ARM: ixp4xx: Move NPE and QMGR to drivers/soc

The Network Processing Engine and Queue Manager are
versatile firmware components used by several IXP4xx
drivers.

Drivers are relying on getting access to these components
using <mach/*> headers which does not work with
multiplatform. We need to find a better place for the
drivers to live.

Let's first move them to drivers/soc and the start to
refactor a bit by passing resources and moving headers.

This patch introduce static IRQ assignments but that
will be fixed by later patches in this series.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>

4 files changed, 1147 insertions, 0 deletions

diff --git a/drivers/soc/ixp4xx/Kconfig b/drivers/soc/ixp4xx/Kconfig
new file mode 100644
index 000000000000..de6becdc78a2
--- /dev/null
+++ b/drivers/soc/ixp4xx/Kconfig
@@ -0,0 +1,16 @@
+menu "IXP4xx SoC drivers"
+
+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 FW_LOADER
+	help
+	  This driver supports IXP4xx built-in network coprocessors
+	  and is automatically selected by Ethernet and HSS drivers.
+
+endmenu
diff --git a/drivers/soc/ixp4xx/Makefile b/drivers/soc/ixp4xx/Makefile
new file mode 100644
index 000000000000..d20d99e6df65
--- /dev/null
+++ b/drivers/soc/ixp4xx/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_IXP4XX_QMGR)	+= ixp4xx-qmgr.o
+obj-$(CONFIG_IXP4XX_NPE)	+= ixp4xx-npe.o
diff --git a/drivers/soc/ixp4xx/ixp4xx-npe.c b/drivers/soc/ixp4xx/ixp4xx-npe.c
new file mode 100644
index 000000000000..e0ce22cd9bfc
--- /dev/null
+++ b/drivers/soc/ixp4xx/ixp4xx-npe.c
@@ -0,0 +1,747 @@
+/*
+ * 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/of.h>
+#include <mach/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
+
+#define NPE_A_FIRMWARE "NPE-A"
+#define NPE_B_FIRMWARE "NPE-B"
+#define NPE_C_FIRMWARE "NPE-C"
+
+const char *npe_names[] = { NPE_A_FIRMWARE, NPE_B_FIRMWARE, NPE_C_FIRMWARE };
+
+#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));
+	/* 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;
+	}
+
+#if DEBUG_MSG > 1
+	debug_msg(npe, "Sending a message took %i cycles\n", cycles);
+#endif
+	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;
+	}
+
+#if DEBUG_MSG > 1
+	debug_msg(npe, "Receiving a message took %i cycles\n", cycles);
+#endif
+	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_ixp42x() && ((image->id >> 28) & 0xF /* device ID */)) {
+		print_npe(KERN_INFO, npe, "IXP43x/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_ixp42x()) {
+		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(unsigned 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;
+
+	/* This driver does not work with device tree */
+	if (of_have_populated_dt())
+		return -ENODEV;
+
+	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 -ENODEV;
+	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");
+MODULE_FIRMWARE(NPE_A_FIRMWARE);
+MODULE_FIRMWARE(NPE_B_FIRMWARE);
+MODULE_FIRMWARE(NPE_C_FIRMWARE);
+
+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/drivers/soc/ixp4xx/ixp4xx-qmgr.c b/drivers/soc/ixp4xx/ixp4xx-qmgr.c
new file mode 100644
index 000000000000..2e6d33534afe
--- /dev/null
+++ b/drivers/soc/ixp4xx/ixp4xx-qmgr.c
@@ -0,0 +1,382 @@
+/*
+ * 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 <linux/of.h>
+#include <mach/qmgr.h>
+
+/* FIXME: get rid of these static assigments */
+#define IRQ_IXP4XX_BASE		16
+#define IRQ_IXP4XX_QM1		(IRQ_IXP4XX_BASE + 3)
+#define IRQ_IXP4XX_QM2		(IRQ_IXP4XX_BASE + 4)
+
+static struct qmgr_regs __iomem *qmgr_regs = IXP4XX_QMGR_BASE_VIRT;
+static struct resource *mem_res;
+static spinlock_t qmgr_lock;
+static u32 used_sram_bitmap[4]; /* 128 16-dword pages */
+static void (*irq_handlers[QUEUES])(void *pdev);
+static void *irq_pdevs[QUEUES];
+
+#if DEBUG_QMGR
+char qmgr_queue_descs[QUEUES][32];
+#endif
+
+void qmgr_set_irq(unsigned int queue, int src,
+		  void (*handler)(void *pdev), void *pdev)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&qmgr_lock, flags);
+	if (queue < HALF_QUEUES) {
+		u32 __iomem *reg;
+		int bit;
+		BUG_ON(src > QUEUE_IRQ_SRC_NOT_FULL);
+		reg = &qmgr_regs->irqsrc[queue >> 3]; /* 8 queues per u32 */
+		bit = (queue % 8) * 4; /* 3 bits + 1 reserved bit per queue */
+		__raw_writel((__raw_readl(reg) & ~(7 << bit)) | (src << bit),
+			     reg);
+	} else
+		/* IRQ source for queues 32-63 is fixed */
+		BUG_ON(src != QUEUE_IRQ_SRC_NOT_NEARLY_EMPTY);
+
+	irq_handlers[queue] = handler;
+	irq_pdevs[queue] = pdev;
+	spin_unlock_irqrestore(&qmgr_lock, flags);
+}
+
+
+static irqreturn_t qmgr_irq1_a0(int irq, void *pdev)
+{
+	int i, ret = 0;
+	u32 en_bitmap, src, stat;
+
+	/* ACK - it may clear any bits so don't rely on it */
+	__raw_writel(0xFFFFFFFF, &qmgr_regs->irqstat[0]);
+
+	en_bitmap = qmgr_regs->irqen[0];
+	while (en_bitmap) {
+		i = __fls(en_bitmap); /* number of the last "low" queue */
+		en_bitmap &= ~BIT(i);
+		src = qmgr_regs->irqsrc[i >> 3];
+		stat = qmgr_regs->stat1[i >> 3];
+		if (src & 4) /* the IRQ condition is inverted */
+			stat = ~stat;
+		if (stat & BIT(src & 3)) {
+			irq_handlers[i](irq_pdevs[i]);
+			ret = IRQ_HANDLED;
+		}
+	}
+	return ret;
+}
+
+
+static irqreturn_t qmgr_irq2_a0(int irq, void *pdev)
+{
+	int i, ret = 0;
+	u32 req_bitmap;
+
+	/* ACK - it may clear any bits so don't rely on it */
+	__raw_writel(0xFFFFFFFF, &qmgr_regs->irqstat[1]);
+
+	req_bitmap = qmgr_regs->irqen[1] & qmgr_regs->statne_h;
+	while (req_bitmap) {
+		i = __fls(req_bitmap); /* number of the last "high" queue */
+		req_bitmap &= ~BIT(i);
+		irq_handlers[HALF_QUEUES + i](irq_pdevs[HALF_QUEUES + i]);
+		ret = IRQ_HANDLED;
+	}
+	return ret;
+}
+
+
+static irqreturn_t qmgr_irq(int irq, void *pdev)
+{
+	int i, half = (irq == IRQ_IXP4XX_QM1 ? 0 : 1);
+	u32 req_bitmap = __raw_readl(&qmgr_regs->irqstat[half]);
+
+	if (!req_bitmap)
+		return 0;
+	__raw_writel(req_bitmap, &qmgr_regs->irqstat[half]); /* ACK */
+
+	while (req_bitmap) {
+		i = __fls(req_bitmap); /* number of the last queue */
+		req_bitmap &= ~BIT(i);
+		i += half * HALF_QUEUES;
+		irq_handlers[i](irq_pdevs[i]);
+	}
+	return IRQ_HANDLED;
+}
+
+
+void qmgr_enable_irq(unsigned int queue)
+{
+	unsigned long flags;
+	int half = queue / 32;
+	u32 mask = 1 << (queue & (HALF_QUEUES - 1));
+
+	spin_lock_irqsave(&qmgr_lock, flags);
+	__raw_writel(__raw_readl(&qmgr_regs->irqen[half]) | mask,
+		     &qmgr_regs->irqen[half]);
+	spin_unlock_irqrestore(&qmgr_lock, flags);
+}
+
+void qmgr_disable_irq(unsigned int queue)
+{
+	unsigned long flags;
+	int half = queue / 32;
+	u32 mask = 1 << (queue & (HALF_QUEUES - 1));
+
+	spin_lock_irqsave(&qmgr_lock, flags);
+	__raw_writel(__raw_readl(&qmgr_regs->irqen[half]) & ~mask,
+		     &qmgr_regs->irqen[half]);
+	__raw_writel(mask, &qmgr_regs->irqstat[half]); /* clear */
+	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;
+}
+
+#if DEBUG_QMGR
+int qmgr_request_queue(unsigned int queue, unsigned int len /* dwords */,
+		       unsigned int nearly_empty_watermark,
+		       unsigned int nearly_full_watermark,
+		       const char *desc_format, const char* name)
+#else
+int __qmgr_request_queue(unsigned int queue, unsigned int len /* dwords */,
+			 unsigned int nearly_empty_watermark,
+			 unsigned int nearly_full_watermark)
+#endif
+{
+	u32 cfg, addr = 0, mask[4]; /* in 16-dwords */
+	int err;
+
+	BUG_ON(queue >= QUEUES);
+
+	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]);
+#if DEBUG_QMGR
+	snprintf(qmgr_queue_descs[queue], sizeof(qmgr_queue_descs[0]),
+		 desc_format, name);
+	printk(KERN_DEBUG "qmgr: requested queue %s(%i) addr = 0x%02X\n",
+	       qmgr_queue_descs[queue], queue, addr);
+#endif
+	spin_unlock_irq(&qmgr_lock);
+	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 >= 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;
+	}
+
+	mask[1] = mask[2] = mask[3] = 0;
+
+	while (addr--)
+		shift_mask(mask);
+
+#if DEBUG_QMGR
+	printk(KERN_DEBUG "qmgr: releasing queue %s(%i)\n",
+	       qmgr_queue_descs[queue], queue);
+	qmgr_queue_descs[queue][0] = '\x0';
+#endif
+
+	while ((addr = qmgr_get_entry(queue)))
+		printk(KERN_ERR "qmgr: released queue %i not empty: 0x%08X\n",
+		       queue, addr);
+
+	__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);
+}
+
+static int qmgr_init(void)
+{
+	int i, err;
+	irq_handler_t handler1, handler2;
+
+	/* This driver does not work with device tree */
+	if (of_have_populated_dt())
+		return -ENODEV;
+
+	mem_res = request_mem_region(IXP4XX_QMGR_BASE_PHYS,
+				     IXP4XX_QMGR_REGION_SIZE,
+				     "IXP4xx Queue Manager");
+	if (mem_res == NULL)
+		return -EBUSY;
+
+	/* 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]);
+	}
+
+	__raw_writel(0xFFFFFFFF, &qmgr_regs->statne_h);
+	__raw_writel(0, &qmgr_regs->statf_h);
+
+	for (i = 0; i < QUEUES; i++)
+		__raw_writel(0, &qmgr_regs->sram[i]);
+
+	if (cpu_is_ixp42x_rev_a0()) {
+		handler1 = qmgr_irq1_a0;
+		handler2 = qmgr_irq2_a0;
+	} else
+		handler1 = handler2 = qmgr_irq;
+
+	err = request_irq(IRQ_IXP4XX_QM1, handler1, 0, "IXP4xx Queue Manager",
+			  NULL);
+	if (err) {
+		printk(KERN_ERR "qmgr: failed to request IRQ%i (%i)\n",
+		       IRQ_IXP4XX_QM1, err);
+		goto error_irq;
+	}
+
+	err = request_irq(IRQ_IXP4XX_QM2, handler2, 0, "IXP4xx Queue Manager",
+			  NULL);
+	if (err) {
+		printk(KERN_ERR "qmgr: failed to request IRQ%i (%i)\n",
+		       IRQ_IXP4XX_QM2, err);
+		goto error_irq2;
+	}
+
+	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_irq2:
+	free_irq(IRQ_IXP4XX_QM1, NULL);
+error_irq:
+	release_mem_region(IXP4XX_QMGR_BASE_PHYS, IXP4XX_QMGR_REGION_SIZE);
+	return err;
+}
+
+static void qmgr_remove(void)
+{
+	free_irq(IRQ_IXP4XX_QM1, NULL);
+	free_irq(IRQ_IXP4XX_QM2, NULL);
+	synchronize_irq(IRQ_IXP4XX_QM1);
+	synchronize_irq(IRQ_IXP4XX_QM2);
+	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_set_irq);
+EXPORT_SYMBOL(qmgr_enable_irq);
+EXPORT_SYMBOL(qmgr_disable_irq);
+#if DEBUG_QMGR
+EXPORT_SYMBOL(qmgr_queue_descs);
+EXPORT_SYMBOL(qmgr_request_queue);
+#else
+EXPORT_SYMBOL(__qmgr_request_queue);
+#endif
+EXPORT_SYMBOL(qmgr_release_queue);