20 files changed, 211 insertions, 316 deletions

diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 2c2ac3f3ff80..76dde9db7934 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -73,9 +73,6 @@ config STACKTRACE_SUPPORT
 	def_bool y
 	select STACKTRACE
 
-config HAVE_LATENCYTOP_SUPPORT
-	def_bool y
-
 config HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	def_bool y
 	depends on ARC_MMU_V4
@@ -445,6 +442,7 @@ config LINUX_LINK_BASE
 	  However some customers have peripherals mapped at this addr, so
 	  Linux needs to be scooted a bit.
 	  If you don't know what the above means, leave this setting alone.
+	  This needs to match memory start address specified in Device Tree
 
 config HIGHMEM
 	bool "High Memory Support"
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index cf0cf34eeb24..aeb19021099e 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -81,7 +81,7 @@ endif
 LIBGCC	:= $(shell $(CC) $(cflags-y) --print-libgcc-file-name)
 
 # Modules with short calls might break for calls into builtin-kernel
-KBUILD_CFLAGS_MODULE	+= -mlong-calls
+KBUILD_CFLAGS_MODULE	+= -mlong-calls -mno-millicode
 
 # Finally dump eveything into kernel build system
 KBUILD_CFLAGS	+= $(cflags-y)
diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi
index f3db32154973..44a578c10732 100644
--- a/arch/arc/boot/dts/axs10x_mb.dtsi
+++ b/arch/arc/boot/dts/axs10x_mb.dtsi
@@ -46,6 +46,7 @@
 			snps,pbl = < 32 >;
 			clocks = <&apbclk>;
 			clock-names = "stmmaceth";
+			max-speed = <100>;
 		};
 
 		ehci@0x40000 {
diff --git a/arch/arc/boot/dts/nsim_hs.dts b/arch/arc/boot/dts/nsim_hs.dts
index b0eb0e7fe21d..fc81879bc1f5 100644
--- a/arch/arc/boot/dts/nsim_hs.dts
+++ b/arch/arc/boot/dts/nsim_hs.dts
@@ -17,7 +17,8 @@
 
 	memory {
 		device_type = "memory";
-		reg = <0x0 0x80000000 0x0 0x40000000	/* 1 GB low mem */
+		/* CONFIG_LINUX_LINK_BASE needs to match low mem start */
+		reg = <0x0 0x80000000 0x0 0x20000000	/* 512 MB low mem */
 		       0x1 0x00000000 0x0 0x40000000>;	/* 1 GB highmem */
 	};
 
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index abf06e81c929..210ef3e72332 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -62,9 +62,7 @@ extern int ioc_exists;
 #define ARC_REG_IC_IVIC		0x10
 #define ARC_REG_IC_CTRL		0x11
 #define ARC_REG_IC_IVIL		0x19
-#if defined(CONFIG_ARC_MMU_V3) || defined(CONFIG_ARC_MMU_V4)
 #define ARC_REG_IC_PTAG		0x1E
-#endif
 #define ARC_REG_IC_PTAG_HI	0x1F
 
 /* Bit val in IC_CTRL */
diff --git a/arch/arc/include/asm/dma-mapping.h b/arch/arc/include/asm/dma-mapping.h
index 2d28ba939d8e..660205414f1d 100644
--- a/arch/arc/include/asm/dma-mapping.h
+++ b/arch/arc/include/asm/dma-mapping.h
@@ -11,192 +11,11 @@
 #ifndef ASM_ARC_DMA_MAPPING_H
 #define ASM_ARC_DMA_MAPPING_H
 
-#include <asm-generic/dma-coherent.h>
-#include <asm/cacheflush.h>
+extern struct dma_map_ops arc_dma_ops;
 
-void *dma_alloc_noncoherent(struct device *dev, size_t size,
-			    dma_addr_t *dma_handle, gfp_t gfp);
-
-void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr,
-			  dma_addr_t dma_handle);
-
-void *dma_alloc_coherent(struct device *dev, size_t size,
-			 dma_addr_t *dma_handle, gfp_t gfp);
-
-void dma_free_coherent(struct device *dev, size_t size, void *kvaddr,
-		       dma_addr_t dma_handle);
-
-/* drivers/base/dma-mapping.c */
-extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
-			   void *cpu_addr, dma_addr_t dma_addr, size_t size);
-extern int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
-				  void *cpu_addr, dma_addr_t dma_addr,
-				  size_t size);
-
-#define dma_mmap_coherent(d, v, c, h, s) dma_common_mmap(d, v, c, h, s)
-#define dma_get_sgtable(d, t, v, h, s) dma_common_get_sgtable(d, t, v, h, s)
-
-/*
- * streaming DMA Mapping API...
- * CPU accesses page via normal paddr, thus needs to explicitly made
- * consistent before each use
- */
-
-static inline void __inline_dma_cache_sync(unsigned long paddr, size_t size,
-					   enum dma_data_direction dir)
-{
-	switch (dir) {
-	case DMA_FROM_DEVICE:
-		dma_cache_inv(paddr, size);
-		break;
-	case DMA_TO_DEVICE:
-		dma_cache_wback(paddr, size);
-		break;
-	case DMA_BIDIRECTIONAL:
-		dma_cache_wback_inv(paddr, size);
-		break;
-	default:
-		pr_err("Invalid DMA dir [%d] for OP @ %lx\n", dir, paddr);
-	}
-}
-
-void __arc_dma_cache_sync(unsigned long paddr, size_t size,
-			  enum dma_data_direction dir);
-
-#define _dma_cache_sync(addr, sz, dir)			\
-do {							\
-	if (__builtin_constant_p(dir))			\
-		__inline_dma_cache_sync(addr, sz, dir);	\
-	else						\
-		__arc_dma_cache_sync(addr, sz, dir);	\
-}							\
-while (0);
-
-static inline dma_addr_t
-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 (dma_addr_t)cpu_addr;
-}
-
-static inline void
-dma_unmap_single(struct device *dev, dma_addr_t dma_addr,
-		 size_t size, enum dma_data_direction dir)
-{
-}
-
-static inline dma_addr_t
-dma_map_page(struct device *dev, struct page *page,
-	     unsigned long offset, size_t size,
-	     enum dma_data_direction dir)
-{
-	unsigned long paddr = page_to_phys(page) + offset;
-	return dma_map_single(dev, (void *)paddr, size, dir);
-}
-
-static inline void
-dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
-	       size_t size, enum dma_data_direction dir)
-{
-}
-
-static inline int
-dma_map_sg(struct device *dev, struct scatterlist *sg,
-	   int nents, enum dma_data_direction dir)
-{
-	struct scatterlist *s;
-	int i;
-
-	for_each_sg(sg, s, nents, i)
-		s->dma_address = dma_map_page(dev, sg_page(s), s->offset,
-					       s->length, dir);
-
-	return nents;
-}
-
-static inline void
-dma_unmap_sg(struct device *dev, struct scatterlist *sg,
-	     int nents, enum dma_data_direction dir)
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 {
-	struct scatterlist *s;
-	int i;
-
-	for_each_sg(sg, s, nents, i)
-		dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir);
-}
-
-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(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(dma_handle, size, DMA_TO_DEVICE);
-}
-
-static inline void
-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(dma_handle + offset, size, DMA_FROM_DEVICE);
-}
-
-static inline void
-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(dma_handle + offset, size, DMA_TO_DEVICE);
-}
-
-static inline void
-dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sglist, int nelems,
-		    enum dma_data_direction dir)
-{
-	int i;
-	struct scatterlist *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 *sglist,
-		       int nelems, enum dma_data_direction dir)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nelems, i)
-		_dma_cache_sync((unsigned int)sg_virt(sg), sg->length, dir);
-}
-
-static inline int dma_supported(struct device *dev, u64 dma_mask)
-{
-	/* Support 32 bit DMA mask exclusively */
-	return dma_mask == DMA_BIT_MASK(32);
-}
-
-static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return 0;
-}
-
-static inline int dma_set_mask(struct device *dev, u64 dma_mask)
-{
-	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
-		return -EIO;
-
-	*dev->dma_mask = dma_mask;
-
-	return 0;
+	return &arc_dma_ops;
 }
 
 #endif
diff --git a/arch/arc/include/asm/mach_desc.h b/arch/arc/include/asm/mach_desc.h
index 6ff657a904b6..c28e6c347b49 100644
--- a/arch/arc/include/asm/mach_desc.h
+++ b/arch/arc/include/asm/mach_desc.h
@@ -23,7 +23,7 @@
  * @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_cpu_smp:	for each CPU as it is coming up (SMP as well as UP)
+ * @init_per_cpu:	for each CPU as it is coming up (SMP as well as UP)
  * 			[(M):init_IRQ(), (o):start_kernel_secondary()]
  * @init_machine:	arch initcall level callback (e.g. populate static
  * 			platform devices or parse Devicetree)
@@ -35,7 +35,7 @@ struct machine_desc {
 	const char		**dt_compat;
 	void			(*init_early)(void);
 #ifdef CONFIG_SMP
-	void			(*init_cpu_smp)(unsigned int);
+	void			(*init_per_cpu)(unsigned int);
 #endif
 	void			(*init_machine)(void);
 	void			(*init_late)(void);
diff --git a/arch/arc/include/asm/smp.h b/arch/arc/include/asm/smp.h
index 133c867d15af..991380438d6b 100644
--- a/arch/arc/include/asm/smp.h
+++ b/arch/arc/include/asm/smp.h
@@ -48,7 +48,7 @@ extern int smp_ipi_irq_setup(int cpu, int irq);
  * @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_irq_cpu:	Called for each core so SMP h/w block driver can do
+ * @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
@@ -57,7 +57,7 @@ extern int smp_ipi_irq_setup(int cpu, int irq);
 struct plat_smp_ops {
 	const char 	*info;
 	void		(*init_early_smp)(void);
-	void		(*init_irq_cpu)(int cpu);
+	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/arch/arc/include/asm/unwind.h b/arch/arc/include/asm/unwind.h
index 7ca628b6ee2a..c11a25bb8158 100644
--- a/arch/arc/include/asm/unwind.h
+++ b/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/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c
index 26c156827479..0394f9f61b46 100644
--- a/arch/arc/kernel/intc-arcv2.c
+++ b/arch/arc/kernel/intc-arcv2.c
@@ -106,10 +106,21 @@ static struct irq_chip arcv2_irq_chip = {
 static int arcv2_irq_map(struct irq_domain *d, unsigned int irq,
 			 irq_hw_number_t hw)
 {
-	if (irq == TIMER0_IRQ || irq == IPI_IRQ)
+	/*
+	 * core intc IRQs [16, 23]:
+	 * Statically assigned always private-per-core (Timers, WDT, IPI, PCT)
+	 */
+	if (hw < 24) {
+		/*
+		 * A subsequent request_percpu_irq() fails if percpu_devid is
+		 * not set. That in turns sets NOAUTOEN, meaning each core needs
+		 * to call enable_percpu_irq()
+		 */
+		irq_set_percpu_devid(irq);
 		irq_set_chip_and_handler(irq, &arcv2_irq_chip, handle_percpu_irq);
-	else
+	} else {
 		irq_set_chip_and_handler(irq, &arcv2_irq_chip, handle_level_irq);
+	}
 
 	return 0;
 }
diff --git a/arch/arc/kernel/irq.c b/arch/arc/kernel/irq.c
index 2ee226546c6a..ba17f85285cf 100644
--- a/arch/arc/kernel/irq.c
+++ b/arch/arc/kernel/irq.c
@@ -29,11 +29,11 @@ void __init init_IRQ(void)
 
 #ifdef CONFIG_SMP
 	/* a SMP H/w block could do IPI IRQ request here */
-	if (plat_smp_ops.init_irq_cpu)
-		plat_smp_ops.init_irq_cpu(smp_processor_id());
+	if (plat_smp_ops.init_per_cpu)
+		plat_smp_ops.init_per_cpu(smp_processor_id());
 
-	if (machine_desc->init_cpu_smp)
-		machine_desc->init_cpu_smp(smp_processor_id());
+	if (machine_desc->init_per_cpu)
+		machine_desc->init_per_cpu(smp_processor_id());
 #endif
 }
 
@@ -51,6 +51,18 @@ void arch_do_IRQ(unsigned int irq, struct pt_regs *regs)
 	set_irq_regs(old_regs);
 }
 
+/*
+ * API called for requesting percpu interrupts - called by each CPU
+ *  - For boot CPU, actually request the IRQ with genirq core + enables
+ *  - For subsequent callers only enable called locally
+ *
+ * Relies on being called by boot cpu first (i.e. request called ahead) of
+ * any enable as expected by genirq. Hence Suitable only for TIMER, IPI
+ * which are guaranteed to be setup on boot core first.
+ * Late probed peripherals such as perf can't use this as there no guarantee
+ * of being called on boot CPU first.
+ */
+
 void arc_request_percpu_irq(int irq, int cpu,
                             irqreturn_t (*isr)(int irq, void *dev),
                             const char *irq_nm,
@@ -60,14 +72,17 @@ void arc_request_percpu_irq(int irq, int cpu,
 	if (!cpu) {
 		int rc;
 
+#ifdef CONFIG_ISA_ARCOMPACT
 		/*
-		 * These 2 calls are essential to making percpu IRQ APIs work
-		 * Ideally these details could be hidden in irq chip map function
-		 * but the issue is IPIs IRQs being static (non-DT) and platform
-		 * specific, so we can't identify them there.
+		 * A subsequent request_percpu_irq() fails if percpu_devid is
+		 * not set. That in turns sets NOAUTOEN, meaning each core needs
+		 * to call enable_percpu_irq()
+		 *
+		 * For ARCv2, this is done in irq map function since we know
+		 * which irqs are strictly per cpu
 		 */
 		irq_set_percpu_devid(irq);
-		irq_modify_status(irq, IRQ_NOAUTOEN, 0);  /* @irq, @clr, @set */
+#endif
 
 		rc = request_percpu_irq(irq, isr, irq_nm, percpu_dev);
 		if (rc)
diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c
index 74a9b074ac3e..bd237acdf4f2 100644
--- a/arch/arc/kernel/mcip.c
+++ b/arch/arc/kernel/mcip.c
@@ -132,7 +132,7 @@ static void mcip_probe_n_setup(void)
 struct plat_smp_ops plat_smp_ops = {
 	.info		= smp_cpuinfo_buf,
 	.init_early_smp	= mcip_probe_n_setup,
-	.init_irq_cpu	= mcip_setup_per_cpu,
+	.init_per_cpu	= mcip_setup_per_cpu,
 	.ipi_send	= mcip_ipi_send,
 	.ipi_clear	= mcip_ipi_clear,
 };
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index 0c08bb1ce15a..8b134cfe5e1f 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -428,12 +428,11 @@ static irqreturn_t arc_pmu_intr(int irq, void *dev)
 
 #endif /* CONFIG_ISA_ARCV2 */
 
-void arc_cpu_pmu_irq_init(void)
+static void arc_cpu_pmu_irq_init(void *data)
 {
-	struct arc_pmu_cpu *pmu_cpu = this_cpu_ptr(&arc_pmu_cpu);
+	int irq = *(int *)data;
 
-	arc_request_percpu_irq(arc_pmu->irq, smp_processor_id(), arc_pmu_intr,
-			       "ARC perf counters", pmu_cpu);
+	enable_percpu_irq(irq, IRQ_TYPE_NONE);
 
 	/* Clear all pending interrupt flags */
 	write_aux_reg(ARC_REG_PCT_INT_ACT, 0xffffffff);
@@ -515,7 +514,6 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 
 	if (has_interrupts) {
 		int irq = platform_get_irq(pdev, 0);
-		unsigned long flags;
 
 		if (irq < 0) {
 			pr_err("Cannot get IRQ number for the platform\n");
@@ -524,24 +522,12 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 
 		arc_pmu->irq = irq;
 
-		/*
-		 * arc_cpu_pmu_irq_init() needs to be called on all cores for
-		 * their respective local PMU.
-		 * However we use opencoded on_each_cpu() to ensure it is called
-		 * on core0 first, so that arc_request_percpu_irq() sets up
-		 * AUTOEN etc. Otherwise enable_percpu_irq() fails to enable
-		 * perf IRQ on non master cores.
-		 * see arc_request_percpu_irq()
-		 */
-		preempt_disable();
-		local_irq_save(flags);
-		arc_cpu_pmu_irq_init();
-		local_irq_restore(flags);
-		smp_call_function((smp_call_func_t)arc_cpu_pmu_irq_init, 0, 1);
-		preempt_enable();
-
-		/* Clean all pending interrupt flags */
-		write_aux_reg(ARC_REG_PCT_INT_ACT, 0xffffffff);
+		/* intc map function ensures irq_set_percpu_devid() called */
+		request_percpu_irq(irq, arc_pmu_intr, "ARC perf counters",
+				   this_cpu_ptr(&arc_pmu_cpu));
+
+		on_each_cpu(arc_cpu_pmu_irq_init, &irq, 1);
+
 	} else
 		arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
 
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index c33e77c0ad3e..e1b87444ea9a 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -429,7 +429,6 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 	arc_unwind_init();
-	arc_unwind_setup();
 }
 
 static int __init customize_machine(void)
diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c
index 580587805fa3..ef6e9e15b82a 100644
--- a/arch/arc/kernel/smp.c
+++ b/arch/arc/kernel/smp.c
@@ -132,11 +132,11 @@ void start_kernel_secondary(void)
 	pr_info("## CPU%u LIVE ##: Executing Code...\n", cpu);
 
 	/* Some SMP H/w setup - for each cpu */
-	if (plat_smp_ops.init_irq_cpu)
-		plat_smp_ops.init_irq_cpu(cpu);
+	if (plat_smp_ops.init_per_cpu)
+		plat_smp_ops.init_per_cpu(cpu);
 
-	if (machine_desc->init_cpu_smp)
-		machine_desc->init_cpu_smp(cpu);
+	if (machine_desc->init_per_cpu)
+		machine_desc->init_per_cpu(cpu);
 
 	arc_local_timer_setup();
 
diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c
index 7352475451f6..0587bf121d11 100644
--- a/arch/arc/kernel/unwind.c
+++ b/arch/arc/kernel/unwind.c
@@ -170,6 +170,23 @@ static struct unwind_table *find_table(unsigned long pc)
 
 static unsigned long read_pointer(const u8 **pLoc,
 				  const void *end, signed ptrType);
+static void init_unwind_hdr(struct unwind_table *table,
+			    void *(*alloc) (unsigned long));
+
+/*
+ * wrappers for header alloc (vs. calling one vs. other at call site)
+ * to elide section mismatches warnings
+ */
+static void *__init unw_hdr_alloc_early(unsigned long sz)
+{
+	return __alloc_bootmem_nopanic(sz, sizeof(unsigned int),
+				       MAX_DMA_ADDRESS);
+}
+
+static void *unw_hdr_alloc(unsigned long sz)
+{
+	return kmalloc(sz, GFP_KERNEL);
+}
 
 static void init_unwind_table(struct unwind_table *table, const char *name,
 			      const void *core_start, unsigned long core_size,
@@ -209,6 +226,8 @@ void __init arc_unwind_init(void)
 			  __start_unwind, __end_unwind - __start_unwind,
 			  NULL, 0);
 	  /*__start_unwind_hdr, __end_unwind_hdr - __start_unwind_hdr);*/
+
+	init_unwind_hdr(&root_table, unw_hdr_alloc_early);
 }
 
 static const u32 bad_cie, not_fde;
@@ -241,8 +260,8 @@ static void swap_eh_frame_hdr_table_entries(void *p1, void *p2, int size)
 	e2->fde = v;
 }
 
-static void __init setup_unwind_table(struct unwind_table *table,
-				      void *(*alloc) (unsigned long))
+static void init_unwind_hdr(struct unwind_table *table,
+			    void *(*alloc) (unsigned long))
 {
 	const u8 *ptr;
 	unsigned long tableSize = table->size, hdrSize;
@@ -277,10 +296,10 @@ static void __init setup_unwind_table(struct unwind_table *table,
 		if (cie == &not_fde)
 			continue;
 		if (cie == NULL || cie == &bad_cie)
-			return;
+			goto ret_err;
 		ptrType = fde_pointer_type(cie);
 		if (ptrType < 0)
-			return;
+			goto ret_err;
 
 		ptr = (const u8 *)(fde + 2);
 		if (!read_pointer(&ptr, (const u8 *)(fde + 1) + *fde,
@@ -296,13 +315,15 @@ static void __init setup_unwind_table(struct unwind_table *table,
 	}
 
 	if (tableSize || !n)
-		return;
+		goto ret_err;
 
 	hdrSize = 4 + sizeof(unsigned long) + sizeof(unsigned int)
 	    + 2 * n * sizeof(unsigned long);
+
 	header = alloc(hdrSize);
 	if (!header)
-		return;
+		goto ret_err;
+
 	header->version = 1;
 	header->eh_frame_ptr_enc = DW_EH_PE_abs | DW_EH_PE_native;
 	header->fde_count_enc = DW_EH_PE_abs | DW_EH_PE_data4;
@@ -340,18 +361,10 @@ static void __init setup_unwind_table(struct unwind_table *table,
 	table->hdrsz = hdrSize;
 	smp_wmb();
 	table->header = (const void *)header;
-}
-
-static void *__init balloc(unsigned long sz)
-{
-	return __alloc_bootmem_nopanic(sz,
-				       sizeof(unsigned int),
-				       __pa(MAX_DMA_ADDRESS));
-}
+	return;
 
-void __init arc_unwind_setup(void)
-{
-	setup_unwind_table(&root_table, balloc);
+ret_err:
+	panic("Attention !!! Dwarf FDE parsing errors\n");;
 }
 
 #ifdef CONFIG_MODULES
@@ -372,11 +385,13 @@ void *unwind_add_table(struct module *module, const void *table_start,
 		return NULL;
 
 	init_unwind_table(table, module->name,
-			  module->module_core, module->core_size,
-			  module->module_init, module->init_size,
+			  module->core_layout.base, module->core_layout.size,
+			  module->init_layout.base, module->init_layout.size,
 			  table_start, table_size,
 			  NULL, 0);
 
+	init_unwind_hdr(table, unw_hdr_alloc);
+
 #ifdef UNWIND_DEBUG
 	unw_debug("Table added for [%s] %lx %lx\n",
 		module->name, table->core.pc, table->core.range);
@@ -439,6 +454,7 @@ void unwind_remove_table(void *handle, int init_only)
 	info.init_only = init_only;
 
 	unlink_table(&info); /* XXX: SMP */
+	kfree(table->header);
 	kfree(table);
 }
 
@@ -588,9 +604,6 @@ static signed fde_pointer_type(const u32 *cie)
 	const u8 *ptr = (const u8 *)(cie + 2);
 	unsigned version = *ptr;
 
-	if (version != 1)
-		return -1;	/* unsupported */
-
 	if (*++ptr) {
 		const char *aug;
 		const u8 *end = (const u8 *)(cie + 1) + *cie;
@@ -1002,9 +1015,7 @@ int arc_unwind(struct unwind_frame_info *frame)
 		ptr = (const u8 *)(cie + 2);
 		end = (const u8 *)(cie + 1) + *cie;
 		frame->call_frame = 1;
-		if ((state.version = *ptr) != 1)
-			cie = NULL;	/* unsupported version */
-		else if (*++ptr) {
+		if (*++ptr) {
 			/* check if augmentation size is first (thus present) */
 			if (*ptr == 'z') {
 				while (++ptr < end && *ptr) {
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index ff7ff6cbb811..b65f797e9ad6 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -617,7 +617,7 @@ void flush_dcache_page(struct page *page)
 	 */
 	if (!mapping_mapped(mapping)) {
 		clear_bit(PG_dc_clean, &page->flags);
-	} else if (page_mapped(page)) {
+	} else if (page_mapcount(page)) {
 
 		/* kernel reading from page with U-mapping */
 		phys_addr_t paddr = (unsigned long)page_address(page);
@@ -857,7 +857,7 @@ void copy_user_highpage(struct page *to, struct page *from,
 	 * For !VIPT cache, all of this gets compiled out as
 	 * addr_not_cache_congruent() is 0
 	 */
-	if (page_mapped(from) && addr_not_cache_congruent(kfrom, u_vaddr)) {
+	if (page_mapcount(from) && addr_not_cache_congruent(kfrom, u_vaddr)) {
 		__flush_dcache_page((unsigned long)kfrom, u_vaddr);
 		clean_src_k_mappings = 1;
 	}
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 29a46bb198cc..01eaf88bf821 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -17,18 +17,14 @@
  */
 
 #include <linux/dma-mapping.h>
-#include <linux/dma-debug.h>
-#include <linux/export.h>
 #include <asm/cache.h>
 #include <asm/cacheflush.h>
 
-/*
- * Helpers for Coherent DMA API.
- */
-void *dma_alloc_noncoherent(struct device *dev, size_t size,
-			    dma_addr_t *dma_handle, gfp_t gfp)
+
+static void *arc_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp, struct dma_attrs *attrs)
 {
-	void *paddr;
+	void *paddr, *kvaddr;
 
 	/* This is linear addr (0x8000_0000 based) */
 	paddr = alloc_pages_exact(size, gfp);
@@ -38,22 +34,6 @@ void *dma_alloc_noncoherent(struct device *dev, size_t size,
 	/* This is bus address, platform dependent */
 	*dma_handle = (dma_addr_t)paddr;
 
-	return paddr;
-}
-EXPORT_SYMBOL(dma_alloc_noncoherent);
-
-void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr,
-			  dma_addr_t dma_handle)
-{
-	free_pages_exact((void *)dma_handle, size);
-}
-EXPORT_SYMBOL(dma_free_noncoherent);
-
-void *dma_alloc_coherent(struct device *dev, size_t size,
-			 dma_addr_t *dma_handle, gfp_t gfp)
-{
-	void *paddr, *kvaddr;
-
 	/*
 	 * IOC relies on all data (even coherent DMA data) being in cache
 	 * Thus allocate normal cached memory
@@ -65,22 +45,15 @@ void *dma_alloc_coherent(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)
-		return dma_alloc_noncoherent(dev, size, dma_handle, gfp);
-
-	/* This is linear addr (0x8000_0000 based) */
-	paddr = alloc_pages_exact(size, gfp);
-	if (!paddr)
-		return NULL;
+	if ((is_isa_arcv2() && ioc_exists) ||
+	    dma_get_attr(DMA_ATTR_NON_CONSISTENT, attrs))
+		return paddr;
 
 	/* This is kernel Virtual address (0x7000_0000 based) */
 	kvaddr = ioremap_nocache((unsigned long)paddr, size);
 	if (kvaddr == NULL)
 		return NULL;
 
-	/* This is bus address, platform dependent */
-	*dma_handle = (dma_addr_t)paddr;
-
 	/*
 	 * Evict any existing L1 and/or L2 lines for the backing page
 	 * in case it was used earlier as a normal "cached" page.
@@ -95,26 +68,111 @@ void *dma_alloc_coherent(struct device *dev, size_t size,
 
 	return kvaddr;
 }
-EXPORT_SYMBOL(dma_alloc_coherent);
 
-void dma_free_coherent(struct device *dev, size_t size, void *kvaddr,
-		       dma_addr_t dma_handle)
+static void arc_dma_free(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
-	if (is_isa_arcv2() && ioc_exists)
-		return dma_free_noncoherent(dev, size, kvaddr, dma_handle);
-
-	iounmap((void __force __iomem *)kvaddr);
+	if (!dma_get_attr(DMA_ATTR_NON_CONSISTENT, attrs) &&
+	    !(is_isa_arcv2() && ioc_exists))
+		iounmap((void __force __iomem *)vaddr);
 
 	free_pages_exact((void *)dma_handle, size);
 }
-EXPORT_SYMBOL(dma_free_coherent);
 
 /*
- * Helper for streaming DMA...
+ * streaming DMA Mapping API...
+ * CPU accesses page via normal paddr, thus needs to explicitly made
+ * consistent before each use
  */
-void __arc_dma_cache_sync(unsigned long paddr, size_t size,
-			  enum dma_data_direction dir)
+static void _dma_cache_sync(unsigned long paddr, size_t size,
+		enum dma_data_direction dir)
+{
+	switch (dir) {
+	case DMA_FROM_DEVICE:
+		dma_cache_inv(paddr, size);
+		break;
+	case DMA_TO_DEVICE:
+		dma_cache_wback(paddr, size);
+		break;
+	case DMA_BIDIRECTIONAL:
+		dma_cache_wback_inv(paddr, size);
+		break;
+	default:
+		pr_err("Invalid DMA dir [%d] for OP @ %lx\n", dir, paddr);
+	}
+}
+
+static dma_addr_t arc_dma_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size, enum dma_data_direction dir,
+		struct dma_attrs *attrs)
+{
+	unsigned long paddr = page_to_phys(page) + offset;
+	_dma_cache_sync(paddr, size, dir);
+	return (dma_addr_t)paddr;
+}
+
+static int arc_dma_map_sg(struct device *dev, struct scatterlist *sg,
+	   int nents, enum dma_data_direction dir, struct dma_attrs *attrs)
+{
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sg, s, nents, i)
+		s->dma_address = dma_map_page(dev, sg_page(s), s->offset,
+					       s->length, dir);
+
+	return nents;
+}
+
+static void arc_dma_sync_single_for_cpu(struct device *dev,
+		dma_addr_t dma_handle, size_t size, enum dma_data_direction dir)
+{
+	_dma_cache_sync(dma_handle, size, DMA_FROM_DEVICE);
+}
+
+static void arc_dma_sync_single_for_device(struct device *dev,
+		dma_addr_t dma_handle, size_t size, enum dma_data_direction dir)
 {
-	__inline_dma_cache_sync(paddr, size, dir);
+	_dma_cache_sync(dma_handle, size, DMA_TO_DEVICE);
 }
-EXPORT_SYMBOL(__arc_dma_cache_sync);
+
+static void arc_dma_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sglist, int nelems,
+		enum dma_data_direction dir)
+{
+	int i;
+	struct scatterlist *sg;
+
+	for_each_sg(sglist, sg, nelems, i)
+		_dma_cache_sync((unsigned int)sg_virt(sg), sg->length, dir);
+}
+
+static void arc_dma_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sglist, int nelems,
+		enum dma_data_direction dir)
+{
+	int i;
+	struct scatterlist *sg;
+
+	for_each_sg(sglist, sg, nelems, i)
+		_dma_cache_sync((unsigned int)sg_virt(sg), sg->length, dir);
+}
+
+static int arc_dma_supported(struct device *dev, u64 dma_mask)
+{
+	/* Support 32 bit DMA mask exclusively */
+	return dma_mask == DMA_BIT_MASK(32);
+}
+
+struct dma_map_ops arc_dma_ops = {
+	.alloc			= arc_dma_alloc,
+	.free			= arc_dma_free,
+	.map_page		= arc_dma_map_page,
+	.map_sg			= arc_dma_map_sg,
+	.sync_single_for_device	= arc_dma_sync_single_for_device,
+	.sync_single_for_cpu	= arc_dma_sync_single_for_cpu,
+	.sync_sg_for_cpu	= arc_dma_sync_sg_for_cpu,
+	.sync_sg_for_device	= arc_dma_sync_sg_for_device,
+	.dma_supported		= arc_dma_supported,
+};
+EXPORT_SYMBOL(arc_dma_ops);
diff --git a/arch/arc/mm/highmem.c b/arch/arc/mm/highmem.c
index 065ee6bfa82a..92dd92cad7f9 100644
--- a/arch/arc/mm/highmem.c
+++ b/arch/arc/mm/highmem.c
@@ -111,7 +111,7 @@ void __kunmap_atomic(void *kv)
 }
 EXPORT_SYMBOL(__kunmap_atomic);
 
-noinline pte_t *alloc_kmap_pgtable(unsigned long kvaddr)
+static noinline pte_t * __init alloc_kmap_pgtable(unsigned long kvaddr)
 {
 	pgd_t *pgd_k;
 	pud_t *pud_k;
@@ -127,7 +127,7 @@ noinline pte_t *alloc_kmap_pgtable(unsigned long kvaddr)
 	return pte_k;
 }
 
-void kmap_init(void)
+void __init kmap_init(void)
 {
 	/* Due to recursive include hell, we can't do this in processor.h */
 	BUILD_BUG_ON(PAGE_OFFSET < (VMALLOC_END + FIXMAP_SIZE + PKMAP_SIZE));
diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c
index a9305b5a2cd4..7d2c4fbf4f22 100644
--- a/arch/arc/mm/init.c
+++ b/arch/arc/mm/init.c
@@ -51,7 +51,9 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 	int in_use = 0;
 
 	if (!low_mem_sz) {
-		BUG_ON(base != low_mem_start);
+		if (base != low_mem_start)
+			panic("CONFIG_LINUX_LINK_BASE != DT memory { }");
+
 		low_mem_sz = size;
 		in_use = 1;
 	} else {