Merge branch 'sh/stable-updates'

72 files changed, 970 insertions, 632 deletions

diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index 72da7e0..0d08d41 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -15,6 +15,7 @@
 #include <asm/glue.h>
 #include <asm/shmparam.h>
 #include <asm/cachetype.h>
+#include <asm/outercache.h>
 
 #define CACHE_COLOUR(vaddr)	((vaddr & (SHMLBA - 1)) >> PAGE_SHIFT)
 
@@ -219,12 +220,6 @@ struct cpu_cache_fns {
 	void (*dma_flush_range)(const void *, const void *);
 };
 
-struct outer_cache_fns {
-	void (*inv_range)(unsigned long, unsigned long);
-	void (*clean_range)(unsigned long, unsigned long);
-	void (*flush_range)(unsigned long, unsigned long);
-};
-
 /*
  * Select the calling method
  */
@@ -281,37 +276,6 @@ extern void dmac_flush_range(const void *, const void *);
 
 #endif
 
-#ifdef CONFIG_OUTER_CACHE
-
-extern struct outer_cache_fns outer_cache;
-
-static inline void outer_inv_range(unsigned long start, unsigned long end)
-{
-	if (outer_cache.inv_range)
-		outer_cache.inv_range(start, end);
-}
-static inline void outer_clean_range(unsigned long start, unsigned long end)
-{
-	if (outer_cache.clean_range)
-		outer_cache.clean_range(start, end);
-}
-static inline void outer_flush_range(unsigned long start, unsigned long end)
-{
-	if (outer_cache.flush_range)
-		outer_cache.flush_range(start, end);
-}
-
-#else
-
-static inline void outer_inv_range(unsigned long start, unsigned long end)
-{ }
-static inline void outer_clean_range(unsigned long start, unsigned long end)
-{ }
-static inline void outer_flush_range(unsigned long start, unsigned long end)
-{ }
-
-#endif
-
 /*
  * Copy user data from/to a page which is mapped into a different
  * processes address space.  Really, we want to allow our "user
diff --git a/arch/arm/include/asm/clkdev.h b/arch/arm/include/asm/clkdev.h
index 7a0690d..b56c138 100644
--- a/arch/arm/include/asm/clkdev.h
+++ b/arch/arm/include/asm/clkdev.h
@@ -13,6 +13,7 @@
 #define __ASM_CLKDEV_H
 
 struct clk;
+struct device;
 
 struct clk_lookup {
 	struct list_head	node;
diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h
index 328f14a..237282f 100644
--- a/arch/arm/include/asm/irq.h
+++ b/arch/arm/include/asm/irq.h
@@ -17,6 +17,7 @@
 
 #ifndef __ASSEMBLY__
 struct irqaction;
+struct pt_regs;
 extern void migrate_irqs(void);
 
 extern void asm_do_IRQ(unsigned int, struct pt_regs *);
diff --git a/arch/arm/include/asm/outercache.h b/arch/arm/include/asm/outercache.h
new file mode 100644
index 0000000..25f76ba
--- /dev/null
+++ b/arch/arm/include/asm/outercache.h
@@ -0,0 +1,75 @@
+/*
+ * arch/arm/include/asm/outercache.h
+ *
+ * Copyright (C) 2010 ARM Ltd.
+ * Written by Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef __ASM_OUTERCACHE_H
+#define __ASM_OUTERCACHE_H
+
+struct outer_cache_fns {
+	void (*inv_range)(unsigned long, unsigned long);
+	void (*clean_range)(unsigned long, unsigned long);
+	void (*flush_range)(unsigned long, unsigned long);
+#ifdef CONFIG_OUTER_CACHE_SYNC
+	void (*sync)(void);
+#endif
+};
+
+#ifdef CONFIG_OUTER_CACHE
+
+extern struct outer_cache_fns outer_cache;
+
+static inline void outer_inv_range(unsigned long start, unsigned long end)
+{
+	if (outer_cache.inv_range)
+		outer_cache.inv_range(start, end);
+}
+static inline void outer_clean_range(unsigned long start, unsigned long end)
+{
+	if (outer_cache.clean_range)
+		outer_cache.clean_range(start, end);
+}
+static inline void outer_flush_range(unsigned long start, unsigned long end)
+{
+	if (outer_cache.flush_range)
+		outer_cache.flush_range(start, end);
+}
+
+#else
+
+static inline void outer_inv_range(unsigned long start, unsigned long end)
+{ }
+static inline void outer_clean_range(unsigned long start, unsigned long end)
+{ }
+static inline void outer_flush_range(unsigned long start, unsigned long end)
+{ }
+
+#endif
+
+#ifdef CONFIG_OUTER_CACHE_SYNC
+static inline void outer_sync(void)
+{
+	if (outer_cache.sync)
+		outer_cache.sync();
+}
+#else
+static inline void outer_sync(void)
+{ }
+#endif
+
+#endif	/* __ASM_OUTERCACHE_H */
diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h
index ca88e6a..4ace45e 100644
--- a/arch/arm/include/asm/system.h
+++ b/arch/arm/include/asm/system.h
@@ -60,6 +60,8 @@
 #include <linux/linkage.h>
 #include <linux/irqflags.h>
 
+#include <asm/outercache.h>
+
 #define __exception	__attribute__((section(".exception.text")))
 
 struct thread_info;
@@ -137,10 +139,12 @@ extern unsigned int user_debug;
 #define dmb() __asm__ __volatile__ ("" : : : "memory")
 #endif
 
-#if __LINUX_ARM_ARCH__ >= 7 || defined(CONFIG_SMP)
-#define mb()		dmb()
+#ifdef CONFIG_ARCH_HAS_BARRIERS
+#include <mach/barriers.h>
+#elif __LINUX_ARM_ARCH__ >= 7 || defined(CONFIG_SMP)
+#define mb()		do { dsb(); outer_sync(); } while (0)
 #define rmb()		dmb()
-#define wmb()		dmb()
+#define wmb()		mb()
 #else
 #define mb()	do { if (arch_is_coherent()) dmb(); else barrier(); } while (0)
 #define rmb()	do { if (arch_is_coherent()) dmb(); else barrier(); } while (0)
@@ -152,9 +156,9 @@ extern unsigned int user_debug;
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
 #else
-#define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	wmb()
+#define smp_mb()	dmb()
+#define smp_rmb()	dmb()
+#define smp_wmb()	dmb()
 #endif
 
 #define read_barrier_depends()		do { } while(0)
diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c
index 60c62c3..610e0f5 100644
--- a/arch/arm/kernel/kprobes.c
+++ b/arch/arm/kernel/kprobes.c
@@ -393,6 +393,14 @@ void __kprobes jprobe_return(void)
 		/*
 		 * Setup an empty pt_regs. Fill SP and PC fields as
 		 * they're needed by longjmp_break_handler.
+		 *
+		 * We allocate some slack between the original SP and start of
+		 * our fabricated regs. To be precise we want to have worst case
+		 * covered which is STMFD with all 16 regs so we allocate 2 *
+		 * sizeof(struct_pt_regs)).
+		 *
+		 * This is to prevent any simulated instruction from writing
+		 * over the regs when they are accessing the stack.
 		 */
 		"sub    sp, %0, %1		\n\t"
 		"ldr    r0, ="__stringify(JPROBE_MAGIC_ADDR)"\n\t"
@@ -410,7 +418,7 @@ void __kprobes jprobe_return(void)
 		"ldmia	sp, {r0 - pc}		\n\t"
 		:
 		: "r" (kcb->jprobe_saved_regs.ARM_sp),
-		  "I" (sizeof(struct pt_regs)),
+		  "I" (sizeof(struct pt_regs) * 2),
 		  "J" (offsetof(struct pt_regs, ARM_sp)),
 		  "J" (offsetof(struct pt_regs, ARM_pc)),
 		  "J" (offsetof(struct pt_regs, ARM_cpsr))
diff --git a/arch/arm/lib/memmove.S b/arch/arm/lib/memmove.S
index 5025c86..938fc14 100644
--- a/arch/arm/lib/memmove.S
+++ b/arch/arm/lib/memmove.S
@@ -74,7 +74,7 @@ ENTRY(memmove)
 		rsb	ip, ip, #32
 		addne	pc, pc, ip		@ C is always clear here
 		b	7f
-6:		nop
+6:		W(nop)
 		W(ldr)	r3, [r1, #-4]!
 		W(ldr)	r4, [r1, #-4]!
 		W(ldr)	r5, [r1, #-4]!
@@ -85,7 +85,7 @@ ENTRY(memmove)
 
 		add	pc, pc, ip
 		nop
-		nop
+		W(nop)
 		W(str)	r3, [r0, #-4]!
 		W(str)	r4, [r0, #-4]!
 		W(str)	r5, [r0, #-4]!
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index c4ed9f9..5bd7c89 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -736,6 +736,12 @@ config NEEDS_SYSCALL_FOR_CMPXCHG
 config OUTER_CACHE
 	bool
 
+config OUTER_CACHE_SYNC
+	bool
+	help
+	  The outer cache has a outer_cache_fns.sync function pointer
+	  that can be used to drain the write buffer of the outer cache.
+
 config CACHE_FEROCEON_L2
 	bool "Enable the Feroceon L2 cache controller"
 	depends on ARCH_KIRKWOOD || ARCH_MV78XX0
@@ -757,6 +763,7 @@ config CACHE_L2X0
 		   REALVIEW_EB_A9MP || ARCH_MX35 || ARCH_MX31 || MACH_REALVIEW_PBX || ARCH_NOMADIK || ARCH_OMAP4
 	default y
 	select OUTER_CACHE
+	select OUTER_CACHE_SYNC
 	help
 	  This option enables the L2x0 PrimeCell.
 
@@ -781,3 +788,9 @@ config ARM_L1_CACHE_SHIFT
 	int
 	default 6 if ARM_L1_CACHE_SHIFT_6
 	default 5
+
+config ARCH_HAS_BARRIERS
+	bool
+	help
+	  This option allows the use of custom mandatory barriers
+	  included via the mach/barriers.h file.
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 0733463..21ad68b 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -93,6 +93,15 @@ static inline void l2x0_flush_line(unsigned long addr)
 }
 #endif
 
+static void l2x0_cache_sync(void)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&l2x0_lock, flags);
+	cache_sync();
+	spin_unlock_irqrestore(&l2x0_lock, flags);
+}
+
 static inline void l2x0_inv_all(void)
 {
 	unsigned long flags;
@@ -225,6 +234,7 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask)
 	outer_cache.inv_range = l2x0_inv_range;
 	outer_cache.clean_range = l2x0_clean_range;
 	outer_cache.flush_range = l2x0_flush_range;
+	outer_cache.sync = l2x0_cache_sync;
 
 	printk(KERN_INFO "L2X0 cache controller enabled\n");
 }
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 7f3f59f..a420cb9 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -545,7 +545,7 @@ static int __init vfp_init(void)
 		 */
 		elf_hwcap |= HWCAP_VFP;
 #ifdef CONFIG_VFPv3
-		if (VFP_arch >= 3) {
+		if (VFP_arch >= 2) {
 			elf_hwcap |= HWCAP_VFPv3;
 
 			/*
diff --git a/arch/cris/arch-v32/drivers/pci/bios.c b/arch/cris/arch-v32/drivers/pci/bios.c
index d4b9c36..bc0cfda 100644
--- a/arch/cris/arch-v32/drivers/pci/bios.c
+++ b/arch/cris/arch-v32/drivers/pci/bios.c
@@ -50,7 +50,7 @@ pcibios_align_resource(void *data, const struct resource *res,
 	if ((res->flags & IORESOURCE_IO) && (start & 0x300))
 		start = (start + 0x3ff) & ~0x3ff;
 
-	return start
+	return start;
 }
 
 int pcibios_enable_resources(struct pci_dev *dev, int mask)
diff --git a/arch/frv/mb93090-mb00/pci-frv.c b/arch/frv/mb93090-mb00/pci-frv.c
index 1ed15d7..6b4fb28 100644
--- a/arch/frv/mb93090-mb00/pci-frv.c
+++ b/arch/frv/mb93090-mb00/pci-frv.c
@@ -41,7 +41,7 @@ pcibios_align_resource(void *data, const struct resource *res,
 	if ((res->flags & IORESOURCE_IO) && (start & 0x300))
 		start = (start + 0x3ff) & ~0x3ff;
 
-	return start
+	return start;
 }
 
 
@@ -94,8 +94,7 @@ static void __init pcibios_allocate_bus_resources(struct list_head *bus_list)
 				r = &dev->resource[idx];
 				if (!r->start)
 					continue;
-				if (pci_claim_resource(dev, idx) < 0)
-					printk(KERN_ERR "PCI: Cannot allocate resource region %d of bridge %s\n", idx, pci_name(dev));
+				pci_claim_resource(dev, idx);
 			}
 		}
 		pcibios_allocate_bus_resources(&bus->children);
@@ -125,7 +124,6 @@ static void __init pcibios_allocate_resources(int pass)
 				DBG("PCI: Resource %08lx-%08lx (f=%lx, d=%d, p=%d)\n",
 				    r->start, r->end, r->flags, disabled, pass);
 				if (pci_claim_resource(dev, idx) < 0) {
-					printk(KERN_ERR "PCI: Cannot allocate resource region %d of device %s\n", idx, pci_name(dev));
 					/* We'll assign a new address later */
 					r->end -= r->start;
 					r->start = 0;
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index 203ec61..76818f9 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -75,9 +75,6 @@ config LOCKDEP_SUPPORT
 config HAVE_LATENCYTOP_SUPPORT
 	def_bool y
 
-config PCI
-	def_bool n
-
 config DTC
 	def_bool y
 
diff --git a/arch/microblaze/Makefile b/arch/microblaze/Makefile
index 836832d..72f6e85 100644
--- a/arch/microblaze/Makefile
+++ b/arch/microblaze/Makefile
@@ -84,7 +84,7 @@ define archhelp
   echo '* linux.bin    - Create raw binary'
   echo '  linux.bin.gz - Create compressed raw binary'
   echo '  simpleImage.<dt> - ELF image with $(arch)/boot/dts/<dt>.dts linked in'
-  echo '                   - stripped elf with fdt blob
+  echo '                   - stripped elf with fdt blob'
   echo '  simpleImage.<dt>.unstrip - full ELF image with fdt blob'
   echo '  *_defconfig      - Select default config from arch/microblaze/configs'
   echo ''
@@ -94,3 +94,5 @@ define archhelp
   echo '  name of a dts file from the arch/microblaze/boot/dts/ directory'
   echo '  (minus the .dts extension).'
 endef
+
+MRPROPER_FILES += $(boot)/simpleImage.*
diff --git a/arch/microblaze/boot/Makefile b/arch/microblaze/boot/Makefile
index 902cf98..57f50c2 100644
--- a/arch/microblaze/boot/Makefile
+++ b/arch/microblaze/boot/Makefile
@@ -23,8 +23,6 @@ $(obj)/system.dtb: $(obj)/$(DTB).dtb
 endif
 
 $(obj)/linux.bin: vmlinux FORCE
-	[ -n $(CONFIG_INITRAMFS_SOURCE) ] && [ ! -e $(CONFIG_INITRAMFS_SOURCE) ] && \
-	touch $(CONFIG_INITRAMFS_SOURCE) || echo "No CPIO image"
 	$(call if_changed,objcopy)
 	$(call if_changed,uimage)
 	@echo 'Kernel: $@ is ready' ' (#'`cat .version`')'
@@ -62,6 +60,4 @@ quiet_cmd_dtc = DTC     $@
 $(obj)/%.dtb: $(dtstree)/%.dts FORCE
 	$(call if_changed,dtc)
 
-clean-kernel += linux.bin linux.bin.gz simpleImage.*
-
-clean-files += *.dtb simpleImage.*.unstrip
+clean-files += *.dtb simpleImage.*.unstrip linux.bin.ub
diff --git a/arch/microblaze/include/asm/processor.h b/arch/microblaze/include/asm/processor.h
index 563c6b9..8eeb092 100644
--- a/arch/microblaze/include/asm/processor.h
+++ b/arch/microblaze/include/asm/processor.h
@@ -14,7 +14,6 @@
 #include <asm/ptrace.h>
 #include <asm/setup.h>
 #include <asm/registers.h>
-#include <asm/segment.h>
 #include <asm/entry.h>
 #include <asm/current.h>
 
diff --git a/arch/microblaze/include/asm/segment.h b/arch/microblaze/include/asm/segment.h
deleted file mode 100644
index 0e7102c..0000000
--- a/arch/microblaze/include/asm/segment.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/*
- * Copyright (C) 2008-2009 Michal Simek <monstr@monstr.eu>
- * Copyright (C) 2008-2009 PetaLogix
- * Copyright (C) 2006 Atmark Techno, Inc.
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-
-#ifndef _ASM_MICROBLAZE_SEGMENT_H
-#define _ASM_MICROBLAZE_SEGMENT_H
-
-# ifndef __ASSEMBLY__
-
-typedef struct {
-	unsigned long seg;
-} mm_segment_t;
-
-/*
- * On Microblaze the fs value is actually the top of the corresponding
- * address space.
- *
- * The fs value determines whether argument validity checking should be
- * performed or not. If get_fs() == USER_DS, checking is performed, with
- * get_fs() == KERNEL_DS, checking is bypassed.
- *
- * For historical reasons, these macros are grossly misnamed.
- *
- * For non-MMU arch like Microblaze, KERNEL_DS and USER_DS is equal.
- */
-# define MAKE_MM_SEG(s)       ((mm_segment_t) { (s) })
-
-#  ifndef CONFIG_MMU
-#  define KERNEL_DS	MAKE_MM_SEG(0)
-#  define USER_DS	KERNEL_DS
-#  else
-#  define KERNEL_DS	MAKE_MM_SEG(0xFFFFFFFF)
-#  define USER_DS	MAKE_MM_SEG(TASK_SIZE - 1)
-#  endif
-
-# define get_ds()	(KERNEL_DS)
-# define get_fs()	(current_thread_info()->addr_limit)
-# define set_fs(val)	(current_thread_info()->addr_limit = (val))
-
-# define segment_eq(a, b)	((a).seg == (b).seg)
-
-# endif /* __ASSEMBLY__ */
-#endif /* _ASM_MICROBLAZE_SEGMENT_H */
diff --git a/arch/microblaze/include/asm/thread_info.h b/arch/microblaze/include/asm/thread_info.h
index 6e92885..b2ca80f 100644
--- a/arch/microblaze/include/asm/thread_info.h
+++ b/arch/microblaze/include/asm/thread_info.h
@@ -19,7 +19,6 @@
 #ifndef __ASSEMBLY__
 # include <linux/types.h>
 # include <asm/processor.h>
-# include <asm/segment.h>
 
 /*
  * low level task data that entry.S needs immediate access to
@@ -60,6 +59,10 @@ struct cpu_context {
 	__u32	fsr;
 };
 
+typedef struct {
+	unsigned long seg;
+} mm_segment_t;
+
 struct thread_info {
 	struct task_struct	*task; /* main task structure */
 	struct exec_domain	*exec_domain; /* execution domain */
diff --git a/arch/microblaze/include/asm/tlbflush.h b/arch/microblaze/include/asm/tlbflush.h
index bcb8b41..2e1353c 100644
--- a/arch/microblaze/include/asm/tlbflush.h
+++ b/arch/microblaze/include/asm/tlbflush.h
@@ -24,6 +24,7 @@ extern void _tlbie(unsigned long address);
 extern void _tlbia(void);
 
 #define __tlbia()	{ preempt_disable(); _tlbia(); preempt_enable(); }
+#define __tlbie(x)	{ _tlbie(x); }
 
 static inline void local_flush_tlb_all(void)
 	{ __tlbia(); }
@@ -31,7 +32,7 @@ static inline void local_flush_tlb_mm(struct mm_struct *mm)
 	{ __tlbia(); }
 static inline void local_flush_tlb_page(struct vm_area_struct *vma,
 				unsigned long vmaddr)
-	{ _tlbie(vmaddr); }
+	{ __tlbie(vmaddr); }
 static inline void local_flush_tlb_range(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end)
 	{ __tlbia(); }
diff --git a/arch/microblaze/include/asm/uaccess.h b/arch/microblaze/include/asm/uaccess.h
index 371bd6e..446bec2 100644
--- a/arch/microblaze/include/asm/uaccess.h
+++ b/arch/microblaze/include/asm/uaccess.h
@@ -22,101 +22,73 @@
 #include <asm/mmu.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
-#include <asm/segment.h>
 #include <linux/string.h>
 
 #define VERIFY_READ	0
 #define VERIFY_WRITE	1
 
-#define __clear_user(addr, n)	(memset((void *)(addr), 0, (n)), 0)
-
-#ifndef CONFIG_MMU
-
-extern int ___range_ok(unsigned long addr, unsigned long size);
-
-#define __range_ok(addr, size) \
-		___range_ok((unsigned long)(addr), (unsigned long)(size))
-
-#define access_ok(type, addr, size) (__range_ok((addr), (size)) == 0)
-#define __access_ok(add, size) (__range_ok((addr), (size)) == 0)
-
-/* Undefined function to trigger linker error */
-extern int bad_user_access_length(void);
-
-/* FIXME this is function for optimalization -> memcpy */
-#define __get_user(var, ptr)				\
-({							\
-	int __gu_err = 0;				\
-	switch (sizeof(*(ptr))) {			\
-	case 1:						\
-	case 2:						\
-	case 4:						\
-		(var) = *(ptr);				\
-		break;					\
-	case 8:						\
-		memcpy((void *) &(var), (ptr), 8);	\
-		break;					\
-	default:					\
-		(var) = 0;				\
-		__gu_err = __get_user_bad();		\
-		break;					\
-	}						\
-	__gu_err;					\
-})
+/*
+ * On Microblaze the fs value is actually the top of the corresponding
+ * address space.
+ *
+ * The fs value determines whether argument validity checking should be
+ * performed or not. If get_fs() == USER_DS, checking is performed, with
+ * get_fs() == KERNEL_DS, checking is bypassed.
+ *
+ * For historical reasons, these macros are grossly misnamed.
+ *
+ * For non-MMU arch like Microblaze, KERNEL_DS and USER_DS is equal.
+ */
+# define MAKE_MM_SEG(s)       ((mm_segment_t) { (s) })
 
-#define __get_user_bad()	(bad_user_access_length(), (-EFAULT))
+#  ifndef CONFIG_MMU
+#  define KERNEL_DS	MAKE_MM_SEG(0)
+#  define USER_DS	KERNEL_DS
+#  else
+#  define KERNEL_DS	MAKE_MM_SEG(0xFFFFFFFF)
+#  define USER_DS	MAKE_MM_SEG(TASK_SIZE - 1)
+#  endif
 
-/* FIXME is not there defined __pu_val */
-#define __put_user(var, ptr)					\
-({								\
-	int __pu_err = 0;					\
-	switch (sizeof(*(ptr))) {				\
-	case 1:							\
-	case 2:							\
-	case 4:							\
-		*(ptr) = (var);					\
-		break;						\
-	case 8: {						\
-		typeof(*(ptr)) __pu_val = (var);		\
-		memcpy(ptr, &__pu_val, sizeof(__pu_val));	\
-		}						\
-		break;						\
-	default:						\
-		__pu_err = __put_user_bad();			\
-		break;						\
-	}							\
-	__pu_err;						\
-})
+# define get_ds()	(KERNEL_DS)
+# define get_fs()	(current_thread_info()->addr_limit)
+# define set_fs(val)	(current_thread_info()->addr_limit = (val))
 
-#define __put_user_bad()	(bad_user_access_length(), (-EFAULT))
+# define segment_eq(a, b)	((a).seg == (b).seg)
 
-#define put_user(x, ptr)	__put_user((x), (ptr))
-#define get_user(x, ptr)	__get_user((x), (ptr))
+/*
+ * The exception table consists of pairs of addresses: the first is the
+ * address of an instruction that is allowed to fault, and the second is
+ * the address at which the program should continue. No registers are
+ * modified, so it is entirely up to the continuation code to figure out
+ * what to do.
+ *
+ * All the routines below use bits of fixup code that are out of line
+ * with the main instruction path. This means when everything is well,
+ * we don't even have to jump over them. Further, they do not intrude
+ * on our cache or tlb entries.
+ */
+struct exception_table_entry {
+	unsigned long insn, fixup;
+};
 
-#define copy_to_user(to, from, n)	(memcpy((to), (from), (n)), 0)
-#define copy_from_user(to, from, n)	(memcpy((to), (from), (n)), 0)
+/* Returns 0 if exception not found and fixup otherwise.  */
+extern unsigned long search_exception_table(unsigned long);
 
-#define __copy_to_user(to, from, n)	(copy_to_user((to), (from), (n)))
-#define __copy_from_user(to, from, n)	(copy_from_user((to), (from), (n)))
-#define __copy_to_user_inatomic(to, from, n) \
-			(__copy_to_user((to), (from), (n)))
-#define __copy_from_user_inatomic(to, from, n) \
-			(__copy_from_user((to), (from), (n)))
+#ifndef CONFIG_MMU
 
-static inline unsigned long clear_user(void *addr, unsigned long size)
+/* Check against bounds of physical memory */
+static inline int ___range_ok(unsigned long addr, unsigned long size)
 {
-	if (access_ok(VERIFY_WRITE, addr, size))
-		size = __clear_user(addr, size);
-	return size;
+	return ((addr < memory_start) ||
+		((addr + size) > memory_end));
 }
 
-/* Returns 0 if exception not found and fixup otherwise.  */
-extern unsigned long search_exception_table(unsigned long);
+#define __range_ok(addr, size) \
+		___range_ok((unsigned long)(addr), (unsigned long)(size))
 
-extern long strncpy_from_user(char *dst, const char *src, long count);
-extern long strnlen_user(const char *src, long count);
+#define access_ok(type, addr, size) (__range_ok((addr), (size)) == 0)
 
-#else /* CONFIG_MMU */
+#else
 
 /*
  * Address is valid if:
@@ -129,24 +101,88 @@ extern long strnlen_user(const char *src, long count);
 /* || printk("access_ok failed for %s at 0x%08lx (size %d), seg 0x%08x\n",
  type?"WRITE":"READ",addr,size,get_fs().seg)) */
 
-/*
- * All the __XXX versions macros/functions below do not perform
- * access checking. It is assumed that the necessary checks have been
- * already performed before the finction (macro) is called.
- */
+#endif
 
-#define get_user(x, ptr)						\
-({									\
-	access_ok(VERIFY_READ, (ptr), sizeof(*(ptr)))			\
-		? __get_user((x), (ptr)) : -EFAULT;			\
-})
+#ifdef CONFIG_MMU
+# define __FIXUP_SECTION	".section .fixup,\"ax\"\n"
+# define __EX_TABLE_SECTION	".section __ex_table,\"a\"\n"
+#else
+# define __FIXUP_SECTION	".section .discard,\"ax\"\n"
+# define __EX_TABLE_SECTION	".section .discard,\"a\"\n"
+#endif
 
-#define put_user(x, ptr)						\
-({									\
-	access_ok(VERIFY_WRITE, (ptr), sizeof(*(ptr)))			\
-		? __put_user((x), (ptr)) : -EFAULT;			\
+extern unsigned long __copy_tofrom_user(void __user *to,
+		const void __user *from, unsigned long size);
+
+/* Return: number of not copied bytes, i.e. 0 if OK or non-zero if fail. */
+static inline unsigned long __must_check __clear_user(void __user *to,
+							unsigned long n)
+{
+	/* normal memset with two words to __ex_table */
+	__asm__ __volatile__ (				\
+			"1:	sb	r0, %2, r0;"	\
+			"	addik	%0, %0, -1;"	\
+			"	bneid	%0, 1b;"	\
+			"	addik	%2, %2, 1;"	\
+			"2:			"	\
+			__EX_TABLE_SECTION		\
+			".word	1b,2b;"			\
+			".previous;"			\
+		: "=r"(n)				\
+		: "0"(n), "r"(to)
+	);
+	return n;
+}
+
+static inline unsigned long __must_check clear_user(void __user *to,
+							unsigned long n)
+{
+	might_sleep();
+	if (unlikely(!access_ok(VERIFY_WRITE, to, n)))
+		return n;
+
+	return __clear_user(to, n);
+}
+
+/* put_user and get_user macros */
+extern long __user_bad(void);
+
+#define __get_user_asm(insn, __gu_ptr, __gu_val, __gu_err)	\
+({								\
+	__asm__ __volatile__ (					\
+			"1:"	insn	" %1, %2, r0;"		\
+			"	addk	%0, r0, r0;"		\
+			"2:			"		\
+			__FIXUP_SECTION				\
+			"3:	brid	2b;"			\
+			"	addik	%0, r0, %3;"		\
+			".previous;"				\
+			__EX_TABLE_SECTION			\
+			".word	1b,3b;"				\
+			".previous;"				\
+		: "=&r"(__gu_err), "=r"(__gu_val)		\
+		: "r"(__gu_ptr), "i"(-EFAULT)			\
+	);							\
 })
 
+/**
+ * get_user: - Get a simple variable from user space.
+ * @x:   Variable to store result.
+ * @ptr: Source address, in user space.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * This macro copies a single simple variable from user space to kernel
+ * space.  It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and the result of
+ * dereferencing @ptr must be assignable to @x without a cast.
+ *
+ * Returns zero on success, or -EFAULT on error.
+ * On error, the variable @x is set to zero.
+ */
+
 #define __get_user(x, ptr)						\
 ({									\
 	unsigned long __gu_val;						\
@@ -163,30 +199,74 @@ extern long strnlen_user(const char *src, long count);
 		__get_user_asm("lw", (ptr), __gu_val, __gu_err);	\
 		break;							\
 	default:							\
-		__gu_val = 0; __gu_err = -EINVAL;			\
+		/* __gu_val = 0; __gu_err = -EINVAL;*/ __gu_err = __user_bad();\
 	}								\
 	x = (__typeof__(*(ptr))) __gu_val;				\
 	__gu_err;							\
 })
 
-#define __get_user_asm(insn, __gu_ptr, __gu_val, __gu_err)		\
+
+#define get_user(x, ptr)						\
 ({									\
-	__asm__ __volatile__ (						\
-			"1:"	insn	" %1, %2, r0;			\
-				addk	%0, r0, r0;			\
-			2:						\
-			.section .fixup,\"ax\";				\
-			3:	brid	2b;				\
-				addik	%0, r0, %3;			\
-			.previous;					\
-			.section __ex_table,\"a\";			\
-			.word	1b,3b;					\
-			.previous;"					\
-		: "=r"(__gu_err), "=r"(__gu_val)			\
-		: "r"(__gu_ptr), "i"(-EFAULT)				\
-	);								\
+	access_ok(VERIFY_READ, (ptr), sizeof(*(ptr)))			\
+		? __get_user((x), (ptr)) : -EFAULT;			\
+})
+
+#define __put_user_asm(insn, __gu_ptr, __gu_val, __gu_err)	\
+({								\
+	__asm__ __volatile__ (					\
+			"1:"	insn	" %1, %2, r0;"		\
+			"	addk	%0, r0, r0;"		\
+			"2:			"		\
+			__FIXUP_SECTION				\
+			"3:	brid	2b;"			\
+			"	addik	%0, r0, %3;"		\
+			".previous;"				\
+			__EX_TABLE_SECTION			\
+			".word	1b,3b;"				\
+			".previous;"				\
+		: "=&r"(__gu_err)				\
+		: "r"(__gu_val), "r"(__gu_ptr), "i"(-EFAULT)	\
+	);							\
 })
 
+#define __put_user_asm_8(__gu_ptr, __gu_val, __gu_err)		\
+({								\
+	__asm__ __volatile__ ("	lwi	%0, %1, 0;"		\
+			"1:	swi	%0, %2, 0;"		\
+			"	lwi	%0, %1, 4;"		\
+			"2:	swi	%0, %2, 4;"		\
+			"	addk	%0, r0, r0;"		\
+			"3:			"		\
+			__FIXUP_SECTION				\
+			"4:	brid	3b;"			\
+			"	addik	%0, r0, %3;"		\
+			".previous;"				\
+			__EX_TABLE_SECTION			\
+			".word	1b,4b,2b,4b;"			\
+			".previous;"				\
+		: "=&r"(__gu_err)				\
+		: "r"(&__gu_val), "r"(__gu_ptr), "i"(-EFAULT)	\
+		);						\
+})
+
+/**
+ * put_user: - Write a simple value into user space.
+ * @x:   Value to copy to user space.
+ * @ptr: Destination address, in user space.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * This macro copies a single simple value from kernel space to user
+ * space.  It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and @x must be assignable
+ * to the result of dereferencing @ptr.
+ *
+ * Returns zero on success, or -EFAULT on error.
+ */
+
 #define __put_user(x, ptr)						\
 ({									\
 	__typeof__(*(ptr)) volatile __gu_val = (x);			\
@@ -195,7 +275,7 @@ extern long strnlen_user(const char *src, long count);
 	case 1:								\
 		__put_user_asm("sb", (ptr), __gu_val, __gu_err);	\
 		break;							\
-	case 2: 							\
+	case 2:								\
 		__put_user_asm("sh", (ptr), __gu_val, __gu_err);	\
 		break;							\
 	case 4:								\
@@ -205,121 +285,82 @@ extern long strnlen_user(const char *src, long count);
 		__put_user_asm_8((ptr), __gu_val, __gu_err);		\
 		break;							\
 	default:							\
-		__gu_err = -EINVAL;					\
+		/*__gu_err = -EINVAL;*/	__gu_err = __user_bad();	\
 	}								\
 	__gu_err;							\
 })
 
-#define __put_user_asm_8(__gu_ptr, __gu_val, __gu_err)	\
-({							\
-__asm__ __volatile__ ("	lwi	%0, %1, 0;		\
-		1:	swi	%0, %2, 0;		\
-			lwi	%0, %1, 4;		\
-		2:	swi	%0, %2, 4;		\
-			addk	%0,r0,r0;		\
-		3:					\
-		.section .fixup,\"ax\";			\
-		4:	brid	3b;			\
-			addik	%0, r0, %3;		\
-		.previous;				\
-		.section __ex_table,\"a\";		\
-		.word	1b,4b,2b,4b;			\
-		.previous;"				\
-	: "=&r"(__gu_err)				\
-	: "r"(&__gu_val),				\
-	"r"(__gu_ptr), "i"(-EFAULT)			\
-	);						\
-})
+#ifndef CONFIG_MMU
 
-#define __put_user_asm(insn, __gu_ptr, __gu_val, __gu_err)	\
-({								\
-	__asm__ __volatile__ (					\
-			"1:"	insn	" %1, %2, r0;		\
-				addk	%0, r0, r0;		\
-			2:					\
-			.section .fixup,\"ax\";			\
-			3:	brid	2b;			\
-				addik	%0, r0, %3;		\
-			.previous;				\
-			.section __ex_table,\"a\";		\
-			.word	1b,3b;				\
-			.previous;"				\
-		: "=r"(__gu_err)				\
-		: "r"(__gu_val), "r"(__gu_ptr), "i"(-EFAULT)	\
-	);							\
-})
+#define put_user(x, ptr)	__put_user((x), (ptr))
 
-/*
- * Return: number of not copied bytes, i.e. 0 if OK or non-zero if fail.
- */
-static inline int clear_user(char *to, int size)
-{
-	if (size && access_ok(VERIFY_WRITE, to, size)) {
-		__asm__ __volatile__ ("				\
-				1:				\
-					sb	r0, %2, r0;	\
-					addik	%0, %0, -1;	\
-					bneid	%0, 1b;		\
-					addik	%2, %2, 1;	\
-				2:				\
-				.section __ex_table,\"a\";	\
-				.word	1b,2b;			\
-				.section .text;"		\
-			: "=r"(size)				\
-			: "0"(size), "r"(to)
-		);
-	}
-	return size;
-}
+#else /* CONFIG_MMU */
 
-#define __copy_from_user(to, from, n)	copy_from_user((to), (from), (n))
+#define put_user(x, ptr)						\
+({									\
+	access_ok(VERIFY_WRITE, (ptr), sizeof(*(ptr)))			\
+		? __put_user((x), (ptr)) : -EFAULT;			\
+})
+#endif /* CONFIG_MMU */
+
+/* copy_to_from_user */
+#define __copy_from_user(to, from, n)	\
+	__copy_tofrom_user((__force void __user *)(to), \
+				(void __user *)(from), (n))
 #define __copy_from_user_inatomic(to, from, n) \
 		copy_from_user((to), (from), (n))
 
-#define copy_to_user(to, from, n)					\
-	(access_ok(VERIFY_WRITE, (to), (n)) ?				\
-		__copy_tofrom_user((void __user *)(to),			\
-			(__force const void __user *)(from), (n))	\
-		: -EFAULT)
+static inline long copy_from_user(void *to,
+		const void __user *from, unsigned long n)
+{
+	might_sleep();
+	if (access_ok(VERIFY_READ, from, n))
+		return __copy_from_user(to, from, n);
+	return n;
+}
 
-#define __copy_to_user(to, from, n)	copy_to_user((to), (from), (n))
+#define __copy_to_user(to, from, n)	\
+		__copy_tofrom_user((void __user *)(to), \
+			(__force const void __user *)(from), (n))
 #define __copy_to_user_inatomic(to, from, n)	copy_to_user((to), (from), (n))
 
-#define copy_from_user(to, from, n)					\
-	(access_ok(VERIFY_READ, (from), (n)) ?				\
-		__copy_tofrom_user((__force void __user *)(to),		\
-			(void __user *)(from), (n))			\
-		: -EFAULT)
+static inline long copy_to_user(void __user *to,
+		const void *from, unsigned long n)
+{
+	might_sleep();
+	if (access_ok(VERIFY_WRITE, to, n))
+		return __copy_to_user(to, from, n);
+	return n;
+}
 
+/*
+ * Copy a null terminated string from userspace.
+ */
 extern int __strncpy_user(char *to, const char __user *from, int len);
-extern int __strnlen_user(const char __user *sstr, int len);
 
-#define strncpy_from_user(to, from, len)	\
-		(access_ok(VERIFY_READ, from, 1) ?	\
-			__strncpy_user(to, from, len) : -EFAULT)
-#define strnlen_user(str, len)	\
-		(access_ok(VERIFY_READ, str, 1) ? __strnlen_user(str, len) : 0)
+#define __strncpy_from_user	__strncpy_user
 
-#endif /* CONFIG_MMU */
-
-extern unsigned long __copy_tofrom_user(void __user *to,
-		const void __user *from, unsigned long size);
+static inline long
+strncpy_from_user(char *dst, const char __user *src, long count)
+{
+	if (!access_ok(VERIFY_READ, src, 1))
+		return -EFAULT;
+	return __strncpy_from_user(dst, src, count);
+}
 
 /*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue. No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
+ * Return the size of a string (including the ending 0)
  *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path. This means when everything is well,
- * we don't even have to jump over them. Further, they do not intrude
- * on our cache or tlb entries.
+ * Return 0 on exception, a value greater than N if too long
  */
-struct exception_table_entry {
-	unsigned long insn, fixup;
-};
+extern int __strnlen_user(const char __user *sstr, int len);
+
+static inline long strnlen_user(const char __user *src, long n)
+{
+	if (!access_ok(VERIFY_READ, src, 1))
+		return 0;
+	return __strnlen_user(src, n);
+}
 
 #endif  /* __ASSEMBLY__ */
 #endif /* __KERNEL__ */
diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c
index b108497..4d5b0311 100644
--- a/arch/microblaze/kernel/dma.c
+++ b/arch/microblaze/kernel/dma.c
@@ -37,7 +37,7 @@ static inline void __dma_sync_page(unsigned long paddr, unsigned long offset,
 
 static unsigned long get_dma_direct_offset(struct device *dev)
 {
-	if (dev)
+	if (likely(dev))
 		return (unsigned long)dev->archdata.dma_data;
 
 	return PCI_DRAM_OFFSET; /* FIXME Not sure if is correct */
diff --git a/arch/microblaze/kernel/head.S b/arch/microblaze/kernel/head.S
index cb7815c..da6a5f5 100644
--- a/arch/microblaze/kernel/head.S
+++ b/arch/microblaze/kernel/head.S
@@ -51,6 +51,12 @@ swapper_pg_dir:
 
 	.text
 ENTRY(_start)
+#if CONFIG_KERNEL_BASE_ADDR == 0
+	brai	TOPHYS(real_start)
+	.org	0x100
+real_start:
+#endif
+
 	mfs	r1, rmsr
 	andi	r1, r1, ~2
 	mts	rmsr, r1
@@ -99,8 +105,8 @@ no_fdt_arg:
 	tophys(r4,r4)			/* convert to phys address */
 	ori	r3, r0, COMMAND_LINE_SIZE - 1 /* number of loops */
 _copy_command_line:
-	lbu	r2, r5, r6 /* r7=r5+r6 - r5 contain pointer to command line */
-	sb	r2, r4, r6		/* addr[r4+r6]= r7*/
+	lbu	r2, r5, r6 /* r2=r5+r6 - r5 contain pointer to command line */
+	sb	r2, r4, r6		/* addr[r4+r6]= r2*/
 	addik	r6, r6, 1		/* increment counting */
 	bgtid	r3, _copy_command_line	/* loop for all entries       */
 	addik	r3, r3, -1		/* descrement loop */
@@ -128,7 +134,7 @@ _copy_bram:
 	 * virtual to physical.
 	 */
 	nop
-	addik	r3, r0, 63		/* Invalidate all TLB entries */
+	addik	r3, r0, MICROBLAZE_TLB_SIZE -1	/* Invalidate all TLB entries */
 _invalidate:
 	mts	rtlbx, r3
 	mts	rtlbhi, r0			/* flush: ensure V is clear   */
diff --git a/arch/microblaze/kernel/hw_exception_handler.S b/arch/microblaze/kernel/hw_exception_handler.S
index 2b86c03..995a212 100644
--- a/arch/microblaze/kernel/hw_exception_handler.S
+++ b/arch/microblaze/kernel/hw_exception_handler.S
@@ -313,13 +313,13 @@ _hw_exception_handler:
 	mfs	r5, rmsr;
 	nop
 	swi	r5, r1, 0;
-	mfs	r3, resr
+	mfs	r4, resr
 	nop
-	mfs	r4, rear;
+	mfs	r3, rear;
 	nop
 
 #ifndef CONFIG_MMU
-	andi	r5, r3, 0x1000;		/* Check ESR[DS] */
+	andi	r5, r4, 0x1000;		/* Check ESR[DS] */
 	beqi	r5, not_in_delay_slot;	/* Branch if ESR[DS] not set */
 	mfs	r17, rbtr;	/* ESR[DS] set - return address in BTR */
 	nop
@@ -327,13 +327,14 @@ not_in_delay_slot:
 	swi	r17, r1, PT_R17
 #endif
 
-	andi	r5, r3, 0x1F;		/* Extract ESR[EXC] */
+	andi	r5, r4, 0x1F;		/* Extract ESR[EXC] */
 
 #ifdef CONFIG_MMU
 	/* Calculate exception vector offset = r5 << 2 */
 	addk	r6, r5, r5; /* << 1 */
 	addk	r6, r6, r6; /* << 2 */
 
+#ifdef DEBUG
 /* counting which exception happen */
 	lwi	r5, r0, 0x200 + TOPHYS(r0_ram)
 	addi	r5, r5, 1
@@ -341,6 +342,7 @@ not_in_delay_slot:
 	lwi	r5, r6, 0x200 + TOPHYS(r0_ram)
 	addi	r5, r5, 1
 	swi	r5, r6, 0x200 + TOPHYS(r0_ram)
+#endif
 /* end */
 	/* Load the HW Exception vector */
 	lwi	r6, r6, TOPHYS(_MB_HW_ExceptionVectorTable)
@@ -376,7 +378,7 @@ handle_other_ex: /* Handle Other exceptions here */
 	swi	r18, r1, PT_R18
 
 	or	r5, r1, r0
-	andi	r6, r3, 0x1F; /* Load ESR[EC] */
+	andi	r6, r4, 0x1F; /* Load ESR[EC] */
 	lwi	r7, r0, PER_CPU(KM) /* MS: saving current kernel mode to regs */
 	swi	r7, r1, PT_MODE
 	mfs	r7, rfsr
@@ -426,11 +428,11 @@ handle_other_ex: /* Handle Other exceptions here */
  */
 handle_unaligned_ex:
 	/* Working registers already saved: R3, R4, R5, R6
-	 *  R3 = ESR
-	 *  R4 = EAR
+	 *  R4 = ESR
+	 *  R3 = EAR
 	 */
 #ifdef CONFIG_MMU
-	andi	r6, r3, 0x1000			/* Check ESR[DS] */
+	andi	r6, r4, 0x1000			/* Check ESR[DS] */
 	beqi	r6, _no_delayslot		/* Branch if ESR[DS] not set */
 	mfs	r17, rbtr;	/* ESR[DS] set - return address in BTR */
 	nop
@@ -439,7 +441,7 @@ _no_delayslot:
 	RESTORE_STATE;
 	bri	unaligned_data_trap
 #endif
-	andi	r6, r3, 0x3E0; /* Mask and extract the register operand */
+	andi	r6, r4, 0x3E0; /* Mask and extract the register operand */
 	srl	r6, r6; /* r6 >> 5 */
 	srl	r6, r6;
 	srl	r6, r6;
@@ -448,33 +450,33 @@ _no_delayslot:
 	/* Store the register operand in a temporary location */
 	sbi	r6, r0, TOPHYS(ex_reg_op);
 
-	andi	r6, r3, 0x400; /* Extract ESR[S] */
+	andi	r6, r4, 0x400; /* Extract ESR[S] */
 	bnei	r6, ex_sw;
 ex_lw:
-	andi	r6, r3, 0x800; /* Extract ESR[W] */
+	andi	r6, r4, 0x800; /* Extract ESR[W] */
 	beqi	r6, ex_lhw;
-	lbui	r5, r4, 0; /* Exception address in r4 */
+	lbui	r5, r3, 0; /* Exception address in r3 */
 	/* Load a word, byte-by-byte from destination address
 		and save it in tmp space */
 	sbi	r5, r0, TOPHYS(ex_tmp_data_loc_0);
-	lbui	r5, r4, 1;
+	lbui	r5, r3, 1;
 	sbi	r5, r0, TOPHYS(ex_tmp_data_loc_1);
-	lbui	r5, r4, 2;
+	lbui	r5, r3, 2;
 	sbi	r5, r0, TOPHYS(ex_tmp_data_loc_2);
-	lbui	r5, r4, 3;
+	lbui	r5, r3, 3;
 	sbi	r5, r0, TOPHYS(ex_tmp_data_loc_3);
-	/* Get the destination register value into r3 */
-	lwi	r3, r0, TOPHYS(ex_tmp_data_loc_0);
+	/* Get the destination register value into r4 */
+	lwi	r4, r0, TOPHYS(ex_tmp_data_loc_0);
 	bri	ex_lw_tail;
 ex_lhw:
-	lbui	r5, r4, 0; /* Exception address in r4 */
+	lbui	r5, r3, 0; /* Exception address in r3 */
 	/* Load a half-word, byte-by-byte from destination
 		address and save it in tmp space */
 	sbi	r5, r0, TOPHYS(ex_tmp_data_loc_0);
-	lbui	r5, r4, 1;
+	lbui	r5, r3, 1;
 	sbi	r5, r0, TOPHYS(ex_tmp_data_loc_1);
-	/* Get the destination register value into r3 */
-	lhui	r3, r0, TOPHYS(ex_tmp_data_loc_0);
+	/* Get the destination register value into r4 */
+	lhui	r4, r0, TOPHYS(ex_tmp_data_loc_0);
 ex_lw_tail:
 	/* Get the destination register number into r5 */
 	lbui	r5, r0, TOPHYS(ex_reg_op);
@@ -502,25 +504,25 @@ ex_sw_tail:
 	andi	r6, r6, 0x800; /* Extract ESR[W] */
 	beqi	r6, ex_shw;
 	/* Get the word - delay slot */
-	swi	r3, r0, TOPHYS(ex_tmp_data_loc_0);
+	swi	r4, r0, TOPHYS(ex_tmp_data_loc_0);
 	/* Store the word, byte-by-byte into destination address */
-	lbui	r3, r0, TOPHYS(ex_tmp_data_loc_0);
-	sbi	r3, r4, 0;
-	lbui	r3, r0, TOPHYS(ex_tmp_data_loc_1);
-	sbi	r3, r4, 1;
-	lbui	r3, r0, TOPHYS(ex_tmp_data_loc_2);
-	sbi	r3, r4, 2;
-	lbui	r3, r0, TOPHYS(ex_tmp_data_loc_3);
-	sbi	r3, r4, 3;
+	lbui	r4, r0, TOPHYS(ex_tmp_data_loc_0);
+	sbi	r4, r3, 0;
+	lbui	r4, r0, TOPHYS(ex_tmp_data_loc_1);
+	sbi	r4, r3, 1;
+	lbui	r4, r0, TOPHYS(ex_tmp_data_loc_2);
+	sbi	r4, r3, 2;
+	lbui	r4, r0, TOPHYS(ex_tmp_data_loc_3);
+	sbi	r4, r3, 3;
 	bri	ex_handler_done;
 
 ex_shw:
 	/* Store the lower half-word, byte-by-byte into destination address */
-	swi	r3, r0, TOPHYS(ex_tmp_data_loc_0);
-	lbui	r3, r0, TOPHYS(ex_tmp_data_loc_2);
-	sbi	r3, r4, 0;
-	lbui	r3, r0, TOPHYS(ex_tmp_data_loc_3);
-	sbi	r3, r4, 1;
+	swi	r4, r0, TOPHYS(ex_tmp_data_loc_0);
+	lbui	r4, r0, TOPHYS(ex_tmp_data_loc_2);
+	sbi	r4, r3, 0;
+	lbui	r4, r0, TOPHYS(ex_tmp_data_loc_3);
+	sbi	r4, r3, 1;
 ex_sw_end: /* Exception handling of store word, ends. */
 
 ex_handler_done:
@@ -560,21 +562,16 @@ ex_handler_done:
 		 */
 		mfs	r11, rpid
 		nop
-		bri	4
-		mfs	r3, rear		/* Get faulting address */
-		nop
 		/* If we are faulting a kernel address, we have to use the
 		 * kernel page tables.
 		 */
-		ori	r4, r0, CONFIG_KERNEL_START
-		cmpu	r4, r3, r4
-		bgti	r4, ex3
+		ori	r5, r0, CONFIG_KERNEL_START
+		cmpu	r5, r3, r5
+		bgti	r5, ex3
 		/* First, check if it was a zone fault (which means a user
 		 * tried to access a kernel or read-protected page - always
 		 * a SEGV). All other faults here must be stores, so no
 		 * need to check ESR_S as well. */
-		mfs	r4, resr
-		nop
 		andi	r4, r4, 0x800		/* ESR_Z - zone protection */
 		bnei	r4, ex2
 
@@ -589,8 +586,6 @@ ex_handler_done:
 		 * tried to access a kernel or read-protected page - always
 		 * a SEGV). All other faults here must be stores, so no
 		 * need to check ESR_S as well. */
-		mfs	r4, resr
-		nop
 		andi	r4, r4, 0x800		/* ESR_Z */
 		bnei	r4, ex2
 		/* get current task address */
@@ -665,8 +660,6 @@ ex_handler_done:
 		 * R3 = ESR
 		 */
 
-		mfs	r3, rear		/* Get faulting address */
-		nop
 		RESTORE_STATE;
 		bri	page_fault_instr_trap
 
@@ -677,18 +670,15 @@ ex_handler_done:
 	 */
 	handle_data_tlb_miss_exception:
 		/* Working registers already saved: R3, R4, R5, R6
-		 * R3 = ESR
+		 * R3 = EAR, R4 = ESR
 		 */
 		mfs	r11, rpid
 		nop
-		bri	4
-		mfs	r3, rear		/* Get faulting address */
-		nop
 
 		/* If we are faulting a kernel address, we have to use the
 		 * kernel page tables. */
-		ori	r4, r0, CONFIG_KERNEL_START
-		cmpu	r4, r3, r4
+		ori	r6, r0, CONFIG_KERNEL_START
+		cmpu	r4, r3, r6
 		bgti	r4, ex5
 		ori	r4, r0, swapper_pg_dir
 		mts	rpid, r0		/* TLB will have 0 TID */
@@ -731,9 +721,8 @@ ex_handler_done:
 		 * Many of these bits are software only. Bits we don't set
 		 * here we (properly should) assume have the appropriate value.
 		 */
+		brid	finish_tlb_load
 		andni	r4, r4, 0x0ce2		/* Make sure 20, 21 are zero */
-
-		bri	finish_tlb_load
 	ex7:
 		/* The bailout. Restore registers to pre-exception conditions
 		 * and call the heavyweights to help us out.
@@ -754,9 +743,6 @@ ex_handler_done:
 		 */
 		mfs	r11, rpid
 		nop
-		bri	4
-		mfs	r3, rear		/* Get faulting address */
-		nop
 
 		/* If we are faulting a kernel address, we have to use the
 		 * kernel page tables.
@@ -792,7 +778,7 @@ ex_handler_done:
 		lwi	r4, r5, 0		/* Get Linux PTE */
 
 		andi	r6, r4, _PAGE_PRESENT
-		beqi	r6, ex7
+		beqi	r6, ex10
 
 		ori	r4, r4, _PAGE_ACCESSED
 		swi	r4, r5, 0
@@ -805,9 +791,8 @@ ex_handler_done:
 		 * Many of these bits are software only. Bits we don't set
 		 * here we (properly should) assume have the appropriate value.
 		 */
+		brid	finish_tlb_load
 		andni	r4, r4, 0x0ce2		/* Make sure 20, 21 are zero */
-
-		bri	finish_tlb_load
 	ex10:
 		/* The bailout. Restore registers to pre-exception conditions
 		 * and call the heavyweights to help us out.
@@ -837,9 +822,9 @@ ex_handler_done:
 		andi	r5, r5, (MICROBLAZE_TLB_SIZE-1)
 		ori	r6, r0, 1
 		cmp	r31, r5, r6
-		blti	r31, sem
+		blti	r31, ex12
 		addik	r5, r6, 1
-	sem:
+	ex12:
 		/* MS: save back current TLB index */
 		swi	r5, r0, TOPHYS(tlb_index)
 
@@ -859,7 +844,6 @@ ex_handler_done:
 		nop
 
 		/* Done...restore registers and get out of here. */
-	ex12:
 		mts	rpid, r11
 		nop
 		bri 4
diff --git a/arch/microblaze/kernel/misc.S b/arch/microblaze/kernel/misc.S
index df16c62..7cf8649 100644
--- a/arch/microblaze/kernel/misc.S
+++ b/arch/microblaze/kernel/misc.S
@@ -26,9 +26,10 @@
  * We avoid flushing the pinned 0, 1 and possibly 2 entries.
  */
 .globl _tlbia;
+.type  _tlbia, @function
 .align 4;
 _tlbia:
-	addik	r12, r0, 63 /* flush all entries (63 - 3) */
+	addik	r12, r0, MICROBLAZE_TLB_SIZE - 1 /* flush all entries (63 - 3) */
 	/* isync */
 _tlbia_1:
 	mts	rtlbx, r12
@@ -41,11 +42,13 @@ _tlbia_1:
 	/* sync */
 	rtsd	r15, 8
 	nop
+	.size  _tlbia, . - _tlbia
 
 /*
  * Flush MMU TLB for a particular address (in r5)
  */
 .globl _tlbie;
+.type  _tlbie, @function
 .align 4;
 _tlbie:
 	mts	rtlbsx, r5 /* look up the address in TLB */
@@ -59,17 +62,20 @@ _tlbie_1:
 	rtsd	r15, 8
 	nop
 
+	.size  _tlbie, . - _tlbie
+
 /*
  * Allocate TLB entry for early console
  */
 .globl early_console_reg_tlb_alloc;
+.type  early_console_reg_tlb_alloc, @function
 .align 4;
 early_console_reg_tlb_alloc:
 	/*
 	 * Load a TLB entry for the UART, so that microblaze_progress() can use
 	 * the UARTs nice and early.  We use a 4k real==virtual mapping.
 	 */
-	ori	r4, r0, 63
+	ori	r4, r0, MICROBLAZE_TLB_SIZE - 1
 	mts	rtlbx, r4 /* TLB slot 2 */
 
 	or	r4,r5,r0
@@ -86,6 +92,8 @@ early_console_reg_tlb_alloc:
 	rtsd	r15, 8
 	nop
 
+	.size  early_console_reg_tlb_alloc, . - early_console_reg_tlb_alloc
+
 /*
  * Copy a whole page (4096 bytes).
  */
@@ -104,6 +112,7 @@ early_console_reg_tlb_alloc:
 #define DCACHE_LINE_BYTES (4 * 4)
 
 .globl copy_page;
+.type  copy_page, @function
 .align 4;
 copy_page:
 	ori	r11, r0, (PAGE_SIZE/DCACHE_LINE_BYTES) - 1
@@ -118,3 +127,5 @@ _copy_page_loop:
 	addik	r11, r11, -1
 	rtsd	r15, 8
 	nop
+
+	.size  copy_page, . - copy_page
diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c
index 812f1bf..09bed44 100644
--- a/arch/microblaze/kernel/process.c
+++ b/arch/microblaze/kernel/process.c
@@ -15,6 +15,7 @@
 #include <linux/bitops.h>
 #include <asm/system.h>
 #include <asm/pgalloc.h>
+#include <asm/uaccess.h> /* for USER_DS macros */
 #include <asm/cacheflush.h>
 
 void show_regs(struct pt_regs *regs)
@@ -74,7 +75,10 @@ __setup("hlt", hlt_setup);
 
 void default_idle(void)
 {
-	if (!hlt_counter) {
+	if (likely(hlt_counter)) {
+		while (!need_resched())
+			cpu_relax();
+	} else {
 		clear_thread_flag(TIF_POLLING_NRFLAG);
 		smp_mb__after_clear_bit();
 		local_irq_disable();
@@ -82,9 +86,7 @@ void default_idle(void)
 			cpu_sleep();
 		local_irq_enable();
 		set_thread_flag(TIF_POLLING_NRFLAG);
-	} else
-		while (!need_resched())
-			cpu_relax();
+	}
 }
 
 void cpu_idle(void)
diff --git a/arch/microblaze/kernel/setup.c b/arch/microblaze/kernel/setup.c
index f974ec7..17c98db 100644
--- a/arch/microblaze/kernel/setup.c
+++ b/arch/microblaze/kernel/setup.c
@@ -92,6 +92,12 @@ inline unsigned get_romfs_len(unsigned *addr)
 }
 #endif	/* CONFIG_MTD_UCLINUX_EBSS */
 
+#if defined(CONFIG_EARLY_PRINTK) && defined(CONFIG_SERIAL_UARTLITE_CONSOLE)
+#define eprintk early_printk
+#else
+#define eprintk printk
+#endif
+
 void __init machine_early_init(const char *cmdline, unsigned int ram,
 		unsigned int fdt, unsigned int msr)
 {
@@ -139,32 +145,32 @@ void __init machine_early_init(const char *cmdline, unsigned int ram,
 	setup_early_printk(NULL);
 #endif
 
-	early_printk("Ramdisk addr 0x%08x, ", ram);
+	eprintk("Ramdisk addr 0x%08x, ", ram);
 	if (fdt)
-		early_printk("FDT at 0x%08x\n", fdt);
+		eprintk("FDT at 0x%08x\n", fdt);
 	else
-		early_printk("Compiled-in FDT at 0x%08x\n",
+		eprintk("Compiled-in FDT at 0x%08x\n",
 					(unsigned int)_fdt_start);
 
 #ifdef CONFIG_MTD_UCLINUX
-	early_printk("Found romfs @ 0x%08x (0x%08x)\n",
+	eprintk("Found romfs @ 0x%08x (0x%08x)\n",
 			romfs_base, romfs_size);
-	early_printk("#### klimit %p ####\n", old_klimit);
+	eprintk("#### klimit %p ####\n", old_klimit);
 	BUG_ON(romfs_size < 0); /* What else can we do? */
 
-	early_printk("Moved 0x%08x bytes from 0x%08x to 0x%08x\n",
+	eprintk("Moved 0x%08x bytes from 0x%08x to 0x%08x\n",
 			romfs_size, romfs_base, (unsigned)&_ebss);
 
-	early_printk("New klimit: 0x%08x\n", (unsigned)klimit);
+	eprintk("New klimit: 0x%08x\n", (unsigned)klimit);
 #endif
 
 #if CONFIG_XILINX_MICROBLAZE0_USE_MSR_INSTR
 	if (msr)
-		early_printk("!!!Your kernel has setup MSR instruction but "
+		eprintk("!!!Your kernel has setup MSR instruction but "
 				"CPU don't have it %d\n", msr);
 #else
 	if (!msr)
-		early_printk("!!!Your kernel not setup MSR instruction but "
+		eprintk("!!!Your kernel not setup MSR instruction but "
 				"CPU have it %d\n", msr);
 #endif
 
diff --git a/arch/microblaze/kernel/traps.c b/arch/microblaze/kernel/traps.c
index eaaaf80..5e4570e 100644
--- a/arch/microblaze/kernel/traps.c
+++ b/arch/microblaze/kernel/traps.c
@@ -22,13 +22,11 @@ void trap_init(void)
 	__enable_hw_exceptions();
 }
 
-static int kstack_depth_to_print = 24;
+static unsigned long kstack_depth_to_print = 24;
 
 static int __init kstack_setup(char *s)
 {
-	kstack_depth_to_print = strict_strtoul(s, 0, NULL);
-
-	return 1;
+	return !strict_strtoul(s, 0, &kstack_depth_to_print);
 }
 __setup("kstack=", kstack_setup);
 
diff --git a/arch/microblaze/lib/Makefile b/arch/microblaze/lib/Makefile
index b579db0..4dfe47d 100644
--- a/arch/microblaze/lib/Makefile
+++ b/arch/microblaze/lib/Makefile
@@ -10,5 +10,4 @@ else
 lib-y += memcpy.o memmove.o
 endif
 
-lib-$(CONFIG_NO_MMU) += uaccess.o
-lib-$(CONFIG_MMU) += uaccess_old.o
+lib-y += uaccess_old.o
diff --git a/arch/microblaze/lib/fastcopy.S b/arch/microblaze/lib/fastcopy.S
index 02e3ab4..fdc48bb 100644
--- a/arch/microblaze/lib/fastcopy.S
+++ b/arch/microblaze/lib/fastcopy.S
@@ -30,8 +30,9 @@
  */
 
 #include <linux/linkage.h>
-
+	.text
 	.globl	memcpy
+	.type  memcpy, @function
 	.ent	memcpy
 
 memcpy:
@@ -345,9 +346,11 @@ a_done:
 	rtsd	r15, 8
 	nop
 
+.size  memcpy, . - memcpy
 .end memcpy
 /*----------------------------------------------------------------------------*/
 	.globl	memmove
+	.type  memmove, @function
 	.ent	memmove
 
 memmove:
@@ -659,4 +662,5 @@ d_done:
 	rtsd	r15, 8
 	nop
 
+.size  memmove, . - memmove
 .end memmove
diff --git a/arch/microblaze/lib/memcpy.c b/arch/microblaze/lib/memcpy.c
index cc2108b..014bac9 100644
--- a/arch/microblaze/lib/memcpy.c
+++ b/arch/microblaze/lib/memcpy.c
@@ -53,7 +53,7 @@ void *memcpy(void *v_dst, const void *v_src, __kernel_size_t c)
 	const uint32_t *i_src;
 	uint32_t *i_dst;
 
-	if (c >= 4) {
+	if (likely(c >= 4)) {
 		unsigned  value, buf_hold;
 
 		/* Align the dstination to a word boundry. */
diff --git a/arch/microblaze/lib/memset.c b/arch/microblaze/lib/memset.c
index 4df851d..ecfb663 100644
--- a/arch/microblaze/lib/memset.c
+++ b/arch/microblaze/lib/memset.c
@@ -33,22 +33,23 @@
 #ifdef __HAVE_ARCH_MEMSET
 void *memset(void *v_src, int c, __kernel_size_t n)
 {
-
 	char *src = v_src;
 #ifdef CONFIG_OPT_LIB_FUNCTION
 	uint32_t *i_src;
-	uint32_t w32;
+	uint32_t w32 = 0;
 #endif
 	/* Truncate c to 8 bits */
 	c = (c & 0xFF);
 
 #ifdef CONFIG_OPT_LIB_FUNCTION
-	/* Make a repeating word out of it */
-	w32 = c;
-	w32 |= w32 << 8;
-	w32 |= w32 << 16;
+	if (unlikely(c)) {
+		/* Make a repeating word out of it */
+		w32 = c;
+		w32 |= w32 << 8;
+		w32 |= w32 << 16;
+	}
 
-	if (n >= 4) {
+	if (likely(n >= 4)) {
 		/* Align the destination to a word boundary */
 		/* This is done in an endian independant manner */
 		switch ((unsigned) src & 3) {
diff --git a/arch/microblaze/lib/uaccess.c b/arch/microblaze/lib/uaccess.c
deleted file mode 100644
index a853fe0..0000000
--- a/arch/microblaze/lib/uaccess.c
+++ /dev/null
@@ -1,48 +0,0 @@
-/*
- * Copyright (C) 2006 Atmark Techno, Inc.
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-
-#include <linux/string.h>
-#include <asm/uaccess.h>
-
-#include <asm/bug.h>
-
-long strnlen_user(const char __user *src, long count)
-{
-	return strlen(src) + 1;
-}
-
-#define __do_strncpy_from_user(dst, src, count, res)			\
-	do {								\
-		char *tmp;						\
-		strncpy(dst, src, count);				\
-		for (tmp = dst; *tmp && count > 0; tmp++, count--)	\
-			;						\
-		res = (tmp - dst);					\
-	} while (0)
-
-long __strncpy_from_user(char *dst, const char __user *src, long count)
-{
-	long res;
-	__do_strncpy_from_user(dst, src, count, res);
-	return res;
-}
-
-long strncpy_from_user(char *dst, const char __user *src, long count)
-{
-	long res = -EFAULT;
-	if (access_ok(VERIFY_READ, src, 1))
-		__do_strncpy_from_user(dst, src, count, res);
-	return res;
-}
-
-unsigned long __copy_tofrom_user(void __user *to,
-		const void __user *from, unsigned long size)
-{
-	memcpy(to, from, size);
-	return 0;
-}
diff --git a/arch/microblaze/lib/uaccess_old.S b/arch/microblaze/lib/uaccess_old.S
index 67f991c..5810cec 100644
--- a/arch/microblaze/lib/uaccess_old.S
+++ b/arch/microblaze/lib/uaccess_old.S
@@ -22,6 +22,7 @@
 
 	.text
 .globl __strncpy_user;
+.type  __strncpy_user, @function
 .align 4;
 __strncpy_user:
 
@@ -50,7 +51,7 @@ __strncpy_user:
 3:
 	rtsd	r15,8
 	nop
-
+	.size   __strncpy_user, . - __strncpy_user
 
 	.section	.fixup, "ax"
 	.align	2
@@ -72,6 +73,7 @@ __strncpy_user:
 
 	.text
 .globl __strnlen_user;
+.type  __strnlen_user, @function
 .align 4;
 __strnlen_user:
 	addik	r3,r6,0
@@ -90,7 +92,7 @@ __strnlen_user:
 3:
 	rtsd	r15,8
 	nop
-
+	.size   __strnlen_user, . - __strnlen_user
 
 	.section	.fixup,"ax"
 4:
@@ -108,6 +110,7 @@ __strnlen_user:
  */
 	.text
 .globl __copy_tofrom_user;
+.type  __copy_tofrom_user, @function
 .align 4;
 __copy_tofrom_user:
 	/*
@@ -116,20 +119,34 @@ __copy_tofrom_user:
 	 * r7, r3 - count
 	 * r4 - tempval
 	 */
-	addik	r3,r7,0
-	beqi	r3,3f
-1:
-	lbu	r4,r6,r0
-	addik	r6,r6,1
-2:
-	sb	r4,r5,r0
-	addik	r3,r3,-1
-	bneid	r3,1b
-	addik	r5,r5,1		/* delay slot */
+	beqid	r7, 3f /* zero size is not likely */
+	andi	r3, r7, 0x3 /* filter add count */
+	bneid	r3, 4f /* if is odd value then byte copying */
+	or	r3, r5, r6 /* find if is any to/from unaligned */
+	andi	r3, r3, 0x3 /* mask unaligned */
+	bneid	r3, 1f /* it is unaligned -> then jump */
+	or	r3, r0, r0
+
+/* at least one 4 byte copy */
+5:	lw	r4, r6, r3
+6:	sw	r4, r5, r3
+	addik	r7, r7, -4
+	bneid	r7, 5b
+	addik	r3, r3, 4
+	addik	r3, r7, 0
+	rtsd	r15, 8
+	nop
+4:	or	r3, r0, r0
+1:	lbu	r4,r6,r3
+2:	sb	r4,r5,r3
+	addik	r7,r7,-1
+	bneid	r7,1b
+	addik	r3,r3,1		/* delay slot */
 3:
+	addik	r3,r7,0
 	rtsd	r15,8
 	nop
-
+	.size   __copy_tofrom_user, . - __copy_tofrom_user
 
 	.section	__ex_table,"a"
-	.word	1b,3b,2b,3b
+	.word	1b,3b,2b,3b,5b,3b,6b,3b
diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index d9d249a..7af87f4 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -106,7 +106,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 	regs->esr = error_code;
 
 	/* On a kernel SLB miss we can only check for a valid exception entry */
-	if (kernel_mode(regs) && (address >= TASK_SIZE)) {
+	if (unlikely(kernel_mode(regs) && (address >= TASK_SIZE))) {
 		printk(KERN_WARNING "kernel task_size exceed");
 		_exception(SIGSEGV, regs, code, address);
 	}
@@ -122,7 +122,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 	}
 #endif /* CONFIG_KGDB */
 
-	if (in_atomic() || !mm) {
+	if (unlikely(in_atomic() || !mm)) {
 		if (kernel_mode(regs))
 			goto bad_area_nosemaphore;
 
@@ -150,7 +150,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 	 * source.  If this is invalid we can skip the address space check,
 	 * thus avoiding the deadlock.
 	 */
-	if (!down_read_trylock(&mm->mmap_sem)) {
+	if (unlikely(!down_read_trylock(&mm->mmap_sem))) {
 		if (kernel_mode(regs) && !search_exception_tables(regs->pc))
 			goto bad_area_nosemaphore;
 
@@ -158,16 +158,16 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 	}
 
 	vma = find_vma(mm, address);
-	if (!vma)
+	if (unlikely(!vma))
 		goto bad_area;
 
 	if (vma->vm_start <= address)
 		goto good_area;
 
-	if (!(vma->vm_flags & VM_GROWSDOWN))
+	if (unlikely(!(vma->vm_flags & VM_GROWSDOWN)))
 		goto bad_area;
 
-	if (!is_write)
+	if (unlikely(!is_write))
 		goto bad_area;
 
 	/*
@@ -179,7 +179,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 	 * before setting the user r1.  Thus we allow the stack to
 	 * expand to 1MB without further checks.
 	 */
-	if (address + 0x100000 < vma->vm_end) {
+	if (unlikely(address + 0x100000 < vma->vm_end)) {
 
 		/* get user regs even if this fault is in kernel mode */
 		struct pt_regs *uregs = current->thread.regs;
@@ -209,15 +209,15 @@ good_area:
 	code = SEGV_ACCERR;
 
 	/* a write */
-	if (is_write) {
-		if (!(vma->vm_flags & VM_WRITE))
+	if (unlikely(is_write)) {
+		if (unlikely(!(vma->vm_flags & VM_WRITE)))
 			goto bad_area;
 	/* a read */
 	} else {
 		/* protection fault */
-		if (error_code & 0x08000000)
+		if (unlikely(error_code & 0x08000000))
 			goto bad_area;
-		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
+		if (unlikely(!(vma->vm_flags & (VM_READ | VM_EXEC))))
 			goto bad_area;
 	}
 
@@ -235,7 +235,7 @@ survive:
 			goto do_sigbus;
 		BUG();
 	}
-	if (fault & VM_FAULT_MAJOR)
+	if (unlikely(fault & VM_FAULT_MAJOR))
 		current->maj_flt++;
 	else
 		current->min_flt++;
diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
index 1608e2e..40bc10e 100644
--- a/arch/microblaze/mm/init.c
+++ b/arch/microblaze/mm/init.c
@@ -165,7 +165,6 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
 	for (addr = begin; addr < end; addr += PAGE_SIZE) {
 		ClearPageReserved(virt_to_page(addr));
 		init_page_count(virt_to_page(addr));
-		memset((void *)addr, 0xcc, PAGE_SIZE);
 		free_page(addr);
 		totalram_pages++;
 	}
@@ -208,14 +207,6 @@ void __init mem_init(void)
 }
 
 #ifndef CONFIG_MMU
-/* Check against bounds of physical memory */
-int ___range_ok(unsigned long addr, unsigned long size)
-{
-	return ((addr < memory_start) ||
-		((addr + size) > memory_end));
-}
-EXPORT_SYMBOL(___range_ok);
-
 int page_is_ram(unsigned long pfn)
 {
 	return __range_ok(pfn, 0);
diff --git a/arch/microblaze/mm/pgtable.c b/arch/microblaze/mm/pgtable.c
index 63a6fd0..d31312c 100644
--- a/arch/microblaze/mm/pgtable.c
+++ b/arch/microblaze/mm/pgtable.c
@@ -154,7 +154,7 @@ int map_page(unsigned long va, phys_addr_t pa, int flags)
 		err = 0;
 		set_pte_at(&init_mm, va, pg, pfn_pte(pa >> PAGE_SHIFT,
 				__pgprot(flags)));
-		if (mem_init_done)
+		if (unlikely(mem_init_done))
 			flush_HPTE(0, va, pmd_val(*pd));
 			/* flush_HPTE(0, va, pg); */
 	}
diff --git a/arch/powerpc/include/asm/asm-compat.h b/arch/powerpc/include/asm/asm-compat.h
index c1b475a..a9b91ed 100644
--- a/arch/powerpc/include/asm/asm-compat.h
+++ b/arch/powerpc/include/asm/asm-compat.h
@@ -28,6 +28,7 @@
 #define PPC_LLARX(t, a, b, eh)	PPC_LDARX(t, a, b, eh)
 #define PPC_STLCX	stringify_in_c(stdcx.)
 #define PPC_CNTLZL	stringify_in_c(cntlzd)
+#define PPC_LR_STKOFF	16
 
 /* Move to CR, single-entry optimized version. Only available
  * on POWER4 and later.
@@ -51,6 +52,7 @@
 #define PPC_STLCX	stringify_in_c(stwcx.)
 #define PPC_CNTLZL	stringify_in_c(cntlzw)
 #define PPC_MTOCRF	stringify_in_c(mtcrf)
+#define PPC_LR_STKOFF	4
 
 #endif
 
diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S
index 2d29752..22e507c 100644
--- a/arch/powerpc/kernel/misc.S
+++ b/arch/powerpc/kernel/misc.S
@@ -127,3 +127,29 @@ _GLOBAL(__setup_cpu_power7)
 _GLOBAL(__restore_cpu_power7)
 	/* place holder */
 	blr
+
+/*
+ * Get a minimal set of registers for our caller's nth caller.
+ * r3 = regs pointer, r5 = n.
+ *
+ * We only get R1 (stack pointer), NIP (next instruction pointer)
+ * and LR (link register).  These are all we can get in the
+ * general case without doing complicated stack unwinding, but
+ * fortunately they are enough to do a stack backtrace, which
+ * is all we need them for.
+ */
+_GLOBAL(perf_arch_fetch_caller_regs)
+	mr	r6,r1
+	cmpwi	r5,0
+	mflr	r4
+	ble	2f
+	mtctr	r5
+1:	PPC_LL	r6,0(r6)
+	bdnz	1b
+	PPC_LL	r4,PPC_LR_STKOFF(r6)
+2:	PPC_LL	r7,0(r6)
+	PPC_LL	r7,PPC_LR_STKOFF(r7)
+	PPC_STL	r6,GPR1-STACK_FRAME_OVERHEAD(r3)
+	PPC_STL	r4,_NIP-STACK_FRAME_OVERHEAD(r3)
+	PPC_STL	r7,_LINK-STACK_FRAME_OVERHEAD(r3)
+	blr
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c
index 929d017..d4f8be3 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c
@@ -481,6 +481,8 @@ mpc52xx_lpbfifo_probe(struct of_device *op, const struct of_device_id *match)
 	if (rc)
 		goto err_bcom_rx_irq;
 
+	lpbfifo.dma_irqs_enabled = 1;
+
 	/* Request the Bestcomm transmit (memory --> fifo) task and IRQ */
 	lpbfifo.bcom_tx_task =
 		bcom_gen_bd_tx_init(2, res.start + LPBFIFO_REG_FIFO_DATA,
diff --git a/arch/sh/kernel/return_address.c b/arch/sh/kernel/return_address.c
index df3ab58..cbf1dd5 100644
--- a/arch/sh/kernel/return_address.c
+++ b/arch/sh/kernel/return_address.c
@@ -9,6 +9,7 @@
  * for more details.
  */
 #include <linux/kernel.h>
+#include <linux/module.h>
 #include <asm/dwarf.h>
 
 #ifdef CONFIG_DWARF_UNWINDER
@@ -52,3 +53,5 @@ void *return_address(unsigned int depth)
 }
 
 #endif
+
+EXPORT_SYMBOL_GPL(return_address);
diff --git a/arch/sh/mm/tlb-pteaex.c b/arch/sh/mm/tlb-pteaex.c
index bdd0982..b71db6a 100644
--- a/arch/sh/mm/tlb-pteaex.c
+++ b/arch/sh/mm/tlb-pteaex.c
@@ -77,3 +77,31 @@ void local_flush_tlb_one(unsigned long asid, unsigned long page)
 	__raw_writel(asid, MMU_ITLB_ADDRESS_ARRAY2 | MMU_PAGE_ASSOC_BIT);
 	back_to_cached();
 }
+
+void local_flush_tlb_all(void)
+{
+	unsigned long flags, status;
+	int i;
+
+	/*
+	 * Flush all the TLB.
+	 */
+	local_irq_save(flags);
+	jump_to_uncached();
+
+	status = __raw_readl(MMUCR);
+	status = ((status & MMUCR_URB) >> MMUCR_URB_SHIFT);
+
+	if (status == 0)
+		status = MMUCR_URB_NENTRIES;
+
+	for (i = 0; i < status; i++)
+		__raw_writel(0x0, MMU_UTLB_ADDRESS_ARRAY | (i << 8));
+
+	for (i = 0; i < 4; i++)
+		__raw_writel(0x0, MMU_ITLB_ADDRESS_ARRAY | (i << 8));
+
+	back_to_cached();
+	ctrl_barrier();
+	local_irq_restore(flags);
+}
diff --git a/arch/sh/mm/tlb-sh3.c b/arch/sh/mm/tlb-sh3.c
index 4f5f7cb..7a940db 100644
--- a/arch/sh/mm/tlb-sh3.c
+++ b/arch/sh/mm/tlb-sh3.c
@@ -77,3 +77,22 @@ void local_flush_tlb_one(unsigned long asid, unsigned long page)
 	for (i = 0; i < ways; i++)
 		__raw_writel(data, addr + (i << 8));
 }
+
+void local_flush_tlb_all(void)
+{
+	unsigned long flags, status;
+
+	/*
+	 * Flush all the TLB.
+	 *
+	 * Write to the MMU control register's bit:
+	 *	TF-bit for SH-3, TI-bit for SH-4.
+	 *      It's same position, bit #2.
+	 */
+	local_irq_save(flags);
+	status = __raw_readl(MMUCR);
+	status |= 0x04;
+	__raw_writel(status, MMUCR);
+	ctrl_barrier();
+	local_irq_restore(flags);
+}
diff --git a/arch/sh/mm/tlb-sh4.c b/arch/sh/mm/tlb-sh4.c
index ccac77f..cfdf793 100644
--- a/arch/sh/mm/tlb-sh4.c
+++ b/arch/sh/mm/tlb-sh4.c
@@ -80,3 +80,31 @@ void local_flush_tlb_one(unsigned long asid, unsigned long page)
 	__raw_writel(data, addr);
 	back_to_cached();
 }
+
+void local_flush_tlb_all(void)
+{
+	unsigned long flags, status;
+	int i;
+
+	/*
+	 * Flush all the TLB.
+	 */
+	local_irq_save(flags);
+	jump_to_uncached();
+
+	status = __raw_readl(MMUCR);
+	status = ((status & MMUCR_URB) >> MMUCR_URB_SHIFT);
+
+	if (status == 0)
+		status = MMUCR_URB_NENTRIES;
+
+	for (i = 0; i < status; i++)
+		__raw_writel(0x0, MMU_UTLB_ADDRESS_ARRAY | (i << 8));
+
+	for (i = 0; i < 4; i++)
+		__raw_writel(0x0, MMU_ITLB_ADDRESS_ARRAY | (i << 8));
+
+	back_to_cached();
+	ctrl_barrier();
+	local_irq_restore(flags);
+}
diff --git a/arch/sh/mm/tlbflush_32.c b/arch/sh/mm/tlbflush_32.c
index 77dc5ef..3fbe03c 100644
--- a/arch/sh/mm/tlbflush_32.c
+++ b/arch/sh/mm/tlbflush_32.c
@@ -119,31 +119,3 @@ void local_flush_tlb_mm(struct mm_struct *mm)
 		local_irq_restore(flags);
 	}
 }
-
-void local_flush_tlb_all(void)
-{
-	unsigned long flags, status;
-	int i;
-
-	/*
-	 * Flush all the TLB.
-	 */
-	local_irq_save(flags);
-	jump_to_uncached();
-
-	status = __raw_readl(MMUCR);
-	status = ((status & MMUCR_URB) >> MMUCR_URB_SHIFT);
-
-	if (status == 0)
-		status = MMUCR_URB_NENTRIES;
-
-	for (i = 0; i < status; i++)
-		__raw_writel(0x0, MMU_UTLB_ADDRESS_ARRAY | (i << 8));
-
-	for (i = 0; i < 4; i++)
-		__raw_writel(0x0, MMU_ITLB_ADDRESS_ARRAY | (i << 8));
-
-	back_to_cached();
-	ctrl_barrier();
-	local_irq_restore(flags);
-}
diff --git a/arch/sparc/configs/sparc64_defconfig b/arch/sparc/configs/sparc64_defconfig
index 56e3163..259e3fd 100644
--- a/arch/sparc/configs/sparc64_defconfig
+++ b/arch/sparc/configs/sparc64_defconfig
@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.33
-# Wed Mar  3 02:54:29 2010
+# Linux kernel version: 2.6.34-rc3
+# Sat Apr  3 15:49:56 2010
 #
 CONFIG_64BIT=y
 CONFIG_SPARC=y
@@ -23,6 +23,7 @@ CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK=y
 CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK=y
 CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y
 CONFIG_MMU=y
+CONFIG_NEED_DMA_MAP_STATE=y
 CONFIG_ARCH_NO_VIRT_TO_BUS=y
 CONFIG_OF=y
 CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC=y
@@ -439,6 +440,7 @@ CONFIG_MISC_DEVICES=y
 # CONFIG_ENCLOSURE_SERVICES is not set
 # CONFIG_HP_ILO is not set
 # CONFIG_ISL29003 is not set
+# CONFIG_SENSORS_TSL2550 is not set
 # CONFIG_DS1682 is not set
 # CONFIG_C2PORT is not set
 
@@ -511,6 +513,7 @@ CONFIG_BLK_DEV_IDEDMA=y
 #
 # SCSI device support
 #
+CONFIG_SCSI_MOD=y
 CONFIG_RAID_ATTRS=m
 CONFIG_SCSI=y
 CONFIG_SCSI_DMA=y
@@ -888,6 +891,7 @@ CONFIG_SERIAL_SUNHV=y
 CONFIG_SERIAL_CORE=y
 CONFIG_SERIAL_CORE_CONSOLE=y
 # CONFIG_SERIAL_JSM is not set
+# CONFIG_SERIAL_TIMBERDALE is not set
 # CONFIG_SERIAL_GRLIB_GAISLER_APBUART is not set
 CONFIG_UNIX98_PTYS=y
 # CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set
@@ -935,6 +939,7 @@ CONFIG_I2C_ALGOBIT=y
 #
 # CONFIG_I2C_OCORES is not set
 # CONFIG_I2C_SIMTEC is not set
+# CONFIG_I2C_XILINX is not set
 
 #
 # External I2C/SMBus adapter drivers
@@ -948,15 +953,9 @@ CONFIG_I2C_ALGOBIT=y
 #
 # CONFIG_I2C_PCA_PLATFORM is not set
 # CONFIG_I2C_STUB is not set
-
-#
-# Miscellaneous I2C Chip support
-#
-# CONFIG_SENSORS_TSL2550 is not set
 # CONFIG_I2C_DEBUG_CORE is not set
 # CONFIG_I2C_DEBUG_ALGO is not set
 # CONFIG_I2C_DEBUG_BUS is not set
-# CONFIG_I2C_DEBUG_CHIP is not set
 # CONFIG_SPI is not set
 
 #
@@ -982,10 +981,11 @@ CONFIG_HWMON=y
 # CONFIG_SENSORS_ADM1029 is not set
 # CONFIG_SENSORS_ADM1031 is not set
 # CONFIG_SENSORS_ADM9240 is not set
+# CONFIG_SENSORS_ADT7411 is not set
 # CONFIG_SENSORS_ADT7462 is not set
 # CONFIG_SENSORS_ADT7470 is not set
-# CONFIG_SENSORS_ADT7473 is not set
 # CONFIG_SENSORS_ADT7475 is not set
+# CONFIG_SENSORS_ASC7621 is not set
 # CONFIG_SENSORS_ATXP1 is not set
 # CONFIG_SENSORS_DS1621 is not set
 # CONFIG_SENSORS_I5K_AMB is not set
@@ -1052,18 +1052,21 @@ CONFIG_SSB_POSSIBLE=y
 # Multifunction device drivers
 #
 # CONFIG_MFD_CORE is not set
+# CONFIG_MFD_88PM860X is not set
 # CONFIG_MFD_SM501 is not set
 # CONFIG_HTC_PASIC3 is not set
 # CONFIG_TWL4030_CORE is not set
 # CONFIG_MFD_TMIO is not set
 # CONFIG_PMIC_DA903X is not set
 # CONFIG_PMIC_ADP5520 is not set
+# CONFIG_MFD_MAX8925 is not set
 # CONFIG_MFD_WM8400 is not set
 # CONFIG_MFD_WM831X is not set
 # CONFIG_MFD_WM8350_I2C is not set
+# CONFIG_MFD_WM8994 is not set
 # CONFIG_MFD_PCF50633 is not set
 # CONFIG_AB3100_CORE is not set
-# CONFIG_MFD_88PM8607 is not set
+# CONFIG_LPC_SCH is not set
 # CONFIG_REGULATOR is not set
 # CONFIG_MEDIA_SUPPORT is not set
 
@@ -1113,6 +1116,7 @@ CONFIG_FB_FFB=y
 # CONFIG_FB_LEO is not set
 CONFIG_FB_XVR500=y
 CONFIG_FB_XVR2500=y
+CONFIG_FB_XVR1000=y
 # CONFIG_FB_S1D13XXX is not set
 # CONFIG_FB_NVIDIA is not set
 # CONFIG_FB_RIVA is not set
@@ -1430,7 +1434,6 @@ CONFIG_USB_STORAGE=m
 # CONFIG_USB_RIO500 is not set
 # CONFIG_USB_LEGOTOWER is not set
 # CONFIG_USB_LCD is not set
-# CONFIG_USB_BERRY_CHARGE is not set
 # CONFIG_USB_LED is not set
 # CONFIG_USB_CYPRESS_CY7C63 is not set
 # CONFIG_USB_CYTHERM is not set
@@ -1443,7 +1446,6 @@ CONFIG_USB_STORAGE=m
 # CONFIG_USB_IOWARRIOR is not set
 # CONFIG_USB_TEST is not set
 # CONFIG_USB_ISIGHTFW is not set
-# CONFIG_USB_VST is not set
 # CONFIG_USB_GADGET is not set
 
 #
@@ -1610,6 +1612,7 @@ CONFIG_MISC_FILESYSTEMS=y
 # CONFIG_BEFS_FS is not set
 # CONFIG_BFS_FS is not set
 # CONFIG_EFS_FS is not set
+# CONFIG_LOGFS is not set
 # CONFIG_CRAMFS is not set
 # CONFIG_SQUASHFS is not set
 # CONFIG_VXFS_FS is not set
@@ -1624,6 +1627,7 @@ CONFIG_NETWORK_FILESYSTEMS=y
 # CONFIG_NFS_FS is not set
 # CONFIG_NFSD is not set
 # CONFIG_SMB_FS is not set
+# CONFIG_CEPH_FS is not set
 # CONFIG_CIFS is not set
 # CONFIG_NCP_FS is not set
 # CONFIG_CODA_FS is not set
diff --git a/arch/sparc/include/asm/stat.h b/arch/sparc/include/asm/stat.h
index 39327d6..a232e9e 100644
--- a/arch/sparc/include/asm/stat.h
+++ b/arch/sparc/include/asm/stat.h
@@ -53,8 +53,8 @@ struct stat {
 	ino_t		st_ino;
 	mode_t		st_mode;
 	short		st_nlink;
-	uid16_t		st_uid;
-	gid16_t		st_gid;
+	unsigned short	st_uid;
+	unsigned short	st_gid;
 	unsigned short	st_rdev;
 	off_t		st_size;
 	time_t		st_atime;
diff --git a/arch/sparc/kernel/helpers.S b/arch/sparc/kernel/helpers.S
index 314dd0c..92090cc 100644
--- a/arch/sparc/kernel/helpers.S
+++ b/arch/sparc/kernel/helpers.S
@@ -46,6 +46,81 @@ stack_trace_flush:
 	 nop
 	.size		stack_trace_flush,.-stack_trace_flush
 
+#ifdef CONFIG_PERF_EVENTS
+	.globl		perf_arch_fetch_caller_regs
+	.type		perf_arch_fetch_caller_regs,#function
+perf_arch_fetch_caller_regs:
+	/* We always read the %pstate into %o5 since we will use
+	 * that to construct a fake %tstate to store into the regs.
+	 */
+	rdpr		%pstate, %o5
+	brz,pn		%o2, 50f
+	 mov		%o2, %g7
+
+	/* Turn off interrupts while we walk around the register
+	 * window by hand.
+	 */
+	wrpr		%o5, PSTATE_IE, %pstate
+
+	/* The %canrestore tells us how many register windows are
+	 * still live in the chip above us, past that we have to
+	 * walk the frame as saved on the stack.   We stash away
+	 * the %cwp in %g1 so we can return back to the original
+	 * register window.
+	 */
+	rdpr		%cwp, %g1
+	rdpr		%canrestore, %g2
+	sub		%g1, 1, %g3
+
+	/* We have the skip count in %g7, if it hits zero then
+	 * %fp/%i7 are the registers we need.  Otherwise if our
+	 * %canrestore count maintained in %g2 hits zero we have
+	 * to start traversing the stack.
+	 */
+10:	brz,pn		%g2, 4f
+	 sub		%g2, 1, %g2
+	wrpr		%g3, %cwp
+	subcc		%g7, 1, %g7
+	bne,pt		%xcc, 10b
+	 sub		%g3, 1, %g3
+
+	/* We found the values we need in the cpu's register
+	 * windows.
+	 */
+	mov		%fp, %g3
+	ba,pt		%xcc, 3f
+	 mov		%i7, %g2
+
+50:	mov		%fp, %g3
+	ba,pt		%xcc, 2f
+	 mov		%i7, %g2
+
+	/* We hit the end of the valid register windows in the
+	 * cpu, start traversing the stack frame.
+	 */
+4:	mov		%fp, %g3
+
+20:	ldx		[%g3 + STACK_BIAS + RW_V9_I7], %g2
+	subcc		%g7, 1, %g7
+	bne,pn		%xcc, 20b
+	 ldx		[%g3 + STACK_BIAS + RW_V9_I6], %g3
+
+	/* Restore the current register window position and
+	 * re-enable interrupts.
+	 */
+3:	wrpr		%g1, %cwp
+	wrpr		%o5, %pstate
+
+2:	stx		%g3, [%o0 + PT_V9_FP]
+	sllx		%o5, 8, %o5
+	stx		%o5, [%o0 + PT_V9_TSTATE]
+	stx		%g2, [%o0 + PT_V9_TPC]
+	add		%g2, 4, %g2
+	retl
+	 stx		%g2, [%o0 + PT_V9_TNPC]
+	.size		perf_arch_fetch_caller_regs,.-perf_arch_fetch_caller_regs
+#endif /* CONFIG_PERF_EVENTS */
+
 #ifdef CONFIG_SMP
 	.globl		hard_smp_processor_id
 	.type		hard_smp_processor_id,#function
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 68cb9b4..e277193 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1337,7 +1337,7 @@ static void perf_callchain_user_32(struct pt_regs *regs,
 	callchain_store(entry, PERF_CONTEXT_USER);
 	callchain_store(entry, regs->tpc);
 
-	ufp = regs->u_regs[UREG_I6];
+	ufp = regs->u_regs[UREG_I6] & 0xffffffffUL;
 	do {
 		struct sparc_stackf32 *usf, sf;
 		unsigned long pc;
diff --git a/arch/sparc/kernel/ptrace_32.c b/arch/sparc/kernel/ptrace_32.c
index 7e3dfd9..e608f39 100644
--- a/arch/sparc/kernel/ptrace_32.c
+++ b/arch/sparc/kernel/ptrace_32.c
@@ -65,6 +65,7 @@ static int genregs32_get(struct task_struct *target,
 			*k++ = regs->u_regs[pos++];
 
 		reg_window = (unsigned long __user *) regs->u_regs[UREG_I6];
+		reg_window -= 16;
 		for (; count > 0 && pos < 32; count--) {
 			if (get_user(*k++, &reg_window[pos++]))
 				return -EFAULT;
@@ -76,6 +77,7 @@ static int genregs32_get(struct task_struct *target,
 		}
 
 		reg_window = (unsigned long __user *) regs->u_regs[UREG_I6];
+		reg_window -= 16;
 		for (; count > 0 && pos < 32; count--) {
 			if (get_user(reg, &reg_window[pos++]) ||
 			    put_user(reg, u++))
@@ -141,6 +143,7 @@ static int genregs32_set(struct task_struct *target,
 			regs->u_regs[pos++] = *k++;
 
 		reg_window = (unsigned long __user *) regs->u_regs[UREG_I6];
+		reg_window -= 16;
 		for (; count > 0 && pos < 32; count--) {
 			if (put_user(*k++, &reg_window[pos++]))
 				return -EFAULT;
@@ -153,6 +156,7 @@ static int genregs32_set(struct task_struct *target,
 		}
 
 		reg_window = (unsigned long __user *) regs->u_regs[UREG_I6];
+		reg_window -= 16;
 		for (; count > 0 && pos < 32; count--) {
 			if (get_user(reg, u++) ||
 			    put_user(reg, &reg_window[pos++]))
diff --git a/arch/sparc/kernel/ptrace_64.c b/arch/sparc/kernel/ptrace_64.c
index 2f6524d..aa90da0 100644
--- a/arch/sparc/kernel/ptrace_64.c
+++ b/arch/sparc/kernel/ptrace_64.c
@@ -492,6 +492,7 @@ static int genregs32_get(struct task_struct *target,
 			*k++ = regs->u_regs[pos++];
 
 		reg_window = (compat_ulong_t __user *) regs->u_regs[UREG_I6];
+		reg_window -= 16;
 		if (target == current) {
 			for (; count > 0 && pos < 32; count--) {
 				if (get_user(*k++, &reg_window[pos++]))
@@ -516,6 +517,7 @@ static int genregs32_get(struct task_struct *target,
 		}
 
 		reg_window = (compat_ulong_t __user *) regs->u_regs[UREG_I6];
+		reg_window -= 16;
 		if (target == current) {
 			for (; count > 0 && pos < 32; count--) {
 				if (get_user(reg, &reg_window[pos++]) ||
@@ -599,6 +601,7 @@ static int genregs32_set(struct task_struct *target,
 			regs->u_regs[pos++] = *k++;
 
 		reg_window = (compat_ulong_t __user *) regs->u_regs[UREG_I6];
+		reg_window -= 16;
 		if (target == current) {
 			for (; count > 0 && pos < 32; count--) {
 				if (put_user(*k++, &reg_window[pos++]))
@@ -625,6 +628,7 @@ static int genregs32_set(struct task_struct *target,
 		}
 
 		reg_window = (compat_ulong_t __user *) regs->u_regs[UREG_I6];
+		reg_window -= 16;
 		if (target == current) {
 			for (; count > 0 && pos < 32; count--) {
 				if (get_user(reg, u++) ||
diff --git a/arch/sparc/kernel/sysfs.c b/arch/sparc/kernel/sysfs.c
index ca39c60..1eb8b00 100644
--- a/arch/sparc/kernel/sysfs.c
+++ b/arch/sparc/kernel/sysfs.c
@@ -107,12 +107,12 @@ static unsigned long run_on_cpu(unsigned long cpu,
 	unsigned long ret;
 
 	/* should return -EINVAL to userspace */
-	if (set_cpus_allowed(current, cpumask_of_cpu(cpu)))
+	if (set_cpus_allowed_ptr(current, cpumask_of(cpu)))
 		return 0;
 
 	ret = func(arg);
 
-	set_cpus_allowed(current, old_affinity);
+	set_cpus_allowed_ptr(current, &old_affinity);
 
 	return ret;
 }
diff --git a/arch/sparc/kernel/us2e_cpufreq.c b/arch/sparc/kernel/us2e_cpufreq.c
index 791c151..8f982b7 100644
--- a/arch/sparc/kernel/us2e_cpufreq.c
+++ b/arch/sparc/kernel/us2e_cpufreq.c
@@ -238,12 +238,12 @@ static unsigned int us2e_freq_get(unsigned int cpu)
 		return 0;
 
 	cpus_allowed = current->cpus_allowed;
-	set_cpus_allowed(current, cpumask_of_cpu(cpu));
+	set_cpus_allowed_ptr(current, cpumask_of(cpu));
 
 	clock_tick = sparc64_get_clock_tick(cpu) / 1000;
 	estar = read_hbreg(HBIRD_ESTAR_MODE_ADDR);
 
-	set_cpus_allowed(current, cpus_allowed);
+	set_cpus_allowed_ptr(current, &cpus_allowed);
 
 	return clock_tick / estar_to_divisor(estar);
 }
@@ -259,7 +259,7 @@ static void us2e_set_cpu_divider_index(unsigned int cpu, unsigned int index)
 		return;
 
 	cpus_allowed = current->cpus_allowed;
-	set_cpus_allowed(current, cpumask_of_cpu(cpu));
+	set_cpus_allowed_ptr(current, cpumask_of(cpu));
 
 	new_freq = clock_tick = sparc64_get_clock_tick(cpu) / 1000;
 	new_bits = index_to_estar_mode(index);
@@ -281,7 +281,7 @@ static void us2e_set_cpu_divider_index(unsigned int cpu, unsigned int index)
 
 	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
 
-	set_cpus_allowed(current, cpus_allowed);
+	set_cpus_allowed_ptr(current, &cpus_allowed);
 }
 
 static int us2e_freq_target(struct cpufreq_policy *policy,
diff --git a/arch/sparc/kernel/us3_cpufreq.c b/arch/sparc/kernel/us3_cpufreq.c
index 365b646..f35d1e7 100644
--- a/arch/sparc/kernel/us3_cpufreq.c
+++ b/arch/sparc/kernel/us3_cpufreq.c
@@ -86,12 +86,12 @@ static unsigned int us3_freq_get(unsigned int cpu)
 		return 0;
 
 	cpus_allowed = current->cpus_allowed;
-	set_cpus_allowed(current, cpumask_of_cpu(cpu));
+	set_cpus_allowed_ptr(current, cpumask_of(cpu));
 
 	reg = read_safari_cfg();
 	ret = get_current_freq(cpu, reg);
 
-	set_cpus_allowed(current, cpus_allowed);
+	set_cpus_allowed_ptr(current, &cpus_allowed);
 
 	return ret;
 }
@@ -106,7 +106,7 @@ static void us3_set_cpu_divider_index(unsigned int cpu, unsigned int index)
 		return;
 
 	cpus_allowed = current->cpus_allowed;
-	set_cpus_allowed(current, cpumask_of_cpu(cpu));
+	set_cpus_allowed_ptr(current, cpumask_of(cpu));
 
 	new_freq = sparc64_get_clock_tick(cpu) / 1000;
 	switch (index) {
@@ -140,7 +140,7 @@ static void us3_set_cpu_divider_index(unsigned int cpu, unsigned int index)
 
 	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
 
-	set_cpus_allowed(current, cpus_allowed);
+	set_cpus_allowed_ptr(current, &cpus_allowed);
 }
 
 static int us3_freq_target(struct cpufreq_policy *policy,
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 9245a82..20beb80 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -2117,7 +2117,7 @@ int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node)
 			       "node=%d entry=%lu/%lu\n", start, block, nr,
 			       node,
 			       addr >> VMEMMAP_CHUNK_SHIFT,
-			       VMEMMAP_SIZE >> VMEMMAP_CHUNK_SHIFT);
+			       VMEMMAP_SIZE);
 		}
 	}
 	return 0;
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 635f03b..d07b44f 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -82,6 +82,9 @@ enum fixed_addresses {
 #endif
 	FIX_DBGP_BASE,
 	FIX_EARLYCON_MEM_BASE,
+#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
+	FIX_OHCI1394_BASE,
+#endif
 #ifdef CONFIG_X86_LOCAL_APIC
 	FIX_APIC_BASE,	/* local (CPU) APIC) -- required for SMP or not */
 #endif
@@ -132,9 +135,6 @@ enum fixed_addresses {
 	   (__end_of_permanent_fixed_addresses & (TOTAL_FIX_BTMAPS - 1))
 	 : __end_of_permanent_fixed_addresses,
 	FIX_BTMAP_BEGIN = FIX_BTMAP_END + TOTAL_FIX_BTMAPS - 1,
-#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
-	FIX_OHCI1394_BASE,
-#endif
 #ifdef CONFIG_X86_32
 	FIX_WP_TEST,
 #endif
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index a929c9e..46c0fe0 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -133,6 +133,7 @@ extern void (*__initconst interrupt[NR_VECTORS-FIRST_EXTERNAL_VECTOR])(void);
 
 typedef int vector_irq_t[NR_VECTORS];
 DECLARE_PER_CPU(vector_irq_t, vector_irq);
+extern void setup_vector_irq(int cpu);
 
 #ifdef CONFIG_X86_IO_APIC
 extern void lock_vector_lock(void);
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 1cd58cd..4604e6a 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -105,6 +105,8 @@
 #define MSR_AMD64_PATCH_LEVEL		0x0000008b
 #define MSR_AMD64_NB_CFG		0xc001001f
 #define MSR_AMD64_PATCH_LOADER		0xc0010020
+#define MSR_AMD64_OSVW_ID_LENGTH	0xc0010140
+#define MSR_AMD64_OSVW_STATUS		0xc0010141
 #define MSR_AMD64_IBSFETCHCTL		0xc0011030
 #define MSR_AMD64_IBSFETCHLINAD		0xc0011031
 #define MSR_AMD64_IBSFETCHPHYSAD	0xc0011032
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index e4e0ddc..463de9a 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1268,6 +1268,14 @@ void __setup_vector_irq(int cpu)
 	/* Mark the inuse vectors */
 	for_each_irq_desc(irq, desc) {
 		cfg = desc->chip_data;
+
+		/*
+		 * If it is a legacy IRQ handled by the legacy PIC, this cpu
+		 * will be part of the irq_cfg's domain.
+		 */
+		if (irq < legacy_pic->nr_legacy_irqs && !IO_APIC_IRQ(irq))
+			cpumask_set_cpu(cpu, cfg->domain);
+
 		if (!cpumask_test_cpu(cpu, cfg->domain))
 			continue;
 		vector = cfg->vector;
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 60398a0..53ea4cf 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -28,6 +28,7 @@
 #include <asm/apic.h>
 #include <asm/stacktrace.h>
 #include <asm/nmi.h>
+#include <asm/compat.h>
 
 static u64 perf_event_mask __read_mostly;
 
@@ -158,7 +159,7 @@ struct x86_pmu {
 						 struct perf_event *event);
 	struct event_constraint *event_constraints;
 
-	void		(*cpu_prepare)(int cpu);
+	int		(*cpu_prepare)(int cpu);
 	void		(*cpu_starting)(int cpu);
 	void		(*cpu_dying)(int cpu);
 	void		(*cpu_dead)(int cpu);
@@ -1333,11 +1334,12 @@ static int __cpuinit
 x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (long)hcpu;
+	int ret = NOTIFY_OK;
 
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_UP_PREPARE:
 		if (x86_pmu.cpu_prepare)
-			x86_pmu.cpu_prepare(cpu);
+			ret = x86_pmu.cpu_prepare(cpu);
 		break;
 
 	case CPU_STARTING:
@@ -1350,6 +1352,7 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 			x86_pmu.cpu_dying(cpu);
 		break;
 
+	case CPU_UP_CANCELED:
 	case CPU_DEAD:
 		if (x86_pmu.cpu_dead)
 			x86_pmu.cpu_dead(cpu);
@@ -1359,7 +1362,7 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 		break;
 	}
 
-	return NOTIFY_OK;
+	return ret;
 }
 
 static void __init pmu_check_apic(void)
@@ -1628,14 +1631,42 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 	return len;
 }
 
-static int copy_stack_frame(const void __user *fp, struct stack_frame *frame)
+#ifdef CONFIG_COMPAT
+static inline int
+perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 {
-	unsigned long bytes;
+	/* 32-bit process in 64-bit kernel. */
+	struct stack_frame_ia32 frame;
+	const void __user *fp;
 
-	bytes = copy_from_user_nmi(frame, fp, sizeof(*frame));
+	if (!test_thread_flag(TIF_IA32))
+		return 0;
+
+	fp = compat_ptr(regs->bp);
+	while (entry->nr < PERF_MAX_STACK_DEPTH) {
+		unsigned long bytes;
+		frame.next_frame     = 0;
+		frame.return_address = 0;
+
+		bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
+		if (bytes != sizeof(frame))
+			break;
+
+		if (fp < compat_ptr(regs->sp))
+			break;
 
-	return bytes == sizeof(*frame);
+		callchain_store(entry, frame.return_address);
+		fp = compat_ptr(frame.next_frame);
+	}
+	return 1;
+}
+#else
+static inline int
+perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
+{
+    return 0;
 }
+#endif
 
 static void
 perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
@@ -1651,11 +1682,16 @@ perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
 	callchain_store(entry, PERF_CONTEXT_USER);
 	callchain_store(entry, regs->ip);
 
+	if (perf_callchain_user32(regs, entry))
+		return;
+
 	while (entry->nr < PERF_MAX_STACK_DEPTH) {
+		unsigned long bytes;
 		frame.next_frame	     = NULL;
 		frame.return_address = 0;
 
-		if (!copy_stack_frame(fp, &frame))
+		bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
+		if (bytes != sizeof(frame))
 			break;
 
 		if ((unsigned long)fp < regs->sp)
@@ -1702,7 +1738,6 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 	return entry;
 }
 
-#ifdef CONFIG_EVENT_TRACING
 void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip)
 {
 	regs->ip = ip;
@@ -1714,4 +1749,3 @@ void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int ski
 	regs->cs = __KERNEL_CS;
 	local_save_flags(regs->flags);
 }
-#endif
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index b87e0b6..db6f7d4 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -137,6 +137,13 @@ static inline int amd_is_nb_event(struct hw_perf_event *hwc)
 	return (hwc->config & 0xe0) == 0xe0;
 }
 
+static inline int amd_has_nb(struct cpu_hw_events *cpuc)
+{
+	struct amd_nb *nb = cpuc->amd_nb;
+
+	return nb && nb->nb_id != -1;
+}
+
 static void amd_put_event_constraints(struct cpu_hw_events *cpuc,
 				      struct perf_event *event)
 {
@@ -147,7 +154,7 @@ static void amd_put_event_constraints(struct cpu_hw_events *cpuc,
 	/*
 	 * only care about NB events
 	 */
-	if (!(nb && amd_is_nb_event(hwc)))
+	if (!(amd_has_nb(cpuc) && amd_is_nb_event(hwc)))
 		return;
 
 	/*
@@ -214,7 +221,7 @@ amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
 	/*
 	 * if not NB event or no NB, then no constraints
 	 */
-	if (!(nb && amd_is_nb_event(hwc)))
+	if (!(amd_has_nb(cpuc) && amd_is_nb_event(hwc)))
 		return &unconstrained;
 
 	/*
@@ -293,51 +300,55 @@ static struct amd_nb *amd_alloc_nb(int cpu, int nb_id)
 	return nb;
 }
 
-static void amd_pmu_cpu_online(int cpu)
+static int amd_pmu_cpu_prepare(int cpu)
+{
+	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+
+	WARN_ON_ONCE(cpuc->amd_nb);
+
+	if (boot_cpu_data.x86_max_cores < 2)
+		return NOTIFY_OK;
+
+	cpuc->amd_nb = amd_alloc_nb(cpu, -1);
+	if (!cpuc->amd_nb)
+		return NOTIFY_BAD;
+
+	return NOTIFY_OK;
+}
+
+static void amd_pmu_cpu_starting(int cpu)
 {
-	struct cpu_hw_events *cpu1, *cpu2;
-	struct amd_nb *nb = NULL;
+	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+	struct amd_nb *nb;
 	int i, nb_id;
 
 	if (boot_cpu_data.x86_max_cores < 2)
 		return;
 
-	/*
-	 * function may be called too early in the
-	 * boot process, in which case nb_id is bogus
-	 */
 	nb_id = amd_get_nb_id(cpu);
-	if (nb_id == BAD_APICID)
-		return;
-
-	cpu1 = &per_cpu(cpu_hw_events, cpu);
-	cpu1->amd_nb = NULL;
+	WARN_ON_ONCE(nb_id == BAD_APICID);
 
 	raw_spin_lock(&amd_nb_lock);
 
 	for_each_online_cpu(i) {
-		cpu2 = &per_cpu(cpu_hw_events, i);
-		nb = cpu2->amd_nb;
-		if (!nb)
+		nb = per_cpu(cpu_hw_events, i).amd_nb;
+		if (WARN_ON_ONCE(!nb))
 			continue;
-		if (nb->nb_id == nb_id)
-			goto found;
-	}
 
-	nb = amd_alloc_nb(cpu, nb_id);
-	if (!nb) {
-		pr_err("perf_events: failed NB allocation for CPU%d\n", cpu);
-		raw_spin_unlock(&amd_nb_lock);
-		return;
+		if (nb->nb_id == nb_id) {
+			kfree(cpuc->amd_nb);
+			cpuc->amd_nb = nb;
+			break;
+		}
 	}
-found:
-	nb->refcnt++;
-	cpu1->amd_nb = nb;
+
+	cpuc->amd_nb->nb_id = nb_id;
+	cpuc->amd_nb->refcnt++;
 
 	raw_spin_unlock(&amd_nb_lock);
 }
 
-static void amd_pmu_cpu_offline(int cpu)
+static void amd_pmu_cpu_dead(int cpu)
 {
 	struct cpu_hw_events *cpuhw;
 
@@ -349,8 +360,10 @@ static void amd_pmu_cpu_offline(int cpu)
 	raw_spin_lock(&amd_nb_lock);
 
 	if (cpuhw->amd_nb) {
-		if (--cpuhw->amd_nb->refcnt == 0)
-			kfree(cpuhw->amd_nb);
+		struct amd_nb *nb = cpuhw->amd_nb;
+
+		if (nb->nb_id == -1 || --nb->refcnt == 0)
+			kfree(nb);
 
 		cpuhw->amd_nb = NULL;
 	}
@@ -379,8 +392,9 @@ static __initconst struct x86_pmu amd_pmu = {
 	.get_event_constraints	= amd_get_event_constraints,
 	.put_event_constraints	= amd_put_event_constraints,
 
-	.cpu_prepare		= amd_pmu_cpu_online,
-	.cpu_dead		= amd_pmu_cpu_offline,
+	.cpu_prepare		= amd_pmu_cpu_prepare,
+	.cpu_starting		= amd_pmu_cpu_starting,
+	.cpu_dead		= amd_pmu_cpu_dead,
 };
 
 static __init int amd_pmu_init(void)
diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h
index 29e5f7c..e39e771 100644
--- a/arch/x86/kernel/dumpstack.h
+++ b/arch/x86/kernel/dumpstack.h
@@ -30,6 +30,11 @@ struct stack_frame {
 	unsigned long return_address;
 };
 
+struct stack_frame_ia32 {
+    u32 next_frame;
+    u32 return_address;
+};
+
 static inline unsigned long rewind_frame_pointer(int n)
 {
 	struct stack_frame *frame;
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index adedeef..b2e2460 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -7,6 +7,7 @@
 
 #include <linux/init.h>
 #include <linux/start_kernel.h>
+#include <linux/mm.h>
 
 #include <asm/setup.h>
 #include <asm/sections.h>
@@ -44,9 +45,10 @@ void __init i386_start_kernel(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 	/* Reserve INITRD */
 	if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
+		/* Assume only end is not page aligned */
 		u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 		u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
-		u64 ramdisk_end   = ramdisk_image + ramdisk_size;
+		u64 ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
 		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index b5a9896..7147143 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -103,9 +103,10 @@ void __init x86_64_start_reservations(char *real_mode_data)
 #ifdef CONFIG_BLK_DEV_INITRD
 	/* Reserve INITRD */
 	if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
+		/* Assume only end is not page aligned */
 		unsigned long ramdisk_image = boot_params.hdr.ramdisk_image;
 		unsigned long ramdisk_size  = boot_params.hdr.ramdisk_size;
-		unsigned long ramdisk_end   = ramdisk_image + ramdisk_size;
+		unsigned long ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
 		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index ef257fc..f01d390 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -141,6 +141,28 @@ void __init init_IRQ(void)
 	x86_init.irqs.intr_init();
 }
 
+/*
+ * Setup the vector to irq mappings.
+ */
+void setup_vector_irq(int cpu)
+{
+#ifndef CONFIG_X86_IO_APIC
+	int irq;
+
+	/*
+	 * On most of the platforms, legacy PIC delivers the interrupts on the
+	 * boot cpu. But there are certain platforms where PIC interrupts are
+	 * delivered to multiple cpu's. If the legacy IRQ is handled by the
+	 * legacy PIC, for the new cpu that is coming online, setup the static
+	 * legacy vector to irq mapping:
+	 */
+	for (irq = 0; irq < legacy_pic->nr_legacy_irqs; irq++)
+		per_cpu(vector_irq, cpu)[IRQ0_VECTOR + irq] = irq;
+#endif
+
+	__setup_vector_irq(cpu);
+}
+
 static void __init smp_intr_init(void)
 {
 #ifdef CONFIG_SMP
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index bfba601..b2258ca 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -618,8 +618,8 @@ int kgdb_arch_init(void)
 	 * portion of kgdb because this operation requires mutexs to
 	 * complete.
 	 */
+	hw_breakpoint_init(&attr);
 	attr.bp_addr = (unsigned long)kgdb_arch_init;
-	attr.type = PERF_TYPE_BREAKPOINT;
 	attr.bp_len = HW_BREAKPOINT_LEN_1;
 	attr.bp_type = HW_BREAKPOINT_W;
 	attr.disabled = 1;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index ad95406..28ad9f4 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -526,21 +526,37 @@ static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
 }
 
 /*
- * Check for AMD CPUs, which have potentially C1E support
+ * Check for AMD CPUs, where APIC timer interrupt does not wake up CPU from C1e.
+ * For more information see
+ * - Erratum #400 for NPT family 0xf and family 0x10 CPUs
+ * - Erratum #365 for family 0x11 (not affected because C1e not in use)
  */
 static int __cpuinit check_c1e_idle(const struct cpuinfo_x86 *c)
 {
+	u64 val;
 	if (c->x86_vendor != X86_VENDOR_AMD)
-		return 0;
-
-	if (c->x86 < 0x0F)
-		return 0;
+		goto no_c1e_idle;
 
 	/* Family 0x0f models < rev F do not have C1E */
-	if (c->x86 == 0x0f && c->x86_model < 0x40)
-		return 0;
+	if (c->x86 == 0x0F && c->x86_model >= 0x40)
+		return 1;
 
-	return 1;
+	if (c->x86 == 0x10) {
+		/*
+		 * check OSVW bit for CPUs that are not affected
+		 * by erratum #400
+		 */
+		rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, val);
+		if (val >= 2) {
+			rdmsrl(MSR_AMD64_OSVW_STATUS, val);
+			if (!(val & BIT(1)))
+				goto no_c1e_idle;
+		}
+		return 1;
+	}
+
+no_c1e_idle:
+	return 0;
 }
 
 static cpumask_var_t c1e_mask;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 5d7ba1a..d76e185 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -314,16 +314,17 @@ static void __init reserve_brk(void)
 #define MAX_MAP_CHUNK	(NR_FIX_BTMAPS << PAGE_SHIFT)
 static void __init relocate_initrd(void)
 {
-
+	/* Assume only end is not page aligned */
 	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 	u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
+	u64 area_size     = PAGE_ALIGN(ramdisk_size);
 	u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
 	u64 ramdisk_here;
 	unsigned long slop, clen, mapaddr;
 	char *p, *q;
 
 	/* We need to move the initrd down into lowmem */
-	ramdisk_here = find_e820_area(0, end_of_lowmem, ramdisk_size,
+	ramdisk_here = find_e820_area(0, end_of_lowmem, area_size,
 					 PAGE_SIZE);
 
 	if (ramdisk_here == -1ULL)
@@ -332,7 +333,7 @@ static void __init relocate_initrd(void)
 
 	/* Note: this includes all the lowmem currently occupied by
 	   the initrd, we rely on that fact to keep the data intact. */
-	reserve_early(ramdisk_here, ramdisk_here + ramdisk_size,
+	reserve_early(ramdisk_here, ramdisk_here + area_size,
 			 "NEW RAMDISK");
 	initrd_start = ramdisk_here + PAGE_OFFSET;
 	initrd_end   = initrd_start + ramdisk_size;
@@ -376,9 +377,10 @@ static void __init relocate_initrd(void)
 
 static void __init reserve_initrd(void)
 {
+	/* Assume only end is not page aligned */
 	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 	u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
-	u64 ramdisk_end   = ramdisk_image + ramdisk_size;
+	u64 ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
 	u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
 
 	if (!boot_params.hdr.type_of_loader ||
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index a02e80c..6808b93 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -242,12 +242,10 @@ static void __cpuinit smp_callin(void)
 	end_local_APIC_setup();
 	map_cpu_to_logical_apicid();
 
-	notify_cpu_starting(cpuid);
-
 	/*
 	 * Need to setup vector mappings before we enable interrupts.
 	 */
-	__setup_vector_irq(smp_processor_id());
+	setup_vector_irq(smp_processor_id());
 	/*
 	 * Get our bogomips.
 	 *
@@ -264,6 +262,8 @@ static void __cpuinit smp_callin(void)
 	 */
 	smp_store_cpu_info(cpuid);
 
+	notify_cpu_starting(cpuid);
+
 	/*
 	 * Allow the master to continue.
 	 */
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 44879df..2cc2497 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -291,8 +291,8 @@ SECTIONS
 	.smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
 		__smp_locks = .;
 		*(.smp_locks)
-		__smp_locks_end = .;
 		. = ALIGN(PAGE_SIZE);
+		__smp_locks_end = .;
 	}
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index e71c5cb..452ee5b 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -331,11 +331,23 @@ int devmem_is_allowed(unsigned long pagenr)
 
 void free_init_pages(char *what, unsigned long begin, unsigned long end)
 {
-	unsigned long addr = begin;
+	unsigned long addr;
+	unsigned long begin_aligned, end_aligned;
 
-	if (addr >= end)
+	/* Make sure boundaries are page aligned */
+	begin_aligned = PAGE_ALIGN(begin);
+	end_aligned   = end & PAGE_MASK;
+
+	if (WARN_ON(begin_aligned != begin || end_aligned != end)) {
+		begin = begin_aligned;
+		end   = end_aligned;
+	}
+
+	if (begin >= end)
 		return;
 
+	addr = begin;
+
 	/*
 	 * If debugging page accesses then do not free this memory but
 	 * mark them not present - any buggy init-section access will
@@ -343,7 +355,7 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
 	 */
 #ifdef CONFIG_DEBUG_PAGEALLOC
 	printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n",
-		begin, PAGE_ALIGN(end));
+		begin, end);
 	set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
 #else
 	/*
@@ -358,8 +370,7 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
 	for (; addr < end; addr += PAGE_SIZE) {
 		ClearPageReserved(virt_to_page(addr));
 		init_page_count(virt_to_page(addr));
-		memset((void *)(addr & ~(PAGE_SIZE-1)),
-			POISON_FREE_INITMEM, PAGE_SIZE);
+		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
 		free_page(addr);
 		totalram_pages++;
 	}
@@ -376,6 +387,15 @@ void free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_init_pages("initrd memory", start, end);
+	/*
+	 * end could be not aligned, and We can not align that,
+	 * decompresser could be confused by aligned initrd_end
+	 * We already reserve the end partial page before in
+	 *   - i386_start_kernel()
+	 *   - x86_64_start_kernel()
+	 *   - relocate_initrd()
+	 * So here We can do PAGE_ALIGN() safely to get partial page to be freed
+	 */
+	free_init_pages("initrd memory", start, PAGE_ALIGN(end));
 }
 #endif
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 6e22454..e311602 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -122,8 +122,8 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 	struct acpi_resource_address64 addr;
 	acpi_status status;
 	unsigned long flags;
-	struct resource *root;
-	u64 start, end;
+	struct resource *root, *conflict;
+	u64 start, end, max_len;
 
 	status = resource_to_addr(acpi_res, &addr);
 	if (!ACPI_SUCCESS(status))
@@ -140,6 +140,17 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 	} else
 		return AE_OK;
 
+	max_len = addr.maximum - addr.minimum + 1;
+	if (addr.address_length > max_len) {
+		dev_printk(KERN_DEBUG, &info->bridge->dev,
+			   "host bridge window length %#llx doesn't fit in "
+			   "%#llx-%#llx, trimming\n",
+			   (unsigned long long) addr.address_length,
+			   (unsigned long long) addr.minimum,
+			   (unsigned long long) addr.maximum);
+		addr.address_length = max_len;
+	}
+
 	start = addr.minimum + addr.translation_offset;
 	end = start + addr.address_length - 1;
 
@@ -157,9 +168,12 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 		return AE_OK;
 	}
 
-	if (insert_resource(root, res)) {
+	conflict = insert_resource_conflict(root, res);
+	if (conflict) {
 		dev_err(&info->bridge->dev,
-			"can't allocate host bridge window %pR\n", res);
+			"address space collision: host bridge window %pR "
+			"conflicts with %s %pR\n",
+			res, conflict->name, conflict);
 	} else {
 		pci_bus_add_resource(info->bus, res, 0);
 		info->res_num++;
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index dece3eb..46fd43f 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -127,9 +127,6 @@ static void __init pcibios_allocate_bus_resources(struct list_head *bus_list)
 					continue;
 				if (!r->start ||
 				    pci_claim_resource(dev, idx) < 0) {
-					dev_info(&dev->dev,
-						 "can't reserve window %pR\n",
-						 r);
 					/*
 					 * Something is wrong with the region.
 					 * Invalidate the resource to prevent
@@ -181,8 +178,6 @@ static void __init pcibios_allocate_resources(int pass)
 					"BAR %d: reserving %pr (d=%d, p=%d)\n",
 					idx, r, disabled, pass);
 				if (pci_claim_resource(dev, idx) < 0) {
-					dev_info(&dev->dev,
-						 "can't reserve %pR\n", r);
 					/* We'll assign a new address later */
 					r->end -= r->start;
 					r->start = 0;