Merge branch 'devel-stable' into for-linus

Conflicts: arch/arm/kernel/setup.c arch/arm/mach-shmobile/board-kota2.c
2012-01-05 13:24:33 +00:00
parent a32737e1ca ef3a0bf5bf
commit 2e0e943436
433 changed files with 3326 additions and 4081 deletions
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -629,6 +629,23 @@ config IO_36

 comment "Processor Features"

+config ARM_LPAE
+	bool "Support for the Large Physical Address Extension"
+	depends on MMU && CPU_V7
+	help
+	  Say Y if you have an ARMv7 processor supporting the LPAE page
+	  table format and you would like to access memory beyond the
+	  4GB limit. The resulting kernel image will not run on
+	  processors without the LPA extension.
+
+	  If unsure, say N.
+
+config ARCH_PHYS_ADDR_T_64BIT
+	def_bool ARM_LPAE
+
+config ARCH_DMA_ADDR_T_64BIT
+	bool
+
 config ARM_THUMB
 	bool "Support Thumb user binaries"
 	depends on CPU_ARM720T || CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM946E || CPU_ARM1020 || CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_V6 || CPU_V6K || CPU_V7 || CPU_FEROCEON
@@ -816,14 +833,23 @@ config CACHE_FEROCEON_L2_WRITETHROUGH
 	  Say Y here to use the Feroceon L2 cache in writethrough mode.
 	  Unless you specifically require this, say N for writeback mode.

+config MIGHT_HAVE_CACHE_L2X0
+	bool
+	help
+	  This option should be selected by machines which have a L2x0
+	  or PL310 cache controller, but where its use is optional.
+
+	  The only effect of this option is to make CACHE_L2X0 and
+	  related options available to the user for configuration.
+
+	  Boards or SoCs which always require the cache controller
+	  support to be present should select CACHE_L2X0 directly
+	  instead of this option, thus preventing the user from
+	  inadvertently configuring a broken kernel.
+
 config CACHE_L2X0
-	bool "Enable the L2x0 outer cache controller"
-	depends on REALVIEW_EB_ARM11MP || MACH_REALVIEW_PB11MP || MACH_REALVIEW_PB1176 || \
-		   REALVIEW_EB_A9MP || ARCH_IMX_V6_V7 || MACH_REALVIEW_PBX || \
-		   ARCH_NOMADIK || ARCH_OMAP4 || ARCH_EXYNOS4 || ARCH_TEGRA || \
-		   ARCH_U8500 || ARCH_VEXPRESS_CA9X4 || ARCH_SHMOBILE || \
-		   ARCH_PRIMA2 || ARCH_ZYNQ || ARCH_CNS3XXX || ARCH_HIGHBANK
-	default y
+	bool "Enable the L2x0 outer cache controller" if MIGHT_HAVE_CACHE_L2X0
+	default MIGHT_HAVE_CACHE_L2X0
 	select OUTER_CACHE
 	select OUTER_CACHE_SYNC
 	help
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -968,7 +968,7 @@ static int __init alignment_init(void)
 		ai_usermode = safe_usermode(ai_usermode, false);
 	}

-	hook_fault_code(1, do_alignment, SIGBUS, BUS_ADRALN,
+	hook_fault_code(FAULT_CODE_ALIGNMENT, do_alignment, SIGBUS, BUS_ADRALN,
 			"alignment exception");

 	/*
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -22,6 +22,21 @@ unsigned int cpu_last_asid = ASID_FIRST_VERSION;
 DEFINE_PER_CPU(struct mm_struct *, current_mm);
 #endif

+#ifdef CONFIG_ARM_LPAE
+#define cpu_set_asid(asid) {						\
+	unsigned long ttbl, ttbh;					\
+	asm volatile(							\
+	"	mrrc	p15, 0, %0, %1, c2		@ read TTBR0\n"	\
+	"	mov	%1, %2, lsl #(48 - 32)		@ set ASID\n"	\
+	"	mcrr	p15, 0, %0, %1, c2		@ set TTBR0\n"	\
+	: "=&r" (ttbl), "=&r" (ttbh)					\
+	: "r" (asid & ~ASID_MASK));					\
+}
+#else
+#define cpu_set_asid(asid) \
+	asm("	mcr	p15, 0, %0, c13, c0, 1\n" : : "r" (asid))
+#endif
+
 /*
 * We fork()ed a process, and we need a new context for the child
 * to run in.  We reserve version 0 for initial tasks so we will
@@ -37,7 +52,7 @@ void __init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 static void flush_context(void)
 {
 	/* set the reserved ASID before flushing the TLB */
-	asm("mcr	p15, 0, %0, c13, c0, 1\n" : : "r" (0));
+	cpu_set_asid(0);
 	isb();
 	local_flush_tlb_all();
 	if (icache_is_vivt_asid_tagged()) {
@@ -99,7 +114,7 @@ static void reset_context(void *info)
 	set_mm_context(mm, asid);

 	/* set the new ASID */
-	asm("mcr	p15, 0, %0, c13, c0, 1\n" : : "r" (mm->context.id));
+	cpu_set_asid(mm->context.id);
 	isb();
 }

--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -27,19 +27,6 @@

 #include "fault.h"

-/*
- * Fault status register encodings.  We steal bit 31 for our own purposes.
- */
-#define FSR_LNX_PF		(1 << 31)
-#define FSR_WRITE		(1 << 11)
-#define FSR_FS4			(1 << 10)
-#define FSR_FS3_0		(15)
-
-static inline int fsr_fs(unsigned int fsr)
-{
-	return (fsr & FSR_FS3_0) | (fsr & FSR_FS4) >> 6;
-}
-
 #ifdef CONFIG_MMU

 #ifdef CONFIG_KPROBES
@@ -123,8 +110,10 @@ void show_pte(struct mm_struct *mm, unsigned long addr)

 		pte = pte_offset_map(pmd, addr);
 		printk(", *pte=%08llx", (long long)pte_val(*pte));
+#ifndef CONFIG_ARM_LPAE
 		printk(", *ppte=%08llx",
 		       (long long)pte_val(pte[PTE_HWTABLE_PTRS]));
+#endif
 		pte_unmap(pte);
 	} while(0);

@@ -461,6 +450,12 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 	pmd = pmd_offset(pud, addr);
 	pmd_k = pmd_offset(pud_k, addr);

+#ifdef CONFIG_ARM_LPAE
+	/*
+	 * Only one hardware entry per PMD with LPAE.
+	 */
+	index = 0;
+#else
 	/*
 	 * On ARM one Linux PGD entry contains two hardware entries (see page
 	 * tables layout in pgtable.h). We normally guarantee that we always
@@ -470,6 +465,7 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 	 * for the first of pair.
 	 */
 	index = (addr >> SECTION_SHIFT) & 1;
+#endif
 	if (pmd_none(pmd_k[index]))
 		goto bad_area;

@@ -509,55 +505,20 @@ do_bad(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	return 1;
 }

-static struct fsr_info {
+struct fsr_info {
 	int	(*fn)(unsigned long addr, unsigned int fsr, struct pt_regs *regs);
 	int	sig;
 	int	code;
 	const char *name;
-} fsr_info[] = {
-	/*
-	 * The following are the standard ARMv3 and ARMv4 aborts.  ARMv5
-	 * defines these to be "precise" aborts.
-	 */
-	{ do_bad,		SIGSEGV, 0,		"vector exception"		   },
-	{ do_bad,		SIGBUS,	 BUS_ADRALN,	"alignment exception"		   },
-	{ do_bad,		SIGKILL, 0,		"terminal exception"		   },
-	{ do_bad,		SIGBUS,	 BUS_ADRALN,	"alignment exception"		   },
-	{ do_bad,		SIGBUS,	 0,		"external abort on linefetch"	   },
-	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"section translation fault"	   },
-	{ do_bad,		SIGBUS,	 0,		"external abort on linefetch"	   },
-	{ do_page_fault,	SIGSEGV, SEGV_MAPERR,	"page translation fault"	   },
-	{ do_bad,		SIGBUS,	 0,		"external abort on non-linefetch"  },
-	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"section domain fault"		   },
-	{ do_bad,		SIGBUS,	 0,		"external abort on non-linefetch"  },
-	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"page domain fault"		   },
-	{ do_bad,		SIGBUS,	 0,		"external abort on translation"	   },
-	{ do_sect_fault,	SIGSEGV, SEGV_ACCERR,	"section permission fault"	   },
-	{ do_bad,		SIGBUS,	 0,		"external abort on translation"	   },
-	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"page permission fault"		   },
-	/*
-	 * The following are "imprecise" aborts, which are signalled by bit
-	 * 10 of the FSR, and may not be recoverable.  These are only
-	 * supported if the CPU abort handler supports bit 10.
-	 */
-	{ do_bad,		SIGBUS,  0,		"unknown 16"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 17"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 18"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 19"			   },
-	{ do_bad,		SIGBUS,  0,		"lock abort"			   }, /* xscale */
-	{ do_bad,		SIGBUS,  0,		"unknown 21"			   },
-	{ do_bad,		SIGBUS,  BUS_OBJERR,	"imprecise external abort"	   }, /* xscale */
-	{ do_bad,		SIGBUS,  0,		"unknown 23"			   },
-	{ do_bad,		SIGBUS,  0,		"dcache parity error"		   }, /* xscale */
-	{ do_bad,		SIGBUS,  0,		"unknown 25"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 26"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 27"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 28"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 29"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 30"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 31"			   }
 };

+/* FSR definition */
+#ifdef CONFIG_ARM_LPAE
+#include "fsr-3level.c"
+#else
+#include "fsr-2level.c"
+#endif
+
 void __init
 hook_fault_code(int nr, int (*fn)(unsigned long, unsigned int, struct pt_regs *),
 		int sig, int code, const char *name)
@@ -593,42 +554,6 @@ do_DataAbort(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	arm_notify_die("", regs, &info, fsr, 0);
 }

-
-static struct fsr_info ifsr_info[] = {
-	{ do_bad,		SIGBUS,  0,		"unknown 0"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 1"			   },
-	{ do_bad,		SIGBUS,  0,		"debug event"			   },
-	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"section access flag fault"	   },
-	{ do_bad,		SIGBUS,  0,		"unknown 4"			   },
-	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"section translation fault"	   },
-	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"page access flag fault"	   },
-	{ do_page_fault,	SIGSEGV, SEGV_MAPERR,	"page translation fault"	   },
-	{ do_bad,		SIGBUS,	 0,		"external abort on non-linefetch"  },
-	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"section domain fault"		   },
-	{ do_bad,		SIGBUS,  0,		"unknown 10"			   },
-	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"page domain fault"		   },
-	{ do_bad,		SIGBUS,	 0,		"external abort on translation"	   },
-	{ do_sect_fault,	SIGSEGV, SEGV_ACCERR,	"section permission fault"	   },
-	{ do_bad,		SIGBUS,	 0,		"external abort on translation"	   },
-	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"page permission fault"		   },
-	{ do_bad,		SIGBUS,  0,		"unknown 16"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 17"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 18"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 19"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 20"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 21"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 22"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 23"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 24"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 25"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 26"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 27"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 28"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 29"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 30"			   },
-	{ do_bad,		SIGBUS,  0,		"unknown 31"			   },
-};
-
 void __init
 hook_ifault_code(int nr, int (*fn)(unsigned long, unsigned int, struct pt_regs *),
 		 int sig, int code, const char *name)
@@ -661,6 +586,7 @@ do_PrefetchAbort(unsigned long addr, unsigned int ifsr, struct pt_regs *regs)
 	arm_notify_die("", regs, &info, ifsr, 0);
 }

+#ifndef CONFIG_ARM_LPAE
 static int __init exceptions_init(void)
 {
 	if (cpu_architecture() >= CPU_ARCH_ARMv6) {
@@ -683,3 +609,4 @@ static int __init exceptions_init(void)
 }

 arch_initcall(exceptions_init);
+#endif
--- a/arch/arm/mm/fault.h
+++ b/arch/arm/mm/fault.h
@@ -1,3 +1,28 @@
-void do_bad_area(unsigned long addr, unsigned int fsr, struct pt_regs *regs);
+#ifndef __ARCH_ARM_FAULT_H
+#define __ARCH_ARM_FAULT_H

+/*
+ * Fault status register encodings.  We steal bit 31 for our own purposes.
+ */
+#define FSR_LNX_PF		(1 << 31)
+#define FSR_WRITE		(1 << 11)
+#define FSR_FS4			(1 << 10)
+#define FSR_FS3_0		(15)
+#define FSR_FS5_0		(0x3f)
+
+#ifdef CONFIG_ARM_LPAE
+static inline int fsr_fs(unsigned int fsr)
+{
+	return fsr & FSR_FS5_0;
+}
+#else
+static inline int fsr_fs(unsigned int fsr)
+{
+	return (fsr & FSR_FS3_0) | (fsr & FSR_FS4) >> 6;
+}
+#endif
+
+void do_bad_area(unsigned long addr, unsigned int fsr, struct pt_regs *regs);
 unsigned long search_exception_table(unsigned long addr);
+
+#endif	/* __ARCH_ARM_FAULT_H */
--- a/arch/arm/mm/fsr-2level.c
+++ b/arch/arm/mm/fsr-2level.c
@@ -0,0 +1,78 @@
+static struct fsr_info fsr_info[] = {
+	/*
+	 * The following are the standard ARMv3 and ARMv4 aborts.  ARMv5
+	 * defines these to be "precise" aborts.
+	 */
+	{ do_bad,		SIGSEGV, 0,		"vector exception"		   },
+	{ do_bad,		SIGBUS,	 BUS_ADRALN,	"alignment exception"		   },
+	{ do_bad,		SIGKILL, 0,		"terminal exception"		   },
+	{ do_bad,		SIGBUS,	 BUS_ADRALN,	"alignment exception"		   },
+	{ do_bad,		SIGBUS,	 0,		"external abort on linefetch"	   },
+	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"section translation fault"	   },
+	{ do_bad,		SIGBUS,	 0,		"external abort on linefetch"	   },
+	{ do_page_fault,	SIGSEGV, SEGV_MAPERR,	"page translation fault"	   },
+	{ do_bad,		SIGBUS,	 0,		"external abort on non-linefetch"  },
+	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"section domain fault"		   },
+	{ do_bad,		SIGBUS,	 0,		"external abort on non-linefetch"  },
+	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"page domain fault"		   },
+	{ do_bad,		SIGBUS,	 0,		"external abort on translation"	   },
+	{ do_sect_fault,	SIGSEGV, SEGV_ACCERR,	"section permission fault"	   },
+	{ do_bad,		SIGBUS,	 0,		"external abort on translation"	   },
+	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"page permission fault"		   },
+	/*
+	 * The following are "imprecise" aborts, which are signalled by bit
+	 * 10 of the FSR, and may not be recoverable.  These are only
+	 * supported if the CPU abort handler supports bit 10.
+	 */
+	{ do_bad,		SIGBUS,  0,		"unknown 16"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 17"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 18"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 19"			   },
+	{ do_bad,		SIGBUS,  0,		"lock abort"			   }, /* xscale */
+	{ do_bad,		SIGBUS,  0,		"unknown 21"			   },
+	{ do_bad,		SIGBUS,  BUS_OBJERR,	"imprecise external abort"	   }, /* xscale */
+	{ do_bad,		SIGBUS,  0,		"unknown 23"			   },
+	{ do_bad,		SIGBUS,  0,		"dcache parity error"		   }, /* xscale */
+	{ do_bad,		SIGBUS,  0,		"unknown 25"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 26"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 27"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 28"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 29"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 30"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 31"			   },
+};
+
+static struct fsr_info ifsr_info[] = {
+	{ do_bad,		SIGBUS,  0,		"unknown 0"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 1"			   },
+	{ do_bad,		SIGBUS,  0,		"debug event"			   },
+	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"section access flag fault"	   },
+	{ do_bad,		SIGBUS,  0,		"unknown 4"			   },
+	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"section translation fault"	   },
+	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"page access flag fault"	   },
+	{ do_page_fault,	SIGSEGV, SEGV_MAPERR,	"page translation fault"	   },
+	{ do_bad,		SIGBUS,	 0,		"external abort on non-linefetch"  },
+	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"section domain fault"		   },
+	{ do_bad,		SIGBUS,  0,		"unknown 10"			   },
+	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"page domain fault"		   },
+	{ do_bad,		SIGBUS,	 0,		"external abort on translation"	   },
+	{ do_sect_fault,	SIGSEGV, SEGV_ACCERR,	"section permission fault"	   },
+	{ do_bad,		SIGBUS,	 0,		"external abort on translation"	   },
+	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"page permission fault"		   },
+	{ do_bad,		SIGBUS,  0,		"unknown 16"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 17"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 18"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 19"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 20"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 21"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 22"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 23"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 24"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 25"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 26"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 27"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 28"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 29"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 30"			   },
+	{ do_bad,		SIGBUS,  0,		"unknown 31"			   },
+};
--- a/arch/arm/mm/fsr-3level.c
+++ b/arch/arm/mm/fsr-3level.c
@@ -0,0 +1,68 @@
+static struct fsr_info fsr_info[] = {
+	{ do_bad,		SIGBUS,  0,		"unknown 0"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 1"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 2"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 3"			},
+	{ do_bad,		SIGBUS,  0,		"reserved translation fault"	},
+	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 1 translation fault"	},
+	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 2 translation fault"	},
+	{ do_page_fault,	SIGSEGV, SEGV_MAPERR,	"level 3 translation fault"	},
+	{ do_bad,		SIGBUS,  0,		"reserved access flag fault"	},
+	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 1 access flag fault"	},
+	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 2 access flag fault"	},
+	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 access flag fault"	},
+	{ do_bad,		SIGBUS,  0,		"reserved permission fault"	},
+	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 1 permission fault"	},
+	{ do_sect_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 permission fault"	},
+	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 permission fault"	},
+	{ do_bad,		SIGBUS,  0,		"synchronous external abort"	},
+	{ do_bad,		SIGBUS,  0,		"asynchronous external abort"	},
+	{ do_bad,		SIGBUS,  0,		"unknown 18"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 19"			},
+	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error"	},
+	{ do_bad,		SIGBUS,  0,		"asynchronous parity error"	},
+	{ do_bad,		SIGBUS,  0,		"unknown 26"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 27"			},
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk" },
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk" },
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk" },
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk" },
+	{ do_bad,		SIGBUS,  0,		"unknown 32"			},
+	{ do_bad,		SIGBUS,  BUS_ADRALN,	"alignment fault"		},
+	{ do_bad,		SIGBUS,  0,		"debug event"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 35"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 36"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 37"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 38"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 39"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 40"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 41"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 42"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 43"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 44"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 45"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 46"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 47"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 48"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 49"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 50"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 51"			},
+	{ do_bad,		SIGBUS,  0,		"implementation fault (lockdown abort)" },
+	{ do_bad,		SIGBUS,  0,		"unknown 53"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 54"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 55"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 56"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 57"			},
+	{ do_bad,		SIGBUS,  0,		"implementation fault (coprocessor abort)" },
+	{ do_bad,		SIGBUS,  0,		"unknown 59"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 60"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 61"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 62"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 63"			},
+};
+
+#define ifsr_info	fsr_info
--- a/arch/arm/mm/idmap.c
+++ b/arch/arm/mm/idmap.c
@@ -1,9 +1,38 @@
 #include <linux/kernel.h>

 #include <asm/cputype.h>
+#include <asm/idmap.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
+#include <asm/sections.h>

+pgd_t *idmap_pgd;
+
+#ifdef CONFIG_ARM_LPAE
+static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end,
+	unsigned long prot)
+{
+	pmd_t *pmd;
+	unsigned long next;
+
+	if (pud_none_or_clear_bad(pud) || (pud_val(*pud) & L_PGD_SWAPPER)) {
+		pmd = pmd_alloc_one(&init_mm, addr);
+		if (!pmd) {
+			pr_warning("Failed to allocate identity pmd.\n");
+			return;
+		}
+		pud_populate(&init_mm, pud, pmd);
+		pmd += pmd_index(addr);
+	} else
+		pmd = pmd_offset(pud, addr);
+
+	do {
+		next = pmd_addr_end(addr, end);
+		*pmd = __pmd((addr & PMD_MASK) | prot);
+		flush_pmd_entry(pmd);
+	} while (pmd++, addr = next, addr != end);
+}
+#else	/* !CONFIG_ARM_LPAE */
 static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end,
 	unsigned long prot)
 {
@@ -15,6 +44,7 @@ static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end,
 	pmd[1] = __pmd(addr);
 	flush_pmd_entry(pmd);
 }
+#endif	/* CONFIG_ARM_LPAE */

 static void idmap_add_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
 	unsigned long prot)
@@ -28,11 +58,11 @@ static void idmap_add_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
 	} while (pud++, addr = next, addr != end);
 }

-void identity_mapping_add(pgd_t *pgd, unsigned long addr, unsigned long end)
+static void identity_mapping_add(pgd_t *pgd, unsigned long addr, unsigned long end)
 {
 	unsigned long prot, next;

-	prot = PMD_TYPE_SECT | PMD_SECT_AP_WRITE;
+	prot = PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AF;
 	if (cpu_architecture() <= CPU_ARCH_ARMv5TEJ && !cpu_is_xscale())
 		prot |= PMD_BIT4;

@@ -43,48 +73,41 @@ void identity_mapping_add(pgd_t *pgd, unsigned long addr, unsigned long end)
 	} while (pgd++, addr = next, addr != end);
 }

-#ifdef CONFIG_SMP
-static void idmap_del_pmd(pud_t *pud, unsigned long addr, unsigned long end)
+extern char  __idmap_text_start[], __idmap_text_end[];
+
+static int __init init_static_idmap(void)
 {
-	pmd_t *pmd = pmd_offset(pud, addr);
-	pmd_clear(pmd);
+	phys_addr_t idmap_start, idmap_end;
+
+	idmap_pgd = pgd_alloc(&init_mm);
+	if (!idmap_pgd)
+		return -ENOMEM;
+
+	/* Add an identity mapping for the physical address of the section. */
+	idmap_start = virt_to_phys((void *)__idmap_text_start);
+	idmap_end = virt_to_phys((void *)__idmap_text_end);
+
+	pr_info("Setting up static identity map for 0x%llx - 0x%llx\n",
+		(long long)idmap_start, (long long)idmap_end);
+	identity_mapping_add(idmap_pgd, idmap_start, idmap_end);
+
+	return 0;
 }
-
-static void idmap_del_pud(pgd_t *pgd, unsigned long addr, unsigned long end)
-{
-	pud_t *pud = pud_offset(pgd, addr);
-	unsigned long next;
-
-	do {
-		next = pud_addr_end(addr, end);
-		idmap_del_pmd(pud, addr, next);
-	} while (pud++, addr = next, addr != end);
-}
-
-void identity_mapping_del(pgd_t *pgd, unsigned long addr, unsigned long end)
-{
-	unsigned long next;
-
-	pgd += pgd_index(addr);
-	do {
-		next = pgd_addr_end(addr, end);
-		idmap_del_pud(pgd, addr, next);
-	} while (pgd++, addr = next, addr != end);
-}
-#endif
+early_initcall(init_static_idmap);

 /*
- * In order to soft-boot, we need to insert a 1:1 mapping in place of
- * the user-mode pages.  This will then ensure that we have predictable
- * results when turning the mmu off
+ * In order to soft-boot, we need to switch to a 1:1 mapping for the
+ * cpu_reset functions. This will then ensure that we have predictable
+ * results when turning off the mmu.
 */
-void setup_mm_for_reboot(char mode)
+void setup_mm_for_reboot(void)
 {
-	/*
-	 * We need to access to user-mode page tables here. For kernel threads
-	 * we don't have any user-mode mappings so we use the context that we
-	 * "borrowed".
-	 */
-	identity_mapping_add(current->active_mm->pgd, 0, TASK_SIZE);
+	/* Clean and invalidate L1. */
+	flush_cache_all();
+
+	/* Switch to the identity mapping. */
+	cpu_switch_mm(idmap_pgd, &init_mm);
+
+	/* Flush the TLB. */
 	local_flush_tlb_all();
 }
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -20,7 +20,6 @@
 #include <linux/highmem.h>
 #include <linux/gfp.h>
 #include <linux/memblock.h>
-#include <linux/sort.h>

 #include <asm/mach-types.h>
 #include <asm/prom.h>
@@ -134,30 +133,18 @@ void show_mem(unsigned int filter)
 }

 static void __init find_limits(unsigned long *min, unsigned long *max_low,
-	unsigned long *max_high)
+			       unsigned long *max_high)
 {
 	struct meminfo *mi = &meminfo;
 	int i;

-	*min = -1UL;
-	*max_low = *max_high = 0;
-
-	for_each_bank (i, mi) {
-		struct membank *bank = &mi->bank[i];
-		unsigned long start, end;
-
-		start = bank_pfn_start(bank);
-		end = bank_pfn_end(bank);
-
-		if (*min > start)
-			*min = start;
-		if (*max_high < end)
-			*max_high = end;
-		if (bank->highmem)
-			continue;
-		if (*max_low < end)
-			*max_low = end;
-	}
+	/* This assumes the meminfo array is properly sorted */
+	*min = bank_pfn_start(&mi->bank[0]);
+	for_each_bank (i, mi)
+		if (mi->bank[i].highmem)
+				break;
+	*max_low = bank_pfn_end(&mi->bank[i - 1]);
+	*max_high = bank_pfn_end(&mi->bank[mi->nr_banks - 1]);
 }

 static void __init arm_bootmem_init(unsigned long start_pfn,
@@ -319,19 +306,10 @@ static void arm_memory_present(void)
 }
 #endif

-static int __init meminfo_cmp(const void *_a, const void *_b)
-{
-	const struct membank *a = _a, *b = _b;
-	long cmp = bank_pfn_start(a) - bank_pfn_start(b);
-	return cmp < 0 ? -1 : cmp > 0 ? 1 : 0;
-}
-
 void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc)
 {
 	int i;

-	sort(&meminfo.bank, meminfo.nr_banks, sizeof(meminfo.bank[0]), meminfo_cmp, NULL);
-
 	memblock_init();
 	for (i = 0; i < mi->nr_banks; i++)
 		memblock_add(mi->bank[i].start, mi->bank[i].size);
@@ -403,8 +381,6 @@ void __init bootmem_init(void)
 	 */
 	arm_bootmem_free(min, max_low, max_high);

-	high_memory = __va(((phys_addr_t)max_low << PAGE_SHIFT) - 1) + 1;
-
 	/*
 	 * This doesn't seem to be used by the Linux memory manager any
 	 * more, but is used by ll_rw_block.  If we can get rid of it, we
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -36,12 +36,6 @@
 #include <asm/mach/map.h>
 #include "mm.h"

-/*
- * Used by ioremap() and iounmap() code to mark (super)section-mapped
- * I/O regions in vm_struct->flags field.
- */
-#define VM_ARM_SECTION_MAPPING	0x80000000
-
 int ioremap_page(unsigned long virt, unsigned long phys,
 		 const struct mem_type *mtype)
 {
@@ -64,7 +58,7 @@ void __check_kvm_seq(struct mm_struct *mm)
 	} while (seq != init_mm.context.kvm_seq);
 }

-#ifndef CONFIG_SMP
+#if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE)
 /*
 * Section support is unsafe on SMP - If you iounmap and ioremap a region,
 * the other CPUs will not see this change until their next context switch.
@@ -79,13 +73,16 @@ static void unmap_area_sections(unsigned long virt, unsigned long size)
 {
 	unsigned long addr = virt, end = virt + (size & ~(SZ_1M - 1));
 	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmdp;

 	flush_cache_vunmap(addr, end);
 	pgd = pgd_offset_k(addr);
+	pud = pud_offset(pgd, addr);
+	pmdp = pmd_offset(pud, addr);
 	do {
-		pmd_t pmd, *pmdp = pmd_offset(pgd, addr);
+		pmd_t pmd = *pmdp;

-		pmd = *pmdp;
 		if (!pmd_none(pmd)) {
 			/*
 			 * Clear the PMD from the page table, and
@@ -104,8 +101,8 @@ static void unmap_area_sections(unsigned long virt, unsigned long size)
 				pte_free_kernel(&init_mm, pmd_page_vaddr(pmd));
 		}

-		addr += PGDIR_SIZE;
-		pgd++;
+		addr += PMD_SIZE;
+		pmdp += 2;
 	} while (addr < end);

 	/*
@@ -124,6 +121,8 @@ remap_area_sections(unsigned long virt, unsigned long pfn,
 {
 	unsigned long addr = virt, end = virt + size;
 	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;

 	/*
 	 * Remove and free any PTE-based mapping, and
@@ -132,17 +131,17 @@ remap_area_sections(unsigned long virt, unsigned long pfn,
 	unmap_area_sections(virt, size);

 	pgd = pgd_offset_k(addr);
+	pud = pud_offset(pgd, addr);
+	pmd = pmd_offset(pud, addr);
 	do {
-		pmd_t *pmd = pmd_offset(pgd, addr);
-
 		pmd[0] = __pmd(__pfn_to_phys(pfn) | type->prot_sect);
 		pfn += SZ_1M >> PAGE_SHIFT;
 		pmd[1] = __pmd(__pfn_to_phys(pfn) | type->prot_sect);
 		pfn += SZ_1M >> PAGE_SHIFT;
 		flush_pmd_entry(pmd);

-		addr += PGDIR_SIZE;
-		pgd++;
+		addr += PMD_SIZE;
+		pmd += 2;
 	} while (addr < end);

 	return 0;
@@ -154,6 +153,8 @@ remap_area_supersections(unsigned long virt, unsigned long pfn,
 {
 	unsigned long addr = virt, end = virt + size;
 	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;

 	/*
 	 * Remove and free any PTE-based mapping, and
@@ -162,6 +163,8 @@ remap_area_supersections(unsigned long virt, unsigned long pfn,
 	unmap_area_sections(virt, size);

 	pgd = pgd_offset_k(virt);
+	pud = pud_offset(pgd, addr);
+	pmd = pmd_offset(pud, addr);
 	do {
 		unsigned long super_pmd_val, i;

@@ -170,14 +173,12 @@ remap_area_supersections(unsigned long virt, unsigned long pfn,
 		super_pmd_val |= ((pfn >> (32 - PAGE_SHIFT)) & 0xf) << 20;

 		for (i = 0; i < 8; i++) {
-			pmd_t *pmd = pmd_offset(pgd, addr);
-
 			pmd[0] = __pmd(super_pmd_val);
 			pmd[1] = __pmd(super_pmd_val);
 			flush_pmd_entry(pmd);

-			addr += PGDIR_SIZE;
-			pgd++;
+			addr += PMD_SIZE;
+			pmd += 2;
 		}

 		pfn += SUPERSECTION_SIZE >> PAGE_SHIFT;
@@ -195,17 +196,13 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
 	unsigned long addr;
 	struct vm_struct * area;

+#ifndef CONFIG_ARM_LPAE
 	/*
 	 * High mappings must be supersection aligned
 	 */
 	if (pfn >= 0x100000 && (__pfn_to_phys(pfn) & ~SUPERSECTION_MASK))
 		return NULL;
-
-	/*
-	 * Don't allow RAM to be mapped - this causes problems with ARMv6+
-	 */
-	if (WARN_ON(pfn_valid(pfn)))
-		return NULL;
+#endif

 	type = get_mem_type(mtype);
 	if (!type)
@@ -216,12 +213,40 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
 	 */
 	size = PAGE_ALIGN(offset + size);

+	/*
+	 * Try to reuse one of the static mapping whenever possible.
+	 */
+	read_lock(&vmlist_lock);
+	for (area = vmlist; area; area = area->next) {
+		if (!size || (sizeof(phys_addr_t) == 4 && pfn >= 0x100000))
+			break;
+		if (!(area->flags & VM_ARM_STATIC_MAPPING))
+			continue;
+		if ((area->flags & VM_ARM_MTYPE_MASK) != VM_ARM_MTYPE(mtype))
+			continue;
+		if (__phys_to_pfn(area->phys_addr) > pfn ||
+		    __pfn_to_phys(pfn) + size-1 > area->phys_addr + area->size-1)
+			continue;
+		/* we can drop the lock here as we know *area is static */
+		read_unlock(&vmlist_lock);
+		addr = (unsigned long)area->addr;
+		addr += __pfn_to_phys(pfn) - area->phys_addr;
+		return (void __iomem *) (offset + addr);
+	}
+	read_unlock(&vmlist_lock);
+
+	/*
+	 * Don't allow RAM to be mapped - this causes problems with ARMv6+
+	 */
+	if (WARN_ON(pfn_valid(pfn)))
+		return NULL;
+
 	area = get_vm_area_caller(size, VM_IOREMAP, caller);
 	if (!area)
 		return NULL;
 	addr = (unsigned long)area->addr;

-#ifndef CONFIG_SMP
+#if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE)
 	if (DOMAIN_IO == 0 &&
 	    (((cpu_architecture() >= CPU_ARCH_ARMv6) && (get_cr() & CR_XP)) ||
 	       cpu_is_xsc3()) && pfn >= 0x100000 &&
@@ -313,28 +338,34 @@ __arm_ioremap_exec(unsigned long phys_addr, size_t size, bool cached)
 void __iounmap(volatile void __iomem *io_addr)
 {
 	void *addr = (void *)(PAGE_MASK & (unsigned long)io_addr);
-#ifndef CONFIG_SMP
-	struct vm_struct **p, *tmp;
+	struct vm_struct *vm;

-	/*
-	 * If this is a section based mapping we need to handle it
-	 * specially as the VM subsystem does not know how to handle
-	 * such a beast. We need the lock here b/c we need to clear
-	 * all the mappings before the area can be reclaimed
-	 * by someone else.
-	 */
-	write_lock(&vmlist_lock);
-	for (p = &vmlist ; (tmp = *p) ; p = &tmp->next) {
-		if ((tmp->flags & VM_IOREMAP) && (tmp->addr == addr)) {
-			if (tmp->flags & VM_ARM_SECTION_MAPPING) {
-				unmap_area_sections((unsigned long)tmp->addr,
-						    tmp->size);
-			}
+	read_lock(&vmlist_lock);
+	for (vm = vmlist; vm; vm = vm->next) {
+		if (vm->addr > addr)
+			break;
+		if (!(vm->flags & VM_IOREMAP))
+			continue;
+		/* If this is a static mapping we must leave it alone */
+		if ((vm->flags & VM_ARM_STATIC_MAPPING) &&
+		    (vm->addr <= addr) && (vm->addr + vm->size > addr)) {
+			read_unlock(&vmlist_lock);
+			return;
+		}
+#if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE)
+		/*
+		 * If this is a section based mapping we need to handle it
+		 * specially as the VM subsystem does not know how to handle
+		 * such a beast.
+		 */
+		if ((vm->addr == addr) &&
+		    (vm->flags & VM_ARM_SECTION_MAPPING)) {
+			unmap_area_sections((unsigned long)vm->addr, vm->size);
 			break;
 		}
-	}
-	write_unlock(&vmlist_lock);
 #endif
+	}
+	read_unlock(&vmlist_lock);

 	vunmap(addr);
 }
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -21,6 +21,20 @@ const struct mem_type *get_mem_type(unsigned int type);

 extern void __flush_dcache_page(struct address_space *mapping, struct page *page);

+/*
+ * ARM specific vm_struct->flags bits.
+ */
+
+/* (super)section-mapped I/O regions used by ioremap()/iounmap() */
+#define VM_ARM_SECTION_MAPPING	0x80000000
+
+/* permanent static mappings from iotable_init() */
+#define VM_ARM_STATIC_MAPPING	0x40000000
+
+/* mapping type (attributes) for permanent static mappings */
+#define VM_ARM_MTYPE(mt)		((mt) << 20)
+#define VM_ARM_MTYPE_MASK	(0x1f << 20)
+
 #endif

 #ifdef CONFIG_ZONE_DMA
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -15,6 +15,7 @@
 #include <linux/nodemask.h>
 #include <linux/memblock.h>
 #include <linux/fs.h>
+#include <linux/vmalloc.h>

 #include <asm/cputype.h>
 #include <asm/sections.h>
@@ -150,6 +151,7 @@ static int __init early_nowrite(char *__unused)
 }
 early_param("nowb", early_nowrite);

+#ifndef CONFIG_ARM_LPAE
 static int __init early_ecc(char *p)
 {
 	if (memcmp(p, "on", 2) == 0)
@@ -159,6 +161,7 @@ static int __init early_ecc(char *p)
 	return 0;
 }
 early_param("ecc", early_ecc);
+#endif

 static int __init noalign_setup(char *__unused)
 {
@@ -228,10 +231,12 @@ static struct mem_type mem_types[] = {
 		.prot_sect = PMD_TYPE_SECT | PMD_SECT_XN,
 		.domain    = DOMAIN_KERNEL,
 	},
+#ifndef CONFIG_ARM_LPAE
 	[MT_MINICLEAN] = {
 		.prot_sect = PMD_TYPE_SECT | PMD_SECT_XN | PMD_SECT_MINICACHE,
 		.domain    = DOMAIN_KERNEL,
 	},
+#endif
 	[MT_LOW_VECTORS] = {
 		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
 				L_PTE_RDONLY,
@@ -429,6 +434,7 @@ static void __init build_mem_type_table(void)
 	 * ARMv6 and above have extended page tables.
 	 */
 	if (cpu_arch >= CPU_ARCH_ARMv6 && (cr & CR_XP)) {
+#ifndef CONFIG_ARM_LPAE
 		/*
 		 * Mark cache clean areas and XIP ROM read only
 		 * from SVC mode and no access from userspace.
@@ -436,6 +442,7 @@ static void __init build_mem_type_table(void)
 		mem_types[MT_ROM].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
 		mem_types[MT_MINICLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
 		mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
+#endif

 		if (is_smp()) {
 			/*
@@ -474,6 +481,18 @@ static void __init build_mem_type_table(void)
 		mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_BUFFERABLE;
 	}

+#ifdef CONFIG_ARM_LPAE
+	/*
+	 * Do not generate access flag faults for the kernel mappings.
+	 */
+	for (i = 0; i < ARRAY_SIZE(mem_types); i++) {
+		mem_types[i].prot_pte |= PTE_EXT_AF;
+		mem_types[i].prot_sect |= PMD_SECT_AF;
+	}
+	kern_pgprot |= PTE_EXT_AF;
+	vecs_pgprot |= PTE_EXT_AF;
+#endif
+
 	for (i = 0; i < 16; i++) {
 		unsigned long v = pgprot_val(protection_map[i]);
 		protection_map[i] = __pgprot(v | user_pgprot);
@@ -529,13 +548,18 @@ EXPORT_SYMBOL(phys_mem_access_prot);

 #define vectors_base()	(vectors_high() ? 0xffff0000 : 0)

-static void __init *early_alloc(unsigned long sz)
+static void __init *early_alloc_aligned(unsigned long sz, unsigned long align)
 {
-	void *ptr = __va(memblock_alloc(sz, sz));
+	void *ptr = __va(memblock_alloc(sz, align));
 	memset(ptr, 0, sz);
 	return ptr;
 }

+static void __init *early_alloc(unsigned long sz)
+{
+	return early_alloc_aligned(sz, sz);
+}
+
 static pte_t * __init early_pte_alloc(pmd_t *pmd, unsigned long addr, unsigned long prot)
 {
 	if (pmd_none(*pmd)) {
@@ -572,8 +596,10 @@ static void __init alloc_init_section(pud_t *pud, unsigned long addr,
 	if (((addr | end | phys) & ~SECTION_MASK) == 0) {
 		pmd_t *p = pmd;

+#ifndef CONFIG_ARM_LPAE
 		if (addr & SECTION_SIZE)
 			pmd++;
+#endif

 		do {
 			*pmd = __pmd(phys | type->prot_sect);
@@ -603,6 +629,7 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
 	} while (pud++, addr = next, addr != end);
 }

+#ifndef CONFIG_ARM_LPAE
 static void __init create_36bit_mapping(struct map_desc *md,
 					const struct mem_type *type)
 {
@@ -662,6 +689,7 @@ static void __init create_36bit_mapping(struct map_desc *md,
 		pgd += SUPERSECTION_SIZE >> PGDIR_SHIFT;
 	} while (addr != end);
 }
+#endif	/* !CONFIG_ARM_LPAE */

 /*
 * Create the page directory entries and any necessary
@@ -685,14 +713,16 @@ static void __init create_mapping(struct map_desc *md)
 	}

 	if ((md->type == MT_DEVICE || md->type == MT_ROM) &&
-	    md->virtual >= PAGE_OFFSET && md->virtual < VMALLOC_END) {
+	    md->virtual >= PAGE_OFFSET &&
+	    (md->virtual < VMALLOC_START || md->virtual >= VMALLOC_END)) {
 		printk(KERN_WARNING "BUG: mapping for 0x%08llx"
-		       " at 0x%08lx overlaps vmalloc space\n",
+		       " at 0x%08lx out of vmalloc space\n",
 		       (long long)__pfn_to_phys((u64)md->pfn), md->virtual);
 	}

 	type = &mem_types[md->type];

+#ifndef CONFIG_ARM_LPAE
 	/*
 	 * Catch 36-bit addresses
 	 */
@@ -700,6 +730,7 @@ static void __init create_mapping(struct map_desc *md)
 		create_36bit_mapping(md, type);
 		return;
 	}
+#endif

 	addr = md->virtual & PAGE_MASK;
 	phys = __pfn_to_phys(md->pfn);
@@ -729,18 +760,33 @@ static void __init create_mapping(struct map_desc *md)
 */
 void __init iotable_init(struct map_desc *io_desc, int nr)
 {
-	int i;
+	struct map_desc *md;
+	struct vm_struct *vm;

-	for (i = 0; i < nr; i++)
-		create_mapping(io_desc + i);
+	if (!nr)
+		return;
+
+	vm = early_alloc_aligned(sizeof(*vm) * nr, __alignof__(*vm));
+
+	for (md = io_desc; nr; md++, nr--) {
+		create_mapping(md);
+		vm->addr = (void *)(md->virtual & PAGE_MASK);
+		vm->size = PAGE_ALIGN(md->length + (md->virtual & ~PAGE_MASK));
+		vm->phys_addr = __pfn_to_phys(md->pfn); 
+		vm->flags = VM_IOREMAP | VM_ARM_STATIC_MAPPING; 
+		vm->flags |= VM_ARM_MTYPE(md->type);
+		vm->caller = iotable_init;
+		vm_area_add_early(vm++);
+	}
 }

-static void * __initdata vmalloc_min = (void *)(VMALLOC_END - SZ_128M);
+static void * __initdata vmalloc_min =
+	(void *)(VMALLOC_END - (240 << 20) - VMALLOC_OFFSET);

 /*
 * vmalloc=size forces the vmalloc area to be exactly 'size'
 * bytes. This can be used to increase (or decrease) the vmalloc
- * area - the default is 128m.
+ * area - the default is 240m.
 */
 static int __init early_vmalloc(char *arg)
 {
@@ -775,6 +821,9 @@ void __init sanity_check_meminfo(void)
 		struct membank *bank = &meminfo.bank[j];
 		*bank = meminfo.bank[i];

+		if (bank->start > ULONG_MAX)
+			highmem = 1;
+
 #ifdef CONFIG_HIGHMEM
 		if (__va(bank->start) >= vmalloc_min ||
 		    __va(bank->start) < (void *)PAGE_OFFSET)
@@ -786,7 +835,7 @@ void __init sanity_check_meminfo(void)
 		 * Split those memory banks which are partially overlapping
 		 * the vmalloc area greatly simplifying things later.
 		 */
-		if (__va(bank->start) < vmalloc_min &&
+		if (!highmem && __va(bank->start) < vmalloc_min &&
 		    bank->size > vmalloc_min - __va(bank->start)) {
 			if (meminfo.nr_banks >= NR_BANKS) {
 				printk(KERN_CRIT "NR_BANKS too low, "
@@ -806,6 +855,17 @@ void __init sanity_check_meminfo(void)
 #else
 		bank->highmem = highmem;

+		/*
+		 * Highmem banks not allowed with !CONFIG_HIGHMEM.
+		 */
+		if (highmem) {
+			printk(KERN_NOTICE "Ignoring RAM at %.8llx-%.8llx "
+			       "(!CONFIG_HIGHMEM).\n",
+			       (unsigned long long)bank->start,
+			       (unsigned long long)bank->start + bank->size - 1);
+			continue;
+		}
+
 		/*
 		 * Check whether this memory bank would entirely overlap
 		 * the vmalloc area.
@@ -860,6 +920,7 @@ void __init sanity_check_meminfo(void)
 	}
 #endif
 	meminfo.nr_banks = j;
+	high_memory = __va(lowmem_limit - 1) + 1;
 	memblock_set_current_limit(lowmem_limit);
 }

@@ -890,14 +951,20 @@ static inline void prepare_page_table(void)

 	/*
 	 * Clear out all the kernel space mappings, except for the first
-	 * memory bank, up to the end of the vmalloc region.
+	 * memory bank, up to the vmalloc region.
 	 */
 	for (addr = __phys_to_virt(end);
-	     addr < VMALLOC_END; addr += PMD_SIZE)
+	     addr < VMALLOC_START; addr += PMD_SIZE)
 		pmd_clear(pmd_off_k(addr));
 }

+#ifdef CONFIG_ARM_LPAE
+/* the first page is reserved for pgd */
+#define SWAPPER_PG_DIR_SIZE	(PAGE_SIZE + \
+				 PTRS_PER_PGD * PTRS_PER_PMD * sizeof(pmd_t))
+#else
 #define SWAPPER_PG_DIR_SIZE	(PTRS_PER_PGD * sizeof(pgd_t))
+#endif

 /*
 * Reserve the special regions of memory
@@ -920,8 +987,8 @@ void __init arm_mm_memblock_reserve(void)
 }

 /*
- * Set up device the mappings.  Since we clear out the page tables for all
- * mappings above VMALLOC_END, we will remove any debug device mappings.
+ * Set up the device mappings.  Since we clear out the page tables for all
+ * mappings above VMALLOC_START, we will remove any debug device mappings.
 * This means you have to be careful how you debug this function, or any
 * called function.  This means you can't use any function or debugging
 * method which may touch any device, otherwise the kernel _will_ crash.
@@ -936,7 +1003,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
 	 */
 	vectors_page = early_alloc(PAGE_SIZE);

-	for (addr = VMALLOC_END; addr; addr += PMD_SIZE)
+	for (addr = VMALLOC_START; addr; addr += PMD_SIZE)
 		pmd_clear(pmd_off_k(addr));

 	/*
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -29,6 +29,8 @@ void __init arm_mm_memblock_reserve(void)

 void __init sanity_check_meminfo(void)
 {
+	phys_addr_t end = bank_phys_end(&meminfo.bank[meminfo.nr_banks - 1]);
+	high_memory = __va(end - 1) + 1;
 }

 /*
@@ -43,7 +45,7 @@ void __init paging_init(struct machine_desc *mdesc)
 /*
 * We don't need to do anything here for nommu machines.
 */
-void setup_mm_for_reboot(char mode)
+void setup_mm_for_reboot(void)
 {
 }

--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -10,6 +10,7 @@
 #include <linux/mm.h>
 #include <linux/gfp.h>
 #include <linux/highmem.h>
+#include <linux/slab.h>

 #include <asm/pgalloc.h>
 #include <asm/page.h>
@@ -17,6 +18,14 @@

 #include "mm.h"

+#ifdef CONFIG_ARM_LPAE
+#define __pgd_alloc()	kmalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL)
+#define __pgd_free(pgd)	kfree(pgd)
+#else
+#define __pgd_alloc()	(pgd_t *)__get_free_pages(GFP_KERNEL, 2)
+#define __pgd_free(pgd)	free_pages((unsigned long)pgd, 2)
+#endif
+
 /*
 * need to get a 16k page for level 1
 */
@@ -27,7 +36,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 	pmd_t *new_pmd, *init_pmd;
 	pte_t *new_pte, *init_pte;

-	new_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL, 2);
+	new_pgd = __pgd_alloc();
 	if (!new_pgd)
 		goto no_pgd;

@@ -42,10 +51,25 @@ pgd_t *pgd_alloc(struct mm_struct *mm)

 	clean_dcache_area(new_pgd, PTRS_PER_PGD * sizeof(pgd_t));

+#ifdef CONFIG_ARM_LPAE
+	/*
+	 * Allocate PMD table for modules and pkmap mappings.
+	 */
+	new_pud = pud_alloc(mm, new_pgd + pgd_index(MODULES_VADDR),
+			    MODULES_VADDR);
+	if (!new_pud)
+		goto no_pud;
+
+	new_pmd = pmd_alloc(mm, new_pud, 0);
+	if (!new_pmd)
+		goto no_pmd;
+#endif
+
 	if (!vectors_high()) {
 		/*
 		 * On ARM, first page must always be allocated since it
-		 * contains the machine vectors.
+		 * contains the machine vectors. The vectors are always high
+		 * with LPAE.
 		 */
 		new_pud = pud_alloc(mm, new_pgd, 0);
 		if (!new_pud)
@@ -74,7 +98,7 @@ no_pte:
 no_pmd:
 	pud_free(mm, new_pud);
 no_pud:
-	free_pages((unsigned long)new_pgd, 2);
+	__pgd_free(new_pgd);
 no_pgd:
 	return NULL;
 }
@@ -111,5 +135,24 @@ no_pud:
 	pgd_clear(pgd);
 	pud_free(mm, pud);
 no_pgd:
-	free_pages((unsigned long) pgd_base, 2);
+#ifdef CONFIG_ARM_LPAE
+	/*
+	 * Free modules/pkmap or identity pmd tables.
+	 */
+	for (pgd = pgd_base; pgd < pgd_base + PTRS_PER_PGD; pgd++) {
+		if (pgd_none_or_clear_bad(pgd))
+			continue;
+		if (pgd_val(*pgd) & L_PGD_SWAPPER)
+			continue;
+		pud = pud_offset(pgd, 0);
+		if (pud_none_or_clear_bad(pud))
+			continue;
+		pmd = pmd_offset(pud, 0);
+		pud_clear(pud);
+		pmd_free(mm, pmd);
+		pgd_clear(pgd);
+		pud_free(mm, pud);
+	}
+#endif
+	__pgd_free(pgd_base);
 }
--- a/arch/arm/mm/proc-arm1020.S
+++ b/arch/arm/mm/proc-arm1020.S
@@ -95,6 +95,7 @@ ENTRY(cpu_arm1020_proc_fin)
 * loc: location to jump to for soft reset
 */
 	.align	5
+	.pushsection	.idmap.text, "ax"
 ENTRY(cpu_arm1020_reset)
 	mov	ip, #0
 	mcr	p15, 0, ip, c7, c7, 0		@ invalidate I,D caches
@@ -107,6 +108,8 @@ ENTRY(cpu_arm1020_reset)
 	bic	ip, ip, #0x1100 		@ ...i...s........
 	mcr	p15, 0, ip, c1, c0, 0		@ ctrl register
 	mov	pc, r0
+ENDPROC(cpu_arm1020_reset)
+	.popsection

 /*
 * cpu_arm1020_do_idle()
--- a/arch/arm/mm/proc-arm1020e.S
+++ b/arch/arm/mm/proc-arm1020e.S
@@ -95,6 +95,7 @@ ENTRY(cpu_arm1020e_proc_fin)
 * loc: location to jump to for soft reset
 */
 	.align	5
+	.pushsection	.idmap.text, "ax"
 ENTRY(cpu_arm1020e_reset)
 	mov	ip, #0
 	mcr	p15, 0, ip, c7, c7, 0		@ invalidate I,D caches
@@ -107,6 +108,8 @@ ENTRY(cpu_arm1020e_reset)
 	bic	ip, ip, #0x1100 		@ ...i...s........
 	mcr	p15, 0, ip, c1, c0, 0		@ ctrl register
 	mov	pc, r0
+ENDPROC(cpu_arm1020e_reset)
+	.popsection

 /*
 * cpu_arm1020e_do_idle()
--- a/arch/arm/mm/proc-arm1022.S
+++ b/arch/arm/mm/proc-arm1022.S
@@ -84,6 +84,7 @@ ENTRY(cpu_arm1022_proc_fin)
 * loc: location to jump to for soft reset
 */
 	.align	5
+	.pushsection	.idmap.text, "ax"
 ENTRY(cpu_arm1022_reset)
 	mov	ip, #0
 	mcr	p15, 0, ip, c7, c7, 0		@ invalidate I,D caches
@@ -96,6 +97,8 @@ ENTRY(cpu_arm1022_reset)
 	bic	ip, ip, #0x1100 		@ ...i...s........
 	mcr	p15, 0, ip, c1, c0, 0		@ ctrl register
 	mov	pc, r0
+ENDPROC(cpu_arm1022_reset)
+	.popsection

 /*
 * cpu_arm1022_do_idle()
--- a/arch/arm/mm/proc-arm1026.S
+++ b/arch/arm/mm/proc-arm1026.S
@@ -84,6 +84,7 @@ ENTRY(cpu_arm1026_proc_fin)
 * loc: location to jump to for soft reset
 */
 	.align	5
+	.pushsection	.idmap.text, "ax"
 ENTRY(cpu_arm1026_reset)
 	mov	ip, #0
 	mcr	p15, 0, ip, c7, c7, 0		@ invalidate I,D caches
@@ -96,6 +97,8 @@ ENTRY(cpu_arm1026_reset)
 	bic	ip, ip, #0x1100 		@ ...i...s........
 	mcr	p15, 0, ip, c1, c0, 0		@ ctrl register
 	mov	pc, r0
+ENDPROC(cpu_arm1026_reset)
+	.popsection

 /*
 * cpu_arm1026_do_idle()
--- a/arch/arm/mm/proc-arm6_7.S
+++ b/arch/arm/mm/proc-arm6_7.S
@@ -225,6 +225,7 @@ ENTRY(cpu_arm7_set_pte_ext)
 * Params  : r0 = address to jump to
 * Notes   : This sets up everything for a reset
 */
+		.pushsection	.idmap.text, "ax"
 ENTRY(cpu_arm6_reset)
 ENTRY(cpu_arm7_reset)
 		mov	r1, #0
@@ -235,6 +236,9 @@ ENTRY(cpu_arm7_reset)
 		mov	r1, #0x30
 		mcr	p15, 0, r1, c1, c0, 0		@ turn off MMU etc
 		mov	pc, r0
+ENDPROC(cpu_arm6_reset)
+ENDPROC(cpu_arm7_reset)
+		.popsection

 		__CPUINIT

--- a/arch/arm/mm/proc-arm720.S
+++ b/arch/arm/mm/proc-arm720.S
@@ -101,6 +101,7 @@ ENTRY(cpu_arm720_set_pte_ext)
 * Params  : r0 = address to jump to
 * Notes   : This sets up everything for a reset
 */
+		.pushsection	.idmap.text, "ax"
 ENTRY(cpu_arm720_reset)
 		mov	ip, #0
 		mcr	p15, 0, ip, c7, c7, 0		@ invalidate cache
@@ -112,6 +113,8 @@ ENTRY(cpu_arm720_reset)
 		bic	ip, ip, #0x2100			@ ..v....s........
 		mcr	p15, 0, ip, c1, c0, 0		@ ctrl register
 		mov	pc, r0
+ENDPROC(cpu_arm720_reset)
+		.popsection

 	__CPUINIT

--- a/arch/arm/mm/proc-arm740.S
+++ b/arch/arm/mm/proc-arm740.S
@@ -49,6 +49,7 @@ ENTRY(cpu_arm740_proc_fin)
 * Params  : r0 = address to jump to
 * Notes   : This sets up everything for a reset
 */
+	.pushsection	.idmap.text, "ax"
 ENTRY(cpu_arm740_reset)
 	mov	ip, #0
 	mcr	p15, 0, ip, c7, c0, 0		@ invalidate cache
@@ -56,6 +57,8 @@ ENTRY(cpu_arm740_reset)
 	bic	ip, ip, #0x0000000c		@ ............wc..
 	mcr	p15, 0, ip, c1, c0, 0		@ ctrl register
 	mov	pc, r0
+ENDPROC(cpu_arm740_reset)
+	.popsection

 	__CPUINIT

--- a/arch/arm/mm/proc-arm7tdmi.S
+++ b/arch/arm/mm/proc-arm7tdmi.S
@@ -45,8 +45,11 @@ ENTRY(cpu_arm7tdmi_proc_fin)
 * Params  : loc(r0)	address to jump to
 * Purpose : Sets up everything for a reset and jump to the location for soft reset.
 */
+		.pushsection	.idmap.text, "ax"
 ENTRY(cpu_arm7tdmi_reset)
 		mov	pc, r0
+ENDPROC(cpu_arm7tdmi_reset)
+		.popsection

 		__CPUINIT

--- a/arch/arm/mm/proc-arm920.S
+++ b/arch/arm/mm/proc-arm920.S
@@ -85,6 +85,7 @@ ENTRY(cpu_arm920_proc_fin)
 * loc: location to jump to for soft reset
 */
 	.align	5
+	.pushsection	.idmap.text, "ax"
 ENTRY(cpu_arm920_reset)
 	mov	ip, #0
 	mcr	p15, 0, ip, c7, c7, 0		@ invalidate I,D caches
@@ -97,6 +98,8 @@ ENTRY(cpu_arm920_reset)
 	bic	ip, ip, #0x1100			@ ...i...s........
 	mcr	p15, 0, ip, c1, c0, 0		@ ctrl register
 	mov	pc, r0
+ENDPROC(cpu_arm920_reset)
+	.popsection

 /*
 * cpu_arm920_do_idle()
--- a/arch/arm/mm/proc-arm922.S
+++ b/arch/arm/mm/proc-arm922.S
@@ -87,6 +87,7 @@ ENTRY(cpu_arm922_proc_fin)
 * loc: location to jump to for soft reset
 */
 	.align	5
+	.pushsection	.idmap.text, "ax"
 ENTRY(cpu_arm922_reset)
 	mov	ip, #0
 	mcr	p15, 0, ip, c7, c7, 0		@ invalidate I,D caches
@@ -99,6 +100,8 @@ ENTRY(cpu_arm922_reset)
 	bic	ip, ip, #0x1100			@ ...i...s........
 	mcr	p15, 0, ip, c1, c0, 0		@ ctrl register
 	mov	pc, r0
+ENDPROC(cpu_arm922_reset)
+	.popsection

 /*
 * cpu_arm922_do_idle()
--- a/arch/arm/mm/proc-arm925.S
+++ b/arch/arm/mm/proc-arm925.S
@@ -108,6 +108,7 @@ ENTRY(cpu_arm925_proc_fin)
 * loc: location to jump to for soft reset
 */
 	.align	5
+	.pushsection	.idmap.text, "ax"
 ENTRY(cpu_arm925_reset)
 	/* Send software reset to MPU and DSP */
 	mov	ip, #0xff000000
@@ -115,6 +116,8 @@ ENTRY(cpu_arm925_reset)
 	orr	ip, ip, #0x0000ce00
 	mov	r4, #1
 	strh	r4, [ip, #0x10]
+ENDPROC(cpu_arm925_reset)
+	.popsection

 	mov	ip, #0
 	mcr	p15, 0, ip, c7, c7, 0		@ invalidate I,D caches
--- a/arch/arm/mm/proc-arm926.S
+++ b/arch/arm/mm/proc-arm926.S
@@ -77,6 +77,7 @@ ENTRY(cpu_arm926_proc_fin)
 * loc: location to jump to for soft reset
 */
 	.align	5
+	.pushsection	.idmap.text, "ax"
 ENTRY(cpu_arm926_reset)
 	mov	ip, #0
 	mcr	p15, 0, ip, c7, c7, 0		@ invalidate I,D caches
@@ -89,6 +90,8 @@ ENTRY(cpu_arm926_reset)
 	bic	ip, ip, #0x1100			@ ...i...s........
 	mcr	p15, 0, ip, c1, c0, 0		@ ctrl register
 	mov	pc, r0
+ENDPROC(cpu_arm926_reset)
+	.popsection

 /*
 * cpu_arm926_do_idle()
--- a/arch/arm/mm/proc-arm940.S
+++ b/arch/arm/mm/proc-arm940.S
@@ -48,6 +48,7 @@ ENTRY(cpu_arm940_proc_fin)
 * Params  : r0 = address to jump to
 * Notes   : This sets up everything for a reset
 */
+	.pushsection	.idmap.text, "ax"
 ENTRY(cpu_arm940_reset)
 	mov	ip, #0
 	mcr	p15, 0, ip, c7, c5, 0		@ flush I cache
@@ -58,6 +59,8 @@ ENTRY(cpu_arm940_reset)
 	bic	ip, ip, #0x00001000		@ i-cache
 	mcr	p15, 0, ip, c1, c0, 0		@ ctrl register
 	mov	pc, r0
+ENDPROC(cpu_arm940_reset)
+	.popsection

 /*
 * cpu_arm940_do_idle()
--- a/arch/arm/mm/proc-arm946.S
+++ b/arch/arm/mm/proc-arm946.S
@@ -55,6 +55,7 @@ ENTRY(cpu_arm946_proc_fin)
 * Params  : r0 = address to jump to
 * Notes   : This sets up everything for a reset
 */
+	.pushsection	.idmap.text, "ax"
 ENTRY(cpu_arm946_reset)
 	mov	ip, #0
 	mcr	p15, 0, ip, c7, c5, 0		@ flush I cache
@@ -65,6 +66,8 @@ ENTRY(cpu_arm946_reset)
 	bic	ip, ip, #0x00001000		@ i-cache
 	mcr	p15, 0, ip, c1, c0, 0		@ ctrl register
 	mov	pc, r0
+ENDPROC(cpu_arm946_reset)
+	.popsection

 /*
 * cpu_arm946_do_idle()
--- a/arch/arm/mm/proc-arm9tdmi.S
+++ b/arch/arm/mm/proc-arm9tdmi.S
@@ -45,8 +45,11 @@ ENTRY(cpu_arm9tdmi_proc_fin)
 * Params  : loc(r0)	address to jump to
 * Purpose : Sets up everything for a reset and jump to the location for soft reset.
 */
+		.pushsection	.idmap.text, "ax"
 ENTRY(cpu_arm9tdmi_reset)
 		mov	pc, r0
+ENDPROC(cpu_arm9tdmi_reset)
+		.popsection

 		__CPUINIT

--- a/arch/arm/mm/proc-fa526.S
+++ b/arch/arm/mm/proc-fa526.S
@@ -57,6 +57,7 @@ ENTRY(cpu_fa526_proc_fin)
 * loc: location to jump to for soft reset
 */
 	.align	4
+	.pushsection	.idmap.text, "ax"
 ENTRY(cpu_fa526_reset)
 /* TODO: Use CP8 if possible... */
 	mov	ip, #0
@@ -73,6 +74,8 @@ ENTRY(cpu_fa526_reset)
 	nop
 	nop
 	mov	pc, r0
+ENDPROC(cpu_fa526_reset)
+	.popsection

 /*
 * cpu_fa526_do_idle()
--- a/arch/arm/mm/proc-feroceon.S
+++ b/arch/arm/mm/proc-feroceon.S
@@ -98,6 +98,7 @@ ENTRY(cpu_feroceon_proc_fin)
 * loc: location to jump to for soft reset
 */
 	.align	5
+	.pushsection	.idmap.text, "ax"
 ENTRY(cpu_feroceon_reset)
 	mov	ip, #0
 	mcr	p15, 0, ip, c7, c7, 0		@ invalidate I,D caches
@@ -110,6 +111,8 @@ ENTRY(cpu_feroceon_reset)
 	bic	ip, ip, #0x1100			@ ...i...s........
 	mcr	p15, 0, ip, c1, c0, 0		@ ctrl register
 	mov	pc, r0
+ENDPROC(cpu_feroceon_reset)
+	.popsection

 /*
 * cpu_feroceon_do_idle()
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -91,8 +91,9 @@
 #if L_PTE_SHARED != PTE_EXT_SHARED
 #error PTE shared bit mismatch
 #endif
-#if (L_PTE_XN+L_PTE_USER+L_PTE_RDONLY+L_PTE_DIRTY+L_PTE_YOUNG+\
-     L_PTE_FILE+L_PTE_PRESENT) > L_PTE_SHARED
+#if !defined (CONFIG_ARM_LPAE) && \
+	(L_PTE_XN+L_PTE_USER+L_PTE_RDONLY+L_PTE_DIRTY+L_PTE_YOUNG+\
+	 L_PTE_FILE+L_PTE_PRESENT) > L_PTE_SHARED
 #error Invalid Linux PTE bit settings
 #endif
 #endif	/* CONFIG_MMU */
--- a/arch/arm/mm/proc-mohawk.S
+++ b/arch/arm/mm/proc-mohawk.S
@@ -69,6 +69,7 @@ ENTRY(cpu_mohawk_proc_fin)
 * (same as arm926)
 */
 	.align	5
+	.pushsection	.idmap.text, "ax"
 ENTRY(cpu_mohawk_reset)
 	mov	ip, #0
 	mcr	p15, 0, ip, c7, c7, 0		@ invalidate I,D caches
@@ -79,6 +80,8 @@ ENTRY(cpu_mohawk_reset)
 	bic	ip, ip, #0x1100			@ ...i...s........
 	mcr	p15, 0, ip, c1, c0, 0		@ ctrl register
 	mov	pc, r0
+ENDPROC(cpu_mohawk_reset)
+	.popsection

 /*
 * cpu_mohawk_do_idle()
--- a/arch/arm/mm/proc-sa110.S
+++ b/arch/arm/mm/proc-sa110.S
@@ -62,6 +62,7 @@ ENTRY(cpu_sa110_proc_fin)
 * loc: location to jump to for soft reset
 */
 	.align	5
+	.pushsection	.idmap.text, "ax"
 ENTRY(cpu_sa110_reset)
 	mov	ip, #0
 	mcr	p15, 0, ip, c7, c7, 0		@ invalidate I,D caches
@@ -74,6 +75,8 @@ ENTRY(cpu_sa110_reset)
 	bic	ip, ip, #0x1100			@ ...i...s........
 	mcr	p15, 0, ip, c1, c0, 0		@ ctrl register
 	mov	pc, r0
+ENDPROC(cpu_sa110_reset)
+	.popsection

 /*
 * cpu_sa110_do_idle(type)
--- a/arch/arm/mm/proc-sa1100.S
+++ b/arch/arm/mm/proc-sa1100.S
@@ -70,6 +70,7 @@ ENTRY(cpu_sa1100_proc_fin)
 * loc: location to jump to for soft reset
 */
 	.align	5
+	.pushsection	.idmap.text, "ax"
 ENTRY(cpu_sa1100_reset)
 	mov	ip, #0
 	mcr	p15, 0, ip, c7, c7, 0		@ invalidate I,D caches
@@ -82,6 +83,8 @@ ENTRY(cpu_sa1100_reset)
 	bic	ip, ip, #0x1100			@ ...i...s........
 	mcr	p15, 0, ip, c1, c0, 0		@ ctrl register
 	mov	pc, r0
+ENDPROC(cpu_sa1100_reset)
+	.popsection

 /*
 * cpu_sa1100_do_idle(type)
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -55,6 +55,7 @@ ENTRY(cpu_v6_proc_fin)
 *	- loc   - location to jump to for soft reset
 */
 	.align	5
+	.pushsection	.idmap.text, "ax"
 ENTRY(cpu_v6_reset)
 	mrc	p15, 0, r1, c1, c0, 0		@ ctrl register
 	bic	r1, r1, #0x1			@ ...............m
@@ -62,6 +63,8 @@ ENTRY(cpu_v6_reset)
 	mov	r1, #0
 	mcr	p15, 0, r1, c7, c5, 4		@ ISB
 	mov	pc, r0
+ENDPROC(cpu_v6_reset)
+	.popsection

 /*
 *	cpu_v6_do_idle()
--- a/arch/arm/mm/proc-v7-2level.S
+++ b/arch/arm/mm/proc-v7-2level.S
@@ -0,0 +1,171 @@
+/*
+ * arch/arm/mm/proc-v7-2level.S
+ *
+ * Copyright (C) 2001 Deep Blue Solutions Ltd.
+ *
+ * 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.
+ */
+
+#define TTB_S		(1 << 1)
+#define TTB_RGN_NC	(0 << 3)
+#define TTB_RGN_OC_WBWA	(1 << 3)
+#define TTB_RGN_OC_WT	(2 << 3)
+#define TTB_RGN_OC_WB	(3 << 3)
+#define TTB_NOS		(1 << 5)
+#define TTB_IRGN_NC	((0 << 0) | (0 << 6))
+#define TTB_IRGN_WBWA	((0 << 0) | (1 << 6))
+#define TTB_IRGN_WT	((1 << 0) | (0 << 6))
+#define TTB_IRGN_WB	((1 << 0) | (1 << 6))
+
+/* PTWs cacheable, inner WB not shareable, outer WB not shareable */
+#define TTB_FLAGS_UP	TTB_IRGN_WB|TTB_RGN_OC_WB
+#define PMD_FLAGS_UP	PMD_SECT_WB
+
+/* PTWs cacheable, inner WBWA shareable, outer WBWA not shareable */
+#define TTB_FLAGS_SMP	TTB_IRGN_WBWA|TTB_S|TTB_NOS|TTB_RGN_OC_WBWA
+#define PMD_FLAGS_SMP	PMD_SECT_WBWA|PMD_SECT_S
+
+/*
+ *	cpu_v7_switch_mm(pgd_phys, tsk)
+ *
+ *	Set the translation table base pointer to be pgd_phys
+ *
+ *	- pgd_phys - physical address of new TTB
+ *
+ *	It is assumed that:
+ *	- we are not using split page tables
+ */
+ENTRY(cpu_v7_switch_mm)
+#ifdef CONFIG_MMU
+	mov	r2, #0
+	ldr	r1, [r1, #MM_CONTEXT_ID]	@ get mm->context.id
+	ALT_SMP(orr	r0, r0, #TTB_FLAGS_SMP)
+	ALT_UP(orr	r0, r0, #TTB_FLAGS_UP)
+#ifdef CONFIG_ARM_ERRATA_430973
+	mcr	p15, 0, r2, c7, c5, 6		@ flush BTAC/BTB
+#endif
+#ifdef CONFIG_ARM_ERRATA_754322
+	dsb
+#endif
+	mcr	p15, 0, r2, c13, c0, 1		@ set reserved context ID
+	isb
+1:	mcr	p15, 0, r0, c2, c0, 0		@ set TTB 0
+	isb
+#ifdef CONFIG_ARM_ERRATA_754322
+	dsb
+#endif
+	mcr	p15, 0, r1, c13, c0, 1		@ set context ID
+	isb
+#endif
+	mov	pc, lr
+ENDPROC(cpu_v7_switch_mm)
+
+/*
+ *	cpu_v7_set_pte_ext(ptep, pte)
+ *
+ *	Set a level 2 translation table entry.
+ *
+ *	- ptep  - pointer to level 2 translation table entry
+ *		  (hardware version is stored at +2048 bytes)
+ *	- pte   - PTE value to store
+ *	- ext	- value for extended PTE bits
+ */
+ENTRY(cpu_v7_set_pte_ext)
+#ifdef CONFIG_MMU
+	str	r1, [r0]			@ linux version
+
+	bic	r3, r1, #0x000003f0
+	bic	r3, r3, #PTE_TYPE_MASK
+	orr	r3, r3, r2
+	orr	r3, r3, #PTE_EXT_AP0 | 2
+
+	tst	r1, #1 << 4
+	orrne	r3, r3, #PTE_EXT_TEX(1)
+
+	eor	r1, r1, #L_PTE_DIRTY
+	tst	r1, #L_PTE_RDONLY | L_PTE_DIRTY
+	orrne	r3, r3, #PTE_EXT_APX
+
+	tst	r1, #L_PTE_USER
+	orrne	r3, r3, #PTE_EXT_AP1
+#ifdef CONFIG_CPU_USE_DOMAINS
+	@ allow kernel read/write access to read-only user pages
+	tstne	r3, #PTE_EXT_APX
+	bicne	r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
+#endif
+
+	tst	r1, #L_PTE_XN
+	orrne	r3, r3, #PTE_EXT_XN
+
+	tst	r1, #L_PTE_YOUNG
+	tstne	r1, #L_PTE_PRESENT
+	moveq	r3, #0
+
+ ARM(	str	r3, [r0, #2048]! )
+ THUMB(	add	r0, r0, #2048 )
+ THUMB(	str	r3, [r0] )
+	mcr	p15, 0, r0, c7, c10, 1		@ flush_pte
+#endif
+	mov	pc, lr
+ENDPROC(cpu_v7_set_pte_ext)
+
+	/*
+	 * Memory region attributes with SCTLR.TRE=1
+	 *
+	 *   n = TEX[0],C,B
+	 *   TR = PRRR[2n+1:2n]		- memory type
+	 *   IR = NMRR[2n+1:2n]		- inner cacheable property
+	 *   OR = NMRR[2n+17:2n+16]	- outer cacheable property
+	 *
+	 *			n	TR	IR	OR
+	 *   UNCACHED		000	00
+	 *   BUFFERABLE		001	10	00	00
+	 *   WRITETHROUGH	010	10	10	10
+	 *   WRITEBACK		011	10	11	11
+	 *   reserved		110
+	 *   WRITEALLOC		111	10	01	01
+	 *   DEV_SHARED		100	01
+	 *   DEV_NONSHARED	100	01
+	 *   DEV_WC		001	10
+	 *   DEV_CACHED		011	10
+	 *
+	 * Other attributes:
+	 *
+	 *   DS0 = PRRR[16] = 0		- device shareable property
+	 *   DS1 = PRRR[17] = 1		- device shareable property
+	 *   NS0 = PRRR[18] = 0		- normal shareable property
+	 *   NS1 = PRRR[19] = 1		- normal shareable property
+	 *   NOS = PRRR[24+n] = 1	- not outer shareable
+	 */
+.equ	PRRR,	0xff0a81a8
+.equ	NMRR,	0x40e040e0
+
+	/*
+	 * Macro for setting up the TTBRx and TTBCR registers.
+	 * - \ttb0 and \ttb1 updated with the corresponding flags.
+	 */
+	.macro	v7_ttb_setup, zero, ttbr0, ttbr1, tmp
+	mcr	p15, 0, \zero, c2, c0, 2	@ TTB control register
+	ALT_SMP(orr	\ttbr0, \ttbr0, #TTB_FLAGS_SMP)
+	ALT_UP(orr	\ttbr0, \ttbr0, #TTB_FLAGS_UP)
+	ALT_SMP(orr	\ttbr1, \ttbr1, #TTB_FLAGS_SMP)
+	ALT_UP(orr	\ttbr1, \ttbr1, #TTB_FLAGS_UP)
+	mcr	p15, 0, \ttbr1, c2, c0, 1	@ load TTB1
+	.endm
+
+	__CPUINIT
+
+	/*   AT
+	 *  TFR   EV X F   I D LR    S
+	 * .EEE ..EE PUI. .T.T 4RVI ZWRS BLDP WCAM
+	 * rxxx rrxx xxx0 0101 xxxx xxxx x111 xxxx < forced
+	 *    1    0 110       0011 1100 .111 1101 < we want
+	 */
+	.align	2
+	.type	v7_crval, #object
+v7_crval:
+	crval	clear=0x0120c302, mmuset=0x10c03c7d, ucset=0x00c01c7c
+
+	.previous
--- a/arch/arm/mm/proc-v7-3level.S
+++ b/arch/arm/mm/proc-v7-3level.S
@@ -0,0 +1,150 @@
+/*
+ * arch/arm/mm/proc-v7-3level.S
+ *
+ * Copyright (C) 2001 Deep Blue Solutions Ltd.
+ * Copyright (C) 2011 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ *   based on arch/arm/mm/proc-v7-2level.S
+ *
+ * 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
+ */
+
+#define TTB_IRGN_NC	(0 << 8)
+#define TTB_IRGN_WBWA	(1 << 8)
+#define TTB_IRGN_WT	(2 << 8)
+#define TTB_IRGN_WB	(3 << 8)
+#define TTB_RGN_NC	(0 << 10)
+#define TTB_RGN_OC_WBWA	(1 << 10)
+#define TTB_RGN_OC_WT	(2 << 10)
+#define TTB_RGN_OC_WB	(3 << 10)
+#define TTB_S		(3 << 12)
+#define TTB_EAE		(1 << 31)
+
+/* PTWs cacheable, inner WB not shareable, outer WB not shareable */
+#define TTB_FLAGS_UP	(TTB_IRGN_WB|TTB_RGN_OC_WB)
+#define PMD_FLAGS_UP	(PMD_SECT_WB)
+
+/* PTWs cacheable, inner WBWA shareable, outer WBWA not shareable */
+#define TTB_FLAGS_SMP	(TTB_IRGN_WBWA|TTB_S|TTB_RGN_OC_WBWA)
+#define PMD_FLAGS_SMP	(PMD_SECT_WBWA|PMD_SECT_S)
+
+/*
+ * cpu_v7_switch_mm(pgd_phys, tsk)
+ *
+ * Set the translation table base pointer to be pgd_phys (physical address of
+ * the new TTB).
+ */
+ENTRY(cpu_v7_switch_mm)
+#ifdef CONFIG_MMU
+	ldr	r1, [r1, #MM_CONTEXT_ID]	@ get mm->context.id
+	and	r3, r1, #0xff
+	mov	r3, r3, lsl #(48 - 32)		@ ASID
+	mcrr	p15, 0, r0, r3, c2		@ set TTB 0
+	isb
+#endif
+	mov	pc, lr
+ENDPROC(cpu_v7_switch_mm)
+
+/*
+ * cpu_v7_set_pte_ext(ptep, pte)
+ *
+ * Set a level 2 translation table entry.
+ * - ptep - pointer to level 3 translation table entry
+ * - pte - PTE value to store (64-bit in r2 and r3)
+ */
+ENTRY(cpu_v7_set_pte_ext)
+#ifdef CONFIG_MMU
+	tst	r2, #L_PTE_PRESENT
+	beq	1f
+	tst	r3, #1 << (55 - 32)		@ L_PTE_DIRTY
+	orreq	r2, #L_PTE_RDONLY
+1:	strd	r2, r3, [r0]
+	mcr	p15, 0, r0, c7, c10, 1		@ flush_pte
+#endif
+	mov	pc, lr
+ENDPROC(cpu_v7_set_pte_ext)
+
+	/*
+	 * Memory region attributes for LPAE (defined in pgtable-3level.h):
+	 *
+	 *   n = AttrIndx[2:0]
+	 *
+	 *			n	MAIR
+	 *   UNCACHED		000	00000000
+	 *   BUFFERABLE		001	01000100
+	 *   DEV_WC		001	01000100
+	 *   WRITETHROUGH	010	10101010
+	 *   WRITEBACK		011	11101110
+	 *   DEV_CACHED		011	11101110
+	 *   DEV_SHARED		100	00000100
+	 *   DEV_NONSHARED	100	00000100
+	 *   unused		101
+	 *   unused		110
+	 *   WRITEALLOC		111	11111111
+	 */
+.equ	PRRR,	0xeeaa4400			@ MAIR0
+.equ	NMRR,	0xff000004			@ MAIR1
+
+	/*
+	 * Macro for setting up the TTBRx and TTBCR registers.
+	 * - \ttbr1 updated.
+	 */
+	.macro	v7_ttb_setup, zero, ttbr0, ttbr1, tmp
+	ldr	\tmp, =swapper_pg_dir		@ swapper_pg_dir virtual address
+	cmp	\ttbr1, \tmp			@ PHYS_OFFSET > PAGE_OFFSET? (branch below)
+	mrc	p15, 0, \tmp, c2, c0, 2		@ TTB control register
+	orr	\tmp, \tmp, #TTB_EAE
+	ALT_SMP(orr	\tmp, \tmp, #TTB_FLAGS_SMP)
+	ALT_UP(orr	\tmp, \tmp, #TTB_FLAGS_UP)
+	ALT_SMP(orr	\tmp, \tmp, #TTB_FLAGS_SMP << 16)
+	ALT_UP(orr	\tmp, \tmp, #TTB_FLAGS_UP << 16)
+	/*
+	 * TTBR0/TTBR1 split (PAGE_OFFSET):
+	 *   0x40000000: T0SZ = 2, T1SZ = 0 (not used)
+	 *   0x80000000: T0SZ = 0, T1SZ = 1
+	 *   0xc0000000: T0SZ = 0, T1SZ = 2
+	 *
+	 * Only use this feature if PHYS_OFFSET <= PAGE_OFFSET, otherwise
+	 * booting secondary CPUs would end up using TTBR1 for the identity
+	 * mapping set up in TTBR0.
+	 */
+	bhi	9001f				@ PHYS_OFFSET > PAGE_OFFSET?
+	orr	\tmp, \tmp, #(((PAGE_OFFSET >> 30) - 1) << 16) @ TTBCR.T1SZ
+#if defined CONFIG_VMSPLIT_2G
+	/* PAGE_OFFSET == 0x80000000, T1SZ == 1 */
+	add	\ttbr1, \ttbr1, #1 << 4		@ skip two L1 entries
+#elif defined CONFIG_VMSPLIT_3G
+	/* PAGE_OFFSET == 0xc0000000, T1SZ == 2 */
+	add	\ttbr1, \ttbr1, #4096 * (1 + 3)	@ only L2 used, skip pgd+3*pmd
+#endif
+	/* CONFIG_VMSPLIT_1G does not need TTBR1 adjustment */
+9001:	mcr	p15, 0, \tmp, c2, c0, 2		@ TTB control register
+	mcrr	p15, 1, \ttbr1, \zero, c2	@ load TTBR1
+	.endm
+
+	__CPUINIT
+
+	/*
+	 *   AT
+	 *  TFR   EV X F   IHD LR    S
+	 * .EEE ..EE PUI. .TAT 4RVI ZWRS BLDP WCAM
+	 * rxxx rrxx xxx0 0101 xxxx xxxx x111 xxxx < forced
+	 *   11    0 110    1  0011 1100 .111 1101 < we want
+	 */
+	.align	2
+	.type	v7_crval, #object
+v7_crval:
+	crval	clear=0x0120c302, mmuset=0x30c23c7d, ucset=0x00c01c7c
+
+	.previous
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -19,24 +19,11 @@

 #include "proc-macros.S"

-#define TTB_S		(1 << 1)
-#define TTB_RGN_NC	(0 << 3)
-#define TTB_RGN_OC_WBWA	(1 << 3)
-#define TTB_RGN_OC_WT	(2 << 3)
-#define TTB_RGN_OC_WB	(3 << 3)
-#define TTB_NOS		(1 << 5)
-#define TTB_IRGN_NC	((0 << 0) | (0 << 6))
-#define TTB_IRGN_WBWA	((0 << 0) | (1 << 6))
-#define TTB_IRGN_WT	((1 << 0) | (0 << 6))
-#define TTB_IRGN_WB	((1 << 0) | (1 << 6))
-
-/* PTWs cacheable, inner WB not shareable, outer WB not shareable */
-#define TTB_FLAGS_UP	TTB_IRGN_WB|TTB_RGN_OC_WB
-#define PMD_FLAGS_UP	PMD_SECT_WB
-
-/* PTWs cacheable, inner WBWA shareable, outer WBWA not shareable */
-#define TTB_FLAGS_SMP	TTB_IRGN_WBWA|TTB_S|TTB_NOS|TTB_RGN_OC_WBWA
-#define PMD_FLAGS_SMP	PMD_SECT_WBWA|PMD_SECT_S
+#ifdef CONFIG_ARM_LPAE
+#include "proc-v7-3level.S"
+#else
+#include "proc-v7-2level.S"
+#endif

 ENTRY(cpu_v7_proc_init)
 	mov	pc, lr
@@ -63,6 +50,7 @@ ENDPROC(cpu_v7_proc_fin)
 *      caches disabled.
 */
 	.align	5
+	.pushsection	.idmap.text, "ax"
 ENTRY(cpu_v7_reset)
 	mrc	p15, 0, r1, c1, c0, 0		@ ctrl register
 	bic	r1, r1, #0x1			@ ...............m
@@ -71,6 +59,7 @@ ENTRY(cpu_v7_reset)
 	isb
 	mov	pc, r0
 ENDPROC(cpu_v7_reset)
+	.popsection

 /*
 *	cpu_v7_do_idle()
@@ -97,127 +86,12 @@ ENTRY(cpu_v7_dcache_clean_area)
 	mov	pc, lr
 ENDPROC(cpu_v7_dcache_clean_area)

-/*
- *	cpu_v7_switch_mm(pgd_phys, tsk)
- *
- *	Set the translation table base pointer to be pgd_phys
- *
- *	- pgd_phys - physical address of new TTB
- *
- *	It is assumed that:
- *	- we are not using split page tables
- */
-ENTRY(cpu_v7_switch_mm)
-#ifdef CONFIG_MMU
-	mov	r2, #0
-	ldr	r1, [r1, #MM_CONTEXT_ID]	@ get mm->context.id
-	ALT_SMP(orr	r0, r0, #TTB_FLAGS_SMP)
-	ALT_UP(orr	r0, r0, #TTB_FLAGS_UP)
-#ifdef CONFIG_ARM_ERRATA_430973
-	mcr	p15, 0, r2, c7, c5, 6		@ flush BTAC/BTB
-#endif
-#ifdef CONFIG_ARM_ERRATA_754322
-	dsb
-#endif
-	mcr	p15, 0, r2, c13, c0, 1		@ set reserved context ID
-	isb
-1:	mcr	p15, 0, r0, c2, c0, 0		@ set TTB 0
-	isb
-#ifdef CONFIG_ARM_ERRATA_754322
-	dsb
-#endif
-	mcr	p15, 0, r1, c13, c0, 1		@ set context ID
-	isb
-#endif
-	mov	pc, lr
-ENDPROC(cpu_v7_switch_mm)
-
-/*
- *	cpu_v7_set_pte_ext(ptep, pte)
- *
- *	Set a level 2 translation table entry.
- *
- *	- ptep  - pointer to level 2 translation table entry
- *		  (hardware version is stored at +2048 bytes)
- *	- pte   - PTE value to store
- *	- ext	- value for extended PTE bits
- */
-ENTRY(cpu_v7_set_pte_ext)
-#ifdef CONFIG_MMU
-	str	r1, [r0]			@ linux version
-
-	bic	r3, r1, #0x000003f0
-	bic	r3, r3, #PTE_TYPE_MASK
-	orr	r3, r3, r2
-	orr	r3, r3, #PTE_EXT_AP0 | 2
-
-	tst	r1, #1 << 4
-	orrne	r3, r3, #PTE_EXT_TEX(1)
-
-	eor	r1, r1, #L_PTE_DIRTY
-	tst	r1, #L_PTE_RDONLY | L_PTE_DIRTY
-	orrne	r3, r3, #PTE_EXT_APX
-
-	tst	r1, #L_PTE_USER
-	orrne	r3, r3, #PTE_EXT_AP1
-#ifdef CONFIG_CPU_USE_DOMAINS
-	@ allow kernel read/write access to read-only user pages
-	tstne	r3, #PTE_EXT_APX
-	bicne	r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
-#endif
-
-	tst	r1, #L_PTE_XN
-	orrne	r3, r3, #PTE_EXT_XN
-
-	tst	r1, #L_PTE_YOUNG
-	tstne	r1, #L_PTE_PRESENT
-	moveq	r3, #0
-
- ARM(	str	r3, [r0, #2048]! )
- THUMB(	add	r0, r0, #2048 )
- THUMB(	str	r3, [r0] )
-	mcr	p15, 0, r0, c7, c10, 1		@ flush_pte
-#endif
-	mov	pc, lr
-ENDPROC(cpu_v7_set_pte_ext)
-
 	string	cpu_v7_name, "ARMv7 Processor"
 	.align

-	/*
-	 * Memory region attributes with SCTLR.TRE=1
-	 *
-	 *   n = TEX[0],C,B
-	 *   TR = PRRR[2n+1:2n]		- memory type
-	 *   IR = NMRR[2n+1:2n]		- inner cacheable property
-	 *   OR = NMRR[2n+17:2n+16]	- outer cacheable property
-	 *
-	 *			n	TR	IR	OR
-	 *   UNCACHED		000	00
-	 *   BUFFERABLE		001	10	00	00
-	 *   WRITETHROUGH	010	10	10	10
-	 *   WRITEBACK		011	10	11	11
-	 *   reserved		110
-	 *   WRITEALLOC		111	10	01	01
-	 *   DEV_SHARED		100	01
-	 *   DEV_NONSHARED	100	01
-	 *   DEV_WC		001	10
-	 *   DEV_CACHED		011	10
-	 *
-	 * Other attributes:
-	 *
-	 *   DS0 = PRRR[16] = 0		- device shareable property
-	 *   DS1 = PRRR[17] = 1		- device shareable property
-	 *   NS0 = PRRR[18] = 0		- normal shareable property
-	 *   NS1 = PRRR[19] = 1		- normal shareable property
-	 *   NOS = PRRR[24+n] = 1	- not outer shareable
-	 */
-.equ	PRRR,	0xff0a81a8
-.equ	NMRR,	0x40e040e0
-
 /* Suspend/resume support: derived from arch/arm/mach-s5pv210/sleep.S */
 .globl	cpu_v7_suspend_size
-.equ	cpu_v7_suspend_size, 4 * 7
+.equ	cpu_v7_suspend_size, 4 * 8
 #ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_v7_do_suspend)
 	stmfd	sp!, {r4 - r10, lr}
@@ -226,10 +100,11 @@ ENTRY(cpu_v7_do_suspend)
 	stmia	r0!, {r4 - r5}
 	mrc	p15, 0, r6, c3, c0, 0	@ Domain ID
 	mrc	p15, 0, r7, c2, c0, 1	@ TTB 1
+	mrc	p15, 0, r11, c2, c0, 2	@ TTB control register
 	mrc	p15, 0, r8, c1, c0, 0	@ Control register
 	mrc	p15, 0, r9, c1, c0, 1	@ Auxiliary control register
 	mrc	p15, 0, r10, c1, c0, 2	@ Co-processor access control
-	stmia	r0, {r6 - r10}
+	stmia	r0, {r6 - r11}
 	ldmfd	sp!, {r4 - r10, pc}
 ENDPROC(cpu_v7_do_suspend)

@@ -241,13 +116,15 @@ ENTRY(cpu_v7_do_resume)
 	ldmia	r0!, {r4 - r5}
 	mcr	p15, 0, r4, c13, c0, 0	@ FCSE/PID
 	mcr	p15, 0, r5, c13, c0, 3	@ User r/o thread ID
-	ldmia	r0, {r6 - r10}
+	ldmia	r0, {r6 - r11}
 	mcr	p15, 0, r6, c3, c0, 0	@ Domain ID
+#ifndef CONFIG_ARM_LPAE
 	ALT_SMP(orr	r1, r1, #TTB_FLAGS_SMP)
 	ALT_UP(orr	r1, r1, #TTB_FLAGS_UP)
+#endif
 	mcr	p15, 0, r1, c2, c0, 0	@ TTB 0
 	mcr	p15, 0, r7, c2, c0, 1	@ TTB 1
-	mcr	p15, 0, ip, c2, c0, 2	@ TTB control register
+	mcr	p15, 0, r11, c2, c0, 2	@ TTB control register
 	mrc	p15, 0, r4, c1, c0, 1	@ Read Auxiliary control register
 	teq	r4, r9			@ Is it already set?
 	mcrne	p15, 0, r9, c1, c0, 1	@ No, so write it
@@ -380,12 +257,7 @@ __v7_setup:
 	dsb
 #ifdef CONFIG_MMU
 	mcr	p15, 0, r10, c8, c7, 0		@ invalidate I + D TLBs
-	mcr	p15, 0, r10, c2, c0, 2		@ TTB control register
-	ALT_SMP(orr	r4, r4, #TTB_FLAGS_SMP)
-	ALT_UP(orr	r4, r4, #TTB_FLAGS_UP)
-	ALT_SMP(orr	r8, r8, #TTB_FLAGS_SMP)
-	ALT_UP(orr	r8, r8, #TTB_FLAGS_UP)
-	mcr	p15, 0, r8, c2, c0, 1		@ load TTB1
+	v7_ttb_setup r10, r4, r8, r5		@ TTBCR, TTBRx setup
 	ldr	r5, =PRRR			@ PRRR
 	ldr	r6, =NMRR			@ NMRR
 	mcr	p15, 0, r5, c10, c2, 0		@ write PRRR
@@ -407,16 +279,7 @@ __v7_setup:
 	mov	pc, lr				@ return to head.S:__ret
 ENDPROC(__v7_setup)

-	/*   AT
-	 *  TFR   EV X F   I D LR    S
-	 * .EEE ..EE PUI. .T.T 4RVI ZWRS BLDP WCAM
-	 * rxxx rrxx xxx0 0101 xxxx xxxx x111 xxxx < forced
-	 *    1    0 110       0011 1100 .111 1101 < we want
-	 */
-	.type	v7_crval, #object
-v7_crval:
-	crval	clear=0x0120c302, mmuset=0x10c03c7d, ucset=0x00c01c7c
-
+	.align	2
 __v7_setup_stack:
 	.space	4 * 11				@ 11 registers

@@ -438,11 +301,11 @@ __v7_setup_stack:
 	 */
 .macro __v7_proc initfunc, mm_mmuflags = 0, io_mmuflags = 0, hwcaps = 0
 	ALT_SMP(.long	PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AP_READ | \
-			PMD_FLAGS_SMP | \mm_mmuflags)
+			PMD_SECT_AF | PMD_FLAGS_SMP | \mm_mmuflags)
 	ALT_UP(.long	PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AP_READ | \
-			PMD_FLAGS_UP | \mm_mmuflags)
-	.long	PMD_TYPE_SECT | PMD_SECT_XN | PMD_SECT_AP_WRITE | \
-		PMD_SECT_AP_READ | \io_mmuflags
+			PMD_SECT_AF | PMD_FLAGS_UP | \mm_mmuflags)
+	.long	PMD_TYPE_SECT | PMD_SECT_AP_WRITE | \
+		PMD_SECT_AP_READ | PMD_SECT_AF | \io_mmuflags
 	W(b)	\initfunc
 	.long	cpu_arch_name
 	.long	cpu_elf_name
@@ -455,6 +318,7 @@ __v7_setup_stack:
 	.long	v7_cache_fns
 .endm

+#ifndef CONFIG_ARM_LPAE
 	/*
 	 * ARM Ltd. Cortex A5 processor.
 	 */
@@ -484,6 +348,7 @@ __v7_ca9mp_proc_info:
 	.long	0xff0ffff0
 	__v7_proc __v7_ca9mp_setup
 	.size	__v7_ca9mp_proc_info, . - __v7_ca9mp_proc_info
+#endif	/* CONFIG_ARM_LPAE */

 	/*
 	 * ARM Ltd. Cortex A15 processor.
--- a/arch/arm/mm/proc-xsc3.S
+++ b/arch/arm/mm/proc-xsc3.S
@@ -105,6 +105,7 @@ ENTRY(cpu_xsc3_proc_fin)
 * loc: location to jump to for soft reset
 */
 	.align	5
+	.pushsection	.idmap.text, "ax"
 ENTRY(cpu_xsc3_reset)
 	mov	r1, #PSR_F_BIT|PSR_I_BIT|SVC_MODE
 	msr	cpsr_c, r1			@ reset CPSR
@@ -119,6 +120,8 @@ ENTRY(cpu_xsc3_reset)
 	@ already containing those two last instructions to survive.
 	mcr	p15, 0, ip, c8, c7, 0		@ invalidate I and D TLBs
 	mov	pc, r0
+ENDPROC(cpu_xsc3_reset)
+	.popsection

 /*
 * cpu_xsc3_do_idle()
--- a/arch/arm/mm/proc-xscale.S
+++ b/arch/arm/mm/proc-xscale.S
@@ -142,6 +142,7 @@ ENTRY(cpu_xscale_proc_fin)
 * Beware PXA270 erratum E7.
 */
 	.align	5
+	.pushsection	.idmap.text, "ax"
 ENTRY(cpu_xscale_reset)
 	mov	r1, #PSR_F_BIT|PSR_I_BIT|SVC_MODE
 	msr	cpsr_c, r1			@ reset CPSR
@@ -160,6 +161,8 @@ ENTRY(cpu_xscale_reset)
 	@ already containing those two last instructions to survive.
 	mcr	p15, 0, ip, c8, c7, 0		@ invalidate I & D TLBs
 	mov	pc, r0
+ENDPROC(cpu_xscale_reset)
+	.popsection

 /*
 * cpu_xscale_do_idle()