Merge master.kernel.org:/home/rmk/linux-2.6-arm

34 files changed, 1091 insertions, 482 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 475950c8a83..ee8a9ad7bbd 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -67,10 +67,6 @@ config GENERIC_BUST_SPINLOCK
 config GENERIC_ISA_DMA
 	bool
 
-config GENERIC_IOMAP
-	bool
-	default y
-
 config FIQ
 	bool
 
@@ -202,6 +198,11 @@ config ARCH_H720X
 	help
 	  This enables support for systems based on the Hynix HMS720x
 
+config ARCH_AAEC2000
+	bool "Agilent AAEC-2000 based"
+	help
+	  This enables support for systems based on the Agilent AAEC-2000
+
 endchoice
 
 source "arch/arm/mach-clps711x/Kconfig"
@@ -234,6 +235,8 @@ source "arch/arm/mach-h720x/Kconfig"
 
 source "arch/arm/mach-versatile/Kconfig"
 
+source "arch/arm/mach-aaec2000/Kconfig"
+
 # Definitions to make life easier
 config ARCH_ACORN
 	bool
@@ -277,7 +280,7 @@ config ISA_DMA_API
 	default y
 
 config PCI
-	bool "PCI support" if ARCH_INTEGRATOR_AP
+	bool "PCI support" if ARCH_INTEGRATOR_AP || ARCH_VERSATILE_PB
 	help
 	  Find out whether you have a PCI motherboard. PCI is the name of a
 	  bus system, i.e. the way the CPU talks to the other stuff inside
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 2277e3d179c..8330495e244 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -97,6 +97,7 @@ textaddr-$(CONFIG_ARCH_FORTUNET)   := 0xc0008000
  machine-$(CONFIG_ARCH_VERSATILE)  := versatile
  machine-$(CONFIG_ARCH_IMX)	   := imx
  machine-$(CONFIG_ARCH_H720X)	   := h720x
+ machine-$(CONFIG_ARCH_AAEC2000)   := aaec2000
 
 ifeq ($(CONFIG_ARCH_EBSA110),y)
 # This is what happens if you forget the IOCS16 line.
diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c
index 5797b1b100a..9d63a01214e 100644
--- a/arch/arm/common/dmabounce.c
+++ b/arch/arm/common/dmabounce.c
@@ -30,6 +30,8 @@
 #include <linux/dmapool.h>
 #include <linux/list.h>
 
+#include <asm/cacheflush.h>
+
 #undef DEBUG
 
 #undef STATS
@@ -302,12 +304,24 @@ unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
 
 		DO_STATS ( device_info->bounce_count++ );
 
-		if ((dir == DMA_FROM_DEVICE) ||
-		    (dir == DMA_BIDIRECTIONAL)) {
+		if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) {
+			unsigned long ptr;
+
 			dev_dbg(dev,
 				"%s: copy back safe %p to unsafe %p size %d\n",
 				__func__, buf->safe, buf->ptr, size);
 			memcpy(buf->ptr, buf->safe, size);
+
+			/*
+			 * DMA buffers must have the same cache properties
+			 * as if they were really used for DMA - which means
+			 * data must be written back to RAM.  Note that
+			 * we don't use dmac_flush_range() here for the
+			 * bidirectional case because we know the cache
+			 * lines will be coherent with the data written.
+			 */
+			ptr = (unsigned long)buf->ptr;
+			dmac_clean_range(ptr, ptr + size);
 		}
 		free_safe_buffer(device_info, buf);
 	}
diff --git a/arch/arm/common/sharpsl_param.c b/arch/arm/common/sharpsl_param.c
index c2c557a224c..c94864c5b1a 100644
--- a/arch/arm/common/sharpsl_param.c
+++ b/arch/arm/common/sharpsl_param.c
@@ -22,7 +22,7 @@
  * them early in the boot process, then pass them to the appropriate drivers.
  * Not all devices use all paramaters but the format is common to all.
  */
-#ifdef ARCH_SA1100
+#ifdef CONFIG_ARCH_SA1100
 #define PARAM_BASE	0xe8ffc000
 #else
 #define PARAM_BASE	0xa0000a00
diff --git a/arch/arm/configs/enp2611_defconfig b/arch/arm/configs/enp2611_defconfig
index e8f9fccffe8..06fae4b6277 100644
--- a/arch/arm/configs/enp2611_defconfig
+++ b/arch/arm/configs/enp2611_defconfig
@@ -50,7 +50,13 @@ CONFIG_BASE_SMALL=0
 #
 # Loadable module support
 #
-# CONFIG_MODULES is not set
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+# CONFIG_MODULE_FORCE_UNLOAD is not set
+CONFIG_OBSOLETE_MODPARM=y
+# CONFIG_MODVERSIONS is not set
+# CONFIG_MODULE_SRCVERSION_ALL is not set
+CONFIG_KMOD=y
 
 #
 # System Type
diff --git a/arch/arm/configs/ixdp2400_defconfig b/arch/arm/configs/ixdp2400_defconfig
index 4fd663ecbe3..810a450a55d 100644
--- a/arch/arm/configs/ixdp2400_defconfig
+++ b/arch/arm/configs/ixdp2400_defconfig
@@ -50,7 +50,13 @@ CONFIG_BASE_SMALL=0
 #
 # Loadable module support
 #
-# CONFIG_MODULES is not set
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+# CONFIG_MODULE_FORCE_UNLOAD is not set
+CONFIG_OBSOLETE_MODPARM=y
+# CONFIG_MODVERSIONS is not set
+# CONFIG_MODULE_SRCVERSION_ALL is not set
+CONFIG_KMOD=y
 
 #
 # System Type
diff --git a/arch/arm/configs/ixdp2401_defconfig b/arch/arm/configs/ixdp2401_defconfig
index 6f51c98084a..72e1b940e97 100644
--- a/arch/arm/configs/ixdp2401_defconfig
+++ b/arch/arm/configs/ixdp2401_defconfig
@@ -50,7 +50,13 @@ CONFIG_BASE_SMALL=0
 #
 # Loadable module support
 #
-# CONFIG_MODULES is not set
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+# CONFIG_MODULE_FORCE_UNLOAD is not set
+CONFIG_OBSOLETE_MODPARM=y
+# CONFIG_MODVERSIONS is not set
+# CONFIG_MODULE_SRCVERSION_ALL is not set
+CONFIG_KMOD=y
 
 #
 # System Type
diff --git a/arch/arm/configs/ixdp2800_defconfig b/arch/arm/configs/ixdp2800_defconfig
index 7be3521f91f..1592e45f027 100644
--- a/arch/arm/configs/ixdp2800_defconfig
+++ b/arch/arm/configs/ixdp2800_defconfig
@@ -50,7 +50,13 @@ CONFIG_BASE_SMALL=0
 #
 # Loadable module support
 #
-# CONFIG_MODULES is not set
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+# CONFIG_MODULE_FORCE_UNLOAD is not set
+CONFIG_OBSOLETE_MODPARM=y
+# CONFIG_MODVERSIONS is not set
+# CONFIG_MODULE_SRCVERSION_ALL is not set
+CONFIG_KMOD=y
 
 #
 # System Type
diff --git a/arch/arm/configs/ixdp2801_defconfig b/arch/arm/configs/ixdp2801_defconfig
index cd84a20f30f..f1afe3d09ec 100644
--- a/arch/arm/configs/ixdp2801_defconfig
+++ b/arch/arm/configs/ixdp2801_defconfig
@@ -50,7 +50,13 @@ CONFIG_BASE_SMALL=0
 #
 # Loadable module support
 #
-# CONFIG_MODULES is not set
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+# CONFIG_MODULE_FORCE_UNLOAD is not set
+CONFIG_OBSOLETE_MODPARM=y
+# CONFIG_MODVERSIONS is not set
+# CONFIG_MODULE_SRCVERSION_ALL is not set
+CONFIG_KMOD=y
 
 #
 # System Type
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 4a2af55e134..3e1b0327e4d 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -6,7 +6,7 @@ AFLAGS_head.o := -DTEXTADDR=$(TEXTADDR) -DDATAADDR=$(DATAADDR)
 
 # Object file lists.
 
-obj-y		:= arch.o compat.o dma.o entry-armv.o entry-common.o irq.o   \
+obj-y		:= compat.o dma.o entry-armv.o entry-common.o irq.o \
 		   process.o ptrace.o semaphore.o setup.o signal.o sys_arm.o \
 		   time.o traps.o
 
diff --git a/arch/arm/kernel/arch.c b/arch/arm/kernel/arch.c
deleted file mode 100644
index 4e02fbeb10a..00000000000
--- a/arch/arm/kernel/arch.c
+++ /dev/null
@@ -1,46 +0,0 @@
-/*
- *  linux/arch/arm/kernel/arch.c
- *
- *  Architecture specific fixups.
- */
-#include <linux/config.h>
-#include <linux/init.h>
-#include <linux/types.h>
-
-#include <asm/elf.h>
-#include <asm/page.h>
-#include <asm/setup.h>
-#include <asm/mach/arch.h>
-
-unsigned int vram_size;
-
-#ifdef CONFIG_ARCH_ACORN
-
-unsigned int memc_ctrl_reg;
-unsigned int number_mfm_drives;
-
-static int __init parse_tag_acorn(const struct tag *tag)
-{
-	memc_ctrl_reg = tag->u.acorn.memc_control_reg;
-	number_mfm_drives = tag->u.acorn.adfsdrives;
-
-	switch (tag->u.acorn.vram_pages) {
-	case 512:
-		vram_size += PAGE_SIZE * 256;
-	case 256:
-		vram_size += PAGE_SIZE * 256;
-	default:
-		break;
-	}
-#if 0
-	if (vram_size) {
-		desc->video_start = 0x02000000;
-		desc->video_end   = 0x02000000 + vram_size;
-	}
-#endif
-	return 0;
-}
-
-__tagtable(ATAG_ACORN, parse_tag_acorn);
-
-#endif
diff --git a/arch/arm/lib/ashldi3.c b/arch/arm/lib/ashldi3.c
index 130f5a83966..b62875cfd8f 100644
--- a/arch/arm/lib/ashldi3.c
+++ b/arch/arm/lib/ashldi3.c
@@ -31,31 +31,26 @@ Boston, MA 02111-1307, USA.  */
 
 #include "gcclib.h"
 
-DItype
-__ashldi3 (DItype u, word_type b)
+s64 __ashldi3(s64 u, int b)
 {
-  DIunion w;
-  word_type bm;
-  DIunion uu;
-
-  if (b == 0)
-    return u;
-
-  uu.ll = u;
-
-  bm = (sizeof (SItype) * BITS_PER_UNIT) - b;
-  if (bm <= 0)
-    {
-      w.s.low = 0;
-      w.s.high = (USItype)uu.s.low << -bm;
-    }
-  else
-    {
-      USItype carries = (USItype)uu.s.low >> bm;
-      w.s.low = (USItype)uu.s.low << b;
-      w.s.high = ((USItype)uu.s.high << b) | carries;
-    }
-
-  return w.ll;
+	DIunion w;
+	int bm;
+	DIunion uu;
+
+	if (b == 0)
+		return u;
+
+	uu.ll = u;
+
+	bm = (sizeof(s32) * BITS_PER_UNIT) - b;
+	if (bm <= 0) {
+		w.s.low = 0;
+		w.s.high = (u32) uu.s.low << -bm;
+	} else {
+		u32 carries = (u32) uu.s.low >> bm;
+		w.s.low = (u32) uu.s.low << b;
+		w.s.high = ((u32) uu.s.high << b) | carries;
+	}
+
+	return w.ll;
 }
-
diff --git a/arch/arm/lib/ashrdi3.c b/arch/arm/lib/ashrdi3.c
index 71625d218f8..9a8600a7543 100644
--- a/arch/arm/lib/ashrdi3.c
+++ b/arch/arm/lib/ashrdi3.c
@@ -31,31 +31,27 @@ Boston, MA 02111-1307, USA.  */
 
 #include "gcclib.h"
 
-DItype
-__ashrdi3 (DItype u, word_type b)
+s64 __ashrdi3(s64 u, int b)
 {
-  DIunion w;
-  word_type bm;
-  DIunion uu;
-
-  if (b == 0)
-    return u;
-
-  uu.ll = u;
-
-  bm = (sizeof (SItype) * BITS_PER_UNIT) - b;
-  if (bm <= 0)
-    {
-      /* w.s.high = 1..1 or 0..0 */
-      w.s.high = uu.s.high >> (sizeof (SItype) * BITS_PER_UNIT - 1);
-      w.s.low = uu.s.high >> -bm;
-    }
-  else
-    {
-      USItype carries = (USItype)uu.s.high << bm;
-      w.s.high = uu.s.high >> b;
-      w.s.low = ((USItype)uu.s.low >> b) | carries;
-    }
-
-  return w.ll;
+	DIunion w;
+	int bm;
+	DIunion uu;
+
+	if (b == 0)
+		return u;
+
+	uu.ll = u;
+
+	bm = (sizeof(s32) * BITS_PER_UNIT) - b;
+	if (bm <= 0) {
+		/* w.s.high = 1..1 or 0..0 */
+		w.s.high = uu.s.high >> (sizeof(s32) * BITS_PER_UNIT - 1);
+		w.s.low = uu.s.high >> -bm;
+	} else {
+		u32 carries = (u32) uu.s.high << bm;
+		w.s.high = uu.s.high >> b;
+		w.s.low = ((u32) uu.s.low >> b) | carries;
+	}
+
+	return w.ll;
 }
diff --git a/arch/arm/lib/gcclib.h b/arch/arm/lib/gcclib.h
index 65314a3d9e2..8b6dcc656de 100644
--- a/arch/arm/lib/gcclib.h
+++ b/arch/arm/lib/gcclib.h
@@ -1,25 +1,22 @@
 /* gcclib.h -- definitions for various functions 'borrowed' from gcc-2.95.3 */
 /* I Molton     29/07/01 */
 
-#define BITS_PER_UNIT  8
-#define SI_TYPE_SIZE (sizeof (SItype) * BITS_PER_UNIT)
+#include <linux/types.h>
 
-typedef unsigned int UQItype    __attribute__ ((mode (QI)));
-typedef          int SItype     __attribute__ ((mode (SI)));
-typedef unsigned int USItype    __attribute__ ((mode (SI)));
-typedef          int DItype     __attribute__ ((mode (DI)));
-typedef          int word_type 	__attribute__ ((mode (__word__)));
-typedef unsigned int UDItype    __attribute__ ((mode (DI)));
+#define BITS_PER_UNIT	8
+#define SI_TYPE_SIZE	(sizeof(s32) * BITS_PER_UNIT)
 
 #ifdef __ARMEB__
-  struct DIstruct {SItype high, low;};
+struct DIstruct {
+	s32 high, low;
+};
 #else
-  struct DIstruct {SItype low, high;};
+struct DIstruct {
+	s32 low, high;
+};
 #endif
 
-typedef union
-{
-  struct DIstruct s;
-  DItype ll;
+typedef union {
+	struct DIstruct s;
+	s64 ll;
 } DIunion;
-
diff --git a/arch/arm/lib/longlong.h b/arch/arm/lib/longlong.h
index 179eea4edc3..90ae647e4d7 100644
--- a/arch/arm/lib/longlong.h
+++ b/arch/arm/lib/longlong.h
@@ -26,18 +26,18 @@
 
 #define __BITS4 (SI_TYPE_SIZE / 4)
 #define __ll_B (1L << (SI_TYPE_SIZE / 2))
-#define __ll_lowpart(t) ((USItype) (t) % __ll_B)
-#define __ll_highpart(t) ((USItype) (t) / __ll_B)
+#define __ll_lowpart(t) ((u32) (t) % __ll_B)
+#define __ll_highpart(t) ((u32) (t) / __ll_B)
 
 /* Define auxiliary asm macros.
 
    1) umul_ppmm(high_prod, low_prod, multipler, multiplicand)
-   multiplies two USItype integers MULTIPLER and MULTIPLICAND,
-   and generates a two-part USItype product in HIGH_PROD and
+   multiplies two u32 integers MULTIPLER and MULTIPLICAND,
+   and generates a two-part u32 product in HIGH_PROD and
    LOW_PROD.
 
-   2) __umulsidi3(a,b) multiplies two USItype integers A and B,
-   and returns a UDItype product.  This is just a variant of umul_ppmm.
+   2) __umulsidi3(a,b) multiplies two u32 integers A and B,
+   and returns a u64 product.  This is just a variant of umul_ppmm.
 
    3) udiv_qrnnd(quotient, remainder, high_numerator, low_numerator,
    denominator) divides a two-word unsigned integer, composed by the
@@ -77,23 +77,23 @@
 #define add_ssaaaa(sh, sl, ah, al, bh, bl) \
   __asm__ ("adds	%1, %4, %5					\n\
 	adc	%0, %2, %3"						\
-	   : "=r" ((USItype) (sh)),					\
-	     "=&r" ((USItype) (sl))					\
-	   : "%r" ((USItype) (ah)),					\
-	     "rI" ((USItype) (bh)),					\
-	     "%r" ((USItype) (al)),					\
-	     "rI" ((USItype) (bl)))
+	   : "=r" ((u32) (sh)),					\
+	     "=&r" ((u32) (sl))					\
+	   : "%r" ((u32) (ah)),					\
+	     "rI" ((u32) (bh)),					\
+	     "%r" ((u32) (al)),					\
+	     "rI" ((u32) (bl)))
 #define sub_ddmmss(sh, sl, ah, al, bh, bl) \
   __asm__ ("subs	%1, %4, %5					\n\
 	sbc	%0, %2, %3"						\
-	   : "=r" ((USItype) (sh)),					\
-	     "=&r" ((USItype) (sl))					\
-	   : "r" ((USItype) (ah)),					\
-	     "rI" ((USItype) (bh)),					\
-	     "r" ((USItype) (al)),					\
-	     "rI" ((USItype) (bl)))
+	   : "=r" ((u32) (sh)),					\
+	     "=&r" ((u32) (sl))					\
+	   : "r" ((u32) (ah)),					\
+	     "rI" ((u32) (bh)),					\
+	     "r" ((u32) (al)),					\
+	     "rI" ((u32) (bl)))
 #define umul_ppmm(xh, xl, a, b) \
-{register USItype __t0, __t1, __t2;					\
+{register u32 __t0, __t1, __t2;					\
   __asm__ ("%@ Inlined umul_ppmm					\n\
 	mov	%2, %5, lsr #16						\n\
 	mov	%0, %6, lsr #16						\n\
@@ -107,14 +107,14 @@
 	addcs	%0, %0, #65536						\n\
 	adds	%1, %1, %3, lsl #16					\n\
 	adc	%0, %0, %3, lsr #16"					\
-	   : "=&r" ((USItype) (xh)),					\
-	     "=r" ((USItype) (xl)),					\
+	   : "=&r" ((u32) (xh)),					\
+	     "=r" ((u32) (xl)),					\
 	     "=&r" (__t0), "=&r" (__t1), "=r" (__t2)			\
-	   : "r" ((USItype) (a)),					\
-	     "r" ((USItype) (b)));}
+	   : "r" ((u32) (a)),					\
+	     "r" ((u32) (b)));}
 #define UMUL_TIME 20
 #define UDIV_TIME 100
-#endif /* __arm__ */
+#endif				/* __arm__ */
 
 #define __umulsidi3(u, v) \
   ({DIunion __w;							\
@@ -123,14 +123,14 @@
 
 #define __udiv_qrnnd_c(q, r, n1, n0, d) \
   do {									\
-    USItype __d1, __d0, __q1, __q0;					\
-    USItype __r1, __r0, __m;						\
+    u32 __d1, __d0, __q1, __q0;					\
+    u32 __r1, __r0, __m;						\
     __d1 = __ll_highpart (d);						\
     __d0 = __ll_lowpart (d);						\
 									\
     __r1 = (n1) % __d1;							\
     __q1 = (n1) / __d1;							\
-    __m = (USItype) __q1 * __d0;					\
+    __m = (u32) __q1 * __d0;					\
     __r1 = __r1 * __ll_B | __ll_highpart (n0);				\
     if (__r1 < __m)							\
       {									\
@@ -143,7 +143,7 @@
 									\
     __r0 = __r1 % __d1;							\
     __q0 = __r1 / __d1;							\
-    __m = (USItype) __q0 * __d0;					\
+    __m = (u32) __q0 * __d0;					\
     __r0 = __r0 * __ll_B | __ll_lowpart (n0);				\
     if (__r0 < __m)							\
       {									\
@@ -154,7 +154,7 @@
       }									\
     __r0 -= __m;							\
 									\
-    (q) = (USItype) __q1 * __ll_B | __q0;				\
+    (q) = (u32) __q1 * __ll_B | __q0;				\
     (r) = __r0;								\
   } while (0)
 
@@ -163,14 +163,14 @@
 
 #define count_leading_zeros(count, x) \
   do {									\
-    USItype __xr = (x);							\
-    USItype __a;							\
+    u32 __xr = (x);							\
+    u32 __a;							\
 									\
     if (SI_TYPE_SIZE <= 32)						\
       {									\
-	__a = __xr < ((USItype)1<<2*__BITS4)				\
-	  ? (__xr < ((USItype)1<<__BITS4) ? 0 : __BITS4)		\
-	  : (__xr < ((USItype)1<<3*__BITS4) ?  2*__BITS4 : 3*__BITS4);	\
+	__a = __xr < ((u32)1<<2*__BITS4)				\
+	  ? (__xr < ((u32)1<<__BITS4) ? 0 : __BITS4)		\
+	  : (__xr < ((u32)1<<3*__BITS4) ?  2*__BITS4 : 3*__BITS4);	\
       }									\
     else								\
       {									\
diff --git a/arch/arm/lib/lshrdi3.c b/arch/arm/lib/lshrdi3.c
index b666f1bad45..3681f49d2b6 100644
--- a/arch/arm/lib/lshrdi3.c
+++ b/arch/arm/lib/lshrdi3.c
@@ -31,31 +31,26 @@ Boston, MA 02111-1307, USA.  */
 
 #include "gcclib.h"
 
-DItype
-__lshrdi3 (DItype u, word_type b)
+s64 __lshrdi3(s64 u, int b)
 {
-  DIunion w;
-  word_type bm;
-  DIunion uu;
-
-  if (b == 0)
-    return u;
-
-  uu.ll = u;
-
-  bm = (sizeof (SItype) * BITS_PER_UNIT) - b;
-  if (bm <= 0)
-    {
-      w.s.high = 0;
-      w.s.low = (USItype)uu.s.high >> -bm;
-    }
-  else
-    {
-      USItype carries = (USItype)uu.s.high << bm;
-      w.s.high = (USItype)uu.s.high >> b;
-      w.s.low = ((USItype)uu.s.low >> b) | carries;
-    }
-
-  return w.ll;
+	DIunion w;
+	int bm;
+	DIunion uu;
+
+	if (b == 0)
+		return u;
+
+	uu.ll = u;
+
+	bm = (sizeof(s32) * BITS_PER_UNIT) - b;
+	if (bm <= 0) {
+		w.s.high = 0;
+		w.s.low = (u32) uu.s.high >> -bm;
+	} else {
+		u32 carries = (u32) uu.s.high << bm;
+		w.s.high = (u32) uu.s.high >> b;
+		w.s.low = ((u32) uu.s.low >> b) | carries;
+	}
+
+	return w.ll;
 }
-
diff --git a/arch/arm/lib/muldi3.c b/arch/arm/lib/muldi3.c
index 44d611b1cfd..0a3b93313f1 100644
--- a/arch/arm/lib/muldi3.c
+++ b/arch/arm/lib/muldi3.c
@@ -32,7 +32,7 @@ Boston, MA 02111-1307, USA.  */
 #include "gcclib.h"
 
 #define umul_ppmm(xh, xl, a, b) \
-{register USItype __t0, __t1, __t2;                                     \
+{register u32 __t0, __t1, __t2;                                     \
   __asm__ ("%@ Inlined umul_ppmm					\n\
         mov     %2, %5, lsr #16						\n\
         mov     %0, %6, lsr #16						\n\
@@ -46,32 +46,27 @@ Boston, MA 02111-1307, USA.  */
         addcs   %0, %0, #65536						\n\
         adds    %1, %1, %3, lsl #16					\n\
         adc     %0, %0, %3, lsr #16"                                    \
-           : "=&r" ((USItype) (xh)),                                    \
-             "=r" ((USItype) (xl)),                                     \
+           : "=&r" ((u32) (xh)),                                    \
+             "=r" ((u32) (xl)),                                     \
              "=&r" (__t0), "=&r" (__t1), "=r" (__t2)                    \
-           : "r" ((USItype) (a)),                                       \
-             "r" ((USItype) (b)));}
-
+           : "r" ((u32) (a)),                                       \
+             "r" ((u32) (b)));}
 
 #define __umulsidi3(u, v) \
   ({DIunion __w;                                                        \
     umul_ppmm (__w.s.high, __w.s.low, u, v);                            \
     __w.ll; })
 
-
-DItype
-__muldi3 (DItype u, DItype v)
+s64 __muldi3(s64 u, s64 v)
 {
-  DIunion w;
-  DIunion uu, vv;
+	DIunion w;
+	DIunion uu, vv;
 
-  uu.ll = u,
-  vv.ll = v;
+	uu.ll = u, vv.ll = v;
 
-  w.ll = __umulsidi3 (uu.s.low, vv.s.low);
-  w.s.high += ((USItype) uu.s.low * (USItype) vv.s.high
-               + (USItype) uu.s.high * (USItype) vv.s.low);
+	w.ll = __umulsidi3(uu.s.low, vv.s.low);
+	w.s.high += ((u32) uu.s.low * (u32) vv.s.high
+		     + (u32) uu.s.high * (u32) vv.s.low);
 
-  return w.ll;
+	return w.ll;
 }
-
diff --git a/arch/arm/lib/ucmpdi2.c b/arch/arm/lib/ucmpdi2.c
index 6c6ae63efa0..57f3f2df385 100644
--- a/arch/arm/lib/ucmpdi2.c
+++ b/arch/arm/lib/ucmpdi2.c
@@ -31,21 +31,19 @@ Boston, MA 02111-1307, USA.  */
 
 #include "gcclib.h"
 
-word_type
-__ucmpdi2 (DItype a, DItype b)
+int __ucmpdi2(s64 a, s64 b)
 {
-  DIunion au, bu;
-
-  au.ll = a, bu.ll = b;
-
-  if ((USItype) au.s.high < (USItype) bu.s.high)
-    return 0;
-  else if ((USItype) au.s.high > (USItype) bu.s.high)
-    return 2;
-  if ((USItype) au.s.low < (USItype) bu.s.low)
-    return 0;
-  else if ((USItype) au.s.low > (USItype) bu.s.low)
-    return 2;
-  return 1;
+	DIunion au, bu;
+
+	au.ll = a, bu.ll = b;
+
+	if ((u32) au.s.high < (u32) bu.s.high)
+		return 0;
+	else if ((u32) au.s.high > (u32) bu.s.high)
+		return 2;
+	if ((u32) au.s.low < (u32) bu.s.low)
+		return 0;
+	else if ((u32) au.s.low > (u32) bu.s.low)
+		return 2;
+	return 1;
 }
-
diff --git a/arch/arm/lib/udivdi3.c b/arch/arm/lib/udivdi3.c
index d25195f673f..e343be4c664 100644
--- a/arch/arm/lib/udivdi3.c
+++ b/arch/arm/lib/udivdi3.c
@@ -32,211 +32,191 @@ Boston, MA 02111-1307, USA.  */
 #include "gcclib.h"
 #include "longlong.h"
 
-static const UQItype __clz_tab[] =
-{
-  0,1,2,2,3,3,3,3,4,4,4,4,4,4,4,4,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,
-  6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,
-  7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,
-  7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,
-  8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,
-  8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,
-  8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,
-  8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,
+static const u8 __clz_tab[] = {
+	0, 1, 2, 2, 3, 3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 5, 5, 5, 5,
+	    5, 5, 5, 5, 5, 5, 5, 5,
+	6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,
+	    6, 6, 6, 6, 6, 6, 6, 6,
+	7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
+	    7, 7, 7, 7, 7, 7, 7, 7,
+	7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
+	    7, 7, 7, 7, 7, 7, 7, 7,
+	8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8,
+	    8, 8, 8, 8, 8, 8, 8, 8,
+	8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8,
+	    8, 8, 8, 8, 8, 8, 8, 8,
+	8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8,
+	    8, 8, 8, 8, 8, 8, 8, 8,
+	8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8,
+	    8, 8, 8, 8, 8, 8, 8, 8,
 };
 
-UDItype
-__udivmoddi4 (UDItype n, UDItype d, UDItype *rp)
+u64 __udivmoddi4(u64 n, u64 d, u64 * rp)
 {
-  DIunion ww;
-  DIunion nn, dd;
-  DIunion rr;
-  USItype d0, d1, n0, n1, n2;
-  USItype q0, q1;
-  USItype b, bm;
-
-  nn.ll = n;
-  dd.ll = d;
-
-  d0 = dd.s.low;
-  d1 = dd.s.high;
-  n0 = nn.s.low;
-  n1 = nn.s.high;
-
-  if (d1 == 0)
-    {
-      if (d0 > n1)
-        {
-          /* 0q = nn / 0D */
-
-          count_leading_zeros (bm, d0);
-
-          if (bm != 0)
-            {
-              /* Normalize, i.e. make the most significant bit of the
-                 denominator set.  */
-
-              d0 = d0 << bm;
-              n1 = (n1 << bm) | (n0 >> (SI_TYPE_SIZE - bm));
-              n0 = n0 << bm;
-            }
-
-          udiv_qrnnd (q0, n0, n1, n0, d0);
-          q1 = 0;
-
-          /* Remainder in n0 >> bm.  */
-        }
-      else
-        {
-          /* qq = NN / 0d */
-
-          if (d0 == 0)
-            d0 = 1 / d0;        /* Divide intentionally by zero.  */
-
-          count_leading_zeros (bm, d0);
-
-          if (bm == 0)
-            {
-              /* From (n1 >= d0) /\ (the most significant bit of d0 is set),
-                 conclude (the most significant bit of n1 is set) /\ (the
-                 leading quotient digit q1 = 1).
-
-                 This special case is necessary, not an optimization.
-                 (Shifts counts of SI_TYPE_SIZE are undefined.)  */
-
-              n1 -= d0;
-              q1 = 1;
-            }
-          else
-            {
-              /* Normalize.  */
-
-              b = SI_TYPE_SIZE - bm;
-
-              d0 = d0 << bm;
-              n2 = n1 >> b;
-              n1 = (n1 << bm) | (n0 >> b);
-              n0 = n0 << bm;
-
-              udiv_qrnnd (q1, n1, n2, n1, d0);
-            }
-
-          /* n1 != d0...  */
-
-          udiv_qrnnd (q0, n0, n1, n0, d0);
-
-          /* Remainder in n0 >> bm.  */
-        }
-
-      if (rp != 0)
-        {
-          rr.s.low = n0 >> bm;
-          rr.s.high = 0;
-          *rp = rr.ll;
-        }
-    }
-  else
-    {
-      if (d1 > n1)
-        {
-          /* 00 = nn / DD */
-
-          q0 = 0;
-          q1 = 0;
-
-          /* Remainder in n1n0.  */
-          if (rp != 0)
-            {
-              rr.s.low = n0;
-              rr.s.high = n1;
-              *rp = rr.ll;
-            }
-        }
-      else
-        {
-          /* 0q = NN / dd */
-
-          count_leading_zeros (bm, d1);
-          if (bm == 0)
-            {
-              /* From (n1 >= d1) /\ (the most significant bit of d1 is set),
-                 conclude (the most significant bit of n1 is set) /\ (the
-                 quotient digit q0 = 0 or 1).
-
-                 This special case is necessary, not an optimization.  */
-
-              /* The condition on the next line takes advantage of that
-                 n1 >= d1 (true due to program flow).  */
-              if (n1 > d1 || n0 >= d0)
-                {
-                  q0 = 1;
-                  sub_ddmmss (n1, n0, n1, n0, d1, d0);
-                }
-              else
-                q0 = 0;
-
-              q1 = 0;
-
-              if (rp != 0)
-                {
-                  rr.s.low = n0;
-                  rr.s.high = n1;
-                  *rp = rr.ll;
-                }
-            }
-          else
-            {
-              USItype m1, m0;
-              /* Normalize.  */
-
-              b = SI_TYPE_SIZE - bm;
-
-              d1 = (d1 << bm) | (d0 >> b);
-              d0 = d0 << bm;
-              n2 = n1 >> b;
-              n1 = (n1 << bm) | (n0 >> b);
-              n0 = n0 << bm;
-
-              udiv_qrnnd (q0, n1, n2, n1, d1);
-              umul_ppmm (m1, m0, q0, d0);
-
-              if (m1 > n1 || (m1 == n1 && m0 > n0))
-                {
-                  q0--;
-                  sub_ddmmss (m1, m0, m1, m0, d1, d0);
-                }
-
-              q1 = 0;
-
-              /* Remainder in (n1n0 - m1m0) >> bm.  */
-              if (rp != 0)
-                {
-                  sub_ddmmss (n1, n0, n1, n0, m1, m0);
-                  rr.s.low = (n1 << b) | (n0 >> bm);
-                  rr.s.high = n1 >> bm;
-                  *rp = rr.ll;
-                }
-            }
-        }
-    }
-
-  ww.s.low = q0;
-  ww.s.high = q1;
-  return ww.ll;
+	DIunion ww;
+	DIunion nn, dd;
+	DIunion rr;
+	u32 d0, d1, n0, n1, n2;
+	u32 q0, q1;
+	u32 b, bm;
+
+	nn.ll = n;
+	dd.ll = d;
+
+	d0 = dd.s.low;
+	d1 = dd.s.high;
+	n0 = nn.s.low;
+	n1 = nn.s.high;
+
+	if (d1 == 0) {
+		if (d0 > n1) {
+			/* 0q = nn / 0D */
+
+			count_leading_zeros(bm, d0);
+
+			if (bm != 0) {
+				/* Normalize, i.e. make the most significant bit of the
+				   denominator set.  */
+
+				d0 = d0 << bm;
+				n1 = (n1 << bm) | (n0 >> (SI_TYPE_SIZE - bm));
+				n0 = n0 << bm;
+			}
+
+			udiv_qrnnd(q0, n0, n1, n0, d0);
+			q1 = 0;
+
+			/* Remainder in n0 >> bm.  */
+		} else {
+			/* qq = NN / 0d */
+
+			if (d0 == 0)
+				d0 = 1 / d0;	/* Divide intentionally by zero.  */
+
+			count_leading_zeros(bm, d0);
+
+			if (bm == 0) {
+				/* From (n1 >= d0) /\ (the most significant bit of d0 is set),
+				   conclude (the most significant bit of n1 is set) /\ (the
+				   leading quotient digit q1 = 1).
+
+				   This special case is necessary, not an optimization.
+				   (Shifts counts of SI_TYPE_SIZE are undefined.)  */
+
+				n1 -= d0;
+				q1 = 1;
+			} else {
+				/* Normalize.  */
+
+				b = SI_TYPE_SIZE - bm;
+
+				d0 = d0 << bm;
+				n2 = n1 >> b;
+				n1 = (n1 << bm) | (n0 >> b);
+				n0 = n0 << bm;
+
+				udiv_qrnnd(q1, n1, n2, n1, d0);
+			}
+
+			/* n1 != d0...  */
+
+			udiv_qrnnd(q0, n0, n1, n0, d0);
+
+			/* Remainder in n0 >> bm.  */
+		}
+
+		if (rp != 0) {
+			rr.s.low = n0 >> bm;
+			rr.s.high = 0;
+			*rp = rr.ll;
+		}
+	} else {
+		if (d1 > n1) {
+			/* 00 = nn / DD */
+
+			q0 = 0;
+			q1 = 0;
+
+			/* Remainder in n1n0.  */
+			if (rp != 0) {
+				rr.s.low = n0;
+				rr.s.high = n1;
+				*rp = rr.ll;
+			}
+		} else {
+			/* 0q = NN / dd */
+
+			count_leading_zeros(bm, d1);
+			if (bm == 0) {
+				/* From (n1 >= d1) /\ (the most significant bit of d1 is set),
+				   conclude (the most significant bit of n1 is set) /\ (the
+				   quotient digit q0 = 0 or 1).
+
+				   This special case is necessary, not an optimization.  */
+
+				/* The condition on the next line takes advantage of that
+				   n1 >= d1 (true due to program flow).  */
+				if (n1 > d1 || n0 >= d0) {
+					q0 = 1;
+					sub_ddmmss(n1, n0, n1, n0, d1, d0);
+				} else
+					q0 = 0;
+
+				q1 = 0;
+
+				if (rp != 0) {
+					rr.s.low = n0;
+					rr.s.high = n1;
+					*rp = rr.ll;
+				}
+			} else {
+				u32 m1, m0;
+				/* Normalize.  */
+
+				b = SI_TYPE_SIZE - bm;
+
+				d1 = (d1 << bm) | (d0 >> b);
+				d0 = d0 << bm;
+				n2 = n1 >> b;
+				n1 = (n1 << bm) | (n0 >> b);
+				n0 = n0 << bm;
+
+				udiv_qrnnd(q0, n1, n2, n1, d1);
+				umul_ppmm(m1, m0, q0, d0);
+
+				if (m1 > n1 || (m1 == n1 && m0 > n0)) {
+					q0--;
+					sub_ddmmss(m1, m0, m1, m0, d1, d0);
+				}
+
+				q1 = 0;
+
+				/* Remainder in (n1n0 - m1m0) >> bm.  */
+				if (rp != 0) {
+					sub_ddmmss(n1, n0, n1, n0, m1, m0);
+					rr.s.low = (n1 << b) | (n0 >> bm);
+					rr.s.high = n1 >> bm;
+					*rp = rr.ll;
+				}
+			}
+		}
+	}
+
+	ww.s.low = q0;
+	ww.s.high = q1;
+	return ww.ll;
 }
 
-UDItype
-__udivdi3 (UDItype n, UDItype d)
+u64 __udivdi3(u64 n, u64 d)
 {
-  return __udivmoddi4 (n, d, (UDItype *) 0);
+	return __udivmoddi4(n, d, (u64 *) 0);
 }
 
-UDItype
-__umoddi3 (UDItype u, UDItype v)
+u64 __umoddi3(u64 u, u64 v)
 {
-  UDItype w;
+	u64 w;
 
-  (void) __udivmoddi4 (u ,v, &w);
+	(void)__udivmoddi4(u, v, &w);
 
-  return w;
+	return w;
 }
-
diff --git a/arch/arm/mach-aaec2000/Kconfig b/arch/arm/mach-aaec2000/Kconfig
new file mode 100644
index 00000000000..5e4bef93754
--- /dev/null
+++ b/arch/arm/mach-aaec2000/Kconfig
@@ -0,0 +1,11 @@
+if ARCH_AAEC2000
+
+menu "Agilent AAEC-2000 Implementations"
+
+config MACH_AAED2000
+	bool "Agilent AAED-2000 Development Platform"
+	select CPU_ARM920T
+
+endmenu
+
+endif
diff --git a/arch/arm/mach-aaec2000/Makefile b/arch/arm/mach-aaec2000/Makefile
new file mode 100644
index 00000000000..20ec83896c3
--- /dev/null
+++ b/arch/arm/mach-aaec2000/Makefile
@@ -0,0 +1,9 @@
+#
+# Makefile for the linux kernel.
+#
+
+# Common support (must be linked before board specific support)
+obj-y += core.o
+
+# Specific board support
+obj-$(CONFIG_MACH_AAED2000) += aaed2000.o
diff --git a/arch/arm/mach-aaec2000/aaed2000.c b/arch/arm/mach-aaec2000/aaed2000.c
new file mode 100644
index 00000000000..5417ca3f462
--- /dev/null
+++ b/arch/arm/mach-aaec2000/aaed2000.c
@@ -0,0 +1,48 @@
+/*
+ *  linux/arch/arm/mach-aaec2000/aaed2000.c
+ *
+ *  Support for the Agilent AAED-2000 Development Platform.
+ *
+ *  Copyright (c) 2005 Nicolas Bellido Y Ortega
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ *
+ */
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/major.h>
+#include <linux/interrupt.h>
+
+#include <asm/setup.h>
+#include <asm/memory.h>
+#include <asm/mach-types.h>
+#include <asm/hardware.h>
+#include <asm/irq.h>
+
+#include <asm/mach/arch.h>
+#include <asm/mach/map.h>
+#include <asm/mach/irq.h>
+
+#include "core.h"
+
+static void __init aaed2000_init_irq(void)
+{
+	aaec2000_init_irq();
+}
+
+static void __init aaed2000_map_io(void)
+{
+	aaec2000_map_io();
+}
+
+MACHINE_START(AAED2000, "Agilent AAED-2000 Development Platform")
+	MAINTAINER("Nicolas Bellido Y Ortega")
+	BOOT_MEM(0xf0000000, PIO_BASE, VIO_BASE)
+	MAPIO(aaed2000_map_io)
+	INITIRQ(aaed2000_init_irq)
+	.timer		= &aaec2000_timer,
+MACHINE_END
diff --git a/arch/arm/mach-aaec2000/core.c b/arch/arm/mach-aaec2000/core.c
new file mode 100644
index 00000000000..fc145b3768f
--- /dev/null
+++ b/arch/arm/mach-aaec2000/core.c
@@ -0,0 +1,157 @@
+/*
+ *  linux/arch/arm/mach-aaec2000/core.c
+ *
+ *  Code common to all AAEC-2000 machines
+ *
+ *  Copyright (c) 2005 Nicolas Bellido Y Ortega
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ */
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/timex.h>
+#include <linux/signal.h>
+
+#include <asm/hardware.h>
+#include <asm/irq.h>
+
+#include <asm/mach/irq.h>
+#include <asm/mach/time.h>
+#include <asm/mach/map.h>
+
+/*
+ * Common I/O mapping:
+ *
+ * Static virtual address mappings are as follow:
+ *
+ * 0xf8000000-0xf8001ffff: Devices connected to APB bus
+ * 0xf8002000-0xf8003ffff: Devices connected to AHB bus
+ *
+ * Below 0xe8000000 is reserved for vm allocation.
+ *
+ * The machine specific code must provide the extra mapping beside the
+ * default mapping provided here.
+ */
+static struct map_desc standard_io_desc[] __initdata = {
+ /* virtual         physical       length           type */
+  { VIO_APB_BASE,   PIO_APB_BASE,  IO_APB_LENGTH,   MT_DEVICE },
+  { VIO_AHB_BASE,   PIO_AHB_BASE,  IO_AHB_LENGTH,   MT_DEVICE }
+};
+
+void __init aaec2000_map_io(void)
+{
+	iotable_init(standard_io_desc, ARRAY_SIZE(standard_io_desc));
+}
+
+/*
+ * Interrupt handling routines
+ */
+static void aaec2000_int_ack(unsigned int irq)
+{
+	IRQ_INTSR = 1 << irq;
+}
+
+static void aaec2000_int_mask(unsigned int irq)
+{
+	IRQ_INTENC |= (1 << irq);
+}
+
+static void aaec2000_int_unmask(unsigned int irq)
+{
+	IRQ_INTENS |= (1 << irq);
+}
+
+static struct irqchip aaec2000_irq_chip = {
+	.ack	= aaec2000_int_ack,
+	.mask	= aaec2000_int_mask,
+	.unmask	= aaec2000_int_unmask,
+};
+
+void __init aaec2000_init_irq(void)
+{
+	unsigned int i;
+
+	for (i = 0; i < NR_IRQS; i++) {
+		set_irq_handler(i, do_level_IRQ);
+		set_irq_chip(i, &aaec2000_irq_chip);
+		set_irq_flags(i, IRQF_VALID);
+	}
+
+	/* Disable all interrupts */
+	IRQ_INTENC = 0xffffffff;
+
+	/* Clear any pending interrupts */
+	IRQ_INTSR = IRQ_INTSR;
+}
+
+/*
+ * Time keeping
+ */
+/* IRQs are disabled before entering here from do_gettimeofday() */
+static unsigned long aaec2000_gettimeoffset(void)
+{
+	unsigned long ticks_to_match, elapsed, usec;
+
+	/* Get ticks before next timer match */
+	ticks_to_match = TIMER1_LOAD - TIMER1_VAL;
+
+	/* We need elapsed ticks since last match */
+	elapsed = LATCH - ticks_to_match;
+
+	/* Now, convert them to usec */
+	usec = (unsigned long)(elapsed * (tick_nsec / 1000))/LATCH;
+
+	return usec;
+}
+
+/* We enter here with IRQs enabled */
+static irqreturn_t
+aaec2000_timer_interrupt(int irq, void *dev_id, struct pt_regs *regs)
+{
+	/* TODO: Check timer accuracy */
+	write_seqlock(&xtime_lock);
+
+	timer_tick(regs);
+	TIMER1_CLEAR = 1;
+
+	write_sequnlock(&xtime_lock);
+
+	return IRQ_HANDLED;
+}
+
+static struct irqaction aaec2000_timer_irq = {
+	.name		= "AAEC-2000 Timer Tick",
+	.flags		= SA_INTERRUPT,
+	.handler	= aaec2000_timer_interrupt
+};
+
+static void __init aaec2000_timer_init(void)
+{
+	/* Disable timer 1 */
+	TIMER1_CTRL = 0;
+
+	/* We have somehow to generate a 100Hz clock.
+	 * We then use the 508KHz timer in periodic mode.
+	 */
+	TIMER1_LOAD = LATCH;
+	TIMER1_CLEAR = 1; /* Clear interrupt */
+
+	setup_irq(INT_TMR1_OFL, &aaec2000_timer_irq);
+
+	TIMER1_CTRL = TIMER_CTRL_ENABLE |
+	                TIMER_CTRL_PERIODIC |
+	                TIMER_CTRL_CLKSEL_508K;
+}
+
+struct sys_timer aaec2000_timer = {
+	.init		= aaec2000_timer_init,
+	.offset		= aaec2000_gettimeoffset,
+};
+
diff --git a/arch/arm/mach-aaec2000/core.h b/arch/arm/mach-aaec2000/core.h
new file mode 100644
index 00000000000..91893d848c1
--- /dev/null
+++ b/arch/arm/mach-aaec2000/core.h
@@ -0,0 +1,16 @@
+/*
+ *  linux/arch/arm/mach-aaec2000/core.h
+ *
+ *  Copyright (c) 2005 Nicolas Bellido Y Ortega
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ *
+ */
+
+struct sys_timer;
+
+extern struct sys_timer aaec2000_timer;
+extern void __init aaec2000_map_io(void);
+extern void __init aaec2000_init_irq(void);
diff --git a/arch/arm/mach-integrator/core.c b/arch/arm/mach-integrator/core.c
index d302f0405fd..bd1e5e3c9d3 100644
--- a/arch/arm/mach-integrator/core.c
+++ b/arch/arm/mach-integrator/core.c
@@ -227,7 +227,6 @@ integrator_timer_interrupt(int irq, void *dev_id, struct pt_regs *regs)
 	 * primary CPU
 	 */
 	if (hard_smp_processor_id() == 0) {
-		nmi_tick();
 		timer_tick(regs);
 #ifdef CONFIG_SMP
 		smp_send_timer();
diff --git a/arch/arm/mach-ixp2000/core.c b/arch/arm/mach-ixp2000/core.c
index 4f3c3d5c781..fc0555596d6 100644
--- a/arch/arm/mach-ixp2000/core.c
+++ b/arch/arm/mach-ixp2000/core.c
@@ -162,12 +162,13 @@ void __init ixp2000_map_io(void)
 static unsigned ticks_per_jiffy;
 static unsigned ticks_per_usec;
 static unsigned next_jiffy_time;
+static volatile unsigned long *missing_jiffy_timer_csr;
 
 unsigned long ixp2000_gettimeoffset (void)
 {
  	unsigned long offset;
 
-	offset = next_jiffy_time - *IXP2000_T4_CSR;
+	offset = next_jiffy_time - *missing_jiffy_timer_csr;
 
 	return offset / ticks_per_usec;
 }
@@ -179,7 +180,7 @@ static int ixp2000_timer_interrupt(int irq, void *dev_id, struct pt_regs *regs)
 	/* clear timer 1 */
 	ixp2000_reg_write(IXP2000_T1_CLR, 1);
 	
-	while ((next_jiffy_time - *IXP2000_T4_CSR) > ticks_per_jiffy) {
+	while ((next_jiffy_time - *missing_jiffy_timer_csr) > ticks_per_jiffy) {
 		timer_tick(regs);
 		next_jiffy_time -= ticks_per_jiffy;
 	}
@@ -197,20 +198,37 @@ static struct irqaction ixp2000_timer_irq = {
 
 void __init ixp2000_init_time(unsigned long tick_rate)
 {
-	ixp2000_reg_write(IXP2000_T1_CLR, 0);
-	ixp2000_reg_write(IXP2000_T4_CLR, 0);
-
 	ticks_per_jiffy = (tick_rate + HZ/2) / HZ;
 	ticks_per_usec = tick_rate / 1000000;
 
+	/*
+	 * We use timer 1 as our timer interrupt.
+	 */
+	ixp2000_reg_write(IXP2000_T1_CLR, 0);
 	ixp2000_reg_write(IXP2000_T1_CLD, ticks_per_jiffy - 1);
 	ixp2000_reg_write(IXP2000_T1_CTL, (1 << 7));
 
 	/*
-	 * We use T4 as a monotonic counter to track missed jiffies
+	 * We use a second timer as a monotonic counter for tracking
+	 * missed jiffies.  The IXP2000 has four timers, but if we're
+	 * on an A-step IXP2800, timer 2 and 3 don't work, so on those
+	 * chips we use timer 4.  Timer 4 is the only timer that can
+	 * be used for the watchdog, so we use timer 2 if we're on a
+	 * non-buggy chip.
 	 */
-	ixp2000_reg_write(IXP2000_T4_CLD, -1);
-	ixp2000_reg_write(IXP2000_T4_CTL, (1 << 7));
+	if ((*IXP2000_PRODUCT_ID & 0x001ffef0) == 0x00000000) {
+		printk(KERN_INFO "Enabling IXP2800 erratum #25 workaround\n");
+
+		ixp2000_reg_write(IXP2000_T4_CLR, 0);
+		ixp2000_reg_write(IXP2000_T4_CLD, -1);
+		ixp2000_reg_write(IXP2000_T4_CTL, (1 << 7));
+		missing_jiffy_timer_csr = IXP2000_T4_CSR;
+	} else {
+		ixp2000_reg_write(IXP2000_T2_CLR, 0);
+		ixp2000_reg_write(IXP2000_T2_CLD, -1);
+		ixp2000_reg_write(IXP2000_T2_CTL, (1 << 7));
+		missing_jiffy_timer_csr = IXP2000_T2_CSR;
+	}
  	next_jiffy_time = 0xffffffff;
 
 	/* register for interrupt */
diff --git a/arch/arm/mach-versatile/Makefile b/arch/arm/mach-versatile/Makefile
index 5d608837757..ba81e70ed81 100644
--- a/arch/arm/mach-versatile/Makefile
+++ b/arch/arm/mach-versatile/Makefile
@@ -5,3 +5,4 @@
 obj-y					:= core.o clock.o
 obj-$(CONFIG_ARCH_VERSATILE_PB)		+= versatile_pb.o
 obj-$(CONFIG_MACH_VERSATILE_AB)		+= versatile_ab.o
+obj-$(CONFIG_PCI)			+= pci.o
diff --git a/arch/arm/mach-versatile/core.c b/arch/arm/mach-versatile/core.c
index 302c2a7b9b6..6a7cbea5e09 100644
--- a/arch/arm/mach-versatile/core.c
+++ b/arch/arm/mach-versatile/core.c
@@ -196,11 +196,15 @@ static struct map_desc versatile_io_desc[] __initdata = {
 #ifdef CONFIG_DEBUG_LL
  { IO_ADDRESS(VERSATILE_UART0_BASE), VERSATILE_UART0_BASE, SZ_4K,      MT_DEVICE },
 #endif
-#ifdef FIXME
- { PCI_MEMORY_VADDR,		     PHYS_PCI_MEM_BASE,    SZ_16M,     MT_DEVICE },
- { PCI_CONFIG_VADDR,		     PHYS_PCI_CONFIG_BASE, SZ_16M,     MT_DEVICE },
- { PCI_V3_VADDR,		     PHYS_PCI_V3_BASE,     SZ_512K,    MT_DEVICE },
- { PCI_IO_VADDR,		     PHYS_PCI_IO_BASE,     SZ_64K,     MT_DEVICE },
+#ifdef CONFIG_PCI
+ { IO_ADDRESS(VERSATILE_PCI_CORE_BASE), VERSATILE_PCI_CORE_BASE, SZ_4K, MT_DEVICE },
+ { VERSATILE_PCI_VIRT_BASE,          VERSATILE_PCI_BASE,   VERSATILE_PCI_BASE_SIZE, MT_DEVICE },
+ { VERSATILE_PCI_CFG_VIRT_BASE,      VERSATILE_PCI_CFG_BASE, VERSATILE_PCI_CFG_BASE_SIZE, MT_DEVICE },
+#if 0
+ { VERSATILE_PCI_VIRT_MEM_BASE0,     VERSATILE_PCI_MEM_BASE0, SZ_16M,  MT_DEVICE },
+ { VERSATILE_PCI_VIRT_MEM_BASE1,     VERSATILE_PCI_MEM_BASE1, SZ_16M,  MT_DEVICE },
+ { VERSATILE_PCI_VIRT_MEM_BASE2,     VERSATILE_PCI_MEM_BASE2, SZ_16M,  MT_DEVICE },
+#endif
 #endif
 };
 
diff --git a/arch/arm/mach-versatile/pci.c b/arch/arm/mach-versatile/pci.c
new file mode 100644
index 00000000000..d1565e851f0
--- /dev/null
+++ b/arch/arm/mach-versatile/pci.c
@@ -0,0 +1,360 @@
+/*
+ *  linux/arch/arm/mach-versatile/pci.c
+ *
+ * (C) Copyright Koninklijke Philips Electronics NV 2004. All rights reserved.
+ * You can redistribute and/or modify this software under the terms of version 2
+ * of the GNU General Public License as published by the Free Software Foundation.
+ * THIS SOFTWARE IS PROVIDED "AS IS" WITHOUT ANY WARRANTY; WITHOUT EVEN THE IMPLIED
+ * WARRANTY OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ * Koninklijke Philips Electronics nor its subsidiaries is obligated to provide any support for this software.
+ *
+ * ARM Versatile PCI driver.
+ *
+ * 14/04/2005 Initial version, colin.king@philips.com
+ *
+ */
+#include <linux/config.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/ptrace.h>
+#include <linux/slab.h>
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
+#include <linux/init.h>
+
+#include <asm/hardware.h>
+#include <asm/io.h>
+#include <asm/irq.h>
+#include <asm/system.h>
+#include <asm/mach/pci.h>
+#include <asm/mach-types.h>
+
+/*
+ * these spaces are mapped using the following base registers:
+ *
+ * Usage Local Bus Memory         Base/Map registers used
+ *
+ * Mem   50000000 - 5FFFFFFF      LB_BASE0/LB_MAP0,  non prefetch
+ * Mem   60000000 - 6FFFFFFF      LB_BASE1/LB_MAP1,  prefetch
+ * IO    44000000 - 4FFFFFFF      LB_BASE2/LB_MAP2,  IO
+ * Cfg   42000000 - 42FFFFFF	  PCI config
+ *
+ */
+#define SYS_PCICTL			IO_ADDRESS(VERSATILE_SYS_PCICTL)
+#define PCI_IMAP0			IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x0)
+#define PCI_IMAP1			IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x4)
+#define PCI_IMAP2			IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x8)
+#define PCI_SMAP0			IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x10)
+#define PCI_SMAP1			IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x14)
+#define PCI_SMAP2			IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x18)
+#define PCI_SELFID			IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0xc)
+
+#define DEVICE_ID_OFFSET		0x00
+#define CSR_OFFSET			0x04
+#define CLASS_ID_OFFSET			0x08
+
+#define VP_PCI_DEVICE_ID		0x030010ee
+#define VP_PCI_CLASS_ID			0x0b400000
+
+static unsigned long pci_slot_ignore = 0;
+
+static int __init versatile_pci_slot_ignore(char *str)
+{
+	int retval;
+	int slot;
+
+	while ((retval = get_option(&str,&slot))) {
+		if ((slot < 0) || (slot > 31)) {
+			printk("Illegal slot value: %d\n",slot);
+		} else {
+			pci_slot_ignore |= (1 << slot);
+		}
+	}
+	return 1;
+}
+
+__setup("pci_slot_ignore=", versatile_pci_slot_ignore);
+
+
+static unsigned long __pci_addr(struct pci_bus *bus,
+				unsigned int devfn, int offset)
+{
+	unsigned int busnr = bus->number;
+
+	/*
+	 * Trap out illegal values
+	 */
+	if (offset > 255)
+		BUG();
+	if (busnr > 255)
+		BUG();
+	if (devfn > 255)
+		BUG();
+
+	return (VERSATILE_PCI_CFG_VIRT_BASE | (busnr << 16) |
+		(PCI_SLOT(devfn) << 11) | (PCI_FUNC(devfn) << 8) | offset);
+}
+
+static int versatile_read_config(struct pci_bus *bus, unsigned int devfn, int where,
+				 int size, u32 *val)
+{
+	unsigned long addr = __pci_addr(bus, devfn, where);
+	u32 v;
+	int slot = PCI_SLOT(devfn);
+
+	if (pci_slot_ignore & (1 << slot)) {
+		/* Ignore this slot */
+		switch (size) {
+		case 1:
+			v = 0xff;
+			break;
+		case 2:
+			v = 0xffff;
+			break;
+		default:
+			v = 0xffffffff;
+		}
+	} else {
+		switch (size) {
+		case 1:
+			addr &= ~3;
+			v = __raw_readb(addr);
+			break;
+
+		case 2:
+			v = __raw_readl(addr & ~3);
+			if (addr & 2) v >>= 16;
+ 			v &= 0xffff;
+			break;
+
+		default:
+			addr &= ~3;
+			v = __raw_readl(addr);
+			break;
+		}
+	}
+
+	*val = v;
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static int versatile_write_config(struct pci_bus *bus, unsigned int devfn, int where,
+				  int size, u32 val)
+{
+	unsigned long addr = __pci_addr(bus, devfn, where);
+	int slot = PCI_SLOT(devfn);
+
+	if (pci_slot_ignore & (1 << slot)) {
+		return PCIBIOS_SUCCESSFUL;
+	}
+
+	switch (size) {
+	case 1:
+		__raw_writeb((u8)val, addr);
+		break;
+
+	case 2:
+		__raw_writew((u16)val, addr);
+		break;
+
+	case 4:
+		__raw_writel(val, addr);
+		break;
+	}
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static struct pci_ops pci_versatile_ops = {
+	.read	= versatile_read_config,
+	.write	= versatile_write_config,
+};
+
+static struct resource io_mem = {
+	.name	= "PCI I/O space",
+	.start	= VERSATILE_PCI_MEM_BASE0,
+	.end	= VERSATILE_PCI_MEM_BASE0+VERSATILE_PCI_MEM_BASE0_SIZE-1,
+	.flags	= IORESOURCE_IO,
+};
+
+static struct resource non_mem = {
+	.name	= "PCI non-prefetchable",
+	.start	= VERSATILE_PCI_MEM_BASE1,
+	.end	= VERSATILE_PCI_MEM_BASE1+VERSATILE_PCI_MEM_BASE1_SIZE-1,
+	.flags	= IORESOURCE_MEM,
+};
+
+static struct resource pre_mem = {
+	.name	= "PCI prefetchable",
+	.start	= VERSATILE_PCI_MEM_BASE2,
+	.end	= VERSATILE_PCI_MEM_BASE2+VERSATILE_PCI_MEM_BASE2_SIZE-1,
+	.flags	= IORESOURCE_MEM | IORESOURCE_PREFETCH,
+};
+
+static int __init pci_versatile_setup_resources(struct resource **resource)
+{
+	int ret = 0;
+
+	ret = request_resource(&iomem_resource, &io_mem);
+	if (ret) {
+		printk(KERN_ERR "PCI: unable to allocate I/O "
+		       "memory region (%d)\n", ret);
+		goto out;
+	}
+	ret = request_resource(&iomem_resource, &non_mem);
+	if (ret) {
+		printk(KERN_ERR "PCI: unable to allocate non-prefetchable "
+		       "memory region (%d)\n", ret);
+		goto release_io_mem;
+	}
+	ret = request_resource(&iomem_resource, &pre_mem);
+	if (ret) {
+		printk(KERN_ERR "PCI: unable to allocate prefetchable "
+		       "memory region (%d)\n", ret);
+		goto release_non_mem;
+	}
+
+	/*
+	 * bus->resource[0] is the IO resource for this bus
+	 * bus->resource[1] is the mem resource for this bus
+	 * bus->resource[2] is the prefetch mem resource for this bus
+	 */
+	resource[0] = &io_mem;
+	resource[1] = &non_mem;
+	resource[2] = &pre_mem;
+
+	goto out;
+
+ release_non_mem:
+	release_resource(&non_mem);
+ release_io_mem:
+	release_resource(&io_mem);
+ out:
+	return ret;
+}
+
+int __init pci_versatile_setup(int nr, struct pci_sys_data *sys)
+{
+	int ret = 0;
+        int i;
+        int myslot = -1;
+	unsigned long val;
+
+	if (nr == 0) {
+		sys->mem_offset = 0;
+		ret = pci_versatile_setup_resources(sys->resource);
+		if (ret < 0) {
+			printk("pci_versatile_setup: resources... oops?\n");
+			goto out;
+		}
+	} else {
+		printk("pci_versatile_setup: resources... nr == 0??\n");
+		goto out;
+	}
+
+	__raw_writel(VERSATILE_PCI_MEM_BASE0 >> 28,PCI_IMAP0);
+	__raw_writel(VERSATILE_PCI_MEM_BASE1 >> 28,PCI_IMAP1);
+	__raw_writel(VERSATILE_PCI_MEM_BASE2 >> 28,PCI_IMAP2);
+
+	__raw_writel(1, SYS_PCICTL);
+
+	val = __raw_readl(SYS_PCICTL);
+	if (!(val & 1)) {
+		printk("Not plugged into PCI backplane!\n");
+		ret = -EIO;
+		goto out;
+	}
+
+	/*
+	 *  We need to discover the PCI core first to configure itself
+	 *  before the main PCI probing is performed
+	 */
+	for (i=0; i<32; i++) {
+		if ((__raw_readl(VERSATILE_PCI_VIRT_BASE+(i<<11)+DEVICE_ID_OFFSET) == VP_PCI_DEVICE_ID) &&
+		    (__raw_readl(VERSATILE_PCI_VIRT_BASE+(i<<11)+CLASS_ID_OFFSET) == VP_PCI_CLASS_ID)) {
+			myslot = i;
+
+			__raw_writel(myslot, PCI_SELFID);
+			val = __raw_readl(VERSATILE_PCI_CFG_VIRT_BASE+(myslot<<11)+CSR_OFFSET);
+			val |= (1<<2);
+			__raw_writel(val, VERSATILE_PCI_CFG_VIRT_BASE+(myslot<<11)+CSR_OFFSET);
+			break;
+		}
+	}
+
+	if (myslot == -1) {
+		printk("Cannot find PCI core!\n");
+		ret = -EIO;
+	} else {
+		printk("PCI core found (slot %d)\n",myslot);
+		/* Do not to map Versatile FPGA PCI device
+		   into memory space as we are short of
+		   mappable memory */
+		pci_slot_ignore |= (1 << myslot);
+		ret = 1;
+	}
+
+ out:
+	return ret;
+}
+
+
+struct pci_bus *pci_versatile_scan_bus(int nr, struct pci_sys_data *sys)
+{
+	return pci_scan_bus(sys->busnr, &pci_versatile_ops, sys);
+}
+
+/*
+ * V3_LB_BASE? - local bus address
+ * V3_LB_MAP?  - pci bus address
+ */
+void __init pci_versatile_preinit(void)
+{
+}
+
+void __init pci_versatile_postinit(void)
+{
+}
+
+
+/*
+ * map the specified device/slot/pin to an IRQ.   Different backplanes may need to modify this.
+ */
+static int __init versatile_map_irq(struct pci_dev *dev, u8 slot, u8 pin)
+{
+	int irq;
+	int devslot = PCI_SLOT(dev->devfn);
+
+	/* slot,  pin,  irq
+	    24	  1	27
+	    25    1	28	untested
+	    26	  1	29
+	    27    1	30	untested
+	*/
+
+	irq = 27 + ((slot + pin + 2) % 3);	/* Fudged */
+
+	printk("map irq: slot %d, pin %d, devslot %d, irq: %d\n",slot,pin,devslot,irq);
+
+	return irq;
+}
+
+static struct hw_pci versatile_pci __initdata = {
+	.swizzle		= NULL,
+	.map_irq		= versatile_map_irq,
+	.nr_controllers		= 1,
+	.setup			= pci_versatile_setup,
+	.scan			= pci_versatile_scan_bus,
+	.preinit		= pci_versatile_preinit,
+	.postinit		= pci_versatile_postinit,
+};
+
+static int __init versatile_pci_init(void)
+{
+	pci_common_init(&versatile_pci);
+	return 0;
+}
+
+subsys_initcall(versatile_pci_init);
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 3fefb43c67f..95606b4a3ba 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -62,7 +62,7 @@ config CPU_ARM720T
 # ARM920T
 config CPU_ARM920T
 	bool "Support ARM920T processor" if !ARCH_S3C2410
-	depends on ARCH_INTEGRATOR || ARCH_S3C2410 || ARCH_IMX
+	depends on ARCH_INTEGRATOR || ARCH_S3C2410 || ARCH_IMX || ARCH_AAEC2000
 	default y if ARCH_S3C2410
 	select CPU_32v4
 	select CPU_ABRT_EV4T
diff --git a/arch/arm/mm/copypage-v6.c b/arch/arm/mm/copypage-v6.c
index a8c00236bd3..27d041574ea 100644
--- a/arch/arm/mm/copypage-v6.c
+++ b/arch/arm/mm/copypage-v6.c
@@ -30,8 +30,6 @@
 
 static DEFINE_SPINLOCK(v6_lock);
 
-#define DCACHE_COLOUR(vaddr) ((vaddr & (SHMLBA - 1)) >> PAGE_SHIFT)
-
 /*
  * Copy the user page.  No aliasing to deal with so we can just
  * attack the kernel's existing mapping of these pages.
@@ -55,7 +53,7 @@ void v6_clear_user_page_nonaliasing(void *kaddr, unsigned long vaddr)
  */
 void v6_copy_user_page_aliasing(void *kto, const void *kfrom, unsigned long vaddr)
 {
-	unsigned int offset = DCACHE_COLOUR(vaddr);
+	unsigned int offset = CACHE_COLOUR(vaddr);
 	unsigned long from, to;
 
 	/*
@@ -95,7 +93,7 @@ void v6_copy_user_page_aliasing(void *kto, const void *kfrom, unsigned long vadd
  */
 void v6_clear_user_page_aliasing(void *kaddr, unsigned long vaddr)
 {
-	unsigned int offset = DCACHE_COLOUR(vaddr);
+	unsigned int offset = CACHE_COLOUR(vaddr);
 	unsigned long to = to_address + (offset << PAGE_SHIFT);
 
 	/*
diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c
index 01967ddeef5..be4ab3d73c9 100644
--- a/arch/arm/mm/fault-armv.c
+++ b/arch/arm/mm/fault-armv.c
@@ -77,9 +77,8 @@ no_pmd:
 }
 
 static void
-make_coherent(struct vm_area_struct *vma, unsigned long addr, struct page *page, int dirty)
+make_coherent(struct address_space *mapping, struct vm_area_struct *vma, unsigned long addr, unsigned long pfn)
 {
-	struct address_space *mapping = page_mapping(page);
 	struct mm_struct *mm = vma->vm_mm;
 	struct vm_area_struct *mpnt;
 	struct prio_tree_iter iter;
@@ -87,9 +86,6 @@ make_coherent(struct vm_area_struct *vma, unsigned long addr, struct page *page,
 	pgoff_t pgoff;
 	int aliases = 0;
 
-	if (!mapping)
-		return;
-
 	pgoff = vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT);
 
 	/*
@@ -115,9 +111,11 @@ make_coherent(struct vm_area_struct *vma, unsigned long addr, struct page *page,
 	if (aliases)
 		adjust_pte(vma, addr);
 	else
-		flush_cache_page(vma, addr, page_to_pfn(page));
+		flush_cache_page(vma, addr, pfn);
 }
 
+void __flush_dcache_page(struct address_space *mapping, struct page *page);
+
 /*
  * Take care of architecture specific things when placing a new PTE into
  * a page table, or changing an existing PTE.  Basically, there are two
@@ -134,29 +132,22 @@ make_coherent(struct vm_area_struct *vma, unsigned long addr, struct page *page,
 void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr, pte_t pte)
 {
 	unsigned long pfn = pte_pfn(pte);
+	struct address_space *mapping;
 	struct page *page;
 
 	if (!pfn_valid(pfn))
 		return;
+
 	page = pfn_to_page(pfn);
-	if (page_mapping(page)) {
+	mapping = page_mapping(page);
+	if (mapping) {
 		int dirty = test_and_clear_bit(PG_dcache_dirty, &page->flags);
 
-		if (dirty) {
-			/*
-			 * This is our first userspace mapping of this page.
-			 * Ensure that the physical page is coherent with
-			 * the kernel mapping.
-			 *
-			 * FIXME: only need to do this on VIVT and aliasing
-			 *        VIPT cache architectures.  We can do that
-			 *	  by choosing whether to set this bit...
-			 */
-			__cpuc_flush_dcache_page(page_address(page));
-		}
+		if (dirty)
+			__flush_dcache_page(mapping, page);
 
 		if (cache_is_vivt())
-			make_coherent(vma, addr, page, dirty);
+			make_coherent(mapping, vma, addr, pfn);
 	}
 }
 
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 4085ed983e4..191788fb18d 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -37,13 +37,8 @@ static void flush_pfn_alias(unsigned long pfn, unsigned long vaddr)
 #define flush_pfn_alias(pfn,vaddr)	do { } while (0)
 #endif
 
-static void __flush_dcache_page(struct address_space *mapping, struct page *page)
+void __flush_dcache_page(struct address_space *mapping, struct page *page)
 {
-	struct mm_struct *mm = current->active_mm;
-	struct vm_area_struct *mpnt;
-	struct prio_tree_iter iter;
-	pgoff_t pgoff;
-
 	/*
 	 * Writeback any data associated with the kernel mapping of this
 	 * page.  This ensures that data in the physical page is mutually
@@ -52,24 +47,21 @@ static void __flush_dcache_page(struct address_space *mapping, struct page *page
 	__cpuc_flush_dcache_page(page_address(page));
 
 	/*
-	 * If there's no mapping pointer here, then this page isn't
-	 * visible to userspace yet, so there are no cache lines
-	 * associated with any other aliases.
-	 */
-	if (!mapping)
-		return;
-
-	/*
-	 * This is a page cache page.  If we have a VIPT cache, we
-	 * only need to do one flush - which would be at the relevant
+	 * If this is a page cache page, and we have an aliasing VIPT cache,
+	 * we only need to do one flush - which would be at the relevant
 	 * userspace colour, which is congruent with page->index.
 	 */
-	if (cache_is_vipt()) {
-		if (cache_is_vipt_aliasing())
-			flush_pfn_alias(page_to_pfn(page),
-					page->index << PAGE_CACHE_SHIFT);
-		return;
-	}
+	if (mapping && cache_is_vipt_aliasing())
+		flush_pfn_alias(page_to_pfn(page),
+				page->index << PAGE_CACHE_SHIFT);
+}
+
+static void __flush_dcache_aliases(struct address_space *mapping, struct page *page)
+{
+	struct mm_struct *mm = current->active_mm;
+	struct vm_area_struct *mpnt;
+	struct prio_tree_iter iter;
+	pgoff_t pgoff;
 
 	/*
 	 * There are possible user space mappings of this page:
@@ -116,12 +108,12 @@ void flush_dcache_page(struct page *page)
 {
 	struct address_space *mapping = page_mapping(page);
 
-	if (cache_is_vipt_nonaliasing())
-		return;
-
 	if (mapping && !mapping_mapped(mapping))
 		set_bit(PG_dcache_dirty, &page->flags);
-	else
+	else {
 		__flush_dcache_page(mapping, page);
+		if (mapping && cache_is_vivt())
+			__flush_dcache_aliases(mapping, page);
+	}
 }
 EXPORT_SYMBOL(flush_dcache_page);
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 00bb8fd37a5..7110e54182b 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -170,3 +170,50 @@ void __iounmap(void __iomem *addr)
 	vfree((void *) (PAGE_MASK & (unsigned long) addr));
 }
 EXPORT_SYMBOL(__iounmap);
+
+#ifdef __io
+void __iomem *ioport_map(unsigned long port, unsigned int nr)
+{
+	return __io(port);
+}
+EXPORT_SYMBOL(ioport_map);
+
+void ioport_unmap(void __iomem *addr)
+{
+}
+EXPORT_SYMBOL(ioport_unmap);
+#endif
+
+#ifdef CONFIG_PCI
+#include <linux/pci.h>
+#include <linux/ioport.h>
+
+void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
+{
+	unsigned long start = pci_resource_start(dev, bar);
+	unsigned long len   = pci_resource_len(dev, bar);
+	unsigned long flags = pci_resource_flags(dev, bar);
+
+	if (!len || !start)
+		return NULL;
+	if (maxlen && len > maxlen)
+		len = maxlen;
+	if (flags & IORESOURCE_IO)
+		return ioport_map(start, len);
+	if (flags & IORESOURCE_MEM) {
+		if (flags & IORESOURCE_CACHEABLE)
+			return ioremap(start, len);
+		return ioremap_nocache(start, len);
+	}
+	return NULL;
+}
+EXPORT_SYMBOL(pci_iomap);
+
+void pci_iounmap(struct pci_dev *dev, void __iomem *addr)
+{
+	if ((unsigned long)addr >= VMALLOC_START &&
+	    (unsigned long)addr < VMALLOC_END)
+		iounmap(addr);
+}
+EXPORT_SYMBOL(pci_iounmap);
+#endif