Merge branch 'for-rmk/lpae' of...

Merge branch 'for-rmk/lpae' of git://git.kernel.org/pub/scm/linux/kernel/git/will/linux into devel-stable

Conflicts:
	arch/arm/kernel/smp.c

Please pull these miscellaneous LPAE fixes I've been collecting for a while
now for 3.11. They've been tested and reviewed by quite a few people, and most
of the patches are pretty trivial. -- Will Deacon.

arch/arm/include/asm/memory.h

@@ -18,6 +18,8 @@
 #include <linux/types.h>
 #include <linux/sizes.h>
 
+#include <asm/cache.h>
+
 #ifdef CONFIG_NEED_MACH_MEMORY_H
 #include <mach/memory.h>
 #endif
@@ -141,6 +143,20 @@
 #define page_to_phys(page)	(__pfn_to_phys(page_to_pfn(page)))
 #define phys_to_page(phys)	(pfn_to_page(__phys_to_pfn(phys)))
 
+/*
+ * Minimum guaranted alignment in pgd_alloc().  The page table pointers passed
+ * around in head.S and proc-*.S are shifted by this amount, in order to
+ * leave spare high bits for systems with physical address extension.  This
+ * does not fully accomodate the 40-bit addressing capability of ARM LPAE, but
+ * gives us about 38-bits or so.
+ */
+#ifdef CONFIG_ARM_LPAE
+#define ARCH_PGD_SHIFT		L1_CACHE_SHIFT
+#else
+#define ARCH_PGD_SHIFT		0
+#endif
+#define ARCH_PGD_MASK		((1 << ARCH_PGD_SHIFT) - 1)
+
 #ifndef __ASSEMBLY__
 
 /*
@@ -207,7 +223,7 @@ static inline unsigned long __phys_to_virt(unsigned long x)
  * direct-mapped view.  We assume this is the first page
  * of RAM in the mem_map as well.
  */
-#define PHYS_PFN_OFFSET	(PHYS_OFFSET >> PAGE_SHIFT)
+#define PHYS_PFN_OFFSET	((unsigned long)(PHYS_OFFSET >> PAGE_SHIFT))
 
 /*
  * These are *only* valid on the kernel direct mapped RAM memory.

arch/arm/include/asm/page.h

@@ -13,7 +13,7 @@
 /* PAGE_SHIFT determines the page size */
 #define PAGE_SHIFT		12
 #define PAGE_SIZE		(_AC(1,UL) << PAGE_SHIFT)
-#define PAGE_MASK		(~(PAGE_SIZE-1))
+#define PAGE_MASK		(~((1 << PAGE_SHIFT) - 1))
 
 #ifndef __ASSEMBLY__
 

arch/arm/include/asm/pgtable-3level-hwdef.h

@@ -83,4 +83,24 @@
 #define PHYS_MASK_SHIFT		(40)
 #define PHYS_MASK		((1ULL << PHYS_MASK_SHIFT) - 1)
 
+/*
+ * 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.
+ */
+#if defined CONFIG_VMSPLIT_2G
+#define TTBR1_OFFSET	16			/* skip two L1 entries */
+#elif defined CONFIG_VMSPLIT_3G
+#define TTBR1_OFFSET	(4096 * (1 + 3))	/* only L2, skip pgd + 3*pmd */
+#else
+#define TTBR1_OFFSET	0
+#endif
+
+#define TTBR1_SIZE	(((PAGE_OFFSET >> 30) - 1) << 16)
+
 #endif

arch/arm/include/asm/pgtable-3level.h

@@ -33,7 +33,7 @@
 #define PTRS_PER_PMD		512
 #define PTRS_PER_PGD		4
 
-#define PTE_HWTABLE_PTRS	(PTRS_PER_PTE)
+#define PTE_HWTABLE_PTRS	(0)
 #define PTE_HWTABLE_OFF		(0)
 #define PTE_HWTABLE_SIZE	(PTRS_PER_PTE * sizeof(u64))
 
@@ -48,16 +48,16 @@
 #define PMD_SHIFT		21
 
 #define PMD_SIZE		(1UL << PMD_SHIFT)
-#define PMD_MASK		(~(PMD_SIZE-1))
+#define PMD_MASK		(~((1 << PMD_SHIFT) - 1))
 #define PGDIR_SIZE		(1UL << PGDIR_SHIFT)
-#define PGDIR_MASK		(~(PGDIR_SIZE-1))
+#define PGDIR_MASK		(~((1 << PGDIR_SHIFT) - 1))
 
 /*
  * section address mask and size definitions.
  */
 #define SECTION_SHIFT		21
 #define SECTION_SIZE		(1UL << SECTION_SHIFT)
-#define SECTION_MASK		(~(SECTION_SIZE-1))
+#define SECTION_MASK		(~((1 << SECTION_SHIFT) - 1))
 
 #define USER_PTRS_PER_PGD	(PAGE_OFFSET / PGDIR_SIZE)
 

arch/arm/include/asm/proc-fns.h

@@ -60,7 +60,7 @@ extern struct processor {
 	/*
 	 * Set the page table
 	 */
-	void (*switch_mm)(unsigned long pgd_phys, struct mm_struct *mm);
+	void (*switch_mm)(phys_addr_t pgd_phys, struct mm_struct *mm);
 	/*
 	 * Set a possibly extended PTE.  Non-extended PTEs should
 	 * ignore 'ext'.
@@ -82,7 +82,7 @@ extern void cpu_proc_init(void);
 extern void cpu_proc_fin(void);
 extern int cpu_do_idle(void);
 extern void cpu_dcache_clean_area(void *, int);
-extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
+extern void cpu_do_switch_mm(phys_addr_t pgd_phys, struct mm_struct *mm);
 #ifdef CONFIG_ARM_LPAE
 extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte);
 #else
@@ -116,13 +116,25 @@ extern void cpu_resume(void);
 #define cpu_switch_mm(pgd,mm) cpu_do_switch_mm(virt_to_phys(pgd),mm)
 
 #ifdef CONFIG_ARM_LPAE
+
+#define cpu_get_ttbr(nr)					\
+	({							\
+		u64 ttbr;					\
+		__asm__("mrrc	p15, " #nr ", %Q0, %R0, c2"	\
+			: "=r" (ttbr));				\
+		ttbr;						\
+	})
+
+#define cpu_set_ttbr(nr, val)					\
+	do {							\
+		u64 ttbr = val;					\
+		__asm__("mcrr	p15, " #nr ", %Q0, %R0, c2"	\
+			: : "r" (ttbr));			\
+	} while (0)
+
 #define cpu_get_pgd()	\
 	({						\
-		unsigned long pg, pg2;			\
-		__asm__("mrrc	p15, 0, %0, %1, c2"	\
-			: "=r" (pg), "=r" (pg2)		\
-			:				\
-			: "cc");			\
+		u64 pg = cpu_get_ttbr(0);		\
 		pg &= ~(PTRS_PER_PGD*sizeof(pgd_t)-1);	\
 		(pgd_t *)phys_to_virt(pg);		\
 	})

arch/arm/include/uapi/asm/hwcap.h

@@ -25,6 +25,6 @@
 #define HWCAP_IDIVT	(1 << 18)
 #define HWCAP_VFPD32	(1 << 19)	/* set if VFP has 32 regs (not 16) */
 #define HWCAP_IDIV	(HWCAP_IDIVA | HWCAP_IDIVT)
-
+#define HWCAP_LPAE	(1 << 20)
 
 #endif /* _UAPI__ASMARM_HWCAP_H */

arch/arm/kernel/head.S

@@ -156,7 +156,7 @@ ENDPROC(stext)
  *
  * Returns:
  *  r0, r3, r5-r7 corrupted
- *  r4 = physical page table address
+ *  r4 = page table (see ARCH_PGD_SHIFT in asm/memory.h)
  */
 __create_page_tables:
 	pgtbl	r4, r8				@ page table address
@@ -331,6 +331,7 @@ __create_page_tables:
 #endif
 #ifdef CONFIG_ARM_LPAE
 	sub	r4, r4, #0x1000		@ point to the PGD table
+	mov	r4, r4, lsr #ARCH_PGD_SHIFT
 #endif
 	mov	pc, lr
 ENDPROC(__create_page_tables)
@@ -408,7 +409,7 @@ __secondary_data:
  *  r0  = cp#15 control register
  *  r1  = machine ID
  *  r2  = atags or dtb pointer
- *  r4  = page table pointer
+ *  r4  = page table (see ARCH_PGD_SHIFT in asm/memory.h)
  *  r9  = processor ID
  *  r13 = *virtual* address to jump to upon completion
  */
@@ -427,10 +428,7 @@ __enable_mmu:
 #ifdef CONFIG_CPU_ICACHE_DISABLE
 	bic	r0, r0, #CR_I
 #endif
-#ifdef CONFIG_ARM_LPAE
-	mov	r5, #0
-	mcrr	p15, 0, r4, r5, c2		@ load TTBR0
-#else
+#ifndef CONFIG_ARM_LPAE
 	mov	r5, #(domain_val(DOMAIN_USER, DOMAIN_MANAGER) | \
 		      domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
 		      domain_val(DOMAIN_TABLE, DOMAIN_MANAGER) | \

arch/arm/kernel/setup.c

@@ -367,7 +367,7 @@ void __init early_print(const char *str, ...)
 
 static void __init cpuid_init_hwcaps(void)
 {
-	unsigned int divide_instrs;
+	unsigned int divide_instrs, vmsa;
 
 	if (cpu_architecture() < CPU_ARCH_ARMv7)
 		return;
@@ -380,6 +380,11 @@ static void __init cpuid_init_hwcaps(void)
 	case 1:
 		elf_hwcap |= HWCAP_IDIVT;
 	}
+
+	/* LPAE implies atomic ldrd/strd instructions */
+	vmsa = (read_cpuid_ext(CPUID_EXT_MMFR0) & 0xf) >> 0;
+	if (vmsa >= 5)
+		elf_hwcap |= HWCAP_LPAE;
 }
 
 static void __init feat_v6_fixup(void)
@@ -892,6 +897,7 @@ static const char *hwcap_str[] = {
 	"vfpv4",
 	"idiva",
 	"idivt",
+	"lpae",
 	NULL
 };
 

arch/arm/kernel/smp.c

@@ -79,6 +79,13 @@ void __init smp_set_ops(struct smp_operations *ops)
 		smp_ops = *ops;
 };
 
+static unsigned long get_arch_pgd(pgd_t *pgd)
+{
+	phys_addr_t pgdir = virt_to_phys(pgd);
+	BUG_ON(pgdir & ARCH_PGD_MASK);
+	return pgdir >> ARCH_PGD_SHIFT;
+}
+
 int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *idle)
 {
 	int ret;
@@ -93,8 +100,8 @@ int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *idle)
 #endif
 
 #ifdef CONFIG_MMU
-	secondary_data.pgdir = virt_to_phys(idmap_pgd);
-	secondary_data.swapper_pg_dir = virt_to_phys(swapper_pg_dir);
+	secondary_data.pgdir = get_arch_pgd(idmap_pgd);
+	secondary_data.swapper_pg_dir = get_arch_pgd(swapper_pg_dir);
 #endif
 	__cpuc_flush_dcache_area(&secondary_data, sizeof(secondary_data));
 	outer_clean_range(__pa(&secondary_data), __pa(&secondary_data + 1));

arch/arm/mm/context.c

@@ -20,6 +20,7 @@
 #include <asm/smp_plat.h>
 #include <asm/thread_notify.h>
 #include <asm/tlbflush.h>
+#include <asm/proc-fns.h>
 
 /*
  * On ARMv6, we have the following structure in the Context ID:
@@ -55,17 +56,11 @@ static cpumask_t tlb_flush_pending;
 #ifdef CONFIG_ARM_LPAE
 static void cpu_set_reserved_ttbr0(void)
 {
-	unsigned long ttbl = __pa(swapper_pg_dir);
-	unsigned long ttbh = 0;
-
 	/*
 	 * Set TTBR0 to swapper_pg_dir which contains only global entries. The
 	 * ASID is set to 0.
 	 */
-	asm volatile(
-	"	mcrr	p15, 0, %0, %1, c2		@ set TTBR0\n"
-	:
-	: "r" (ttbl), "r" (ttbh));
+	cpu_set_ttbr(0, __pa(swapper_pg_dir));
 	isb();
 }
 #else

arch/arm/mm/init.c

@@ -36,12 +36,13 @@
 
 #include "mm.h"
 
-static unsigned long phys_initrd_start __initdata = 0;
+static phys_addr_t phys_initrd_start __initdata = 0;
 static unsigned long phys_initrd_size __initdata = 0;
 
 static int __init early_initrd(char *p)
 {
-	unsigned long start, size;
+	phys_addr_t start;
+	unsigned long size;
 	char *endp;
 
 	start = memparse(p, &endp);
@@ -350,14 +351,14 @@ void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc)
 #ifdef CONFIG_BLK_DEV_INITRD
 	if (phys_initrd_size &&
 	    !memblock_is_region_memory(phys_initrd_start, phys_initrd_size)) {
-		pr_err("INITRD: 0x%08lx+0x%08lx is not a memory region - disabling initrd\n",
-		       phys_initrd_start, phys_initrd_size);
+		pr_err("INITRD: 0x%08llx+0x%08lx is not a memory region - disabling initrd\n",
+		       (u64)phys_initrd_start, phys_initrd_size);
 		phys_initrd_start = phys_initrd_size = 0;
 	}
 	if (phys_initrd_size &&
 	    memblock_is_region_reserved(phys_initrd_start, phys_initrd_size)) {
-		pr_err("INITRD: 0x%08lx+0x%08lx overlaps in-use memory region - disabling initrd\n",
-		       phys_initrd_start, phys_initrd_size);
+		pr_err("INITRD: 0x%08llx+0x%08lx overlaps in-use memory region - disabling initrd\n",
+		       (u64)phys_initrd_start, phys_initrd_size);
 		phys_initrd_start = phys_initrd_size = 0;
 	}
 	if (phys_initrd_size) {
@@ -442,7 +443,7 @@ static inline void
 free_memmap(unsigned long start_pfn, unsigned long end_pfn)
 {
 	struct page *start_pg, *end_pg;
-	unsigned long pg, pgend;
+	phys_addr_t pg, pgend;
 
 	/*
 	 * Convert start_pfn/end_pfn to a struct page pointer.
@@ -454,8 +455,8 @@ free_memmap(unsigned long start_pfn, unsigned long end_pfn)
 	 * Convert to physical addresses, and
 	 * round start upwards and end downwards.
 	 */
-	pg = (unsigned long)PAGE_ALIGN(__pa(start_pg));
-	pgend = (unsigned long)__pa(end_pg) & PAGE_MASK;
+	pg = PAGE_ALIGN(__pa(start_pg));
+	pgend = __pa(end_pg) & PAGE_MASK;
 
 	/*
 	 * If there are free pages between these,

arch/arm/mm/mmu.c

@@ -673,7 +673,8 @@ static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
 }
 
 static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
-	unsigned long end, unsigned long phys, const struct mem_type *type)
+				  unsigned long end, phys_addr_t phys,
+				  const struct mem_type *type)
 {
 	pud_t *pud = pud_offset(pgd, addr);
 	unsigned long next;
@@ -987,27 +988,28 @@ phys_addr_t arm_lowmem_limit __initdata = 0;
 void __init sanity_check_meminfo(void)
 {
 	int i, j, highmem = 0;
+	phys_addr_t vmalloc_limit = __pa(vmalloc_min - 1) + 1;
 
 	for (i = 0, j = 0; i < meminfo.nr_banks; i++) {
 		struct membank *bank = &meminfo.bank[j];
-		*bank = meminfo.bank[i];
+		phys_addr_t size_limit;
 
-		if (bank->start > ULONG_MAX)
-			highmem = 1;
+		*bank = meminfo.bank[i];
+		size_limit = bank->size;
 
-#ifdef CONFIG_HIGHMEM
-		if (__va(bank->start) >= vmalloc_min ||
-		    __va(bank->start) < (void *)PAGE_OFFSET)
+		if (bank->start >= vmalloc_limit)
 			highmem = 1;
+		else
+			size_limit = vmalloc_limit - bank->start;
 
 		bank->highmem = highmem;
 
+#ifdef CONFIG_HIGHMEM
 		/*
 		 * Split those memory banks which are partially overlapping
 		 * the vmalloc area greatly simplifying things later.
 		 */
-		if (!highmem && __va(bank->start) < vmalloc_min &&
-		    bank->size > vmalloc_min - __va(bank->start)) {
+		if (!highmem && bank->size > size_limit) {
 			if (meminfo.nr_banks >= NR_BANKS) {
 				printk(KERN_CRIT "NR_BANKS too low, "
 						 "ignoring high memory\n");
@@ -1016,16 +1018,14 @@ void __init sanity_check_meminfo(void)
 					(meminfo.nr_banks - i) * sizeof(*bank));
 				meminfo.nr_banks++;
 				i++;
-				bank[1].size -= vmalloc_min - __va(bank->start);
-				bank[1].start = __pa(vmalloc_min - 1) + 1;
+				bank[1].size -= size_limit;
+				bank[1].start = vmalloc_limit;
 				bank[1].highmem = highmem = 1;
 				j++;
 			}
-			bank->size = vmalloc_min - __va(bank->start);
+			bank->size = size_limit;
 		}
 #else
-		bank->highmem = highmem;
-
 		/*
 		 * Highmem banks not allowed with !CONFIG_HIGHMEM.
 		 */
@@ -1037,32 +1037,17 @@ void __init sanity_check_meminfo(void)
 			continue;
 		}
 
-		/*
-		 * Check whether this memory bank would entirely overlap
-		 * the vmalloc area.
-		 */
-		if (__va(bank->start) >= vmalloc_min ||
-		    __va(bank->start) < (void *)PAGE_OFFSET) {
-			printk(KERN_NOTICE "Ignoring RAM at %.8llx-%.8llx "
-			       "(vmalloc region overlap).\n",
-			       (unsigned long long)bank->start,
-			       (unsigned long long)bank->start + bank->size - 1);
-			continue;
-		}
-
 		/*
 		 * Check whether this memory bank would partially overlap
 		 * the vmalloc area.
 		 */
-		if (__va(bank->start + bank->size - 1) >= vmalloc_min ||
-		    __va(bank->start + bank->size - 1) <= __va(bank->start)) {
-			unsigned long newsize = vmalloc_min - __va(bank->start);
+		if (bank->size > size_limit) {
 			printk(KERN_NOTICE "Truncating RAM at %.8llx-%.8llx "
 			       "to -%.8llx (vmalloc region overlap).\n",
 			       (unsigned long long)bank->start,
 			       (unsigned long long)bank->start + bank->size - 1,
-			       (unsigned long long)bank->start + newsize - 1);
-			bank->size = newsize;
+			       (unsigned long long)bank->start + size_limit - 1);
+			bank->size = size_limit;
 		}
 #endif
 		if (!bank->highmem && bank->start + bank->size > arm_lowmem_limit)

arch/arm/mm/proc-v7-3level.S

@@ -39,6 +39,14 @@
 #define TTB_FLAGS_SMP	(TTB_IRGN_WBWA|TTB_S|TTB_RGN_OC_WBWA)
 #define PMD_FLAGS_SMP	(PMD_SECT_WBWA|PMD_SECT_S)
 
+#ifndef __ARMEB__
+#  define rpgdl	r0
+#  define rpgdh	r1
+#else
+#  define rpgdl	r1
+#  define rpgdh	r0
+#endif
+
 /*
  * cpu_v7_switch_mm(pgd_phys, tsk)
  *
@@ -47,10 +55,10 @@
  */
 ENTRY(cpu_v7_switch_mm)
 #ifdef CONFIG_MMU
-	mmid	r1, r1				@ get mm->context.id
-	asid	r3, r1
-	mov	r3, r3, lsl #(48 - 32)		@ ASID
-	mcrr	p15, 0, r0, r3, c2		@ set TTB 0
+	mmid	r2, r2
+	asid	r2, r2
+	orr	rpgdh, rpgdh, r2, lsl #(48 - 32)	@ upper 32-bits of pgd
+	mcrr	p15, 0, rpgdl, rpgdh, c2		@ set TTB 0
 	isb
 #endif
 	mov	pc, lr
@@ -106,7 +114,8 @@ ENDPROC(cpu_v7_set_pte_ext)
 	 */
 	.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)
+	mov	\tmp, \tmp, lsr #ARCH_PGD_SHIFT
+	cmp	\ttbr1, \tmp			@ PHYS_OFFSET > PAGE_OFFSET?
 	mrc	p15, 0, \tmp, c2, c0, 2		@ TTB control register
 	orr	\tmp, \tmp, #TTB_EAE
 	ALT_SMP(orr	\tmp, \tmp, #TTB_FLAGS_SMP)
@@ -114,27 +123,21 @@ ENDPROC(cpu_v7_set_pte_ext)
 	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.
+	 * Only use split TTBRs if PHYS_OFFSET <= PAGE_OFFSET (cmp above),
+	 * 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
+	orrls	\tmp, \tmp, #TTBR1_SIZE				@ TTBCR.T1SZ
+	mcr	p15, 0, \tmp, c2, c0, 2				@ TTBCR
+	mov	\tmp, \ttbr1, lsr #(32 - ARCH_PGD_SHIFT)	@ upper bits
+	mov	\ttbr1, \ttbr1, lsl #ARCH_PGD_SHIFT		@ lower bits
+	addls	\ttbr1, \ttbr1, #TTBR1_OFFSET
+	mcrr	p15, 1, \ttbr1, \zero, c2			@ load TTBR1
+	mov	\tmp, \ttbr0, lsr #(32 - ARCH_PGD_SHIFT)	@ upper bits
+	mov	\ttbr0, \ttbr0, lsl #ARCH_PGD_SHIFT		@ lower bits
+	mcrr	p15, 0, \ttbr0, \zero, c2			@ load TTBR0
+	mcrr	p15, 1, \ttbr1, \zero, c2			@ load TTBR1
+	mcrr	p15, 0, \ttbr0, \zero, c2			@ load TTBR0
 	.endm
 
 	__CPUINIT