Merge tag 'arc-6.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc

Pull ARC updates from Vineet Gupta:

 - fixes for -Wmissing-prototype warnings

 - missing compiler barrier in relaxed atomics

 - some uaccess simplification, declutter

 - removal of massive glocal struct cpuinfo_arc from bootlog code

 - __switch_to consolidation (removal of inline asm variant)

 - use GP to cache task pointer (vs. r25)

 - misc rework of entry code

* tag 'arc-6.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc: (24 commits)
  ARC: boot log: fix warning
  arc: Explicitly include correct DT includes
  ARC: pt_regs: create seperate type for ecr
  ARCv2: entry: rearrange pt_regs slightly
  ARC: entry: replace 8 byte ADD.ne with 4 byte ADD2.ne
  ARC: entry: replace 8 byte OR with 4 byte BSET
  ARC: entry: Add more common chores to EXCEPTION_PROLOGUE
  ARC: entry: EV_MachineCheck dont re-read ECR
  ARC: entry: ARcompact EV_ProtV to use r10 directly
  ARC: entry: rework (non-functional)
  ARC: __switch_to: move ksp to thread_info from thread_struct
  ARC: __switch_to: asm with dwarf ops (vs. inline asm)
  ARC: kernel stack: INIT_THREAD need not setup @init_stack in @ksp
  ARC: entry: use gp to cache task pointer (vs. r25)
  ARC: boot log: eliminate struct cpuinfo_arc #4: boot log per ISA
  ARC: boot log: eliminate struct cpuinfo_arc #3: don't export
  ARC: boot log: eliminate struct cpuinfo_arc #2: cache
  ARC: boot log: eliminate struct cpuinfo_arc #1: mm
  ARCv2: memset: don't prefetch for len == 0 which happens a alot
  ARC: uaccess: elide unaliged handling if hardware supports
  ...

19 files changed, 358 insertions, 579 deletions

diff --git a/arch/arc/kernel/Makefile b/arch/arc/kernel/Makefile
index 0723d888ac44..95fbf9364c67 100644
--- a/arch/arc/kernel/Makefile
+++ b/arch/arc/kernel/Makefile
@@ -5,6 +5,8 @@
 
 obj-y	:= head.o arcksyms.o setup.o irq.o reset.o ptrace.o process.o devtree.o
 obj-y	+= signal.o traps.o sys.o troubleshoot.o stacktrace.o disasm.o
+obj-y	+= ctx_sw_asm.o
+
 obj-$(CONFIG_ISA_ARCOMPACT)		+= entry-compact.o intc-compact.o
 obj-$(CONFIG_ISA_ARCV2)			+= entry-arcv2.o intc-arcv2.o
 
@@ -24,11 +26,4 @@ ifdef CONFIG_ISA_ARCOMPACT
 CFLAGS_fpu.o   += -mdpfp
 endif
 
-ifdef CONFIG_ARC_DW2_UNWIND
-CFLAGS_ctx_sw.o += -fno-omit-frame-pointer
-obj-y += ctx_sw.o
-else
-obj-y += ctx_sw_asm.o
-endif
-
 extra-y := vmlinux.lds
diff --git a/arch/arc/kernel/asm-offsets.c b/arch/arc/kernel/asm-offsets.c
index 0e884036ab74..f77deb799175 100644
--- a/arch/arc/kernel/asm-offsets.c
+++ b/arch/arc/kernel/asm-offsets.c
@@ -20,13 +20,13 @@ int main(void)
 
 	BLANK();
 
-	DEFINE(THREAD_KSP, offsetof(struct thread_struct, ksp));
 	DEFINE(THREAD_CALLEE_REG, offsetof(struct thread_struct, callee_reg));
 	DEFINE(THREAD_FAULT_ADDR,
 	       offsetof(struct thread_struct, fault_address));
 
 	BLANK();
 
+	DEFINE(THREAD_INFO_KSP, offsetof(struct thread_info, ksp));
 	DEFINE(THREAD_INFO_FLAGS, offsetof(struct thread_info, flags));
 	DEFINE(THREAD_INFO_PREEMPT_COUNT,
 	       offsetof(struct thread_info, preempt_count));
@@ -46,7 +46,8 @@ int main(void)
 	BLANK();
 
 	DEFINE(PT_status32, offsetof(struct pt_regs, status32));
-	DEFINE(PT_event, offsetof(struct pt_regs, event));
+	DEFINE(PT_event, offsetof(struct pt_regs, ecr));
+	DEFINE(PT_bta, offsetof(struct pt_regs, bta));
 	DEFINE(PT_sp, offsetof(struct pt_regs, sp));
 	DEFINE(PT_r0, offsetof(struct pt_regs, r0));
 	DEFINE(PT_r1, offsetof(struct pt_regs, r1));
@@ -61,13 +62,9 @@ int main(void)
 	DEFINE(PT_r26, offsetof(struct pt_regs, r26));
 	DEFINE(PT_ret, offsetof(struct pt_regs, ret));
 	DEFINE(PT_blink, offsetof(struct pt_regs, blink));
+	OFFSET(PT_fp, pt_regs, fp);
 	DEFINE(PT_lpe, offsetof(struct pt_regs, lp_end));
 	DEFINE(PT_lpc, offsetof(struct pt_regs, lp_count));
-	DEFINE(PT_user_r25, offsetof(struct pt_regs, user_r25));
-
-	DEFINE(SZ_CALLEE_REGS, sizeof(struct callee_regs));
-	DEFINE(SZ_PT_REGS, sizeof(struct pt_regs));
-
 #ifdef CONFIG_ISA_ARCV2
 	OFFSET(PT_r12, pt_regs, r12);
 	OFFSET(PT_r30, pt_regs, r30);
@@ -80,5 +77,8 @@ int main(void)
 	OFFSET(PT_DSP_CTRL, pt_regs, DSP_CTRL);
 #endif
 
+	DEFINE(SZ_CALLEE_REGS, sizeof(struct callee_regs));
+	DEFINE(SZ_PT_REGS, sizeof(struct pt_regs));
+
 	return 0;
 }
diff --git a/arch/arc/kernel/ctx_sw.c b/arch/arc/kernel/ctx_sw.c
deleted file mode 100644
index 1a76f2d6f694..000000000000
--- a/arch/arc/kernel/ctx_sw.c
+++ /dev/null
@@ -1,112 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
- *
- * Vineetg: Aug 2009
- *  -"C" version of lowest level context switch asm macro called by schedular
- *   gcc doesn't generate the dward CFI info for hand written asm, hence can't
- *   backtrace out of it (e.g. tasks sleeping in kernel).
- *   So we cheat a bit by writing almost similar code in inline-asm.
- *  -This is a hacky way of doing things, but there is no other simple way.
- *   I don't want/intend to extend unwinding code to understand raw asm
- */
-
-#include <asm/asm-offsets.h>
-#include <linux/sched.h>
-#include <linux/sched/debug.h>
-
-#define KSP_WORD_OFF 	((TASK_THREAD + THREAD_KSP) / 4)
-
-struct task_struct *__sched
-__switch_to(struct task_struct *prev_task, struct task_struct *next_task)
-{
-	unsigned int tmp;
-	unsigned int prev = (unsigned int)prev_task;
-	unsigned int next = (unsigned int)next_task;
-
-	__asm__ __volatile__(
-		/* FP/BLINK save generated by gcc (standard function prologue */
-		"st.a    r13, [sp, -4]   \n\t"
-		"st.a    r14, [sp, -4]   \n\t"
-		"st.a    r15, [sp, -4]   \n\t"
-		"st.a    r16, [sp, -4]   \n\t"
-		"st.a    r17, [sp, -4]   \n\t"
-		"st.a    r18, [sp, -4]   \n\t"
-		"st.a    r19, [sp, -4]   \n\t"
-		"st.a    r20, [sp, -4]   \n\t"
-		"st.a    r21, [sp, -4]   \n\t"
-		"st.a    r22, [sp, -4]   \n\t"
-		"st.a    r23, [sp, -4]   \n\t"
-		"st.a    r24, [sp, -4]   \n\t"
-#ifndef CONFIG_ARC_CURR_IN_REG
-		"st.a    r25, [sp, -4]   \n\t"
-#else
-		"sub     sp, sp, 4      \n\t"	/* usual r25 placeholder */
-#endif
-
-		/* set ksp of outgoing task in tsk->thread.ksp */
-#if KSP_WORD_OFF <= 255
-		"st.as   sp, [%3, %1]    \n\t"
-#else
-		/*
-		 * Workaround for NR_CPUS=4k
-		 * %1 is bigger than 255 (S9 offset for st.as)
-		 */
-		"add2    r24, %3, %1     \n\t"
-		"st      sp, [r24]       \n\t"
-#endif
-
-		/*
-		 * setup _current_task with incoming tsk.
-		 * optionally, set r25 to that as well
-		 * For SMP extra work to get to &_current_task[cpu]
-		 * (open coded SET_CURR_TASK_ON_CPU)
-		 */
-#ifndef CONFIG_SMP
-		"st  %2, [@_current_task]	\n\t"
-#else
-		"lr   r24, [identity]		\n\t"
-		"lsr  r24, r24, 8		\n\t"
-		"bmsk r24, r24, 7		\n\t"
-		"add2 r24, @_current_task, r24	\n\t"
-		"st   %2,  [r24]		\n\t"
-#endif
-#ifdef CONFIG_ARC_CURR_IN_REG
-		"mov r25, %2   \n\t"
-#endif
-
-		/* get ksp of incoming task from tsk->thread.ksp */
-		"ld.as  sp, [%2, %1]   \n\t"
-
-		/* start loading it's CALLEE reg file */
-
-#ifndef CONFIG_ARC_CURR_IN_REG
-		"ld.ab   r25, [sp, 4]   \n\t"
-#else
-		"add    sp, sp, 4       \n\t"
-#endif
-		"ld.ab   r24, [sp, 4]   \n\t"
-		"ld.ab   r23, [sp, 4]   \n\t"
-		"ld.ab   r22, [sp, 4]   \n\t"
-		"ld.ab   r21, [sp, 4]   \n\t"
-		"ld.ab   r20, [sp, 4]   \n\t"
-		"ld.ab   r19, [sp, 4]   \n\t"
-		"ld.ab   r18, [sp, 4]   \n\t"
-		"ld.ab   r17, [sp, 4]   \n\t"
-		"ld.ab   r16, [sp, 4]   \n\t"
-		"ld.ab   r15, [sp, 4]   \n\t"
-		"ld.ab   r14, [sp, 4]   \n\t"
-		"ld.ab   r13, [sp, 4]   \n\t"
-
-		/* last (ret value) = prev : although for ARC it mov r0, r0 */
-		"mov     %0, %3        \n\t"
-
-		/* FP/BLINK restore generated by gcc (standard func epilogue */
-
-		: "=r"(tmp)
-		: "n"(KSP_WORD_OFF), "r"(next), "r"(prev)
-		: "blink"
-	);
-
-	return (struct task_struct *)tmp;
-}
diff --git a/arch/arc/kernel/ctx_sw_asm.S b/arch/arc/kernel/ctx_sw_asm.S
index 02c461484761..48e1f21976ed 100644
--- a/arch/arc/kernel/ctx_sw_asm.S
+++ b/arch/arc/kernel/ctx_sw_asm.S
@@ -11,50 +11,54 @@
 #include <asm/entry.h>       /* For the SAVE_* macros */
 #include <asm/asm-offsets.h>
 
-#define KSP_WORD_OFF 	((TASK_THREAD + THREAD_KSP) / 4)
-
-;################### Low Level Context Switch ##########################
+; IN
+;  - r0: prev task (also current)
+;  - r1: next task
+; OUT
+;  - r0: prev task (so r0 not touched)
 
 	.section .sched.text,"ax",@progbits
-	.align 4
-	.global __switch_to
-	.type   __switch_to, @function
-__switch_to:
-	CFI_STARTPROC
-
-	/* Save regs on kernel mode stack of task */
-	st.a    blink, [sp, -4]
-	st.a    fp, [sp, -4]
-	SAVE_CALLEE_SAVED_KERNEL
+ENTRY_CFI(__switch_to)
 
-	/* Save the now KSP in task->thread.ksp */
-#if KSP_WORD_OFF  <= 255
-	st.as  sp, [r0, KSP_WORD_OFF]
-#else
-	/* Workaround for NR_CPUS=4k as ST.as can only take s9 offset */
-	add2	r24, r0, KSP_WORD_OFF
-	st	sp, [r24]
-#endif
-	/*
-	* Return last task in r0 (return reg)
-	* On ARC, Return reg = First Arg reg = r0.
-	* Since we already have last task in r0,
-	* don't need to do anything special to return it
-	*/
+	/* save kernel stack frame regs of @prev task */
+	push	blink
+	CFI_DEF_CFA_OFFSET 4
+	CFI_OFFSET r31, -4
+
+	push	fp
+	CFI_DEF_CFA_OFFSET 8
+	CFI_OFFSET r27, -8
+
+	mov	fp, sp
+	CFI_DEF_CFA_REGISTER r27
+
+	/* kernel mode callee regs of @prev */
+	SAVE_CALLEE_SAVED_KERNEL
 
 	/*
-	 * switch to new task, contained in r1
-	 * Temp reg r3 is required to get the ptr to store val
+	 * save final SP to @prev->thread_info.ksp
+	 * @prev is "current" so thread_info derived from SP
 	 */
-	SET_CURR_TASK_ON_CPU  r1, r3
+	GET_CURR_THR_INFO_FROM_SP  r10
+	st	sp,  [r10, THREAD_INFO_KSP]
+
+	/* update @next in _current_task[] and GP register caching it */
+	SET_CURR_TASK_ON_CPU  r1, r10
 
-	/* reload SP with kernel mode stack pointer in task->thread.ksp */
-	ld.as  sp, [r1, (TASK_THREAD + THREAD_KSP)/4]
+	/* load SP from @next->thread_info.ksp */
+	ld	r10, [r1, TASK_THREAD_INFO]
+	ld	sp,  [r10, THREAD_INFO_KSP]
 
-	/* restore the registers */
+	/* restore callee regs, stack frame regs of @next */
 	RESTORE_CALLEE_SAVED_KERNEL
-	ld.ab   fp, [sp, 4]
-	ld.ab   blink, [sp, 4]
-	j       [blink]
 
+	pop	fp
+	CFI_RESTORE r27
+	CFI_DEF_CFA r28, 4
+
+	pop	blink
+	CFI_RESTORE r31
+	CFI_DEF_CFA_OFFSET 0
+
+	j      [blink]
 END_CFI(__switch_to)
diff --git a/arch/arc/kernel/devtree.c b/arch/arc/kernel/devtree.c
index 721d465f1580..4c9e61457b2f 100644
--- a/arch/arc/kernel/devtree.c
+++ b/arch/arc/kernel/devtree.c
@@ -12,6 +12,7 @@
 #include <linux/of.h>
 #include <linux/of_fdt.h>
 #include <asm/mach_desc.h>
+#include <asm/serial.h>
 
 #ifdef CONFIG_SERIAL_EARLYCON
 
diff --git a/arch/arc/kernel/entry-arcv2.S b/arch/arc/kernel/entry-arcv2.S
index a7e6a2174187..2e49c81c8086 100644
--- a/arch/arc/kernel/entry-arcv2.S
+++ b/arch/arc/kernel/entry-arcv2.S
@@ -125,11 +125,6 @@ ENTRY(mem_service)
 
 	EXCEPTION_PROLOGUE
 
-	lr  r0, [efa]
-	mov r1, sp
-
-	FAKE_RET_FROM_EXCPN
-
 	bl  do_memory_error
 	b   ret_from_exception
 END(mem_service)
@@ -138,11 +133,6 @@ ENTRY(EV_Misaligned)
 
 	EXCEPTION_PROLOGUE
 
-	lr  r0, [efa]	; Faulting Data address
-	mov r1, sp
-
-	FAKE_RET_FROM_EXCPN
-
 	SAVE_CALLEE_SAVED_USER
 	mov r2, sp              ; callee_regs
 
@@ -163,11 +153,6 @@ ENTRY(EV_TLBProtV)
 
 	EXCEPTION_PROLOGUE
 
-	lr  r0, [efa]	; Faulting Data address
-	mov r1, sp	; pt_regs
-
-	FAKE_RET_FROM_EXCPN
-
 	mov blink, ret_from_exception
 	b   do_page_fault
 
diff --git a/arch/arc/kernel/entry-compact.S b/arch/arc/kernel/entry-compact.S
index 5cb0cd7e4eab..774c03cc1d1a 100644
--- a/arch/arc/kernel/entry-compact.S
+++ b/arch/arc/kernel/entry-compact.S
@@ -254,18 +254,7 @@ END(handle_interrupt_level1)
 
 ENTRY(EV_TLBProtV)
 
-	EXCEPTION_PROLOGUE
-
-	mov r2, r10	; ECR set into r10 already
-	lr  r0, [efa]	; Faulting Data address (not part of pt_regs saved above)
-
-	; Exception auto-disables further Intr/exceptions.
-	; Re-enable them by pretending to return from exception
-	; (so rest of handler executes in pure K mode)
-
-	FAKE_RET_FROM_EXCPN
-
-	mov   r1, sp	; Handle to pt_regs
+	EXCEPTION_PROLOGUE	; ECR returned in r10
 
 	;------ (5) Type of Protection Violation? ----------
 	;
@@ -273,8 +262,7 @@ ENTRY(EV_TLBProtV)
 	;   -Access Violation	: 00_23_(00|01|02|03)_00
 	;			         x  r  w  r+w
 	;   -Unaligned Access	: 00_23_04_00
-	;
-	bbit1 r2, ECR_C_BIT_PROTV_MISALIG_DATA, 4f
+	bbit1 r10, ECR_C_BIT_PROTV_MISALIG_DATA, 4f
 
 	;========= (6a) Access Violation Processing ========
 	bl  do_page_fault
@@ -303,9 +291,6 @@ END(EV_TLBProtV)
 ENTRY(call_do_page_fault)
 
 	EXCEPTION_PROLOGUE
-	lr  r0, [efa]	; Faulting Data address
-	mov   r1, sp
-	FAKE_RET_FROM_EXCPN
 
 	mov blink, ret_from_exception
 	b  do_page_fault
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index 54e91df678dd..089f6680518f 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -80,11 +80,6 @@ ENTRY(instr_service)
 
 	EXCEPTION_PROLOGUE
 
-	lr  r0, [efa]
-	mov r1, sp
-
-	FAKE_RET_FROM_EXCPN
-
 	bl  do_insterror_or_kprobe
 	b   ret_from_exception
 END(instr_service)
@@ -95,16 +90,15 @@ END(instr_service)
 
 ENTRY(EV_MachineCheck)
 
-	EXCEPTION_PROLOGUE
+	EXCEPTION_PROLOGUE_KEEP_AE	; ECR returned in r10
 
-	lr  r2, [ecr]
 	lr  r0, [efa]
 	mov r1, sp
 
 	; MC excpetions disable MMU
 	ARC_MMU_REENABLE r3
 
-	lsr  	r3, r2, 8
+	lsr  	r3, r10, 8
 	bmsk 	r3, r3, 7
 	brne    r3, ECR_C_MCHK_DUP_TLB, 1f
 
@@ -129,11 +123,6 @@ ENTRY(EV_PrivilegeV)
 
 	EXCEPTION_PROLOGUE
 
-	lr  r0, [efa]
-	mov r1, sp
-
-	FAKE_RET_FROM_EXCPN
-
 	bl  do_privilege_fault
 	b   ret_from_exception
 END(EV_PrivilegeV)
@@ -145,11 +134,6 @@ ENTRY(EV_Extension)
 
 	EXCEPTION_PROLOGUE
 
-	lr  r0, [efa]
-	mov r1, sp
-
-	FAKE_RET_FROM_EXCPN
-
 	bl  do_extension_fault
 	b   ret_from_exception
 END(EV_Extension)
@@ -160,20 +144,19 @@ END(EV_Extension)
 ; syscall Tracing
 ; ---------------------------------------------
 tracesys:
-	; save EFA in case tracer wants the PC of traced task
-	; using ERET won't work since next-PC has already committed
+	; safekeep EFA (r12) if syscall tracer wanted PC
+	; for traps, ERET is pre-commit so points to next-PC
 	GET_CURR_TASK_FIELD_PTR   TASK_THREAD, r11
 	st  r12, [r11, THREAD_FAULT_ADDR]	; thread.fault_address
 
-	; PRE Sys Call Ptrace hook
-	mov r0, sp			; pt_regs needed
-	bl  @syscall_trace_entry
+	; PRE syscall trace hook
+	mov r0, sp				; pt_regs
+	bl  @syscall_trace_enter
 
 	; Tracing code now returns the syscall num (orig or modif)
 	mov r8, r0
 
 	; Do the Sys Call as we normally would.
-	; Validate the Sys Call number
 	cmp     r8,  NR_syscalls - 1
 	mov.hi  r0, -ENOSYS
 	bhi     tracesys_exit
@@ -190,37 +173,36 @@ tracesys:
 	ld  r6, [sp, PT_r6]
 	ld  r7, [sp, PT_r7]
 	ld.as   r9, [sys_call_table, r8]
-	jl      [r9]        ; Entry into Sys Call Handler
+	jl      [r9]
 
 tracesys_exit:
-	st  r0, [sp, PT_r0]     ; sys call return value in pt_regs
+	st  r0, [sp, PT_r0]
 
-	;POST Sys Call Ptrace Hook
+	; POST syscall trace hook
 	mov r0, sp		; pt_regs needed
 	bl  @syscall_trace_exit
-	b   ret_from_exception ; NOT ret_from_system_call at is saves r0 which
-	; we'd done before calling post hook above
+
+	; don't call ret_from_system_call as it saves r0, already done above
+	b   ret_from_exception
 
 ; ---------------------------------------------
 ; Breakpoint TRAP
 ; ---------------------------------------------
 trap_with_param:
 	mov r0, r12	; EFA in case ptracer/gdb wants stop_pc
-	mov r1, sp
+	mov r1, sp	; pt_regs
 
-	; Save callee regs in case gdb wants to have a look
-	; SP will grow up by size of CALLEE Reg-File
-	; NOTE: clobbers r12
+	; save callee regs in case tracer/gdb wants to peek
 	SAVE_CALLEE_SAVED_USER
 
-	; save location of saved Callee Regs @ thread_struct->pc
+	; safekeep ref to callee regs
 	GET_CURR_TASK_FIELD_PTR   TASK_THREAD, r10
 	st  sp, [r10, THREAD_CALLEE_REG]
 
-	; Call the trap handler
+	; call the non syscall trap handler
 	bl  do_non_swi_trap
 
-	; unwind stack to discard Callee saved Regs
+	; unwind stack to discard callee regs
 	DISCARD_CALLEE_SAVED_USER
 
 	b   ret_from_exception
@@ -232,37 +214,33 @@ trap_with_param:
 
 ENTRY(EV_Trap)
 
-	EXCEPTION_PROLOGUE
+	EXCEPTION_PROLOGUE_KEEP_AE
 
 	lr  r12, [efa]
 
 	FAKE_RET_FROM_EXCPN
 
-	;============ TRAP 1   :breakpoints
-	; Check ECR for trap with arg (PROLOGUE ensures r10 has ECR)
+	;============ TRAP N : breakpoints, kprobes etc
 	bmsk.f 0, r10, 7
 	bnz    trap_with_param
 
-	;============ TRAP  (no param): syscall top level
+	;============ TRAP 0 (no param): syscall
 
-	; If syscall tracing ongoing, invoke pre-post-hooks
+	; syscall tracing ongoing, invoke pre-post-hooks around syscall
 	GET_CURR_THR_INFO_FLAGS   r10
 	and.f 0, r10, _TIF_SYSCALL_WORK
 	bnz   tracesys  ; this never comes back
 
 	;============ Normal syscall case
 
-	; syscall num shd not exceed the total system calls avail
 	cmp     r8,  NR_syscalls - 1
 	mov.hi  r0, -ENOSYS
 	bhi     .Lret_from_system_call
 
-	; Offset into the syscall_table and call handler
 	ld.as   r9,[sys_call_table, r8]
-	jl      [r9]        ; Entry into Sys Call Handler
+	jl      [r9]
 
 .Lret_from_system_call:
-
 	st  r0, [sp, PT_r0]     ; sys call return value in pt_regs
 
 	; fall through to ret_from_exception
@@ -318,7 +296,7 @@ resume_user_mode_begin:
 	;      tracer might call PEEKUSR(CALLEE reg)
 	;
 	; NOTE: SP will grow up by size of CALLEE Reg-File
-	SAVE_CALLEE_SAVED_USER		; clobbers r12
+	SAVE_CALLEE_SAVED_USER
 
 	; save location of saved Callee Regs @ thread_struct->callee
 	GET_CURR_TASK_FIELD_PTR   TASK_THREAD, r10
diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c
index 5cda19d0aa91..678898757e47 100644
--- a/arch/arc/kernel/intc-arcv2.c
+++ b/arch/arc/kernel/intc-arcv2.c
@@ -108,7 +108,7 @@ static void arcv2_irq_unmask(struct irq_data *data)
 	write_aux_reg(AUX_IRQ_ENABLE, 1);
 }
 
-void arcv2_irq_enable(struct irq_data *data)
+static void arcv2_irq_enable(struct irq_data *data)
 {
 	/* set default priority */
 	write_aux_reg(AUX_IRQ_SELECT, data->hwirq);
diff --git a/arch/arc/kernel/kgdb.c b/arch/arc/kernel/kgdb.c
index 345a0000554c..4f2b5951454f 100644
--- a/arch/arc/kernel/kgdb.c
+++ b/arch/arc/kernel/kgdb.c
@@ -175,7 +175,7 @@ void kgdb_trap(struct pt_regs *regs)
 	 * with trap_s 4 (compiled) breakpoints, continuation needs to
 	 * start after the breakpoint.
 	 */
-	if (regs->ecr_param == 3)
+	if (regs->ecr.param == 3)
 		instruction_pointer(regs) -= BREAK_INSTR_SIZE;
 
 	kgdb_handle_exception(1, SIGTRAP, 0, regs);
diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c
index f9fdb557c263..55373ca0d28b 100644
--- a/arch/arc/kernel/mcip.c
+++ b/arch/arc/kernel/mcip.c
@@ -165,8 +165,6 @@ static void mcip_probe_n_setup(void)
 		IS_AVAIL1(mp.idu, "IDU "),
 		IS_AVAIL1(mp.dbg, "DEBUG "),
 		IS_AVAIL1(mp.gfrc, "GFRC"));
-
-	cpuinfo_arc700[0].extn.gfrc = mp.gfrc;
 }
 
 struct plat_smp_ops plat_smp_ops = {
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index 980b71da2f61..186ceab661eb 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -141,7 +141,7 @@ asmlinkage void ret_from_fork(void);
  * |    unused      |
  * |                |
  * ------------------
- * |     r25        |   <==== top of Stack (thread.ksp)
+ * |     r25        |   <==== top of Stack (thread_info.ksp)
  * ~                ~
  * |    --to--      |   (CALLEE Regs of kernel mode)
  * |     r13        |
@@ -162,7 +162,6 @@ asmlinkage void ret_from_fork(void);
  * |      SP        |
  * |    orig_r0     |
  * |    event/ECR   |
- * |    user_r25    |
  * ------------------  <===== END of PAGE
  */
 int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
@@ -182,14 +181,14 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	c_callee = ((struct callee_regs *)childksp) - 1;
 
 	/*
-	 * __switch_to() uses thread.ksp to start unwinding stack
+	 * __switch_to() uses thread_info.ksp to start unwinding stack
 	 * For kernel threads we don't need to create callee regs, the
 	 * stack layout nevertheless needs to remain the same.
 	 * Also, since __switch_to anyways unwinds callee regs, we use
 	 * this to populate kernel thread entry-pt/args into callee regs,
 	 * so that ret_from_kernel_thread() becomes simpler.
 	 */
-	p->thread.ksp = (unsigned long)c_callee;	/* THREAD_KSP */
+	task_thread_info(p)->ksp = (unsigned long)c_callee;	/* THREAD_INFO_KSP */
 
 	/* __switch_to expects FP(0), BLINK(return addr) at top */
 	childksp[0] = 0;			/* fp */
@@ -243,16 +242,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	 */
 	c_callee->r25 = task_thread_info(p)->thr_ptr;
 
-#ifdef CONFIG_ARC_CURR_IN_REG
-	/*
-	 * setup usermode thread pointer #2:
-	 * however for this special use of r25 in kernel, __switch_to() sets
-	 * r25 for kernel needs and only in the final return path is usermode
-	 * r25 setup, from pt_regs->user_r25. So set that up as well
-	 */
-	c_regs->user_r25 = c_callee->r25;
-#endif
-
 	return 0;
 }
 
diff --git a/arch/arc/kernel/ptrace.c b/arch/arc/kernel/ptrace.c
index 2abdcd9b09e8..e0c233c178b1 100644
--- a/arch/arc/kernel/ptrace.c
+++ b/arch/arc/kernel/ptrace.c
@@ -46,8 +46,7 @@ static const struct pt_regs_offset regoffset_table[] = {
 	REG_OFFSET_NAME(r0),
 	REG_OFFSET_NAME(sp),
 	REG_OFFSET_NAME(orig_r0),
-	REG_OFFSET_NAME(event),
-	REG_OFFSET_NAME(user_r25),
+	REG_OFFSET_NAME(ecr),
 	REG_OFFSET_END,
 };
 
@@ -55,9 +54,8 @@ static const struct pt_regs_offset regoffset_table[] = {
 
 static const struct pt_regs_offset regoffset_table[] = {
 	REG_OFFSET_NAME(orig_r0),
-	REG_OFFSET_NAME(event),
+	REG_OFFSET_NAME(ecr),
 	REG_OFFSET_NAME(bta),
-	REG_OFFSET_NAME(user_r25),
 	REG_OFFSET_NAME(r26),
 	REG_OFFSET_NAME(fp),
 	REG_OFFSET_NAME(sp),
@@ -341,7 +339,7 @@ long arch_ptrace(struct task_struct *child, long request,
 	return ret;
 }
 
-asmlinkage int syscall_trace_entry(struct pt_regs *regs)
+asmlinkage int syscall_trace_enter(struct pt_regs *regs)
 {
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
 		if (ptrace_report_syscall_entry(regs))
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index 41f07b3e594e..4dcf8589b708 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -29,6 +29,7 @@
 #include <asm/mach_desc.h>
 #include <asm/smp.h>
 #include <asm/dsp-impl.h>
+#include <soc/arc/mcip.h>
 
 #define FIX_PTR(x)  __asm__ __volatile__(";" : "+r"(x))
 
@@ -43,19 +44,22 @@ const struct machine_desc *machine_desc;
 
 struct task_struct *_current_task[NR_CPUS];	/* For stack switching */
 
-struct cpuinfo_arc cpuinfo_arc700[NR_CPUS];
+struct cpuinfo_arc {
+	int arcver;
+	unsigned int t0:1, t1:1;
+	struct {
+		unsigned long base;
+		unsigned int sz;
+	} iccm, dccm;
+};
+
+#ifdef CONFIG_ISA_ARCV2
 
-static const struct id_to_str arc_legacy_rel[] = {
+static const struct id_to_str arc_hs_rel[] = {
 	/* ID.ARCVER,	Release */
-#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_hs_ver54_rel[] = {
@@ -66,323 +70,296 @@ static const struct id_to_str arc_hs_ver54_rel[] = {
 	{  3,		"R4.00a"},
 	{  0xFF,	NULL   }
 };
+#endif
 
-static void read_decode_ccm_bcr(struct cpuinfo_arc *cpu)
+static int
+arcompact_mumbojumbo(int c, struct cpuinfo_arc *info, char *buf, int len)
 {
-	if (is_isa_arcompact()) {
-		struct bcr_iccm_arcompact iccm;
-		struct bcr_dccm_arcompact dccm;
+	int n = 0;
+#ifdef CONFIG_ISA_ARCOMPACT
+	char *cpu_nm, *isa_nm = "ARCompact";
+	struct bcr_fp_arcompact fpu_sp, fpu_dp;
+	int atomic = 0, be, present;
+	int bpu_full, bpu_cache, bpu_pred;
+	struct bcr_bpu_arcompact bpu;
+	struct bcr_iccm_arcompact iccm;
+	struct bcr_dccm_arcompact dccm;
+	struct bcr_generic isa;
 
-		READ_BCR(ARC_REG_ICCM_BUILD, iccm);
-		if (iccm.ver) {
-			cpu->iccm.sz = 4096 << iccm.sz;	/* 8K to 512K */
-			cpu->iccm.base_addr = iccm.base << 16;
-		}
+	READ_BCR(ARC_REG_ISA_CFG_BCR, isa);
 
-		READ_BCR(ARC_REG_DCCM_BUILD, dccm);
-		if (dccm.ver) {
-			unsigned long base;
-			cpu->dccm.sz = 2048 << dccm.sz;	/* 2K to 256K */
+	if (!isa.ver)	/* ISA BCR absent, use Kconfig info */
+		atomic = IS_ENABLED(CONFIG_ARC_HAS_LLSC);
+	else {
+		/* ARC700_BUILD only has 2 bits of isa info */
+		atomic = isa.info & 1;
+	}
 
-			base = read_aux_reg(ARC_REG_DCCM_BASE_BUILD);
-			cpu->dccm.base_addr = base & ~0xF;
-		}
-	} else {
-		struct bcr_iccm_arcv2 iccm;
-		struct bcr_dccm_arcv2 dccm;
-		unsigned long region;
-
-		READ_BCR(ARC_REG_ICCM_BUILD, iccm);
-		if (iccm.ver) {
-			cpu->iccm.sz = 256 << iccm.sz00;	/* 512B to 16M */
-			if (iccm.sz00 == 0xF && iccm.sz01 > 0)
-				cpu->iccm.sz <<= iccm.sz01;
-
-			region = read_aux_reg(ARC_REG_AUX_ICCM);
-			cpu->iccm.base_addr = region & 0xF0000000;
-		}
+	be = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN);
 
-		READ_BCR(ARC_REG_DCCM_BUILD, dccm);
-		if (dccm.ver) {
-			cpu->dccm.sz = 256 << dccm.sz0;
-			if (dccm.sz0 == 0xF && dccm.sz1 > 0)
-				cpu->dccm.sz <<= dccm.sz1;
+	if (info->arcver < 0x34)
+		cpu_nm = "ARC750";
+	else
+		cpu_nm = "ARC770";
 
-			region = read_aux_reg(ARC_REG_AUX_DCCM);
-			cpu->dccm.base_addr = region & 0xF0000000;
-		}
-	}
-}
+	n += scnprintf(buf + n, len - n, "processor [%d]\t: %s (%s ISA) %s%s%s\n",
+		       c, cpu_nm, isa_nm,
+		       IS_AVAIL2(atomic, "atomic ", CONFIG_ARC_HAS_LLSC),
+		       IS_AVAIL1(be, "[Big-Endian]"));
 
-static void decode_arc_core(struct cpuinfo_arc *cpu)
-{
-	struct bcr_uarch_build_arcv2 uarch;
-	const struct id_to_str *tbl;
-
-	if (cpu->core.family < 0x54) { /* includes arc700 */
+	READ_BCR(ARC_REG_FP_BCR, fpu_sp);
+	READ_BCR(ARC_REG_DPFP_BCR, fpu_dp);
 
-		for (tbl = &arc_legacy_rel[0]; tbl->id != 0; tbl++) {
-			if (cpu->core.family == tbl->id) {
-				cpu->release = tbl->str;
-				break;
-			}
-		}
+	if (fpu_sp.ver | fpu_dp.ver)
+		n += scnprintf(buf + n, len - n, "FPU\t\t: %s%s\n",
+			       IS_AVAIL1(fpu_sp.ver, "SP "),
+			       IS_AVAIL1(fpu_dp.ver, "DP "));
 
-		if (is_isa_arcompact())
-			cpu->name = "ARC700";
-		else if (tbl->str)
-			cpu->name = "HS38";
-		else
-			cpu->name = cpu->release = "Unknown";
+	READ_BCR(ARC_REG_BPU_BCR, bpu);
+	bpu_full = bpu.fam ? 1 : 0;
+	bpu_cache = 256 << (bpu.ent - 1);
+	bpu_pred = 256 << (bpu.ent - 1);
 
-		return;
+	n += scnprintf(buf + n, len - n,
+			"BPU\t\t: %s%s match, cache:%d, Predict Table:%d\n",
+			IS_AVAIL1(bpu_full, "full"),
+			IS_AVAIL1(!bpu_full, "partial"),
+			bpu_cache, bpu_pred);
+
+	READ_BCR(ARC_REG_ICCM_BUILD, iccm);
+	if (iccm.ver) {
+		info->iccm.sz = 4096 << iccm.sz;	/* 8K to 512K */
+		info->iccm.base = iccm.base << 16;
 	}
 
-	/*
-	 * Initial HS cores bumped AUX IDENTITY.ARCVER for each release until
-	 * ARCVER 0x54 which introduced AUX MICRO_ARCH_BUILD and subsequent
-	 * releases only update it.
-	 */
-	READ_BCR(ARC_REG_MICRO_ARCH_BCR, uarch);
-
-	if (uarch.prod == 4) {
-		cpu->name = "HS48";
-		cpu->extn.dual = 1;
+	READ_BCR(ARC_REG_DCCM_BUILD, dccm);
+	if (dccm.ver) {
+		unsigned long base;
+		info->dccm.sz = 2048 << dccm.sz;	/* 2K to 256K */
 
-	} else {
-		cpu->name = "HS38";
+		base = read_aux_reg(ARC_REG_DCCM_BASE_BUILD);
+		info->dccm.base = base & ~0xF;
 	}
 
-	for (tbl = &arc_hs_ver54_rel[0]; tbl->id != 0xFF; tbl++) {
-		if (uarch.maj == tbl->id) {
-			cpu->release = tbl->str;
-			break;
-		}
-	}
+	/* ARCompact ISA specific sanity checks */
+	present = fpu_dp.ver;	/* SP has no arch visible regs */
+	CHK_OPT_STRICT(CONFIG_ARC_FPU_SAVE_RESTORE, present);
+#endif
+	return n;
+
 }
 
-static void read_arc_build_cfg_regs(void)
+static int arcv2_mumbojumbo(int c, struct cpuinfo_arc *info, char *buf,