22 files changed, 294 insertions, 87 deletions
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index 7611b10a2d23..0b10ef2a4372 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -48,4 +48,5 @@ generic-y += types.h
 generic-y += ucontext.h
 generic-y += user.h
 generic-y += vga.h
+generic-y += word-at-a-time.h
 generic-y += xor.h
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index d8023bc8d1ad..7fac7d85ed6a 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -120,7 +120,7 @@
 
 /* gcc builtin sr needs reg param to be long immediate */
 #define write_aux_reg(reg_immed, val)		\
-		__builtin_arc_sr((unsigned int)val, reg_immed)
+		__builtin_arc_sr((unsigned int)(val), reg_immed)
 
 #else
 
@@ -327,8 +327,8 @@ struct bcr_generic {
  */
 
 struct cpuinfo_arc_mmu {
-	unsigned int ver:4, pg_sz_k:8, s_pg_sz_m:8, u_dtlb:6, u_itlb:6;
-	unsigned int num_tlb:16, sets:12, ways:4;
+	unsigned int ver:4, pg_sz_k:8, s_pg_sz_m:8, pad:10, sasid:1, pae:1;
+	unsigned int sets:12, ways:4, u_dtlb:8, u_itlb:8;
 };
 
 struct cpuinfo_arc_cache {
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index c3ecda023e3a..7730d302cadb 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -17,11 +17,11 @@
 #include <asm/barrier.h>
 #include <asm/smp.h>
 
-#define atomic_read(v)  ((v)->counter)
+#define atomic_read(v)  READ_ONCE((v)->counter)
 
 #ifdef CONFIG_ARC_HAS_LLSC
 
-#define atomic_set(v, i) (((v)->counter) = (i))
+#define atomic_set(v, i) WRITE_ONCE(((v)->counter), (i))
 
 #ifdef CONFIG_ARC_STAR_9000923308
 
@@ -107,7 +107,7 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 #ifndef CONFIG_SMP
 
  /* violating atomic_xxx API locking protocol in UP for optimization sake */
-#define atomic_set(v, i) (((v)->counter) = (i))
+#define atomic_set(v, i) WRITE_ONCE(((v)->counter), (i))
 
 #else
 
@@ -125,7 +125,7 @@ static inline void atomic_set(atomic_t *v, int i)
 	unsigned long flags;
 
 	atomic_ops_lock(flags);
-	v->counter = i;
+	WRITE_ONCE(v->counter, i);
 	atomic_ops_unlock(flags);
 }
 
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index e23ea6e7633a..abf06e81c929 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -65,6 +65,7 @@ extern int ioc_exists;
 #if defined(CONFIG_ARC_MMU_V3) || defined(CONFIG_ARC_MMU_V4)
 #define ARC_REG_IC_PTAG		0x1E
 #endif
+#define ARC_REG_IC_PTAG_HI	0x1F
 
 /* Bit val in IC_CTRL */
 #define IC_CTRL_CACHE_DISABLE   0x1
@@ -77,6 +78,7 @@ extern int ioc_exists;
 #define ARC_REG_DC_FLSH		0x4B
 #define ARC_REG_DC_FLDL		0x4C
 #define ARC_REG_DC_PTAG		0x5C
+#define ARC_REG_DC_PTAG_HI	0x5F
 
 /* Bit val in DC_CTRL */
 #define DC_CTRL_INV_MODE_FLUSH  0x40
diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h
index 0992d3dbcc65..fbe3587c4f36 100644
--- a/arch/arc/include/asm/cacheflush.h
+++ b/arch/arc/include/asm/cacheflush.h
@@ -31,10 +31,10 @@
 
 void flush_cache_all(void);
 
-void flush_icache_range(unsigned long start, unsigned long end);
-void __sync_icache_dcache(unsigned long paddr, unsigned long vaddr, int len);
-void __inv_icache_page(unsigned long paddr, unsigned long vaddr);
-void __flush_dcache_page(unsigned long paddr, unsigned long vaddr);
+void flush_icache_range(unsigned long kstart, unsigned long kend);
+void __sync_icache_dcache(phys_addr_t paddr, unsigned long vaddr, int len);
+void __inv_icache_page(phys_addr_t paddr, unsigned long vaddr);
+void __flush_dcache_page(phys_addr_t paddr, unsigned long vaddr);
 
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 
diff --git a/arch/arc/include/asm/entry-compact.h b/arch/arc/include/asm/entry-compact.h
index 415443c2a8c4..1aff3be91075 100644
--- a/arch/arc/include/asm/entry-compact.h
+++ b/arch/arc/include/asm/entry-compact.h
@@ -110,13 +110,12 @@
 
 .macro FAKE_RET_FROM_EXCPN
 
-	ld  r9, [sp, PT_status32]
-	bic r9, r9, (STATUS_U_MASK|STATUS_DE_MASK)
-	bset  r9, r9, STATUS_L_BIT
-	sr  r9, [erstatus]
-	mov r9, 55f
-	sr  r9, [eret]
-
+	lr	r9, [status32]
+	bclr	r9, r9, STATUS_AE_BIT
+	or	r9, r9, (STATUS_E1_MASK|STATUS_E2_MASK)
+	sr	r9, [erstatus]
+	mov	r9, 55f
+	sr	r9, [eret]
 	rtie
 55:
 .endm
diff --git a/arch/arc/include/asm/highmem.h b/arch/arc/include/asm/highmem.h
new file mode 100644
index 000000000000..b1585c96324a
--- /dev/null
+++ b/arch/arc/include/asm/highmem.h
@@ -0,0 +1,61 @@
+/*
+ * Copyright (C) 2015 Synopsys, Inc. (www.synopsys.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.
+ *
+ */
+
+#ifndef _ASM_HIGHMEM_H
+#define _ASM_HIGHMEM_H
+
+#ifdef CONFIG_HIGHMEM
+
+#include <uapi/asm/page.h>
+#include <asm/kmap_types.h>
+
+/* start after vmalloc area */
+#define FIXMAP_BASE		(PAGE_OFFSET - FIXMAP_SIZE - PKMAP_SIZE)
+#define FIXMAP_SIZE		PGDIR_SIZE	/* only 1 PGD worth */
+#define KM_TYPE_NR		((FIXMAP_SIZE >> PAGE_SHIFT)/NR_CPUS)
+#define FIXMAP_ADDR(nr)		(FIXMAP_BASE + ((nr) << PAGE_SHIFT))
+
+/* start after fixmap area */
+#define PKMAP_BASE		(FIXMAP_BASE + FIXMAP_SIZE)
+#define PKMAP_SIZE		PGDIR_SIZE
+#define LAST_PKMAP		(PKMAP_SIZE >> PAGE_SHIFT)
+#define LAST_PKMAP_MASK		(LAST_PKMAP - 1)
+#define PKMAP_ADDR(nr)		(PKMAP_BASE + ((nr) << PAGE_SHIFT))
+#define PKMAP_NR(virt)		(((virt) - PKMAP_BASE) >> PAGE_SHIFT)
+
+#define kmap_prot		PAGE_KERNEL
+
+
+#include <asm/cacheflush.h>
+
+extern void *kmap(struct page *page);
+extern void *kmap_high(struct page *page);
+extern void *kmap_atomic(struct page *page);
+extern void __kunmap_atomic(void *kvaddr);
+extern void kunmap_high(struct page *page);
+
+extern void kmap_init(void);
+
+static inline void flush_cache_kmaps(void)
+{
+	flush_cache_all();
+}
+
+static inline void kunmap(struct page *page)
+{
+	BUG_ON(in_interrupt());
+	if (!PageHighMem(page))
+		return;
+	kunmap_high(page);
+}
+
+
+#endif
+
+#endif
diff --git a/arch/arc/include/asm/hugepage.h b/arch/arc/include/asm/hugepage.h
new file mode 100644
index 000000000000..c5094de86403
--- /dev/null
+++ b/arch/arc/include/asm/hugepage.h
@@ -0,0 +1,81 @@
+/*
+ * Copyright (C) 2013-15 Synopsys, Inc. (www.synopsys.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.
+ */
+
+
+#ifndef _ASM_ARC_HUGEPAGE_H
+#define _ASM_ARC_HUGEPAGE_H
+
+#include <linux/types.h>
+#include <asm-generic/pgtable-nopmd.h>
+
+static inline pte_t pmd_pte(pmd_t pmd)
+{
+	return __pte(pmd_val(pmd));
+}
+
+static inline pmd_t pte_pmd(pte_t pte)
+{
+	return __pmd(pte_val(pte));
+}
+
+#define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
+#define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))
+#define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
+#define pmd_mkold(pmd)		pte_pmd(pte_mkold(pmd_pte(pmd)))
+#define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
+#define pmd_mkhuge(pmd)		pte_pmd(pte_mkhuge(pmd_pte(pmd)))
+#define pmd_mknotpresent(pmd)	pte_pmd(pte_mknotpresent(pmd_pte(pmd)))
+#define pmd_mksplitting(pmd)	pte_pmd(pte_mkspecial(pmd_pte(pmd)))
+#define pmd_mkclean(pmd)	pte_pmd(pte_mkclean(pmd_pte(pmd)))
+
+#define pmd_write(pmd)		pte_write(pmd_pte(pmd))
+#define pmd_young(pmd)		pte_young(pmd_pte(pmd))
+#define pmd_pfn(pmd)		pte_pfn(pmd_pte(pmd))
+#define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
+#define pmd_special(pmd)	pte_special(pmd_pte(pmd))
+
+#define mk_pmd(page, prot)	pte_pmd(mk_pte(page, prot))
+
+#define pmd_trans_huge(pmd)	(pmd_val(pmd) & _PAGE_HW_SZ)
+#define pmd_trans_splitting(pmd)	(pmd_trans_huge(pmd) && pmd_special(pmd))
+
+#define pfn_pmd(pfn, prot)	(__pmd(((pfn) << PAGE_SHIFT) | pgprot_val(prot)))
+
+static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
+{
+        /*
+         * open-coded pte_modify() with additional retaining of HW_SZ bit
+         * so that pmd_trans_huge() remains true for this PMD
+         */
+        return __pmd((pmd_val(pmd) & (_PAGE_CHG_MASK | _PAGE_HW_SZ)) | pgprot_val(newprot));
+}
+
+static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+			      pmd_t *pmdp, pmd_t pmd)
+{
+	*pmdp = pmd;
+}
+
+extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
+				 pmd_t *pmd);
+
+#define has_transparent_hugepage() 1
+
+/* Generic variants assume pgtable_t is struct page *, hence need for these */
+#define __HAVE_ARCH_PGTABLE_DEPOSIT
+extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				       pgtable_t pgtable);
+
+#define __HAVE_ARCH_PGTABLE_WITHDRAW
+extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
+
+#define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
+extern void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
+				unsigned long end);
+
+#endif
diff --git a/arch/arc/include/asm/irq.h b/arch/arc/include/asm/irq.h
index bc5103637326..4fd7d62a6e30 100644
--- a/arch/arc/include/asm/irq.h
+++ b/arch/arc/include/asm/irq.h
@@ -16,6 +16,7 @@
 #ifdef CONFIG_ISA_ARCOMPACT
 #define TIMER0_IRQ      3
 #define TIMER1_IRQ      4
+#define IPI_IRQ		(NR_CPU_IRQS-1) /* dummy to enable SMP build for up hardware */
 #else
 #define TIMER0_IRQ      16
 #define TIMER1_IRQ      17
diff --git a/arch/arc/include/asm/irqflags-compact.h b/arch/arc/include/asm/irqflags-compact.h
index aa805575c320..d8c608174617 100644
--- a/arch/arc/include/asm/irqflags-compact.h
+++ b/arch/arc/include/asm/irqflags-compact.h
@@ -23,11 +23,13 @@
 #define STATUS_E2_BIT		2	/* Int 2 enable */
 #define STATUS_A1_BIT		3	/* Int 1 active */
 #define STATUS_A2_BIT		4	/* Int 2 active */
+#define STATUS_AE_BIT		5	/* Exception active */
 
 #define STATUS_E1_MASK		(1<<STATUS_E1_BIT)
 #define STATUS_E2_MASK		(1<<STATUS_E2_BIT)
 #define STATUS_A1_MASK		(1<<STATUS_A1_BIT)
 #define STATUS_A2_MASK		(1<<STATUS_A2_BIT)
+#define STATUS_AE_MASK		(1<<STATUS_AE_BIT)
 #define STATUS_IE_MASK		(STATUS_E1_MASK | STATUS_E2_MASK)
 
 /* Other Interrupt Handling related Aux regs */
@@ -91,7 +93,19 @@ static inline void arch_local_irq_restore(unsigned long flags)
 /*
  * Unconditionally Enable IRQs
  */
-extern void arch_local_irq_enable(void);
+static inline void arch_local_irq_enable(void)
+{
+	unsigned long temp;
+
+	__asm__ __volatile__(
+	"	lr   %0, [status32]	\n"
+	"	or   %0, %0, %1		\n"
+	"	flag %0			\n"
+	: "=&r"(temp)
+	: "n"((STATUS_E1_MASK | STATUS_E2_MASK))
+	: "cc", "memory");
+}
+
 
 /*
  * Unconditionally Disable IRQs
diff --git a/arch/arc/include/asm/kmap_types.h b/arch/arc/include/asm/kmap_types.h
new file mode 100644
index 000000000000..f0d7f6acea4e
--- /dev/null
+++ b/arch/arc/include/asm/kmap_types.h
@@ -0,0 +1,18 @@
+/*
+ * Copyright (C) 2015 Synopsys, Inc. (www.synopsys.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.
+ *
+ */
+
+#ifndef _ASM_KMAP_TYPES_H
+#define _ASM_KMAP_TYPES_H
+
+/*
+ * We primarily need to define KM_TYPE_NR here but that in turn
+ * is a function of PGDIR_SIZE etc.
+ * To avoid circular deps issue, put everything in asm/highmem.h
+ */
+#endif
diff --git a/arch/arc/include/asm/mach_desc.h b/arch/arc/include/asm/mach_desc.h
index e8993a2be6c2..6ff657a904b6 100644
--- a/arch/arc/include/asm/mach_desc.h
+++ b/arch/arc/include/asm/mach_desc.h
@@ -23,11 +23,8 @@
  * @dt_compat:		Array of device tree 'compatible' strings
  * 			(XXX: although only 1st entry is looked at)
  * @init_early:		Very early callback [called from setup_arch()]
- * @init_irq:		setup external IRQ controllers [called from init_IRQ()]
- * @init_smp:		for each CPU (e.g. setup IPI)
+ * @init_cpu_smp:	for each CPU as it is coming up (SMP as well as UP)
  * 			[(M):init_IRQ(), (o):start_kernel_secondary()]
- * @init_time:		platform specific clocksource/clockevent registration
- * 			[called from time_init()]
  * @init_machine:	arch initcall level callback (e.g. populate static
  * 			platform devices or parse Devicetree)
  * @init_late:		Late initcall level callback
@@ -36,13 +33,10 @@
 struct machine_desc {
 	const char		*name;
 	const char		**dt_compat;
-
 	void			(*init_early)(void);
-	void			(*init_irq)(void);
 #ifdef CONFIG_SMP
-	void			(*init_smp)(unsigned int);
+	void			(*init_cpu_smp)(unsigned int);
 #endif
-	void			(*init_time)(void);
 	void			(*init_machine)(void);
 	void			(*init_late)(void);
 
diff --git a/arch/arc/include/asm/mcip.h b/arch/arc/include/asm/mcip.h
index 52c11f0bb0e5..46f4e5351b2a 100644
--- a/arch/arc/include/asm/mcip.h
+++ b/arch/arc/include/asm/mcip.h
@@ -86,9 +86,6 @@ static inline void __mcip_cmd_data(unsigned int cmd, unsigned int param,
 	__mcip_cmd(cmd, param);
 }
 
-extern void mcip_init_early_smp(void);
-extern void mcip_init_smp(unsigned int cpu);
-
 #endif
 
 #endif
diff --git a/arch/arc/include/asm/mmu.h b/arch/arc/include/asm/mmu.h
index 0f9c3eb5327e..b144d7ca7d20 100644
--- a/arch/arc/include/asm/mmu.h
+++ b/arch/arc/include/asm/mmu.h
@@ -24,6 +24,7 @@
 #if (CONFIG_ARC_MMU_VER < 4)
 #define ARC_REG_TLBPD0		0x405
 #define ARC_REG_TLBPD1		0x406
+#define ARC_REG_TLBPD1HI	0	/* Dummy: allows code sharing with ARC700 */
 #define ARC_REG_TLBINDEX	0x407
 #define ARC_REG_TLBCOMMAND	0x408
 #define ARC_REG_PID		0x409
@@ -31,6 +32,7 @@
 #else
 #define ARC_REG_TLBPD0		0x460
 #define ARC_REG_TLBPD1		0x461
+#define ARC_REG_TLBPD1HI	0x463
 #define ARC_REG_TLBINDEX	0x464
 #define ARC_REG_TLBCOMMAND	0x465
 #define ARC_REG_PID		0x468
@@ -83,6 +85,11 @@ void arc_mmu_init(void);
 extern char *arc_mmu_mumbojumbo(int cpu_id, char *buf, int len);
 void read_decode_mmu_bcr(void);
 
+static inline int is_pae40_enabled(void)
+{
+	return IS_ENABLED(CONFIG_ARC_HAS_PAE40);
+}
+
 #endif	/* !__ASSEMBLY__ */
 
 #endif
diff --git a/arch/arc/include/asm/page.h b/arch/arc/include/asm/page.h
index 9c8aa41e45c2..429957f1c236 100644
--- a/arch/arc/include/asm/page.h
+++ b/arch/arc/include/asm/page.h
@@ -43,7 +43,6 @@ typedef struct {
 typedef struct {
 	unsigned long pgprot;
 } pgprot_t;
-typedef unsigned long pgtable_t;
 
 #define pte_val(x)      ((x).pte)
 #define pgd_val(x)      ((x).pgd)
@@ -57,20 +56,26 @@ typedef unsigned long pgtable_t;
 
 #else /* !STRICT_MM_TYPECHECKS */
 
+#ifdef CONFIG_ARC_HAS_PAE40
+typedef unsigned long long pte_t;
+#else
 typedef unsigned long pte_t;
+#endif
 typedef unsigned long pgd_t;
 typedef unsigned long pgprot_t;
-typedef unsigned long pgtable_t;
 
 #define pte_val(x)	(x)
 #define pgd_val(x)	(x)
 #define pgprot_val(x)	(x)
 #define __pte(x)	(x)
+#define __pgd(x)	(x)
 #define __pgprot(x)	(x)
 #define pte_pgprot(x)	(x)
 
 #endif
 
+typedef pte_t * pgtable_t;
+
 #define ARCH_PFN_OFFSET     (CONFIG_LINUX_LINK_BASE >> PAGE_SHIFT)
 
 #define pfn_valid(pfn)      (((pfn) - ARCH_PFN_OFFSET) < max_mapnr)
diff --git a/arch/arc/include/asm/pgalloc.h b/arch/arc/include/asm/pgalloc.h
index 81208bfd9dcb..86ed671286df 100644
--- a/arch/arc/include/asm/pgalloc.h
+++ b/arch/arc/include/asm/pgalloc.h
@@ -49,7 +49,7 @@ pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t ptep)
 
 static inline int __get_order_pgd(void)
 {
-	return get_order(PTRS_PER_PGD * 4);
+	return get_order(PTRS_PER_PGD * sizeof(pgd_t));
 }
 
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
@@ -87,7 +87,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 
 static inline int __get_order_pte(void)
 {
-	return get_order(PTRS_PER_PTE * 4);
+	return get_order(PTRS_PER_PTE * sizeof(pte_t));
 }
 
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
@@ -107,10 +107,10 @@ pte_alloc_one(struct mm_struct *mm, unsigned long address)
 	pgtable_t pte_pg;
 	struct page *page;
 
-	pte_pg = __get_free_pages(GFP_KERNEL | __GFP_REPEAT, __get_order_pte());
+	pte_pg = (pgtable_t)__get_free_pages(GFP_KERNEL | __GFP_REPEAT, __get_order_pte());
 	if (!pte_pg)
 		return 0;
-	memzero((void *)pte_pg, PTRS_PER_PTE * 4);
+	memzero((void *)pte_pg, PTRS_PER_PTE * sizeof(pte_t));
 	page = virt_to_page(pte_pg);
 	if (!pgtable_page_ctor(page)) {
 		__free_page(page);
@@ -128,12 +128,12 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
 static inline void pte_free(struct mm_struct *mm, pgtable_t ptep)
 {
 	pgtable_page_dtor(virt_to_page(ptep));
-	free_pages(ptep, __get_order_pte());
+	free_pages((unsigned long)ptep, __get_order_pte());
 }
 
 #define __pte_free_tlb(tlb, pte, addr)  pte_free((tlb)->mm, pte)
 
 #define check_pgt_cache()   do { } while (0)
-#define pmd_pgtable(pmd) pmd_page_vaddr(pmd)
+#define pmd_pgtable(pmd)	((pgtable_t) pmd_page_vaddr(pmd))
 
 #endif /* _ASM_ARC_PGALLOC_H */
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 1281718802f7..57af2f05ae84 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -38,6 +38,7 @@
 #include <asm/page.h>
 #include <asm/mmu.h>
 #include <asm-generic/pgtable-nopmd.h>
+#include <linux/const.h>
 
 /**************************************************************************
  * Page Table Flags
@@ -60,7 +61,8 @@
 #define _PAGE_EXECUTE       (1<<3)	/* Page has user execute perm (H) */
 #define _PAGE_WRITE         (1<<4)	/* Page has user write perm (H) */
 #define _PAGE_READ          (1<<5)	/* Page has user read perm (H) */
-#define _PAGE_MODIFIED      (1<<6)	/* Page modified (dirty) (S) */
+#define _PAGE_DIRTY         (1<<6)	/* Page modified (dirty) (S) */
+#define _PAGE_SPECIAL       (1<<7)
 #define _PAGE_GLOBAL        (1<<8)	/* Page is global (H) */
 #define _PAGE_PRESENT       (1<<10)	/* TLB entry is valid (H) */
 
@@ -71,7 +73,8 @@
 #define _PAGE_WRITE         (1<<2)	/* Page has user write perm (H) */
 #define _PAGE_READ          (1<<3)	/* Page has user read perm (H) */
 #define _PAGE_ACCESSED      (1<<4)	/* Page is accessed (S) */
-#define _PAGE_MODIFIED      (1<<5)	/* Page modified (dirty) (S) */
+#define _PAGE_DIRTY         (1<<5)	/* Page modified (dirty) (S) */
+#define _PAGE_SPECIAL       (1<<6)
 
 #if (CONFIG_ARC_MMU_VER >= 4)
 #define _PAGE_WTHRU         (1<<7)	/* Page cache mode write-thru (H) */
@@ -81,32 +84,33 @@
 #define _PAGE_PRESENT       (1<<9)	/* TLB entry is valid (H) */
 
 #if (CONFIG_ARC_MMU_VER >= 4)
-#define _PAGE_SZ            (1<<10)	/* Page Size indicator (H) */
+#define _PAGE_HW_SZ         (1<<10)	/* Page Size indicator (H): 0 normal, 1 super */
 #endif
 
 #define _PAGE_SHARED_CODE   (1<<11)	/* Shared Code page with cmn vaddr
 					   usable for shared TLB entries (H) */
+
+#define _PAGE_UNUSED_BIT    (1<<12)
 #endif
 
 /* vmalloc permissions */
 #define _K_PAGE_PERMS  (_PAGE_EXECUTE | _PAGE_WRITE | _PAGE_READ | \
 			_PAGE_GLOBAL | _PAGE_PRESENT)
 
-#ifdef CONFIG_ARC_CACHE_PAGES
-#define _PAGE_DEF_CACHEABLE _PAGE_CACHEABLE
-#else
-#define _PAGE_DEF_CACHEABLE (0)
+#ifndef CONFIG_ARC_CACHE_PAGES
+#undef _PAGE_CACHEABLE
+#define _PAGE_CACHEABLE 0
 #endif
 
-/* Helper for every "user" page
- * -kernel can R/W/X
- * -by default cached, unless config otherwise
- * -present in memory
- */
-#define ___DEF (_PAGE_PRESENT | _PAGE_DEF_CACHEABLE)
+#ifndef _PAGE_HW_SZ
+#define _PAGE_HW_SZ	0
+#endif
+
+/* Defaults for every user page */
+#define ___DEF (_PAGE_PRESENT | _PAGE_CACHEABLE)
 
 /* Set of bits not changed in pte_modify */
-#define _PAGE_CHG_MASK	(PAGE_MASK | _PAGE_ACCESSED | _PAGE_MODIFIED)
+#define _PAGE_CHG_MASK	(PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)
 
 /* More Abbrevaited helpers */
 #define PAGE_U_NONE     __pgprot(___DEF)
@@ -122,15 +126,20 @@
  * user vaddr space - visible in all addr spaces, but kernel mode only
  * Thus Global, all-kernel-access, no-user-access, cached
  */
-#define PAGE_KERNEL          __pgprot(_K_PAGE_PERMS | _PAGE_DEF_CACHEABLE)
+#define PAGE_KERNEL          __pgprot(_K_PAGE_PERMS | _PAGE_CACHEABLE)
 
 /* ioremap */
 #define PAGE_KERNEL_NO_CACHE __pgprot(_K_PAGE_PERMS)
 
 /* Masks for actual TLB "PD"s */
-#define PTE_BITS_IN_PD0		(_PAGE_GLOBAL | _PAGE_PRESENT)
+#define PTE_BITS_IN_PD0		(_PAGE_GLOBAL | _PAGE_PRESENT | _PAGE_HW_SZ)
 #define PTE_BITS_RWX		(_PAGE_EXECUTE | _PAGE_WRITE | _PAGE_READ)
+
+#ifdef CONFIG_ARC_HAS_PAE40
+#define PTE_BITS_NON_RWX_IN_PD1	(0xff00000000 | PAGE_MASK | _PAGE_CACHEABLE)
+#else
 #define PTE_BITS_NON_RWX_IN_PD1	(PAGE_MASK | _PAGE_CACHEABLE)
+#endif
 
 /**************************************************************************
  * Mapping of vm_flags (Generic VM) to PTE flags (arch specific)
@@ -191,26 +200,22 @@
 
 /* Optimal Sizing of Pg Tbl - based on MMU page size */
 #if defined(CONFIG_ARC_PAGE_SIZE_8K)
-#define BITS_FOR_PTE	8
+#define BITS_FOR_PTE	8		/* 11:8:13 */
 #elif defined(CONFIG_ARC_PAGE_SIZE_16K)
-#define BITS_FOR_PTE	8
+#define BITS_FOR_PTE	8		/* 10:8:14 */
 #elif defined(CONFIG_ARC_PAGE_SIZE_4K)
-#define BITS_FOR_PTE	9
+#define BITS_FOR_PTE	9		/* 11:9:12 */
 #endif
 
 #define BITS_FOR_PGD	(32 - BITS_FOR_PTE - BITS_IN_PAGE)
 
-#define PGDIR_SHIFT	(BITS_FOR_PTE + BITS_IN_PAGE)
+#define PGDIR_SHIFT	(32 - BITS_FOR_PGD)
 #define PGDIR_SIZE	(1UL << PGDIR_SHIFT)	/* vaddr span, not PDG sz */
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 
-#ifdef __ASSEMBLY__
-#define	PTRS_PER_PTE	(1 << BITS_FOR_PTE)
-#define	PTRS_PER_PGD	(1 << BITS_FOR_PGD)
-#else
-#define	PTRS_PER_PTE	(1UL << BITS_FOR_PTE)
-#define	PTRS_PER_PGD	(1UL << BITS_FOR_PGD)
-#endif
+#define	PTRS_PER_PTE	_BITUL(BITS_FOR_PTE)
+#define	PTRS_PER_PGD	_BITUL(BITS_FOR_PGD)
+
 /*
  * Number of entries a user land program use.
  * TASK_SIZE is the maximum vaddr that can be used by a userland program.
@@ -270,15 +275,10 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep)
 		(unsigned long)(((pte_val(x) - CONFIG_LINUX_LINK_BASE) >> \
 				PAGE_SHIFT)))
 
-#define mk_pte(page, pgprot)						\
-({									\
-	pte_t pte;							\
-	pte_val(pte) = __pa(page_address(page)) + pgprot_val(pgprot);	\
-	pte;								\
-})
-
+#define mk_pte(page, prot)	pfn_pte(page_to_pfn(page), prot)
 #define pte_pfn(pte)		(pte_val(pte) >> PAGE_SHIFT)
-#define pfn_pte(pfn, prot)	(__pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot)))
+#define pfn_pte(pfn, prot)	(__pte(((pte_t)(pfn) << PAGE_SHIFT) | \
+				 pgprot_val(prot)))
 #define __pte_index(addr)	(((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
 
 /*
@@ -295,23 +295,26 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep)
 /* Zoo of pte_xxx function */
 #define pte_read(pte)		(pte_val(pte) & _PAGE_READ)
 #define pte_write(pte)		(pte_val(pte) & _PAGE_WRITE)
-#define pte_dirty(pte)		(pte_val(pte) & _PAGE_MODIFIED)
+#define pte_dirty(pte)		(pte_val(pte) & _PAGE_DIRTY)
 #define pte_young(pte)		(pte_val(pte) & _PAGE_ACCESSED)
-#define pte_special(pte)	(0)
+#define pte_special(pte)	(pte_val(pte) & _PAGE_SPECIAL)
 
 #define PTE_BIT_FUNC(fn, op) \
 	static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; }
 
+PTE_BIT_FUNC(mknotpresent,	&= ~(_PAGE_PRESENT));
 PTE_BIT_FUNC(wrprotect,	&= ~(_PAGE_WRITE));
 PTE_BIT_FUNC(mkwrite,	|= (_PAGE_WRITE));
-PTE_BIT_FUNC(mkclean,	&= ~(_PAGE_MODIFIED));
-PTE_BIT_FUNC(mkdirty,	|= (_PAGE_MODIFIED));
+PTE_BIT_FUNC(mkclean,	&= ~(_PAGE_DIRTY));
+PTE_BIT_FUNC(mkdirty,	|= (_PAGE_DIRTY));
 PTE_BIT_FUNC(mkold,	&= ~(_PAGE_ACCESSED));
 PTE_BIT_FUNC(mkyoung,	|= (_PAGE_ACCESSED));
 PTE_BIT_FUNC(exprotect,	&= ~(_PAGE_EXECUTE));
 PTE_BIT_FUNC(mkexec,	|= (_PAGE_EXECUTE));
+PTE_BIT_FUNC(mkspecial,	|= (_PAGE_SPECIAL));
+PTE_BIT_FUNC(mkhuge,	|= (_PAGE_HW_SZ));
 
-static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
+#define __HAVE_ARCH_PTE_SPECIAL
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
@@ -357,7 +360,6 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 #define pgd_offset_fast(mm, addr)	pgd_offset(mm, addr)
 #endif
 
-extern void paging_init(void);
 extern pgd_t swapper_pg_dir[] __aligned(PAGE_SIZE);
 void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
 		      pte_t *ptep);
@@ -383,6 +385,10 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
  * remap a physical page `pfn' of size `size' with page protection `prot'
  * into virtual address `from'
  */
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#include <asm/hugepage.h>
+#endif
+
 #include <asm-generic/pgtable.h>
 
 /* to cope with aliasing VIPT cache */
diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h
index ee682d8e0213..44545354e9e8 100644
--- a/arch/arc/include/asm/processor.h
+++ b/arch/arc/include/asm/processor.h
@@ -114,7 +114,12 @@ extern unsigned int get_wchan(struct task_struct *p);
  * -----------------------------------------------------------------------------
  */
 #define VMALLOC_START	0x70000000
-#define VMALLOC_SIZE	(PAGE_OFFSET - VMALLOC_START)
+
+/*
+ * 1 PGDIR_SIZE each for fixmap/pkmap, 2 PGDIR_SIZE gutter
+ * See asm/highmem.h for details
+ */
+#define VMALLOC_SIZE	(PAGE_OFFSET - VMALLOC_START - PGDIR_SIZE * 4)
 #define VMALLOC_END	(VMALLOC_START + VMALLOC_SIZE)
 
 #define USER_KERNEL_GUTTER    0x10000000
diff --git a/arch/arc/include/asm/setup.h b/arch/arc/include/asm/setup.h
index 6e3ef5ba4f74..307846691be6 100644
--- a/arch/arc/include/asm/setup.h
+++ b/arch/arc/include/asm/setup.h
@@ -33,4 +33,11 @@ extern int root_mountflags, end_mem;
 void setup_processor(void);
 void __init setup_arch_memory(void);
 
+/* Helpers used in arc_*_mumbojumbo routines */
+#define IS_AVAIL1(v, s)		((v) ? s : "")
+#define IS_DISABLED_RUN(v)	((v) ? "" : "(disabled) ")
+#define IS_USED_RUN(v)		((v) ? "" : "(not used) ")
+#define IS_USED_CFG(cfg)	IS_USED_RUN(IS_ENABLED(cfg))
+#define IS_AVAIL2(v, s, cfg)	IS_AVAIL1(v, s), IS_AVAIL1(v, IS_USED_CFG(cfg))
+
 #endif /* __ASMARC_SETUP_H */
diff --git a/arch/arc/include/asm/smp.h b/arch/arc/include/asm/smp.h
index 3845b9e94f69..133c867d15af 100644
--- a/arch/arc/include/asm/smp.h
+++ b/arch/arc/include/asm/smp.h
@@ -45,12 +45,19 @@ extern int smp_ipi_irq_setup(int cpu, int irq);
  * struct plat_smp_ops	- SMP callbacks provided by platform to ARC SMP
  *
  * @info:		SoC SMP specific info for /proc/cpuinfo etc
+ * @init_early_smp:	A SMP specific h/w block can init itself
+ * 			Could be common across platforms so not covered by
+ * 			mach_desc->init_early()
+ * @init_irq_cpu:	Called for each core so SMP h/w block driver can do
+ * 			any needed setup per cpu (e.g. IPI request)
  * @cpu_kick:		For Master to kickstart a cpu (optionally at a PC)
  * @ipi_send:		To send IPI to a @cpu
  * @ips_clear:		To clear IPI received at @irq
  */
 struct plat_smp_ops {
 	const char 	*info;
+	void		(*init_early_smp)(void);
+	void		(*init_irq_cpu)(int cpu);
 	void		(*cpu_kick)(int cpu, unsigned long pc);
 	void		(*ipi_send)(int cpu);
 	void		(*ipi_clear)(int irq);
diff --git a/arch/arc/include/asm/tlbflush.h b/arch/arc/include/asm/tlbflush.h
index 71c7b2e4b874..1fe9c8c80280 100644
--- a/arch/arc/include/asm/tlbflush.h
+++ b/arch/arc/include/asm/tlbflush.h
@@ -17,6 +17,8 @@ void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long page);
 void local_flush_tlb_kernel_range(unsigned long start, unsigned long end);
 void local_flush_tlb_range(struct vm_area_struct *vma,
 			   unsigned long start, unsigned long end);
+void local_flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
+			       unsigned long end);
 
 #ifndef CONFIG_SMP
 #define flush_tlb_range(vma, s, e)	local_flush_tlb_range(vma, s, e)
@@ -24,6 +26,7 @@ void local_flush_tlb_range(struct vm_area_struct *vma,
 #define flush_tlb_kernel_range(s, e)	local_flush_tlb_kernel_range(s, e)
 #define flush_tlb_all()			local_flush_tlb_all()
 #define flush_tlb_mm(mm)		local_flush_tlb_mm(mm)
+#define flush_pmd_tlb_range(vma, s, e)	local_flush_pmd_tlb_range(vma, s, e)
 #else
 extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 							 unsigned long end);
@@ -31,5 +34,7 @@ extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long page);
 extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
 extern void flush_tlb_all(void);
 extern void flush_tlb_mm(struct mm_struct *mm);
+extern void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
+
 #endif /* CONFIG_SMP */
 #endif
diff --git a/arch/arc/include/uapi/asm/page.h b/arch/arc/include/uapi/asm/page.h
index 9d129a2a1351..059aff38f10a 100644
--- a/arch/arc/include/uapi/asm/page.h
+++ b/arch/arc/include/uapi/asm/page.h
@@ -9,6 +9,8 @@
 #ifndef _UAPI__ASM_ARC_PAGE_H
 #define _UAPI__ASM_ARC_PAGE_H
 
+#include <linux/const.h>
+
 /* PAGE_SHIFT determines the page size */
 #if defined(CONFIG_ARC_PAGE_SIZE_16K)
 #define PAGE_SHIFT 14
@@ -25,13 +27,8 @@
 #define PAGE_SHIFT 13
 #endif
 
-#ifdef __ASSEMBLY__
-#define PAGE_SIZE	(1 << PAGE_SHIFT)
-#define PAGE_OFFSET	(0x80000000)
-#else
-#define PAGE_SIZE	(1UL << PAGE_SHIFT)	/* Default 8K */
-#define PAGE_OFFSET	(0x80000000UL)		/* Kernel starts at 2G onwards */
-#endif
+#define PAGE_SIZE	_BITUL(PAGE_SHIFT)	/* Default 8K */
+#define PAGE_OFFSET	_AC(0x80000000, UL)	/* Kernel starts at 2G onwrds */
 
 #define PAGE_MASK	(~(PAGE_SIZE-1))