These changes are the raw update to linux-4.4.6-rt14. Kernel sources

are taken from kernel.org, and rt patch from the rt wiki download page.

During the rebasing, the following patch collided:

Force tick interrupt and get rid of softirq magic(I70131fb85).

Collisions have been removed because its logic was found on the
source already.

Change-Id: I7f57a4081d9deaa0d9ccfc41a6c8daccdee3b769
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>

42 files changed, 2300 insertions, 796 deletions

diff --git a/kernel/arch/arc/include/asm/Kbuild b/kernel/arch/arc/include/asm/Kbuild
index be0c39e76..0b10ef2a4 100644
--- a/kernel/arch/arc/include/asm/Kbuild
+++ b/kernel/arch/arc/include/asm/Kbuild
@@ -1,5 +1,4 @@
 generic-y += auxvec.h
-generic-y += barrier.h
 generic-y += bitsperlong.h
 generic-y += bugs.h
 generic-y += clkdev.h
@@ -23,6 +22,7 @@ generic-y += kvm_para.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += msgbuf.h
 generic-y += param.h
@@ -33,7 +33,6 @@ generic-y += poll.h
 generic-y += posix_types.h
 generic-y += preempt.h
 generic-y += resource.h
-generic-y += scatterlist.h
 generic-y += sembuf.h
 generic-y += shmbuf.h
 generic-y += siginfo.h
@@ -49,4 +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/kernel/arch/arc/include/asm/arcregs.h b/kernel/arch/arc/include/asm/arcregs.h
index e2b1b1211..7fac7d85e 100644
--- a/kernel/arch/arc/include/asm/arcregs.h
+++ b/kernel/arch/arc/include/asm/arcregs.h
@@ -16,6 +16,8 @@
 #define ARC_REG_PERIBASE_BCR	0x69
 #define ARC_REG_FP_BCR		0x6B	/* ARCompact: Single-Precision FPU */
 #define ARC_REG_DPFP_BCR	0x6C	/* ARCompact: Dbl Precision FPU */
+#define ARC_REG_FP_V2_BCR	0xc8	/* ARCv2 FPU */
+#define ARC_REG_SLC_BCR		0xce
 #define ARC_REG_DCCM_BCR	0x74	/* DCCM Present + SZ */
 #define ARC_REG_TIMERS_BCR	0x75
 #define ARC_REG_AP_BCR		0x76
@@ -31,7 +33,9 @@
 #define ARC_REG_BPU_BCR		0xc0
 #define ARC_REG_ISA_CFG_BCR	0xc1
 #define ARC_REG_RTT_BCR		0xF2
+#define ARC_REG_IRQ_BCR		0xF3
 #define ARC_REG_SMART_BCR	0xFF
+#define ARC_REG_CLUSTER_BCR	0xcf
 
 /* status32 Bits Positions */
 #define STATUS_AE_BIT		5	/* Exception active */
@@ -51,6 +55,7 @@
  * [15: 8] = Exception Cause Code
  * [ 7: 0] = Exception Parameters (for certain types only)
  */
+#ifdef CONFIG_ISA_ARCOMPACT
 #define ECR_V_MEM_ERR			0x01
 #define ECR_V_INSN_ERR			0x02
 #define ECR_V_MACH_CHK			0x20
@@ -58,6 +63,15 @@
 #define ECR_V_DTLB_MISS			0x22
 #define ECR_V_PROTV			0x23
 #define ECR_V_TRAP			0x25
+#else
+#define ECR_V_MEM_ERR			0x01
+#define ECR_V_INSN_ERR			0x02
+#define ECR_V_MACH_CHK			0x03
+#define ECR_V_ITLB_MISS			0x04
+#define ECR_V_DTLB_MISS			0x05
+#define ECR_V_PROTV			0x06
+#define ECR_V_TRAP			0x09
+#endif
 
 /* DTLB Miss and Protection Violation Cause Codes */
 
@@ -76,14 +90,10 @@
 #define ECR_C_BIT_DTLB_LD_MISS		8
 #define ECR_C_BIT_DTLB_ST_MISS		9
 
-/* Dummy ECR values for Interrupts */
-#define event_IRQ1		0x0031abcd
-#define event_IRQ2		0x0032abcd
-
 /* Auxiliary registers */
 #define AUX_IDENTITY		4
 #define AUX_INTR_VEC_BASE	0x25
-
+#define AUX_NON_VOL		0x5e
 
 /*
  * Floating Pt Registers
@@ -110,7 +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
 
@@ -204,9 +214,11 @@ struct bcr_identity {
 
 struct bcr_isa {
 #ifdef CONFIG_CPU_BIG_ENDIAN
-	unsigned int pad1:23, atomic1:1, ver:8;
+	unsigned int div_rem:4, pad2:4, ldd:1, unalign:1, atomic:1, be:1,
+		     pad1:11, atomic1:1, ver:8;
 #else
-	unsigned int ver:8, atomic1:1, pad1:23;
+	unsigned int ver:8, atomic1:1, pad1:11, be:1, atomic:1, unalign:1,
+		     ldd:1, pad2:4, div_rem:4;
 #endif
 };
 
@@ -228,9 +240,9 @@ struct bcr_extn_xymem {
 
 struct bcr_perip {
 #ifdef CONFIG_CPU_BIG_ENDIAN
-	unsigned int start:8, pad2:8, sz:8, pad:8;
+	unsigned int start:8, pad2:8, sz:8, ver:8;
 #else
-	unsigned int pad:8, sz:8, pad2:8, start:8;
+	unsigned int ver:8, sz:8, pad2:8, start:8;
 #endif
 };
 
@@ -269,11 +281,19 @@ struct bcr_fp_arcompact {
 #endif
 };
 
+struct bcr_fp_arcv2 {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad2:15, dp:1, pad1:7, sp:1, ver:8;
+#else
+	unsigned int ver:8, sp:1, pad1:7, dp:1, pad2:15;
+#endif
+};
+
 struct bcr_timer {
 #ifdef CONFIG_CPU_BIG_ENDIAN
-	unsigned int pad2:15, rtsc:1, pad1:6, t1:1, t0:1, ver:8;
+	unsigned int pad2:15, rtsc:1, pad1:5, rtc:1, t1:1, t0:1, ver:8;
 #else
-	unsigned int ver:8, t0:1, t1:1, pad1:6, rtsc:1, pad2:15;
+	unsigned int ver:8, t0:1, t1:1, rtc:1, pad1:5, rtsc:1, pad2:15;
 #endif
 };
 
@@ -285,6 +305,14 @@ struct bcr_bpu_arcompact {
 #endif
 };
 
+struct bcr_bpu_arcv2 {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad:6, fbe:2, tqe:2, ts:4, ft:1, rse:2, pte:3, bce:3, ver:8;
+#else
+	unsigned int ver:8, bce:3, pte:3, rse:2, ft:1, ts:4, tqe:2, fbe:2, pad:6;
+#endif
+};
+
 struct bcr_generic {
 #ifdef CONFIG_CPU_BIG_ENDIAN
 	unsigned int pad:24, ver:8;
@@ -299,11 +327,12 @@ struct bcr_generic {
  */
 
 struct cpuinfo_arc_mmu {
-	unsigned int ver, pg_sz, sets, ways, u_dtlb, u_itlb, num_tlb;
+	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 {
-	unsigned int sz_k:8, line_len:8, assoc:4, ver:4, alias:1, vipt:1, pad:6;
+	unsigned int sz_k:14, line_len:8, assoc:4, ver:4, alias:1, vipt:1;
 };
 
 struct cpuinfo_arc_bpu {
@@ -315,14 +344,13 @@ struct cpuinfo_arc_ccm {
 };
 
 struct cpuinfo_arc {
-	struct cpuinfo_arc_cache icache, dcache;
+	struct cpuinfo_arc_cache icache, dcache, slc;
 	struct cpuinfo_arc_mmu mmu;
 	struct cpuinfo_arc_bpu bpu;
 	struct bcr_identity core;
 	struct bcr_isa isa;
 	struct bcr_timer timers;
 	unsigned int vec_base;
-	unsigned int uncached_base;
 	struct cpuinfo_arc_ccm iccm, dccm;
 	struct {
 		unsigned int swap:1, norm:1, minmax:1, barrel:1, crc:1, pad1:3,
@@ -336,6 +364,22 @@ struct cpuinfo_arc {
 
 extern struct cpuinfo_arc cpuinfo_arc700[];
 
+static inline int is_isa_arcv2(void)
+{
+	return IS_ENABLED(CONFIG_ISA_ARCV2);
+}
+
+static inline int is_isa_arcompact(void)
+{
+	return IS_ENABLED(CONFIG_ISA_ARCOMPACT);
+}
+
+#if defined(CONFIG_ISA_ARCOMPACT) && !defined(_CPU_DEFAULT_A7)
+#error "Toolchain not configured for ARCompact builds"
+#elif defined(CONFIG_ISA_ARCV2) && !defined(_CPU_DEFAULT_HS)
+#error "Toolchain not configured for ARCv2 builds"
+#endif
+
 #endif /* __ASEMBLY__ */
 
 #endif /* _ASM_ARC_ARCREGS_H */
diff --git a/kernel/arch/arc/include/asm/atomic.h b/kernel/arch/arc/include/asm/atomic.h
index 20b7dc179..7730d302c 100644
--- a/kernel/arch/arc/include/asm/atomic.h
+++ b/kernel/arch/arc/include/asm/atomic.h
@@ -17,31 +17,66 @@
 #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
+
+#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 temp;						\
+	unsigned int val;				                \
+	SCOND_FAIL_RETRY_VAR_DEF                                        \
 									\
 	__asm__ __volatile__(						\
-	"1:	llock   %0, [%1]	\n"				\
-	"	" #asm_op " %0, %0, %2	\n"				\
-	"	scond   %0, [%1]	\n"				\
-	"	bnz     1b		\n"				\
-	: "=&r"(temp)	/* Early clobber, to prevent reg reuse */	\
-	: "r"(&v->counter), "ir"(i)					\
+	"1:	llock   %[val], [%[ctr]]		\n"		\
+	"	" #asm_op " %[val], %[val], %[i]	\n"		\
+	"	scond   %[val], [%[ctr]]		\n"		\
+	"						\n"		\
+	SCOND_FAIL_RETRY_ASM						\
+									\
+	: [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");							\
 }									\
 
 #define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
 static inline int atomic_##op##_return(int i, atomic_t *v)		\
 {									\
-	unsigned int temp;						\
+	unsigned int val;				                \
+	SCOND_FAIL_RETRY_VAR_DEF                                        \
 									\
 	/*								\
 	 * Explicit full memory barrier needed before/after as		\
@@ -50,17 +85,21 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	smp_mb();							\
 									\
 	__asm__ __volatile__(						\
-	"1:	llock   %0, [%1]	\n"				\
-	"	" #asm_op " %0, %0, %2	\n"				\
-	"	scond   %0, [%1]	\n"				\
-	"	bnz     1b		\n"				\
-	: "=&r"(temp)							\
-	: "r"(&v->counter), "ir"(i)					\
+	"1:	llock   %[val], [%[ctr]]		\n"		\
+	"	" #asm_op " %[val], %[val], %[i]	\n"		\
+	"	scond   %[val], [%[ctr]]		\n"		\
+	"						\n"		\
+	SCOND_FAIL_RETRY_ASM						\
+									\
+	: [val]	"=&r"	(val)						\
+	  SCOND_FAIL_RETRY_VARS						\
+	: [ctr]	"r"	(&v->counter),					\
+	  [i]	"ir"	(i)						\
 	: "cc");							\
 									\
 	smp_mb();							\
 									\
-	return temp;							\
+	return val;							\
 }
 
 #else	/* !CONFIG_ARC_HAS_LLSC */
@@ -68,7 +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
 
@@ -86,7 +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);
 }
 
@@ -133,13 +172,20 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 
 ATOMIC_OPS(add, +=, add)
 ATOMIC_OPS(sub, -=, sub)
-ATOMIC_OP(and, &=, and)
 
-#define atomic_clear_mask(mask, v) atomic_and(~(mask), (v))
+#define atomic_andnot atomic_andnot
+
+ATOMIC_OP(and, &=, and)
+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
 
 /**
  * __atomic_add_unless - add unless the number is a given value
diff --git a/kernel/arch/arc/include/asm/barrier.h b/kernel/arch/arc/include/asm/barrier.h
new file mode 100644
index 000000000..a7209983e
--- /dev/null
+++ b/kernel/arch/arc/include/asm/barrier.h
@@ -0,0 +1,48 @@
+/*
+ * Copyright (C) 2014-15 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_BARRIER_H
+#define __ASM_BARRIER_H
+
+#ifdef CONFIG_ISA_ARCV2
+
+/*
+ * ARCv2 based HS38 cores are in-order issue, but still weakly ordered
+ * due to micro-arch buffering/queuing of load/store, cache hit vs. miss ...
+ *
+ * Explicit barrier provided by DMB instruction
+ *  - Operand supports fine grained load/store/load+store semantics
+ *  - Ensures that selected memory operation issued before it will complete
+ *    before any subsequent memory operation of same type
+ *  - DMB guarantees SMP as well as local barrier semantics
+ *    (asm-generic/barrier.h ensures sane smp_*mb if not defined here, i.e.
+ *    UP: barrier(), SMP: smp_*mb == *mb)
+ *  - DSYNC provides DMB+completion_of_cache_bpu_maintenance_ops hence not needed
+ *    in the general case. Plus it only provides full barrier.
+ */
+
+#define mb()	asm volatile("dmb 3\n" : : : "memory")
+#define rmb()	asm volatile("dmb 1\n" : : : "memory")
+#define wmb()	asm volatile("dmb 2\n" : : : "memory")
+
+#endif
+
+#ifdef CONFIG_ISA_ARCOMPACT
+
+/*
+ * ARCompact based cores (ARC700) only have SYNC instruction which is super
+ * heavy weight as it flushes the pipeline as well.
+ * There are no real SMP implementations of such cores.
+ */
+
+#define mb()	asm volatile("sync\n" : : : "memory")
+#endif
+
+#include <asm-generic/barrier.h>
+
+#endif
diff --git a/kernel/arch/arc/include/asm/bitops.h b/kernel/arch/arc/include/asm/bitops.h
index dae03e66f..57c1f3384 100644
--- a/kernel/arch/arc/include/asm/bitops.h
+++ b/kernel/arch/arc/include/asm/bitops.h
@@ -215,6 +215,8 @@ test_bit(unsigned int nr, const volatile unsigned long *addr)
 	return ((mask & *addr) != 0);
 }
 
+#ifdef CONFIG_ISA_ARCOMPACT
+
 /*
  * Count the number of zeros, starting from MSB
  * Helper for fls( ) friends
@@ -307,6 +309,75 @@ static inline __attribute__ ((const)) int __ffs(unsigned long word)
 	return ffs(word) - 1;
 }
 
+#else	/* CONFIG_ISA_ARCV2 */
+
+/*
+ * fls = Find Last Set in word
+ * @result: [1-32]
+ * fls(1) = 1, fls(0x80000000) = 32, fls(0) = 0
+ */
+static inline __attribute__ ((const)) int fls(unsigned long x)
+{
+	int n;
+
+	asm volatile(
+	"	fls.f	%0, %1		\n"  /* 0:31; 0(Z) if src 0 */
+	"	add.nz	%0, %0, 1	\n"  /* 0:31 -> 1:32 */
+	: "=r"(n)	/* Early clobber not needed */
+	: "r"(x)
+	: "cc");
+
+	return n;
+}
+
+/*
+ * __fls: Similar to fls, but zero based (0-31). Also 0 if no bit set
+ */
+static inline __attribute__ ((const)) int __fls(unsigned long x)
+{
+	/* FLS insn has exactly same semantics as the API */
+	return	__builtin_arc_fls(x);
+}
+
+/*
+ * ffs = Find First Set in word (LSB to MSB)
+ * @result: [1-32], 0 if all 0's
+ */
+static inline __attribute__ ((const)) int ffs(unsigned long x)
+{
+	int n;
+
+	asm volatile(
+	"	ffs.f	%0, %1		\n"  /* 0:31; 31(Z) if src 0 */
+	"	add.nz	%0, %0, 1	\n"  /* 0:31 -> 1:32 */
+	"	mov.z	%0, 0		\n"  /* 31(Z)-> 0 */
+	: "=r"(n)	/* Early clobber not needed */
+	: "r"(x)
+	: "cc");
+
+	return n;
+}
+
+/*
+ * __ffs: Similar to ffs, but zero based (0-31)
+ */
+static inline __attribute__ ((const)) int __ffs(unsigned long x)
+{
+	int n;
+
+	asm volatile(
+	"	ffs.f	%0, %1		\n"  /* 0:31; 31(Z) if src 0 */
+	"	mov.z	%0, 0		\n"  /* 31(Z)-> 0 */
+	: "=r"(n)
+	: "r"(x)
+	: "cc");
+
+	return n;
+
+}
+
+#endif	/* CONFIG_ISA_ARCOMPACT */
+
 /*
  * ffz = Find First Zero in word.
  * @return:[0-31], 32 if all 1's
diff --git a/kernel/arch/arc/include/asm/cache.h b/kernel/arch/arc/include/asm/cache.h
index 7861255da..210ef3e72 100644
--- a/kernel/arch/arc/include/asm/cache.h
+++ b/kernel/arch/arc/include/asm/cache.h
@@ -53,6 +53,8 @@ extern void arc_cache_init(void);
 extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len);
 extern void read_decode_cache_bcr(void);
 
+extern int ioc_exists;
+
 #endif	/* !__ASSEMBLY__ */
 
 /* Instruction cache related Auxiliary registers */
@@ -60,9 +62,8 @@ extern void read_decode_cache_bcr(void);
 #define ARC_REG_IC_IVIC		0x10
 #define ARC_REG_IC_CTRL		0x11
 #define ARC_REG_IC_IVIL		0x19
-#if defined(CONFIG_ARC_MMU_V3)
 #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
@@ -74,12 +75,31 @@ extern void read_decode_cache_bcr(void);
 #define ARC_REG_DC_IVDL		0x4A
 #define ARC_REG_DC_FLSH		0x4B
 #define ARC_REG_DC_FLDL		0x4C
-#if defined(CONFIG_ARC_MMU_V3)
 #define ARC_REG_DC_PTAG		0x5C
-#endif
+#define ARC_REG_DC_PTAG_HI	0x5F
 
 /* Bit val in DC_CTRL */
 #define DC_CTRL_INV_MODE_FLUSH  0x40
 #define DC_CTRL_FLUSH_STATUS    0x100
 
+/*System-level cache (L2 cache) related Auxiliary registers */
+#define ARC_REG_SLC_CFG		0x901
+#define ARC_REG_SLC_CTRL	0x903
+#define ARC_REG_SLC_FLUSH	0x904
+#define ARC_REG_SLC_INVALIDATE	0x905
+#define ARC_REG_SLC_RGN_START	0x914
+#define ARC_REG_SLC_RGN_END	0x916
+
+/* Bit val in SLC_CONTROL */
+#define SLC_CTRL_IM		0x040
+#define SLC_CTRL_DISABLE	0x001
+#define SLC_CTRL_BUSY		0x100
+#define SLC_CTRL_RGN_OP_INV	0x200
+
+/* IO coherency related Auxiliary registers */
+#define ARC_REG_IO_COH_ENABLE	0x500
+#define ARC_REG_IO_COH_PARTIAL	0x501
+#define ARC_REG_IO_COH_AP0_BASE	0x508
+#define ARC_REG_IO_COH_AP0_SIZE	0x509
+
 #endif /* _ASM_CACHE_H */
diff --git a/kernel/arch/arc/include/asm/cacheflush.h b/kernel/arch/arc/include/asm/cacheflush.h
index 6abc4972b..fbe3587c4 100644
--- a/kernel/arch/arc/include/asm/cacheflush.h
+++ b/kernel/arch/arc/include/asm/cacheflush.h
@@ -31,12 +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);
-#define __flush_dcache_page(p, v)	\
-		___flush_dcache_page((unsigned long)p, (unsigned long)v)
+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/kernel/arch/arc/include/asm/cmpxchg.h b/kernel/arch/arc/include/asm/cmpxchg.h
index 44fd531f4..af7a2db13 100644
--- a/kernel/arch/arc/include/asm/cmpxchg.h
+++ b/kernel/arch/arc/include/asm/cmpxchg.h
@@ -110,18 +110,18 @@ static inline unsigned long __xchg(unsigned long val, volatile void *ptr,
 						 sizeof(*(ptr))))
 
 /*
- * On ARC700, EX insn is inherently atomic, so by default "vanilla" xchg() need
- * not require any locking. However there's a quirk.
- * ARC lacks native CMPXCHG, thus emulated (see above), using external locking -
- * incidently it "reuses" the same atomic_ops_lock used by atomic APIs.
- * Now, llist code uses cmpxchg() and xchg() on same data, so xchg() needs to
- * abide by same serializing rules, thus ends up using atomic_ops_lock as well.
+ * xchg() maps directly to ARC EX instruction which guarantees atomicity.
+ * However in !LLSC config, it also needs to be use @atomic_ops_lock spinlock
+ * due to a subtle reason:
+ *  - For !LLSC, cmpxchg() needs to use that lock (see above) and there is lot
+ *    of  kernel code which calls xchg()/cmpxchg() on same data (see llist.h)
+ *    Hence xchg() needs to follow same locking rules.
  *
- * This however is only relevant if SMP and/or ARC lacks LLSC
- *   if (UP or LLSC)
- *      xchg doesn't need serialization
- *   else <==> !(UP or LLSC) <==> (!UP and !LLSC) <==> (SMP and !LLSC)
- *      xchg needs serialization
+ * Technically the lock is also needed for UP (boils down to irq save/restore)
+ * but we can cheat a bit since cmpxchg() atomic_ops_lock() would cause irqs to
+ * be disabled thus can't possibly be interrpted/preempted/clobbered by xchg()
+ * Other way around, xchg is one instruction anyways, so can't be interrupted
+ * as such
  */
 
 #if !defined(CONFIG_ARC_HAS_LLSC) && defined(CONFIG_SMP)
diff --git a/kernel/arch/arc/include/asm/delay.h b/kernel/arch/arc/include/asm/delay.h
index 43de30256..08e7e2a16 100644
--- a/kernel/arch/arc/include/asm/delay.h
+++ b/kernel/arch/arc/include/asm/delay.h
@@ -22,11 +22,10 @@
 static inline void __delay(unsigned long loops)
 {
 	__asm__ __volatile__(
-	"1:	sub.f %0, %0, 1	\n"
-	"	jpnz 1b		\n"
-	: "+r"(loops)
-	:
-	: "cc");
+	"	lp  1f	\n"
+	"	nop	\n"
+	"1:		\n"
+	: "+l"(loops));
 }
 
 extern void __bad_udelay(void);
diff --git a/kernel/arch/arc/include/asm/dma-mapping.h b/kernel/arch/arc/include/asm/dma-mapping.h
index 45b8e0cea..2d28ba939 100644
--- a/kernel/arch/arc/include/asm/dma-mapping.h
+++ b/kernel/arch/arc/include/asm/dma-mapping.h
@@ -14,23 +14,6 @@
 #include <asm-generic/dma-coherent.h>
 #include <asm/cacheflush.h>
 
-#ifndef CONFIG_ARC_PLAT_NEEDS_CPU_TO_DMA
-/*
- * dma_map_* API take cpu addresses, which is kernel logical address in the
- * untranslated address space (0x8000_0000) based. The dma address (bus addr)
- * ideally needs to be 0x0000_0000 based hence these glue routines.
- * However given that intermediate bus bridges can ignore the high bit, we can
- * do with these routines being no-ops.
- * If a platform/device comes up which sriclty requires 0 based bus addr
- * (e.g. AHB-PCI bridge on Angel4 board), then it can provide it's own versions
- */
-#define plat_dma_addr_to_kernel(dev, addr) ((unsigned long)(addr))
-#define plat_kernel_addr_to_dma(dev, ptr) ((dma_addr_t)(ptr))
-
-#else
-#include <plat/dma_addr.h>
-#endif
-
 void *dma_alloc_noncoherent(struct device *dev, size_t size,
 			    dma_addr_t *dma_handle, gfp_t gfp);
 
@@ -94,7 +77,7 @@ dma_map_single(struct device *dev, void *cpu_addr, size_t size,
 	       enum dma_data_direction dir)
 {
 	_dma_cache_sync((unsigned long)cpu_addr, size, dir);
-	return plat_kernel_addr_to_dma(dev, cpu_addr);
+	return (dma_addr_t)cpu_addr;
 }
 
 static inline void
@@ -147,16 +130,14 @@ static inline void
 dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
 			size_t size, enum dma_data_direction dir)
 {
-	_dma_cache_sync(plat_dma_addr_to_kernel(dev, dma_handle), size,
-			DMA_FROM_DEVICE);
+	_dma_cache_sync(dma_handle, size, DMA_FROM_DEVICE);
 }
 
 static inline void
 dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle,
 			   size_t size, enum dma_data_direction dir)
 {
-	_dma_cache_sync(plat_dma_addr_to_kernel(dev, dma_handle), size,
-			DMA_TO_DEVICE);
+	_dma_cache_sync(dma_handle, size, DMA_TO_DEVICE);
 }
 
 static inline void
@@ -164,8 +145,7 @@ dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t dma_handle,
 			      unsigned long offset, size_t size,
 			      enum dma_data_direction direction)
 {
-	_dma_cache_sync(plat_dma_addr_to_kernel(dev, dma_handle) + offset,
-			size, DMA_FROM_DEVICE);
+	_dma_cache_sync(dma_handle + offset, size, DMA_FROM_DEVICE);
 }
 
 static inline void
@@ -173,27 +153,28 @@ dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle,
 				 unsigned long offset, size_t size,
 				 enum dma_data_direction direction)
 {
-	_dma_cache_sync(plat_dma_addr_to_kernel(dev, dma_handle) + offset,
-			size, DMA_TO_DEVICE);
+	_dma_cache_sync(dma_handle + offset, size, DMA_TO_DEVICE);
 }
 
 static inline void
-dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems,
+dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sglist, int nelems,
 		    enum dma_data_direction dir)
 {
 	int i;
+	struct scatterlist *sg;
 
-	for (i = 0; i < nelems; i++, sg++)
+	for_each_sg(sglist, sg, nelems, i)
 		_dma_cache_sync((unsigned int)sg_virt(sg), sg->length, dir);
 }
 
 static inline void
-dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems,
-		       enum dma_data_direction dir)
+dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist,
+		       int nelems, enum dma_data_direction dir)
 {
 	int i;
+	struct scatterlist *sg;
 
-	for (i = 0; i < nelems; i++, sg++)
+	for_each_sg(sglist, sg, nelems, i)
 		_dma_cache_sync((unsigned int)sg_virt(sg), sg->length, dir);
 }
 
diff --git a/kernel/arch/arc/include/asm/elf.h b/kernel/arch/arc/include/asm/elf.h
index a26282857..51a99e25f 100644
--- a/kernel/arch/arc/include/asm/elf.h
+++ b/kernel/arch/arc/include/asm/elf.h
@@ -15,6 +15,11 @@
 /* These ELF defines belong to uapi but libc elf.h already defines them */
 #define EM_ARCOMPACT		93
 
+#define EM_ARCV2		195	/* ARCv2 Cores */
+
+#define EM_ARC_INUSE		(IS_ENABLED(CONFIG_ISA_ARCOMPACT) ? \
+					EM_ARCOMPACT : EM_ARCV2)
+
 /* ARC Relocations (kernel Modules only) */
 #define  R_ARC_32		0x4
 #define  R_ARC_32_ME		0x1B
diff --git a/kernel/arch/arc/include/asm/entry-arcv2.h b/kernel/arch/arc/include/asm/entry-arcv2.h
new file mode 100644
index 000000000..b5ff87e6f
--- /dev/null
+++ b/kernel/arch/arc/include/asm/entry-arcv2.h
@@ -0,0 +1,190 @@
+
+#ifndef __ASM_ARC_ENTRY_ARCV2_H
+#define __ASM_ARC_ENTRY_ARCV2_H
+
+#include <asm/asm-offsets.h>
+#include <asm/irqflags-arcv2.h>
+#include <asm/thread_info.h>	/* For THREAD_SIZE */
+
+/*------------------------------------------------------------------------*/
+.macro INTERRUPT_PROLOGUE	called_from
+
+	; Before jumping to Interrupt Vector, hardware micro-ops did following:
+	;   1. SP auto-switched to kernel mode stack
+	;   2. STATUS32.Z flag set to U mode at time of interrupt (U:1, K:0)
+	;   3. Auto saved: r0-r11, blink, LPE,LPS,LPC, JLI,LDI,EI, PC, STAT32
+	;
+	; Now manually save: r12, sp, fp, gp, r25
+
+	PUSH	r12
+
+	; Saving pt_regs->sp correctly requires some extra work due to the way
+	; Auto stack switch works
+	;  - U mode: retrieve it from AUX_USER_SP
+	;  - K mode: add the offset from current SP where H/w starts auto push
+	;
+	; Utilize the fact that Z bit is set if Intr taken in U mode
+	mov.nz	r9, sp
+	add.nz	r9, r9, SZ_PT_REGS - PT_sp - 4
+	bnz	1f
+
+	lr	r9, [AUX_USER_SP]
+1:
+	PUSH	r9	; SP
+
+	PUSH	fp
+	PUSH	gp
+
+#ifdef CONFIG_ARC_CURR_IN_REG
+	PUSH	r25			; user_r25
+	GET_CURR_TASK_ON_CPU	r25
+#else
+	sub	sp, sp, 4
+#endif
+
+.ifnc \called_from, exception
+	sub	sp, sp, 12	; BTA/ECR/orig_r0 placeholder per pt_regs
+.endif
+
+.endm
+
+/*------------------------------------------------------------------------*/
+.macro INTERRUPT_EPILOGUE	called_from
+
+.ifnc \called_from, exception
+	add	sp, sp, 12	; skip BTA/ECR/orig_r0 placeholderss
+.endif
+
+#ifdef CONFIG_ARC_CURR_IN_REG
+	POP	r25
+#else
+	add	sp, sp, 4
+#endif
+
+	POP	gp
+	POP	fp
+
+	; Don't touch AUX_USER_SP if returning to K mode (Z bit set)
+	; (Z bit set on K mode is inverse of INTERRUPT_PROLOGUE)
+	add.z	sp, sp, 4
+	bz	1f
+
+	POPAX	AUX_USER_SP
+1:
+	POP	r12
+
+.endm
+
+/*------------------------------------------------------------------------*/
+.macro EXCEPTION_PROLOGUE
+
+	; Before jumping to Exception Vector, hardware micro-ops did following:
+	;   1. SP auto-switched to kernel mode stack
+	;   2. STATUS32.Z flag set to U mode at time of interrupt (U:1,K:0)
+	;
+	; Now manually save the complete reg file
+
+	PUSH	r9		; freeup a register: slot of erstatus
+
+	PUSHAX	eret
+	sub	sp, sp, 12	; skip JLI, LDI, EI
+	PUSH	lp_count
+	PUSHAX	lp_start
+	PUSHAX	lp_end
+	PUSH	blink
+
+	PUSH	r11
+	PUSH	r10
+
+	ld.as	r9,  [sp, 10]	; load stashed r9 (status32 stack slot)
+	lr	r10, [erstatus]
+	st.as	r10, [sp, 10]	; save status32 at it's right stack slot
+
+	PUSH	r9
+	PUSH	r8
+	PUSH	r7
+	PUSH	r6
+	PUSH	r5
+	PUSH	r4
+	PUSH	r3
+	PUSH	r2
+	PUSH	r1
+	PUSH	r0
+
+	; -- for interrupts, regs above are auto-saved by h/w in that order --
+	; Now do what ISR prologue does (manually save r12, sp, fp, gp, r25)
+	;
+	; Set Z flag if this was from U mode (expected by INTERRUPT_PROLOGUE)
+	; Although H/w exception micro-ops do set Z flag for U mode (just like
+	; for interrupts), it could get clobbered in case we soft land here from
+	; a TLB Miss exception handler (tlbex.S)
+
+	and	r10, r10, STATUS_U_MASK
+	xor.f	0, r10, STATUS_U_MASK
+
+	INTERRUPT_PROLOGUE  exception
+
+	PUSHAX	erbta
+	PUSHAX	ecr		; r9 contains ECR, expected by EV_Trap
+
+	PUSH	r0		; orig_r0
+.endm
+
+/*------------------------------------------------------------------------*/
+.macro EXCEPTION_EPILOGUE
+
+	; Assumes r0 has PT_status32
+	btst   r0, STATUS_U_BIT	; Z flag set if K, used in INTERRUPT_EPILOGUE
+
+	add	sp, sp, 8	; orig_r0/ECR don't need restoring
+	POPAX	erbta
+
+	INTERRUPT_EPILOGUE  exception
+
+	POP	r0
+	POP	r1
+	POP	r2
+	POP	r3
+	POP	r4
+	POP	r5
+	POP	r6
+	POP	r7
+	POP	r8
+	POP	r9
+	POP	r10
+	POP	r11
+
+	POP	blink
+	POPAX	lp_end
+	POPAX	lp_start
+
+	POP	r9
+	mov	lp_count, r9
+
+	add	sp, sp, 12	; skip JLI, LDI, EI
+	POPAX	eret
+	POPAX	erstatus
+
+	ld.as	r9, [sp, -12]	; reload r9 which got clobbered
+.endm
+
+.macro FAKE_RET_FROM_EXCPN
+	lr      r9, [status32]
+	bic     r9, r9, (STATUS_U_MASK|STATUS_DE_MASK|STATUS_AE_MASK)
+	or      r9, r9, (STATUS_L_MASK|STATUS_IE_MASK)
+	kflag   r9
+.endm
+
+/* Get thread_info of "current" tsk */
+.macro GET_CURR_THR_INFO_FROM_SP  reg
+	bmskn \reg, sp, THREAD_SHIFT - 1
+.endm
+
+/* Get CPU-ID of this core */
+.macro  GET_CPU_ID  reg
+	lr  \reg, [identity]
+	xbfu \reg, \reg, 0xE8	/* 00111    01000 */
+				/* M = 8-1  N = 8 */
+.endm
+
+#endif
diff --git a/kernel/arch/arc/include/asm/entry-compact.h b/kernel/arch/arc/include/asm/entry-compact.h
new file mode 100644
index 000000000..1aff3be91
--- /dev/null
+++ b/kernel/arch/arc/include/asm/entry-compact.h
@@ -0,0 +1,306 @@
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ * Copyright (C) 2004, 2007-2010, 2011-2012 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.
+ *
+ * Vineetg: March 2009 (Supporting 2 levels of Interrupts)
+ *  Stack switching code can no longer reliably rely on the fact that
+ *  if we are NOT in user mode, stack is switched to kernel mode.
+ *  e.g. L2 IRQ interrupted a L1 ISR which had not yet completed
+ *  it's prologue including stack switching from user mode
+ *
+ * Vineetg: Aug 28th 2008: Bug #94984
+ *  -Zero Overhead Loop Context shd be cleared when entering IRQ/EXcp/Trap
+ *   Normally CPU does this automatically, however when doing FAKE rtie,
+ *   we also need to explicitly do this. The problem in macros
+ *   FAKE_RET_FROM_EXCPN and FAKE_RET_FROM_EXCPN_LOCK_IRQ was that this bit
+ *   was being "CLEARED" rather then "SET". Actually "SET" clears ZOL context
+ *
+ * Vineetg: May 5th 2008
+ *  -Modified CALLEE_REG save/restore macros to handle the fact that
+ *      r25 contains the kernel current task ptr
+ *  - Defined Stack Switching Macro to be reused in all intr/excp hdlrs
+ *  - Shaved off 11 instructions from RESTORE_ALL_INT1 by using the
+ *      address Write back load ld.ab instead of seperate ld/add instn
+ *
+ * Amit Bhor, Sameer Dhavale: Codito Technologies 2004
+ */
+
+#ifndef __ASM_ARC_ENTRY_COMPACT_H
+#define __ASM_ARC_ENTRY_COMPACT_H
+
+#include <asm/asm-offsets.h>
+#include <asm/irqflags-compact.h>
+#include <asm/thread_info.h>	/* For THREAD_SIZE */
+
+/*--------------------------------------------------------------
+ * Switch to Kernel Mode stack if SP points to User Mode stack
+ *
+ * Entry   : r9 contains pre-IRQ/exception/trap status32
+ * Exit    : SP set to K mode stack
+ *           SP at the time of entry (K/U) saved @ pt_regs->sp
+ * Clobbers: r9
+ *-------------------------------------------------------------*/
+
+.macro SWITCH_TO_KERNEL_STK
+
+	/* User Mode when this happened ? Yes: Proceed to switch stack */
+	bbit1   r9, STATUS_U_BIT, 88f
+
+	/* OK we were already in kernel mode when this event happened, thus can
+	 * assume SP is kernel mode SP. _NO_ need to do any stack switching
+	 */
+
+#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
+	/* However....
+	 * If Level 2 Interrupts enabled, we may end up with a corner case:
+	 * 1. User Task executing
+	 * 2. L1 IRQ taken, ISR starts (CPU auto-switched to KERNEL mode)
+	 * 3. But before it could switch SP from USER to KERNEL stack
+	 *      a L2 IRQ "Interrupts" L1
+	 * Thay way although L2 IRQ happened in Kernel mode, stack is still
+	 * not switched.
+	 * To handle this, we may need to switch stack even if in kernel mode
+	 * provided SP has values in range of USER mode stack ( < 0x7000_0000 )
+	 */
+	brlo sp, VMALLOC_START, 88f
+
+	/* TODO: vineetg:
+	 * 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
+	 * 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
+	 */
+
+#endif
+
+    /*------Intr/Ecxp happened in kernel mode, SP already setup ------ */
+	/* save it nevertheless @ pt_regs->sp for uniformity */
+
+	b.d	66f
+	st	sp, [sp, PT_sp - SZ_PT_REGS]
+
+88: /*------Intr/Ecxp happened in user mode, "switch" stack ------ */
+
+	GET_CURR_TASK_ON_CPU   r9
+
+	/* With current tsk in r9, get it's kernel mode stack base */
+	GET_TSK_STACK_BASE  r9, r9
+
+	/* save U mode SP @ pt_regs->sp */
+	st	sp, [r9, PT_sp - SZ_PT_REGS]
+
+	/* final SP switch */
+	mov	sp, r9
+66:
+.endm
+
+/*------------------------------------------------------------
+ * "FAKE" a rtie to return from CPU Exception context
+ * This is to re-enable Exceptions within exception
+ * Look at EV_ProtV to see how this is actually used
+ *-------------------------------------------------------------*/
+
+.macro FAKE_RET_FROM_EXCPN
+
+	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
+
+/*--------------------------------------------------------------
+ * For early Exception/ISR Prologue, a core reg is temporarily needed to
+ * code the rest of prolog (stack switching). This is done by stashing
+ * it to memory (non-SMP case) or SCRATCH0 Aux Reg (SMP).
+ *
+ * Before saving the full regfile - this reg is restored back, only
+ * to be saved again on kernel mode stack, as part of pt_regs.
+ *-------------------------------------------------------------*/
+.macro PROLOG_FREEUP_REG	reg, mem
+#ifdef CONFIG_SMP
+	sr  \reg, [ARC_REG_SCRATCH_DATA0]
+#else
+	st  \reg, [\mem]
+#endif
+.endm
+
+.macro PROLOG_RESTORE_REG	reg, mem
+#ifdef CONFIG_SMP
+	lr  \reg, [ARC_REG_SCRATCH_DATA0]
+#else
+	ld  \reg, [\mem]
+#endif
+.endm
+
+/*--------------------------------------------------------------
+ * Exception Entry prologue
+ * -Switches stack to K mode (if not already)
+ * -Saves the register file
+ *
+ * After this it is safe to call the "C" handlers
+ *-------------------------------------------------------------*/
+.macro EXCEPTION_PROLOGUE
+
+	/* Need at least 1 reg to code the early exception prologue */
+	PROLOG_FREEUP_REG r9, @ex_saved_reg1
+
+	/* U/K mode at time of exception (stack not switched if already K) */
+	lr  r9, [erstatus]
+
+	/* ARC700 doesn't provide auto-stack switching */
+	SWITCH_TO_KERNEL_STK
+
+#ifdef CONFIG_ARC_CURR_IN_REG
+	/* Treat r25 as scratch reg (save on stack) and load with "current" */
+	PUSH    r25
+	GET_CURR_TASK_ON_CPU   r25
+#else
+	sub     sp, sp, 4
+#endif
+
+	st.a	r0, [sp, -8]    /* orig_r0 needed for syscall (skip ECR slot) */
+	sub	sp, sp, 4	/* skip pt_regs->sp, already saved above */
+
+	/* Restore r9 used to code the early prologue */
+	PROLOG_RESTORE_REG  r9, @ex_saved_reg1
+
+	/* now we are ready to save the regfile */
+	SAVE_R0_TO_R12
+	PUSH	gp
+	PUSH	fp
+	PUSH	blink
+	PUSHAX	eret
+	PUSHAX	erstatus
+	PUSH	lp_count
+	PUSHAX	lp_end
+	PUSHAX	lp_start
+	PUSHAX	erbta
+
+	lr	r9, [ecr]
+	st      r9, [sp, PT_event]    /* EV_Trap expects r9 to have ECR */
+.endm
+
+/*--------------------------------------------------------------
+ * Restore all registers used by system call or Exceptions
+ * SP should always be pointing to the next free stack element
+ * when entering this macro.
+ *
+ * NOTE:
+ *
+ * It is recommended that lp_count/ilink1/ilink2 not be used as a dest reg
+ * for memory load operations. If used in that way interrupts are deffered
+ * by hardware and that is not good.
+ *-------------------------------------------------------------*/
+.macro EXCEPTION_EPILOGUE
+	POPAX	erbta
+	POPAX	lp_start
+	POPAX	lp_end
+
+	POP	r9
+	mov	lp_count, r9	;LD to lp_count is not allowed
+
+	POPAX	erstatus
+	POPAX	eret
+	POP	blink
+	POP	fp
+	POP	gp
+	RESTORE_R12_TO_R0
+
+	ld  sp, [sp] /* restore original sp */
+	/* orig_r0, ECR, user_r25 skipped automatically */
+.endm
+
+/* Dummy ECR values for Interrupts */
+#define event_IRQ1		0x0031abcd
+#define event_IRQ2		0x0032abcd
+
+.macro INTERRUPT_PROLOGUE  LVL
+
+	/* free up r9 as scratchpad */
+	PROLOG_FREEUP_REG r9, @int\LVL\()_saved_reg
+
+	/* Which mode (user/kernel) was the system in when intr occured */
+	lr  r9, [status32_l\LVL\()]
+
+	SWITCH_TO_KERNEL_STK
+
+#ifdef CONFIG_ARC_CURR_IN_REG
+	/* Treat r25 as scratch reg (save on stack) and load with "current" */
+	PUSH    r25
+	GET_CURR_TASK_ON_CPU   r25
+#else
+	sub     sp, sp, 4
+#endif
+
+	PUSH	0x003\LVL\()abcd    /* Dummy ECR */
+	sub	sp, sp, 8	    /* skip orig_r0 (not needed)
+				       skip pt_regs->sp, already saved above */
+
+	/* Restore r9 used to code the early prologue */
+	PROLOG_RESTORE_REG  r9, @int\LVL\()_saved_reg
+
+	SAVE_R0_TO_R12
+	PUSH	gp
+	PUSH	fp
+	PUSH	blink
+	PUSH	ilink\LVL\()
+	PUSHAX	status32_l\LVL\()
+	PUSH	lp_count
+	PUSHAX	lp_end
+	PUSHAX	lp_start
+	PUSHAX	bta_l\LVL\()
+.endm
+
+/*--------------------------------------------------------------
+ * Restore all registers used by interrupt handlers.
+ *
+ * NOTE:
+ *
+ * It is recommended that lp_count/ilink1/ilink2 not be used as a dest reg
+ * for memory load operations. If used in that way interrupts are deffered
+ * by hardware and that is not good.
+ *-------------------------------------------------------------*/
+.macro INTERRUPT_EPILOGUE  LVL
+	POPAX	bta_l\LVL\()
+	POPAX	lp_start
+	POPAX	lp_end
+
+	POP	r9
+	mov	lp_count, r9	;LD to lp_count is not allowed
+
+	POPAX	status32_l\LVL\()
+	POP	ilink\LVL\()
+	POP	blink
+	POP	fp
+	POP	gp
+	RESTORE_R12_TO_R0
+
+	ld  sp, [sp] /* restore original sp */
+	/* orig_r0, ECR, user_r25 skipped automatically */
+.endm
+
+/* Get thread_info of "current" tsk */
+.macro GET_CURR_THR_INFO_FROM_SP  reg
+	bic \reg, sp, (THREAD_SIZE - 1)
+.endm
+
+/* Get CPU-ID of this core */
+.macro  GET_CPU_ID  reg
+	lr  \reg, [identity]
+	lsr \reg, \reg, 8
+	bmsk \reg, \reg, 7
+.endm
+
+#endif  /* __ASM_ARC_ENTRY_COMPACT_H */
diff --git a/kernel/arch/arc/include/asm/entry.h b/kernel/arch/arc/include/asm/entry.h
index 884081099..ad7860c5c 100644
--- a/kernel/arch/arc/include/asm/entry.h
+++ b/kernel/arch/arc/include/asm/entry.h
@@ -1,45 +1,27 @@
 /*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
  * Copyright (C) 2004, 2007-2010, 2011-2012 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.
- *
- * Vineetg: March 2009 (Supporting 2 levels of Interrupts)
- *  Stack switching code can no longer reliably rely on the fact that
- *  if we are NOT in user mode, stack is switched to kernel mode.
- *  e.g. L2 IRQ interrupted a L1 ISR which had not yet completed
- *  it's prologue including stack switching from user mode
- *
- * Vineetg: Aug 28th 2008: Bug #94984
- *  -Zero Overhead Loop Context shd be cleared when entering IRQ/EXcp/Trap
- *   Normally CPU does this automatically, however when doing FAKE rtie,
- *   we also need to explicitly do this. The problem in macros
- *   FAKE_RET_FROM_EXCPN and FAKE_RET_FROM_EXCPN_LOCK_IRQ was that this bit
- *   was being "CLEARED" rather then "SET". Actually "SET" clears ZOL context
- *
- * Vineetg: May 5th 2008
- *  -Modified CALLEE_REG save/restore macros to handle the fact that
- *      r25 contains the kernel current task ptr
- *  - Defined Stack Switching Macro to be reused in all intr/excp hdlrs
- *  - Shaved off 11 instructions from RESTORE_ALL_INT1 by using the
- *      address Write back load ld.ab instead of seperate ld/add instn
- *
- * Amit Bhor, Sameer Dhavale: Codito Technologies 2004
  */
 
 #ifndef __ASM_ARC_ENTRY_H
 #define __ASM_ARC_ENTRY_H
 
-#ifdef __ASSEMBLY__
 #include <asm/unistd.h>		/* For NR_syscalls defination */
-#include <asm/asm-offsets.h>
 #include <asm/arcregs.h>
 #include <asm/ptrace.h>
 #include <asm/processor.h>	/* For VMALLOC_START */
-#include <asm/thread_info.h>	/* For THREAD_SIZE */
 #include <asm/mmu.h>
 
+#ifdef CONFIG_ISA_ARCOMPACT
+#include <asm/entry-compact.h>	/* ISA specific bits */
+#else
+#include <asm/entry-arcv2.h>
+#endif
+
 /* Note on the LD/ST addr modes with addr reg wback
  *
  * LD.a same as LD.aw
@@ -143,8 +125,6 @@
 	POP	r13
 .endm
 
-#define OFF_USER_R25_FROM_R24	(SZ_CALLEE_REGS + SZ_PT_REGS - 8)/4
-
 /*--------------------------------------------------------------
  * Collect User Mode callee regs as struct callee_regs - needed by
  * fork/do_signal/unaligned-access-emulation.
@@ -157,12 +137,13 @@
  *-------------------------------------------------------------*/
 .macro SAVE_CALLEE_SAVED_USER
 
+	mov	r12, sp		; save SP as ref to pt_regs
 	SAVE_R13_TO_R24
 
 #ifdef CONFIG_ARC_CURR_IN_REG
-	; Retrieve orig r25 and save it on stack
-	ld.as   r12, [sp, OFF_USER_R25_FROM_R24]
-	st.a    r12, [sp, -4]
+	; Retrieve orig r25 and save it with rest of callee_regs
+	ld.as   r12, [r12, PT_user_r25]
+	PUSH	r12
 #else
 	PUSH	r25
 #endif
@@ -209,12 +190,16 @@
 .macro RESTORE_CALLEE_SAVED_USER
 
 #ifdef CONFIG_ARC_CURR_IN_REG
-	ld.ab   r12, [sp, 4]
-	st.as   r12, [sp, OFF_USER_R25_FROM_R24]
+	POP	r12
 #else
 	POP	r25
 #endif
 	RESTORE_R24_TO_R13
+
+	; SP is back to start of pt_regs
+#ifdef CONFIG_ARC_CURR_IN_REG
+	st.as   r12, [sp, PT_user_r25]
+#endif
 .endm
 
 /*--------------------------------------------------------------
@@ -240,117 +225,6 @@
 
 .endm
 
-/*--------------------------------------------------------------
- * Switch to Kernel Mode stack if SP points to User Mode stack
- *
- * Entry   : r9 contains pre-IRQ/exception/trap status32
- * Exit    : SP is set to kernel mode stack pointer
- *           If CURR_IN_REG, r25 set to "current" task pointer
- * Clobbers: r9
- *-------------------------------------------------------------*/
-
-.macro SWITCH_TO_KERNEL_STK
-
-	/* User Mode when this happened ? Yes: Proceed to switch stack */
-	bbit1   r9, STATUS_U_BIT, 88f
-
-	/* OK we were already in kernel mode when this event happened, thus can
-	 * assume SP is kernel mode SP. _NO_ need to do any stack switching
-	 */
-
-#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
-	/* However....
-	 * If Level 2 Interrupts enabled, we may end up with a corner case:
-	 * 1. User Task executing
-	 * 2. L1 IRQ taken, ISR starts (CPU auto-switched to KERNEL mode)
-	 * 3. But before it could switch SP from USER to KERNEL stack
-	 *      a L2 IRQ "Interrupts" L1
-	 * Thay way although L2 IRQ happened in Kernel mode, stack is still
-	 * not switched.
-	 * To handle this, we may need to switch stack even if in kernel mode
-	 * provided SP has values in range of USER mode stack ( < 0x7000_0000 )
-	 */
-	brlo sp, VMALLOC_START, 88f
-
-	/* TODO: vineetg:
-	 * 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
-	 * 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
-	 */
-
-#endif
-
-	/* Save Pre Intr/Exception KERNEL MODE SP on kernel stack
-	 * safe-keeping not really needed, but it keeps the epilogue code
-	 * (SP restore) simpler/uniform.
-	 */
-	b.d	66f
-	mov	r9, sp
-
-88: /*------Intr/Ecxp happened in user mode, "switch" stack ------ */
-
-	GET_CURR_TASK_ON_CPU   r9
-
-	/* With current tsk in r9, get it's kernel mode stack base */
-	GET_TSK_STACK_BASE  r9, r9
-
-66:
-#ifdef CONFIG_ARC_CURR_IN_REG
-	/*
-	 * Treat r25 as scratch reg, save it on stack first
-	 * Load it with current task pointer
-	 */
-	st	r25, [r9, -4]
-	GET_CURR_TASK_ON_CPU   r25
-#endif
-
-	/* Save Pre Intr/Exception User SP on kernel stack */
-	st.a    sp, [r9, -16]	; Make room for orig_r0, ECR, user_r25
-
-	/* CAUTION:
-	 * SP should be set at the very end when we are done with everything
-	 * In case of 2 levels of interrupt we depend on value of SP to assume
-	 * that everything else is done (loading r25 etc)
-	 */
-
-	/* set SP to point to kernel mode stack */
-	mov sp, r9
-
-	/* ----- Stack Switched to kernel Mode, Now save REG FILE ----- */
-
-.endm
-
-/*------------------------------------------------------------
- * "FAKE" a rtie to return from CPU Exception context
- * This is to re-enable Exceptions within exception
- * Look at EV_ProtV to see how this is actually used
- *-------------------------------------------------------------*/
-
-.macro FAKE_RET_FROM_EXCPN  reg
-
-	ld  \reg, [sp, PT_status32]
-	bic  \reg, \reg, (STATUS_U_MASK|STATUS_DE_MASK)
-	bset \reg, \reg, STATUS_L_BIT
-	sr  \reg, [erstatus]
-	mov \reg, 55f
-	sr  \reg, [eret]
-
-	rtie
-55:
-.endm
-
-/*
- * @reg [OUT] &thread_info of "current"
- */
-.macro GET_CURR_THR_INFO_FROM_SP  reg
-	bic \reg, sp, (THREAD_SIZE - 1)
-.endm
-
 /*
  * @reg [OUT] thread_info->flags of "current"
  */
@@ -359,222 +233,6 @@
 	ld  \reg, [\reg, THREAD_INFO_FLAGS]
 .endm
 
-/*--------------------------------------------------------------
- * For early Exception Prologue, a core reg is temporarily needed to
- * code the rest of prolog (stack switching). This is done by stashing
- * it to memory (non-SMP case) or SCRATCH0 Aux Reg (SMP).
- *
- * Before saving the full regfile - this reg is restored back, only
- * to be saved again on kernel mode stack, as part of pt_regs.
- *-------------------------------------------------------------*/
-.macro EXCPN_PROLOG_FREEUP_REG	reg
-#ifdef CONFIG_SMP
-	sr  \reg, [ARC_REG_SCRATCH_DATA0]
-#else
-	st  \reg, [@ex_saved_reg1]
-#endif
-.endm
-
-.macro EXCPN_PROLOG_RESTORE_REG	reg
-#ifdef CONFIG_SMP
-	lr  \reg, [ARC_REG_SCRATCH_DATA0]
-#else
-	ld  \reg, [@ex_saved_reg1]
-#endif
-.endm
-
-/*--------------------------------------------------------------
- * Exception Entry prologue
- * -Switches stack to K mode (if not already)
- * -Saves the register file
- *
- * After this it is safe to call the "C" handlers
- *-------------------------------------------------------------*/
-.macro EXCEPTION_PROLOGUE
-
-	/* Need at least 1 reg to code the early exception prologue */
-	EXCPN_PROLOG_FREEUP_REG r9
-
-	/* U/K mode at time of exception (stack not switched if already K) */
-	lr  r9, [erstatus]
-
-	/* ARC700 doesn't provide auto-stack switching */
-	SWITCH_TO_KERNEL_STK
-
-	/* save the regfile */
-	SAVE_ALL_SYS
-.endm
-
-/*--------------------------------------------------------------
- * Save all registers used by Exceptions (TLB Miss, Prot-V, Mem err etc)
- * Requires SP to be already switched to kernel mode Stack
- * sp points to the next free element on the stack at exit of this macro.
- * Registers are pushed / popped in the order defined in struct ptregs
- * in asm/ptrace.h
- * Note that syscalls are implemented via TRAP which is also a exception
- * from CPU's point of view
- *-------------------------------------------------------------*/
-.macro SAVE_ALL_SYS
-
-	lr	r9, [ecr]
-	st      r9, [sp, 8]    /* ECR */
-	st      r0, [sp, 4]    /* orig_r0, needed only for sys calls */
-
-	/* Restore r9 used to code the early prologue */
-	EXCPN_PROLOG_RESTORE_REG  r9
-
-	SAVE_R0_TO_R12
-	PUSH	gp
-	PUSH	fp
-	PUSH	blink
-	PUSHAX	eret
-	PUSHAX	erstatus
-	PUSH	lp_count
-	PUSHAX	lp_end
-	PUSHAX	lp_start
-	PUSHAX	erbta
-.endm
-
-/*--------------------------------------------------------------
- * Restore all registers used by system call or Exceptions
- * SP should always be pointing to the next free stack element
- * when entering this macro.
- *
- * NOTE:
- *
- * It is recommended that lp_count/ilink1/ilink2 not be used as a dest reg
- * for memory load operations. If used in that way interrupts are deffered
- * by hardware and that is not good.
- *-------------------------------------------------------------*/
-.macro RESTORE_ALL_SYS
-	POPAX	erbta
-	POPAX	lp_start
-	POPAX	lp_end
-
-	POP	r9
-	mov	lp_count, r9	;LD to lp_count is not allowed
-
-	POPAX	erstatus
-	POPAX	eret
-	POP	blink
-	POP	fp
-	POP	gp
-	RESTORE_R12_TO_R0
-
-	ld  sp, [sp] /* restore original sp */
-	/* orig_r0, ECR, user_r25 skipped automatically */
-.endm
-
-
-/*--------------------------------------------------------------
- * Save all registers used by interrupt handlers.
- *-------------------------------------------------------------*/
-.macro SAVE_ALL_INT1
-
-	/* restore original r9 to be saved as part of reg-file */
-#ifdef CONFIG_SMP
-	lr  r9, [ARC_REG_SCRATCH_DATA0]
-#else
-	ld  r9, [@int1_saved_reg]
-#endif
-
-	/* now we are ready to save the remaining context :) */
-	st      event_IRQ1, [sp, 8]    /* Dummy ECR */
-	st      0, [sp, 4]    /* orig_r0 , N/A for IRQ */
-
-	SAVE_R0_TO_R12
-	PUSH	gp
-	PUSH	fp
-	PUSH	blink
-	PUSH	ilink1
-	PUSHAX	status32_l1
-	PUSH	lp_count
-	PUSHAX	lp_end
-	PUSHAX	lp_start
-	PUSHAX	bta_l1
-.endm
-
-.macro SAVE_ALL_INT2
-
-	/* TODO-vineetg: SMP we can't use global nor can we use
-	*   SCRATCH0 as we do for int1 because while int1 is using
-	*   it, int2 can come
-	*/
-	/* retsore original r9 , saved in sys_saved_r9 */
-	ld  r9, [@int2_saved_reg]
-
-	/* now we are ready to save the remaining context :) */
-	st      event_IRQ2, [sp, 8]    /* Dummy ECR */
-	st      0, [sp, 4]    /* orig_r0 , N/A for IRQ */
-
-	SAVE_R0_TO_R12
-	PUSH	gp
-	PUSH	fp
-	PUSH	blink
-	PUSH	ilink2
-	PUSHAX	status32_l2
-	PUSH	lp_count
-	PUSHAX	lp_end
-	PUSHAX	lp_start
-	PUSHAX	bta_l2
-.endm
-
-/*--------------------------------------------------------------
- * Restore all registers used by interrupt handlers.
- *
- * NOTE:
- *
- * It is recommended that lp_count/ilink1/ilink2 not be used as a dest reg
- * for memory load operations. If used in that way interrupts are deffered
- * by hardware and that is not good.
- *-------------------------------------------------------------*/
-
-.macro RESTORE_ALL_INT1
-	POPAX	bta_l1
-	POPAX	lp_start
-	POPAX	lp_end
-
-	POP	r9
-	mov	lp_count, r9	;LD to lp_count is not allowed
-
-	POPAX	status32_l1
-	POP	ilink1
-	POP	blink
-	POP	fp
-	POP	gp
-	RESTORE_R12_TO_R0
-
-	ld  sp, [sp] /* restore original sp */
-	/* orig_r0, ECR, user_r25 skipped automatically */
-.endm
-
-.macro RESTORE_ALL_INT2
-	POPAX	bta_l2
-	POPAX	lp_start
-	POPAX	lp_end
-
-	POP	r9
-	mov	lp_count, r9	;LD to lp_count is not allowed
-
-	POPAX	status32_l2
-	POP	ilink2
-	POP	blink
-	POP	fp
-	POP	gp
-	RESTORE_R12_TO_R0
-
-	ld  sp, [sp] /* restore original sp */
-	/* orig_r0, ECR, user_r25 skipped automatically */
-.endm
-
-
-/* Get CPU-ID of this core */
-.macro  GET_CPU_ID  reg
-	lr  \reg, [identity]
-	lsr \reg, \reg, 8
-	bmsk \reg, \reg, 7
-.endm
-
 #ifdef CONFIG_SMP
 
 /*-------------------------------------------------
@@ -643,6 +301,4 @@
 
 #endif	/* CONFIG_ARC_CURR_IN_REG */
 
-#endif  /* __ASSEMBLY__ */
-
 #endif  /* __ASM_ARC_ENTRY_H */
diff --git a/kernel/arch/arc/include/asm/futex.h b/kernel/arch/arc/include/asm/futex.h
index 05b5aaf5b..11e1b1f3a 100644
--- a/kernel/arch/arc/include/asm/futex.h
+++ b/kernel/arch/arc/include/asm/futex.h
@@ -16,18 +16,22 @@
 #include <linux/uaccess.h>
 #include <asm/errno.h>
 
+#ifdef CONFIG_ARC_HAS_LLSC
+
 #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)\
 							\
+	smp_mb();					\
 	__asm__ __volatile__(				\
-	"1:	ld  %1, [%2]			\n"	\
+	"1:	llock	%1, [%2]		\n"	\
 		insn				"\n"	\
-	"2:	st  %0, [%2]			\n"	\
+	"2:	scond	%0, [%2]		\n"	\
+	"	bnz	1b			\n"	\
 	"	mov %0, 0			\n"	\
 	"3:					\n"	\
 	"	.section .fixup,\"ax\"		\n"	\
 	"	.align  4			\n"	\
 	"4:	mov %0, %4			\n"	\
-	"	b   3b				\n"	\
+	"	j   3b				\n"	\
 	"	.previous			\n"	\
 	"	.section __ex_table,\"a\"	\n"	\
 	"	.align  4			\n"	\
@@ -37,7 +41,37 @@
 							\
 	: "=&r" (ret), "=&r" (oldval)			\
 	: "r" (uaddr), "r" (oparg), "ir" (-EFAULT)	\
-	: "cc", "memory")
+	: "cc", "memory");				\
+	smp_mb()					\
+
+#else	/* !CONFIG_ARC_HAS_LLSC */
+
+#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)\
+							\
+	smp_mb();					\
+	__asm__ __volatile__(				\
+	"1:	ld	%1, [%2]		\n"	\
+		insn				"\n"	\
+	"2:	st	%0, [%2]		\n"	\
+	"	mov %0, 0			\n"	\
+	"3:					\n"	\
+	"	.section .fixup,\"ax\"		\n"	\
+	"	.align  4			\n"	\
+	"4:	mov %0, %4			\n"	\
+	"	j   3b				\n"	\
+	"	.previous			\n"	\
+	"	.section __ex_table,\"a\"	\n"	\
+	"	.align  4			\n"	\
+	"	.word   1b, 4b			\n"	\
+	"	.word   2b, 4b			\n"	\
+	"	.previous			\n"	\
+							\
+	: "=&r" (ret), "=&r" (oldval)			\
+	: "r" (uaddr), "r" (oparg), "ir" (-EFAULT)	\
+	: "cc", "memory");				\
+	smp_mb()					\
+
+#endif
 
 static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 {
@@ -53,6 +87,9 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
 		return -EFAULT;
 
+#ifndef CONFIG_ARC_HAS_LLSC
+	preempt_disable();	/* to guarantee atomic r-m-w of futex op */
+#endif
 	pagefault_disable();
 
 	switch (op) {
@@ -60,6 +97,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 		__futex_atomic_op("mov %0, %3", ret, oldval, uaddr, oparg);
 		break;
 	case FUTEX_OP_ADD:
+		/* oldval = *uaddr; *uaddr += oparg ; ret = *uaddr */
 		__futex_atomic_op("add %0, %1, %3", ret, oldval, uaddr, oparg);
 		break;
 	case FUTEX_OP_OR:
@@ -76,6 +114,9 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 	}
 
 	pagefault_enable();
+#ifndef CONFIG_ARC_HAS_LLSC
+	preempt_enable();
+#endif
 
 	if (!ret) {
 		switch (cmp) {
@@ -104,48 +145,57 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 	return ret;
 }
 
-/* Compare-xchg with pagefaults disabled.
- *  Notes:
- *      -Best-Effort: Exchg happens only if compare succeeds.
- *          If compare fails, returns; leaving retry/looping to upper layers
- *      -successful cmp-xchg: return orig value in @addr (same as cmp val)
- *      -Compare fails: return orig value in @addr
- *      -user access r/w fails: return -EFAULT
+/*
+ * cmpxchg of futex (pagefaults disabled by caller)
+ * Return 0 for success, -EFAULT otherwise
  */
 static inline int
-futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval,
-					u32 newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 expval,
+			      u32 newval)
 {
-	u32 val;
+	int ret = 0;
+	u32 existval;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
-	pagefault_disable();
+#ifndef CONFIG_ARC_HAS_LLSC
+	preempt_disable();	/* to guarantee atomic r-m-w of futex op */
+#endif
+	smp_mb();
 
-	/* TBD : can use llock/scond */
 	__asm__ __volatile__(
-	"1:	ld    %0, [%3]	\n"
-	"	brne  %0, %1, 3f	\n"
-	"2:	st    %2, [%3]	\n"
+#ifdef CONFIG_ARC_HAS_LLSC
+	"1:	llock	%1, [%4]		\n"
+	"	brne	%1, %2, 3f		\n"
+	"2:	scond	%3, [%4]		\n"
+	"	bnz	1b			\n"
+#else
+	"1:	ld	%1, [%4]		\n"
+	"	brne	%1, %2, 3f		\n"
+	"2:	st	%3, [%4]		\n"
+#endif
 	"3:	\n"
 	"	.section .fixup,\"ax\"	\n"
-	"4:	mov %0, %4	\n"
-	"	b   3b	\n"
+	"4:	mov %0, %5	\n"
+	"	j   3b	\n"
 	"	.previous	\n"
 	"	.section __ex_table,\"a\"	\n"
 	"	.align  4	\n"
 	"	.word   1b, 4b	\n"
 	"	.word   2b, 4b	\n"
 	"	.previous\n"
-	: "=&r"(val)
-	: "r"(oldval), "r"(newval), "r"(uaddr), "ir"(-EFAULT)
+	: "+&r"(ret), "=&r"(existval)
+	: "r"(expval), "r"(newval), "r"(uaddr), "ir"(-EFAULT)
 	: "cc", "memory");
 
-	pagefault_enable();
+	smp_mb();
 
-	*uval = val;
-	return val;
+#ifndef CONFIG_ARC_HAS_LLSC
+	preempt_enable();
+#endif
+	*uval = existval;
+	return ret;
 }
 
 #endif
diff --git a/kernel/arch/arc/include/asm/highmem.h b/kernel/arch/arc/include/asm/highmem.h
new file mode 100644
index 000000000..b1585c963
--- /dev/null
+++ b/kernel/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/kernel/arch/arc/include/asm/hugepage.h b/kernel/arch/arc/include/asm/hugepage.h
new file mode 100644
index 000000000..c5094de86
--- /dev/null
+++ b/kernel/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/kernel/arch/arc/include/asm/io.h b/kernel/arch/arc/include/asm/io.h
index cabd518cb..694ece8a0 100644
--- a/kernel/arch/arc/include/asm/io.h
+++ b/kernel/arch/arc/include/asm/io.h
@@ -20,6 +20,7 @@ extern void iounmap(const void __iomem *addr);
 
 #define ioremap_nocache(phy, sz)	ioremap(phy, sz)
 #define ioremap_wc(phy, sz)		ioremap(phy, sz)
+#define ioremap_wt(phy, sz)		ioremap(phy, sz)
 
 /* Change struct page to physical address */
 #define page_to_phys(page)		(page_to_pfn(page) << PAGE_SHIFT)
@@ -98,9 +99,45 @@ static inline void __raw_writel(u32 w, volatile void __iomem *addr)
 
 }
 
-#define readb_relaxed readb
-#define readw_relaxed readw
-#define readl_relaxed readl
+#ifdef CONFIG_ISA_ARCV2
+#include <asm/barrier.h>
+#define __iormb()		rmb()
+#define __iowmb()		wmb()
+#else
+#define __iormb()		do { } while (0)
+#define __iowmb()		do { } while (0)
+#endif
+
+/*
+ * MMIO can also get buffered/optimized in micro-arch, so barriers needed
+ * Based on ARM model for the typical use case
+ *
+ *	<ST [DMA buffer]>
+ *	<writel MMIO "go" reg>
+ *  or:
+ *	<readl MMIO "status" reg>
+ *	<LD [DMA buffer]>
+ *
+ * http://lkml.kernel.org/r/20150622133656.GG1583@arm.com
+ */
+#define readb(c)		({ u8  __v = readb_relaxed(c); __iormb(); __v; })
+#define readw(c)		({ u16 __v = readw_relaxed(c); __iormb(); __v; })
+#define readl(c)		({ u32 __v = readl_relaxed(c); __iormb(); __v; })
+
+#define writeb(v,c)		({ __iowmb(); writeb_relaxed(v,c); })
+#define writew(v,c)		({ __iowmb(); writew_relaxed(v,c); })
+#define writel(v,c)		({ __iowmb(); writel_relaxed(v,c); })
+
+/*
+ * Relaxed API for drivers which can handle any ordering themselves
+ */
+#define readb_relaxed(c)	__raw_readb(c)
+#define readw_relaxed(c)	__raw_readw(c)
+#define readl_relaxed(c)	__raw_readl(c)
+
+#define writeb_relaxed(v,c)	__raw_writeb(v,c)
+#define writew_relaxed(v,c)	__raw_writew(v,c)
+#define writel_relaxed(v,c)	__raw_writel(v,c)
 
 #include <asm-generic/io.h>
 
diff --git a/kernel/arch/arc/include/asm/irq.h b/kernel/arch/arc/include/asm/irq.h
index f38652fb2..4fd7d62a6 100644
--- a/kernel/arch/arc/include/asm/irq.h
+++ b/kernel/arch/arc/include/asm/irq.h
@@ -13,8 +13,15 @@
 #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
+#define IPI_IRQ		(NR_CPU_IRQS-1) /* dummy to enable SMP build for up hardware */
+#else
+#define TIMER0_IRQ      16
+#define TIMER1_IRQ      17
+#define IPI_IRQ         19
+#endif
 
 #include <linux/interrupt.h>
 #include <asm-generic/irq.h>
diff --git a/kernel/arch/arc/include/asm/irqflags-arcv2.h b/kernel/arch/arc/include/asm/irqflags-arcv2.h
new file mode 100644
index 000000000..68b609234
--- /dev/null
+++ b/kernel/arch/arc/include/asm/irqflags-arcv2.h
@@ -0,0 +1,138 @@
+/*
+ * Copyright (C) 2014-15 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_IRQFLAGS_ARCV2_H
+#define __ASM_IRQFLAGS_ARCV2_H
+
+#include <asm/arcregs.h>
+
+/* status32 Bits */
+#define STATUS_AD_BIT	19   /* Disable Align chk: core supports non-aligned */
+#define STATUS_IE_BIT	31
+
+#define STATUS_AD_MASK		(1<<STATUS_AD_BIT)
+#define STATUS_IE_MASK		(1<<STATUS_IE_BIT)
+
+#define AUX_USER_SP		0x00D
+#define AUX_IRQ_CTRL		0x00E
+#define AUX_IRQ_ACT		0x043	/* Active Intr across all levels */
+#define AUX_IRQ_LVL_PEND	0x200	/* Pending Intr across all levels */
+#define AUX_IRQ_HINT		0x201	/* For generating Soft Interrupts */
+#define AUX_IRQ_PRIORITY	0x206
+#define ICAUSE			0x40a
+#define AUX_IRQ_SELECT		0x40b
+#define AUX_IRQ_ENABLE		0x40c
+
+/* Was Intr taken in User Mode */
+#define AUX_IRQ_ACT_BIT_U	31
+
+/* 0 is highest level, but taken by FIRQs, if present in design */
+#define ARCV2_IRQ_DEF_PRIO		0
+
+/* seed value for status register */
+#define ISA_INIT_STATUS_BITS	(STATUS_IE_MASK | STATUS_AD_MASK | \
+					(ARCV2_IRQ_DEF_PRIO << 1))
+
+/* SLEEP needs default irq priority (<=) which can interrupt the doze */
+#define ISA_SLEEP_ARG		(0x10 | ARCV2_IRQ_DEF_PRIO)
+
+#ifndef __ASSEMBLY__
+
+/*
+ * Save IRQ state and disable IRQs
+ */
+static inline long arch_local_irq_save(void)
+{
+	unsigned long flags;
+
+	__asm__ __volatile__("	clri %0	\n" : "=r" (flags) : : "memory");
+
+	return flags;
+}
+
+/*
+ * restore saved IRQ state
+ */
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+	__asm__ __volatile__("	seti %0	\n" : : "r" (flags) : "memory");
+}
+
+/*
+ * Unconditionally Enable IRQs
+ */
+static inline void arch_local_irq_enable(void)
+{
+	unsigned int irqact = read_aux_reg(AUX_IRQ_ACT);
+
+	if (irqact & 0xffff)
+		write_aux_reg(AUX_IRQ_ACT, irqact & ~0xffff);
+
+	__asm__ __volatile__("	seti	\n" : : : "memory");
+}
+
+/*
+ * Unconditionally Disable IRQs
+ */
+static inline void arch_local_irq_disable(void)
+{
+	__asm__ __volatile__("	clri	\n" : : : "memory");
+}
+
+/*
+ * save IRQ state
+ */
+static inline long arch_local_save_flags(void)
+{
+	unsigned long temp;
+
+	__asm__ __volatile__(
+	"	lr  %0, [status32]	\n"
+	: "=&r"(temp)
+	:
+	: "memory");
+
+	return temp;
+}
+
+/*
+ * Query IRQ state
+ */
+static inline int arch_irqs_disabled_flags(unsigned long flags)
+{
+	return !(flags & (STATUS_IE_MASK));
+}
+
+static inline int arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
+static inline void arc_softirq_trigger(int irq)
+{
+	write_aux_reg(AUX_IRQ_HINT, irq);
+}
+
+static inline void arc_softirq_clear(int irq)
+{
+	write_aux_reg(AUX_IRQ_HINT, 0);
+}
+
+#else
+
+.macro IRQ_DISABLE  scratch
+	clri
+.endm
+
+.macro IRQ_ENABLE  scratch
+	seti
+.endm
+
+#endif	/* __ASSEMBLY__ */
+
+#endif
diff --git a/kernel/arch/arc/include/asm/irqflags-compact.h b/kernel/arch/arc/include/asm/irqflags-compact.h
new file mode 100644
index 000000000..c1d36458b
--- /dev/null
+++ b/kernel/arch/arc/include/asm/irqflags-compact.h
@@ -0,0 +1,199 @@
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ * Copyright (C) 2004, 2007-2010, 2011-2012 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_IRQFLAGS_ARCOMPACT_H
+#define __ASM_IRQFLAGS_ARCOMPACT_H
+
+/* vineetg: March 2010 : local_irq_save( ) optimisation
+ *  -Remove explicit mov of current status32 into reg, that is not needed
+ *  -Use BIC  insn instead of INVERTED + AND
+ *  -Conditionally disable interrupts (if they are not enabled, don't disable)
+*/
+
+#include <asm/arcregs.h>
+
+/* status32 Reg bits related to Interrupt Handling */
+#define STATUS_E1_BIT		1	/* Int 1 enable */
+#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 */
+#define AUX_IRQ_LEV		0x200	/* IRQ Priority: L1 or L2 */
+#define AUX_IRQ_HINT		0x201	/* For generating Soft Interrupts */
+#define AUX_IRQ_LV12		0x43	/* interrupt level register */
+
+#define AUX_IENABLE		0x40c
+#define AUX_ITRIGGER		0x40d
+#define AUX_IPULSE		0x415
+
+#define ISA_INIT_STATUS_BITS	STATUS_IE_MASK
+
+#define ISA_SLEEP_ARG		0x3
+
+#ifndef __ASSEMBLY__
+
+/******************************************************************
+ * IRQ Control Macros
+ *
+ * All of them have "memory" clobber (compiler barrier) which is needed to
+ * ensure that LD/ST requiring irq safetly (R-M-W when LLSC is not available)
+ * are redone after IRQs are re-enabled (and gcc doesn't reuse stale register)
+ *
+ * Noted at the time of Abilis Timer List corruption
+ *	Orig Bug + Rejected solution	: https://lkml.org/lkml/2013/3/29/67
+ *	Reasoning			: https://lkml.org/lkml/2013/4/8/15
+ *
+ ******************************************************************/
+
+/*
+ * Save IRQ state and disable IRQs
+ */
+static inline long arch_local_irq_save(void)
+{
+	unsigned long temp, flags;
+
+	__asm__ __volatile__(
+	"	lr  %1, [status32]	\n"
+	"	bic %0, %1, %2		\n"
+	"	and.f 0, %1, %2	\n"
+	"	flag.nz %0		\n"
+	: "=r"(temp), "=r"(flags)
+	: "n"((STATUS_E1_MASK | STATUS_E2_MASK))
+	: "memory", "cc");
+
+	return flags;
+}
+
+/*
+ * restore saved IRQ state
+ */
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+
+	__asm__ __volatile__(
+	"	flag %0			\n"
+	:
+	: "r"(flags)
+	: "memory");
+}
+
+/*
+ * Unconditionally Enable IRQs
+ */
+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
+ */
+static inline void arch_local_irq_disable(void)
+{
+	unsigned long temp;
+
+	__asm__ __volatile__(
+	"	lr  %0, [status32]	\n"
+	"	and %0, %0, %1		\n"
+	"	flag %0			\n"
+	: "=&r"(temp)
+	: "n"(~(STATUS_E1_MASK | STATUS_E2_MASK))
+	: "memory");
+}
+
+/*
+ * save IRQ state
+ */
+static inline long arch_local_save_flags(void)
+{
+	unsigned long temp;
+
+	__asm__ __volatile__(
+	"	lr  %0, [status32]	\n"
+	: "=&r"(temp)
+	:
+	: "memory");
+
+	return temp;
+}
+
+/*
+ * Query IRQ state
+ */
+static inline int arch_irqs_disabled_flags(unsigned long flags)
+{
+	return !(flags & (STATUS_E1_MASK
+#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
+			| STATUS_E2_MASK
+#endif
+		));
+}
+
+static inline int arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
+#else
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+
+.macro TRACE_ASM_IRQ_DISABLE
+	bl	trace_hardirqs_off
+.endm
+
+.macro TRACE_ASM_IRQ_ENABLE
+	bl	trace_hardirqs_on
+.endm
+
+#else
+
+.macro TRACE_ASM_IRQ_DISABLE
+.endm
+
+.macro TRACE_ASM_IRQ_ENABLE
+.endm
+
+#endif
+
+.macro IRQ_DISABLE  scratch
+	lr	\scratch, [status32]
+	bic	\scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK)
+	flag	\scratch
+	TRACE_ASM_IRQ_DISABLE
+.endm
+
+.macro IRQ_ENABLE  scratch
+	lr	\scratch, [status32]
+	or	\scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK)
+	flag	\scratch
+	TRACE_ASM_IRQ_ENABLE
+.endm
+
+#endif	/* __ASSEMBLY__ */
+
+#endif
diff --git a/kernel/arch/arc/include/asm/irqflags.h b/kernel/arch/arc/include/asm/irqflags.h
index 27ecc6975..59bc6a64f 100644
--- a/kernel/arch/arc/include/asm/irqflags.h
+++ b/kernel/arch/arc/include/asm/irqflags.h
@@ -1,4 +1,5 @@
 /*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
  * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
  *
  * This program is free software; you can redistribute it and/or modify
@@ -9,171 +10,10 @@
 #ifndef __ASM_ARC_IRQFLAGS_H
 #define __ASM_ARC_IRQFLAGS_H
 
-/* vineetg: March 2010 : local_irq_save( ) optimisation
- *  -Remove explicit mov of current status32 into reg, that is not needed
- *  -Use BIC  insn instead of INVERTED + AND
- *  -Conditionally disable interrupts (if they are not enabled, don't disable)
-*/
-
-#include <asm/arcregs.h>
-
-/* status32 Reg bits related to Interrupt Handling */
-#define STATUS_E1_BIT		1	/* Int 1 enable */
-#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_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)
-
-/* Other Interrupt Handling related Aux regs */
-#define AUX_IRQ_LEV		0x200	/* IRQ Priority: L1 or L2 */
-#define AUX_IRQ_HINT		0x201	/* For generating Soft Interrupts */
-#define AUX_IRQ_LV12		0x43	/* interrupt level register */
-
-#define AUX_IENABLE		0x40c
-#define AUX_ITRIGGER		0x40d
-#define AUX_IPULSE		0x415
-
-#ifndef __ASSEMBLY__
-
-/******************************************************************
- * IRQ Control Macros
- *
- * All of them have "memory" clobber (compiler barrier) which is needed to
- * ensure that LD/ST requiring irq safetly (R-M-W when LLSC is not available)
- * are redone after IRQs are re-enabled (and gcc doesn't reuse stale register)
- *
- * Noted at the time of Abilis Timer List corruption
- * 	Orig Bug + Rejected solution	: https://lkml.org/lkml/2013/3/29/67
- * 	Reasoning			: https://lkml.org/lkml/2013/4/8/15
- *
- ******************************************************************/
-
-/*
- * Save IRQ state and disable IRQs
- */
-static inline long arch_local_irq_save(void)
-{
-	unsigned long temp, flags;
-
-	__asm__ __volatile__(
-	"	lr  %1, [status32]	\n"
-	"	bic %0, %1, %2		\n"
-	"	and.f 0, %1, %2	\n"
-	"	flag.nz %0		\n"
-	: "=r"(temp), "=r"(flags)
-	: "n"((STATUS_E1_MASK | STATUS_E2_MASK))
-	: "memory", "cc");
-
-	return flags;
-}
-
-/*
- * restore saved IRQ state
- */
-static inline void arch_local_irq_restore(unsigned long flags)
-{
-
-	__asm__ __volatile__(
-	"	flag %0			\n"
-	:
-	: "r"(flags)
-	: "memory");
-}
-
-/*
- * Unconditionally Enable IRQs
- */
-extern void arch_local_irq_enable(void);
-
-/*
- * Unconditionally Disable IRQs
- */
-static inline void arch_local_irq_disable(void)
-{
-	unsigned long temp;
-
-	__asm__ __volatile__(
-	"	lr  %0, [status32]	\n"
-	"	and %0, %0, %1		\n"
-	"	flag %0			\n"
-	: "=&r"(temp)
-	: "n"(~(STATUS_E1_MASK | STATUS_E2_MASK))
-	: "memory");
-}
-
-/*
- * save IRQ state
- */
-static inline long arch_local_save_flags(void)
-{
-	unsigned long temp;
-
-	__asm__ __volatile__(
-	"	lr  %0, [status32]	\n"
-	: "=&r"(temp)
-	:
-	: "memory");
-
-	return temp;
-}
-
-/*
- * Query IRQ state
- */
-static inline int arch_irqs_disabled_flags(unsigned long flags)
-{
-	return !(flags & (STATUS_E1_MASK
-#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
-			| STATUS_E2_MASK
-#endif
-		));
-}
-
-static inline int arch_irqs_disabled(void)
-{
-	return arch_irqs_disabled_flags(arch_local_save_flags());
-}
-
-#else
-
-#ifdef CONFIG_TRACE_IRQFLAGS
-
-.macro TRACE_ASM_IRQ_DISABLE
-	bl	trace_hardirqs_off
-.endm
-
-.macro TRACE_ASM_IRQ_ENABLE
-	bl	trace_hardirqs_on
-.endm
-
+#ifdef CONFIG_ISA_ARCOMPACT
+#include <asm/irqflags-compact.h>
 #else
-
-.macro TRACE_ASM_IRQ_DISABLE
-.endm
-
-.macro TRACE_ASM_IRQ_ENABLE
-.endm
-
+#include <asm/irqflags-arcv2.h>
 #endif
 
-.macro IRQ_DISABLE  scratch
-	lr	\scratch, [status32]
-	bic	\scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK)
-	flag	\scratch
-	TRACE_ASM_IRQ_DISABLE
-.endm
-
-.macro IRQ_ENABLE  scratch
-	lr	\scratch, [status32]
-	or	\scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK)
-	flag	\scratch
-	TRACE_ASM_IRQ_ENABLE
-.endm
-
-#endif	/* __ASSEMBLY__ */
-
 #endif
diff --git a/kernel/arch/arc/include/asm/kmap_types.h b/kernel/arch/arc/include/asm/kmap_types.h
new file mode 100644
index 000000000..f0d7f6ace
--- /dev/null
+++ b/kernel/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/kernel/arch/arc/include/asm/mach_desc.h b/kernel/arch/arc/include/asm/mach_desc.h
index e8993a2be..c28e6c347 100644
--- a/kernel/arch/arc/include/asm/mach_desc.h
+++ b/kernel/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_per_cpu:	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_per_cpu)(unsigned int);
 #endif
-	void			(*init_time)(void);
 	void			(*init_machine)(void);
 	void			(*init_late)(void);
 
diff --git a/kernel/arch/arc/include/asm/mcip.h b/kernel/arch/arc/include/asm/mcip.h
new file mode 100644
index 000000000..46f4e5351
--- /dev/null
+++ b/kernel/arch/arc/include/asm/mcip.h
@@ -0,0 +1,91 @@
+/*
+ * ARConnect IP Support (Multi core enabler: Cross core IPI, RTC ...)
+ *
+ * Copyright (C) 2014-15 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_MCIP_H
+#define __ASM_MCIP_H
+
+#ifdef CONFIG_ISA_ARCV2
+
+#include <asm/arcregs.h>
+
+#define ARC_REG_MCIP_BCR	0x0d0
+#define ARC_REG_MCIP_CMD	0x600
+#define ARC_REG_MCIP_WDATA	0x601
+#define ARC_REG_MCIP_READBACK	0x602
+
+struct mcip_cmd {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad:8, param:16, cmd:8;
+#else
+	unsigned int cmd:8, param:16, pad:8;
+#endif
+
+#define CMD_INTRPT_GENERATE_IRQ		0x01
+#define CMD_INTRPT_GENERATE_ACK		0x02
+#define CMD_INTRPT_READ_STATUS		0x03
+#define CMD_INTRPT_CHECK_SOURCE		0x04
+
+/* Semaphore Commands */
+#define CMD_SEMA_CLAIM_AND_READ		0x11
+#define CMD_SEMA_RELEASE		0x12
+
+#define CMD_DEBUG_SET_MASK		0x34
+#define CMD_DEBUG_SET_SELECT		0x36
+
+#define CMD_GRTC_READ_LO		0x42
+#define CMD_GRTC_READ_HI		0x43
+
+#define CMD_IDU_ENABLE			0x71
+#define CMD_IDU_DISABLE			0x72
+#define CMD_IDU_SET_MODE		0x74
+#define CMD_IDU_SET_DEST		0x76
+#define CMD_IDU_SET_MASK		0x7C
+
+#define IDU_M_TRIG_LEVEL		0x0
+#define IDU_M_TRIG_EDGE			0x1
+
+#define IDU_M_DISTRI_RR			0x0
+#define IDU_M_DISTRI_DEST		0x2
+};
+
+/*
+ * MCIP programming model
+ *
+ * - Simple commands write {cmd:8,param:16} to MCIP_CMD aux reg
+ *   (param could be irq, common_irq, core_id ...)
+ * - More involved commands setup MCIP_WDATA with cmd specific data
+ *   before invoking the simple command
+ */
+static inline void __mcip_cmd(unsigned int cmd, unsigned int param)
+{
+	struct mcip_cmd buf;
+
+	buf.pad = 0;
+	buf.cmd = cmd;
+	buf.param = param;
+
+	WRITE_AUX(ARC_REG_MCIP_CMD, buf);
+}
+
+/*
+ * Setup additional data for a cmd
+ * Callers need to lock to ensure atomicity
+ */
+static inline void __mcip_cmd_data(unsigned int cmd, unsigned int param,
+				   unsigned int data)
+{
+	write_aux_reg(ARC_REG_MCIP_WDATA, data);
+
+	__mcip_cmd(cmd, param);
+}
+
+#endif
+
+#endif
diff --git a/kernel/arch/arc/include/asm/mmu.h b/kernel/arch/arc/include/asm/mmu.h
index 8c84ae98c..b144d7ca7 100644
--- a/kernel/arch/arc/include/asm/mmu.h
+++ b/kernel/arch/arc/include/asm/mmu.h
@@ -15,24 +15,43 @@
 #define CONFIG_ARC_MMU_VER 2
 #elif defined(CONFIG_ARC_MMU_V3)
 #define CONFIG_ARC_MMU_VER 3
+#elif defined(CONFIG_ARC_MMU_V4)
+#define CONFIG_ARC_MMU_VER 4
 #endif
 
 /* MMU Management regs */
 #define ARC_REG_MMU_BCR		0x06f
+#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
 #define ARC_REG_SCRATCH_DATA0	0x418
+#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
+#define ARC_REG_SCRATCH_DATA0	0x46c
+#endif
 
 /* Bits in MMU PID register */
-#define MMU_ENABLE		(1 << 31)	/* Enable MMU for process */
+#define __TLB_ENABLE		(1 << 31)
+#define __PROG_ENABLE		(1 << 30)
+#define MMU_ENABLE		(__TLB_ENABLE | __PROG_ENABLE)
 
 /* Error code if probe fails */
 #define TLB_LKUP_ERR		0x80000000
 
+#if (CONFIG_ARC_MMU_VER < 4)
 #define TLB_DUP_ERR	(TLB_LKUP_ERR | 0x00000001)
+#else
+#define TLB_DUP_ERR	(TLB_LKUP_ERR | 0x40000000)
+#endif
 
 /* TLB Commands */
 #define TLBWrite    0x1
@@ -45,6 +64,11 @@
 #define TLBIVUTLB   0x6		/* explicitly inv uTLBs */
 #endif
 
+#if (CONFIG_ARC_MMU_VER >= 4)
+#define TLBInsertEntry	0x7
+#define TLBDeleteEntry	0x8
+#endif
+
 #ifndef __ASSEMBLY__
 
 typedef struct {
@@ -61,6 +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/kernel/arch/arc/include/asm/page.h b/kernel/arch/arc/include/asm/page.h
index 9c8aa41e4..429957f1c 100644
--- a/kernel/arch/arc/include/asm/page.h
+++ b/kernel/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/kernel/arch/arc/include/asm/perf_event.h b/kernel/arch/arc/include/asm/perf_event.h
index 2b8880e95..5f071762f 100644
--- a/kernel/arch/arc/include/asm/perf_event.h
+++ b/kernel/arch/arc/include/asm/perf_event.h
@@ -1,6 +1,7 @@
 /*
  * Linux performance counter support for ARC
  *
+ * Copyright (C) 2014-2015 Synopsys, Inc. (www.synopsys.com)
  * Copyright (C) 2011-2013 Synopsys, Inc. (www.synopsys.com)
  *
  * This program is free software; you can redistribute it and/or modify
@@ -12,8 +13,8 @@
 #ifndef __ASM_PERF_EVENT_H
 #define __ASM_PERF_EVENT_H
 
-/* real maximum varies per CPU, this is the maximum supported by the driver */
-#define ARC_PMU_MAX_HWEVENTS	64
+/* Max number of counters that PCT block may ever have */
+#define ARC_PERF_MAX_COUNTERS	32
 
 #define ARC_REG_CC_BUILD	0xF6
 #define ARC_REG_CC_INDEX	0x240
@@ -28,15 +29,22 @@
 #define ARC_REG_PCT_CONFIG	0x254
 #define ARC_REG_PCT_CONTROL	0x255
 #define ARC_REG_PCT_INDEX	0x256
+#define ARC_REG_PCT_INT_CNTL	0x25C
+#define ARC_REG_PCT_INT_CNTH	0x25D
+#define ARC_REG_PCT_INT_CTRL	0x25E
+#define ARC_REG_PCT_INT_ACT	0x25F
+
+#define ARC_REG_PCT_CONFIG_USER	(1 << 18)	/* count in user mode */
+#define ARC_REG_PCT_CONFIG_KERN	(1 << 19)	/* count in kernel mode */
 
 #define ARC_REG_PCT_CONTROL_CC	(1 << 16)	/* clear counts */
 #define ARC_REG_PCT_CONTROL_SN	(1 << 17)	/* snapshot */
 
 struct arc_reg_pct_build {
 #ifdef CONFIG_CPU_BIG_ENDIAN
-	unsigned int m:8, c:8, r:6, s:2, v:8;
+	unsigned int m:8, c:8, r:5, i:1, s:2, v:8;
 #else
-	unsigned int v:8, s:2, r:6, c:8, m:8;
+	unsigned int v:8, s:2, i:1, r:5, c:8, m:8;
 #endif
 };
 
@@ -95,10 +103,13 @@ static const char * const arc_pmu_ev_hw_map[] = {
 
 	/* counts condition */
 	[PERF_COUNT_HW_INSTRUCTIONS] = "iall",
-	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmp",
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmp", /* Excludes ZOL jumps */
 	[PERF_COUNT_ARC_BPOK]         = "bpok",	  /* NP-NT, PT-T, PNT-NT */
+#ifdef CONFIG_ISA_ARCV2
+	[PERF_COUNT_HW_BRANCH_MISSES] = "bpmp",
+#else
 	[PERF_COUNT_HW_BRANCH_MISSES] = "bpfail", /* NP-T, PT-NT, PNT-T */
-
+#endif
 	[PERF_COUNT_ARC_LDC] = "imemrdc",	/* Instr: mem read cached */
 	[PERF_COUNT_ARC_STC] = "imemwrc",	/* Instr: mem write cached */
 
diff --git a/kernel/arch/arc/include/asm/pgalloc.h b/kernel/arch/arc/include/asm/pgalloc.h
index 81208bfd9..86ed67128 100644
--- a/kernel/arch/arc/include/asm/pgalloc.h
+++ b/kernel/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/kernel/arch/arc/include/asm/pgtable.h b/kernel/arch/arc/include/asm/pgtable.h
index 9615fe170..57af2f05a 100644
--- a/kernel/arch/arc/include/asm/pgtable.h
+++ b/kernel/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) */
 
@@ -71,32 +73,44 @@
 #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) */
+#endif
+
 #define _PAGE_GLOBAL        (1<<8)	/* Page is global (H) */
 #define _PAGE_PRESENT       (1<<9)	/* TLB entry is valid (H) */
+
+#if (CONFIG_ARC_MMU_VER >= 4)
+#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)
@@ -112,15 +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)
@@ -181,26 +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.
@@ -260,15 +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))
 
 /*
@@ -285,23 +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)
 {
@@ -347,7 +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);
@@ -373,6 +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/kernel/arch/arc/include/asm/processor.h b/kernel/arch/arc/include/asm/processor.h
index 52312cb5d..1d694c1ef 100644
--- a/kernel/arch/arc/include/asm/processor.h
+++ b/kernel/arch/arc/include/asm/processor.h
@@ -57,11 +57,7 @@ struct task_struct;
  * A lot of busy-wait loops in SMP are based off of non-volatile data otherwise
  * get optimised away by gcc
  */
-#ifdef CONFIG_SMP
 #define cpu_relax()	__asm__ __volatile__ ("" : : : "memory")
-#else
-#define cpu_relax()	do { } while (0)
-#endif
 
 #define cpu_relax_lowlatency() cpu_relax()
 
@@ -77,7 +73,7 @@ struct task_struct;
  */
 #define TSK_K_ESP(tsk)		(tsk->thread.ksp)
 
-#define TSK_K_REG(tsk, off)	(*((unsigned int *)(TSK_K_ESP(tsk) + \
+#define TSK_K_REG(tsk, off)	(*((unsigned long *)(TSK_K_ESP(tsk) + \
 					sizeof(struct callee_regs) + off)))
 
 #define TSK_K_BLINK(tsk)	TSK_K_REG(tsk, 4)
@@ -100,29 +96,31 @@ extern unsigned int get_wchan(struct task_struct *p);
 
 #endif /* !__ASSEMBLY__ */
 
-/* Kernels Virtual memory area.
- * Unlike other architectures(MIPS, sh, cris ) ARC 700 does not have a
- * "kernel translated" region (like KSEG2 in MIPS). So we use a upper part
- * of the translated bottom 2GB for kernel virtual memory and protect
- * these pages from user accesses by disabling Ru, Eu and Wu.
+/*
+ * System Memory Map on ARC
+ *
+ * ---------------------------- (lower 2G, Translated) -------------------------
+ * 0x0000_0000		0x5FFF_FFFF	(user vaddr: TASK_SIZE)
+ * 0x6000_0000		0x6FFF_FFFF	(reserved gutter between U/K)
+ * 0x7000_0000		0x7FFF_FFFF	(kvaddr: vmalloc/modules/pkmap..)
+ *
+ * PAGE_OFFSET ---------------- (Upper 2G, Untranslated) -----------------------
+ * 0x8000_0000		0xBFFF_FFFF	(kernel direct mapped)
+ * 0xC000_0000		0xFFFF_FFFF	(peripheral uncached space)
+ * -----------------------------------------------------------------------------
  */
-#define VMALLOC_SIZE	(0x10000000)	/* 256M */
-#define VMALLOC_START	(PAGE_OFFSET - VMALLOC_SIZE)
-#define VMALLOC_END	(PAGE_OFFSET)
+#define VMALLOC_START	0x70000000
 
-/* Most of the architectures seem to be keeping some kind of padding between
- * userspace TASK_SIZE and PAGE_OFFSET. i.e TASK_SIZE != PAGE_OFFSET.
+/*
+ * 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
 
-/* User address space:
- * On ARC700, CPU allows the entire lower half of 32 bit address space to be
- * translated. Thus potentially 2G (0:0x7FFF_FFFF) could be User vaddr space.
- * However we steal 256M for kernel addr (0x7000_0000:0x7FFF_FFFF) and another
- * 256M (0x6000_0000:0x6FFF_FFFF) is gutter between user/kernel spaces
- * Thus total User vaddr space is (0:0x5FFF_FFFF)
- */
-#define TASK_SIZE	(PAGE_OFFSET - VMALLOC_SIZE - USER_KERNEL_GUTTER)
+#define TASK_SIZE	(VMALLOC_START - USER_KERNEL_GUTTER)
 
 #define STACK_TOP       TASK_SIZE
 #define STACK_TOP_MAX   STACK_TOP
diff --git a/kernel/arch/arc/include/asm/ptrace.h b/kernel/arch/arc/include/asm/ptrace.h
index 2a58af7a2..69095da1f 100644
--- a/kernel/arch/arc/include/asm/ptrace.h
+++ b/kernel/arch/arc/include/asm/ptrace.h
@@ -16,23 +16,24 @@
 
 /* THE pt_regs: Defines how regs are saved during entry into kernel */
 
+#ifdef CONFIG_ISA_ARCOMPACT
 struct pt_regs {
 
 	/* Real registers */
-	long bta;	/* bta_l1, bta_l2, erbta */
+	unsigned long bta;	/* bta_l1, bta_l2, erbta */
 
-	long lp_start, lp_end, lp_count;
+	unsigned long lp_start, lp_end, lp_count;
 
-	long status32;	/* status32_l1, status32_l2, erstatus */
-	long ret;	/* ilink1, ilink2 or eret */
-	long blink;
-	long fp;
-	long r26;	/* gp */
+	unsigned long status32;	/* status32_l1, status32_l2, erstatus */
+	unsigned long ret;	/* ilink1, ilink2 or eret */
+	unsigned long blink;
+	unsigned long fp;
+	unsigned long r26;	/* gp */
 
-	long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
+	unsigned long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
 
-	long sp;	/* user/kernel sp depending on where we came from  */
-	long orig_r0;
+	unsigned long sp;	/* User/Kernel depending on where we came from */
+	unsigned long orig_r0;
 
 	/*
 	 * To distinguish bet excp, syscall, irq
@@ -54,16 +55,58 @@ struct pt_regs {
 		unsigned long event;
 	};
 
-	long user_r25;
+	unsigned long user_r25;
 };
+#else
+
+struct pt_regs {
+
+	unsigned long orig_r0;
+
+	union {
+		struct {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+			unsigned long state:8, ecr_vec:8,
+				      ecr_cause:8, ecr_param:8;
+#else
+			unsigned long ecr_param:8, ecr_cause:8,
+				      ecr_vec:8, state:8;
+#endif
+		};
+		unsigned long event;
+	};
+
+	unsigned long bta;	/* bta_l1, bta_l2, erbta */
+
+	unsigned long user_r25;
+
+	unsigned long r26;	/* gp */
+	unsigned long fp;
+	unsigned long sp;	/* user/kernel sp depending on where we came from  */
+
+	unsigned long r12;
+
+	/*------- Below list auto saved by h/w -----------*/
+	unsigned long r0, r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11;
+
+	unsigned long blink;
+	unsigned long lp_end, lp_start, lp_count;
+
+	unsigned long ei, ldi, jli;
+
+	unsigned long ret;
+	unsigned long status32;
+};
+
+#endif
 
 /* Callee saved registers - need to be saved only when you are scheduled out */
 
 struct callee_regs {
-	long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13;
+	unsigned long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13;
 };
 
-#define instruction_pointer(regs)	(unsigned long)((regs)->ret)
+#define instruction_pointer(regs)	((regs)->ret)
 #define profile_pc(regs)		instruction_pointer(regs)
 
 /* return 1 if user mode or 0 if kernel mode */
@@ -99,7 +142,7 @@ struct callee_regs {
 
 static inline long regs_return_value(struct pt_regs *regs)
 {
-	return regs->r0;
+	return (long)regs->r0;
 }
 
 #endif /* !__ASSEMBLY__ */
diff --git a/kernel/arch/arc/include/asm/setup.h b/kernel/arch/arc/include/asm/setup.h
index 6e3ef5ba4..307846691 100644
--- a/kernel/arch/arc/include/asm/setup.h
+++ b/kernel/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/kernel/arch/arc/include/asm/smp.h b/kernel/arch/arc/include/asm/smp.h
index 3845b9e94..991380438 100644
--- a/kernel/arch/arc/include/asm/smp.h
+++ b/kernel/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_per_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_per_cpu)(int cpu);
 	void		(*cpu_kick)(int cpu, unsigned long pc);
 	void		(*ipi_send)(int cpu);
 	void		(*ipi_clear)(int irq);
diff --git a/kernel/arch/arc/include/asm/spinlock.h b/kernel/arch/arc/include/asm/spinlock.h
index e1651df6a..db8c59d1e 100644
--- a/kernel/arch/arc/include/asm/spinlock.h
+++ b/kernel/arch/arc/include/asm/spinlock.h
@@ -18,9 +18,518 @@
 #define arch_spin_unlock_wait(x) \
 	do { while (arch_spin_is_locked(x)) cpu_relax(); } while (0)
 
+#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 tmp = __ARCH_SPIN_LOCK_LOCKED__;
+	unsigned int val;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[slock]]	\n"
+	"	breq	%[val], %[LOCKED], 1b	\n"	/* spin while LOCKED */
+	"	scond	%[LOCKED], [%[slock]]	\n"	/* acquire */
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [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;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[slock]]	\n"
+	"	breq	%[val], %[LOCKED], 4f	\n"	/* already LOCKED, just bail */
+	"	scond	%[LOCKED], [%[slock]]	\n"	/* acquire */
+	"	bnz	1b			\n"
+	"	mov	%[got_it], 1		\n"
+	"4:					\n"
+	"					\n"
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	: [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;
+
+	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__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brls	%[val], %[WR_LOCKED], 1b\n"	/* <= 0: spin while write locked */
+	"	sub	%[val], %[val], 1	\n"	/* reader lock */
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [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;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"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"
+	"	bnz	1b			\n"	/* retry if collided with someone */
+	"	mov	%[got_it], 1		\n"
+	"					\n"
+	"4: ; --- done ---			\n"
+
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	: [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;
+
+	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__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brne	%[val], %[UNLOCKED], 1b	\n"	/* while !UNLOCKED spin */
+	"	mov	%[val], %[WR_LOCKED]	\n"
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [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;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brne	%[val], %[UNLOCKED], 4f	\n"	/* !UNLOCKED, bail */
+	"	mov	%[val], %[WR_LOCKED]	\n"
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"	/* retry if collided with someone */
+	"	mov	%[got_it], 1		\n"
+	"					\n"
+	"4: ; --- done ---			\n"
+
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	: [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)
+{
+	smp_mb();
+
+	rw->counter = __ARCH_RW_LOCK_UNLOCKED__;
+
+	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)
+{
+	unsigned int val = __ARCH_SPIN_LOCK_LOCKED__;
 
 	/*
 	 * This smp_mb() is technically superfluous, we only need the one
@@ -33,7 +542,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 	__asm__ __volatile__(
 	"1:	ex  %0, [%1]		\n"
 	"	breq  %0, %2, 1b	\n"
-	: "+&r" (tmp)
+	: "+&r" (val)
 	: "r"(&(lock->slock)), "ir"(__ARCH_SPIN_LOCK_LOCKED__)
 	: "memory");
 
@@ -48,26 +557,27 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 	smp_mb();
 }
 
+/* 1 - lock taken successfully */
 static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
-	unsigned int tmp = __ARCH_SPIN_LOCK_LOCKED__;
+	unsigned int val = __ARCH_SPIN_LOCK_LOCKED__;
 
 	smp_mb();
 
 	__asm__ __volatile__(
 	"1:	ex  %0, [%1]		\n"
-	: "+r" (tmp)
+	: "+r" (val)
 	: "r"(&(lock->slock))
 	: "memory");
 
 	smp_mb();
 
-	return (tmp == __ARCH_SPIN_LOCK_UNLOCKED__);
+	return (val == __ARCH_SPIN_LOCK_UNLOCKED__);
 }
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
-	unsigned int tmp = __ARCH_SPIN_LOCK_UNLOCKED__;
+	unsigned int val = __ARCH_SPIN_LOCK_UNLOCKED__;
 
 	/*
 	 * RELEASE barrier: given the instructions avail on ARCv2, full barrier
@@ -77,7 +587,7 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 
 	__asm__ __volatile__(
 	"	ex  %0, [%1]		\n"
-	: "+r" (tmp)
+	: "+r" (val)
 	: "r"(&(lock->slock))
 	: "memory");
 
@@ -90,19 +600,12 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 
 /*
  * Read-write spinlocks, allowing multiple readers but only one writer.
+ * Unfair locking as Writers could be starved indefinitely by Reader(s)
  *
  * The spinlock itself is contained in @counter and access to it is
  * serialized with @lock_mutex.
- *
- * Unfair locking as Writers could be starved indefinitely by Reader(s)
  */
 
-/* Would read_trylock() succeed? */
-#define arch_read_can_lock(x)	((x)->counter > 0)
-
-/* Would write_trylock() succeed? */
-#define arch_write_can_lock(x)	((x)->counter == __ARCH_RW_LOCK_UNLOCKED__)
-
 /* 1 - lock taken successfully */
 static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
@@ -173,6 +676,11 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 	arch_spin_unlock(&(rw->lock_mutex));
 }
 
+#endif
+
+#define arch_read_can_lock(x)	((x)->counter > 0)
+#define arch_write_can_lock(x)	((x)->counter == __ARCH_RW_LOCK_UNLOCKED__)
+
 #define arch_read_lock_flags(lock, flags)	arch_read_lock(lock)
 #define arch_write_lock_flags(lock, flags)	arch_write_lock(lock)
 
diff --git a/kernel/arch/arc/include/asm/spinlock_types.h b/kernel/arch/arc/include/asm/spinlock_types.h
index 662627ced..4e1ef5f65 100644
--- a/kernel/arch/arc/include/asm/spinlock_types.h
+++ b/kernel/arch/arc/include/asm/spinlock_types.h
@@ -26,7 +26,9 @@ typedef struct {
  */
 typedef struct {
 	volatile unsigned int	counter;
+#ifndef CONFIG_ARC_HAS_LLSC
 	arch_spinlock_t		lock_mutex;
+#endif
 } arch_rwlock_t;
 
 #define __ARCH_RW_LOCK_UNLOCKED__	0x01000000
diff --git a/kernel/arch/arc/include/asm/thread_info.h b/kernel/arch/arc/include/asm/thread_info.h
index aca0d5a45..3af674556 100644
--- a/kernel/arch/arc/include/asm/thread_info.h
+++ b/kernel/arch/arc/include/asm/thread_info.h
@@ -25,6 +25,7 @@
 #endif
 
 #define THREAD_SIZE     (PAGE_SIZE << THREAD_SIZE_ORDER)
+#define THREAD_SHIFT	(PAGE_SHIFT << THREAD_SIZE_ORDER)
 
 #ifndef __ASSEMBLY__
 
diff --git a/kernel/arch/arc/include/asm/tlbflush.h b/kernel/arch/arc/include/asm/tlbflush.h
index 71c7b2e4b..1fe9c8c80 100644
--- a/kernel/arch/arc/include/asm/tlbflush.h
+++ b/kernel/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/kernel/arch/arc/include/asm/uaccess.h b/kernel/arch/arc/include/asm/uaccess.h
index 30c9baffa..d1da6032b 100644
--- a/kernel/arch/arc/include/asm/uaccess.h
+++ b/kernel/arch/arc/include/asm/uaccess.h
@@ -659,31 +659,30 @@ static inline unsigned long __arc_clear_user(void __user *to, unsigned long n)
 static inline long
 __arc_strncpy_from_user(char *dst, const char __user *src, long count)
 {
-	long res = count;
+	long res = 0;
 	char val;
-	unsigned int hw_count;
 
 	if (count == 0)
 		return 0;
 
 	__asm__ __volatile__(
-	"	lp 2f		\n"
+	"	lp	3f			\n"
 	"1:	ldb.ab  %3, [%2, 1]		\n"
-	"	breq.d  %3, 0, 2f		\n"
+	"	breq.d	%3, 0, 3f               \n"
 	"	stb.ab  %3, [%1, 1]		\n"
-	"2:	sub %0, %6, %4			\n"
-	"3:	;nop				\n"
+	"	add	%0, %0, 1	# Num of NON NULL bytes copied	\n"
+	"3:								\n"
 	"	.section .fixup, \"ax\"		\n"
 	"	.align 4			\n"
-	"4:	mov %0, %5			\n"
+	"4:	mov %0, %4		# sets @res as -EFAULT	\n"
 	"	j   3b				\n"
 	"	.previous			\n"
 	"	.section __ex_table, \"a\"	\n"
 	"	.align 4			\n"
 	"	.word   1b, 4b			\n"
 	"	.previous			\n"
-	: "=r"(res), "+r"(dst), "+r"(src), "=&r"(val), "=l"(hw_count)
-	: "g"(-EFAULT), "ir"(count), "4"(count)	/* this "4" seeds lp_count */
+	: "+r"(res), "+r"(dst), "+r"(src), "=r"(val)
+	: "g"(-EFAULT), "l"(count)
 	: "memory");
 
 	return res;
diff --git a/kernel/arch/arc/include/asm/unwind.h b/kernel/arch/arc/include/asm/unwind.h
index 7ca628b6e..c11a25bb8 100644
--- a/kernel/arch/arc/include/asm/unwind.h
+++ b/kernel/arch/arc/include/asm/unwind.h
@@ -112,7 +112,6 @@ struct unwind_frame_info {
 
 extern int arc_unwind(struct unwind_frame_info *frame);
 extern void arc_unwind_init(void);
-extern void arc_unwind_setup(void);
 extern void *unwind_add_table(struct module *module, const void *table_start,
 			      unsigned long table_size);
 extern void unwind_remove_table(void *handle, int init_only);
@@ -152,9 +151,6 @@ static inline void arc_unwind_init(void)
 {
 }
 
-static inline void arc_unwind_setup(void)
-{
-}
 #define unwind_add_table(a, b, c)
 #define unwind_remove_table(a, b)
 
diff --git a/kernel/arch/arc/include/uapi/asm/page.h b/kernel/arch/arc/include/uapi/asm/page.h
index e5d41e082..059aff38f 100644
--- a/kernel/arch/arc/include/uapi/asm/page.h
+++ b/kernel/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))
 
diff --git a/kernel/arch/arc/include/uapi/asm/ptrace.h b/kernel/arch/arc/include/uapi/asm/ptrace.h
index 76a7739aa..0b3ef63d4 100644
--- a/kernel/arch/arc/include/uapi/asm/ptrace.h
+++ b/kernel/arch/arc/include/uapi/asm/ptrace.h
@@ -32,20 +32,20 @@
 */
 struct user_regs_struct {
 
-	long pad;
+	unsigned long pad;
 	struct {
-		long bta, lp_start, lp_end, lp_count;
-		long status32, ret, blink, fp, gp;
-		long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
-		long sp;
+		unsigned long bta, lp_start, lp_end, lp_count;
+		unsigned long status32, ret, blink, fp, gp;
+		unsigned long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
+		unsigned long sp;
 	} scratch;
-	long pad2;
+	unsigned long pad2;
 	struct {
-		long r25, r24, r23, r22, r21, r20;
-		long r19, r18, r17, r16, r15, r14, r13;
+		unsigned long r25, r24, r23, r22, r21, r20;
+		unsigned long r19, r18, r17, r16, r15, r14, r13;
 	} callee;
-	long efa;	/* break pt addr, for break points in delay slots */
-	long stop_pc;	/* give dbg stop_pc after ensuring brkpt trap */
+	unsigned long efa;	/* break pt addr, for break points in delay slots */
+	unsigned long stop_pc;	/* give dbg stop_pc after ensuring brkpt trap */
 };
 #endif /* !__ASSEMBLY__ */