Merge tag 'arc-4.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc

Pull ARC architecture updates from Vineet Gupta:
 - Big Endian io accessors fix [Lada]
 - Spellos fixes [Adam]
 - Fix for DW GMAC breakage [Alexey]
 - Making DMA API 64-bit ready
 - Shutting up -Wmaybe-uninitialized noise for ARC
 - Other minor fixes here and there, comments update

* tag 'arc-4.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc: (21 commits)
  ARCv2: ioremap: Support dynamic peripheral address space
  ARC: dma: reintroduce platform specific dma<->phys
  ARC: dma: ioremap: use phys_addr_t consistenctly in code paths
  ARC: dma: pass_phys() not sg_virt() to cache ops
  ARC: dma: non-coherent pages need V-P mapping if in HIGHMEM
  ARC: dma: Use struct page based page allocator helpers
  ARC: build: Turn off -Wmaybe-uninitialized for ARC gcc 4.8
  ARC: [plat-axs10x] add Ethernet PHY description in .dts
  arc: use of_platform_default_populate() to populate default bus
  ARC: thp: unbork !CONFIG_TRANSPARENT_HUGEPAGE build
  arc: [plat-nsimosci*] use ezchip network driver
  ARCv2: LLSC: software backoff is NOT needed starting HS2.1c
  ARC: mm: Use virt_to_pfn() for addr >> PAGE_SHIFT pattern
  ARC: [plat-nsim] document ranges
  ARC: build: Better way to detect ISA compatible toolchain
  ARCv2: Allow enabling PAE40 w/o HIGHMEM
  ARC: [BE] readl()/writel() to work in Big Endian CPU configuration
  ARC: [*defconfig] No need to specify CONFIG_CROSS_COMPILE
  ARC: [BE] Select correct CROSS_COMPILE prefix
  ARC: bitops: Remove non relevant comments
  ...

38 files changed, 201 insertions, 155 deletions

diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 07a5cb9..208aae0 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -391,7 +391,7 @@ config ARC_HAS_LLSC
 
 config ARC_STAR_9000923308
 	bool "Workaround for llock/scond livelock"
-	default y
+	default n
 	depends on ISA_ARCV2 && SMP && ARC_HAS_LLSC
 
 config ARC_HAS_SWAPE
@@ -462,7 +462,6 @@ config ARC_HAS_PAE40
 	bool "Support for the 40-bit Physical Address Extension"
 	default n
 	depends on ISA_ARCV2
-	select HIGHMEM
 	help
 	  Enable access to physical memory beyond 4G, only supported on
 	  ARC cores with 40 bit Physical Addressing support
@@ -473,6 +472,9 @@ config ARCH_PHYS_ADDR_T_64BIT
 config ARCH_DMA_ADDR_T_64BIT
 	bool
 
+config ARC_PLAT_NEEDS_PHYS_TO_DMA
+	bool
+
 config ARC_CURR_IN_REG
 	bool "Dedicate Register r25 for current_task pointer"
 	default y
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index c8230f3..def69e3 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -9,7 +9,11 @@
 UTS_MACHINE := arc
 
 ifeq ($(CROSS_COMPILE),)
+ifndef CONFIG_CPU_BIG_ENDIAN
 CROSS_COMPILE := arc-linux-
+else
+CROSS_COMPILE := arceb-linux-
+endif
 endif
 
 KBUILD_DEFCONFIG := nsim_700_defconfig
@@ -18,6 +22,20 @@ cflags-y	+= -fno-common -pipe -fno-builtin -D__linux__
 cflags-$(CONFIG_ISA_ARCOMPACT)	+= -mA7
 cflags-$(CONFIG_ISA_ARCV2)	+= -mcpu=archs
 
+is_700 = $(shell $(CC) -dM -E - < /dev/null | grep -q "ARC700" && echo 1 || echo 0)
+
+ifdef CONFIG_ISA_ARCOMPACT
+ifeq ($(is_700), 0)
+    $(error Toolchain not configured for ARCompact builds)
+endif
+endif
+
+ifdef CONFIG_ISA_ARCV2
+ifeq ($(is_700), 1)
+    $(error Toolchain not configured for ARCv2 builds)
+endif
+endif
+
 ifdef CONFIG_ARC_CURR_IN_REG
 # For a global register defintion, make sure it gets passed to every file
 # We had a customer reported bug where some code built in kernel was NOT using
@@ -58,7 +76,9 @@ endif
 ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE
 # Generic build system uses -O2, we want -O3
 # Note: No need to add to cflags-y as that happens anyways
-ARCH_CFLAGS += -O3
+#
+# Disable the false maybe-uninitialized warings gcc spits out at -O3
+ARCH_CFLAGS += -O3 $(call cc-disable-warning,maybe-uninitialized,)
 endif
 
 # small data is default for elf32 tool-chain. If not usable, disable it
diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi
index 44a578c..ab5d570 100644
--- a/arch/arc/boot/dts/axs10x_mb.dtsi
+++ b/arch/arc/boot/dts/axs10x_mb.dtsi
@@ -47,6 +47,14 @@
 			clocks = <&apbclk>;
 			clock-names = "stmmaceth";
 			max-speed = <100>;
+			mdio0 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "snps,dwmac-mdio";
+				phy1: ethernet-phy@1 {
+					reg = <1>;
+				};
+			};
 		};
 
 		ehci@0x40000 {
diff --git a/arch/arc/boot/dts/nsim_hs.dts b/arch/arc/boot/dts/nsim_hs.dts
index fc81879..f46633e 100644
--- a/arch/arc/boot/dts/nsim_hs.dts
+++ b/arch/arc/boot/dts/nsim_hs.dts
@@ -35,7 +35,8 @@
 		#address-cells = <1>;
 		#size-cells = <1>;
 
-		/* only perip space at end of low mem accessible */
+		/* only perip space at end of low mem accessible
+			 bus addr,   parent bus addr, size */
 		ranges = <0x80000000 0x0 0x80000000 0x80000000>;
 
 		core_intc: core-interrupt-controller {
diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts
index 1c169dc..d94b4ce 100644
--- a/arch/arc/boot/dts/nsimosci.dts
+++ b/arch/arc/boot/dts/nsimosci.dts
@@ -65,10 +65,9 @@
 		};
 
 		eth0: ethernet@f0003000 {
-			compatible = "snps,oscilan";
+			compatible = "ezchip,nps-mgt-enet";
 			reg = <0xf0003000 0x44>;
-			interrupts = <7>, <8>;
-			interrupt-names = "rx", "tx";
+			interrupts = <7>;
 		};
 	};
 };
diff --git a/arch/arc/boot/dts/nsimosci_hs.dts b/arch/arc/boot/dts/nsimosci_hs.dts
index d64a96f..034a313 100644
--- a/arch/arc/boot/dts/nsimosci_hs.dts
+++ b/arch/arc/boot/dts/nsimosci_hs.dts
@@ -65,10 +65,9 @@
 		};
 
 		eth0: ethernet@f0003000 {
-			compatible = "snps,oscilan";
+			compatible = "ezchip,nps-mgt-enet";
 			reg = <0xf0003000 0x44>;
-			interrupts = <25>, <26>;
-			interrupt-names = "rx", "tx";
+			interrupts = <25>;
 		};
 
 		arcpct0: pct {
diff --git a/arch/arc/boot/dts/nsimosci_hs_idu.dts b/arch/arc/boot/dts/nsimosci_hs_idu.dts
index f6bf0ca..8a1297e 100644
--- a/arch/arc/boot/dts/nsimosci_hs_idu.dts
+++ b/arch/arc/boot/dts/nsimosci_hs_idu.dts
@@ -85,11 +85,10 @@
 		};
 
 		eth0: ethernet@f0003000 {
-			compatible = "snps,oscilan";
+			compatible = "ezchip,nps-mgt-enet";
 			reg = <0xf0003000 0x44>;
 			interrupt-parent = <&idu_intc>;
-			interrupts = <1 2>, <2 2>;
-			interrupt-names = "rx", "tx";
+			interrupts = <1 2>;
 		};
 
 		arcpct0: pct {
diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig
index 5d4e2a0..6cdffea 100644
--- a/arch/arc/configs/axs101_defconfig
+++ b/arch/arc/configs/axs101_defconfig
@@ -1,4 +1,3 @@
-CONFIG_CROSS_COMPILE="arc-linux-"
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig
index 87ee46b..f8b396c 100644
--- a/arch/arc/configs/axs103_defconfig
+++ b/arch/arc/configs/axs103_defconfig
@@ -1,4 +1,3 @@
-CONFIG_CROSS_COMPILE="arc-linux-"
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig
index d80daf4..56128ea 100644
--- a/arch/arc/configs/axs103_smp_defconfig
+++ b/arch/arc/configs/axs103_smp_defconfig
@@ -1,4 +1,3 @@
-CONFIG_CROSS_COMPILE="arc-linux-"
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig
index f410953..7314f53 100644
--- a/arch/arc/configs/nsim_700_defconfig
+++ b/arch/arc/configs/nsim_700_defconfig
@@ -1,4 +1,3 @@
-CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig
index cfaa33c..a99dc7a 100644
--- a/arch/arc/configs/nsim_hs_defconfig
+++ b/arch/arc/configs/nsim_hs_defconfig
@@ -1,4 +1,3 @@
-CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig
index bb2a8dc..59f221f 100644
--- a/arch/arc/configs/nsim_hs_smp_defconfig
+++ b/arch/arc/configs/nsim_hs_smp_defconfig
@@ -1,4 +1,3 @@
-CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig
index 646182e..42bafa5 100644
--- a/arch/arc/configs/nsimosci_defconfig
+++ b/arch/arc/configs/nsimosci_defconfig
@@ -1,4 +1,3 @@
-CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
@@ -39,6 +38,7 @@ CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
 # CONFIG_BLK_DEV is not set
 CONFIG_NETDEVICES=y
+CONFIG_EZCHIP_NPS_MANAGEMENT_ENET=y
 # CONFIG_INPUT_MOUSEDEV is not set
 CONFIG_INPUT_EVDEV=y
 # CONFIG_MOUSE_PS2_ALPS is not set
diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig
index ceca254..4bb60c1 100644
--- a/arch/arc/configs/nsimosci_hs_defconfig
+++ b/arch/arc/configs/nsimosci_hs_defconfig
@@ -1,4 +1,3 @@
-CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
@@ -40,6 +39,7 @@ CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
 # CONFIG_BLK_DEV is not set
 CONFIG_NETDEVICES=y
+CONFIG_EZCHIP_NPS_MANAGEMENT_ENET=y
 CONFIG_INPUT_EVDEV=y
 # CONFIG_MOUSE_PS2_ALPS is not set
 # CONFIG_MOUSE_PS2_LOGIPS2PP is not set
diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig
index 4b6da90..7e88f4c 100644
--- a/arch/arc/configs/nsimosci_hs_smp_defconfig
+++ b/arch/arc/configs/nsimosci_hs_smp_defconfig
@@ -1,4 +1,3 @@
-CONFIG_CROSS_COMPILE="arc-linux-"
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
@@ -21,6 +20,7 @@ CONFIG_MODULES=y
 CONFIG_ARC_PLAT_SIM=y
 CONFIG_ISA_ARCV2=y
 CONFIG_SMP=y
+# CONFIG_ARC_HAS_GFRC is not set
 CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci_hs_idu"
 CONFIG_PREEMPT=y
 # CONFIG_COMPACTION is not set
@@ -46,6 +46,7 @@ CONFIG_NETDEVICES=y
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+CONFIG_EZCHIP_NPS_MANAGEMENT_ENET=y
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig
index 9b342ea..4c51183 100644
--- a/arch/arc/configs/tb10x_defconfig
+++ b/arch/arc/configs/tb10x_defconfig
@@ -1,4 +1,3 @@
-CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="tb10x"
 CONFIG_SYSVIPC=y
diff --git a/arch/arc/configs/vdk_hs38_defconfig b/arch/arc/configs/vdk_hs38_defconfig
index a07f20d..c0d6a01 100644
--- a/arch/arc/configs/vdk_hs38_defconfig
+++ b/arch/arc/configs/vdk_hs38_defconfig
@@ -1,4 +1,3 @@
-CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_CROSS_MEMORY_ATTACH is not set
diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig
index 7359859..52ec315 100644
--- a/arch/arc/configs/vdk_hs38_smp_defconfig
+++ b/arch/arc/configs/vdk_hs38_smp_defconfig
@@ -1,4 +1,3 @@
-CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_CROSS_MEMORY_ATTACH is not set
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index f9f4c6f..7fbaea0 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -381,12 +381,6 @@ static inline int is_isa_arcompact(void)
 	return IS_ENABLED(CONFIG_ISA_ARCOMPACT);
 }
 
-#if defined(CONFIG_ISA_ARCOMPACT) && !defined(_CPU_DEFAULT_A7)
-#error "Toolchain not configured for ARCompact builds"
-#elif defined(CONFIG_ISA_ARCV2) && !defined(_CPU_DEFAULT_HS)
-#error "Toolchain not configured for ARCv2 builds"
-#endif
-
 #endif /* __ASEMBLY__ */
 
 #endif /* _ASM_ARC_ARCREGS_H */
diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h
index 57c1f33..0352fb8 100644
--- a/arch/arc/include/asm/bitops.h
+++ b/arch/arc/include/asm/bitops.h
@@ -35,21 +35,6 @@ static inline void op##_bit(unsigned long nr, volatile unsigned long *m)\
 									\
 	m += nr >> 5;							\
 									\
-	/*								\
-	 * ARC ISA micro-optimization:					\
-	 *								\
-	 * Instructions dealing with bitpos only consider lower 5 bits	\
-	 * e.g (x << 33) is handled like (x << 1) by ASL instruction	\
-	 *  (mem pointer still needs adjustment to point to next word)	\
-	 *								\
-	 * Hence the masking to clamp @nr arg can be elided in general.	\
-	 *								\
-	 * However if @nr is a constant (above assumed in a register),	\
-	 * and greater than 31, gcc can optimize away (x << 33) to 0,	\
-	 * as overflow, given the 32-bit ISA. Thus masking needs to be	\
-	 * done for const @nr, but no code is generated due to gcc	\
-	 * const prop.							\
-	 */								\
 	nr &= 0x1f;							\
 									\
 	__asm__ __volatile__(						\
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index 210ef3e..23706c6 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -54,6 +54,7 @@ extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len);
 extern void read_decode_cache_bcr(void);
 
 extern int ioc_exists;
+extern unsigned long perip_base;
 
 #endif	/* !__ASSEMBLY__ */
 
diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h
index fbe3587..a093adb 100644
--- a/arch/arc/include/asm/cacheflush.h
+++ b/arch/arc/include/asm/cacheflush.h
@@ -40,9 +40,9 @@ void __flush_dcache_page(phys_addr_t paddr, unsigned long vaddr);
 
 void flush_dcache_page(struct page *page);
 
-void dma_cache_wback_inv(unsigned long start, unsigned long sz);
-void dma_cache_inv(unsigned long start, unsigned long sz);
-void dma_cache_wback(unsigned long start, unsigned long sz);
+void dma_cache_wback_inv(phys_addr_t start, unsigned long sz);
+void dma_cache_inv(phys_addr_t start, unsigned long sz);
+void dma_cache_wback(phys_addr_t start, unsigned long sz);
 
 #define flush_dcache_mmap_lock(mapping)		do { } while (0)
 #define flush_dcache_mmap_unlock(mapping)	do { } while (0)
diff --git a/arch/arc/include/asm/cmpxchg.h b/arch/arc/include/asm/cmpxchg.h
index af7a2db..a444be6 100644
--- a/arch/arc/include/asm/cmpxchg.h
+++ b/arch/arc/include/asm/cmpxchg.h
@@ -149,7 +149,7 @@ static inline unsigned long __xchg(unsigned long val, volatile void *ptr,
  * Since xchg() doesn't always do that, it would seem that following defintion
  * is incorrect. But here's the rationale:
  *   SMP : Even xchg() takes the atomic_ops_lock, so OK.
- *   LLSC: atomic_ops_lock are not relevent at all (even if SMP, since LLSC
+ *   LLSC: atomic_ops_lock are not relevant at all (even if SMP, since LLSC
  *         is natively "SMP safe", no serialization required).
  *   UP  : other atomics disable IRQ, so no way a difft ctxt atomic_xchg()
  *         could clobber them. atomic_xchg() itself would be 1 insn, so it
diff --git a/arch/arc/include/asm/dma-mapping.h b/arch/arc/include/asm/dma-mapping.h
index 6602054..266f11c 100644
--- a/arch/arc/include/asm/dma-mapping.h
+++ b/arch/arc/include/asm/dma-mapping.h
@@ -11,6 +11,13 @@
 #ifndef ASM_ARC_DMA_MAPPING_H
 #define ASM_ARC_DMA_MAPPING_H
 
+#ifndef CONFIG_ARC_PLAT_NEEDS_PHYS_TO_DMA
+#define plat_dma_to_phys(dev, dma_handle) ((phys_addr_t)(dma_handle))
+#define plat_phys_to_dma(dev, paddr) ((dma_addr_t)(paddr))
+#else
+#include <plat/dma.h>
+#endif
+
 extern struct dma_map_ops arc_dma_ops;
 
 static inline struct dma_map_ops *get_dma_ops(struct device *dev)
diff --git a/arch/arc/include/asm/entry-compact.h b/arch/arc/include/asm/entry-compact.h
index 1aff3be..1d8f57c 100644
--- a/arch/arc/include/asm/entry-compact.h
+++ b/arch/arc/include/asm/entry-compact.h
@@ -231,7 +231,7 @@
 	/* free up r9 as scratchpad */
 	PROLOG_FREEUP_REG r9, @int\LVL\()_saved_reg
 
-	/* Which mode (user/kernel) was the system in when intr occured */
+	/* Which mode (user/kernel) was the system in when intr occurred */
 	lr  r9, [status32_l\LVL\()]
 
 	SWITCH_TO_KERNEL_STK
diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h
index 947bf0c..17f85c9 100644
--- a/arch/arc/include/asm/io.h
+++ b/arch/arc/include/asm/io.h
@@ -13,8 +13,8 @@
 #include <asm/byteorder.h>
 #include <asm/page.h>
 
-extern void __iomem *ioremap(unsigned long physaddr, unsigned long size);
-extern void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size,
+extern void __iomem *ioremap(phys_addr_t paddr, unsigned long size);
+extern void __iomem *ioremap_prot(phys_addr_t paddr, unsigned long size,
 				  unsigned long flags);
 static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
 {
@@ -138,15 +138,23 @@ static inline void __raw_writel(u32 w, volatile void __iomem *addr)
 #define writel(v,c)		({ __iowmb(); writel_relaxed(v,c); })
 
 /*
- * Relaxed API for drivers which can handle any ordering themselves
+ * Relaxed API for drivers which can handle barrier ordering themselves
+ *
+ * Also these are defined to perform little endian accesses.
+ * To provide the typical device register semantics of fixed endian,
+ * swap the byte order for Big Endian
+ *
+ * http://lkml.kernel.org/r/201603100845.30602.arnd@arndb.de
  */
 #define readb_relaxed(c)	__raw_readb(c)
-#define readw_relaxed(c)	__raw_readw(c)
-#define readl_relaxed(c)	__raw_readl(c)
+#define readw_relaxed(c) ({ u16 __r = le16_to_cpu((__force __le16) \
+					__raw_readw(c)); __r; })
+#define readl_relaxed(c) ({ u32 __r = le32_to_cpu((__force __le32) \
+					__raw_readl(c)); __r; })
 
 #define writeb_relaxed(v,c)	__raw_writeb(v,c)
-#define writew_relaxed(v,c)	__raw_writew(v,c)
-#define writel_relaxed(v,c)	__raw_writel(v,c)
+#define writew_relaxed(v,c)	__raw_writew((__force u16) cpu_to_le16(v),c)
+#define writel_relaxed(v,c)	__raw_writel((__force u32) cpu_to_le32(v),c)
 
 #include <asm-generic/io.h>
 
diff --git a/arch/arc/include/asm/page.h b/arch/arc/include/asm/page.h
index 429957f..9a7cf52 100644
--- a/arch/arc/include/asm/page.h
+++ b/arch/arc/include/asm/page.h
@@ -10,7 +10,6 @@
 
 #include <uapi/asm/page.h>
 
-
 #ifndef __ASSEMBLY__
 
 #define get_user_page(vaddr)		__get_free_page(GFP_KERNEL)
@@ -76,30 +75,26 @@ typedef unsigned long pgprot_t;
 
 typedef pte_t * pgtable_t;
 
-#define ARCH_PFN_OFFSET     (CONFIG_LINUX_LINK_BASE >> PAGE_SHIFT)
+#define virt_to_pfn(kaddr)	(__pa(kaddr) >> PAGE_SHIFT)
+
+#define ARCH_PFN_OFFSET		virt_to_pfn(CONFIG_LINUX_LINK_BASE)
 
-#define pfn_valid(pfn)      (((pfn) - ARCH_PFN_OFFSET) < max_mapnr)
+#define pfn_valid(pfn)		(((pfn) - ARCH_PFN_OFFSET) < max_mapnr)
 
 /*
  * __pa, __va, virt_to_page (ALERT: deprecated, don't use them)
  *
  * These macros have historically been misnamed
  * virt here means link-address/program-address as embedded in object code.
- * So if kernel img is linked at 0x8000_0000 onwards, 0x8010_0000 will be
- * 128th page, and virt_to_page( ) will return the struct page corresp to it.
- * mem_map[ ] is an array of struct page for each page frame in the system
- *
- * Independent of where linux is linked at, link-addr = physical address
- * So the old macro  __pa = vaddr + PAGE_OFFSET - CONFIG_LINUX_LINK_BASE
- * would have been wrong in case kernel is not at 0x8zs
+ * And for ARC, link-addr = physical address
  */
 #define __pa(vaddr)  ((unsigned long)vaddr)
 #define __va(paddr)  ((void *)((unsigned long)(paddr)))
 
 #define virt_to_page(kaddr)	\
-	(mem_map + ((__pa(kaddr) - CONFIG_LINUX_LINK_BASE) >> PAGE_SHIFT))
+	(mem_map + virt_to_pfn((kaddr) - CONFIG_LINUX_LINK_BASE))
 
-#define virt_addr_valid(kaddr)  pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
+#define virt_addr_valid(kaddr)  pfn_valid(virt_to_pfn(kaddr))
 
 /* Default Permissions for stack/heaps pages (Non Executable) */
 #define VM_DATA_DEFAULT_FLAGS   (VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE)
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index d426d42..7d6c93e 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -12,7 +12,7 @@
  *  - Utilise some unused free bits to confine PTE flags to 12 bits
  *     This is a must for 4k pg-sz
  *
- * vineetg: Mar 2011 - changes to accomodate MMU TLB Page Descriptor mods
+ * vineetg: Mar 2011 - changes to accommodate MMU TLB Page Descriptor mods
  *  -TLB Locking never really existed, except for initial specs
  *  -SILENT_xxx not needed for our port
  *  -Per my request, MMU V3 changes the layout of some of the bits
@@ -278,15 +278,14 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep)
 #define pmd_present(x)			(pmd_val(x))
 #define pmd_clear(xp)			do { pmd_val(*(xp)) = 0; } while (0)
 
-#define pte_page(x) (mem_map + \
-		(unsigned long)(((pte_val(x) - CONFIG_LINUX_LINK_BASE) >> \
-				PAGE_SHIFT)))
+#define pte_page(pte)	\
+	(mem_map + virt_to_pfn(pte_val(pte) - CONFIG_LINUX_LINK_BASE))
 
 #define mk_pte(page, prot)	pfn_pte(page_to_pfn(page), prot)
-#define pte_pfn(pte)		(pte_val(pte) >> PAGE_SHIFT)
+#define pte_pfn(pte)		virt_to_pfn(pte_val(pte))
 #define pfn_pte(pfn, prot)	(__pte(((pte_t)(pfn) << PAGE_SHIFT) | \
 				 pgprot_val(prot)))
-#define __pte_index(addr)	(((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+#define __pte_index(addr)	(virt_to_pfn(addr) & (PTRS_PER_PTE - 1))
 
 /*
  * pte_offset gets a @ptr to PMD entry (PGD in our 2-tier paging system)
diff --git a/arch/arc/include/asm/tlbflush.h b/arch/arc/include/asm/tlbflush.h
index 1fe9c8c..f0d42f1 100644
--- a/arch/arc/include/asm/tlbflush.h
+++ b/arch/arc/include/asm/tlbflush.h
@@ -17,8 +17,10 @@ void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long page);
 void local_flush_tlb_kernel_range(unsigned long start, unsigned long end);
 void local_flush_tlb_range(struct vm_area_struct *vma,
 			   unsigned long start, unsigned long end);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void local_flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			       unsigned long end);
+#endif
 
 #ifndef CONFIG_SMP
 #define flush_tlb_range(vma, s, e)	local_flush_tlb_range(vma, s, e)
@@ -26,7 +28,9 @@ void local_flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
 #define flush_tlb_kernel_range(s, e)	local_flush_tlb_kernel_range(s, e)
 #define flush_tlb_all()			local_flush_tlb_all()
 #define flush_tlb_mm(mm)		local_flush_tlb_mm(mm)
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define flush_pmd_tlb_range(vma, s, e)	local_flush_pmd_tlb_range(vma, s, e)
+#endif
 #else
 extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 							 unsigned long end);
@@ -34,7 +38,8 @@ extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long page);
 extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
 extern void flush_tlb_all(void);
 extern void flush_tlb_mm(struct mm_struct *mm);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 extern void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
-
+#endif
 #endif /* CONFIG_SMP */
 #endif
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index cdc821d..151acf0 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -91,11 +91,9 @@ static void read_decode_ccm_bcr(struct cpuinfo_arc *cpu)
 
 static void read_arc_build_cfg_regs(void)
 {
-	struct bcr_perip uncached_space;
 	struct bcr_timer timer;
 	struct bcr_generic bcr;
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
-	unsigned long perip_space;
 	FIX_PTR(cpu);
 
 	READ_BCR(AUX_IDENTITY, cpu->core);
@@ -108,14 +106,6 @@ static void read_arc_build_cfg_regs(void)
 
 	cpu->vec_base = read_aux_reg(AUX_INTR_VEC_BASE);
 
-	READ_BCR(ARC_REG_D_UNCACH_BCR, uncached_space);
-        if (uncached_space.ver < 3)
-		perip_space = uncached_space.start << 24;
-	else
-		perip_space = read_aux_reg(AUX_NON_VOL) & 0xF0000000;
-
-	BUG_ON(perip_space != ARC_UNCACHED_ADDR_SPACE);
-
 	READ_BCR(ARC_REG_MUL_BCR, cpu->extn_mpy);
 
 	cpu->extn.norm = read_aux_reg(ARC_REG_NORM_BCR) > 1 ? 1 : 0; /* 2,3 */
@@ -288,8 +278,8 @@ 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\nUncached Base\t: %#x\n",
-		       cpu->vec_base, ARC_UNCACHED_ADDR_SPACE);
+		       "Vector Table\t: %#x\nUncached Base\t: %#lx\n",
+		       cpu->vec_base, perip_base);
 
 	if (cpu->extn.fpu_sp || cpu->extn.fpu_dp)
 		n += scnprintf(buf + n, len - n, "FPU\t\t: %s%s\n",
@@ -357,11 +347,6 @@ static void arc_chk_core_config(void)
 		pr_warn("CONFIG_ARC_FPU_SAVE_RESTORE needed for working apps\n");
 	else if (!cpu->extn.fpu_dp && fpu_enabled)
 		panic("FPU non-existent, disable CONFIG_ARC_FPU_SAVE_RESTORE\n");
-
-	if (is_isa_arcv2() && IS_ENABLED(CONFIG_SMP) && cpu->isa.atomic &&
-	    IS_ENABLED(CONFIG_ARC_HAS_LLSC) &&
-	    !IS_ENABLED(CONFIG_ARC_STAR_9000923308))
-		panic("llock/scond livelock workaround missing\n");
 }
 
 /*
@@ -464,7 +449,7 @@ static int __init customize_machine(void)
 	 * Traverses flattened DeviceTree - registering platform devices
 	 * (if any) complete with their resources
 	 */
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
+	of_platform_default_populate(NULL, NULL, NULL);
 
 	if (machine_desc->init_machine)
 		machine_desc->init_machine();
diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c
index 001de4c..e0efff1 100644
--- a/arch/arc/kernel/stacktrace.c
+++ b/arch/arc/kernel/stacktrace.c
@@ -232,7 +232,7 @@ void show_stack(struct task_struct *tsk, unsigned long *sp)
 }
 
 /* Another API expected by schedular, shows up in "ps" as Wait Channel
- * Ofcourse just returning schedule( ) would be pointless so unwind until
+ * Of course just returning schedule( ) would be pointless so unwind until
  * the function is not in schedular code
  */
 unsigned int get_wchan(struct task_struct *tsk)
diff --git a/arch/arc/kernel/time.c b/arch/arc/kernel/time.c
index 156d983..7d9a736 100644
--- a/arch/arc/kernel/time.c
+++ b/arch/arc/kernel/time.c
@@ -55,8 +55,8 @@
 #define ARC_REG_TIMER1_CTRL	0x101	/* timer 1 control */
 #define ARC_REG_TIMER1_CNT	0x100	/* timer 1 count */
 
-#define TIMER_CTRL_IE		(1 << 0) /* Interupt when Count reachs limit */
-#define TIMER_CTRL_NH		(1 << 1) /* Count only when CPU NOT halted */
+#define TIMER_CTRL_IE	(1 << 0) /* Interrupt when Count reaches limit */
+#define TIMER_CTRL_NH	(1 << 1) /* Count only when CPU NOT halted */
 
 #define ARC_TIMER_MAX	0xFFFFFFFF
 
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index b65f797..d7709e3 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -24,13 +24,14 @@
 static int l2_line_sz;
 int ioc_exists;
 volatile int slc_enable = 1, ioc_enable = 1;
+unsigned long perip_base = ARC_UNCACHED_ADDR_SPACE; /* legacy value for boot */
 
 void (*_cache_line_loop_ic_fn)(phys_addr_t paddr, unsigned long vaddr,
 			       unsigned long sz, const int cacheop);
 
-void (*__dma_cache_wback_inv)(unsigned long start, unsigned long sz);
-void (*__dma_cache_inv)(unsigned long start, unsigned long sz);
-void (*__dma_cache_wback)(unsigned long start, unsigned long sz);
+void (*__dma_cache_wback_inv)(phys_addr_t start, unsigned long sz);
+void (*__dma_cache_inv)(phys_addr_t start, unsigned long sz);
+void (*__dma_cache_wback)(phys_addr_t start, unsigned long sz);
 
 char *arc_cache_mumbojumbo(int c, char *buf, int len)
 {
@@ -75,6 +76,7 @@ char *arc_cache_mumbojumbo(int c, char *buf, int len)
 static void read_decode_cache_bcr_arcv2(int cpu)
 {
 	struct cpuinfo_arc_cache *p_slc = &cpuinfo_arc700[cpu].slc;
+	struct bcr_generic uncached_space;
 	struct bcr_generic sbcr;
 
 	struct bcr_slc_cfg {
@@ -104,6 +106,11 @@ static void read_decode_cache_bcr_arcv2(int cpu)
 	READ_BCR(ARC_REG_CLUSTER_BCR, cbcr);
 	if (cbcr.c && ioc_enable)
 		ioc_exists = 1;
+
+	/* Legacy Data Uncached BCR is deprecated from v3 onwards */
+	READ_BCR(ARC_REG_D_UNCACH_BCR, uncached_space);
+	if (uncached_space.ver > 2)
+		perip_base = read_aux_reg(AUX_NON_VOL) & 0xF0000000;
 }
 
 void read_decode_cache_bcr(void)
@@ -633,38 +640,38 @@ EXPORT_SYMBOL(flush_dcache_page);
  * DMA ops for systems with L1 cache only
  * Make memory coherent with L1 cache by flushing/invalidating L1 lines
  */
-static void __dma_cache_wback_inv_l1(unsigned long start, unsigned long sz)
+static void __dma_cache_wback_inv_l1(phys_addr_t start, unsigned long sz)
 {
 	__dc_line_op_k(start, sz, OP_FLUSH_N_INV);
 }
 
-static void __dma_cache_inv_l1(unsigned long start, unsigned long sz)
+static void __dma_cache_inv_l1(phys_addr_t start, unsigned long sz)
 {
 	__dc_line_op_k(start, sz, OP_INV);
 }
 
-static void __dma_cache_wback_l1(unsigned long start, unsigned long sz)
+static void __dma_cache_wback_l1(phys_addr_t start, unsigned long sz)
 {
 	__dc_line_op_k(start, sz, OP_FLUSH);
 }
 
 /*
  * DMA ops for systems with both L1 and L2 caches, but without IOC
- * Both L1 and L2 lines need to be explicity flushed/invalidated
+ * Both L1 and L2 lines need to be explicitly flushed/invalidated
  */
-static void __dma_cache_wback_inv_slc(unsigned long start, unsigned long sz)
+static void __dma_cache_wback_inv_slc(phys_addr_t start, unsigned long sz)
 {
 	__dc_line_op_k(start, sz, OP_FLUSH_N_INV);
 	slc_op(start, sz, OP_FLUSH_N_INV);
 }
 
-static void __dma_cache_inv_slc(unsigned long start, unsigned long sz)
+static void __dma_cache_inv_slc(phys_addr_t start, unsigned long sz)
 {
 	__dc_line_op_k(start, sz, OP_INV);
 	slc_op(start, sz, OP_INV);
 }
 
-static void __dma_cache_wback_slc(unsigned long start, unsigned long sz)
+static void __dma_cache_wback_slc(phys_addr_t start, unsigned long sz)
 {
 	__dc_line_op_k(start, sz, OP_FLUSH);
 	slc_op(start, sz, OP_FLUSH);
@@ -675,26 +682,26 @@ static void __dma_cache_wback_slc(unsigned long start, unsigned long sz)
  * IOC hardware snoops all DMA traffic keeping the caches consistent with
  * memory - eliding need for any explicit cache maintenance of DMA buffers
  */
-static void __dma_cache_wback_inv_ioc(unsigned long start, unsigned long sz) {}
-static void __dma_cache_inv_ioc(unsigned long start, unsigned long sz) {}
-static void __dma_cache_wback_ioc(unsigned long start, unsigned long sz) {}
+static void __dma_cache_wback_inv_ioc(phys_addr_t start, unsigned long sz) {}
+static void __dma_cache_inv_ioc(phys_addr_t start, unsigned long sz) {}
+static void __dma_cache_wback_ioc(phys_addr_t start, unsigned long sz) {}
 
 /*
  * Exported DMA API
  */
-void dma_cache_wback_inv(unsigned long start, unsigned long sz)
+void dma_cache_wback_inv(phys_addr_t start, unsigned long sz)
 {
 	__dma_cache_wback_inv(start, sz);
 }
 EXPORT_SYMBOL(dma_cache_wback_inv);
 
-void dma_cache_inv(unsigned long start, unsigned long sz)
+void dma_cache_inv(phys_addr_t start, unsigned long sz)
 {
 	__dma_cache_inv(start, sz);
 }
 EXPORT_SYMBOL(dma_cache_inv);
 
-void dma_cache_wback(unsigned long start, unsigned long sz)
+void dma_cache_wback(phys_addr_t start, unsigned long sz)
 {
 	__dma_cache_wback(start, sz);
 }
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 01eaf88..8c8e36f 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -24,22 +24,22 @@
 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, *kvaddr;
-
-	/* This is linear addr (0x8000_0000 based) */
-	paddr = alloc_pages_exact(size, gfp);
-	if (!paddr)
+	unsigned long order = get_order(size);
+	struct page *page;
+	phys_addr_t paddr;
+	void *kvaddr;
+	int need_coh = 1, need_kvaddr = 0;
+
+	page = alloc_pages(gfp, order);
+	if (!page)
 		return NULL;
 
-	/* This is bus address, platform dependent */
-	*dma_handle = (dma_addr_t)paddr;
-
 	/*
 	 * IOC relies on all data (even coherent DMA data) being in cache
 	 * Thus allocate normal cached memory
 	 *
 	 * The gains with IOC are two pronged:
-	 *   -For streaming data, elides needs for cache maintenance, saving
+	 *   -For streaming data, elides need for cache maintenance, saving
 	 *    cycles in flush code, and bus bandwidth as all the lines of a
 	 *    buffer need to be flushed out to memory
 	 *   -For coherent data, Read/Write to buffers terminate early in cache
@@ -47,12 +47,31 @@ static void *arc_dma_alloc(struct device *dev, size_t size,
 	 */
 	if ((is_isa_arcv2() && ioc_exists) ||
 	    dma_get_attr(DMA_ATTR_NON_CONSISTENT, attrs))
-		return paddr;
+		need_coh = 0;
+
+	/*
+	 * - A coherent buffer needs MMU mapping to enforce non-cachability
+	 * - A highmem page needs a virtual handle (hence MMU mapping)
+	 *   independent of cachability
+	 */
+	if (PageHighMem(page) || need_coh)
+		need_kvaddr = 1;
+
+	/* This is linear addr (0x8000_0000 based) */
+	paddr = page_to_phys(page);
+
+	*dma_handle = plat_phys_to_dma(dev, paddr);
 
 	/* This is kernel Virtual address (0x7000_0000 based) */
-	kvaddr = ioremap_nocache((unsigned long)paddr, size);
-	if (kvaddr == NULL)
-		return NULL;
+	if (need_kvaddr) {
+		kvaddr = ioremap_nocache(paddr, size);
+		if (kvaddr == NULL) {
+			__free_pages(page, order);
+			return NULL;
+		}
+	} else {
+		kvaddr = (void *)(u32)paddr;
+	}
 
 	/*
 	 * Evict any existing L1 and/or L2 lines for the backing page
@@ -64,7 +83,8 @@ static void *arc_dma_alloc(struct device *dev, size_t size,
 	 * Currently flush_cache_vmap nukes the L1 cache completely which
 	 * will be optimized as a separate commit
 	 */
-	dma_cache_wback_inv((unsigned long)paddr, size);
+	if (need_coh)
+		dma_cache_wback_inv(paddr, size);
 
 	return kvaddr;
 }
@@ -72,11 +92,16 @@ static void *arc_dma_alloc(struct device *dev, size_t size,
 static void arc_dma_free(struct device *dev, size_t size, void *vaddr,
 		dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
-	if (!dma_get_attr(DMA_ATTR_NON_CONSISTENT, attrs) &&
-	    !(is_isa_arcv2() && ioc_exists))
+	struct page *page = virt_to_page(dma_handle);
+	int is_non_coh = 1;
+
+	is_non_coh = dma_get_attr(DMA_ATTR_NON_CONSISTENT, attrs) ||
+			(is_isa_arcv2() && ioc_exists);
+
+	if (PageHighMem(page) || !is_non_coh)
 		iounmap((void __force __iomem *)vaddr);
 
-	free_pages_exact((void *)dma_handle, size);
+	__free_pages(page, get_order(size));
 }
 
 /*
@@ -84,7 +109,7 @@ static void arc_dma_free(struct device *dev, size_t size, void *vaddr,
  * CPU accesses page via normal paddr, thus needs to explicitly made
  * consistent before each use
  */
-static void _dma_cache_sync(unsigned long paddr, size_t size,
+static void _dma_cache_sync(phys_addr_t paddr, size_t size,
 		enum dma_data_direction dir)
 {
 	switch (dir) {
@@ -98,7 +123,7 @@ static void _dma_cache_sync(unsigned long paddr, size_t size,
 		dma_cache_wback_inv(paddr, size);
 		break;
 	default:
-		pr_err("Invalid DMA dir [%d] for OP @ %lx\n", dir, paddr);
+		pr_err("Invalid DMA dir [%d] for OP @ %pa[p]\n", dir, &paddr);
 	}
 }
 
@@ -106,9 +131,9 @@ 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;
+	phys_addr_t paddr = page_to_phys(page) + offset;
 	_dma_cache_sync(paddr, size, dir);
-	return (dma_addr_t)paddr;
+	return plat_phys_to_dma(dev, paddr);
 }
 
 static int arc_dma_map_sg(struct device *dev, struct scatterlist *sg,
@@ -127,13 +152,13 @@ static int arc_dma_map_sg(struct device *dev, struct scatterlist *sg,
 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);
+	_dma_cache_sync(plat_dma_to_phys(dev, 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)
 {
-	_dma_cache_sync(dma_handle, size, DMA_TO_DEVICE);
+	_dma_cache_sync(plat_dma_to_phys(dev, dma_handle), size, DMA_TO_DEVICE);
 }
 
 static void arc_dma_sync_sg_for_cpu(struct device *dev,
@@ -144,7 +169,7 @@ static void arc_dma_sync_sg_for_cpu(struct device *dev,
 	struct scatterlist *sg;
 
 	for_each_sg(sglist, sg, nelems, i)
-		_dma_cache_sync((unsigned int)sg_virt(sg), sg->length, dir);
+		_dma_cache_sync(sg_phys(sg), sg->length, dir);
 }
 
 static void arc_dma_sync_sg_for_device(struct device *dev,
@@ -155,7 +180,7 @@ static void arc_dma_sync_sg_for_device(struct device *dev,
 	struct scatterlist *sg;
 
 	for_each_sg(sglist, sg, nelems, i)
-		_dma_cache_sync((unsigned int)sg_virt(sg), sg->length, dir);
+		_dma_cache_sync(sg_phys(sg), sg->length, dir);
 }
 
 static int arc_dma_supported(struct device *dev, u64 dma_mask)
diff --git a/arch/arc/mm/highmem.c b/arch/arc/mm/highmem.c
index 92dd92c..04f8332 100644
--- a/arch/arc/mm/highmem.c
+++ b/arch/arc/mm/highmem.c
@@ -18,7 +18,7 @@
 /*
  * HIGHMEM API:
  *
- * kmap() API provides sleep semantics hence refered to as "permanent maps"
+ * kmap() API provides sleep semantics hence referred to as "permanent maps"
  * It allows mapping LAST_PKMAP pages, using @last_pkmap_nr as the cursor
  * for book-keeping
  *
diff --git a/arch/arc/mm/ioremap.c b/arch/arc/mm/ioremap.c
index 739e65f..49b8abd 100644
--- a/arch/arc/mm/ioremap.c
+++ b/arch/arc/mm/ioremap.c
@@ -14,18 +14,33 @@
 #include <linux/slab.h>
 #include <linux/cache.h>
 
-void __iomem *ioremap(unsigned long paddr, unsigned long size)
+static inline bool arc_uncached_addr_space(phys_addr_t paddr)
 {
-	unsigned long end;
+	if (is_isa_arcompact()) {
+		if (paddr >= ARC_UNCACHED_ADDR_SPACE)
+			return true;
+	} else if (paddr >= perip_base && paddr <= 0xFFFFFFFF) {
+		return true;
+	}
+
+	return false;
+}
+
+void __iomem *ioremap(phys_addr_t paddr, unsigned long size)
+{
+	phys_addr_t end;
 
 	/* Don't allow wraparound or zero size */
 	end = paddr + size - 1;
 	if (!size || (end < paddr))
 		return NULL;
 
-	/* If the region is h/w uncached, avoid MMU mappings */
-	if (paddr >= ARC_UNCACHED_ADDR_SPACE)
-		return (void __iomem *)paddr;
+	/*
+	 * If the region is h/w uncached, MMU mapping can be elided as optim
+	 * The cast to u32 is fine as this region can only be inside 4GB
+	 */
+	if (arc_uncached_addr_space(paddr))
+		return (void __iomem *)(u32)paddr;
 
 	return ioremap_prot(paddr, size, PAGE_KERNEL_NO_CACHE);
 }
@@ -41,9 +56,9 @@ EXPORT_SYMBOL(ioremap);
 void __iomem *ioremap_prot(phys_addr_t paddr, unsigned long size,
 			   unsigned long flags)
 {
-	void __iomem *vaddr;
+	unsigned long vaddr;
 	struct vm_struct *area;
-	unsigned long off, end;
+	phys_addr_t off, end;
 	pgprot_t prot = __pgprot(flags);
 
 	/* Don't allow wraparound, zero size */
@@ -70,9 +85,8 @@ void __iomem *ioremap_prot(phys_addr_t paddr, unsigned long size,
 	if (!area)
 		return NULL;
 	area->phys_addr = paddr;
-	vaddr = (void __iomem *)area->addr;
-	if (ioremap_page_range((unsigned long)vaddr,
-			       (unsigned long)vaddr + size, paddr, prot)) {
+	vaddr = (unsigned long)area->addr;
+	if (ioremap_page_range(vaddr, vaddr + size, paddr, prot)) {
 		vunmap((void __force *)vaddr);
 		return NULL;
 	}
@@ -83,7 +97,8 @@ EXPORT_SYMBOL(ioremap_prot);
 
 void iounmap(const void __iomem *addr)
 {
-	if (addr >= (void __force __iomem *)ARC_UNCACHED_ADDR_SPACE)
+	/* weird double cast to handle phys_addr_t > 32 bits */
+	if (arc_uncached_addr_space((phys_addr_t)(u32)addr))
 		return;
 
 	vfree((void *)(PAGE_MASK & (unsigned long __force)addr));
diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c
index daf2bf5..7046c12 100644
--- a/arch/arc/mm/tlb.c
+++ b/arch/arc/mm/tlb.c
@@ -45,7 +45,7 @@
  *       in interrupt-safe region.
  *
  * Vineetg: April 23rd Bug #93131
- *    Problem: tlb_flush_kernel_range() doesnt do anything if the range to
+ *    Problem: tlb_flush_kernel_range() doesn't do anything if the range to
  *              flush is more than the size of TLB itself.
  *
  * Rahul Trivedi : Codito Technologies 2004
@@ -167,7 +167,7 @@ static void utlb_invalidate(void)
 	/* MMU v2 introduced the uTLB Flush command.
 	 * There was however an obscure hardware bug, where uTLB flush would
 	 * fail when a prior probe for J-TLB (both totally unrelated) would
-	 * return lkup err - because the entry didnt exist in MMU.
+	 * return lkup err - because the entry didn't exist in MMU.
 	 * The Workround was to set Index reg with some valid value, prior to
 	 * flush. This was fixed in MMU v3 hence not needed any more
 	 */
@@ -210,7 +210,7 @@ static void tlb_entry_insert(unsigned int pd0, pte_t pd1)
 
 	/*
 	 * Commit the Entry to MMU
-	 * It doesnt sound safe to use the TLBWriteNI cmd here
+	 * It doesn't sound safe to use the TLBWriteNI cmd here
 	 * which doesn't flush uTLBs. I'd rather be safe than sorry.
 	 */
 	write_aux_reg(ARC_REG_TLBCOMMAND, TLBWrite);
@@ -636,7 +636,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long vaddr_unaligned,
  * support.
  *
  * Normal and Super pages can co-exist (ofcourse not overlap) in TLB with a
- * new bit "SZ" in TLB page desciptor to distinguish between them.
+ * new bit "SZ" in TLB page descriptor to distinguish between them.
  * Super Page size is configurable in hardware (4K to 16M), but fixed once
  * RTL builds.
  *