diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index ecd12379e2cd..bd204bfa29ed 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -41,6 +41,8 @@ config ARC
 	select PERF_USE_VMALLOC
 	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_GENERIC_DMA_COHERENT
+	select HAVE_KERNEL_GZIP
+	select HAVE_KERNEL_LZMA
 
 config MIGHT_HAVE_PCI
 	bool
@@ -186,14 +188,6 @@ if SMP
 config ARC_HAS_COH_CACHES
 	def_bool n
 
-config ARC_MCIP
-	bool "ARConnect Multicore IP (MCIP) Support "
-	depends on ISA_ARCV2
-	help
-	  This IP block enables SMP in ARC-HS38 cores.
-	  It provides for cross-core interrupts, multi-core debug
-	  hardware semaphores, shared memory,....
-
 config NR_CPUS
 	int "Maximum number of CPUs (2-4096)"
 	range 2 4096
@@ -211,6 +205,15 @@ config ARC_SMP_HALT_ON_RESET
 
 endif	#SMP
 
+config ARC_MCIP
+	bool "ARConnect Multicore IP (MCIP) Support "
+	depends on ISA_ARCV2
+	default y if SMP
+	help
+	  This IP block enables SMP in ARC-HS38 cores.
+	  It provides for cross-core interrupts, multi-core debug
+	  hardware semaphores, shared memory,....
+
 menuconfig ARC_CACHE
 	bool "Enable Cache Support"
 	default y
@@ -537,14 +540,6 @@ config ARC_DBG_TLB_PARANOIA
 	bool "Paranoia Checks in Low Level TLB Handlers"
 	default n
 
-config ARC_DBG_TLB_MISS_COUNT
-	bool "Profile TLB Misses"
-	default n
-	select DEBUG_FS
-	help
-	  Counts number of I and D TLB Misses and exports them via Debugfs
-	  The counters can be cleared via Debugfs as well
-
 endif
 
 config ARC_UBOOT_SUPPORT
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index aa82d13d4213..864adad52280 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -50,9 +50,6 @@ atleast_gcc44 :=  $(call cc-ifversion, -ge, 0404, y)
 
 cflags-$(atleast_gcc44)			+= -fsection-anchors
 
-cflags-$(CONFIG_ARC_HAS_LLSC)		+= -mlock
-cflags-$(CONFIG_ARC_HAS_SWAPE)		+= -mswape
-
 ifdef CONFIG_ISA_ARCV2
 
 ifndef CONFIG_ARC_HAS_LL64
diff --git a/arch/arc/boot/Makefile b/arch/arc/boot/Makefile
index e597cb34c16a..f94cf151e06a 100644
--- a/arch/arc/boot/Makefile
+++ b/arch/arc/boot/Makefile
@@ -14,9 +14,15 @@ UIMAGE_ENTRYADDR   = $(LINUX_START_TEXT)
 
 suffix-y := bin
 suffix-$(CONFIG_KERNEL_GZIP)	:= gz
+suffix-$(CONFIG_KERNEL_LZMA)	:= lzma
 
-targets += uImage uImage.bin uImage.gz
-extra-y += vmlinux.bin vmlinux.bin.gz
+targets += uImage
+targets += uImage.bin
+targets += uImage.gz
+targets += uImage.lzma
+extra-y += vmlinux.bin
+extra-y += vmlinux.bin.gz
+extra-y += vmlinux.bin.lzma
 
 $(obj)/vmlinux.bin: vmlinux FORCE
 	$(call if_changed,objcopy)
@@ -24,12 +30,18 @@ $(obj)/vmlinux.bin: vmlinux FORCE
 $(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
 	$(call if_changed,gzip)
 
+$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin FORCE
+	$(call if_changed,lzma)
+
 $(obj)/uImage.bin: $(obj)/vmlinux.bin FORCE
 	$(call if_changed,uimage,none)
 
 $(obj)/uImage.gz: $(obj)/vmlinux.bin.gz FORCE
 	$(call if_changed,uimage,gzip)
 
+$(obj)/uImage.lzma: $(obj)/vmlinux.bin.lzma FORCE
+	$(call if_changed,uimage,lzma)
+
 $(obj)/uImage: $(obj)/uImage.$(suffix-y)
 	@ln -sf $(notdir $<) $@
 	@echo '  Image $@ is ready'
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index db25c65155cb..7f3f9f63708c 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -349,10 +349,11 @@ struct cpuinfo_arc {
 	struct cpuinfo_arc_bpu bpu;
 	struct bcr_identity core;
 	struct bcr_isa isa;
+	const char *details, *name;
 	unsigned int vec_base;
 	struct cpuinfo_arc_ccm iccm, dccm;
 	struct {
-		unsigned int swap:1, norm:1, minmax:1, barrel:1, crc:1, pad1:3,
+		unsigned int swap:1, norm:1, minmax:1, barrel:1, crc:1, swape:1, pad1:2,
 			     fpu_sp:1, fpu_dp:1, pad2:6,
 			     debug:1, ap:1, smart:1, rtt:1, pad3:4,
 			     timer0:1, timer1:1, rtc:1, gfrc:1, pad4:4;
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index fb781e34f322..b3410ff6a62d 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -53,7 +53,7 @@ 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;
+extern int ioc_enable;
 extern unsigned long perip_base, perip_end;
 
 #endif	/* !__ASSEMBLY__ */
diff --git a/arch/arc/include/asm/elf.h b/arch/arc/include/asm/elf.h
index 7096f97a1434..aa2d6da9d187 100644
--- a/arch/arc/include/asm/elf.h
+++ b/arch/arc/include/asm/elf.h
@@ -54,7 +54,7 @@ extern int elf_check_arch(const struct elf32_hdr *);
  * the loader.  We need to make sure that it is out of the way of the program
  * that it will "exec", and that there is sufficient room for the brk.
  */
-#define ELF_ET_DYN_BASE		(2 * TASK_SIZE / 3)
+#define ELF_ET_DYN_BASE		(2UL * TASK_SIZE / 3)
 
 /*
  * When the program starts, a1 contains a pointer to a function to be
diff --git a/arch/arc/include/asm/mcip.h b/arch/arc/include/asm/mcip.h
index 847e3bbe387f..c8fbe4114bad 100644
--- a/arch/arc/include/asm/mcip.h
+++ b/arch/arc/include/asm/mcip.h
@@ -55,6 +55,22 @@ struct mcip_cmd {
 #define IDU_M_DISTRI_DEST		0x2
 };
 
+struct mcip_bcr {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+		unsigned int pad3:8,
+			     idu:1, llm:1, num_cores:6,
+			     iocoh:1,  gfrc:1, dbg:1, pad2:1,
+			     msg:1, sem:1, ipi:1, pad:1,
+			     ver:8;
+#else
+		unsigned int ver:8,
+			     pad:1, ipi:1, sem:1, msg:1,
+			     pad2:1, dbg:1, gfrc:1, iocoh:1,
+			     num_cores:6, llm:1, idu:1,
+			     pad3:8;
+#endif
+};
+
 /*
  * MCIP programming model
  *
diff --git a/arch/arc/include/asm/module.h b/arch/arc/include/asm/module.h
index 518222bb3f8e..6e91d8b339c3 100644
--- a/arch/arc/include/asm/module.h
+++ b/arch/arc/include/asm/module.h
@@ -18,6 +18,7 @@
 struct mod_arch_specific {
 	void *unw_info;
 	int unw_sec_idx;
+	const char *secstr;
 };
 #endif
 
diff --git a/arch/arc/include/asm/setup.h b/arch/arc/include/asm/setup.h
index 48b37c693db3..cb954cdab070 100644
--- a/arch/arc/include/asm/setup.h
+++ b/arch/arc/include/asm/setup.h
@@ -27,11 +27,6 @@ struct id_to_str {
 	const char *str;
 };
 
-struct cpuinfo_data {
-	struct id_to_str info;
-	int up_range;
-};
-
 extern int root_mountflags, end_mem;
 
 void setup_processor(void);
@@ -43,5 +38,6 @@ void __init setup_arch_memory(void);
 #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))
+#define IS_AVAIL3(v, v2, s)	IS_AVAIL1(v, s), IS_AVAIL1(v, IS_DISABLED_RUN(v2))
 
 #endif /* __ASMARC_SETUP_H */
diff --git a/arch/arc/include/asm/syscalls.h b/arch/arc/include/asm/syscalls.h
index e56f9fcc5581..772b67ca56e7 100644
--- a/arch/arc/include/asm/syscalls.h
+++ b/arch/arc/include/asm/syscalls.h
@@ -17,6 +17,7 @@ int sys_clone_wrapper(int, int, int, int, int);
 int sys_cacheflush(uint32_t, uint32_t uint32_t);
 int sys_arc_settls(void *);
 int sys_arc_gettls(void);
+int sys_arc_usr_cmpxchg(int *, int, int);
 
 #include <asm-generic/syscalls.h>
 
diff --git a/arch/arc/include/uapi/asm/unistd.h b/arch/arc/include/uapi/asm/unistd.h
index 41fa2ec9e02c..9a34136d84b2 100644
--- a/arch/arc/include/uapi/asm/unistd.h
+++ b/arch/arc/include/uapi/asm/unistd.h
@@ -27,18 +27,19 @@
 
 #define NR_syscalls	__NR_syscalls
 
+/* Generic syscall (fs/filesystems.c - lost in asm-generic/unistd.h */
+#define __NR_sysfs		(__NR_arch_specific_syscall + 3)
+
 /* ARC specific syscall */
 #define __NR_cacheflush		(__NR_arch_specific_syscall + 0)
 #define __NR_arc_settls		(__NR_arch_specific_syscall + 1)
 #define __NR_arc_gettls		(__NR_arch_specific_syscall + 2)
+#define __NR_arc_usr_cmpxchg	(__NR_arch_specific_syscall + 4)
 
 __SYSCALL(__NR_cacheflush, sys_cacheflush)
 __SYSCALL(__NR_arc_settls, sys_arc_settls)
 __SYSCALL(__NR_arc_gettls, sys_arc_gettls)
-
-
-/* Generic syscall (fs/filesystems.c - lost in asm-generic/unistd.h */
-#define __NR_sysfs		(__NR_arch_specific_syscall + 3)
+__SYSCALL(__NR_arc_usr_cmpxchg, sys_arc_usr_cmpxchg)
 __SYSCALL(__NR_sysfs, sys_sysfs)
 
 #undef __SYSCALL
diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c
index 72f9179b1a24..c424d5abc318 100644
--- a/arch/arc/kernel/mcip.c
+++ b/arch/arc/kernel/mcip.c
@@ -15,11 +15,12 @@
 #include <asm/mcip.h>
 #include <asm/setup.h>
 
-static char smp_cpuinfo_buf[128];
-static int idu_detected;
-
 static DEFINE_RAW_SPINLOCK(mcip_lock);
 
+#ifdef CONFIG_SMP
+
+static char smp_cpuinfo_buf[128];
+
 static void mcip_setup_per_cpu(int cpu)
 {
 	smp_ipi_irq_setup(cpu, IPI_IRQ);
@@ -86,21 +87,7 @@ static void mcip_ipi_clear(int irq)
 
 static void mcip_probe_n_setup(void)
 {
-	struct mcip_bcr {
-#ifdef CONFIG_CPU_BIG_ENDIAN
-		unsigned int pad3:8,
-			     idu:1, llm:1, num_cores:6,
-			     iocoh:1,  gfrc:1, dbg:1, pad2:1,
-			     msg:1, sem:1, ipi:1, pad:1,
-			     ver:8;
-#else
-		unsigned int ver:8,
-			     pad:1, ipi:1, sem:1, msg:1,
-			     pad2:1, dbg:1, gfrc:1, iocoh:1,
-			     num_cores:6, llm:1, idu:1,
-			     pad3:8;
-#endif
-	} mp;
+	struct mcip_bcr mp;
 
 	READ_BCR(ARC_REG_MCIP_BCR, mp);
 
@@ -114,7 +101,6 @@ static void mcip_probe_n_setup(void)
 		IS_AVAIL1(mp.gfrc, "GFRC"));
 
 	cpuinfo_arc700[0].extn.gfrc = mp.gfrc;
-	idu_detected = mp.idu;
 
 	if (mp.dbg) {
 		__mcip_cmd_data(CMD_DEBUG_SET_SELECT, 0, 0xf);
@@ -130,6 +116,8 @@ struct plat_smp_ops plat_smp_ops = {
 	.ipi_clear	= mcip_ipi_clear,
 };
 
+#endif
+
 /***************************************************************************
  * ARCv2 Interrupt Distribution Unit (IDU)
  *
@@ -295,8 +283,11 @@ idu_of_init(struct device_node *intc, struct device_node *parent)
 	/* Read IDU BCR to confirm nr_irqs */
 	int nr_irqs = of_irq_count(intc);
 	int i, irq;
+	struct mcip_bcr mp;
 
-	if (!idu_detected)
+	READ_BCR(ARC_REG_MCIP_BCR, mp);
+
+	if (!mp.idu)
 		panic("IDU not detected, but DeviceTree using it");
 
 	pr_info("MCIP: IDU referenced from Devicetree %d irqs\n", nr_irqs);
diff --git a/arch/arc/kernel/module.c b/arch/arc/kernel/module.c
index 9a2849756022..42e964db2967 100644
--- a/arch/arc/kernel/module.c
+++ b/arch/arc/kernel/module.c
@@ -30,17 +30,9 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
 			      char *secstr, struct module *mod)
 {
 #ifdef CONFIG_ARC_DW2_UNWIND
-	int i;
-
 	mod->arch.unw_sec_idx = 0;
 	mod->arch.unw_info = NULL;
-
-	for (i = 1; i < hdr->e_shnum; i++) {
-		if (strcmp(secstr+sechdrs[i].sh_name, ".eh_frame") == 0) {
-			mod->arch.unw_sec_idx = i;
-			break;
-		}
-	}
+	mod->arch.secstr = secstr;
 #endif
 	return 0;
 }
@@ -59,29 +51,33 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 		       unsigned int relsec,	/* sec index for relo sec */
 		       struct module *module)
 {
-	int i, n;
+	int i, n, relo_type;
 	Elf32_Rela *rel_entry = (void *)sechdrs[relsec].sh_addr;
 	Elf32_Sym *sym_entry, *sym_sec;
-	Elf32_Addr relocation;
-	Elf32_Addr location;
-	Elf32_Addr sec_to_patch;
-	int relo_type;
+	Elf32_Addr relocation, location, tgt_addr;
+	unsigned int tgtsec;
 
-	sec_to_patch = sechdrs[sechdrs[relsec].sh_info].sh_addr;
+	/*
+	 * @relsec has relocations e.g. .rela.init.text
+	 * @tgtsec is section to patch e.g. .init.text
+	 */
+	tgtsec = sechdrs[relsec].sh_info;
+	tgt_addr = sechdrs[tgtsec].sh_addr;
 	sym_sec = (Elf32_Sym *) sechdrs[symindex].sh_addr;
 	n = sechdrs[relsec].sh_size / sizeof(*rel_entry);
 
-	pr_debug("\n========== Module Sym reloc ===========================\n");
-	pr_debug("Section to fixup %x\n", sec_to_patch);
+	pr_debug("\nSection to fixup %s @%x\n",
+		 module->arch.secstr + sechdrs[tgtsec].sh_name, tgt_addr);
 	pr_debug("=========================================================\n");
-	pr_debug("rela->r_off | rela->addend | sym->st_value | ADDR | VALUE\n");
+	pr_debug("r_off\tr_add\tst_value ADDRESS  VALUE\n");
 	pr_debug("=========================================================\n");
 
 	/* Loop thru entries in relocation section */
 	for (i = 0; i < n; i++) {
+		const char *s;
 
 		/* This is where to make the change */
-		location = sec_to_patch + rel_entry[i].r_offset;
+		location = tgt_addr + rel_entry[i].r_offset;
 
 		/* This is the symbol it is referring to.  Note that all
 		   undefined symbols have been resolved.  */
@@ -89,10 +85,15 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 
 		relocation = sym_entry->st_value + rel_entry[i].r_addend;
 
-		pr_debug("\t%x\t\t%x\t\t%x  %x %x [%s]\n",
-			rel_entry[i].r_offset, rel_entry[i].r_addend,
-			sym_entry->st_value, location, relocation,
-			strtab + sym_entry->st_name);
+		if (sym_entry->st_name == 0 && ELF_ST_TYPE (sym_entry->st_info) == STT_SECTION) {
+			s = module->arch.secstr + sechdrs[sym_entry->st_shndx].sh_name;
+		} else {
+			s = strtab + sym_entry->st_name;
+		}
+
+		pr_debug("   %x\t%x\t%x %x %x [%s]\n",
+			 rel_entry[i].r_offset, rel_entry[i].r_addend,
+			 sym_entry->st_value, location, relocation, s);
 
 		/* This assumes modules are built with -mlong-calls
 		 * so any branches/jumps are absolute 32 bit jmps
@@ -111,6 +112,10 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 			goto relo_err;
 
 	}
+
+	if (strcmp(module->arch.secstr+sechdrs[tgtsec].sh_name, ".eh_frame") == 0)
+		module->arch.unw_sec_idx = tgtsec;
+
 	return 0;
 
 relo_err:
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index be1972bd2729..59aa43cb146e 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -41,6 +41,39 @@ SYSCALL_DEFINE0(arc_gettls)
 	return task_thread_info(current)->thr_ptr;
 }
 
+SYSCALL_DEFINE3(arc_usr_cmpxchg, int *, uaddr, int, expected, int, new)
+{
+	int uval;
+	int ret;
+
+	/*
+	 * This is only for old cores lacking LLOCK/SCOND, which by defintion
+	 * can't possibly be SMP. Thus doesn't need to be SMP safe.
+	 * And this also helps reduce the overhead for serializing in
+	 * the UP case
+	 */
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_SMP));
+
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+		return -EFAULT;
+
+	preempt_disable();
+
+	ret = __get_user(uval, uaddr);
+	if (ret)
+		goto done;
+
+	if (uval != expected)
+		ret = -EAGAIN;
+	else
+		ret = __put_user(new, uaddr);
+
+done:
+	preempt_enable();
+
+	return ret;
+}
+
 void arch_cpu_idle(void)
 {
 	/* sleep, but enable all interrupts before committing */
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index 3df7f9c72f42..0385df77a697 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -40,6 +40,29 @@ struct task_struct *_current_task[NR_CPUS];	/* For stack switching */
 
 struct cpuinfo_arc cpuinfo_arc700[NR_CPUS];
 
+static const struct id_to_str arc_cpu_rel[] = {
+#ifdef CONFIG_ISA_ARCOMPACT
+	{ 0x34, "R4.10"},
+	{ 0x35, "R4.11"},
+#else
+	{ 0x51, "R2.0" },
+	{ 0x52, "R2.1" },
+	{ 0x53, "R3.0" },
+#endif
+	{ 0x00, NULL   }
+};
+
+static const struct id_to_str arc_cpu_nm[] = {
+#ifdef CONFIG_ISA_ARCOMPACT
+	{ 0x20, "ARC 600"   },
+	{ 0x30, "ARC 770"   },  /* 750 identified seperately */
+#else
+	{ 0x40, "ARC EM"  },
+	{ 0x50, "ARC HS38"  },
+#endif
+	{ 0x00, "Unknown"   }
+};
+
 static void read_decode_ccm_bcr(struct cpuinfo_arc *cpu)
 {
 	if (is_isa_arcompact()) {
@@ -92,11 +115,26 @@ static void read_arc_build_cfg_regs(void)
 	struct bcr_timer timer;
 	struct bcr_generic bcr;
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
+	const struct id_to_str *tbl;
+
 	FIX_PTR(cpu);
 
 	READ_BCR(AUX_IDENTITY, cpu->core);
 	READ_BCR(ARC_REG_ISA_CFG_BCR, cpu->isa);
 
+	for (tbl = &arc_cpu_rel[0]; tbl->id != 0; tbl++) {
+		if (cpu->core.family == tbl->id) {
+			cpu->details = tbl->str;
+			break;
+		}
+	}
+
+	for (tbl = &arc_cpu_nm[0]; tbl->id != 0; tbl++) {
+		if ((cpu->core.family & 0xF0) == tbl->id)
+			break;
+	}
+	cpu->name = tbl->str;
+
 	READ_BCR(ARC_REG_TIMERS_BCR, timer);
 	cpu->extn.timer0 = timer.t0;
 	cpu->extn.timer1 = timer.t1;
@@ -111,6 +149,9 @@ static void read_arc_build_cfg_regs(void)
 	cpu->extn.swap = read_aux_reg(ARC_REG_SWAP_BCR) ? 1 : 0;        /* 1,3 */
 	cpu->extn.crc = read_aux_reg(ARC_REG_CRC_BCR) ? 1 : 0;
 	cpu->extn.minmax = read_aux_reg(ARC_REG_MIXMAX_BCR) > 1 ? 1 : 0; /* 2 */
+	cpu->extn.swape = (cpu->core.family >= 0x34) ? 1 :
+				IS_ENABLED(CONFIG_ARC_HAS_SWAPE);
+
 	READ_BCR(ARC_REG_XY_MEM_BCR, cpu->extn_xymem);
 
 	/* Read CCM BCRs for boot reporting even if not enabled in Kconfig */
@@ -160,64 +201,38 @@ static void read_arc_build_cfg_regs(void)
 	cpu->extn.rtt = bcr.ver ? 1 : 0;
 
 	cpu->extn.debug = cpu->extn.ap | cpu->extn.smart | cpu->extn.rtt;
+
+	/* some hacks for lack of feature BCR info in old ARC700 cores */
+	if (is_isa_arcompact()) {
+		if (!cpu->isa.ver)	/* ISA BCR absent, use Kconfig info */
+			cpu->isa.atomic = IS_ENABLED(CONFIG_ARC_HAS_LLSC);
+		else
+			cpu->isa.atomic = cpu->isa.atomic1;
+
+		cpu->isa.be = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN);
+
+		 /* there's no direct way to distinguish 750 vs. 770 */
+		if (unlikely(cpu->core.family < 0x34 || cpu->mmu.ver < 3))
+			cpu->name = "ARC750";
+	}
 }
 
-static const struct cpuinfo_data arc_cpu_tbl[] = {
-#ifdef CONFIG_ISA_ARCOMPACT
-	{ {0x20, "ARC 600"      }, 0x2F},
-	{ {0x30, "ARC 700"      }, 0x33},
-	{ {0x34, "ARC 700 R4.10"}, 0x34},
-	{ {0x35, "ARC 700 R4.11"}, 0x35},
-#else
-	{ {0x50, "ARC HS38 R2.0"}, 0x51},
-	{ {0x52, "ARC HS38 R2.1"}, 0x52},
-	{ {0x53, "ARC HS38 R3.0"}, 0x53},
-#endif
-	{ {0x00, NULL		} }
-};
-
-
 static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 {
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[cpu_id];
 	struct bcr_identity *core = &cpu->core;
-	const struct cpuinfo_data *tbl;
-	char *isa_nm;
-	int i, be, atomic;
-	int n = 0;
+	int i, n = 0;
 
 	FIX_PTR(cpu);
 
-	if (is_isa_arcompact()) {
-		isa_nm = "ARCompact";
-		be = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN);
-
-		atomic = cpu->isa.atomic1;
-		if (!cpu->isa.ver)	/* ISA BCR absent, use Kconfig info */
-			atomic = IS_ENABLED(CONFIG_ARC_HAS_LLSC);
-	} else {
-		isa_nm = "ARCv2";
-		be = cpu->isa.be;
-		atomic = cpu->isa.atomic;
-	}
-
 	n += scnprintf(buf + n, len - n,
 		       "\nIDENTITY\t: ARCVER [%#02x] ARCNUM [%#02x] CHIPID [%#4x]\n",
 		       core->family, core->cpu_id, core->chip_id);
 
-	for (tbl = &arc_cpu_tbl[0]; tbl->info.id != 0; tbl++) {
-		if ((core->family >= tbl->info.id) &&
-		    (core->family <= tbl->up_range)) {
-			n += scnprintf(buf + n, len - n,
-				       "processor [%d]\t: %s (%s ISA) %s\n",
-				       cpu_id, tbl->info.str, isa_nm,
-				       IS_AVAIL1(be, "[Big-Endian]"));
-			break;
-		}
-	}
-
-	if (tbl->info.id == 0)
-		n += scnprintf(buf + n, len - n, "UNKNOWN ARC Processor\n");
+	n += scnprintf(buf + n, len - n, "processor [%d]\t: %s %s (%s ISA) %s\n",
+		       cpu_id, cpu->name, cpu->details,
+		       is_isa_arcompact() ? "ARCompact" : "ARCv2",
+		       IS_AVAIL1(cpu->isa.be, "[Big-Endian]"));
 
 	n += scnprintf(buf + n, len - n, "Timers\t\t: %s%s%s%s\nISA Extn\t: ",
 		       IS_AVAIL1(cpu->extn.timer0, "Timer0 "),
@@ -226,7 +241,7 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 				 CONFIG_ARC_HAS_RTC));
 
 	n += i = scnprintf(buf + n, len - n, "%s%s%s%s%s",
-			   IS_AVAIL2(atomic, "atomic ", CONFIG_ARC_HAS_LLSC),
+			   IS_AVAIL2(cpu->isa.atomic, "atomic ", CONFIG_ARC_HAS_LLSC),
 			   IS_AVAIL2(cpu->isa.ldd, "ll64 ", CONFIG_ARC_HAS_LL64),
 			   IS_AVAIL1(cpu->isa.unalign, "unalign (not used)"));
 
@@ -253,7 +268,7 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 		       IS_AVAIL1(cpu->extn.swap, "swap "),
 		       IS_AVAIL1(cpu->extn.minmax, "minmax "),
 		       IS_AVAIL1(cpu->extn.crc, "crc "),
-		       IS_AVAIL2(1, "swape", CONFIG_ARC_HAS_SWAPE));
+		       IS_AVAIL2(cpu->extn.swape, "swape", CONFIG_ARC_HAS_SWAPE));
 
 	if (cpu->bpu.ver)
 		n += scnprintf(buf + n, len - n,
@@ -272,9 +287,7 @@ static char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len)
 
 	FIX_PTR(cpu);
 
-	n += scnprintf(buf + n, len - n,
-		       "Vector Table\t: %#x\nPeripherals\t: %#lx:%#lx\n",
-		       cpu->vec_base, perip_base, perip_end);
+	n += scnprintf(buf + n, len - n, "Vector Table\t: %#x\n", cpu->vec_base);
 
 	if (cpu->extn.fpu_sp || cpu->extn.fpu_dp)
 		n += scnprintf(buf + n, len - n, "FPU\t\t: %s%s\n",
@@ -507,7 +520,7 @@ static void *c_start(struct seq_file *m, loff_t *pos)
 	 * way to pass it w/o having to kmalloc/free a 2 byte string.
 	 * Encode cpu-id as 0xFFcccc, which is decoded by show routine.
 	 */
-	return *pos < num_possible_cpus() ? cpu_to_ptr(*pos) : NULL;
+	return *pos < nr_cpu_ids ? cpu_to_ptr(*pos) : NULL;
 }
 
 static void *c_next(struct seq_file *m, void *v, loff_t *pos)
diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c
index 934150e7ac48..82f9bc819f4a 100644
--- a/arch/arc/kernel/troubleshoot.c
+++ b/arch/arc/kernel/troubleshoot.c
@@ -237,113 +237,3 @@ void show_kernel_fault_diag(const char *str, struct pt_regs *regs,
 	if (!user_mode(regs))
 		show_stacktrace(current, regs);
 }
-
-#ifdef CONFIG_DEBUG_FS
-
-#include <linux/module.h>
-#include <linux/fs.h>
-#include <linux/mount.h>
-#include <linux/pagemap.h>
-#include <linux/init.h>
-#include <linux/namei.h>
-#include <linux/debugfs.h>
-
-static struct dentry *test_dentry;
-static struct dentry *test_dir;
-static struct dentry *test_u32_dentry;
-
-static u32 clr_on_read = 1;
-
-#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
-u32 numitlb, numdtlb, num_pte_not_present;
-
-static int fill_display_data(char *kbuf)
-{
-	size_t num = 0;
-	num += sprintf(kbuf + num, "I-TLB Miss %x\n", numitlb);
-	num += sprintf(kbuf + num, "D-TLB Miss %x\n", numdtlb);
-	num += sprintf(kbuf + num, "PTE not present %x\n", num_pte_not_present);
-
-	if (clr_on_read)
-		numitlb = numdtlb = num_pte_not_present = 0;
-
-	return num;
-}
-
-static int tlb_stats_open(struct inode *inode, struct file *file)
-{
-	file->private_data = (void *)__get_free_page(GFP_KERNEL);
-	return 0;
-}
-
-/* called on user read(): display the counters */
-static ssize_t tlb_stats_output(struct file *file,	/* file descriptor */
-				char __user *user_buf,	/* user buffer */
-				size_t len,		/* length of buffer */
-				loff_t *offset)		/* offset in the file */
-{
-	size_t num;
-	char *kbuf = (char *)file->private_data;
-
-	/* All of the data can he shoved in one iteration */
-	if (*offset != 0)
-		return 0;
-
-	num = fill_display_data(kbuf);
-
-	/* simple_read_from_buffer() is helper for copy to user space
-	   It copies up to @2 (num) bytes from kernel buffer @4 (kbuf) at offset
-	   @3 (offset) into the user space address starting at @1 (user_buf).
-	   @5 (len) is max size of user buffer
-	 */
-	return simple_read_from_buffer(user_buf, num, offset, kbuf, len);
-}
-
-/* called on user write : clears the counters */
-static ssize_t tlb_stats_clear(struct file *file, const char __user *user_buf,
-			       size_t length, loff_t *offset)
-{
-	numitlb = numdtlb = num_pte_not_present = 0;
-	return length;
-}
-
-static int tlb_stats_close(struct inode *inode, struct file *file)
-{
-	free_page((unsigned long)(file->private_data));
-	return 0;
-}
-
-static const struct file_operations tlb_stats_file_ops = {
-	.read = tlb_stats_output,
-	.write = tlb_stats_clear,
-	.open = tlb_stats_open,
-	.release = tlb_stats_close
-};
-#endif
-
-static int __init arc_debugfs_init(void)
-{
-	test_dir = debugfs_create_dir("arc", NULL);
-
-#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
-	test_dentry = debugfs_create_file("tlb_stats", 0444, test_dir, NULL,
-					  &tlb_stats_file_ops);
-#endif
-
-	test_u32_dentry =
-	    debugfs_create_u32("clr_on_read", 0444, test_dir, &clr_on_read);
-
-	return 0;
-}
-
-module_init(arc_debugfs_init);
-
-static void __exit arc_debugfs_exit(void)
-{
-	debugfs_remove(test_u32_dentry);
-	debugfs_remove(test_dentry);
-	debugfs_remove(test_dir);
-}
-module_exit(arc_debugfs_exit);
-
-#endif
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index 97dddbefb86a..2b96cfc3be75 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -22,8 +22,8 @@
 #include <asm/setup.h>
 
 static int l2_line_sz;
-int ioc_exists;
-volatile int slc_enable = 1, ioc_enable = 1;
+static int ioc_exists;
+int slc_enable = 1, ioc_enable = 1;
 unsigned long perip_base = ARC_UNCACHED_ADDR_SPACE; /* legacy value for boot */
 unsigned long perip_end = 0xFFFFFFFF; /* legacy value */
 
@@ -53,18 +53,15 @@ char *arc_cache_mumbojumbo(int c, char *buf, int len)
 	PR_CACHE(&cpuinfo_arc700[c].icache, CONFIG_ARC_HAS_ICACHE, "I-Cache");
 	PR_CACHE(&cpuinfo_arc700[c].dcache, CONFIG_ARC_HAS_DCACHE, "D-Cache");
 
-	if (!is_isa_arcv2())
-                return buf;
-
 	p = &cpuinfo_arc700[c].slc;
 	if (p->ver)
 		n += scnprintf(buf + n, len - n,
 			       "SLC\t\t: %uK, %uB Line%s\n",
 			       p->sz_k, p->line_len, IS_USED_RUN(slc_enable));
 
-	if (ioc_exists)
-		n += scnprintf(buf + n, len - n, "IOC\t\t:%s\n",
-				IS_DISABLED_RUN(ioc_enable));
+	n += scnprintf(buf + n, len - n, "Peripherals\t: %#lx%s%s\n",
+		       perip_base,
+		       IS_AVAIL3(ioc_exists, ioc_enable, ", IO-Coherency "));
 
 	return buf;
 }
@@ -113,8 +110,10 @@ static void read_decode_cache_bcr_arcv2(int cpu)
 	}
 
 	READ_BCR(ARC_REG_CLUSTER_BCR, cbcr);
-	if (cbcr.c && ioc_enable)
+	if (cbcr.c)
 		ioc_exists = 1;
+	else
+		ioc_enable = 0;
 
 	/* HS 2.0 didn't have AUX_VOL */
 	if (cpuinfo_arc700[cpu].core.family > 0x51) {
@@ -1002,7 +1001,7 @@ void arc_cache_init(void)
 			read_aux_reg(ARC_REG_SLC_CTRL) | SLC_CTRL_DISABLE);
 	}
 
-	if (is_isa_arcv2() && ioc_exists) {
+	if (is_isa_arcv2() && ioc_enable) {
 		/* IO coherency base - 0x8z */
 		write_aux_reg(ARC_REG_IO_COH_AP0_BASE, 0x80000);
 		/* IO coherency aperture size - 512Mb: 0x8z-0xAz */
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 20afc65e22dc..60aab5a7522b 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -45,7 +45,7 @@ static void *arc_dma_alloc(struct device *dev, size_t size,
 	 *   -For coherent data, Read/Write to buffers terminate early in cache
 	 *   (vs. always going to memory - thus are faster)
 	 */
-	if ((is_isa_arcv2() && ioc_exists) ||
+	if ((is_isa_arcv2() && ioc_enable) ||
 	    (attrs & DMA_ATTR_NON_CONSISTENT))
 		need_coh = 0;
 
@@ -97,7 +97,7 @@ static void arc_dma_free(struct device *dev, size_t size, void *vaddr,
 	int is_non_coh = 1;
 
 	is_non_coh = (attrs & DMA_ATTR_NON_CONSISTENT) ||
-			(is_isa_arcv2() && ioc_exists);
+			(is_isa_arcv2() && ioc_enable);
 
 	if (PageHighMem(page) || !is_non_coh)
 		iounmap((void __force __iomem *)vaddr);
diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c
index ec868a9081a1..bdb295e09160 100644
--- a/arch/arc/mm/tlb.c
+++ b/arch/arc/mm/tlb.c
@@ -793,16 +793,16 @@ char *arc_mmu_mumbojumbo(int cpu_id, char *buf, int len)
 	char super_pg[64] = "";
 
 	if (p_mmu->s_pg_sz_m)
-		scnprintf(super_pg, 64, "%dM Super Page%s, ",
+		scnprintf(super_pg, 64, "%dM Super Page %s",
 			  p_mmu->s_pg_sz_m,
 			  IS_USED_CFG(CONFIG_TRANSPARENT_HUGEPAGE));
 
 	n += scnprintf(buf + n, len - n,
-		      "MMU [v%x]\t: %dk PAGE, %sJTLB %d (%dx%d), uDTLB %d, uITLB %d %s%s\n",
+		      "MMU [v%x]\t: %dk PAGE, %sJTLB %d (%dx%d), uDTLB %d, uITLB %d%s%s\n",
 		       p_mmu->ver, p_mmu->pg_sz_k, super_pg,
 		       p_mmu->sets * p_mmu->ways, p_mmu->sets, p_mmu->ways,
 		       p_mmu->u_dtlb, p_mmu->u_itlb,
-		       IS_AVAIL2(p_mmu->pae, "PAE40 ", CONFIG_ARC_HAS_PAE40));
+		       IS_AVAIL2(p_mmu->pae, ", PAE40 ", CONFIG_ARC_HAS_PAE40));
 
 	return buf;
 }
diff --git a/arch/arc/mm/tlbex.S b/arch/arc/mm/tlbex.S
index f1967eeb32e7..b30e4e36bb00 100644
--- a/arch/arc/mm/tlbex.S
+++ b/arch/arc/mm/tlbex.S
@@ -237,15 +237,6 @@ ex_saved_reg1:
 
 2:
 
-#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
-	and.f 0, r0, _PAGE_PRESENT
-	bz   1f
-	ld   r3, [num_pte_not_present]
-	add  r3, r3, 1
-	st   r3, [num_pte_not_present]
-1:
-#endif
-
 .endm
 
 ;-----------------------------------------------------------------
@@ -309,12 +300,6 @@ ENTRY(EV_TLBMissI)
 
 	TLBMISS_FREEUP_REGS
 
-#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
-	ld  r0, [@numitlb]
-	add r0, r0, 1
-	st  r0, [@numitlb]
-#endif
-
 	;----------------------------------------------------------------
 	; Get the PTE corresponding to V-addr accessed, r2 is setup with EFA
 	LOAD_FAULT_PTE
@@ -349,12 +334,6 @@ ENTRY(EV_TLBMissD)
 
 	TLBMISS_FREEUP_REGS
 
-#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
-	ld  r0, [@numdtlb]
-	add r0, r0, 1
-	st  r0, [@numdtlb]
-#endif
-
 	;----------------------------------------------------------------
 	; Get the PTE corresponding to V-addr accessed
 	; If PTE exists, it will setup, r0 = PTE, r1 = Ptr to PTE, r2 = EFA