Merge branch 'vexpress-dt-v3.3-rc4' of git://git.linaro.org/people/pawelmoll/linux into next/dt

* 'vexpress-dt-v3.3-rc4' of git://git.linaro.org/people/pawelmoll/linux: (573 commits)
  ARM: vexpress: Add Device Tree for V2P-CA15 core tile (TC1 variant)
  ARM: vexpress: Add Device Tree for V2P-CA9 core tile
  ARM: vexpress: Add Device Tree for V2P-CA5s core tile
  ARM: vexpress: Motherboard RS1 memory map support
  ARM: vexpress: Add Device Tree support
  ARM: vexpress: Use FDT data in platform SMP calls
  ARM: versatile: Map local timers using Device Tree when possible
  ARM: vexpress: Get rid of MMIO_P2V

This adds full device tree boot support for the versatile express
platform, as has been awaited for a long time.

Conflicts:
	arch/arm/mach-vexpress/core.h

The definition of AMBA_DEVICE was removed in one branch, and the
definition of MMIO_P2V was removed in the other branch.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>

11 files changed, 566 insertions, 110 deletions

diff --git a/arch/arm/mach-vexpress/Kconfig b/arch/arm/mach-vexpress/Kconfig
index 9b3d0fb..cf8730d 100644
--- a/arch/arm/mach-vexpress/Kconfig
+++ b/arch/arm/mach-vexpress/Kconfig
@@ -1,14 +1,55 @@
 menu "Versatile Express platform type"
 	depends on ARCH_VEXPRESS
 
+config ARCH_VEXPRESS_CORTEX_A5_A9_ERRATA
+	bool
+	select ARM_ERRATA_720789
+	select ARM_ERRATA_751472
+	select PL310_ERRATA_753970 if CACHE_PL310
+	help
+	  Provides common dependencies for Versatile Express platforms
+	  based on Cortex-A5 and Cortex-A9 processors. In order to
+	  build a working kernel, you must also enable relevant core
+	  tile support or Flattened Device Tree based support options.
+
 config ARCH_VEXPRESS_CA9X4
 	bool "Versatile Express Cortex-A9x4 tile"
+	select ARCH_VEXPRESS_CORTEX_A5_A9_ERRATA
+	select ARM_GIC
 	select CPU_V7
+	select HAVE_SMP
+	select MIGHT_HAVE_CACHE_L2X0
+
+config ARCH_VEXPRESS_DT
+	bool "Device Tree support for Versatile Express platforms"
+	select ARCH_VEXPRESS_CORTEX_A5_A9_ERRATA
 	select ARM_GIC
-	select ARM_ERRATA_720789
-	select ARM_ERRATA_751472
-	select ARM_ERRATA_753970
+	select ARM_PATCH_PHYS_VIRT
+	select AUTO_ZRELADDR
+	select CPU_V7
 	select HAVE_SMP
 	select MIGHT_HAVE_CACHE_L2X0
+	select USE_OF
+	help
+	  New Versatile Express platforms require Flattened Device Tree to
+	  be passed to the kernel.
+
+	  This option enables support for systems using Cortex processor based
+	  ARM core and logic (FPGA) tiles on the Versatile Express motherboard,
+	  for example:
+
+	  - CoreTile Express A5x2 (V2P-CA5s)
+	  - CoreTile Express A9x4 (V2P-CA9)
+	  - CoreTile Express A15x2 (V2P-CA15)
+	  - LogicTile Express 13MG (V2F-2XV6) with A5, A7, A9 or A15 SMMs
+	    (Soft Macrocell Models)
+	  - Versatile Express RTSMs (Models)
+
+	  You must boot using a Flattened Device Tree in order to use these
+	  platforms. The traditional (ATAGs) boot method is not usable on
+	  these boards with this option.
+
+	  If your bootloader supports Flattened Device Tree based booting,
+	  say Y here.
 
 endmenu
diff --git a/arch/arm/mach-vexpress/Makefile.boot b/arch/arm/mach-vexpress/Makefile.boot
index 8630b3d..909f85e 100644
--- a/arch/arm/mach-vexpress/Makefile.boot
+++ b/arch/arm/mach-vexpress/Makefile.boot
@@ -1,3 +1,9 @@
+# Those numbers are used only by the non-DT V2P-CA9 platform
+# The DT-enabled ones require CONFIG_AUTO_ZRELADDR=y
    zreladdr-y	+= 0x60008000
 params_phys-y	:= 0x60000100
 initrd_phys-y	:= 0x60800000
+
+dtb-$(CONFIG_ARCH_VEXPRESS_DT)	+= vexpress-v2p-ca5s.dtb \
+				   vexpress-v2p-ca9.dtb \
+				   vexpress-v2p-ca15-tc1.dtb
diff --git a/arch/arm/mach-vexpress/core.h b/arch/arm/mach-vexpress/core.h
index 9f0f282..a3a4980 100644
--- a/arch/arm/mach-vexpress/core.h
+++ b/arch/arm/mach-vexpress/core.h
@@ -1,2 +1,7 @@
-#define __MMIO_P2V(x)	(((x) & 0xfffff) | (((x) & 0x0f000000) >> 4) | 0xf8000000)
-#define MMIO_P2V(x)	((void __iomem *)__MMIO_P2V(x))
+/* 2MB large area for motherboard's peripherals static mapping */
+#define V2M_PERIPH 0xf8000000
+
+/* Tile's peripherals static mappings should start here */
+#define V2T_PERIPH 0xf8200000
+
+void vexpress_dt_smp_map_io(void);
diff --git a/arch/arm/mach-vexpress/ct-ca9x4.c b/arch/arm/mach-vexpress/ct-ca9x4.c
index 1b1d2e4..73791f0 100644
--- a/arch/arm/mach-vexpress/ct-ca9x4.c
+++ b/arch/arm/mach-vexpress/ct-ca9x4.c
@@ -30,57 +30,29 @@
 
 #include <plat/clcd.h>
 
-#define V2M_PA_CS7	0x10000000
-
 static struct map_desc ct_ca9x4_io_desc[] __initdata = {
 	{
-		.virtual	= __MMIO_P2V(CT_CA9X4_MPIC),
-		.pfn		= __phys_to_pfn(CT_CA9X4_MPIC),
-		.length		= SZ_16K,
-		.type		= MT_DEVICE,
-	}, {
-		.virtual	= __MMIO_P2V(CT_CA9X4_SP804_TIMER),
-		.pfn		= __phys_to_pfn(CT_CA9X4_SP804_TIMER),
-		.length		= SZ_4K,
-		.type		= MT_DEVICE,
-	}, {
-		.virtual	= __MMIO_P2V(CT_CA9X4_L2CC),
-		.pfn		= __phys_to_pfn(CT_CA9X4_L2CC),
-		.length		= SZ_4K,
-		.type		= MT_DEVICE,
+		.virtual        = V2T_PERIPH,
+		.pfn            = __phys_to_pfn(CT_CA9X4_MPIC),
+		.length         = SZ_8K,
+		.type           = MT_DEVICE,
 	},
 };
 
 static void __init ct_ca9x4_map_io(void)
 {
+	iotable_init(ct_ca9x4_io_desc, ARRAY_SIZE(ct_ca9x4_io_desc));
 #ifdef CONFIG_LOCAL_TIMERS
-	twd_base = MMIO_P2V(A9_MPCORE_TWD);
+	twd_base = ioremap(A9_MPCORE_TWD, SZ_32);
 #endif
-	iotable_init(ct_ca9x4_io_desc, ARRAY_SIZE(ct_ca9x4_io_desc));
 }
 
 static void __init ct_ca9x4_init_irq(void)
 {
-	gic_init(0, 29, MMIO_P2V(A9_MPCORE_GIC_DIST),
-		 MMIO_P2V(A9_MPCORE_GIC_CPU));
-}
-
-#if 0
-static void __init ct_ca9x4_timer_init(void)
-{
-	writel(0, MMIO_P2V(CT_CA9X4_TIMER0) + TIMER_CTRL);
-	writel(0, MMIO_P2V(CT_CA9X4_TIMER1) + TIMER_CTRL);
-
-	sp804_clocksource_init(MMIO_P2V(CT_CA9X4_TIMER1), "ct-timer1");
-	sp804_clockevents_init(MMIO_P2V(CT_CA9X4_TIMER0), IRQ_CT_CA9X4_TIMER0,
-		"ct-timer0");
+	gic_init(0, 29, ioremap(A9_MPCORE_GIC_DIST, SZ_4K),
+		 ioremap(A9_MPCORE_GIC_CPU, SZ_256));
 }
 
-static struct sys_timer ct_ca9x4_timer = {
-	.init	= ct_ca9x4_timer_init,
-};
-#endif
-
 static void ct_ca9x4_clcd_enable(struct clcd_fb *fb)
 {
 	v2m_cfg_write(SYS_CFG_MUXFPGA | SYS_CFG_SITE_DB1, 0);
@@ -201,7 +173,7 @@ static void __init ct_ca9x4_init(void)
 	int i;
 
 #ifdef CONFIG_CACHE_L2X0
-	void __iomem *l2x0_base = MMIO_P2V(CT_CA9X4_L2CC);
+	void __iomem *l2x0_base = ioremap(CT_CA9X4_L2CC, SZ_4K);
 
 	/* set RAM latencies to 1 cycle for this core tile. */
 	writel(0, l2x0_base + L2X0_TAG_LATENCY_CTRL);
@@ -217,9 +189,17 @@ static void __init ct_ca9x4_init(void)
 }
 
 #ifdef CONFIG_SMP
+static void *ct_ca9x4_scu_base __initdata;
+
 static void __init ct_ca9x4_init_cpu_map(void)
 {
-	int i, ncores = scu_get_core_count(MMIO_P2V(A9_MPCORE_SCU));
+	int i, ncores;
+
+	ct_ca9x4_scu_base = ioremap(A9_MPCORE_SCU, SZ_128);
+	if (WARN_ON(!ct_ca9x4_scu_base))
+		return;
+
+	ncores = scu_get_core_count(ct_ca9x4_scu_base);
 
 	if (ncores > nr_cpu_ids) {
 		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
@@ -235,7 +215,7 @@ static void __init ct_ca9x4_init_cpu_map(void)
 
 static void __init ct_ca9x4_smp_enable(unsigned int max_cpus)
 {
-	scu_enable(MMIO_P2V(A9_MPCORE_SCU));
+	scu_enable(ct_ca9x4_scu_base);
 }
 #endif
 
diff --git a/arch/arm/mach-vexpress/include/mach/ct-ca9x4.h b/arch/arm/mach-vexpress/include/mach/ct-ca9x4.h
index a40468f..84acf84 100644
--- a/arch/arm/mach-vexpress/include/mach/ct-ca9x4.h
+++ b/arch/arm/mach-vexpress/include/mach/ct-ca9x4.h
@@ -22,9 +22,6 @@
 #define CT_CA9X4_SYSWDT		(0x1e007000)
 #define CT_CA9X4_L2CC		(0x1e00a000)
 
-#define CT_CA9X4_TIMER0		(CT_CA9X4_SP804_TIMER + 0x000)
-#define CT_CA9X4_TIMER1		(CT_CA9X4_SP804_TIMER + 0x020)
-
 #define A9_MPCORE_SCU		(CT_CA9X4_MPIC + 0x0000)
 #define A9_MPCORE_GIC_CPU	(CT_CA9X4_MPIC + 0x0100)
 #define A9_MPCORE_GIT		(CT_CA9X4_MPIC + 0x0200)
diff --git a/arch/arm/mach-vexpress/include/mach/debug-macro.S b/arch/arm/mach-vexpress/include/mach/debug-macro.S
index fd9e6c7..fa82247 100644
--- a/arch/arm/mach-vexpress/include/mach/debug-macro.S
+++ b/arch/arm/mach-vexpress/include/mach/debug-macro.S
@@ -10,12 +10,34 @@
  * published by the Free Software Foundation.
  */
 
-#define DEBUG_LL_UART_OFFSET	0x00009000
+#define DEBUG_LL_PHYS_BASE		0x10000000
+#define DEBUG_LL_UART_OFFSET		0x00009000
+
+#define DEBUG_LL_PHYS_BASE_RS1		0x1c000000
+#define DEBUG_LL_UART_OFFSET_RS1	0x00090000
+
+#define DEBUG_LL_VIRT_BASE		0xf8000000
 
 		.macro	addruart,rp,rv,tmp
-		mov	\rp, #DEBUG_LL_UART_OFFSET
-		orr	\rv, \rp, #0xf8000000	@ virtual base
-		orr	\rp, \rp, #0x10000000	@ physical base
+
+		@ Make an educated guess regarding the memory map:
+		@ - the original A9 core tile, which has MPCore peripherals
+		@   located at 0x1e000000, should use UART at 0x10009000
+		@ - all other (RS1 complaint) tiles use UART mapped
+		@   at 0x1c090000
+		mrc	p15, 4, \tmp, c15, c0, 0
+		cmp	\tmp, #0x1e000000
+
+		@ Original memory map
+		moveq	\rp, #DEBUG_LL_UART_OFFSET
+		orreq	\rv, \rp, #DEBUG_LL_VIRT_BASE
+		orreq	\rp, \rp, #DEBUG_LL_PHYS_BASE
+
+		@ RS1 memory map
+		movne	\rp, #DEBUG_LL_UART_OFFSET_RS1
+		orrne	\rv, \rp, #DEBUG_LL_VIRT_BASE
+		orrne	\rp, \rp, #DEBUG_LL_PHYS_BASE_RS1
+
 		.endm
 
 #include <asm/hardware/debug-pl01x.S>
diff --git a/arch/arm/mach-vexpress/include/mach/irqs.h b/arch/arm/mach-vexpress/include/mach/irqs.h
index 7054cbf..4b10ee7 100644
--- a/arch/arm/mach-vexpress/include/mach/irqs.h
+++ b/arch/arm/mach-vexpress/include/mach/irqs.h
@@ -1,4 +1,4 @@
 #define IRQ_LOCALTIMER		29
 #define IRQ_LOCALWDOG		30
 
-#define NR_IRQS	128
+#define NR_IRQS	256
diff --git a/arch/arm/mach-vexpress/include/mach/motherboard.h b/arch/arm/mach-vexpress/include/mach/motherboard.h
index 0a3a375..31a9289 100644
--- a/arch/arm/mach-vexpress/include/mach/motherboard.h
+++ b/arch/arm/mach-vexpress/include/mach/motherboard.h
@@ -39,33 +39,30 @@
 #define V2M_CF			(V2M_PA_CS7 + 0x0001a000)
 #define V2M_CLCD		(V2M_PA_CS7 + 0x0001f000)
 
-#define V2M_SYS_ID		(V2M_SYSREGS + 0x000)
-#define V2M_SYS_SW		(V2M_SYSREGS + 0x004)
-#define V2M_SYS_LED		(V2M_SYSREGS + 0x008)
-#define V2M_SYS_100HZ		(V2M_SYSREGS + 0x024)
-#define V2M_SYS_FLAGS		(V2M_SYSREGS + 0x030)
-#define V2M_SYS_FLAGSSET	(V2M_SYSREGS + 0x030)
-#define V2M_SYS_FLAGSCLR	(V2M_SYSREGS + 0x034)
-#define V2M_SYS_NVFLAGS		(V2M_SYSREGS + 0x038)
-#define V2M_SYS_NVFLAGSSET	(V2M_SYSREGS + 0x038)
-#define V2M_SYS_NVFLAGSCLR	(V2M_SYSREGS + 0x03c)
-#define V2M_SYS_MCI		(V2M_SYSREGS + 0x048)
-#define V2M_SYS_FLASH		(V2M_SYSREGS + 0x03c)
-#define V2M_SYS_CFGSW		(V2M_SYSREGS + 0x058)
-#define V2M_SYS_24MHZ		(V2M_SYSREGS + 0x05c)
-#define V2M_SYS_MISC		(V2M_SYSREGS + 0x060)
-#define V2M_SYS_DMA		(V2M_SYSREGS + 0x064)
-#define V2M_SYS_PROCID0		(V2M_SYSREGS + 0x084)
-#define V2M_SYS_PROCID1		(V2M_SYSREGS + 0x088)
-#define V2M_SYS_CFGDATA		(V2M_SYSREGS + 0x0a0)
-#define V2M_SYS_CFGCTRL		(V2M_SYSREGS + 0x0a4)
-#define V2M_SYS_CFGSTAT		(V2M_SYSREGS + 0x0a8)
-
-#define V2M_TIMER0		(V2M_TIMER01 + 0x000)
-#define V2M_TIMER1		(V2M_TIMER01 + 0x020)
-
-#define V2M_TIMER2		(V2M_TIMER23 + 0x000)
-#define V2M_TIMER3		(V2M_TIMER23 + 0x020)
+/*
+ * Offsets from SYSREGS base
+ */
+#define V2M_SYS_ID		0x000
+#define V2M_SYS_SW		0x004
+#define V2M_SYS_LED		0x008
+#define V2M_SYS_100HZ		0x024
+#define V2M_SYS_FLAGS		0x030
+#define V2M_SYS_FLAGSSET	0x030
+#define V2M_SYS_FLAGSCLR	0x034
+#define V2M_SYS_NVFLAGS		0x038
+#define V2M_SYS_NVFLAGSSET	0x038
+#define V2M_SYS_NVFLAGSCLR	0x03c
+#define V2M_SYS_MCI		0x048
+#define V2M_SYS_FLASH		0x03c
+#define V2M_SYS_CFGSW		0x058
+#define V2M_SYS_24MHZ		0x05c
+#define V2M_SYS_MISC		0x060
+#define V2M_SYS_DMA		0x064
+#define V2M_SYS_PROCID0		0x084
+#define V2M_SYS_PROCID1		0x088
+#define V2M_SYS_CFGDATA		0x0a0
+#define V2M_SYS_CFGCTRL		0x0a4
+#define V2M_SYS_CFGSTAT		0x0a8
 
 
 /*
@@ -117,6 +114,13 @@
 
 int v2m_cfg_write(u32 devfn, u32 data);
 int v2m_cfg_read(u32 devfn, u32 *data);
+void v2m_flags_set(u32 data);
+
+/*
+ * Miscellaneous
+ */
+#define SYS_MISC_MASTERSITE	(1 << 14)
+#define SYS_PROCIDx_HBI_MASK	0xfff
 
 /*
  * Core tile IDs
diff --git a/arch/arm/mach-vexpress/include/mach/uncompress.h b/arch/arm/mach-vexpress/include/mach/uncompress.h
index 7972c57..7dab559 100644
--- a/arch/arm/mach-vexpress/include/mach/uncompress.h
+++ b/arch/arm/mach-vexpress/include/mach/uncompress.h
@@ -22,7 +22,27 @@
 #define AMBA_UART_CR(base)	(*(volatile unsigned char *)((base) + 0x30))
 #define AMBA_UART_FR(base)	(*(volatile unsigned char *)((base) + 0x18))
 
-#define get_uart_base()	(0x10000000 + 0x00009000)
+#define UART_BASE	0x10009000
+#define UART_BASE_RS1	0x1c090000
+
+static unsigned long get_uart_base(void)
+{
+	unsigned long mpcore_periph;
+
+	/*
+	 * Make an educated guess regarding the memory map:
+	 * - the original A9 core tile, which has MPCore peripherals
+	 *   located at 0x1e000000, should use UART at 0x10009000
+	 * - all other (RS1 complaint) tiles use UART mapped
+	 *   at 0x1c090000
+	 */
+	asm("mrc p15, 4, %0, c15, c0, 0" : "=r" (mpcore_periph));
+
+	if (mpcore_periph == 0x1e000000)
+		return UART_BASE;
+	else
+		return UART_BASE_RS1;
+}
 
 /*
  * This does not append a newline
diff --git a/arch/arm/mach-vexpress/platsmp.c b/arch/arm/mach-vexpress/platsmp.c
index 124ffb1..14ba112 100644
--- a/arch/arm/mach-vexpress/platsmp.c
+++ b/arch/arm/mach-vexpress/platsmp.c
@@ -12,21 +12,168 @@
 #include <linux/errno.h>
 #include <linux/smp.h>
 #include <linux/io.h>
+#include <linux/of_fdt.h>
+
+#include <asm/smp_scu.h>
+#include <asm/hardware/gic.h>
+#include <asm/mach/map.h>
 
 #include <mach/motherboard.h>
-#define V2M_PA_CS7 0x10000000
 
 #include "core.h"
 
 extern void versatile_secondary_startup(void);
 
+#if defined(CONFIG_OF)
+
+static enum {
+	GENERIC_SCU,
+	CORTEX_A9_SCU,
+} vexpress_dt_scu __initdata = GENERIC_SCU;
+
+static struct map_desc vexpress_dt_cortex_a9_scu_map __initdata = {
+	.virtual	= V2T_PERIPH,
+	/* .pfn	set in vexpress_dt_init_cortex_a9_scu() */
+	.length		= SZ_128,
+	.type		= MT_DEVICE,
+};
+
+static void *vexpress_dt_cortex_a9_scu_base __initdata;
+
+const static char *vexpress_dt_cortex_a9_match[] __initconst = {
+	"arm,cortex-a5-scu",
+	"arm,cortex-a9-scu",
+	NULL
+};
+
+static int __init vexpress_dt_find_scu(unsigned long node,
+		const char *uname, int depth, void *data)
+{
+	if (of_flat_dt_match(node, vexpress_dt_cortex_a9_match)) {
+		phys_addr_t phys_addr;
+		__be32 *reg = of_get_flat_dt_prop(node, "reg", NULL);
+
+		if (WARN_ON(!reg))
+			return -EINVAL;
+
+		phys_addr = be32_to_cpup(reg);
+		vexpress_dt_scu = CORTEX_A9_SCU;
+
+		vexpress_dt_cortex_a9_scu_map.pfn = __phys_to_pfn(phys_addr);
+		iotable_init(&vexpress_dt_cortex_a9_scu_map, 1);
+		vexpress_dt_cortex_a9_scu_base = ioremap(phys_addr, SZ_256);
+		if (WARN_ON(!vexpress_dt_cortex_a9_scu_base))
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+void __init vexpress_dt_smp_map_io(void)
+{
+	if (initial_boot_params)
+		WARN_ON(of_scan_flat_dt(vexpress_dt_find_scu, NULL));
+}
+
+static int __init vexpress_dt_cpus_num(unsigned long node, const char *uname,
+		int depth, void *data)
+{
+	static int prev_depth = -1;
+	static int nr_cpus = -1;
+
+	if (prev_depth > depth && nr_cpus > 0)
+		return nr_cpus;
+
+	if (nr_cpus < 0 && strcmp(uname, "cpus") == 0)
+		nr_cpus = 0;
+
+	if (nr_cpus >= 0) {
+		const char *device_type = of_get_flat_dt_prop(node,
+				"device_type", NULL);
+
+		if (device_type && strcmp(device_type, "cpu") == 0)
+			nr_cpus++;
+	}
+
+	prev_depth = depth;
+
+	return 0;
+}
+
+static void __init vexpress_dt_smp_init_cpus(void)
+{
+	int ncores = 0, i;
+
+	switch (vexpress_dt_scu) {
+	case GENERIC_SCU:
+		ncores = of_scan_flat_dt(vexpress_dt_cpus_num, NULL);
+		break;
+	case CORTEX_A9_SCU:
+		ncores = scu_get_core_count(vexpress_dt_cortex_a9_scu_base);
+		break;
+	default:
+		WARN_ON(1);
+		break;
+	}
+
+	if (ncores < 2)
+		return;
+
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
+				ncores, nr_cpu_ids);
+		ncores = nr_cpu_ids;
+	}
+
+	for (i = 0; i < ncores; ++i)
+		set_cpu_possible(i, true);
+
+	set_smp_cross_call(gic_raise_softirq);
+}
+
+static void __init vexpress_dt_smp_prepare_cpus(unsigned int max_cpus)
+{
+	int i;
+
+	switch (vexpress_dt_scu) {
+	case GENERIC_SCU:
+		for (i = 0; i < max_cpus; i++)
+			set_cpu_present(i, true);
+		break;
+	case CORTEX_A9_SCU:
+		scu_enable(vexpress_dt_cortex_a9_scu_base);
+		break;
+	default:
+		WARN_ON(1);
+		break;
+	}
+}
+
+#else
+
+static void __init vexpress_dt_smp_init_cpus(void)
+{
+	WARN_ON(1);
+}
+
+void __init vexpress_dt_smp_prepare_cpus(unsigned int max_cpus)
+{
+	WARN_ON(1);
+}
+
+#endif
+
 /*
  * Initialise the CPU possible map early - this describes the CPUs
  * which may be present or become present in the system.
  */
 void __init smp_init_cpus(void)
 {
-	ct_desc->init_cpu_map();
+	if (ct_desc)
+		ct_desc->init_cpu_map();
+	else
+		vexpress_dt_smp_init_cpus();
+
 }
 
 void __init platform_smp_prepare_cpus(unsigned int max_cpus)
@@ -35,7 +182,10 @@ void __init platform_smp_prepare_cpus(unsigned int max_cpus)
 	 * Initialise the present map, which describes the set of CPUs
 	 * actually populated at the present time.
 	 */
-	ct_desc->smp_enable(max_cpus);
+	if (ct_desc)
+		ct_desc->smp_enable(max_cpus);
+	else
+		vexpress_dt_smp_prepare_cpus(max_cpus);
 
 	/*
 	 * Write the address of secondary startup into the
@@ -43,7 +193,5 @@ void __init platform_smp_prepare_cpus(unsigned int max_cpus)
 	 * until it receives a soft interrupt, and then the
 	 * secondary CPU branches to this address.
 	 */
-	writel(~0, MMIO_P2V(V2M_SYS_FLAGSCLR));
-	writel(virt_to_phys(versatile_secondary_startup),
-		MMIO_P2V(V2M_SYS_FLAGSSET));
+	v2m_flags_set(virt_to_phys(versatile_secondary_startup));
 }
diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c
index ad64f97..47cdcca 100644
--- a/arch/arm/mach-vexpress/v2m.c
+++ b/arch/arm/mach-vexpress/v2m.c
@@ -6,6 +6,10 @@
 #include <linux/amba/mmci.h>
 #include <linux/io.h>
 #include <linux/init.h>
+#include <linux/of_address.h>
+#include <linux/of_fdt.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/ata_platform.h>
 #include <linux/smsc911x.h>
@@ -21,6 +25,8 @@
 #include <asm/mach/map.h>
 #include <asm/mach/time.h>
 #include <asm/hardware/arm_timer.h>
+#include <asm/hardware/cache-l2x0.h>
+#include <asm/hardware/gic.h>
 #include <asm/hardware/timer-sp.h>
 #include <asm/hardware/sp810.h>
 #include <asm/hardware/gic.h>
@@ -40,29 +46,45 @@
 
 static struct map_desc v2m_io_desc[] __initdata = {
 	{
-		.virtual	= __MMIO_P2V(V2M_PA_CS7),
+		.virtual	= V2M_PERIPH,
 		.pfn		= __phys_to_pfn(V2M_PA_CS7),
 		.length		= SZ_128K,
 		.type		= MT_DEVICE,
 	},
 };
 
-static void __init v2m_timer_init(void)
+static void __iomem *v2m_sysreg_base;
+
+static void __init v2m_sysctl_init(void __iomem *base)
 {
 	u32 scctrl;
 
+	if (WARN_ON(!base))
+		return;
+
 	/* Select 1MHz TIMCLK as the reference clock for SP804 timers */
-	scctrl = readl(MMIO_P2V(V2M_SYSCTL + SCCTRL));
+	scctrl = readl(base + SCCTRL);
 	scctrl |= SCCTRL_TIMEREN0SEL_TIMCLK;
 	scctrl |= SCCTRL_TIMEREN1SEL_TIMCLK;
-	writel(scctrl, MMIO_P2V(V2M_SYSCTL + SCCTRL));
+	writel(scctrl, base + SCCTRL);
+}
+
+static void __init v2m_sp804_init(void __iomem *base, unsigned int irq)
+{
+	if (WARN_ON(!base || irq == NO_IRQ))
+		return;
+
+	writel(0, base + TIMER_1_BASE + TIMER_CTRL);
+	writel(0, base + TIMER_2_BASE + TIMER_CTRL);
 
-	writel(0, MMIO_P2V(V2M_TIMER0) + TIMER_CTRL);
-	writel(0, MMIO_P2V(V2M_TIMER1) + TIMER_CTRL);
+	sp804_clocksource_init(base + TIMER_2_BASE, "v2m-timer1");
+	sp804_clockevents_init(base + TIMER_1_BASE, irq, "v2m-timer0");
+}
 
-	sp804_clocksource_init(MMIO_P2V(V2M_TIMER1), "v2m-timer1");
-	sp804_clockevents_init(MMIO_P2V(V2M_TIMER0), IRQ_V2M_TIMER0,
-		"v2m-timer0");
+static void __init v2m_timer_init(void)
+{
+	v2m_sysctl_init(ioremap(V2M_SYSCTL, SZ_4K));
+	v2m_sp804_init(ioremap(V2M_TIMER01, SZ_4K), IRQ_V2M_TIMER0);
 }
 
 static struct sys_timer v2m_timer = {
@@ -82,14 +104,14 @@ int v2m_cfg_write(u32 devfn, u32 data)
 	devfn |= SYS_CFG_START | SYS_CFG_WRITE;
 
 	spin_lock(&v2m_cfg_lock);
-	val = readl(MMIO_P2V(V2M_SYS_CFGSTAT));
-	writel(val & ~SYS_CFG_COMPLETE, MMIO_P2V(V2M_SYS_CFGSTAT));
+	val = readl(v2m_sysreg_base + V2M_SYS_CFGSTAT);
+	writel(val & ~SYS_CFG_COMPLETE, v2m_sysreg_base + V2M_SYS_CFGSTAT);
 
-	writel(data, MMIO_P2V(V2M_SYS_CFGDATA));
-	writel(devfn, MMIO_P2V(V2M_SYS_CFGCTRL));
+	writel(data, v2m_sysreg_base +  V2M_SYS_CFGDATA);
+	writel(devfn, v2m_sysreg_base + V2M_SYS_CFGCTRL);
 
 	do {
-		val = readl(MMIO_P2V(V2M_SYS_CFGSTAT));
+		val = readl(v2m_sysreg_base + V2M_SYS_CFGSTAT);
 	} while (val == 0);
 	spin_unlock(&v2m_cfg_lock);
 
@@ -103,22 +125,28 @@ int v2m_cfg_read(u32 devfn, u32 *data)
 	devfn |= SYS_CFG_START;
 
 	spin_lock(&v2m_cfg_lock);
-	writel(0, MMIO_P2V(V2M_SYS_CFGSTAT));
-	writel(devfn, MMIO_P2V(V2M_SYS_CFGCTRL));
+	writel(0, v2m_sysreg_base + V2M_SYS_CFGSTAT);
+	writel(devfn, v2m_sysreg_base + V2M_SYS_CFGCTRL);
 
 	mb();
 
 	do {
 		cpu_relax();
-		val = readl(MMIO_P2V(V2M_SYS_CFGSTAT));
+		val = readl(v2m_sysreg_base + V2M_SYS_CFGSTAT);
 	} while (val == 0);
 
-	*data = readl(MMIO_P2V(V2M_SYS_CFGDATA));
+	*data = readl(v2m_sysreg_base + V2M_SYS_CFGDATA);
 	spin_unlock(&v2m_cfg_lock);
 
 	return !!(val & SYS_CFG_ERR);
 }
 
+void __init v2m_flags_set(u32 data)
+{
+	writel(~0, v2m_sysreg_base + V2M_SYS_FLAGSCLR);
+	writel(data, v2m_sysreg_base + V2M_SYS_FLAGSSET);
+}
+
 
 static struct resource v2m_pcie_i2c_resource = {
 	.start	= V2M_SERIAL_BUS_PCI,
@@ -204,7 +232,7 @@ static struct platform_device v2m_usb_device = {
 
 static void v2m_flash_set_vpp(struct platform_device *pdev, int on)
 {
-	writel(on != 0, MMIO_P2V(V2M_SYS_FLASH));
+	writel(on != 0, v2m_sysreg_base + V2M_SYS_FLASH);
 }
 
 static struct physmap_flash_data v2m_flash_data = {
@@ -258,7 +286,7 @@ static struct platform_device v2m_cf_device = {
 
 static unsigned int v2m_mmci_status(struct device *dev)
 {
-	return readl(MMIO_P2V(V2M_SYS_MCI)) & (1 << 0);
+	return readl(v2m_sysreg_base + V2M_SYS_MCI) & (1 << 0);
 }
 
 static struct mmci_platform_data v2m_mmci_data = {
@@ -371,7 +399,7 @@ static void __init v2m_init_early(void)
 {
 	ct_desc->init_early();
 	clkdev_add_table(v2m_lookups, ARRAY_SIZE(v2m_lookups));
-	versatile_sched_clock_init(MMIO_P2V(V2M_SYS_24MHZ), 24000000);
+	versatile_sched_clock_init(v2m_sysreg_base + V2M_SYS_24MHZ, 24000000);
 }
 
 static void v2m_power_off(void)
@@ -400,20 +428,23 @@ static void __init v2m_populate_ct_desc(void)
 	u32 current_tile_id;
 
 	ct_desc = NULL;
-	current_tile_id = readl(MMIO_P2V(V2M_SYS_PROCID0)) & V2M_CT_ID_MASK;
+	current_tile_id = readl(v2m_sysreg_base + V2M_SYS_PROCID0)
+				& V2M_CT_ID_MASK;
 
 	for (i = 0; i < ARRAY_SIZE(ct_descs) && !ct_desc; ++i)
 		if (ct_descs[i]->id == current_tile_id)
 			ct_desc = ct_descs[i];
 
 	if (!ct_desc)
-		panic("vexpress: failed to populate core tile description "
-		      "for tile ID 0x%8x\n", current_tile_id);
+		panic("vexpress: this kernel does not support core tile ID 0x%08x when booting via ATAGs.\n"
+		      "You may need a device tree blob or a different kernel to boot on this board.\n",
+		      current_tile_id);
 }
 
 static void __init v2m_map_io(void)
 {
 	iotable_init(v2m_io_desc, ARRAY_SIZE(v2m_io_desc));
+	v2m_sysreg_base = ioremap(V2M_SYSREGS, SZ_4K);
 	v2m_populate_ct_desc();
 	ct_desc->map_io();
 }
@@ -452,3 +483,205 @@ MACHINE_START(VEXPRESS, "ARM-Versatile Express")
 	.init_machine	= v2m_init,
 	.restart	= v2m_restart,
 MACHINE_END
+
+#if defined(CONFIG_ARCH_VEXPRESS_DT)
+
+static struct map_desc v2m_rs1_io_desc __initdata = {
+	.virtual	= V2M_PERIPH,
+	.pfn		= __phys_to_pfn(0x1c000000),
+	.length		= SZ_2M,
+	.type		= MT_DEVICE,
+};
+
+static int __init v2m_dt_scan_memory_map(unsigned long node, const char *uname,
+		int depth, void *data)
+{
+	const char **map = data;
+
+	if (strcmp(uname, "motherboard") != 0)
+		return 0;
+
+	*map = of_get_flat_dt_prop(node, "arm,v2m-memory-map", NULL);
+
+	return 1;
+}
+
+void __init v2m_dt_map_io(void)
+{
+	const char *map = NULL;
+
+	of_scan_flat_dt(v2m_dt_scan_memory_map, &map);
+
+	if (map && strcmp(map, "rs1") == 0)
+		iotable_init(&v2m_rs1_io_desc, 1);
+	else
+		iotable_init(v2m_io_desc, ARRAY_SIZE(v2m_io_desc));
+
+#if defined(CONFIG_SMP)
+	vexpress_dt_smp_map_io();
+#endif
+}
+
+static struct clk_lookup v2m_dt_lookups[] = {
+	{	/* AMBA bus clock */
+		.con_id		= "apb_pclk",
+		.clk		= &dummy_apb_pclk,
+	}, {	/* SP804 timers */
+		.dev_id		= "sp804",
+		.con_id		= "v2m-timer0",
+		.clk		= &v2m_sp804_clk,
+	}, {	/* SP804 timers */
+		.dev_id		= "sp804",
+		.con_id		= "v2m-timer1",
+		.clk		= &v2m_sp804_clk,
+	}, {	/* PL180 MMCI */
+		.dev_id		= "mb:mmci", /* 10005000.mmci */
+		.clk		= &osc2_clk,
+	}, {	/* PL050 KMI0 */
+		.dev_id		= "10006000.kmi",
+		.clk		= &osc2_clk,
+	}, {	/* PL050 KMI1 */
+		.dev_id		= "10007000.kmi",
+		.clk		= &osc2_clk,
+	}, {	/* PL011 UART0 */
+		.dev_id		= "10009000.uart",
+		.clk		= &osc2_clk,
+	}, {	/* PL011 UART1 */
+		.dev_id		= "1000a000.uart",
+		.clk		= &osc2_clk,
+	}, {	/* PL011 UART2 */
+		.dev_id		= "1000b000.uart",
+		.clk		= &osc2_clk,
+	}, {	/* PL011 UART3 */
+		.dev_id		= "1000c000.uart",
+		.clk		= &osc2_clk,
+	}, {	/* SP805 WDT */
+		.dev_id		= "1000f000.wdt",
+		.clk		= &v2m_ref_clk,
+	}, {	/* PL111 CLCD */
+		.dev_id		= "1001f000.clcd",
+		.clk		= &osc1_clk,
+	},
+	/* RS1 memory map */
+	{	/* PL180 MMCI */
+		.dev_id		= "mb:mmci", /* 1c050000.mmci */
+		.clk		= &osc2_clk,
+	}, {	/* PL050 KMI0 */
+		.dev_id		= "1c060000.kmi",
+		.clk		= &osc2_clk,
+	}, {	/* PL050 KMI1 */
+		.dev_id		= "1c070000.kmi",
+		.clk		= &osc2_clk,
+	}, {	/* PL011 UART0 */
+		.dev_id		= "1c090000.uart",
+		.clk		= &osc2_clk,
+	}, {	/* PL011 UART1 */
+		.dev_id		= "1c0a0000.uart",
+		.clk		= &osc2_clk,
+	}, {	/* PL011 UART2 */
+		.dev_id		= "1c0b0000.uart",
+		.clk		= &osc2_clk,
+	}, {	/* PL011 UART3 */
+		.dev_id		= "1c0c0000.uart",
+		.clk		= &osc2_clk,
+	}, {	/* SP805 WDT */
+		.dev_id		= "1c0f0000.wdt",
+		.clk		= &v2m_ref_clk,
+	}, {	/* PL111 CLCD */
+		.dev_id		= "1c1f0000.clcd",
+		.clk		= &osc1_clk,
+	},
+};
+
+void __init v2m_dt_init_early(void)
+{
+	struct device_node *node;
+	u32 dt_hbi;
+
+	node = of_find_compatible_node(NULL, NULL, "arm,vexpress-sysreg");
+	v2m_sysreg_base = of_iomap(node, 0);
+	if (WARN_ON(!v2m_sysreg_base))
+		return;
+
+	/* Confirm board type against DT property, if available */
+	if (of_property_read_u32(allnodes, "arm,hbi", &dt_hbi) == 0) {
+		u32 misc = readl(v2m_sysreg_base + V2M_SYS_MISC);
+		u32 id = readl(v2m_sysreg_base + (misc & SYS_MISC_MASTERSITE ?
+				V2M_SYS_PROCID1 : V2M_SYS_PROCID0));
+		u32 hbi = id & SYS_PROCIDx_HBI_MASK;
+
+		if (WARN_ON(dt_hbi != hbi))
+			pr_warning("vexpress: DT HBI (%x) is not matching "
+					"hardware (%x)!\n", dt_hbi, hbi);
+	}
+
+	clkdev_add_table(v2m_dt_lookups, ARRAY_SIZE(v2m_dt_lookups));
+	versatile_sched_clock_init(v2m_sysreg_base + V2M_SYS_24MHZ, 24000000);
+}
+
+static  struct of_device_id vexpress_irq_match[] __initdata = {
+	{ .compatible = "arm,cortex-a9-gic", .data = gic_of_init, },
+	{}
+};
+
+static void __init v2m_dt_init_irq(void)
+{
+	of_irq_init(vexpress_irq_match);
+}
+
+static void __init v2m_dt_timer_init(void)
+{
+	struct device_node *node;
+	const char *path;
+	int err;
+
+	node = of_find_compatible_node(NULL, NULL, "arm,sp810");
+	v2m_sysctl_init(of_iomap(node, 0));
+
+	err = of_property_read_string(of_aliases, "arm,v2m_timer", &path);
+	if (WARN_ON(err))
+		return;
+	node = of_find_node_by_path(path);
+	v2m_sp804_init(of_iomap(node, 0), irq_of_parse_and_map(node, 0));
+}
+
+static struct sys_timer v2m_dt_timer = {
+	.init = v2m_dt_timer_init,
+};
+
+static struct of_dev_auxdata v2m_dt_auxdata_lookup[] __initdata = {
+	OF_DEV_AUXDATA("arm,vexpress-flash", V2M_NOR0, "physmap-flash",
+			&v2m_flash_data),
+	OF_DEV_AUXDATA("arm,primecell", V2M_MMCI, "mb:mmci", &v2m_mmci_data),
+	/* RS1 memory map */
+	OF_DEV_AUXDATA("arm,vexpress-flash", 0x08000000, "physmap-flash",
+			&v2m_flash_data),
+	OF_DEV_AUXDATA("arm,primecell", 0x1c050000, "mb:mmci", &v2m_mmci_data),
+	{}
+};
+
+static void __init v2m_dt_init(void)
+{
+	l2x0_of_init(0x00400000, 0xfe0fffff);
+	of_platform_populate(NULL, of_default_bus_match_table,
+			v2m_dt_auxdata_lookup, NULL);
+	pm_power_off = v2m_power_off;
+}
+
+const static char *v2m_dt_match[] __initconst = {
+	"arm,vexpress",
+	NULL,
+};
+
+DT_MACHINE_START(VEXPRESS_DT, "ARM-Versatile Express")
+	.dt_compat	= v2m_dt_match,
+	.map_io		= v2m_dt_map_io,
+	.init_early	= v2m_dt_init_early,
+	.init_irq	= v2m_dt_init_irq,
+	.timer		= &v2m_dt_timer,
+	.init_machine	= v2m_dt_init,
+	.handle_irq	= gic_handle_irq,
+	.restart	= v2m_restart,
+MACHINE_END
+
+#endif