Linux-libre 4.7.1-gnupck-4.7.1-gnu

21 files changed, 302 insertions, 409 deletions

diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 7730d302c..dd683995b 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -17,56 +17,25 @@
 #include <asm/barrier.h>
 #include <asm/smp.h>
 
+#ifndef CONFIG_ARC_PLAT_EZNPS
+
 #define atomic_read(v)  READ_ONCE((v)->counter)
 
 #ifdef CONFIG_ARC_HAS_LLSC
 
 #define atomic_set(v, i) WRITE_ONCE(((v)->counter), (i))
 
-#ifdef CONFIG_ARC_STAR_9000923308
-
-#define SCOND_FAIL_RETRY_VAR_DEF						\
-	unsigned int delay = 1, tmp;						\
-
-#define SCOND_FAIL_RETRY_ASM							\
-	"	bz	4f			\n"				\
-	"   ; --- scond fail delay ---		\n"				\
-	"	mov	%[tmp], %[delay]	\n"	/* tmp = delay */	\
-	"2: 	brne.d	%[tmp], 0, 2b		\n"	/* while (tmp != 0) */	\
-	"	sub	%[tmp], %[tmp], 1	\n"	/* tmp-- */		\
-	"	rol	%[delay], %[delay]	\n"	/* delay *= 2 */	\
-	"	b	1b			\n"	/* start over */	\
-	"4: ; --- success ---			\n"				\
-
-#define SCOND_FAIL_RETRY_VARS							\
-	  ,[delay] "+&r" (delay),[tmp] "=&r"	(tmp)				\
-
-#else	/* !CONFIG_ARC_STAR_9000923308 */
-
-#define SCOND_FAIL_RETRY_VAR_DEF
-
-#define SCOND_FAIL_RETRY_ASM							\
-	"	bnz     1b			\n"				\
-
-#define SCOND_FAIL_RETRY_VARS
-
-#endif
-
 #define ATOMIC_OP(op, c_op, asm_op)					\
 static inline void atomic_##op(int i, atomic_t *v)			\
 {									\
-	unsigned int val;				                \
-	SCOND_FAIL_RETRY_VAR_DEF                                        \
+	unsigned int val;						\
 									\
 	__asm__ __volatile__(						\
 	"1:	llock   %[val], [%[ctr]]		\n"		\
 	"	" #asm_op " %[val], %[val], %[i]	\n"		\
 	"	scond   %[val], [%[ctr]]		\n"		\
-	"						\n"		\
-	SCOND_FAIL_RETRY_ASM						\
-									\
+	"	bnz     1b				\n"		\
 	: [val]	"=&r"	(val) /* Early clobber to prevent reg reuse */	\
-	  SCOND_FAIL_RETRY_VARS						\
 	: [ctr]	"r"	(&v->counter), /* Not "m": llock only supports reg direct addr mode */	\
 	  [i]	"ir"	(i)						\
 	: "cc");							\
@@ -75,8 +44,7 @@ static inline void atomic_##op(int i, atomic_t *v)			\
 #define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
 static inline int atomic_##op##_return(int i, atomic_t *v)		\
 {									\
-	unsigned int val;				                \
-	SCOND_FAIL_RETRY_VAR_DEF                                        \
+	unsigned int val;						\
 									\
 	/*								\
 	 * Explicit full memory barrier needed before/after as		\
@@ -88,11 +56,8 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	"1:	llock   %[val], [%[ctr]]		\n"		\
 	"	" #asm_op " %[val], %[val], %[i]	\n"		\
 	"	scond   %[val], [%[ctr]]		\n"		\
-	"						\n"		\
-	SCOND_FAIL_RETRY_ASM						\
-									\
+	"	bnz     1b				\n"		\
 	: [val]	"=&r"	(val)						\
-	  SCOND_FAIL_RETRY_VARS						\
 	: [ctr]	"r"	(&v->counter),					\
 	  [i]	"ir"	(i)						\
 	: "cc");							\
@@ -180,13 +145,88 @@ ATOMIC_OP(andnot, &= ~, bic)
 ATOMIC_OP(or, |=, or)
 ATOMIC_OP(xor, ^=, xor)
 
-#undef ATOMIC_OPS
-#undef ATOMIC_OP_RETURN
-#undef ATOMIC_OP
 #undef SCOND_FAIL_RETRY_VAR_DEF
 #undef SCOND_FAIL_RETRY_ASM
 #undef SCOND_FAIL_RETRY_VARS
 
+#else /* CONFIG_ARC_PLAT_EZNPS */
+
+static inline int atomic_read(const atomic_t *v)
+{
+	int temp;
+
+	__asm__ __volatile__(
+	"	ld.di %0, [%1]"
+	: "=r"(temp)
+	: "r"(&v->counter)
+	: "memory");
+	return temp;
+}
+
+static inline void atomic_set(atomic_t *v, int i)
+{
+	__asm__ __volatile__(
+	"	st.di %0,[%1]"
+	:
+	: "r"(i), "r"(&v->counter)
+	: "memory");
+}
+
+#define ATOMIC_OP(op, c_op, asm_op)					\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	__asm__ __volatile__(						\
+	"	mov r2, %0\n"						\
+	"	mov r3, %1\n"						\
+	"       .word %2\n"						\
+	:								\
+	: "r"(i), "r"(&v->counter), "i"(asm_op)				\
+	: "r2", "r3", "memory");					\
+}									\
+
+#define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	unsigned int temp = i;						\
+									\
+	/* Explicit full memory barrier needed before/after */		\
+	smp_mb();							\
+									\
+	__asm__ __volatile__(						\
+	"	mov r2, %0\n"						\
+	"	mov r3, %1\n"						\
+	"       .word %2\n"						\
+	"	mov %0, r2"						\
+	: "+r"(temp)							\
+	: "r"(&v->counter), "i"(asm_op)					\
+	: "r2", "r3", "memory");					\
+									\
+	smp_mb();							\
+									\
+	temp c_op i;							\
+									\
+	return temp;							\
+}
+
+#define ATOMIC_OPS(op, c_op, asm_op)					\
+	ATOMIC_OP(op, c_op, asm_op)					\
+	ATOMIC_OP_RETURN(op, c_op, asm_op)
+
+ATOMIC_OPS(add, +=, CTOP_INST_AADD_DI_R2_R2_R3)
+#define atomic_sub(i, v) atomic_add(-(i), (v))
+#define atomic_sub_return(i, v) atomic_add_return(-(i), (v))
+
+ATOMIC_OP(and, &=, CTOP_INST_AAND_DI_R2_R2_R3)
+#define atomic_andnot(mask, v) atomic_and(~(mask), (v))
+ATOMIC_OP(or, |=, CTOP_INST_AOR_DI_R2_R2_R3)
+ATOMIC_OP(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3)
+
+#endif /* CONFIG_ARC_PLAT_EZNPS */
+
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
+
 /**
  * __atomic_add_unless - add unless the number is a given value
  * @v: pointer of type atomic_t
diff --git a/arch/arc/include/asm/barrier.h b/arch/arc/include/asm/barrier.h
index a7209983e..b1e327495 100644
--- a/arch/arc/include/asm/barrier.h
+++ b/arch/arc/include/asm/barrier.h
@@ -30,9 +30,7 @@
 #define rmb()	asm volatile("dmb 1\n" : : : "memory")
 #define wmb()	asm volatile("dmb 2\n" : : : "memory")
 
-#endif
-
-#ifdef CONFIG_ISA_ARCOMPACT
+#elif !defined(CONFIG_ARC_PLAT_EZNPS)  /* CONFIG_ISA_ARCOMPACT */
 
 /*
  * ARCompact based cores (ARC700) only have SYNC instruction which is super
@@ -41,6 +39,14 @@
  */
 
 #define mb()	asm volatile("sync\n" : : : "memory")
+
+#else	/* CONFIG_ARC_PLAT_EZNPS */
+
+#include <plat/ctop.h>
+
+#define mb()	asm volatile (".word %0" : : "i"(CTOP_INST_SCHD_RW) : "memory")
+#define rmb()	asm volatile (".word %0" : : "i"(CTOP_INST_SCHD_RD) : "memory")
+
 #endif
 
 #include <asm-generic/barrier.h>
diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h
index 0352fb8d2..8da87feec 100644
--- a/arch/arc/include/asm/bitops.h
+++ b/arch/arc/include/asm/bitops.h
@@ -22,7 +22,7 @@
 #include <asm/smp.h>
 #endif
 
-#if defined(CONFIG_ARC_HAS_LLSC)
+#ifdef CONFIG_ARC_HAS_LLSC
 
 /*
  * Hardware assisted Atomic-R-M-W
@@ -88,7 +88,7 @@ static inline int test_and_##op##_bit(unsigned long nr, volatile unsigned long *
 	return (old & (1 << nr)) != 0;					\
 }
 
-#else	/* !CONFIG_ARC_HAS_LLSC */
+#elif !defined(CONFIG_ARC_PLAT_EZNPS)
 
 /*
  * Non hardware assisted Atomic-R-M-W
@@ -139,7 +139,55 @@ static inline int test_and_##op##_bit(unsigned long nr, volatile unsigned long *
 	return (old & (1UL << (nr & 0x1f))) != 0;			\
 }
 
-#endif /* CONFIG_ARC_HAS_LLSC */
+#else /* CONFIG_ARC_PLAT_EZNPS */
+
+#define BIT_OP(op, c_op, asm_op)					\
+static inline void op##_bit(unsigned long nr, volatile unsigned long *m)\
+{									\
+	m += nr >> 5;							\
+									\
+	nr = (1UL << (nr & 0x1f));					\
+	if (asm_op == CTOP_INST_AAND_DI_R2_R2_R3)			\
+		nr = ~nr;						\
+									\
+	__asm__ __volatile__(						\
+	"	mov r2, %0\n"						\
+	"	mov r3, %1\n"						\
+	"	.word %2\n"						\
+	:								\
+	: "r"(nr), "r"(m), "i"(asm_op)					\
+	: "r2", "r3", "memory");					\
+}
+
+#define TEST_N_BIT_OP(op, c_op, asm_op)					\
+static inline int test_and_##op##_bit(unsigned long nr, volatile unsigned long *m)\
+{									\
+	unsigned long old;						\
+									\
+	m += nr >> 5;							\
+									\
+	nr = old = (1UL << (nr & 0x1f));				\
+	if (asm_op == CTOP_INST_AAND_DI_R2_R2_R3)			\
+		old = ~old;						\
+									\
+	/* Explicit full memory barrier needed before/after */		\
+	smp_mb();							\
+									\
+	__asm__ __volatile__(						\
+	"	mov r2, %0\n"						\
+	"	mov r3, %1\n"						\
+	"       .word %2\n"						\
+	"	mov %0, r2"						\
+	: "+r"(old)							\
+	: "r"(m), "i"(asm_op)						\
+	: "r2", "r3", "memory");					\
+									\
+	smp_mb();							\
+									\
+	return (old & nr) != 0;					\
+}
+
+#endif /* CONFIG_ARC_PLAT_EZNPS */
 
 /***************************************
  * Non atomic variants
@@ -181,9 +229,15 @@ static inline int __test_and_##op##_bit(unsigned long nr, volatile unsigned long
 	/* __test_and_set_bit(), __test_and_clear_bit(), __test_and_change_bit() */\
 	__TEST_N_BIT_OP(op, c_op, asm_op)
 
+#ifndef CONFIG_ARC_PLAT_EZNPS
 BIT_OPS(set, |, bset)
 BIT_OPS(clear, & ~, bclr)
 BIT_OPS(change, ^, bxor)
+#else
+BIT_OPS(set, |, CTOP_INST_AOR_DI_R2_R2_R3)
+BIT_OPS(clear, & ~, CTOP_INST_AAND_DI_R2_R2_R3)
+BIT_OPS(change, ^, CTOP_INST_AXOR_DI_R2_R2_R3)
+#endif
 
 /*
  * This routine doesn't need to be atomic.
diff --git a/arch/arc/include/asm/clk.h b/arch/arc/include/asm/clk.h
deleted file mode 100644
index bf9d29f5b..000000000
--- a/arch/arc/include/asm/clk.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * Copyright (C) 2012 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_CLK_H
-#define _ASM_ARC_CLK_H
-
-/* Although we can't really hide core_freq, the accessor is still better way */
-extern unsigned long core_freq;
-
-static inline unsigned long arc_get_core_freq(void)
-{
-	return core_freq;
-}
-
-extern int arc_set_core_freq(unsigned long);
-
-#endif
diff --git a/arch/arc/include/asm/cmpxchg.h b/arch/arc/include/asm/cmpxchg.h
index a444be67c..d819de1c5 100644
--- a/arch/arc/include/asm/cmpxchg.h
+++ b/arch/arc/include/asm/cmpxchg.h
@@ -44,7 +44,7 @@ __cmpxchg(volatile void *ptr, unsigned long expected, unsigned long new)
 	return prev;
 }
 
-#else
+#elif !defined(CONFIG_ARC_PLAT_EZNPS)
 
 static inline unsigned long
 __cmpxchg(volatile void *ptr, unsigned long expected, unsigned long new)
@@ -64,23 +64,48 @@ __cmpxchg(volatile void *ptr, unsigned long expected, unsigned long new)
 	return prev;
 }
 
+#else /* CONFIG_ARC_PLAT_EZNPS */
+
+static inline unsigned long
+__cmpxchg(volatile void *ptr, unsigned long expected, unsigned long new)
+{
+	/*
+	 * Explicit full memory barrier needed before/after
+	 */
+	smp_mb();
+
+	write_aux_reg(CTOP_AUX_GPA1, expected);
+
+	__asm__ __volatile__(
+	"	mov r2, %0\n"
+	"	mov r3, %1\n"
+	"	.word %2\n"
+	"	mov %0, r2"
+	: "+r"(new)
+	: "r"(ptr), "i"(CTOP_INST_EXC_DI_R2_R2_R3)
+	: "r2", "r3", "memory");
+
+	smp_mb();
+
+	return new;
+}
+
 #endif /* CONFIG_ARC_HAS_LLSC */
 
 #define cmpxchg(ptr, o, n) ((typeof(*(ptr)))__cmpxchg((ptr), \
 				(unsigned long)(o), (unsigned long)(n)))
 
 /*
- * Since not supported natively, ARC cmpxchg() uses atomic_ops_lock (UP/SMP)
- * just to gaurantee semantics.
- * atomic_cmpxchg() needs to use the same locks as it's other atomic siblings
- * which also happens to be atomic_ops_lock.
- *
- * Thus despite semantically being different, implementation of atomic_cmpxchg()
- * is same as cmpxchg().
+ * atomic_cmpxchg is same as cmpxchg
+ *   LLSC: only different in data-type, semantics are exactly same
+ *  !LLSC: cmpxchg() has to use an external lock atomic_ops_lock to guarantee
+ *         semantics, and this lock also happens to be used by atomic_*()
  */
 #define atomic_cmpxchg(v, o, n) ((int)cmpxchg(&((v)->counter), (o), (n)))
 
 
+#ifndef CONFIG_ARC_PLAT_EZNPS
+
 /*
  * xchg (reg with memory) based on "Native atomic" EX insn
  */
@@ -143,6 +168,41 @@ static inline unsigned long __xchg(unsigned long val, volatile void *ptr,
 
 #endif
 
+#else /* CONFIG_ARC_PLAT_EZNPS */
+
+static inline unsigned long __xchg(unsigned long val, volatile void *ptr,
+				   int size)
+{
+	extern unsigned long __xchg_bad_pointer(void);
+
+	switch (size) {
+	case 4:
+		/*
+		 * Explicit full memory barrier needed before/after
+		 */
+		smp_mb();
+
+		__asm__ __volatile__(
+		"	mov r2, %0\n"
+		"	mov r3, %1\n"
+		"	.word %2\n"
+		"	mov %0, r2\n"
+		: "+r"(val)
+		: "r"(ptr), "i"(CTOP_INST_XEX_DI_R2_R2_R3)
+		: "r2", "r3", "memory");
+
+		smp_mb();
+
+		return val;
+	}
+	return __xchg_bad_pointer();
+}
+
+#define xchg(ptr, with) ((typeof(*(ptr)))__xchg((unsigned long)(with), (ptr), \
+						 sizeof(*(ptr))))
+
+#endif /* CONFIG_ARC_PLAT_EZNPS */
+
 /*
  * "atomic" variant of xchg()
  * REQ: It needs to follow the same serialization rules as other atomic_xxx()
diff --git a/arch/arc/include/asm/entry-compact.h b/arch/arc/include/asm/entry-compact.h
index 1d8f57cd6..14c310f2e 100644
--- a/arch/arc/include/asm/entry-compact.h
+++ b/arch/arc/include/asm/entry-compact.h
@@ -36,6 +36,10 @@
 #include <asm/irqflags-compact.h>
 #include <asm/thread_info.h>	/* For THREAD_SIZE */
 
+#ifdef CONFIG_ARC_PLAT_EZNPS
+#include <plat/ctop.h>
+#endif
+
 /*--------------------------------------------------------------
  * Switch to Kernel Mode stack if SP points to User Mode stack
  *
@@ -72,8 +76,8 @@
 	 * We need to be a bit more cautious here. What if a kernel bug in
 	 * L1 ISR, caused SP to go whaco (some small value which looks like
 	 * USER stk) and then we take L2 ISR.
-	 * Above brlo alone would treat it as a valid L1-L2 sceanrio
-	 * instead of shouting alound
+	 * Above brlo alone would treat it as a valid L1-L2 scenario
+	 * instead of shouting around
 	 * The only feasible way is to make sure this L2 happened in
 	 * L1 prelogue ONLY i.e. ilink2 is less than a pre-set marker in
 	 * L1 ISR before it switches stack
@@ -296,11 +300,13 @@
 	bic \reg, sp, (THREAD_SIZE - 1)
 .endm
 
+#ifndef CONFIG_ARC_PLAT_EZNPS
 /* Get CPU-ID of this core */
 .macro  GET_CPU_ID  reg
 	lr  \reg, [identity]
 	lsr \reg, \reg, 8
 	bmsk \reg, \reg, 7
 .endm
+#endif
 
 #endif  /* __ASM_ARC_ENTRY_COMPACT_H */
diff --git a/arch/arc/include/asm/hugepage.h b/arch/arc/include/asm/hugepage.h
index 7afe3356b..317ff773e 100644
--- a/arch/arc/include/asm/hugepage.h
+++ b/arch/arc/include/asm/hugepage.h
@@ -61,8 +61,6 @@ static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 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,
diff --git a/arch/arc/include/asm/irq.h b/arch/arc/include/asm/irq.h
index 49014f0ef..c0fa0d2de 100644
--- a/arch/arc/include/asm/irq.h
+++ b/arch/arc/include/asm/irq.h
@@ -13,21 +13,14 @@
 #define NR_IRQS		128 /* allow some CPU external IRQ handling */
 
 /* Platform Independent IRQs */
-#ifdef CONFIG_ISA_ARCOMPACT
-#define TIMER0_IRQ      3
-#define TIMER1_IRQ      4
-#else
-#define TIMER0_IRQ      16
-#define TIMER1_IRQ      17
+#ifdef CONFIG_ISA_ARCV2
+#define IPI_IRQ		19
+#define SOFTIRQ_IRQ	21
 #endif
 
 #include <linux/interrupt.h>
 #include <asm-generic/irq.h>
 
 extern void arc_init_IRQ(void);
-void arc_local_timer_setup(void);
-void arc_request_percpu_irq(int irq, int cpu,
-                            irqreturn_t (*isr)(int irq, void *dev),
-                            const char *irq_nm, void *percpu_dev);
 
 #endif
diff --git a/arch/arc/include/asm/mmu_context.h b/arch/arc/include/asm/mmu_context.h
index 1fd467ef6..b0b87f244 100644
--- a/arch/arc/include/asm/mmu_context.h
+++ b/arch/arc/include/asm/mmu_context.h
@@ -83,7 +83,7 @@ static inline void get_new_mmu_context(struct mm_struct *mm)
 		local_flush_tlb_all();
 
 		/*
-		 * Above checke for rollover of 8 bit ASID in 32 bit container.
+		 * Above check for rollover of 8 bit ASID in 32 bit container.
 		 * If the container itself wrapped around, set it to a non zero
 		 * "generation" to distinguish from no context
 		 */
diff --git a/arch/arc/include/asm/page.h b/arch/arc/include/asm/page.h
index 0d5385488..296c3426a 100644
--- a/arch/arc/include/asm/page.h
+++ b/arch/arc/include/asm/page.h
@@ -31,7 +31,11 @@ void clear_user_page(void *to, unsigned long u_vaddr, struct page *page);
  * These are used to make use of C type-checking..
  */
 typedef struct {
+#ifdef CONFIG_ARC_HAS_PAE40
+	unsigned long long pte;
+#else
 	unsigned long pte;
+#endif
 } pte_t;
 typedef struct {
 	unsigned long pgd;
diff --git a/arch/arc/include/asm/pgalloc.h b/arch/arc/include/asm/pgalloc.h
index 86ed67128..3749234b7 100644
--- a/arch/arc/include/asm/pgalloc.h
+++ b/arch/arc/include/asm/pgalloc.h
@@ -95,7 +95,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 {
 	pte_t *pte;
 
-	pte = (pte_t *) __get_free_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO,
+	pte = (pte_t *) __get_free_pages(GFP_KERNEL | __GFP_ZERO,
 					 __get_order_pte());
 
 	return pte;
@@ -107,7 +107,7 @@ pte_alloc_one(struct mm_struct *mm, unsigned long address)
 	pgtable_t pte_pg;
 	struct page *page;
 
-	pte_pg = (pgtable_t)__get_free_pages(GFP_KERNEL | __GFP_REPEAT, __get_order_pte());
+	pte_pg = (pgtable_t)__get_free_pages(GFP_KERNEL, __get_order_pte());
 	if (!pte_pg)
 		return 0;
 	memzero((void *)pte_pg, PTRS_PER_PTE * sizeof(pte_t));
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 10d4b8b8e..858f98ef7 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -47,7 +47,7 @@
  * Page Tables are purely for Linux VM's consumption and the bits below are
  * suited to that (uniqueness). Hence some are not implemented in the TLB and
  * some have different value in TLB.
- * e.g. MMU v2: K_READ bit is 8 and so is GLOBAL (possible becoz they live in
+ * e.g. MMU v2: K_READ bit is 8 and so is GLOBAL (possible because they live in
  *      seperate PD0 and PD1, which combined forms a translation entry)
  *      while for PTE perspective, they are 8 and 9 respectively
  * with MMU v3: Most bits (except SHARED) represent the exact hardware pos
@@ -217,7 +217,7 @@
 #define BITS_FOR_PTE	(PGDIR_SHIFT - PAGE_SHIFT)
 #define BITS_FOR_PGD	(32 - PGDIR_SHIFT)
 
-#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)	/* vaddr span, not PDG sz */
+#define PGDIR_SIZE	_BITUL(PGDIR_SHIFT)	/* vaddr span, not PDG sz */
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 
 #define	PTRS_PER_PTE	_BITUL(BITS_FOR_PTE)
diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h
index 1d694c1ef..16b630fbe 100644
--- a/arch/arc/include/asm/processor.h
+++ b/arch/arc/include/asm/processor.h
@@ -57,9 +57,19 @@ struct task_struct;
  * A lot of busy-wait loops in SMP are based off of non-volatile data otherwise
  * get optimised away by gcc
  */
-#define cpu_relax()	__asm__ __volatile__ ("" : : : "memory")
+#ifndef CONFIG_EZNPS_MTM_EXT
 
-#define cpu_relax_lowlatency() cpu_relax()
+#define cpu_relax()		barrier()
+#define cpu_relax_lowlatency()	cpu_relax()
+
+#else
+
+#define cpu_relax()     \
+	__asm__ __volatile__ (".word %0" : : "i"(CTOP_INST_SCHD_RW) : "memory")
+
+#define cpu_relax_lowlatency()	barrier()
+
+#endif
 
 #define copy_segments(tsk, mm)      do { } while (0)
 #define release_segments(mm)        do { } while (0)
@@ -68,7 +78,7 @@ struct task_struct;
 #define KSTK_ESP(tsk)   (task_pt_regs(tsk)->sp)
 
 /*
- * Where abouts of Task's sp, fp, blink when it was last seen in kernel mode.
+ * Where about of Task's sp, fp, blink when it was last seen in kernel mode.
  * Look in process.c for details of kernel stack layout
  */
 #define TSK_K_ESP(tsk)		(tsk->thread.ksp)
@@ -97,7 +107,7 @@ extern unsigned int get_wchan(struct task_struct *p);
 #endif /* !__ASSEMBLY__ */
 
 /*
- * System Memory Map on ARC
+ * Default System Memory Map on ARC
  *
  * ---------------------------- (lower 2G, Translated) -------------------------
  * 0x0000_0000		0x5FFF_FFFF	(user vaddr: TASK_SIZE)
@@ -109,20 +119,37 @@ extern unsigned int get_wchan(struct task_struct *p);
  * 0xC000_0000		0xFFFF_FFFF	(peripheral uncached space)
  * -----------------------------------------------------------------------------
  */
-#define VMALLOC_START	0x70000000
 
-/*
- * 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 TASK_SIZE	0x60000000
 
-#define USER_KERNEL_GUTTER    0x10000000
+#define VMALLOC_START	(PAGE_OFFSET - (CONFIG_ARC_KVADDR_SIZE << 20))
 
-#define TASK_SIZE	(VMALLOC_START - USER_KERNEL_GUTTER)
+/* 1 PGDIR_SIZE each for fixmap/pkmap, 2 PGDIR_SIZE gutter (see asm/highmem.h) */
+#define VMALLOC_SIZE	((CONFIG_ARC_KVADDR_SIZE << 20) - PGDIR_SIZE * 4)
 
+#define VMALLOC_END	(VMALLOC_START + VMALLOC_SIZE)
+
+#define USER_KERNEL_GUTTER    (VMALLOC_START - TASK_SIZE)
+
+#ifdef CONFIG_ARC_PLAT_EZNPS
+/* NPS architecture defines special window of 129M in user address space for
+ * special memory areas, when accessing this window the MMU do not use TLB.
+ * Instead MMU direct the access to:
+ * 0x57f00000:0x57ffffff -- 1M of closely coupled memory (aka CMEM)
+ * 0x58000000:0x5fffffff -- 16 huge pages, 8M each, with fixed map (aka FMTs)
+ *
+ * CMEM - is the fastest memory we got and its size is 16K.
+ * FMT  - is used to map either to internal/external memory.
+ * Internal memory is the second fast memory and its size is 16M
+ * External memory is the biggest memory (16G) and also the slowest.
+ *
+ * STACK_TOP need to be PMD align (21bit) that is why we supply 0x57e00000.
+ */
+#define STACK_TOP       0x57e00000
+#else
 #define STACK_TOP       TASK_SIZE
+#endif
+
 #define STACK_TOP_MAX   STACK_TOP
 
 /* This decides where the kernel will search for a free chunk of vm
diff --git a/arch/arc/include/asm/setup.h b/arch/arc/include/asm/setup.h
index 307846691..48b37c693 100644
--- a/arch/arc/include/asm/setup.h
+++ b/arch/arc/include/asm/setup.h
@@ -12,7 +12,11 @@
 #include <linux/types.h>
 #include <uapi/asm/setup.h>
 
+#ifdef CONFIG_ARC_PLAT_EZNPS
+#define COMMAND_LINE_SIZE 2048
+#else
 #define COMMAND_LINE_SIZE 256
+#endif
 
 /*
  * Data structure to map a ID to string
diff --git a/arch/arc/include/asm/smp.h b/arch/arc/include/asm/smp.h
index 991380438..89fdd1b0a 100644
--- a/arch/arc/include/asm/smp.h
+++ b/arch/arc/include/asm/smp.h
@@ -86,7 +86,7 @@ static inline const char *arc_platform_smp_cpuinfo(void)
  * (1) These insn were introduced only in 4.10 release. So for older released
  *	support needed.
  *
- * (2) In a SMP setup, the LLOCK/SCOND atomiticity across CPUs needs to be
+ * (2) In a SMP setup, the LLOCK/SCOND atomicity across CPUs needs to be
  *	gaurantted by the platform (not something which core handles).
  *	Assuming a platform won't, SMP Linux needs to use spinlocks + local IRQ
  *	disabling for atomicity.
diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h
index db8c59d1e..cded4a9b5 100644
--- a/arch/arc/include/asm/spinlock.h
+++ b/arch/arc/include/asm/spinlock.h
@@ -20,11 +20,6 @@
 
 #ifdef CONFIG_ARC_HAS_LLSC
 
-/*
- * A normal LLOCK/SCOND based system, w/o need for livelock workaround
- */
-#ifndef CONFIG_ARC_STAR_9000923308
-
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	unsigned int val;
@@ -238,293 +233,6 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 	smp_mb();
 }
 
-#else	/* CONFIG_ARC_STAR_9000923308 */
-
-/*
- * HS38x4 could get into a LLOCK/SCOND livelock in case of multiple overlapping
- * coherency transactions in the SCU. The exclusive line state keeps rotating
- * among contenting cores leading to a never ending cycle. So break the cycle
- * by deferring the retry of failed exclusive access (SCOND). The actual delay
- * needed is function of number of contending cores as well as the unrelated
- * coherency traffic from other cores. To keep the code simple, start off with
- * small delay of 1 which would suffice most cases and in case of contention
- * double the delay. Eventually the delay is sufficient such that the coherency
- * pipeline is drained, thus a subsequent exclusive access would succeed.
- */
-
-#define SCOND_FAIL_RETRY_VAR_DEF						\
-	unsigned int delay, tmp;						\
-
-#define SCOND_FAIL_RETRY_ASM							\
-	"   ; --- scond fail delay ---		\n"				\
-	"	mov	%[tmp], %[delay]	\n"	/* tmp = delay */	\
-	"2: 	brne.d	%[tmp], 0, 2b		\n"	/* while (tmp != 0) */	\
-	"	sub	%[tmp], %[tmp], 1	\n"	/* tmp-- */		\
-	"	rol	%[delay], %[delay]	\n"	/* delay *= 2 */	\
-	"	b	1b			\n"	/* start over */	\
-	"					\n"				\
-	"4: ; --- done ---			\n"				\
-
-#define SCOND_FAIL_RETRY_VARS							\
-	  ,[delay] "=&r" (delay), [tmp] "=&r"	(tmp)				\
-
-static inline void arch_spin_lock(arch_spinlock_t *lock)
-{
-	unsigned int val;
-	SCOND_FAIL_RETRY_VAR_DEF;
-
-	smp_mb();
-
-	__asm__ __volatile__(
-	"0:	mov	%[delay], 1		\n"
-	"1:	llock	%[val], [%[slock]]	\n"
-	"	breq	%[val], %[LOCKED], 0b	\n"	/* spin while LOCKED */
-	"	scond	%[LOCKED], [%[slock]]	\n"	/* acquire */
-	"	bz	4f			\n"	/* done */
-	"					\n"
-	SCOND_FAIL_RETRY_ASM
-
-	: [val]		"=&r"	(val)
-	  SCOND_FAIL_RETRY_VARS
-	: [slock]	"r"	(&(lock->slock)),
-	  [LOCKED]	"r"	(__ARCH_SPIN_LOCK_LOCKED__)
-	: "memory", "cc");
-
-	smp_mb();
-}
-
-/* 1 - lock taken successfully */
-static inline int arch_spin_trylock(arch_spinlock_t *lock)
-{
-	unsigned int val, got_it = 0;
-	SCOND_FAIL_RETRY_VAR_DEF;
-
-	smp_mb();
-
-	__asm__ __volatile__(
-	"0:	mov	%[delay], 1		\n"
-	"1:	llock	%[val], [%[slock]]	\n"
-	"	breq	%[val], %[LOCKED], 4f	\n"	/* already LOCKED, just bail */
-	"	scond	%[LOCKED], [%[slock]]	\n"	/* acquire */
-	"	bz.d	4f			\n"
-	"	mov.z	%[got_it], 1		\n"	/* got it */
-	"					\n"
-	SCOND_FAIL_RETRY_ASM
-
-	: [val]		"=&r"	(val),
-	  [got_it]	"+&r"	(got_it)
-	  SCOND_FAIL_RETRY_VARS
-	: [slock]	"r"	(&(lock->slock)),
-	  [LOCKED]	"r"	(__ARCH_SPIN_LOCK_LOCKED__)
-	: "memory", "cc");
-
-	smp_mb();
-
-	return got_it;
-}
-
-static inline void arch_spin_unlock(arch_spinlock_t *lock)
-{
-	smp_mb();
-
-	lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__;
-
-	smp_mb();
-}
-
-/*
- * Read-write spinlocks, allowing multiple readers but only one writer.
- * Unfair locking as Writers could be starved indefinitely by Reader(s)
- */
-
-static inline void arch_read_lock(arch_rwlock_t *rw)
-{
-	unsigned int val;
-	SCOND_FAIL_RETRY_VAR_DEF;
-
-	smp_mb();
-
-	/*
-	 * zero means writer holds the lock exclusively, deny Reader.
-	 * Otherwise grant lock to first/subseq reader
-	 *
-	 * 	if (rw->counter > 0) {
-	 *		rw->counter--;
-	 *		ret = 1;
-	 *	}
-	 */
-
-	__asm__ __volatile__(
-	"0:	mov	%[delay], 1		\n"
-	"1:	llock	%[val], [%[rwlock]]	\n"
-	"	brls	%[val], %[WR_LOCKED], 0b\n"	/* <= 0: spin while write locked */
-	"	sub	%[val], %[val], 1	\n"	/* reader lock */
-	"	scond	%[val], [%[rwlock]]	\n"
-	"	bz	4f			\n"	/* done */
-	"					\n"
-	SCOND_FAIL_RETRY_ASM
-
-	: [val]		"=&r"	(val)
-	  SCOND_FAIL_RETRY_VARS
-	: [rwlock]	"r"	(&(rw->counter)),
-	  [WR_LOCKED]	"ir"	(0)
-	: "memory", "cc");
-
-	smp_mb();
-}
-
-/* 1 - lock taken successfully */
-static inline int arch_read_trylock(arch_rwlock_t *rw)
-{
-	unsigned int val, got_it = 0;
-	SCOND_FAIL_RETRY_VAR_DEF;
-
-	smp_mb();
-
-	__asm__ __volatile__(
-	"0:	mov	%[delay], 1		\n"
-	"1:	llock	%[val], [%[rwlock]]	\n"
-	"	brls	%[val], %[WR_LOCKED], 4f\n"	/* <= 0: already write locked, bail */
-	"	sub	%[val], %[val], 1	\n"	/* counter-- */
-	"	scond	%[val], [%[rwlock]]	\n"
-	"	bz.d	4f			\n"
-	"	mov.z	%[got_it], 1		\n"	/* got it */
-	"					\n"
-	SCOND_FAIL_RETRY_ASM
-
-	: [val]		"=&r"	(val),
-	  [got_it]	"+&r"	(got_it)
-	  SCOND_FAIL_RETRY_VARS
-	: [rwlock]	"r"	(&(rw->counter)),
-	  [WR_LOCKED]	"ir"	(0)
-	: "memory", "cc");
-
-	smp_mb();
-
-	return got_it;
-}
-
-static inline void arch_write_lock(arch_rwlock_t *rw)
-{
-	unsigned int val;
-	SCOND_FAIL_RETRY_VAR_DEF;
-
-	smp_mb();
-
-	/*
-	 * If reader(s) hold lock (lock < __ARCH_RW_LOCK_UNLOCKED__),
-	 * deny writer. Otherwise if unlocked grant to writer
-	 * Hence the claim that Linux rwlocks are unfair to writers.
-	 * (can be starved for an indefinite time by readers).
-	 *
-	 *	if (rw->counter == __ARCH_RW_LOCK_UNLOCKED__) {
-	 *		rw->counter = 0;
-	 *		ret = 1;
-	 *	}
-	 */
-
-	__asm__ __volatile__(
-	"0:	mov	%[delay], 1		\n"
-	"1:	llock	%[val], [%[rwlock]]	\n"
-	"	brne	%[val], %[UNLOCKED], 0b	\n"	/* while !UNLOCKED spin */
-	"	mov	%[val], %[WR_LOCKED]	\n"
-	"	scond	%[val], [%[rwlock]]	\n"
-	"	bz	4f			\n"
-	"					\n"
-	SCOND_FAIL_RETRY_ASM
-
-	: [val]		"=&r"	(val)
-	  SCOND_FAIL_RETRY_VARS
-	: [rwlock]	"r"	(&(rw->counter)),
-	  [UNLOCKED]	"ir"	(__ARCH_RW_LOCK_UNLOCKED__),
-	  [WR_LOCKED]	"ir"	(0)
-	: "memory", "cc");
-
-	smp_mb();
-}
-
-/* 1 - lock taken successfully */
-static inline int arch_write_trylock(arch_rwlock_t *rw)
-{
-	unsigned int val, got_it = 0;
-	SCOND_FAIL_RETRY_VAR_DEF;
-
-	smp_mb();
-
-	__asm__ __volatile__(
-	"0:	mov	%[delay], 1		\n"
-	"1:	llock	%[val], [%[rwlock]]	\n"
-	"	brne	%[val], %[UNLOCKED], 4f	\n"	/* !UNLOCKED, bail */
-	"	mov	%[val], %[WR_LOCKED]	\n"
-	"	scond	%[val], [%[rwlock]]	\n"
-	"	bz.d	4f			\n"
-	"	mov.z	%[got_it], 1		\n"	/* got it */
-	"					\n"
-	SCOND_FAIL_RETRY_ASM
-
-	: [val]		"=&r"	(val),
-	  [got_it]	"+&r"	(got_it)
-	  SCOND_FAIL_RETRY_VARS
-	: [rwlock]	"r"	(&(rw->counter)),
-	  [UNLOCKED]	"ir"	(__ARCH_RW_LOCK_UNLOCKED__),
-	  [WR_LOCKED]	"ir"	(0)
-	: "memory", "cc");
-
-	smp_mb();
-
-	return got_it;
-}
-
-static inline void arch_read_unlock(arch_rwlock_t *rw)
-{
-	unsigned int val;
-
-	smp_mb();
-
-	/*
-	 * rw->counter++;
-	 */
-	__asm__ __volatile__(
-	"1:	llock	%[val], [%[rwlock]]	\n"
-	"	add	%[val], %[val], 1	\n"
-	"	scond	%[val], [%[rwlock]]	\n"
-	"	bnz	1b			\n"
-	"					\n"
-	: [val]		"=&r"	(val)
-	: [rwlock]	"r"	(&(rw->counter))
-	: "memory", "cc");
-
-	smp_mb();
-}
-
-static inline void arch_write_unlock(arch_rwlock_t *rw)
-{
-	unsigned int val;
-
-	smp_mb();
-
-	/*
-	 * rw->counter = __ARCH_RW_LOCK_UNLOCKED__;
-	 */
-	__asm__ __volatile__(
-	"1:	llock	%[val], [%[rwlock]]	\n"
-	"	scond	%[UNLOCKED], [%[rwlock]]\n"
-	"	bnz	1b			\n"
-	"					\n"
-	: [val]		"=&r"	(val)
-	: [rwlock]	"r"	(&(rw->counter)),
-	  [UNLOCKED]	"r"	(__ARCH_RW_LOCK_UNLOCKED__)
-	: "memory", "cc");
-
-	smp_mb();
-}
-
-#undef SCOND_FAIL_RETRY_VAR_DEF
-#undef SCOND_FAIL_RETRY_ASM
-#undef SCOND_FAIL_RETRY_VARS
-
-#endif	/* CONFIG_ARC_STAR_9000923308 */
-
 #else	/* !CONFIG_ARC_HAS_LLSC */
 
 static inline void arch_spin_lock(arch_spinlock_t *lock)
@@ -610,7 +318,9 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
 	int ret = 0;
+	unsigned long flags;
 
+	local_irq_save(flags);
 	arch_spin_lock(&(rw->lock_mutex));
 
 	/*
@@ -623,6 +333,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 	}
 
 	arch_spin_unlock(&(rw->lock_mutex));
+	local_irq_restore(flags);
 
 	smp_mb();
 	return ret;
@@ -632,7 +343,9 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 static inline int arch_write_trylock(arch_rwlock_t *rw)
 {
 	int ret = 0;
+	unsigned long flags;
 
+	local_irq_save(flags);
 	arch_spin_lock(&(rw->lock_mutex));
 
 	/*
@@ -646,6 +359,7 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 		ret = 1;
 	}
 	arch_spin_unlock(&(rw->lock_mutex));
+	local_irq_restore(flags);
 
 	return ret;
 }
@@ -664,16 +378,24 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 
 static inline void arch_read_unlock(arch_rwlock_t *rw)
 {
+	unsigned long flags;
+
+	local_irq_save(flags);
 	arch_spin_lock(&(rw->lock_mutex));
 	rw->counter++;
 	arch_spin_unlock(&(rw->lock_mutex));
+	local_irq_restore(flags);
 }
 
 static inline void arch_write_unlock(arch_rwlock_t *rw)
 {
+	unsigned long flags;
+
+	local_irq_save(flags);
 	arch_spin_lock(&(rw->lock_mutex));
 	rw->counter = __ARCH_RW_LOCK_UNLOCKED__;
 	arch_spin_unlock(&(rw->lock_mutex));
+	local_irq_restore(flags);
 }
 
 #endif
diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h
index 3af674556..2d79e527f 100644
--- a/arch/arc/include/asm/thread_info.h
+++ b/arch/arc/include/asm/thread_info.h
@@ -103,7 +103,7 @@ static inline __attribute_const__ struct thread_info *current_thread_info(void)
 
 /*
  * _TIF_ALLWORK_MASK includes SYSCALL_TRACE, but we don't need it.
- * SYSCALL_TRACE is anways seperately/unconditionally tested right after a
+ * SYSCALL_TRACE is anyway seperately/unconditionally tested right after a
  * syscall, so all that reamins to be tested is _TIF_WORK_MASK
  */
 
diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h
index d1da6032b..a78d56708 100644
--- a/arch/arc/include/asm/uaccess.h
+++ b/arch/arc/include/asm/uaccess.h
@@ -32,7 +32,7 @@
 #define __kernel_ok		(segment_eq(get_fs(), KERNEL_DS))
 
 /*
- * Algorthmically, for __user_ok() we want do:
+ * Algorithmically, for __user_ok() we want do:
  * 	(start < TASK_SIZE) && (start+len < TASK_SIZE)
  * where TASK_SIZE could either be retrieved from thread_info->addr_limit or
  * emitted directly in code.
diff --git a/arch/arc/include/uapi/asm/byteorder.h b/arch/arc/include/uapi/asm/byteorder.h
index 9da71d415..ea5ca444c 100644
--- a/arch/arc/include/uapi/asm/byteorder.h
+++ b/arch/arc/include/uapi/asm/byteorder.h
@@ -9,7 +9,7 @@
 #ifndef __ASM_ARC_BYTEORDER_H
 #define __ASM_ARC_BYTEORDER_H
 
-#ifdef CONFIG_CPU_BIG_ENDIAN
+#ifdef __BIG_ENDIAN__
 #include <linux/byteorder/big_endian.h>
 #else
 #include <linux/byteorder/little_endian.h>
diff --git a/arch/arc/include/uapi/asm/swab.h b/arch/arc/include/uapi/asm/swab.h
index 095599a73..71f3918b0 100644
--- a/arch/arc/include/uapi/asm/swab.h
+++ b/arch/arc/include/uapi/asm/swab.h
@@ -74,7 +74,7 @@
 	__tmp ^ __in;						\
 })
 
-#elif (ARC_BSWAP_TYPE == 2)	/* Custom single cycle bwap instruction */
+#elif (ARC_BSWAP_TYPE == 2)	/* Custom single cycle bswap instruction */
 
 #define __arch_swab32(x)						\
 ({									\
diff --git a/arch/arc/include/uapi/asm/unistd.h b/arch/arc/include/uapi/asm/unistd.h
index 39e58d1cd..41fa2ec9e 100644
--- a/arch/arc/include/uapi/asm/unistd.h
+++ b/arch/arc/include/uapi/asm/unistd.h
@@ -15,6 +15,7 @@
 #if !defined(_UAPI_ASM_ARC_UNISTD_H) || defined(__SYSCALL)
 #define _UAPI_ASM_ARC_UNISTD_H
 
+#define __ARCH_WANT_RENAMEAT
 #define __ARCH_WANT_SYS_EXECVE
 #define __ARCH_WANT_SYS_CLONE
 #define __ARCH_WANT_SYS_VFORK