diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index be956dbf6baea3a7481baa11c58233d0741702d1..1571d126e9ddb08b77c99955538209212755ebfd 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -61,7 +61,7 @@ extern void __pgd_error(const char *file, int line, pgd_t);
  * mapping to be mapped at.  This is particularly important for
  * non-high vector CPUs.
  */
-#define FIRST_USER_ADDRESS	PAGE_SIZE
+#define FIRST_USER_ADDRESS	(PAGE_SIZE * 2)
 
 /*
  * Use TASK_SIZE as the ceiling argument for free_pgtables() and
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index 57221e349a7ce0eec03445cd56de2845e5d23358..f0d180d8b29f4e22558a98fdf9366ebaf1c0c0cb 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -14,11 +14,12 @@
 #include <asm/pgalloc.h>
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
+#include <asm/fncpy.h>
 #include <asm/mach-types.h>
 #include <asm/smp_plat.h>
 #include <asm/system_misc.h>
 
-extern const unsigned char relocate_new_kernel[];
+extern void relocate_new_kernel(void);
 extern const unsigned int relocate_new_kernel_size;
 
 extern unsigned long kexec_start_address;
@@ -142,6 +143,8 @@ void machine_kexec(struct kimage *image)
 {
 	unsigned long page_list;
 	unsigned long reboot_code_buffer_phys;
+	unsigned long reboot_entry = (unsigned long)relocate_new_kernel;
+	unsigned long reboot_entry_phys;
 	void *reboot_code_buffer;
 
 	/*
@@ -168,16 +171,16 @@ void machine_kexec(struct kimage *image)
 
 
 	/* copy our kernel relocation code to the control code page */
-	memcpy(reboot_code_buffer,
-	       relocate_new_kernel, relocate_new_kernel_size);
+	reboot_entry = fncpy(reboot_code_buffer,
+			     reboot_entry,
+			     relocate_new_kernel_size);
+	reboot_entry_phys = (unsigned long)reboot_entry +
+		(reboot_code_buffer_phys - (unsigned long)reboot_code_buffer);
 
-
-	flush_icache_range((unsigned long) reboot_code_buffer,
-			   (unsigned long) reboot_code_buffer + KEXEC_CONTROL_PAGE_SIZE);
 	printk(KERN_INFO "Bye!\n");
 
 	if (kexec_reinit)
 		kexec_reinit();
 
-	soft_restart(reboot_code_buffer_phys);
+	soft_restart(reboot_entry_phys);
 }
diff --git a/arch/arm/kernel/relocate_kernel.S b/arch/arm/kernel/relocate_kernel.S
index d0cdedf4864dc52092355e105f3ba04bba5c5704..95858966d84ec0f10d392a3356cb0367fcee0b85 100644
--- a/arch/arm/kernel/relocate_kernel.S
+++ b/arch/arm/kernel/relocate_kernel.S
@@ -2,10 +2,12 @@
  * relocate_kernel.S - put the kernel image in place to boot
  */
 
+#include <linux/linkage.h>
 #include <asm/kexec.h>
 
-	.globl relocate_new_kernel
-relocate_new_kernel:
+	.align	3	/* not needed for this code, but keeps fncpy() happy */
+
+ENTRY(relocate_new_kernel)
 
 	ldr	r0,kexec_indirection_page
 	ldr	r1,kexec_start_address
@@ -79,6 +81,8 @@ kexec_mach_type:
 kexec_boot_atags:
 	.long	0x0
 
+ENDPROC(relocate_new_kernel)
+
 relocate_new_kernel_end:
 
 	.globl relocate_new_kernel_size
diff --git a/arch/arm/kernel/sigreturn_codes.S b/arch/arm/kernel/sigreturn_codes.S
index 3c5d0f2170fd7ee309260c2d2c0a6108a24e54f8..b84d0cb13682ccd42e41a22894cb8d2c1821496d 100644
--- a/arch/arm/kernel/sigreturn_codes.S
+++ b/arch/arm/kernel/sigreturn_codes.S
@@ -30,6 +30,27 @@
  * snippets.
  */
 
+/*
+ * In CPU_THUMBONLY case kernel arm opcodes are not allowed.
+ * Note in this case codes skips those instructions but it uses .org
+ * directive to keep correct layout of sigreturn_codes array.
+ */
+#ifndef CONFIG_CPU_THUMBONLY
+#define ARM_OK(code...)	code
+#else
+#define ARM_OK(code...)
+#endif
+
+	.macro arm_slot n
+	.org	sigreturn_codes + 12 * (\n)
+ARM_OK(	.arm	)
+	.endm
+
+	.macro thumb_slot n
+	.org	sigreturn_codes + 12 * (\n) + 8
+	.thumb
+	.endm
+
 #if __LINUX_ARM_ARCH__ <= 4
 	/*
 	 * Note we manually set minimally required arch that supports
@@ -45,26 +66,27 @@
 	.global sigreturn_codes
 	.type	sigreturn_codes, #object
 
-	.arm
+	.align
 
 sigreturn_codes:
 
 	/* ARM sigreturn syscall code snippet */
-	mov	r7, #(__NR_sigreturn - __NR_SYSCALL_BASE)
-	swi	#(__NR_sigreturn)|(__NR_OABI_SYSCALL_BASE)
+	arm_slot 0
+ARM_OK(	mov	r7, #(__NR_sigreturn - __NR_SYSCALL_BASE)	)
+ARM_OK(	swi	#(__NR_sigreturn)|(__NR_OABI_SYSCALL_BASE)	)
 
 	/* Thumb sigreturn syscall code snippet */
-	.thumb
+	thumb_slot 0
 	movs	r7, #(__NR_sigreturn - __NR_SYSCALL_BASE)
 	swi	#0
 
 	/* ARM sigreturn_rt syscall code snippet */
-	.arm
-	mov	r7, #(__NR_rt_sigreturn - __NR_SYSCALL_BASE)
-	swi	#(__NR_rt_sigreturn)|(__NR_OABI_SYSCALL_BASE)
+	arm_slot 1
+ARM_OK(	mov	r7, #(__NR_rt_sigreturn - __NR_SYSCALL_BASE)	)
+ARM_OK(	swi	#(__NR_rt_sigreturn)|(__NR_OABI_SYSCALL_BASE)	)
 
 	/* Thumb sigreturn_rt syscall code snippet */
-	.thumb
+	thumb_slot 1
 	movs	r7, #(__NR_rt_sigreturn - __NR_SYSCALL_BASE)
 	swi	#0
 
@@ -74,7 +96,7 @@ sigreturn_codes:
 	 * it is thumb case or not, so we need additional
 	 * word after real last entry.
 	 */
-	.arm
+	arm_slot 2
 	.space	4
 
 	.size	sigreturn_codes, . - sigreturn_codes
diff --git a/arch/arm/lib/delay-loop.S b/arch/arm/lib/delay-loop.S
index 36b668d8e121ee7450c8beffb5e9661923102038..bc1033b897b44510b16a8ab202f0c1b989cc15e5 100644
--- a/arch/arm/lib/delay-loop.S
+++ b/arch/arm/lib/delay-loop.S
@@ -40,6 +40,7 @@ ENTRY(__loop_const_udelay)			@ 0 <= r0 <= 0x7fffff06
 /*
  * loops = r0 * HZ * loops_per_jiffy / 1000000
  */
+		.align 3
 
 @ Delay routine
 ENTRY(__loop_delay)
diff --git a/arch/arm/mach-footbridge/common.c b/arch/arm/mach-footbridge/common.c
index 2739ca2c13346f1ed4bdce26916ae4e2270900ad..e0091685fd4861c8eb6f41b00c5f316865c1668b 100644
--- a/arch/arm/mach-footbridge/common.c
+++ b/arch/arm/mach-footbridge/common.c
@@ -15,6 +15,7 @@
 #include <linux/init.h>
 #include <linux/io.h>
 #include <linux/spinlock.h>
+#include <video/vga.h>
 
 #include <asm/pgtable.h>
 #include <asm/page.h>
@@ -196,6 +197,8 @@ void __init footbridge_map_io(void)
 		iotable_init(ebsa285_host_io_desc, ARRAY_SIZE(ebsa285_host_io_desc));
 		pci_map_io_early(__phys_to_pfn(DC21285_PCI_IO));
 	}
+
+	vga_base = PCIMEM_BASE;
 }
 
 void footbridge_restart(enum reboot_mode mode, const char *cmd)
diff --git a/arch/arm/mach-footbridge/dc21285.c b/arch/arm/mach-footbridge/dc21285.c
index 3490a24f969e4a0b450ef146cee72f37e1cb6c9f..7c2fdae9a38b63454523277a005dcf6c5c1c65ab 100644
--- a/arch/arm/mach-footbridge/dc21285.c
+++ b/arch/arm/mach-footbridge/dc21285.c
@@ -18,7 +18,6 @@
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/spinlock.h>
-#include <video/vga.h>
 
 #include <asm/irq.h>
 #include <asm/mach/pci.h>
@@ -291,7 +290,6 @@ void __init dc21285_preinit(void)
 	int cfn_mode;
 
 	pcibios_min_mem = 0x81000000;
-	vga_base = PCIMEM_BASE;
 
 	mem_size = (unsigned int)high_memory - PAGE_OFFSET;
 	for (mem_mask = 0x00100000; mem_mask < 0x10000000; mem_mask <<= 1)
diff --git a/arch/arm/mach-footbridge/ebsa285.c b/arch/arm/mach-footbridge/ebsa285.c
index b08243500e2e9bc8f7196d6e6c5484b3ba7dadb4..1a7235fb52acb3cb8ae784dbeeda4fb3c940594a 100644
--- a/arch/arm/mach-footbridge/ebsa285.c
+++ b/arch/arm/mach-footbridge/ebsa285.c
@@ -30,21 +30,24 @@ static const struct {
 	const char *name;
 	const char *trigger;
 } ebsa285_leds[] = {
-	{ "ebsa285:amber", "heartbeat", },
-	{ "ebsa285:green", "cpu0", },
+	{ "ebsa285:amber", "cpu0", },
+	{ "ebsa285:green", "heartbeat", },
 	{ "ebsa285:red",},
 };
 
+static unsigned char hw_led_state;
+
 static void ebsa285_led_set(struct led_classdev *cdev,
 		enum led_brightness b)
 {
 	struct ebsa285_led *led = container_of(cdev,
 			struct ebsa285_led, cdev);
 
-	if (b != LED_OFF)
-		*XBUS_LEDS |= led->mask;
+	if (b == LED_OFF)
+		hw_led_state |= led->mask;
 	else
-		*XBUS_LEDS &= ~led->mask;
+		hw_led_state &= ~led->mask;
+	*XBUS_LEDS = hw_led_state;
 }
 
 static enum led_brightness ebsa285_led_get(struct led_classdev *cdev)
@@ -52,18 +55,19 @@ static enum led_brightness ebsa285_led_get(struct led_classdev *cdev)
 	struct ebsa285_led *led = container_of(cdev,
 			struct ebsa285_led, cdev);
 
-	return (*XBUS_LEDS & led->mask) ? LED_FULL : LED_OFF;
+	return hw_led_state & led->mask ? LED_OFF : LED_FULL;
 }
 
 static int __init ebsa285_leds_init(void)
 {
 	int i;
 
-	if (machine_is_ebsa285())
+	if (!machine_is_ebsa285())
 		return -ENODEV;
 
-	/* 3 LEDS All ON */
-	*XBUS_LEDS |= XBUS_LED_AMBER | XBUS_LED_GREEN | XBUS_LED_RED;
+	/* 3 LEDS all off */
+	hw_led_state = XBUS_LED_AMBER | XBUS_LED_GREEN | XBUS_LED_RED;
+	*XBUS_LEDS = hw_led_state;
 
 	for (i = 0; i < ARRAY_SIZE(ebsa285_leds); i++) {
 		struct ebsa285_led *led;
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 79f8b39801a8e570bd86ea80e566ee939bbb600b..f6b6bfa88ecff21ddde5646dfaafa0190792f247 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -9,6 +9,7 @@
  *
  *  DMA uncached mapping support.
  */
+#include <linux/bootmem.h>
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/gfp.h>
@@ -162,6 +163,8 @@ static u64 get_coherent_dma_mask(struct device *dev)
 	u64 mask = (u64)DMA_BIT_MASK(32);
 
 	if (dev) {
+		unsigned long max_dma_pfn;
+
 		mask = dev->coherent_dma_mask;
 
 		/*
@@ -173,6 +176,8 @@ static u64 get_coherent_dma_mask(struct device *dev)
 			return 0;
 		}
 
+		max_dma_pfn = min(max_pfn, arm_dma_pfn_limit);
+
 		/*
 		 * If the mask allows for more memory than we can address,
 		 * and we actually have that much memory, then fail the
@@ -180,7 +185,7 @@ static u64 get_coherent_dma_mask(struct device *dev)
 		 */
 		if (sizeof(mask) != sizeof(dma_addr_t) &&
 		    mask > (dma_addr_t)~0 &&
-		    dma_to_pfn(dev, ~0) > arm_dma_pfn_limit) {
+		    dma_to_pfn(dev, ~0) > max_dma_pfn) {
 			dev_warn(dev, "Coherent DMA mask %#llx is larger than dma_addr_t allows\n",
 				 mask);
 			dev_warn(dev, "Driver did not use or check the return value from dma_set_coherent_mask()?\n");
@@ -192,7 +197,7 @@ static u64 get_coherent_dma_mask(struct device *dev)
 		 * fits within the allowable addresses which we can
 		 * allocate.
 		 */
-		if (dma_to_pfn(dev, mask) < arm_dma_pfn_limit) {
+		if (dma_to_pfn(dev, mask) < max_dma_pfn) {
 			dev_warn(dev, "Coherent DMA mask %#llx (pfn %#lx-%#lx) covers a smaller range of system memory than the DMA zone pfn 0x0-%#lx\n",
 				 mask,
 				 dma_to_pfn(dev, 0), dma_to_pfn(dev, mask) + 1,
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index d27158c38eb0b190b869e028b93d8265fb90969e..5e85ed371364c17657be7d7155139a5e3f536437 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -146,7 +146,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 
 	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
 	info.length = len;
-	info.low_limit = PAGE_SIZE;
+	info.low_limit = FIRST_USER_ADDRESS;
 	info.high_limit = mm->mmap_base;
 	info.align_mask = do_align ? (PAGE_MASK & (SHMLBA - 1)) : 0;
 	info.align_offset = pgoff << PAGE_SHIFT;
diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c
index 0acb089d0f70db818ce487fa67b0fb90b1b0b69d..1046b373d1aedb2823e3bb62f106681f9b63fc2a 100644
--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -87,7 +87,8 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 		init_pud = pud_offset(init_pgd, 0);
 		init_pmd = pmd_offset(init_pud, 0);
 		init_pte = pte_offset_map(init_pmd, 0);
-		set_pte_ext(new_pte, *init_pte, 0);
+		set_pte_ext(new_pte + 0, init_pte[0], 0);
+		set_pte_ext(new_pte + 1, init_pte[1], 0);
 		pte_unmap(init_pte);
 		pte_unmap(new_pte);
 	}