Rewind v3.13-rc3+ (78fd82238d0e5716) to v3.12

16 files changed, 123 insertions, 430 deletions

diff --git a/arch/arc/kernel/Makefile b/arch/arc/kernel/Makefile
index 8004b4f..c242ef0 100644
--- a/arch/arc/kernel/Makefile
+++ b/arch/arc/kernel/Makefile
@@ -19,7 +19,6 @@ obj-$(CONFIG_KPROBES)      		+= kprobes.o
 obj-$(CONFIG_ARC_MISALIGN_ACCESS) 	+= unaligned.o
 obj-$(CONFIG_KGDB)			+= kgdb.o
 obj-$(CONFIG_ARC_METAWARE_HLINK)	+= arc_hostlink.o
-obj-$(CONFIG_PERF_EVENTS)		+= perf_event.o
 
 obj-$(CONFIG_ARC_FPU_SAVE_RESTORE)	+= fpu.o
 CFLAGS_fpu.o   += -mdpfp
diff --git a/arch/arc/kernel/ctx_sw.c b/arch/arc/kernel/ctx_sw.c
index c14a5be..34410eb 100644
--- a/arch/arc/kernel/ctx_sw.c
+++ b/arch/arc/kernel/ctx_sw.c
@@ -17,8 +17,6 @@
 #include <asm/asm-offsets.h>
 #include <linux/sched.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)
 {
@@ -47,16 +45,7 @@ __switch_to(struct task_struct *prev_task, struct task_struct *next_task)
 #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
 
 		"sync   \n\t"
 
@@ -108,7 +97,7 @@ __switch_to(struct task_struct *prev_task, struct task_struct *next_task)
 		/* FP/BLINK restore generated by gcc (standard func epilogue */
 
 		: "=r"(tmp)
-		: "n"(KSP_WORD_OFF), "r"(next), "r"(prev)
+		: "n"((TASK_THREAD + THREAD_KSP) / 4), "r"(next), "r"(prev)
 		: "blink"
 	);
 
diff --git a/arch/arc/kernel/ctx_sw_asm.S b/arch/arc/kernel/ctx_sw_asm.S
index 65690e7..d897234 100644
--- a/arch/arc/kernel/ctx_sw_asm.S
+++ b/arch/arc/kernel/ctx_sw_asm.S
@@ -14,8 +14,6 @@
 #include <asm/asm-offsets.h>
 #include <asm/linkage.h>
 
-#define KSP_WORD_OFF 	((TASK_THREAD + THREAD_KSP) / 4)
-
 ;################### Low Level Context Switch ##########################
 
 	.section .sched.text,"ax",@progbits
@@ -30,13 +28,8 @@ __switch_to:
 	SAVE_CALLEE_SAVED_KERNEL
 
 	/* 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
+	st.as  sp, [r0, (TASK_THREAD + THREAD_KSP)/4]
+
 	/*
 	* Return last task in r0 (return reg)
 	* On ARC, Return reg = First Arg reg = r0.
diff --git a/arch/arc/kernel/devtree.c b/arch/arc/kernel/devtree.c
index b6dc4e2..2340af0 100644
--- a/arch/arc/kernel/devtree.c
+++ b/arch/arc/kernel/devtree.c
@@ -14,22 +14,10 @@
 #include <linux/memblock.h>
 #include <linux/of.h>
 #include <linux/of_fdt.h>
+#include <asm/prom.h>
 #include <asm/clk.h>
 #include <asm/mach_desc.h>
 
-static const void * __init arch_get_next_mach(const char *const **match)
-{
-	static const struct machine_desc *mdesc = __arch_info_begin;
-	const struct machine_desc *m = mdesc;
-
-	if (m >= __arch_info_end)
-		return NULL;
-
-	mdesc++;
-	*match = m->dt_compat;
-	return m;
-}
-
 /**
  * setup_machine_fdt - Machine setup when an dtb was passed to the kernel
  * @dt:		virtual address pointer to dt blob
@@ -37,24 +25,93 @@ static const void * __init arch_get_next_mach(const char *const **match)
  * If a dtb was passed to the kernel, then use it to choose the correct
  * machine_desc and to setup the system.
  */
-const struct machine_desc * __init setup_machine_fdt(void *dt)
+struct machine_desc * __init setup_machine_fdt(void *dt)
 {
-	const struct machine_desc *mdesc;
+	struct boot_param_header *devtree = dt;
+	struct machine_desc *mdesc = NULL, *mdesc_best = NULL;
+	unsigned int score, mdesc_score = ~1;
 	unsigned long dt_root;
+	const char *model, *compat;
 	void *clk;
+	char manufacturer[16];
 	unsigned long len;
 
-	if (!early_init_dt_scan(dt))
+	/* check device tree validity */
+	if (be32_to_cpu(devtree->magic) != OF_DT_HEADER)
 		return NULL;
 
-	mdesc = of_flat_dt_match_machine(NULL, arch_get_next_mach);
-	if (!mdesc)
+	initial_boot_params = devtree;
+	dt_root = of_get_flat_dt_root();
+
+	/*
+	 * The kernel could be multi-platform enabled, thus could have many
+	 * "baked-in" machine descriptors. Search thru all for the best
+	 * "compatible" string match.
+	 */
+	for_each_machine_desc(mdesc) {
+		score = of_flat_dt_match(dt_root, mdesc->dt_compat);
+		if (score > 0 && score < mdesc_score) {
+			mdesc_best = mdesc;
+			mdesc_score = score;
+		}
+	}
+	if (!mdesc_best) {
+		const char *prop;
+		long size;
+
+		pr_err("\n unrecognized device tree list:\n[ ");
+
+		prop = of_get_flat_dt_prop(dt_root, "compatible", &size);
+		if (prop) {
+			while (size > 0) {
+				printk("'%s' ", prop);
+				size -= strlen(prop) + 1;
+				prop += strlen(prop) + 1;
+			}
+		}
+		printk("]\n\n");
+
 		machine_halt();
+	}
+
+	/* compat = "<manufacturer>,<model>" */
+	compat =  mdesc_best->dt_compat[0];
+
+	model = strchr(compat, ',');
+	if (model)
+		model++;
+
+	strlcpy(manufacturer, compat, model ? model - compat : strlen(compat));
+
+	pr_info("Board \"%s\" from %s (Manufacturer)\n", model, manufacturer);
+
+	/* Retrieve various information from the /chosen node */
+	of_scan_flat_dt(early_init_dt_scan_chosen, boot_command_line);
+
+	/* Initialize {size,address}-cells info */
+	of_scan_flat_dt(early_init_dt_scan_root, NULL);
+
+	/* Setup memory, calling early_init_dt_add_memory_arch */
+	of_scan_flat_dt(early_init_dt_scan_memory, NULL);
 
-	dt_root = of_get_flat_dt_root();
 	clk = of_get_flat_dt_prop(dt_root, "clock-frequency", &len);
 	if (clk)
 		arc_set_core_freq(of_read_ulong(clk, len/4));
 
-	return mdesc;
+	return mdesc_best;
+}
+
+/*
+ * Copy the flattened DT out of .init since unflattening doesn't copy strings
+ * and the normal DT APIs refs them from orig flat DT
+ */
+void __init copy_devtree(void)
+{
+	void *alloc = early_init_dt_alloc_memory_arch(
+			be32_to_cpu(initial_boot_params->totalsize), 64);
+	if (alloc) {
+		memcpy(alloc, initial_boot_params,
+				be32_to_cpu(initial_boot_params->totalsize));
+		initial_boot_params = alloc;
+	}
 }
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index 47d09d0..b908dde 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -250,14 +250,6 @@ ARC_ENTRY handle_interrupt_level1
 	lr  r0, [icause1]
 	and r0, r0, 0x1f
 
-#ifdef CONFIG_TRACE_IRQFLAGS
-	; icause1 needs to be read early, before calling tracing, which
-	; can clobber scratch regs, hence use of stack to stash it
-	push r0
-	TRACE_ASM_IRQ_DISABLE
-	pop  r0
-#endif
-
 	bl.d  @arch_do_IRQ
 	mov r1, sp
 
@@ -345,9 +337,9 @@ ARC_ENTRY EV_TLBProtV
 	;  vineetg: Mar 6th: Random Seg Fault issue #1
 	;  ecr and efa were not saved in case an Intr sneaks in
 	;  after fake rtie
-
+	;
 	lr  r2, [ecr]
-	lr  r0, [efa]	; Faulting Data address
+	lr  r1, [efa]	; Faulting Data address
 
 	; --------(4) Return from CPU Exception Mode ---------
 	;  Fake a rtie, but rtie to next label
@@ -356,8 +348,6 @@ ARC_ENTRY EV_TLBProtV
 
 	FAKE_RET_FROM_EXCPN r9
 
-	mov   r1, sp
-
 	;------ (5) Type of Protection Violation? ----------
 	;
 	; ProtV Hardware Exception is triggered for Access Faults of 2 types
@@ -368,12 +358,16 @@ ARC_ENTRY EV_TLBProtV
 	bbit1 r2, ECR_C_BIT_PROTV_MISALIG_DATA, 4f
 
 	;========= (6a) Access Violation Processing ========
+	mov r0, sp              ; pt_regs
 	bl  do_page_fault
 	b   ret_from_exception
 
 	;========== (6b) Non aligned access ============
 4:
+	mov r0, r1
+	mov r1, sp              ; pt_regs
 
+#ifdef  CONFIG_ARC_MISALIGN_ACCESS
 	SAVE_CALLEE_SAVED_USER
 	mov r2, sp              ; callee_regs
 
@@ -382,6 +376,9 @@ ARC_ENTRY EV_TLBProtV
 	; TBD: optimize - do this only if a callee reg was involved
 	; either a dst of emulated LD/ST or src with address-writeback
 	RESTORE_CALLEE_SAVED_USER
+#else
+	bl  do_misaligned_error
+#endif
 
 	b   ret_from_exception
 
@@ -578,7 +575,6 @@ resume_user_mode_begin:
 	; --- (Slow Path #2) pending signal  ---
 	mov r0, sp	; pt_regs for arg to do_signal()/do_notify_resume()
 
-	GET_CURR_THR_INFO_FLAGS   r9
 	bbit0  r9, TIF_SIGPENDING, .Lchk_notify_resume
 
 	; Normal Trap/IRQ entry only saves Scratch (caller-saved) regs
@@ -644,8 +640,6 @@ resume_kernel_mode:
 
 restore_regs :
 
-	TRACE_ASM_IRQ_ENABLE
-
 	lr	r10, [status32]
 
 	; Restore REG File. In case multiple Events outstanding,
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S
index 2c878e9..0f944f0 100644
--- a/arch/arc/kernel/head.S
+++ b/arch/arc/kernel/head.S
@@ -95,7 +95,7 @@ stext:
 ;----------------------------------------------------------------
 ;     First lines of code run by secondary before jumping to 'C'
 ;----------------------------------------------------------------
-	.section .text, "ax",@progbits
+	.section .init.text, "ax",@progbits
 	.type first_lines_of_secondary, @function
 	.globl first_lines_of_secondary
 
diff --git a/arch/arc/kernel/irq.c b/arch/arc/kernel/irq.c
index a4b141e..5fc9245 100644
--- a/arch/arc/kernel/irq.c
+++ b/arch/arc/kernel/irq.c
@@ -39,14 +39,10 @@ void arc_init_IRQ(void)
 	level_mask |= IS_ENABLED(CONFIG_ARC_IRQ5_LV2) << 5;
 	level_mask |= IS_ENABLED(CONFIG_ARC_IRQ6_LV2) << 6;
 
-	/*
-	 * Write to register, even if no LV2 IRQs configured to reset it
-	 * in case bootloader had mucked with it
-	 */
-	write_aux_reg(AUX_IRQ_LEV, level_mask);
-
-	if (level_mask)
+	if (level_mask) {
 		pr_info("Level-2 interrupts bitset %x\n", level_mask);
+		write_aux_reg(AUX_IRQ_LEV, level_mask);
+	}
 }
 
 /*
@@ -150,7 +146,7 @@ void arch_do_IRQ(unsigned int irq, struct pt_regs *regs)
 	set_irq_regs(old_regs);
 }
 
-int get_hw_config_num_irq(void)
+int __init get_hw_config_num_irq(void)
 {
 	uint32_t val = read_aux_reg(ARC_REG_VECBASE_BCR);
 
diff --git a/arch/arc/kernel/kgdb.c b/arch/arc/kernel/kgdb.c
index a2ff5c5..a7698fb 100644
--- a/arch/arc/kernel/kgdb.c
+++ b/arch/arc/kernel/kgdb.c
@@ -196,18 +196,6 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip)
 	instruction_pointer(regs) = ip;
 }
 
-static void kgdb_call_nmi_hook(void *ignored)
-{
-	kgdb_nmicallback(raw_smp_processor_id(), NULL);
-}
-
-void kgdb_roundup_cpus(unsigned long flags)
-{
-	local_irq_enable();
-	smp_call_function(kgdb_call_nmi_hook, NULL, 0);
-	local_irq_disable();
-}
-
 struct kgdb_arch arch_kgdb_ops = {
 	/* breakpoint instruction: TRAP_S 0x3 */
 #ifdef CONFIG_CPU_BIG_ENDIAN
diff --git a/arch/arc/kernel/kprobes.c b/arch/arc/kernel/kprobes.c
index 42b0504..72f9782 100644
--- a/arch/arc/kernel/kprobes.c
+++ b/arch/arc/kernel/kprobes.c
@@ -87,13 +87,13 @@ static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
 
 static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
-	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
+	__get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp;
 	kcb->kprobe_status = kcb->prev_kprobe.status;
 }
 
 static inline void __kprobes set_current_kprobe(struct kprobe *p)
 {
-	__this_cpu_write(current_kprobe, p);
+	__get_cpu_var(current_kprobe) = p;
 }
 
 static void __kprobes resume_execution(struct kprobe *p, unsigned long addr,
@@ -237,7 +237,7 @@ int __kprobes arc_kprobe_handler(unsigned long addr, struct pt_regs *regs)
 
 		return 1;
 	} else if (kprobe_running()) {
-		p = __this_cpu_read(current_kprobe);
+		p = __get_cpu_var(current_kprobe);
 		if (p->break_handler && p->break_handler(p, regs)) {
 			setup_singlestep(p, regs);
 			kcb->kprobe_status = KPROBE_HIT_SS;
@@ -327,7 +327,7 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned long trapnr)
 		 */
 
 		/* We increment the nmissed count for accounting,
-		 * we can also use npre/npostfault count for accounting
+		 * we can also use npre/npostfault count for accouting
 		 * these specific fault cases.
 		 */
 		kprobes_inc_nmissed_count(cur);
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
deleted file mode 100644
index e46d81f..0000000
--- a/arch/arc/kernel/perf_event.c
+++ /dev/null
@@ -1,326 +0,0 @@
-/*
- * Linux performance counter support for ARC700 series
- *
- * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com)
- *
- * This code is inspired by the perf support of various other architectures.
- *
- * 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.
- *
- */
-#include <linux/errno.h>
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/perf_event.h>
-#include <linux/platform_device.h>
-#include <asm/arcregs.h>
-
-struct arc_pmu {
-	struct pmu	pmu;
-	int		counter_size;	/* in bits */
-	int		n_counters;
-	unsigned long	used_mask[BITS_TO_LONGS(ARC_PMU_MAX_HWEVENTS)];
-	int		ev_hw_idx[PERF_COUNT_ARC_HW_MAX];
-};
-
-/* read counter #idx; note that counter# != event# on ARC! */
-static uint64_t arc_pmu_read_counter(int idx)
-{
-	uint32_t tmp;
-	uint64_t result;
-
-	/*
-	 * ARC supports making 'snapshots' of the counters, so we don't
-	 * need to care about counters wrapping to 0 underneath our feet
-	 */
-	write_aux_reg(ARC_REG_PCT_INDEX, idx);
-	tmp = read_aux_reg(ARC_REG_PCT_CONTROL);
-	write_aux_reg(ARC_REG_PCT_CONTROL, tmp | ARC_REG_PCT_CONTROL_SN);
-	result = (uint64_t) (read_aux_reg(ARC_REG_PCT_SNAPH)) << 32;
-	result |= read_aux_reg(ARC_REG_PCT_SNAPL);
-
-	return result;
-}
-
-static void arc_perf_event_update(struct perf_event *event,
-				  struct hw_perf_event *hwc, int idx)
-{
-	struct arc_pmu *arc_pmu = container_of(event->pmu, struct arc_pmu, pmu);
-	uint64_t prev_raw_count, new_raw_count;
-	int64_t delta;
-
-	do {
-		prev_raw_count = local64_read(&hwc->prev_count);
-		new_raw_count = arc_pmu_read_counter(idx);
-	} while (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
-				 new_raw_count) != prev_raw_count);
-
-	delta = (new_raw_count - prev_raw_count) &
-		((1ULL << arc_pmu->counter_size) - 1ULL);
-
-	local64_add(delta, &event->count);
-	local64_sub(delta, &hwc->period_left);
-}
-
-static void arc_pmu_read(struct perf_event *event)
-{
-	arc_perf_event_update(event, &event->hw, event->hw.idx);
-}
-
-static int arc_pmu_cache_event(u64 config)
-{
-	unsigned int cache_type, cache_op, cache_result;
-	int ret;
-
-	cache_type	= (config >>  0) & 0xff;
-	cache_op	= (config >>  8) & 0xff;
-	cache_result	= (config >> 16) & 0xff;
-	if (cache_type >= PERF_COUNT_HW_CACHE_MAX)
-		return -EINVAL;
-	if (cache_type >= PERF_COUNT_HW_CACHE_OP_MAX)
-		return -EINVAL;
-	if (cache_type >= PERF_COUNT_HW_CACHE_RESULT_MAX)
-		return -EINVAL;
-
-	ret = arc_pmu_cache_map[cache_type][cache_op][cache_result];
-
-	if (ret == CACHE_OP_UNSUPPORTED)
-		return -ENOENT;
-
-	return ret;
-}
-
-/* initializes hw_perf_event structure if event is supported */
-static int arc_pmu_event_init(struct perf_event *event)
-{
-	struct arc_pmu *arc_pmu = container_of(event->pmu, struct arc_pmu, pmu);
-	struct hw_perf_event *hwc = &event->hw;
-	int ret;
-
-	/* ARC 700 PMU does not support sampling events */
-	if (is_sampling_event(event))
-		return -ENOENT;
-
-	switch (event->attr.type) {
-	case PERF_TYPE_HARDWARE:
-		if (event->attr.config >= PERF_COUNT_HW_MAX)
-			return -ENOENT;
-		if (arc_pmu->ev_hw_idx[event->attr.config] < 0)
-			return -ENOENT;
-		hwc->config = arc_pmu->ev_hw_idx[event->attr.config];
-		pr_debug("initializing event %d with cfg %d\n",
-			 (int) event->attr.config, (int) hwc->config);
-		return 0;
-	case PERF_TYPE_HW_CACHE:
-		ret = arc_pmu_cache_event(event->attr.config);
-		if (ret < 0)
-			return ret;
-		hwc->config = arc_pmu->ev_hw_idx[ret];
-		return 0;
-	default:
-		return -ENOENT;
-	}
-}
-
-/* starts all counters */
-static void arc_pmu_enable(struct pmu *pmu)
-{
-	uint32_t tmp;
-	tmp = read_aux_reg(ARC_REG_PCT_CONTROL);
-	write_aux_reg(ARC_REG_PCT_CONTROL, (tmp & 0xffff0000) | 0x1);
-}
-
-/* stops all counters */
-static void arc_pmu_disable(struct pmu *pmu)
-{
-	uint32_t tmp;
-	tmp = read_aux_reg(ARC_REG_PCT_CONTROL);
-	write_aux_reg(ARC_REG_PCT_CONTROL, (tmp & 0xffff0000) | 0x0);
-}
-
-/*
- * Assigns hardware counter to hardware condition.
- * Note that there is no separate start/stop mechanism;
- * stopping is achieved by assigning the 'never' condition
- */
-static void arc_pmu_start(struct perf_event *event, int flags)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	int idx = hwc->idx;
-
-	if (WARN_ON_ONCE(idx == -1))
-		return;
-
-	if (flags & PERF_EF_RELOAD)
-		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
-
-	event->hw.state = 0;
-
-	/* enable ARC pmu here */
-	write_aux_reg(ARC_REG_PCT_INDEX, idx);
-	write_aux_reg(ARC_REG_PCT_CONFIG, hwc->config);
-}
-
-static void arc_pmu_stop(struct perf_event *event, int flags)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	int idx = hwc->idx;
-
-	if (!(event->hw.state & PERF_HES_STOPPED)) {
-		/* stop ARC pmu here */
-		write_aux_reg(ARC_REG_PCT_INDEX, idx);
-
-		/* condition code #0 is always "never" */
-		write_aux_reg(ARC_REG_PCT_CONFIG, 0);
-
-		event->hw.state |= PERF_HES_STOPPED;
-	}
-
-	if ((flags & PERF_EF_UPDATE) &&
-	    !(event->hw.state & PERF_HES_UPTODATE)) {
-		arc_perf_event_update(event, &event->hw, idx);
-		event->hw.state |= PERF_HES_UPTODATE;
-	}
-}
-
-static void arc_pmu_del(struct perf_event *event, int flags)
-{
-	struct arc_pmu *arc_pmu = container_of(event->pmu, struct arc_pmu, pmu);
-
-	arc_pmu_stop(event, PERF_EF_UPDATE);
-	__clear_bit(event->hw.idx, arc_pmu->used_mask);
-
-	perf_event_update_userpage(event);
-}
-
-/* allocate hardware counter and optionally start counting */
-static int arc_pmu_add(struct perf_event *event, int flags)
-{
-	struct arc_pmu *arc_pmu = container_of(event->pmu, struct arc_pmu, pmu);
-	struct hw_perf_event *hwc = &event->hw;
-	int idx = hwc->idx;
-
-	if (__test_and_set_bit(idx, arc_pmu->used_mask)) {
-		idx = find_first_zero_bit(arc_pmu->used_mask,
-					  arc_pmu->n_counters);
-		if (idx == arc_pmu->n_counters)
-			return -EAGAIN;
-
-		__set_bit(idx, arc_pmu->used_mask);
-		hwc->idx = idx;
-	}
-
-	write_aux_reg(ARC_REG_PCT_INDEX, idx);
-	write_aux_reg(ARC_REG_PCT_CONFIG, 0);
-	write_aux_reg(ARC_REG_PCT_COUNTL, 0);
-	write_aux_reg(ARC_REG_PCT_COUNTH, 0);
-	local64_set(&hwc->prev_count, 0);
-
-	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
-	if (flags & PERF_EF_START)
-		arc_pmu_start(event, PERF_EF_RELOAD);
-
-	perf_event_update_userpage(event);
-
-	return 0;
-}
-
-static int arc_pmu_device_probe(struct platform_device *pdev)
-{
-	struct arc_pmu *arc_pmu;
-	struct arc_reg_pct_build pct_bcr;
-	struct arc_reg_cc_build cc_bcr;
-	int i, j, ret;
-
-	union cc_name {
-		struct {
-			uint32_t word0, word1;
-			char sentinel;
-		} indiv;
-		char str[9];
-	} cc_name;
-
-
-	READ_BCR(ARC_REG_PCT_BUILD, pct_bcr);
-	if (!pct_bcr.v) {
-		pr_err("This core does not have performance counters!\n");
-		return -ENODEV;
-	}
-
-	arc_pmu = devm_kzalloc(&pdev->dev, sizeof(struct arc_pmu),
-			       GFP_KERNEL);
-	if (!arc_pmu)
-		return -ENOMEM;
-
-	arc_pmu->n_counters = pct_bcr.c;
-	BUG_ON(arc_pmu->n_counters > ARC_PMU_MAX_HWEVENTS);
-
-	arc_pmu->counter_size = 32 + (pct_bcr.s << 4);
-	pr_info("ARC PMU found with %d counters of size %d bits\n",
-		arc_pmu->n_counters, arc_pmu->counter_size);
-
-	READ_BCR(ARC_REG_CC_BUILD, cc_bcr);
-
-	if (!cc_bcr.v)
-		pr_err("Strange! Performance counters exist, but no countable conditions?\n");
-
-	pr_info("ARC PMU has %d countable conditions\n", cc_bcr.c);
-
-	cc_name.str[8] = 0;
-	for (i = 0; i < PERF_COUNT_HW_MAX; i++)
-		arc_pmu->ev_hw_idx[i] = -1;
-
-	for (j = 0; j < cc_bcr.c; j++) {
-		write_aux_reg(ARC_REG_CC_INDEX, j);
-		cc_name.indiv.word0 = read_aux_reg(ARC_REG_CC_NAME0);
-		cc_name.indiv.word1 = read_aux_reg(ARC_REG_CC_NAME1);
-		for (i = 0; i < ARRAY_SIZE(arc_pmu_ev_hw_map); i++) {
-			if (arc_pmu_ev_hw_map[i] &&
-			    !strcmp(arc_pmu_ev_hw_map[i], cc_name.str) &&
-			    strlen(arc_pmu_ev_hw_map[i])) {
-				pr_debug("mapping %d to idx %d with name %s\n",
-					 i, j, cc_name.str);
-				arc_pmu->ev_hw_idx[i] = j;
-			}
-		}
-	}
-
-	arc_pmu->pmu = (struct pmu) {
-		.pmu_enable	= arc_pmu_enable,
-		.pmu_disable	= arc_pmu_disable,
-		.event_init	= arc_pmu_event_init,
-		.add		= arc_pmu_add,
-		.del		= arc_pmu_del,
-		.start		= arc_pmu_start,
-		.stop		= arc_pmu_stop,
-		.read		= arc_pmu_read,
-	};
-
-	ret = perf_pmu_register(&arc_pmu->pmu, pdev->name, PERF_TYPE_RAW);
-
-	return ret;
-}
-
-#ifdef CONFIG_OF
-static const struct of_device_id arc_pmu_match[] = {
-	{ .compatible = "snps,arc700-pmu" },
-	{},
-};
-MODULE_DEVICE_TABLE(of, arc_pmu_match);
-#endif
-
-static struct platform_driver arc_pmu_driver = {
-	.driver	= {
-		.name		= "arc700-pmu",
-		.of_match_table = of_match_ptr(arc_pmu_match),
-	},
-	.probe		= arc_pmu_device_probe,
-};
-
-module_platform_driver(arc_pmu_driver);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Mischa Jonker <mjonker@synopsys.com>");
-MODULE_DESCRIPTION("ARC PMU driver");
diff --git a/arch/arc/kernel/reset.c b/arch/arc/kernel/reset.c
index 2768fa1..e227a2b 100644
--- a/arch/arc/kernel/reset.c
+++ b/arch/arc/kernel/reset.c
@@ -31,4 +31,3 @@ void machine_power_off(void)
 }
 
 void (*pm_power_off) (void) = NULL;
-EXPORT_SYMBOL(pm_power_off);
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index 643eae4..2c68bc7e 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -21,6 +21,7 @@
 #include <asm/setup.h>
 #include <asm/page.h>
 #include <asm/irq.h>
+#include <asm/prom.h>
 #include <asm/unwind.h>
 #include <asm/clk.h>
 #include <asm/mach_desc.h>
@@ -30,13 +31,14 @@
 int running_on_hw = 1;	/* vs. on ISS */
 
 char __initdata command_line[COMMAND_LINE_SIZE];
-const struct machine_desc *machine_desc;
+struct machine_desc *machine_desc;
 
 struct task_struct *_current_task[NR_CPUS];	/* For stack switching */
 
 struct cpuinfo_arc cpuinfo_arc700[NR_CPUS];
 
-static void read_arc_build_cfg_regs(void)
+
+void read_arc_build_cfg_regs(void)
 {
 	struct bcr_perip uncached_space;
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
@@ -104,7 +106,7 @@ static const struct cpuinfo_data arc_cpu_tbl[] = {
 	{ {0x00, NULL		} }
 };
 
-static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
+char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 {
 	int n = 0;
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[cpu_id];
@@ -169,7 +171,7 @@ static const struct id_to_str mac_mul_nm[] = {
 	{0x6, "Dual 16x16 and 32x16"}
 };
 
-static char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len)
+char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len)
 {
 	int n = 0;
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[cpu_id];
@@ -232,7 +234,7 @@ static char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len)
 	return buf;
 }
 
-static void arc_chk_ccms(void)
+void arc_chk_ccms(void)
 {
 #if defined(CONFIG_ARC_HAS_DCCM) || defined(CONFIG_ARC_HAS_ICCM)
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
@@ -267,7 +269,7 @@ static void arc_chk_ccms(void)
  * hardware has dedicated regs which need to be saved/restored on ctx-sw
  * (Single Precision uses core regs), thus kernel is kind of oblivious to it
  */
-static void arc_chk_fpu(void)
+void arc_chk_fpu(void)
 {
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
 
@@ -344,7 +346,8 @@ void __init setup_arch(char **cmdline_p)
 	setup_arch_memory();
 
 	/* copy flat DT out of .init and then unflatten it */
-	unflatten_and_copy_device_tree();
+	copy_devtree();
+	unflatten_device_tree();
 
 	/* Can be issue if someone passes cmd line arg "ro"
 	 * But that is unlikely so keeping it as it is
diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c
index c2f9ebb..bca3052 100644
--- a/arch/arc/kernel/smp.c
+++ b/arch/arc/kernel/smp.c
@@ -95,7 +95,7 @@ void __init smp_cpus_done(unsigned int max_cpus)
  *        If it turns out to be elaborate, it's better to code it in assembly
  *
  */
-void __weak arc_platform_smp_wait_to_boot(int cpu)
+void __attribute__((weak)) arc_platform_smp_wait_to_boot(int cpu)
 {
 	/*
 	 * As a hack for debugging - since debugger will single-step over the
@@ -128,7 +128,6 @@ void start_kernel_secondary(void)
 	atomic_inc(&mm->mm_users);
 	atomic_inc(&mm->mm_count);
 	current->active_mm = mm;
-	cpumask_set_cpu(cpu, mm_cpumask(mm));
 
 	notify_cpu_starting(cpu);
 	set_cpu_online(cpu, true);
@@ -211,6 +210,7 @@ enum ipi_msg_type {
 	IPI_NOP = 0,
 	IPI_RESCHEDULE = 1,
 	IPI_CALL_FUNC,
+	IPI_CALL_FUNC_SINGLE,
 	IPI_CPU_STOP
 };
 
@@ -254,7 +254,7 @@ void smp_send_stop(void)
 
 void arch_send_call_function_single_ipi(int cpu)
 {
-	ipi_send_msg(cpumask_of(cpu), IPI_CALL_FUNC);
+	ipi_send_msg(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
 }
 
 void arch_send_call_function_ipi_mask(const struct cpumask *mask)
@@ -286,6 +286,10 @@ static inline void __do_IPI(unsigned long *ops, struct ipi_data *ipi, int cpu)
 			generic_smp_call_function_interrupt();
 			break;
 
+		case IPI_CALL_FUNC_SINGLE:
+			generic_smp_call_function_single_interrupt();
+			break;
+
 		case IPI_CPU_STOP:
 			ipi_cpu_stop(cpu);
 			break;
diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c
index 9ce47cf..f8b7d88 100644
--- a/arch/arc/kernel/stacktrace.c
+++ b/arch/arc/kernel/stacktrace.c
@@ -237,14 +237,11 @@ unsigned int get_wchan(struct task_struct *tsk)
  */
 void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 {
-	/* Assumes @tsk is sleeping so unwinds from __switch_to */
 	arc_unwind_core(tsk, NULL, __collect_all_but_sched, trace);
 }
 
 void save_stack_trace(struct stack_trace *trace)
 {
-	/* Pass NULL for task so it unwinds the current call frame */
-	arc_unwind_core(NULL, NULL, __collect_all, trace);
+	arc_unwind_core(current, NULL, __collect_all, trace);
 }
-EXPORT_SYMBOL_GPL(save_stack_trace);
 #endif
diff --git a/arch/arc/kernel/time.c b/arch/arc/kernel/time.c
index e5f3a83..3fde7de 100644
--- a/arch/arc/kernel/time.c
+++ b/arch/arc/kernel/time.c
@@ -63,10 +63,9 @@
 
 int arc_counter_setup(void)
 {
-	/*
-	 * For SMP this needs to be 0. However Kconfig glue doesn't
-	 * enable this option for SMP configs
-	 */
+	/* RTSC insn taps into cpu clk, needs no setup */
+
+	/* For SMP, only allowed if cross-core-sync, hence usable as cs */
 	return 1;
 }
 
@@ -207,7 +206,7 @@ static DEFINE_PER_CPU(struct clock_event_device, arc_clockevent_device) = {
 
 static irqreturn_t timer_irq_handler(int irq, void *dev_id)
 {
-	struct clock_event_device *clk = this_cpu_ptr(&arc_clockevent_device);
+	struct clock_event_device *clk = &__get_cpu_var(arc_clockevent_device);
 
 	arc_timer_event_ack(clk->mode == CLOCK_EVT_MODE_PERIODIC);
 	clk->event_handler(clk);
@@ -224,7 +223,7 @@ static struct irqaction arc_timer_irq = {
  * Setup the local event timer for @cpu
  * N.B. weak so that some exotic ARC SoCs can completely override it
  */
-void __weak arc_local_timer_setup(unsigned int cpu)
+void __attribute__((weak)) arc_local_timer_setup(unsigned int cpu)
 {
 	struct clock_event_device *clk = &per_cpu(arc_clockevent_device, cpu);
 
diff --git a/arch/arc/kernel/traps.c b/arch/arc/kernel/traps.c
index 3eadfda..e21692d 100644
--- a/arch/arc/kernel/traps.c
+++ b/arch/arc/kernel/traps.c
@@ -84,18 +84,19 @@ DO_ERROR_INFO(SIGBUS, "Invalid Mem Access", do_memory_error, BUS_ADRERR)
 DO_ERROR_INFO(SIGTRAP, "Breakpoint Set", trap_is_brkpt, TRAP_BRKPT)
 DO_ERROR_INFO(SIGBUS, "Misaligned Access", do_misaligned_error, BUS_ADRALN)
 
+#ifdef CONFIG_ARC_MISALIGN_ACCESS
 /*
  * Entry Point for Misaligned Data access Exception, for emulating in software
  */
 int do_misaligned_access(unsigned long address, struct pt_regs *regs,
 			 struct callee_regs *cregs)
 {
-	/* If emulation not enabled, or failed, kill the task */
 	if (misaligned_fixup(address, regs, cregs) != 0)
 		return do_misaligned_error(address, regs);
 
 	return 0;
 }
+#endif
 
 /*
  * Entry point for miscll errors such as Nested Exceptions