#define CLK42X_SPEED_1536KHZ	((   43 << 22) | ( 18 << 12) |   47)
+#define CLK42X_SPEED_1544KHZ	((   43 << 22) | ( 33 << 12) |  192)
+#define CLK42X_SPEED_2048KHZ	((   32 << 22) | ( 34 << 12) |   63)
+#define CLK42X_SPEED_4096KHZ	((   16 << 22) | ( 34 << 12) |  127)
+#define CLK42X_SPEED_8192KHZ	((    8 << 22) | ( 34 << 12) |  255)
+
+#define CLK46X_SPEED_512KHZ	((  130 << 22) | ( 24 << 12) |  127)
+#define CLK46X_SPEED_1536KHZ	((   43 << 22) | (152 << 12) |  383)
+#define CLK46X_SPEED_1544KHZ	((   43 << 22) | ( 66 << 12) |  385)
+#define CLK46X_SPEED_2048KHZ	((   32 << 22) | (280 << 12) |  511)
+#define CLK46X_SPEED_4096KHZ	((   16 << 22) | (280 << 12) | 1023)
+#define CLK46X_SPEED_8192KHZ	((    8 << 22) | (280 << 12) | 2047)
+
+
+/* hss_config, LUT entries */
+#define TDMMAP_UNASSIGNED	0
+#define TDMMAP_HDLC		1	/* HDLC - packetized */
+#define TDMMAP_VOICE56K		2	/* Voice56K - 7-bit channelized */
+#define TDMMAP_VOICE64K		3	/* Voice64K - 8-bit channelized */
+
+#define TIMESLOTS		128
+#define LUT_BITS		2
+
+/* offsets into HSS config */
+#define HSS_CONFIG_TX_PCR	0x00
+#define HSS_CONFIG_RX_PCR	0x04
+#define HSS_CONFIG_CORE_CR	0x08
+#define HSS_CONFIG_CLOCK_CR	0x0C
+#define HSS_CONFIG_TX_FCR	0x10
+#define HSS_CONFIG_RX_FCR	0x14
+#define HSS_CONFIG_TX_LUT	0x18
+#define HSS_CONFIG_RX_LUT	0x38
+
+
+/* NPE command codes */
+/* writes the ConfigWord value to the location specified by offset */
+#define PORT_CONFIG_WRITE			0x40
+
+/* triggers the NPE to load the contents of the configuration table */
+#define PORT_CONFIG_LOAD			0x41
+
+/* triggers the NPE to return an HssErrorReadResponse message */
+#define PORT_ERROR_READ				0x42
+
+/* reset NPE internal status and enable the HssChannelized operation */
+#define CHAN_FLOW_ENABLE			0x43
+#define CHAN_FLOW_DISABLE			0x44
+#define CHAN_IDLE_PATTERN_WRITE			0x45
+#define CHAN_NUM_CHANS_WRITE			0x46
+#define CHAN_RX_BUF_ADDR_WRITE			0x47
+#define CHAN_RX_BUF_CFG_WRITE			0x48
+#define CHAN_TX_BLK_CFG_WRITE			0x49
+#define CHAN_TX_BUF_ADDR_WRITE			0x4A
+#define CHAN_TX_BUF_SIZE_WRITE			0x4B
+#define CHAN_TSLOTSWITCH_ENABLE			0x4C
+#define CHAN_TSLOTSWITCH_DISABLE		0x4D
+
+/* downloads the gainWord value for a timeslot switching channel associated
+   with bypassNum */
+#define CHAN_TSLOTSWITCH_GCT_DOWNLOAD		0x4E
+
+/* triggers the NPE to reset internal status and enable the HssPacketized
+   operation for the flow specified by pPipe */
+#define PKT_PIPE_FLOW_ENABLE			0x50
+#define PKT_PIPE_FLOW_DISABLE			0x51
+#define PKT_NUM_PIPES_WRITE			0x52
+#define PKT_PIPE_FIFO_SIZEW_WRITE		0x53
+#define PKT_PIPE_HDLC_CFG_WRITE			0x54
+#define PKT_PIPE_IDLE_PATTERN_WRITE		0x55
+#define PKT_PIPE_RX_SIZE_WRITE			0x56
+#define PKT_PIPE_MODE_WRITE			0x57
+
+/* HDLC packet status values - desc->status */
+#define ERR_SHUTDOWN		1 /* stop or shutdown occurrance */
+#define ERR_HDLC_ALIGN		2 /* HDLC alignment error */
+#define ERR_HDLC_FCS		3 /* HDLC Frame Check Sum error */
+#define ERR_RXFREE_Q_EMPTY	4 /* RX-free queue became empty while receiving
+				     this packet (if buf_len < pkt_len) */
+#define ERR_HDLC_TOO_LONG	5 /* HDLC frame size too long */
+#define ERR_HDLC_ABORT		6 /* abort sequence received */
+#define ERR_DISCONNECTING	7 /* disconnect is in progress */
+
+
+#ifdef __ARMEB__
+typedef struct sk_buff buffer_t;
+#define free_buffer dev_kfree_skb
+#define free_buffer_irq dev_kfree_skb_irq
+#else
+typedef void buffer_t;
+#define free_buffer kfree
+#define free_buffer_irq kfree
+#endif
+
+struct port {
+	struct npe *npe;
+	struct net_device *netdev;
+	struct hss_plat_info *plat;
+	buffer_t *rx_buff_tab[RX_DESCS], *tx_buff_tab[TX_DESCS];
+	struct desc *desc_tab;	/* coherent */
+	u32 desc_tab_phys;
+	int id;
+	unsigned int clock_type, clock_rate, loopback;
+	u8 hdlc_cfg;
+};
+
+/* NPE message structure */
+struct msg {
+#ifdef __ARMEB__
+	u8 cmd, unused, hss_port, index;
+	union {
+		struct { u8 data8a, data8b, data8c, data8d; };
+		struct { u16 data16a, data16b; };
+		struct { u32 data32; };
+	};
+#else
+	u8 index, hss_port, unused, cmd;
+	union {
+		struct { u8 data8d, data8c, data8b, data8a; };
+		struct { u16 data16b, data16a; };
+		struct { u32 data32; };
+	};
+#endif
+};
+
+/* HDLC packet descriptor */
+struct desc {
+	u32 next;		/* pointer to next buffer, unused */
+
+#ifdef __ARMEB__
+	u16 buf_len;		/* buffer length */
+	u16 pkt_len;		/* packet length */
+	u32 data;		/* pointer to data buffer in RAM */
+	u8 status;
+	u8 error_count;
+	u16 __reserved;
+#else
+	u16 pkt_len;		/* packet length */
+	u16 buf_len;		/* buffer length */
+	u32 data;		/* pointer to data buffer in RAM */
+	u16 __reserved;
+	u8 error_count;
+	u8 status;
+#endif
+	u32 __reserved1[4];
+};
+
+
+#define rx_desc_phys(port, n)	((port)->desc_tab_phys +		\
+				 (n) * sizeof(struct desc))
+#define rx_desc_ptr(port, n)	(&(port)->desc_tab[n])
+
+#define tx_desc_phys(port, n)	((port)->desc_tab_phys +		\
+				 ((n) + RX_DESCS) * sizeof(struct desc))
+#define tx_desc_ptr(port, n)	(&(port)->desc_tab[(n) + RX_DESCS])
+
+/*****************************************************************************
+ * global variables
+ ****************************************************************************/
+
+static int ports_open;
+static struct dma_pool *dma_pool;
+
+static const struct {
+	int tx, txdone, rx, rxfree;
+}queue_ids[2] = {{ HSS0_PKT_TX0_QUEUE, HSS0_PKT_TXDONE_QUEUE,
+		   HSS0_PKT_RX_QUEUE, HSS0_PKT_RXFREE0_QUEUE },
+		 { HSS1_PKT_TX0_QUEUE, HSS1_PKT_TXDONE_QUEUE,
+		   HSS1_PKT_RX_QUEUE, HSS1_PKT_RXFREE0_QUEUE },
+};
+
+/*****************************************************************************
+ * utility functions
+ ****************************************************************************/
+
+static inline struct port* dev_to_port(struct net_device *dev)
+{
+	return dev_to_hdlc(dev)->priv;
+}
+
+#ifndef __ARMEB__
+static inline void memcpy_swab32(u32 *dest, u32 *src, int cnt)
+{
+	int i;
+	for (i = 0; i < cnt; i++)
+		dest[i] = swab32(src[i]);
+}
+#endif
+
+static inline void debug_pkt(struct net_device *dev, const char *func,
+			     u8 *data, int len)
+{
+#if DEBUG_PKT_BYTES
+	int i;
+
+	printk(KERN_DEBUG "%s: %s(%i) ", dev->name, func, len);
+	for (i = 0; i < len; i++) {
+		if (i >= DEBUG_PKT_BYTES)
+			break;
+		printk("%s%02X", !(i % 4) ? " " : "", data[i]);
+	}
+	printk("\n");
+#endif
+}
+
+
+static inline void debug_desc(u32 phys, struct desc *desc)
+{
+#if DEBUG_DESC
+	printk(KERN_DEBUG "%X: %X %3X %3X %08X %X %X\n",
+	       phys, desc->next, desc->buf_len, desc->pkt_len,
+	       desc->data, desc->status, desc->error_count);
+#endif
+}
+
+static inline void debug_queue(unsigned int queue, int is_get, u32 phys)
+{
+#if DEBUG_QUEUES
+	static struct {
+		int queue;
+		char *name;
+	} names[] = {
+		{ HSS0_PKT_TX0_QUEUE, "TX#0 " },
+		{ HSS0_PKT_TXDONE_QUEUE, "TX-done#0 " },
+		{ HSS0_PKT_RX_QUEUE, "RX#0 " },
+		{ HSS0_PKT_RXFREE0_QUEUE, "RX-free#0 " },
+		{ HSS1_PKT_TX0_QUEUE, "TX#1 " },
+		{ HSS1_PKT_TXDONE_QUEUE, "TX-done#1 " },
+		{ HSS1_PKT_RX_QUEUE, "RX#1 " },
+		{ HSS1_PKT_RXFREE0_QUEUE, "RX-free#1 " },
+	};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(names); i++)
+		if (names[i].queue == queue)
+			break;
+
+	printk(KERN_DEBUG "Queue %i %s%s %X\n", queue,
+	       i < ARRAY_SIZE(names) ? names[i].name : "",
+	       is_get ? "->" : "<-", phys);
+#endif
+}
+
+static inline u32 queue_get_entry(unsigned int queue)
+{
+	u32 phys = qmgr_get_entry(queue);
+	debug_queue(queue, 1, phys);
+	return phys;
+}
+
+static inline int queue_get_desc(unsigned int queue, struct port *port,
+				 int is_tx)
+{
+	u32 phys, tab_phys, n_desc;
+	struct desc *tab;
+
+	if (!(phys = queue_get_entry(queue)))
+		return -1;
+
+	BUG_ON(phys & 0x1F);
+	tab_phys = is_tx ? tx_desc_phys(port, 0) : rx_desc_phys(port, 0);
+	tab = is_tx ? tx_desc_ptr(port, 0) : rx_desc_ptr(port, 0);
+	n_desc = (phys - tab_phys) / sizeof(struct desc);
+	BUG_ON(n_desc >= (is_tx ? TX_DESCS : RX_DESCS));
+	debug_desc(phys, &tab[n_desc]);
+	BUG_ON(tab[n_desc].next);
+	return n_desc;
+}
+
+static inline void queue_put_desc(unsigned int queue, u32 phys,
+				  struct desc *desc)
+{
+	debug_queue(queue, 0, phys);
+	debug_desc(phys, desc);
+	BUG_ON(phys & 0x1F);
+	qmgr_put_entry(queue, phys);
+	BUG_ON(qmgr_stat_overflow(queue));
+}
+
+
+static inline void dma_unmap_tx(struct port *port, struct desc *desc)
+{
+#ifdef __ARMEB__
+	dma_unmap_single(&port->netdev->dev, desc->data,
+			 desc->buf_len, DMA_TO_DEVICE);
+#else
+	dma_unmap_single(&port->netdev->dev, desc->data & ~3,
+			 ALIGN((desc->data & 3) + desc->buf_len, 4),
+			 DMA_TO_DEVICE);
+#endif
+}
+
+
+static void hss_hdlc_set_carrier(void *pdev, int carrier)
+{
+	struct net_device *dev = pdev;
+	if (carrier)
+		netif_carrier_on(dev);
+	else
+		netif_carrier_off(dev);
+}
+
+static void hss_hdlc_rx_irq(void *pdev)
+{
+	struct net_device *dev = pdev;
+	struct port *port = dev_to_port(dev);
+
+#if DEBUG_RX
+	printk(KERN_DEBUG "%s: hss_hdlc_rx_irq\n", dev->name);
+#endif
+	qmgr_disable_irq(queue_ids[port->id].rx);
+	netif_rx_schedule(dev);
+}
+
+static int hss_hdlc_poll(struct net_device *dev, int *budget)
+{
+	struct port *port = dev_to_port(dev);
+	unsigned int rxq = queue_ids[port->id].rx;
+	unsigned int rxfreeq = queue_ids[port->id].rxfree;
+	struct net_device_stats *stats = hdlc_stats(dev);
+	int quota = dev->quota, received = 0;
+
+#if DEBUG_RX
+	printk(KERN_DEBUG "%s: hss_hdlc_poll\n", dev->name);
+#endif
+
+	while (quota) {
+		struct sk_buff *skb;
+		struct desc *desc;
+		int n;
+#ifdef __ARMEB__
+		struct sk_buff *temp;
+		u32 phys;
+#endif
+
+		if ((n = queue_get_desc(rxq, port, 0)) < 0) {
+			dev->quota -= received;	/* No packet received */
+			*budget -= received;
+			received = 0;
+#if DEBUG_RX
+			printk(KERN_DEBUG "%s: hss_hdlc_poll"
+			       " netif_rx_complete\n", dev->name);
+#endif
+			netif_rx_complete(dev);
+			qmgr_enable_irq(rxq);
+			if (!qmgr_stat_empty(rxq) &&
+			    netif_rx_reschedule(dev, 0)) {
+#if DEBUG_RX
+				printk(KERN_DEBUG "%s: hss_hdlc_poll"
+				       " netif_rx_reschedule successed\n",
+				       dev->name);
+#endif
+				qmgr_disable_irq(rxq);
+				continue;
+			}
+#if DEBUG_RX
+			printk(KERN_DEBUG "%s: hss_hdlc_poll all done\n",
+			       dev->name);
+#endif
+			return 0; /* all work done */
+		}
+
+		desc = rx_desc_ptr(port, n);
+
+		if (desc->error_count) /* FIXME - remove printk */
+			printk(KERN_DEBUG "%s: hss_hdlc_poll status 0x%02X"
+			       " errors %u\n", dev->name, desc->status,
+			       desc->error_count);
+
+		skb = NULL;
+		switch (desc->status) {
+		case 0:
+#ifdef __ARMEB__
+			if ((skb = netdev_alloc_skb(dev, RX_SIZE)) != NULL) {
+				phys = dma_map_single(&dev->dev, skb->data,
+						      RX_SIZE,
+						      DMA_FROM_DEVICE);
+				if (dma_mapping_error(phys)) {
+					dev_kfree_skb(skb);
+					skb = NULL;
+				}
+			}
+#else
+			skb = netdev_alloc_skb(dev, desc->pkt_len);
+#endif
+			if (!skb)
+				stats->rx_dropped++;
+			break;
+		case ERR_HDLC_ALIGN:
+		case ERR_HDLC_ABORT:
+			stats->rx_frame_errors++;
+			stats->rx_errors++;
+			break;
+		case ERR_HDLC_FCS:
+			stats->rx_crc_errors++;
+			stats->rx_errors++;
+			break;
+		case ERR_HDLC_TOO_LONG:
+			stats->rx_length_errors++;
+			stats->rx_errors++;
+			break;
+		default:	/* FIXME - remove printk */
+			printk(KERN_ERR "%s: hss_hdlc_poll: status 0x%02X"
+			       " errors %u\n", dev->name, desc->status,
+			       desc->error_count);
+			stats->rx_errors++;
+		}
+
+		if (!skb) {
+			/* put the desc back on RX-ready queue */
+			desc->buf_len = RX_SIZE;
+			desc->pkt_len = desc->status = 0;
+			queue_put_desc(rxfreeq, rx_desc_phys(port, n), desc);
+			continue;
+		}
+
+		/* process received frame */
+#ifdef __ARMEB__
+		temp = skb;
+		skb = port->rx_buff_tab[n];
+		dma_unmap_single(&dev->dev, desc->data,
+				 RX_SIZE, DMA_FROM_DEVICE);
+#else
+		dma_sync_single(&dev->dev, desc->data,
+				RX_SIZE, DMA_FROM_DEVICE);
+		memcpy_swab32((u32 *)skb->data, (u32 *)port->rx_buff_tab[n],
+			      ALIGN(desc->pkt_len, 4) / 4);
+#endif
+		skb_put(skb, desc->pkt_len);
+
+		debug_pkt(dev, "hss_hdlc_poll", skb->data, skb->len);
+
+		skb->protocol = hdlc_type_trans(skb, dev);
+		dev->last_rx = jiffies;
+		stats->rx_packets++;
+		stats->rx_bytes += skb->len;
+		netif_receive_skb(skb);
+
+		/* put the new buffer on RX-free queue */
+#ifdef __ARMEB__
+		port->rx_buff_tab[n] = temp;
+		desc->data = phys;
+#endif
+		desc->buf_len = RX_SIZE;
+		desc->pkt_len = 0;
+		queue_put_desc(rxfreeq, rx_desc_phys(port, n), desc);
+		quota--;
+		received++;
+	}
+	dev->quota -= received;
+	*budget -= received;
+#if DEBUG_RX
+	printk(KERN_DEBUG "hss_hdlc_poll: end, not all work done\n");
+#endif
+	return 1;		/* not all work done */
+}
+
+
+static void hss_hdlc_txdone_irq(void *pdev)
+{
+	struct net_device *dev = pdev;
+	struct port *port = dev_to_port(dev);
+	struct net_device_stats *stats = hdlc_stats(dev);
+	int n_desc;
+
+#if DEBUG_TX
+	printk(KERN_DEBUG DRV_NAME ": hss_hdlc_txdone_irq\n");
+#endif
+	while ((n_desc = queue_get_desc(queue_ids[port->id].txdone,
+					port, 1)) >= 0) {
+		struct desc *desc;
+		int start;
+
+		desc = tx_desc_ptr(port, n_desc);
+
+		stats->tx_packets++;
+		stats->tx_bytes += desc->pkt_len;
+
+		dma_unmap_tx(port, desc);
+#if DEBUG_TX
+		printk(KERN_DEBUG "%s: hss_hdlc_txdone_irq free %p\n",
+		       port->netdev->name, port->tx_buff_tab[n_desc]);
+#endif
+		free_buffer_irq(port->tx_buff_tab[n_desc]);
+		port->tx_buff_tab[n_desc] = NULL;
+
+		start = qmgr_stat_empty(port->plat->txreadyq);
+		queue_put_desc(port->plat->txreadyq,
+			       tx_desc_phys(port, n_desc), desc);
+		if (start) {
+#if DEBUG_TX
+			printk(KERN_DEBUG "%s: hss_hdlc_txdone_irq xmit"
+			       " ready\n", port->netdev->name);
+#endif
+			netif_wake_queue(port->netdev);
+		}
+	}
+}
+
+static int hss_hdlc_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct port *port = dev_to_port(dev);
+	struct net_device_stats *stats = hdlc_stats(dev);
+	unsigned int txreadyq = port->plat->txreadyq;
+	int len, offset, bytes, n;
+	void *mem;
+	u32 phys;
+	struct desc *desc;
+
+#if DEBUG_TX
+	printk(KERN_DEBUG "%s: hss_hdlc_xmit\n", dev->name);
+#endif
+
+	if (unlikely(skb->len > HDLC_MAX_MRU)) {
+		dev_kfree_skb(skb);
+		stats->tx_errors++;
+		return NETDEV_TX_OK;
+	}
+
+	debug_pkt(dev, "hss_hdlc_xmit", skb->data, skb->len);
+
+	len = skb->len;
+#ifdef __ARMEB__
+	offset = 0; /* no need to keep alignment */
+	bytes = len;
+	mem = skb->data;
+#else
+	offset = (int)skb->data & 3; /* keep 32-bit alignment */
+	bytes = ALIGN(offset + len, 4);
+	if (!(mem = kmalloc(bytes, GFP_ATOMIC))) {
+		dev_kfree_skb(skb);
+		stats->tx_dropped++;
+		return NETDEV_TX_OK;
+	}
+	memcpy_swab32(mem, (u32 *)((int)skb->data & ~3), bytes / 4);
+	dev_kfree_skb(skb);
+#endif
+
+	phys = dma_map_single(&dev->dev, mem, bytes, DMA_TO_DEVICE);
+	if (dma_mapping_error(phys)) {
+#ifdef __ARMEB__
+		dev_kfree_skb(skb);
+#else
+		kfree(mem);
+#endif
+		stats->tx_dropped++;
+		return NETDEV_TX_OK;
+	}
+
+	n = queue_get_desc(txreadyq, port, 1);
+	BUG_ON(n < 0);
+	desc = tx_desc_ptr(port, n);
+
+#ifdef __ARMEB__
+	port->tx_buff_tab[n] = skb;
+#else
+	port->tx_buff_tab[n] = mem;
+#endif
+	desc->data = phys + offset;
+	desc->buf_len = desc->pkt_len = len;
+
+	wmb();
+	queue_put_desc(queue_ids[port->id].tx, tx_desc_phys(port, n), desc);
+	dev->trans_start = jiffies;
+
+	if (qmgr_stat_empty(txreadyq)) {
+#if DEBUG_TX
+		printk(KERN_DEBUG "%s: hss_hdlc_xmit queue full\n", dev->name);
+#endif
+		netif_stop_queue(dev);
+		/* we could miss TX ready interrupt */
+		if (!qmgr_stat_empty(txreadyq)) {
+#if DEBUG_TX
+			printk(KERN_DEBUG "%s: hss_hdlc_xmit ready again\n",
+			       dev->name);
+#endif
+			netif_wake_queue(dev);
+		}
+	}
+
+#if DEBUG_TX
+	printk(KERN_DEBUG "%s: hss_hdlc_xmit end\n", dev->name);
+#endif
+	return NETDEV_TX_OK;
+}
+
+
+static int request_hdlc_queues(struct port *port)
+{
+	int err;
+
+	err = qmgr_request_queue(queue_ids[port->id].rxfree, RX_DESCS, 0, 0);
+	if (err)
+		return err;
+
+	err = qmgr_request_queue(queue_ids[port->id].rx, RX_DESCS, 0, 0);
+	if (err)
+		goto rel_rxfree;
+
+	err = qmgr_request_queue(queue_ids[port->id].tx, TX_DESCS, 0, 0);
+	if (err)
+		goto rel_rx;
+
+	err = qmgr_request_queue(port->plat->txreadyq, TX_DESCS, 0, 0);
+	if (err)
+		goto rel_tx;
+
+	err = qmgr_request_queue(queue_ids[port->id].txdone, TX_DESCS, 0, 0);
+	if (err)
+		goto rel_txready;
+	return 0;
+
+rel_txready:
+	qmgr_release_queue(port->plat->txreadyq);
+rel_tx:
+	qmgr_release_queue(queue_ids[port->id].tx);
+rel_rx:
+	qmgr_release_queue(queue_ids[port->id].rx);
+rel_rxfree:
+	qmgr_release_queue(queue_ids[port->id].rxfree);
+	printk(KERN_DEBUG "%s: unable to request hardware queues\n",
+	       port->netdev->name);
+	return err;
+}
+
+static void release_hdlc_queues(struct port *port)
+{
+	qmgr_release_queue(queue_ids[port->id].rxfree);
+	qmgr_release_queue(queue_ids[port->id].rx);
+	qmgr_release_queue(queue_ids[port->id].txdone);
+	qmgr_release_queue(queue_ids[port->id].tx);
+	qmgr_release_queue(port->plat->txreadyq);
+}
+
+static int init_hdlc_queues(struct port *port)
+{
+	int i;
+
+	if (!ports_open)
+		if (!(dma_pool = dma_pool_create(DRV_NAME, NULL,
+						 POOL_ALLOC_SIZE, 32, 0)))
+			return -ENOMEM;
+
+	if (!(port->desc_tab = dma_pool_alloc(dma_pool, GFP_KERNEL,
+					      &port->desc_tab_phys)))
+		return -ENOMEM;
+	memset(port->desc_tab, 0, POOL_ALLOC_SIZE);
+	memset(port->rx_buff_tab, 0, sizeof(port->rx_buff_tab)); /* tables */
+	memset(port->tx_buff_tab, 0, sizeof(port->tx_buff_tab));
+
+	/* Setup RX buffers */
+	for (i = 0; i < RX_DESCS; i++) {
+		struct desc *desc = rx_desc_ptr(port, i);
+		buffer_t *buff;
+		void *data;
+#ifdef __ARMEB__
+		if (!(buff = netdev_alloc_skb(port->netdev, RX_SIZE)))
+			return -ENOMEM;
+		data = buff->data;
+#else
+		if (!(buff = kmalloc(RX_SIZE, GFP_KERNEL)))
+			return -ENOMEM;
+		data = buff;
+#endif
+		desc->buf_len = RX_SIZE;
+		desc->data = dma_map_single(&port->netdev->dev, data,
+					    RX_SIZE, DMA_FROM_DEVICE);
+		if (dma_mapping_error(desc->data)) {
+			free_buffer(buff);
+			return -EIO;
+		}
+		port->rx_buff_tab[i] = buff;
+	}
+
+	return 0;
+}
+
+static void destroy_hdlc_queues(struct port *port)
+{
+	int i;
+
+	if (port->desc_tab) {
+		for (i = 0; i < RX_DESCS; i++) {
+			struct desc *desc = rx_desc_ptr(port, i);
+			buffer_t *buff = port->rx_buff_tab[i];
+			if (buff) {
+				dma_unmap_single(&port->netdev->dev,
+						 desc->data, RX_SIZE,
+						 DMA_FROM_DEVICE);
+				free_buffer(buff);
+			}
+		}
+		for (i = 0; i < TX_DESCS; i++) {
+			struct desc *desc = tx_desc_ptr(port, i);
+			buffer_t *buff = port->tx_buff_tab[i];
+			if (buff) {
+				dma_unmap_tx(port, desc);
+				free_buffer(buff);
+			}
+		}
+		dma_pool_free(dma_pool, port->desc_tab, port->desc_tab_phys);
+		port->desc_tab = NULL;
+	}
+
+	if (!ports_open && dma_pool) {
+		dma_pool_destroy(dma_pool);
+		dma_pool = NULL;
+	}
+}
+
+static int hss_hdlc_open(struct net_device *dev)
+{
+	struct port *port = dev_to_port(dev);
+	struct npe *npe = port->npe;
+	struct msg msg;
+	int i, err;
+
+	if (!npe_running(npe)) {
+		err = npe_load_firmware(npe, npe_name(npe), &dev->dev);
+		if (err)
+			return err;
+	}
+
+	if ((err = hdlc_open(dev)) != 0)
+		return err;
+
+	if (port->plat->open)
+		if ((err = port->plat->open(port->id, port->netdev,
+					    hss_hdlc_set_carrier)) != 0)
+			goto err_hdlc_close;
+
+	/* HSS main configuration */
+	memset(&msg, 0, sizeof(msg));
+	msg.cmd = PORT_CONFIG_WRITE;
+	msg.hss_port = port->id;
+	msg.index = 0;		/* offset in HSS config */
+
+	msg.data32 = PCR_FRM_PULSE_DISABLED |
+		PCR_SOF_NO_FBIT |
+		PCR_MSB_ENDIAN |
+		PCR_TX_DATA_ENABLE;
+
+	if (port->clock_type == CLOCK_INT)
+		msg.data32 |= PCR_SYNC_CLK_DIR_OUTPUT;
+
+	if ((err = npe_send_message(npe, &msg, "HSS_SET_TX_PCR") != 0))
+		goto err_plat_close; /* 0: TX PCR */
+
+	msg.index = 4;
+	msg.data32 ^= PCR_TX_DATA_ENABLE | PCR_DCLK_EDGE_RISING;
+	if ((err = npe_send_message(npe, &msg, "HSS_SET_RX_PCR") != 0))
+		goto err_plat_close; /* 4: RX PCR */
+
+	msg.index = 8;
+	msg.data32 = (port->loopback ? CCR_LOOPBACK : 0) |
+		(port->id ? CCR_SECOND_HSS : 0);
+	if ((err = npe_send_message(npe, &msg, "HSS_SET_CORE_CR") != 0))
+		goto err_plat_close; /* 8: Core CR */
+
+	msg.index = 12;
+	msg.data32 = CLK42X_SPEED_2048KHZ /* FIXME */;
+	if ((err = npe_send_message(npe, &msg, "HSS_SET_CLK_CR") != 0))
+		goto err_plat_close; /* 12: CLK CR */
+
+	msg.data32 = (FRAME_SYNC_OFFSET << 16) | (FRAME_SYNC_SIZE - 1);
+	msg.index = 16;
+	if ((err = npe_send_message(npe, &msg, "HSS_SET_TX_FCR") != 0))
+		goto err_plat_close; /* 16: TX FCR */
+
+	msg.index = 20;
+	if ((err = npe_send_message(npe, &msg, "HSS_SET_RX_FCR") != 0))
+		goto err_plat_close; /* 20: RX FCR */
+
+	msg.data32 = 0;		/* Fill LUT with HDLC timeslots */
+	for (i = 0; i < 32 / LUT_BITS; i++)
+		msg.data32 |= TDMMAP_HDLC << (LUT_BITS * i);
+
+	for (i = 0; i < 2 /* TX and RX */ * TIMESLOTS * LUT_BITS / 8; i += 4) {
+		msg.index = 24 + i; /* 24 - 55: TX LUT, 56 - 87: RX LUT */
+		if ((err = npe_send_message(npe, &msg, "HSS_SET_LUT") != 0))
+			goto err_plat_close;
+	}
+
+	/* HDLC mode configuration */
+	memset(&msg, 0, sizeof(msg));
+	msg.cmd = PKT_NUM_PIPES_WRITE;
+	msg.hss_port = port->id;
+	msg.data8a = PKT_NUM_PIPES;
+	if ((err = npe_send_message(npe, &msg, "HSS_SET_PKT_PIPES") != 0))
+		goto err_plat_close;
+
+	memset(&msg, 0, sizeof(msg));
+	msg.cmd = PKT_PIPE_FIFO_SIZEW_WRITE;
+	msg.hss_port = port->id;
+	msg.data8a = PKT_PIPE_FIFO_SIZEW;
+	if ((err = npe_send_message(npe, &msg, "HSS_SET_PKT_FIFO") != 0))
+		goto err_plat_close;
+
+	memset(&msg, 0, sizeof(msg));
+	msg.cmd = PKT_PIPE_IDLE_PATTERN_WRITE;
+	msg.hss_port = port->id;
+	msg.data32 = 0x7F7F7F7F;
+	if ((err = npe_send_message(npe, &msg, "HSS_SET_PKT_IDLE") != 0))
+		goto err_plat_close;
+
+	memset(&msg, 0, sizeof(msg));
+	msg.cmd = PORT_CONFIG_LOAD;
+	msg.hss_port = port->id;
+	if ((err = npe_send_message(npe, &msg, "HSS_LOAD_CONFIG") != 0))
+		goto err_plat_close;
+	if ((err = npe_recv_message(npe, &msg, "HSS_LOAD_CONFIG") != 0))
+		goto err_plat_close;
+
+	/* HSS_LOAD_CONFIG for port #1 returns port_id = #4 */
+	if (msg.cmd != PORT_CONFIG_LOAD || msg.data32) {
+		printk(KERN_DEBUG "%s: unexpected message received in"
+		       " response to HSS_LOAD_CONFIG\n", npe_name(npe));
+		err = EIO;
+		goto err_plat_close;
+	}
+
+	memset(&msg, 0, sizeof(msg));
+	msg.cmd = PKT_PIPE_HDLC_CFG_WRITE;
+	msg.hss_port = port->id;
+	msg.data8a = port->hdlc_cfg; /* rx_cfg */
+	msg.data8b = port->hdlc_cfg | (PKT_EXTRA_FLAGS << 3); /* tx_cfg */
+	if ((err = npe_send_message(npe, &msg, "HSS_SET_HDLC_CFG") != 0))
+		goto err_plat_close;
+
+	memset(&msg, 0, sizeof(msg));
+	msg.cmd = PKT_PIPE_MODE_WRITE;
+	msg.hss_port = port->id;
+	msg.data8a = NPE_PKT_MODE_HDLC;
+	/* msg.data8b = inv_mask */
+	/* msg.data8c = or_mask */
+	if ((err = npe_send_message(npe, &msg, "HSS_SET_PKT_MODE") != 0))
+		goto err_plat_close;
+
+	memset(&msg, 0, sizeof(msg));
+	msg.cmd = PKT_PIPE_RX_SIZE_WRITE;
+	msg.hss_port = port->id;
+	msg.data16a = HDLC_MAX_MRU;
+	if ((err = npe_send_message(npe, &msg, "HSS_SET_PKT_RX_SIZE") != 0))
+		goto err_plat_close;
+
+	if ((err = request_hdlc_queues(port)) != 0)
+		goto err_plat_close;
+
+	if ((err = init_hdlc_queues(port)) != 0)
+		goto err_destroy_queues;
+
+	memset(&msg, 0, sizeof(msg));
+	msg.cmd = PKT_PIPE_FLOW_ENABLE;
+	msg.hss_port = port->id;
+	if ((err = npe_send_message(npe, &msg, "HSS_ENABLE_PKT_PIPE") != 0))
+		goto err_destroy_queues;
+
+	/* Populate queues with buffers, no failure after this point */
+	for (i = 0; i < TX_DESCS; i++)
+		queue_put_desc(port->plat->txreadyq,
+			       tx_desc_phys(port, i), tx_desc_ptr(port, i));
+
+	for (i = 0; i < RX_DESCS; i++)
+		queue_put_desc(queue_ids[port->id].rxfree,
+			       rx_desc_phys(port, i), rx_desc_ptr(port, i));
+
+	netif_start_queue(dev);
+
+	qmgr_set_irq(queue_ids[port->id].rx, QUEUE_IRQ_SRC_NOT_EMPTY,
+		     hss_hdlc_rx_irq, dev);
+
+	qmgr_set_irq(queue_ids[port->id].txdone, QUEUE_IRQ_SRC_NOT_EMPTY,
+		     hss_hdlc_txdone_irq, dev);
+	qmgr_enable_irq(queue_ids[port->id].txdone);
+
+	ports_open++;
+	netif_rx_schedule(dev); /* we may already have RX data, enables IRQ */
+	return 0;
+
+err_destroy_queues:
+	destroy_hdlc_queues(port);
+	release_hdlc_queues(port);
+err_plat_close:
+	if (port->plat->close)
+		port->plat->close(port->id, port->netdev);
+err_hdlc_close:
+	hdlc_close(dev);
+	return err;
+}
+
+static int hss_hdlc_close(struct net_device *dev)
+{
+	struct port *port = dev_to_port(dev);
+	struct npe *npe = port->npe;
+	struct msg msg;
+	int buffs = RX_DESCS; /* allocated RX buffers */
+	int i;
+
+	ports_open--;
+	qmgr_disable_irq(queue_ids[port->id].rx);
+	netif_stop_queue(dev);
+
+	memset(&msg, 0, sizeof(msg));
+	msg.cmd = PKT_PIPE_FLOW_DISABLE;
+	msg.hss_port = port->id;
+	if (npe_send_message(npe, &msg, "HSS_DISABLE_PKT_PIPE")) {
+		printk(KERN_CRIT "HSS-%i: unable to stop HDLC flow\n",
+		       port->id);
+		/* The upper level would ignore the error anyway */
+	}
+
+	while (queue_get_desc(queue_ids[port->id].rxfree, port, 0) >= 0)
+		buffs--;
+	while (queue_get_desc(queue_ids[port->id].rx, port, 0) >= 0)
+		buffs--;
+
+	if (buffs)
+		printk(KERN_CRIT "%s: unable to drain RX queue, %i buffer(s)"
+		       " left in NPE\n", dev->name, buffs);
+
+	buffs = TX_DESCS;
+	while (queue_get_desc(queue_ids[port->id].tx, port, 1) >= 0)
+		buffs--; /* cancel TX */
+
+	i = 0;
+	do {
+		while (queue_get_desc(port->plat->txreadyq, port, 1) >= 0)
+			buffs--;
+		if (!buffs)
+			break;
+	} while (++i < MAX_CLOSE_WAIT);
+
+	if (buffs)
+		printk(KERN_CRIT "%s: unable to drain TX queue, %i buffer(s) "
+		       "left in NPE\n", dev->name, buffs);
+#if DEBUG_CLOSE
+	if (!buffs)
+		printk(KERN_DEBUG "Draining TX queues took %i cycles\n", i);
+#endif
+	qmgr_disable_irq(queue_ids[port->id].txdone);
+	destroy_hdlc_queues(port);
+	release_hdlc_queues(port);
+
+	if (port->plat->close)
+		port->plat->close(port->id, port->netdev);
+	hdlc_close(dev);
+	return 0;
+}
+
+
+static int hss_hdlc_attach(struct net_device *dev, unsigned short encoding,
+			   unsigned short parity)
+{
+	struct port *port = dev_to_port(dev);
+
+	if (encoding != ENCODING_NRZ)
+		return -EINVAL;
+
+	switch(parity) {
+	case PARITY_CRC16_PR1_CCITT:
+		port->hdlc_cfg = 0;
+		return 0;
+
+	case PARITY_CRC32_PR1_CCITT:
+		port->hdlc_cfg = PKT_HDLC_CRC_32;
+		return 0;
+
+	default:
+		return -EINVAL;
+	}
+}
+
+
+static int hss_hdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+{
+	const size_t size = sizeof(sync_serial_settings);
+	sync_serial_settings new_line;
+	int clk;
+	sync_serial_settings __user *line = ifr->ifr_settings.ifs_ifsu.sync;
+	struct port *port = dev_to_port(dev);
+
+	if (cmd != SIOCWANDEV)
+		return hdlc_ioctl(dev, ifr, cmd);
+
+	switch(ifr->ifr_settings.type) {
+	case IF_GET_IFACE:
+		ifr->ifr_settings.type = IF_IFACE_V35;
+		if (ifr->ifr_settings.size < size) {
+			ifr->ifr_settings.size = size; /* data size wanted */
+			return -ENOBUFS;
+		}
+		memset(&new_line, 0, sizeof(new_line));
+		new_line.clock_type = port->clock_type;
+		new_line.clock_rate = port->clock_rate;
+		new_line.loopback = port->loopback;
+		if (copy_to_user(line, &new_line, size))
+			return -EFAULT;
+		return 0;
+
+	case IF_IFACE_SYNC_SERIAL:
+	case IF_IFACE_V35:
+		if(!capable(CAP_NET_ADMIN))
+			return -EPERM;
+		if (dev->flags & IFF_UP)
+			return -EBUSY; /* Cannot change parameters when open */
+
+		if (copy_from_user(&new_line, line, size))
+			return -EFAULT;
+
+		clk = new_line.clock_type;
+		if (port->plat->set_clock)
+			clk = port->plat->set_clock(port->id, clk);
+
+		if (clk != CLOCK_EXT && clk != CLOCK_INT)
+			return -EINVAL;	/* No such clock setting */
+
+		if (new_line.loopback != 0 && new_line.loopback != 1)
+			return -EINVAL;
+
+		port->clock_type = clk; /* Update settings */
+		port->clock_rate = new_line.clock_rate;
+		port->loopback = new_line.loopback;
+		return 0;
+
+	default:
+		return hdlc_ioctl(dev, ifr, cmd);
+	}
+}
+
+
+static int __devinit hss_init_one(struct platform_device *pdev)
+{
+	struct port *port;
+	struct net_device *dev;
+	hdlc_device *hdlc;
+	int err;
+
+	if ((port = kzalloc(sizeof(*port), GFP_KERNEL)) == NULL)
+		return -ENOMEM;
+	platform_set_drvdata(pdev, port);
+	port->id = pdev->id;
+
+	if ((port->npe = npe_request(0)) == NULL) {
+		err = -ENOSYS;
+		goto err_free;
+	}
+
+	port->plat = pdev->dev.platform_data;
+	if ((port->netdev = dev = alloc_hdlcdev(port)) == NULL) {
+		err = -ENOMEM;
+		goto err_plat;
+	}
+
+	SET_MODULE_OWNER(net);
+	SET_NETDEV_DEV(dev, &pdev->dev);
+	hdlc = dev_to_hdlc(dev);
+	hdlc->attach = hss_hdlc_attach;
+	hdlc->xmit = hss_hdlc_xmit;
+	dev->open = hss_hdlc_open;
+	dev->poll = hss_hdlc_poll;
+	dev->stop = hss_hdlc_close;
+	dev->do_ioctl = hss_hdlc_ioctl;
+	dev->weight = 16;
+	dev->tx_queue_len = 100;
+	port->clock_type = CLOCK_EXT;
+	port->clock_rate = 2048000;
+
+	if (register_hdlc_device(dev)) {
+		printk(KERN_ERR "HSS-%i: unable to register HDLC device\n",
+		       port->id);
+		err = -ENOBUFS;
+		goto err_free_netdev;
+	}
+	printk(KERN_INFO "%s: HSS-%i\n", dev->name, port->id);
+	return 0;
+
+err_free_netdev:
+	free_netdev(dev);
+err_plat:
+	npe_release(port->npe);
+	platform_set_drvdata(pdev, NULL);
+err_free:
+	kfree(port);
+	return err;
+}
+
+static int __devexit hss_remove_one(struct platform_device *pdev)
+{
+	struct port *port = platform_get_drvdata(pdev);
+
+	unregister_hdlc_device(port->netdev);
+	free_netdev(port->netdev);
+	npe_release(port->npe);
+	platform_set_drvdata(pdev, NULL);
+	kfree(port);
+	return 0;
+}
+
+static struct platform_driver drv = {
+	.driver.name	= DRV_NAME,
+	.probe		= hss_init_one,
+	.remove		= hss_remove_one,
+};
+
+static int __init hss_init_module(void)
+{
+	if ((ixp4xx_read_feature_bits() &
+	     (IXP4XX_FEATURE_HDLC | IXP4XX_FEATURE_HSS)) !=
+	    (IXP4XX_FEATURE_HDLC | IXP4XX_FEATURE_HSS))
+		return -ENOSYS;
+	return platform_driver_register(&drv);
+}
+
+static void __exit hss_cleanup_module(void)
+{
+	platform_driver_unregister(&drv);
+}
+
+MODULE_AUTHOR("Krzysztof Halasa");
+MODULE_DESCRIPTION("Intel IXP4xx HSS driver");
+MODULE_LICENSE("GPL v2");
+module_init(hss_init_module);
+module_exit(hss_cleanup_module);
diff --git a/include/asm-arm/arch-ixp4xx/cpu.h b/include/asm-arm/arch-ixp4xx/cpu.h
index d2523b3..2fa3d6b 100644
--- a/include/asm-arm/arch-ixp4xx/cpu.h
+++ b/include/asm-arm/arch-ixp4xx/cpu.h
@@ -28,4 +28,19 @@ extern unsigned int processor_id;
 #define cpu_is_ixp46x()	((processor_id & IXP4XX_PROCESSOR_ID_MASK) == \
 			  IXP465_PROCESSOR_ID_VALUE)
 
+static inline u32 ixp4xx_read_feature_bits(void)
+{
+	unsigned int val = ~*IXP4XX_EXP_CFG2;
+	val &= ~IXP4XX_FEATURE_RESERVED;
+	if (!cpu_is_ixp46x())
+		val &= ~IXP4XX_FEATURE_IXP46X_ONLY;
+
+	return val;
+}
+
+static inline void ixp4xx_write_feature_bits(u32 value)
+{
+	*IXP4XX_EXP_CFG2 = ~value;
+}
+
 #endif  /* _ASM_ARCH_CPU_H */
diff --git a/include/asm-arm/arch-ixp4xx/hardware.h b/include/asm-arm/arch-ixp4xx/hardware.h
index 297ceda..73e8dc3 100644
--- a/include/asm-arm/arch-ixp4xx/hardware.h
+++ b/include/asm-arm/arch-ixp4xx/hardware.h
@@ -27,13 +27,13 @@
 
 #define pcibios_assign_all_busses()	1
 
+/* Register locations and bits */
+#include "ixp4xx-regs.h"
+
 #ifndef __ASSEMBLER__
 #include <asm/arch/cpu.h>
 #endif
 
-/* Register locations and bits */
-#include "ixp4xx-regs.h"
-
 /* Platform helper functions and definitions */
 #include "platform.h"
 
diff --git a/include/asm-arm/arch-ixp4xx/ixp4xx-regs.h b/include/asm-arm/arch-ixp4xx/ixp4xx-regs.h
index 5d949d7..c704fe8 100644
--- a/include/asm-arm/arch-ixp4xx/ixp4xx-regs.h
+++ b/include/asm-arm/arch-ixp4xx/ixp4xx-regs.h
@@ -15,10 +15,6 @@
  *
  */
 
-#ifndef __ASM_ARCH_HARDWARE_H__
-#error "Do not include this directly, instead #include <asm/hardware.h>"
-#endif
-
 #ifndef _ASM_ARM_IXP4XX_H_
 #define _ASM_ARM_IXP4XX_H_
 
@@ -607,4 +603,36 @@
 
 #define DCMD_LENGTH	0x01fff		/* length mask (max = 8K - 1) */
 
+/* "fuse" bits of IXP_EXP_CFG2 */
+#define IXP4XX_FEATURE_RCOMP		(1 << 0)
+#define IXP4XX_FEATURE_USB_DEVICE	(1 << 1)
+#define IXP4XX_FEATURE_HASH		(1 << 2)
+#define IXP4XX_FEATURE_AES		(1 << 3)
+#define IXP4XX_FEATURE_DES		(1 << 4)
+#define IXP4XX_FEATURE_HDLC		(1 << 5)
+#define IXP4XX_FEATURE_AAL		(1 << 6)
+#define IXP4XX_FEATURE_HSS		(1 << 7)
+#define IXP4XX_FEATURE_UTOPIA		(1 << 8)
+#define IXP4XX_FEATURE_NPEB_ETH0	(1 << 9)
+#define IXP4XX_FEATURE_NPEC_ETH		(1 << 10)
+#define IXP4XX_FEATURE_RESET_NPEA	(1 << 11)
+#define IXP4XX_FEATURE_RESET_NPEB	(1 << 12)
+#define IXP4XX_FEATURE_RESET_NPEC	(1 << 13)
+#define IXP4XX_FEATURE_PCI		(1 << 14)
+#define IXP4XX_FEATURE_ECC_TIMESYNC	(1 << 15)
+#define IXP4XX_FEATURE_UTOPIA_PHY_LIMIT	(3 << 16)
+#define IXP4XX_FEATURE_USB_HOST		(1 << 18)
+#define IXP4XX_FEATURE_NPEA_ETH		(1 << 19)
+#define IXP4XX_FEATURE_NPEB_ETH_1_TO_3	(1 << 20)
+#define IXP4XX_FEATURE_RSA		(1 << 21)
+#define IXP4XX_FEATURE_XSCALE_MAX_FREQ	(3 << 22)
+#define IXP4XX_FEATURE_RESERVED		(0xFF << 24)
+
+#define IXP4XX_FEATURE_IXP46X_ONLY (IXP4XX_FEATURE_ECC_TIMESYNC |	\
+				    IXP4XX_FEATURE_USB_HOST |		\
+				    IXP4XX_FEATURE_NPEA_ETH |		\
+				    IXP4XX_FEATURE_NPEB_ETH_1_TO_3 |	\
+				    IXP4XX_FEATURE_RSA |		\
+				    IXP4XX_FEATURE_XSCALE_MAX_FREQ)
+
 #endif
diff --git a/include/asm-arm/arch-ixp4xx/npe.h b/include/asm-arm/arch-ixp4xx/npe.h
new file mode 100644
index 0000000..37d0511
--- /dev/null
+++ b/include/asm-arm/arch-ixp4xx/npe.h
@@ -0,0 +1,39 @@
+#ifndef __IXP4XX_NPE_H
+#define __IXP4XX_NPE_H
+
+#include <linux/kernel.h>
+
+extern const char *npe_names[];
+
+struct npe_regs {
+	u32 exec_addr, exec_data, exec_status_cmd, exec_count;
+	u32 action_points[4];
+	u32 watchpoint_fifo, watch_count;
+	u32 profile_count;
+	u32 messaging_status, messaging_control;
+	u32 mailbox_status, /*messaging_*/ in_out_fifo;
+};
+
+struct npe {
+	struct resource *mem_res;
+	struct npe_regs __iomem *regs;
+	u32 regs_phys;
+	int id;
+	int valid;
+};
+
+
+static inline const char *npe_name(struct npe *npe)
+{
+	return npe_names[npe->id];
+}
+
+int npe_running(struct npe *npe);
+int npe_send_message(struct npe *npe, const void *msg, const char *what);
+int npe_recv_message(struct npe *npe, void *msg, const char *what);
+int npe_send_recv_message(struct npe *npe, void *msg, const char *what);
+int npe_load_firmware(struct npe *npe, const char *name, struct device *dev);
+struct npe *npe_request(int id);
+void npe_release(struct npe *npe);
+
+#endif /* __IXP4XX_NPE_H */
diff --git a/include/asm-arm/arch-ixp4xx/platform.h b/include/asm-arm/arch-ixp4xx/platform.h
index 2a44d3d..695b9c4 100644
--- a/include/asm-arm/arch-ixp4xx/platform.h
+++ b/include/asm-arm/arch-ixp4xx/platform.h
@@ -77,8 +77,7 @@ extern unsigned long ixp4xx_exp_bus_size;
 
 /*
  * The IXP4xx chips do not have an I2C unit, so GPIO lines are just
- * used to 
- * Used as platform_data to provide GPIO pin information to the ixp42x
+ * used as platform_data to provide GPIO pin information to the ixp42x
  * I2C driver.
  */
 struct ixp4xx_i2c_pins {
@@ -86,6 +85,27 @@ struct ixp4xx_i2c_pins {
 	unsigned long scl_pin;
 };
 
+#define IXP4XX_ETH_NPEA		0x00
+#define IXP4XX_ETH_NPEB		0x10
+#define IXP4XX_ETH_NPEC		0x20
+
+/* Information about built-in Ethernet MAC interfaces */
+struct eth_plat_info {
+	u8 phy;		/* MII PHY ID, 0 - 31 */
+	u8 rxq;		/* configurable, currently 0 - 31 only */
+	u8 txreadyq;
+	u8 hwaddr[6];
+};
+
+/* Information about built-in HSS (synchronous serial) interfaces */
+struct hss_plat_info {
+	int (*set_clock)(int port, unsigned int clock_type);
+	int (*open)(int port, void *pdev,
+		    void (*set_carrier_cb)(void *pdev, int carrier));
+	void (*close)(int port, void *pdev);
+	u8 txreadyq;
+};
+
 /*
  * This structure provide a means for the board setup code
  * to give information to th pata_ixp4xx driver. It is
diff --git a/include/asm-arm/arch-ixp4xx/qmgr.h b/include/asm-arm/arch-ixp4xx/qmgr.h
new file mode 100644
index 0000000..1e52b95
--- /dev/null
+++ b/include/asm-arm/arch-ixp4xx/qmgr.h
@@ -0,0 +1,126 @@
+/*
+ * Copyright (C) 2007 Krzysztof Halasa <khc@pm.waw.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ */
+
+#ifndef IXP4XX_QMGR_H
+#define IXP4XX_QMGR_H
+
+#include <linux/io.h>
+#include <linux/kernel.h>
+
+#define HALF_QUEUES	32
+#define QUEUES		64	/* only 32 lower queues currently supported */
+#define MAX_QUEUE_LENGTH 4	/* in dwords */
+
+#define QUEUE_STAT1_EMPTY		1 /* queue status bits */
+#define QUEUE_STAT1_NEARLY_EMPTY	2
+#define QUEUE_STAT1_NEARLY_FULL		4
+#define QUEUE_STAT1_FULL		8
+#define QUEUE_STAT2_UNDERFLOW		1
+#define QUEUE_STAT2_OVERFLOW		2
+
+#define QUEUE_WATERMARK_0_ENTRIES	0
+#define QUEUE_WATERMARK_1_ENTRY		1
+#define QUEUE_WATERMARK_2_ENTRIES	2
+#define QUEUE_WATERMARK_4_ENTRIES	3
+#define QUEUE_WATERMARK_8_ENTRIES	4
+#define QUEUE_WATERMARK_16_ENTRIES	5
+#define QUEUE_WATERMARK_32_ENTRIES	6
+#define QUEUE_WATERMARK_64_ENTRIES	7
+
+/* queue interrupt request conditions */
+#define QUEUE_IRQ_SRC_EMPTY		0
+#define QUEUE_IRQ_SRC_NEARLY_EMPTY	1
+#define QUEUE_IRQ_SRC_NEARLY_FULL	2
+#define QUEUE_IRQ_SRC_FULL		3
+#define QUEUE_IRQ_SRC_NOT_EMPTY		4
+#define QUEUE_IRQ_SRC_NOT_NEARLY_EMPTY	5
+#define QUEUE_IRQ_SRC_NOT_NEARLY_FULL	6
+#define QUEUE_IRQ_SRC_NOT_FULL		7
+
+struct qmgr_regs {
+	u32 acc[QUEUES][MAX_QUEUE_LENGTH]; /* 0x000 - 0x3FF */
+	u32 stat1[4];		/* 0x400 - 0x40F */
+	u32 stat2[2];		/* 0x410 - 0x417 */
+	u32 statne_h;		/* 0x418 - queue nearly empty */
+	u32 statf_h;		/* 0x41C - queue full */
+	u32 irqsrc[4];		/* 0x420 - 0x42F IRC source */
+	u32 irqen[2];		/* 0x430 - 0x437 IRQ enabled */
+	u32 irqstat[2];		/* 0x438 - 0x43F - IRQ access only */
+	u32 reserved[1776];
+	u32 sram[2048];		/* 0x2000 - 0x3FFF - config and buffer */
+};
+
+void qmgr_set_irq(unsigned int queue, int src,
+		  void (*handler)(void *pdev), void *pdev);
+void qmgr_enable_irq(unsigned int queue);
+void qmgr_disable_irq(unsigned int queue);
+
+/* request_ and release_queue() must be called from non-IRQ context */
+int qmgr_request_queue(unsigned int queue, unsigned int len /* dwords */,
+		       unsigned int nearly_empty_watermark,
+		       unsigned int nearly_full_watermark);
+void qmgr_release_queue(unsigned int queue);
+
+
+static inline void qmgr_put_entry(unsigned int queue, u32 val)
+{
+	extern struct qmgr_regs __iomem *qmgr_regs;
+	__raw_writel(val, &qmgr_regs->acc[queue][0]);
+}
+
+static inline u32 qmgr_get_entry(unsigned int queue)
+{
+	extern struct qmgr_regs __iomem *qmgr_regs;
+	return __raw_readl(&qmgr_regs->acc[queue][0]);
+}
+
+static inline int qmgr_get_stat1(unsigned int queue)
+{
+	extern struct qmgr_regs __iomem *qmgr_regs;
+	return (__raw_readl(&qmgr_regs->stat1[queue >> 3])
+		>> ((queue & 7) << 2)) & 0xF;
+}
+
+static inline int qmgr_get_stat2(unsigned int queue)
+{
+	extern struct qmgr_regs __iomem *qmgr_regs;
+	return (__raw_readl(&qmgr_regs->stat2[queue >> 4])
+		>> ((queue & 0xF) << 1)) & 0x3;
+}
+
+static inline int qmgr_stat_empty(unsigned int queue)
+{
+	return !!(qmgr_get_stat1(queue) & QUEUE_STAT1_EMPTY);
+}
+
+static inline int qmgr_stat_nearly_empty(unsigned int queue)
+{
+	return !!(qmgr_get_stat1(queue) & QUEUE_STAT1_NEARLY_EMPTY);
+}
+
+static inline int qmgr_stat_nearly_full(unsigned int queue)
+{
+	return !!(qmgr_get_stat1(queue) & QUEUE_STAT1_NEARLY_FULL);
+}
+
+static inline int qmgr_stat_full(unsigned int queue)
+{
+	return !!(qmgr_get_stat1(queue) & QUEUE_STAT1_FULL);
+}
+
+static inline int qmgr_stat_underflow(unsigned int queue)
+{
+	return !!(qmgr_get_stat2(queue) & QUEUE_STAT2_UNDERFLOW);
+}
+
+static inline int qmgr_stat_overflow(unsigned int queue)
+{
+	return !!(qmgr_get_stat2(queue) & QUEUE_STAT2_OVERFLOW);
+}
+
+#endif
diff --git a/include/asm-arm/arch-ixp4xx/uncompress.h b/include/asm-arm/arch-ixp4xx/uncompress.h
index f7a35b7..34ef48f 100644
--- a/include/asm-arm/arch-ixp4xx/uncompress.h
+++ b/include/asm-arm/arch-ixp4xx/uncompress.h
@@ -13,7 +13,7 @@
 #ifndef _ARCH_UNCOMPRESS_H_
 #define _ARCH_UNCOMPRESS_H_
 
-#include <asm/hardware.h>
+#include "ixp4xx-regs.h"
 #include <asm/mach-types.h>
 #include <linux/serial_reg.h>