Merge tag 'arc-4.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc

Pull ARC updates from Vineet Gupta:

 - ARCv2 support for native 64-bit atomics using LLOCK/SCONDD
   instructions

 - Support for upcoming 3.0 release of HS38 cores

 - Dwarf unwindinder improvements:
   - enable unwinding of hand written assembler code using CFI
     pseudo-ops
   - switch to .eh_frame (as opposed to historic .debug_frame)
   - get rid of a bunch of adhoc band-aids in the process

 - Misc fixes:
   - perf supporting generic cache-references and cache-misses (Alexey)
   - default NODE_SHIFT (Noam Camus)
   - usage of KFLAG instruction to set IE (Yuriy)

 - Platforms:
   - Add "model" property across the DT (Alexey)
   - Enable MODULE_* in defconfigs

* tag 'arc-4.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc:
  ARC: [plat*] enables MODULE*
  ARCv2: fix local_save_flags
  ARC: CONFIG_NODES_SHIFT fix default values
  ARCv2: intc: Use kflag if STATUS32.IE must be reset
  ARC: .exit.* sections can be discarded in .eh_frame regime
  ARC: dw2 unwind: enable cfi pseudo ops in string lib
  ARC: dw2 unwind: add infrastructure for adding cfi pseudo ops to asm
  ARC: entry: make ret_from_system_call local label
  ARC: dw2 unwind: don't force dwarf 2
  ARC: dw2 unwind: switch to .eh_frame based unwinding
  ARC: dw2 unwind: factor CIE specifics for .eh_frame/.debug_frame
  ARC: module: support R_ARC_32_PCREL relocation
  arc: perf: Enable generic "cache-references" and "cache-misses" events
  ARC: [plat-eznps] add missing atomic_fetch_xxx operations
  ARCv2: Implement atomic64 based on LLOCKD/SCONDD instructions
  ARCv2: Support dynamic peripheral address space in HS38 rel 3.0 cores
  ARCv2: identify HS38 rel 3.0 cores
  ARCv2: Add support for ZeBu Emulation platform for HS cores
  arc: Add "model" properly in device tree description of all boards
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 0d3e59f..ecd1237 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -13,7 +13,7 @@
 	select CLKSRC_OF
 	select CLONE_BACKWARDS
 	select COMMON_CLK
-	select GENERIC_ATOMIC64
+	select GENERIC_ATOMIC64 if !ISA_ARCV2 || !(ARC_HAS_LL64 && ARC_HAS_LLSC)
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_FIND_FIRST_BIT
 	# for now, we don't need GENERIC_IRQ_PROBE, CONFIG_GENERIC_IRQ_CHIP
@@ -353,8 +353,8 @@
 
 config NODES_SHIFT
 	int "Maximum NUMA Nodes (as a power of 2)"
-	default "1" if !DISCONTIGMEM
-	default "2" if DISCONTIGMEM
+	default "0" if !DISCONTIGMEM
+	default "1" if DISCONTIGMEM
 	depends on NEED_MULTIPLE_NODES
 	---help---
 	  Accessing memory beyond 1GB (with or w/o PAE) requires 2 memory
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index 601ed17..aa82d13 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -47,7 +47,6 @@
 
 upto_gcc44    :=  $(call cc-ifversion, -le, 0404, y)
 atleast_gcc44 :=  $(call cc-ifversion, -ge, 0404, y)
-atleast_gcc48 :=  $(call cc-ifversion, -ge, 0408, y)
 
 cflags-$(atleast_gcc44)			+= -fsection-anchors
 
@@ -66,10 +65,8 @@
 
 endif
 
-# By default gcc 4.8 generates dwarf4 which kernel unwinder can't grok
-ifeq ($(atleast_gcc48),y)
-cflags-$(CONFIG_ARC_DW2_UNWIND)		+= -gdwarf-2
-endif
+cfi := $(call as-instr,.cfi_startproc\n.cfi_endproc,-DARC_DW2_UNWIND_AS_CFI)
+cflags-$(CONFIG_ARC_DW2_UNWIND)		+= -fasynchronous-unwind-tables $(cfi)
 
 ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE
 # Generic build system uses -O2, we want -O3
diff --git a/arch/arc/boot/dts/abilis_tb100_dvk.dts b/arch/arc/boot/dts/abilis_tb100_dvk.dts
index 3dd6ed9..3acf04d 100644
--- a/arch/arc/boot/dts/abilis_tb100_dvk.dts
+++ b/arch/arc/boot/dts/abilis_tb100_dvk.dts
@@ -24,6 +24,7 @@
 /include/ "abilis_tb100.dtsi"
 
 / {
+	model = "abilis,tb100";
 	chosen {
 		bootargs = "earlycon=uart8250,mmio32,0xff100000,9600n8 console=ttyS0,9600n8";
 	};
diff --git a/arch/arc/boot/dts/abilis_tb101_dvk.dts b/arch/arc/boot/dts/abilis_tb101_dvk.dts
index 1cf51c2..37d88c5 100644
--- a/arch/arc/boot/dts/abilis_tb101_dvk.dts
+++ b/arch/arc/boot/dts/abilis_tb101_dvk.dts
@@ -24,6 +24,7 @@
 /include/ "abilis_tb101.dtsi"
 
 / {
+	model = "abilis,tb101";
 	chosen {
 		bootargs = "earlycon=uart8250,mmio32,0xff100000,9600n8 console=ttyS0,9600n8";
 	};
diff --git a/arch/arc/boot/dts/axs101.dts b/arch/arc/boot/dts/axs101.dts
index 3f9b058..d9b9b9d 100644
--- a/arch/arc/boot/dts/axs101.dts
+++ b/arch/arc/boot/dts/axs101.dts
@@ -13,6 +13,7 @@
 /include/ "axs10x_mb.dtsi"
 
 / {
+	model = "snps,axs101";
 	compatible = "snps,axs101", "snps,arc-sdp";
 
 	chosen {
diff --git a/arch/arc/boot/dts/axs103.dts b/arch/arc/boot/dts/axs103.dts
index e6d0e31..ec7fb27 100644
--- a/arch/arc/boot/dts/axs103.dts
+++ b/arch/arc/boot/dts/axs103.dts
@@ -16,6 +16,7 @@
 /include/ "axs10x_mb.dtsi"
 
 / {
+	model = "snps,axs103";
 	compatible = "snps,axs103", "snps,arc-sdp";
 
 	chosen {
diff --git a/arch/arc/boot/dts/axs103_idu.dts b/arch/arc/boot/dts/axs103_idu.dts
index f999fef..070c297 100644
--- a/arch/arc/boot/dts/axs103_idu.dts
+++ b/arch/arc/boot/dts/axs103_idu.dts
@@ -16,6 +16,7 @@
 /include/ "axs10x_mb.dtsi"
 
 / {
+	model = "snps,axs103-smp";
 	compatible = "snps,axs103", "snps,arc-sdp";
 
 	chosen {
diff --git a/arch/arc/boot/dts/nsim_700.dts b/arch/arc/boot/dts/nsim_700.dts
index 6397051..ce0ccd20 100644
--- a/arch/arc/boot/dts/nsim_700.dts
+++ b/arch/arc/boot/dts/nsim_700.dts
@@ -10,6 +10,7 @@
 /include/ "skeleton.dtsi"
 
 / {
+	model = "snps,nsim";
 	compatible = "snps,nsim";
 	#address-cells = <1>;
 	#size-cells = <1>;
diff --git a/arch/arc/boot/dts/nsim_hs.dts b/arch/arc/boot/dts/nsim_hs.dts
index bf05fe5..3772c40 100644
--- a/arch/arc/boot/dts/nsim_hs.dts
+++ b/arch/arc/boot/dts/nsim_hs.dts
@@ -10,6 +10,7 @@
 /include/ "skeleton_hs.dtsi"
 
 / {
+	model = "snps,nsim_hs";
 	compatible = "snps,nsim_hs";
 	#address-cells = <2>;
 	#size-cells = <2>;
diff --git a/arch/arc/boot/dts/nsim_hs_idu.dts b/arch/arc/boot/dts/nsim_hs_idu.dts
index 99eabe1..48434d7c 100644
--- a/arch/arc/boot/dts/nsim_hs_idu.dts
+++ b/arch/arc/boot/dts/nsim_hs_idu.dts
@@ -10,6 +10,7 @@
 /include/ "skeleton_hs_idu.dtsi"
 
 / {
+	model = "snps,nsim_hs-smp";
 	compatible = "snps,nsim_hs";
 	interrupt-parent = <&core_intc>;
 
diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts
index e659a34..bcf6031 100644
--- a/arch/arc/boot/dts/nsimosci.dts
+++ b/arch/arc/boot/dts/nsimosci.dts
@@ -10,6 +10,7 @@
 /include/ "skeleton.dtsi"
 
 / {
+	model = "snps,nsimosci";
 	compatible = "snps,nsimosci";
 	#address-cells = <1>;
 	#size-cells = <1>;
diff --git a/arch/arc/boot/dts/nsimosci_hs.dts b/arch/arc/boot/dts/nsimosci_hs.dts
index 16ce5d6..14a727c 100644
--- a/arch/arc/boot/dts/nsimosci_hs.dts
+++ b/arch/arc/boot/dts/nsimosci_hs.dts
@@ -10,6 +10,7 @@
 /include/ "skeleton_hs.dtsi"
 
 / {
+	model = "snps,nsimosci_hs";
 	compatible = "snps,nsimosci_hs";
 	#address-cells = <1>;
 	#size-cells = <1>;
diff --git a/arch/arc/boot/dts/nsimosci_hs_idu.dts b/arch/arc/boot/dts/nsimosci_hs_idu.dts
index ce8dfbc..cbf65b6 100644
--- a/arch/arc/boot/dts/nsimosci_hs_idu.dts
+++ b/arch/arc/boot/dts/nsimosci_hs_idu.dts
@@ -10,6 +10,7 @@
 /include/ "skeleton_hs_idu.dtsi"
 
 / {
+	model = "snps,nsimosci_hs-smp";
 	compatible = "snps,nsimosci_hs";
 	#address-cells = <1>;
 	#size-cells = <1>;
diff --git a/arch/arc/boot/dts/vdk_hs38.dts b/arch/arc/boot/dts/vdk_hs38.dts
index 5d803dd..3c51103 100644
--- a/arch/arc/boot/dts/vdk_hs38.dts
+++ b/arch/arc/boot/dts/vdk_hs38.dts
@@ -13,6 +13,7 @@
 /include/ "vdk_axs10x_mb.dtsi"
 
 / {
+	model = "snps,vdk_archs";
 	compatible = "snps,axs103";
 
 	chosen {
diff --git a/arch/arc/boot/dts/vdk_hs38_smp.dts b/arch/arc/boot/dts/vdk_hs38_smp.dts
index 2ba60c39..6be6800 100644
--- a/arch/arc/boot/dts/vdk_hs38_smp.dts
+++ b/arch/arc/boot/dts/vdk_hs38_smp.dts
@@ -13,6 +13,7 @@
 /include/ "vdk_axs10x_mb.dtsi"
 
 / {
+	model = "snps,vdk_archs-smp";
 	compatible = "snps,axs103";
 
 	chosen {
diff --git a/arch/arc/boot/dts/zebu_hs.dts b/arch/arc/boot/dts/zebu_hs.dts
new file mode 100644
index 0000000..1c1324e
--- /dev/null
+++ b/arch/arc/boot/dts/zebu_hs.dts
@@ -0,0 +1,69 @@
+/*
+ * Copyright (C) 2016-2014 Synopsys, Inc. (www.synopsys.com)
+ *
+ * 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.
+ */
+/dts-v1/;
+
+/include/ "skeleton_hs.dtsi"
+
+/ {
+	model = "snps,zebu_hs";
+	compatible = "snps,zebu_hs";
+	#address-cells = <1>;
+	#size-cells = <1>;
+	interrupt-parent = <&core_intc>;
+
+	memory {
+		device_type = "memory";
+		reg = <0x80000000 0x20000000>;	/* 512 */
+	};
+
+	chosen {
+		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=ttyS0,115200n8 debug print-fatal-signals=1";
+	};
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	fpga {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		/* child and parent address space 1:1 mapped */
+		ranges;
+
+		core_clk: core_clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <50000000>;
+		};
+
+		core_intc: interrupt-controller {
+			compatible = "snps,archs-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		uart0: serial@f0000000 {
+			compatible = "ns8250";
+			reg = <0xf0000000 0x2000>;
+			interrupts = <24>;
+			clock-frequency = <50000000>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			no-loopback-test = <1>;
+		};
+
+		arcpct0: pct {
+			compatible = "snps,archs-pct";
+			#interrupt-cells = <1>;
+			interrupts = <20>;
+		};
+	};
+};
diff --git a/arch/arc/boot/dts/zebu_hs_idu.dts b/arch/arc/boot/dts/zebu_hs_idu.dts
new file mode 100644
index 0000000..65204b4
--- /dev/null
+++ b/arch/arc/boot/dts/zebu_hs_idu.dts
@@ -0,0 +1,85 @@
+/*
+ * Copyright (C) 2016-2014 Synopsys, Inc. (www.synopsys.com)
+ *
+ * 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.
+ */
+/dts-v1/;
+
+/include/ "skeleton_hs_idu.dtsi"
+
+/ {
+	model = "snps,zebu_hs-smp";
+	compatible = "snps,zebu_hs";
+	#address-cells = <1>;
+	#size-cells = <1>;
+	interrupt-parent = <&core_intc>;
+
+	memory {
+		device_type = "memory";
+		reg = <0x80000000 0x20000000>;	/* 512 */
+	};
+
+	chosen {
+		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=ttyS0,115200n8 debug";
+	};
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	fpga {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		/* child and parent address space 1:1 mapped */
+		ranges;
+
+		core_clk: core_clk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <50000000>;	/* 50 MHZ */
+		};
+
+		core_intc: interrupt-controller {
+			compatible = "snps,archs-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+/*			interrupts = <16 17 18 19 20 21 22 23 24 25>; */
+		};
+
+		idu_intc: idu-interrupt-controller {
+			compatible = "snps,archs-idu-intc";
+			interrupt-controller;
+			interrupt-parent = <&core_intc>;
+			/* <hwirq  distribution>
+			distribution: 0=RR; 1=cpu0, 2=cpu1, 4=cpu2, 8=cpu3 */
+			#interrupt-cells = <2>;
+			interrupts = <24 25 26 27 28 29 30 31>;
+
+		};
+
+		uart0: serial@f0000000 {
+			/* compatible = "ns8250"; Doesn't use FIFOs */
+			compatible = "ns16550a";
+			reg = <0xf0000000 0x2000>;
+			interrupt-parent = <&idu_intc>;
+			/* interrupts = <0 1>;  DEST=1*/
+			/* interrupts = <0 2>;  DEST=2*/
+			interrupts = <0 0>;  /* RR*/
+			clock-frequency = <50000000>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			no-loopback-test = <1>;
+		};
+
+		arcpct0: pct {
+			compatible = "snps,archs-pct";
+			#interrupt-cells = <1>;
+			interrupts = <20>;
+		};
+	};
+};
diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig
index 6cdffea..0a0eaf0 100644
--- a/arch/arc/configs/axs101_defconfig
+++ b/arch/arc/configs/axs101_defconfig
@@ -18,6 +18,9 @@
 # CONFIG_SLUB_DEBUG is not set
 # CONFIG_COMPAT_BRK is not set
 CONFIG_MODULES=y
+CONFIG_MODULE_FORCE_LOAD=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_ARC_PLAT_AXS10X=y
 CONFIG_AXS101=y
diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig
index 491b3b5..2233f57 100644
--- a/arch/arc/configs/axs103_defconfig
+++ b/arch/arc/configs/axs103_defconfig
@@ -18,6 +18,9 @@
 # CONFIG_SLUB_DEBUG is not set
 # CONFIG_COMPAT_BRK is not set
 CONFIG_MODULES=y
+CONFIG_MODULE_FORCE_LOAD=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_ARC_PLAT_AXS10X=y
 CONFIG_AXS103=y
diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig
index b25ee73..1108747 100644
--- a/arch/arc/configs/axs103_smp_defconfig
+++ b/arch/arc/configs/axs103_smp_defconfig
@@ -18,6 +18,9 @@
 # CONFIG_COMPAT_BRK is not set
 CONFIG_SLAB=y
 CONFIG_MODULES=y
+CONFIG_MODULE_FORCE_LOAD=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_ARC_PLAT_AXS10X=y
 CONFIG_AXS103=y
diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig
index a99dc7a..65ab9fb 100644
--- a/arch/arc/configs/nsim_hs_defconfig
+++ b/arch/arc/configs/nsim_hs_defconfig
@@ -11,13 +11,16 @@
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/"
+CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
 CONFIG_KALLSYMS_ALL=y
 CONFIG_EMBEDDED=y
 # CONFIG_SLUB_DEBUG is not set
 # CONFIG_COMPAT_BRK is not set
 CONFIG_KPROBES=y
 CONFIG_MODULES=y
+CONFIG_MODULE_FORCE_LOAD=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
 # CONFIG_LBDAF is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig
index 59f221f..3b3990c 100644
--- a/arch/arc/configs/nsim_hs_smp_defconfig
+++ b/arch/arc/configs/nsim_hs_smp_defconfig
@@ -16,6 +16,9 @@
 # CONFIG_COMPAT_BRK is not set
 CONFIG_KPROBES=y
 CONFIG_MODULES=y
+CONFIG_MODULE_FORCE_LOAD=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
 # CONFIG_LBDAF is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
diff --git a/arch/arc/configs/zebu_hs_defconfig b/arch/arc/configs/zebu_hs_defconfig
new file mode 100644
index 0000000..9f6166b
--- /dev/null
+++ b/arch/arc/configs/zebu_hs_defconfig
@@ -0,0 +1,86 @@
+CONFIG_DEFAULT_HOSTNAME="ARCLinux"
+# CONFIG_SWAP is not set
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_NO_HZ_IDLE=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_NAMESPACES=y
+# CONFIG_UTS_NS is not set
+# CONFIG_PID_NS is not set
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
+CONFIG_EXPERT=y
+CONFIG_PERF_EVENTS=y
+# CONFIG_COMPAT_BRK is not set
+CONFIG_SLAB=y
+CONFIG_MODULES=y
+# CONFIG_LBDAF is not set
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+# CONFIG_IOSCHED_CFQ is not set
+CONFIG_ARC_PLAT_SIM=y
+CONFIG_ISA_ARCV2=y
+CONFIG_ARC_BUILTIN_DTB_NAME="zebu_hs"
+CONFIG_PREEMPT=y
+# CONFIG_COMPACTION is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_PACKET_DIAG=y
+CONFIG_UNIX=y
+CONFIG_UNIX_DIAG=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_IPV6 is not set
+# CONFIG_WIRELESS is not set
+CONFIG_DEVTMPFS=y
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_FIRMWARE_IN_KERNEL is not set
+# CONFIG_BLK_DEV is not set
+CONFIG_NETDEVICES=y
+# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MARVELL is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
+# CONFIG_WLAN is not set
+CONFIG_INPUT_EVDEV=y
+CONFIG_MOUSE_PS2_TOUCHKIT=y
+# CONFIG_SERIO_SERPORT is not set
+CONFIG_SERIO_ARC_PS2=y
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=1
+CONFIG_SERIAL_8250_RUNTIME_UARTS=1
+CONFIG_SERIAL_8250_DW=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+CONFIG_FB=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_LOGO=y
+# CONFIG_HID is not set
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT2_FS=y
+CONFIG_EXT2_FS_XATTR=y
+CONFIG_TMPFS=y
+# CONFIG_MISC_FILESYSTEMS is not set
+CONFIG_NFS_FS=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_DEBUG_MEMORY_INIT=y
+# CONFIG_DEBUG_PREEMPT is not set
diff --git a/arch/arc/configs/zebu_hs_smp_defconfig b/arch/arc/configs/zebu_hs_smp_defconfig
new file mode 100644
index 0000000..44e9693
--- /dev/null
+++ b/arch/arc/configs/zebu_hs_smp_defconfig
@@ -0,0 +1,89 @@
+CONFIG_DEFAULT_HOSTNAME="ARCLinux"
+# CONFIG_SWAP is not set
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_NO_HZ_IDLE=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_NAMESPACES=y
+# CONFIG_UTS_NS is not set
+# CONFIG_PID_NS is not set
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
+CONFIG_EMBEDDED=y
+CONFIG_PERF_EVENTS=y
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_SLAB=y
+CONFIG_KPROBES=y
+CONFIG_MODULES=y
+# CONFIG_LBDAF is not set
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+# CONFIG_IOSCHED_CFQ is not set
+CONFIG_ARC_PLAT_SIM=y
+CONFIG_ISA_ARCV2=y
+CONFIG_SMP=y
+CONFIG_ARC_BUILTIN_DTB_NAME="zebu_hs_idu"
+CONFIG_PREEMPT=y
+# CONFIG_COMPACTION is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_PACKET_DIAG=y
+CONFIG_UNIX=y
+CONFIG_UNIX_DIAG=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_IPV6 is not set
+# CONFIG_WIRELESS is not set
+CONFIG_DEVTMPFS=y
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_FIRMWARE_IN_KERNEL is not set
+# CONFIG_BLK_DEV is not set
+CONFIG_NETDEVICES=y
+# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MARVELL is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
+# CONFIG_WLAN is not set
+CONFIG_INPUT_EVDEV=y
+CONFIG_MOUSE_PS2_TOUCHKIT=y
+# CONFIG_SERIO_SERPORT is not set
+CONFIG_SERIO_ARC_PS2=y
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=1
+CONFIG_SERIAL_8250_RUNTIME_UARTS=1
+CONFIG_SERIAL_8250_DW=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+CONFIG_FB=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_LOGO=y
+# CONFIG_HID is not set
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT2_FS=y
+CONFIG_EXT2_FS_XATTR=y
+CONFIG_TMPFS=y
+# CONFIG_MISC_FILESYSTEMS is not set
+CONFIG_NFS_FS=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_LOCKUP_DETECTOR=y
+# CONFIG_DEBUG_PREEMPT is not set
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index 7fbaea0..db25c65 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -95,7 +95,7 @@
 /* Auxiliary registers */
 #define AUX_IDENTITY		4
 #define AUX_INTR_VEC_BASE	0x25
-#define AUX_NON_VOL		0x5e
+#define AUX_VOL			0x5e
 
 /*
  * Floating Pt Registers
@@ -240,14 +240,6 @@
 #endif
 };
 
-struct bcr_perip {
-#ifdef CONFIG_CPU_BIG_ENDIAN
-	unsigned int start:8, pad2:8, sz:8, ver:8;
-#else
-	unsigned int ver:8, sz:8, pad2:8, start:8;
-#endif
-};
-
 struct bcr_iccm_arcompact {
 #ifdef CONFIG_CPU_BIG_ENDIAN
 	unsigned int base:16, pad:5, sz:3, ver:8;
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 4e3c1b6..b65930a 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -20,6 +20,7 @@
 #ifndef CONFIG_ARC_PLAT_EZNPS
 
 #define atomic_read(v)  READ_ONCE((v)->counter)
+#define ATOMIC_INIT(i)	{ (i) }
 
 #ifdef CONFIG_ARC_HAS_LLSC
 
@@ -284,6 +285,7 @@
 ATOMIC_OPS(add, +=, CTOP_INST_AADD_DI_R2_R2_R3)
 #define atomic_sub(i, v) atomic_add(-(i), (v))
 #define atomic_sub_return(i, v) atomic_add_return(-(i), (v))
+#define atomic_fetch_sub(i, v) atomic_fetch_add(-(i), (v))
 
 #undef ATOMIC_OPS
 #define ATOMIC_OPS(op, c_op, asm_op)					\
@@ -292,6 +294,7 @@
 
 ATOMIC_OPS(and, &=, CTOP_INST_AAND_DI_R2_R2_R3)
 #define atomic_andnot(mask, v) atomic_and(~(mask), (v))
+#define atomic_fetch_andnot(mask, v) atomic_fetch_and(~(mask), (v))
 ATOMIC_OPS(or, |=, CTOP_INST_AOR_DI_R2_R2_R3)
 ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3)
 
@@ -343,10 +346,266 @@
 
 #define atomic_add_negative(i, v)	(atomic_add_return(i, v) < 0)
 
-#define ATOMIC_INIT(i)			{ (i) }
+
+#ifdef CONFIG_GENERIC_ATOMIC64
 
 #include <asm-generic/atomic64.h>
 
-#endif
+#else	/* Kconfig ensures this is only enabled with needed h/w assist */
+
+/*
+ * ARCv2 supports 64-bit exclusive load (LLOCKD) / store (SCONDD)
+ *  - The address HAS to be 64-bit aligned
+ *  - There are 2 semantics involved here:
+ *    = exclusive implies no interim update between load/store to same addr
+ *    = both words are observed/updated together: this is guaranteed even
+ *      for regular 64-bit load (LDD) / store (STD). Thus atomic64_set()
+ *      is NOT required to use LLOCKD+SCONDD, STD suffices
+ */
+
+typedef struct {
+	aligned_u64 counter;
+} atomic64_t;
+
+#define ATOMIC64_INIT(a) { (a) }
+
+static inline long long atomic64_read(const atomic64_t *v)
+{
+	unsigned long long val;
+
+	__asm__ __volatile__(
+	"	ldd   %0, [%1]	\n"
+	: "=r"(val)
+	: "r"(&v->counter));
+
+	return val;
+}
+
+static inline void atomic64_set(atomic64_t *v, long long a)
+{
+	/*
+	 * This could have been a simple assignment in "C" but would need
+	 * explicit volatile. Otherwise gcc optimizers could elide the store
+	 * which borked atomic64 self-test
+	 * In the inline asm version, memory clobber needed for exact same
+	 * reason, to tell gcc about the store.
+	 *
+	 * This however is not needed for sibling atomic64_add() etc since both
+	 * load/store are explicitly done in inline asm. As long as API is used
+	 * for each access, gcc has no way to optimize away any load/store
+	 */
+	__asm__ __volatile__(
+	"	std   %0, [%1]	\n"
+	:
+	: "r"(a), "r"(&v->counter)
+	: "memory");
+}
+
+#define ATOMIC64_OP(op, op1, op2)					\
+static inline void atomic64_##op(long long a, atomic64_t *v)		\
+{									\
+	unsigned long long val;						\
+									\
+	__asm__ __volatile__(						\
+	"1:				\n"				\
+	"	llockd  %0, [%1]	\n"				\
+	"	" #op1 " %L0, %L0, %L2	\n"				\
+	"	" #op2 " %H0, %H0, %H2	\n"				\
+	"	scondd   %0, [%1]	\n"				\
+	"	bnz     1b		\n"				\
+	: "=&r"(val)							\
+	: "r"(&v->counter), "ir"(a)					\
+	: "cc");						\
+}									\
+
+#define ATOMIC64_OP_RETURN(op, op1, op2)		        	\
+static inline long long atomic64_##op##_return(long long a, atomic64_t *v)	\
+{									\
+	unsigned long long val;						\
+									\
+	smp_mb();							\
+									\
+	__asm__ __volatile__(						\
+	"1:				\n"				\
+	"	llockd   %0, [%1]	\n"				\
+	"	" #op1 " %L0, %L0, %L2	\n"				\
+	"	" #op2 " %H0, %H0, %H2	\n"				\
+	"	scondd   %0, [%1]	\n"				\
+	"	bnz     1b		\n"				\
+	: [val] "=&r"(val)						\
+	: "r"(&v->counter), "ir"(a)					\
+	: "cc");	/* memory clobber comes from smp_mb() */	\
+									\
+	smp_mb();							\
+									\
+	return val;							\
+}
+
+#define ATOMIC64_FETCH_OP(op, op1, op2)		        		\
+static inline long long atomic64_fetch_##op(long long a, atomic64_t *v)	\
+{									\
+	unsigned long long val, orig;					\
+									\
+	smp_mb();							\
+									\
+	__asm__ __volatile__(						\
+	"1:				\n"				\
+	"	llockd   %0, [%2]	\n"				\
+	"	" #op1 " %L1, %L0, %L3	\n"				\
+	"	" #op2 " %H1, %H0, %H3	\n"				\
+	"	scondd   %1, [%2]	\n"				\
+	"	bnz     1b		\n"				\
+	: "=&r"(orig), "=&r"(val)					\
+	: "r"(&v->counter), "ir"(a)					\
+	: "cc");	/* memory clobber comes from smp_mb() */	\
+									\
+	smp_mb();							\
+									\
+	return orig;							\
+}
+
+#define ATOMIC64_OPS(op, op1, op2)					\
+	ATOMIC64_OP(op, op1, op2)					\
+	ATOMIC64_OP_RETURN(op, op1, op2)				\
+	ATOMIC64_FETCH_OP(op, op1, op2)
+
+#define atomic64_andnot atomic64_andnot
+
+ATOMIC64_OPS(add, add.f, adc)
+ATOMIC64_OPS(sub, sub.f, sbc)
+ATOMIC64_OPS(and, and, and)
+ATOMIC64_OPS(andnot, bic, bic)
+ATOMIC64_OPS(or, or, or)
+ATOMIC64_OPS(xor, xor, xor)
+
+#undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
+#undef ATOMIC64_OP_RETURN
+#undef ATOMIC64_OP
+
+static inline long long
+atomic64_cmpxchg(atomic64_t *ptr, long long expected, long long new)
+{
+	long long prev;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	llockd  %0, [%1]	\n"
+	"	brne    %L0, %L2, 2f	\n"
+	"	brne    %H0, %H2, 2f	\n"
+	"	scondd  %3, [%1]	\n"
+	"	bnz     1b		\n"
+	"2:				\n"
+	: "=&r"(prev)
+	: "r"(ptr), "ir"(expected), "r"(new)
+	: "cc");	/* memory clobber comes from smp_mb() */
+
+	smp_mb();
+
+	return prev;
+}
+
+static inline long long atomic64_xchg(atomic64_t *ptr, long long new)
+{
+	long long prev;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	llockd  %0, [%1]	\n"
+	"	scondd  %2, [%1]	\n"
+	"	bnz     1b		\n"
+	"2:				\n"
+	: "=&r"(prev)
+	: "r"(ptr), "r"(new)
+	: "cc");	/* memory clobber comes from smp_mb() */
+
+	smp_mb();
+
+	return prev;
+}
+
+/**
+ * atomic64_dec_if_positive - decrement by 1 if old value positive
+ * @v: pointer of type atomic64_t
+ *
+ * The function returns the old value of *v minus 1, even if
+ * the atomic variable, v, was not decremented.
+ */
+
+static inline long long atomic64_dec_if_positive(atomic64_t *v)
+{
+	long long val;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	llockd  %0, [%1]	\n"
+	"	sub.f   %L0, %L0, 1	# w0 - 1, set C on borrow\n"
+	"	sub.c   %H0, %H0, 1	# if C set, w1 - 1\n"
+	"	brlt    %H0, 0, 2f	\n"
+	"	scondd  %0, [%1]	\n"
+	"	bnz     1b		\n"
+	"2:				\n"
+	: "=&r"(val)
+	: "r"(&v->counter)
+	: "cc");	/* memory clobber comes from smp_mb() */
+
+	smp_mb();
+
+	return val;
+}
+
+/**
+ * atomic64_add_unless - add unless the number is a given value
+ * @v: pointer of type atomic64_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * if (v != u) { v += a; ret = 1} else {ret = 0}
+ * Returns 1 iff @v was not @u (i.e. if add actually happened)
+ */
+static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
+{
+	long long val;
+	int op_done;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	llockd  %0, [%2]	\n"
+	"	mov	%1, 1		\n"
+	"	brne	%L0, %L4, 2f	# continue to add since v != u \n"
+	"	breq.d	%H0, %H4, 3f	# return since v == u \n"
+	"	mov	%1, 0		\n"
+	"2:				\n"
+	"	add.f   %L0, %L0, %L3	\n"
+	"	adc     %H0, %H0, %H3	\n"
+	"	scondd  %0, [%2]	\n"
+	"	bnz     1b		\n"
+	"3:				\n"
+	: "=&r"(val), "=&r" (op_done)
+	: "r"(&v->counter), "r"(a), "r"(u)
+	: "cc");	/* memory clobber comes from smp_mb() */
+
+	smp_mb();
+
+	return op_done;
+}
+
+#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
+#define atomic64_inc(v)			atomic64_add(1LL, (v))
+#define atomic64_inc_return(v)		atomic64_add_return(1LL, (v))
+#define atomic64_inc_and_test(v)	(atomic64_inc_return(v) == 0)
+#define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
+#define atomic64_dec(v)			atomic64_sub(1LL, (v))
+#define atomic64_dec_return(v)		atomic64_sub_return(1LL, (v))
+#define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
+#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1LL, 0LL)
+
+#endif	/* !CONFIG_GENERIC_ATOMIC64 */
+
+#endif	/* !__ASSEMBLY__ */
 
 #endif
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index 23706c6..fb781e3 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -54,7 +54,7 @@
 extern void read_decode_cache_bcr(void);
 
 extern int ioc_exists;
-extern unsigned long perip_base;
+extern unsigned long perip_base, perip_end;
 
 #endif	/* !__ASSEMBLY__ */
 
diff --git a/arch/arc/include/asm/dwarf.h b/arch/arc/include/asm/dwarf.h
new file mode 100644
index 0000000..bb7bdbc
--- /dev/null
+++ b/arch/arc/include/asm/dwarf.h
@@ -0,0 +1,38 @@
+/*
+ * Copyright (C) 2016-17 Synopsys, Inc. (www.synopsys.com)
+ *
+ * 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.
+ */
+
+#ifndef _ASM_ARC_DWARF_H
+#define _ASM_ARC_DWARF_H
+
+#ifdef __ASSEMBLY__
+
+#ifdef ARC_DW2_UNWIND_AS_CFI
+
+#define CFI_STARTPROC	.cfi_startproc
+#define CFI_ENDPROC	.cfi_endproc
+#define CFI_DEF_CFA	.cfi_def_cfa
+#define CFI_REGISTER	.cfi_register
+#define CFI_REL_OFFSET	.cfi_rel_offset
+#define CFI_UNDEFINED	.cfi_undefined
+
+#else
+
+#define CFI_IGNORE	#
+
+#define CFI_STARTPROC	CFI_IGNORE
+#define CFI_ENDPROC	CFI_IGNORE
+#define CFI_DEF_CFA	CFI_IGNORE
+#define CFI_REGISTER	CFI_IGNORE
+#define CFI_REL_OFFSET	CFI_IGNORE
+#define CFI_UNDEFINED	CFI_IGNORE
+
+#endif	/* !ARC_DW2_UNWIND_AS_CFI */
+
+#endif	/* __ASSEMBLY__ */
+
+#endif	/* _ASM_ARC_DWARF_H */
diff --git a/arch/arc/include/asm/elf.h b/arch/arc/include/asm/elf.h
index 51a99e2..7096f97 100644
--- a/arch/arc/include/asm/elf.h
+++ b/arch/arc/include/asm/elf.h
@@ -23,8 +23,7 @@
 /* ARC Relocations (kernel Modules only) */
 #define  R_ARC_32		0x4
 #define  R_ARC_32_ME		0x1B
-#define  R_ARC_S25H_PCREL	0x10
-#define  R_ARC_S25W_PCREL	0x11
+#define  R_ARC_32_PCREL		0x31
 
 /*to set parameters in the core dumps */
 #define ELF_ARCH		EM_ARCOMPACT
diff --git a/arch/arc/include/asm/irqflags-arcv2.h b/arch/arc/include/asm/irqflags-arcv2.h
index d1ec7f6..e880dfa 100644
--- a/arch/arc/include/asm/irqflags-arcv2.h
+++ b/arch/arc/include/asm/irqflags-arcv2.h
@@ -112,7 +112,7 @@
 	 */
 	temp = (1 << 5) |
 		((!!(temp & STATUS_IE_MASK)) << CLRI_STATUS_IE_BIT) |
-		(temp & CLRI_STATUS_E_MASK);
+		((temp >> 1) & CLRI_STATUS_E_MASK);
 	return temp;
 }
 
diff --git a/arch/arc/include/asm/linkage.h b/arch/arc/include/asm/linkage.h
index 5faad17..b29f1a9 100644
--- a/arch/arc/include/asm/linkage.h
+++ b/arch/arc/include/asm/linkage.h
@@ -9,6 +9,8 @@
 #ifndef __ASM_LINKAGE_H
 #define __ASM_LINKAGE_H
 
+#include <asm/dwarf.h>
+
 #ifdef __ASSEMBLY__
 
 #define ASM_NL		 `	/* use '`' to mark new line in macro */
@@ -32,6 +34,16 @@
 #endif
 .endm
 
+#define ENTRY_CFI(name)		\
+	.globl name ASM_NL	\
+	ALIGN ASM_NL 		\
+	name: ASM_NL		\
+	CFI_STARTPROC ASM_NL
+
+#define END_CFI(name) 		\
+	CFI_ENDPROC ASM_NL	\
+	.size name, .-name
+
 #else	/* !__ASSEMBLY__ */
 
 #ifdef CONFIG_ARC_HAS_ICCM
diff --git a/arch/arc/include/asm/perf_event.h b/arch/arc/include/asm/perf_event.h
index 5f07176..9185541 100644
--- a/arch/arc/include/asm/perf_event.h
+++ b/arch/arc/include/asm/perf_event.h
@@ -118,6 +118,9 @@
 	[PERF_COUNT_ARC_ICM] = "icm",		/* I-cache Miss */
 	[PERF_COUNT_ARC_EDTLB] = "edtlb",	/* D-TLB Miss */
 	[PERF_COUNT_ARC_EITLB] = "eitlb",	/* I-TLB Miss */
+
+	[PERF_COUNT_HW_CACHE_REFERENCES] = "imemrdc",	/* Instr: mem read cached */
+	[PERF_COUNT_HW_CACHE_MISSES] = "dclm",		/* D-cache Load Miss */
 };
 
 #define C(_x)			PERF_COUNT_HW_CACHE_##_x
diff --git a/arch/arc/kernel/ctx_sw_asm.S b/arch/arc/kernel/ctx_sw_asm.S
index e6890b1..7c1f365 100644
--- a/arch/arc/kernel/ctx_sw_asm.S
+++ b/arch/arc/kernel/ctx_sw_asm.S
@@ -23,6 +23,7 @@
 	.global __switch_to
 	.type   __switch_to, @function
 __switch_to:
+	CFI_STARTPROC
 
 	/* Save regs on kernel mode stack of task */
 	st.a    blink, [sp, -4]
@@ -59,4 +60,4 @@
 	ld.ab   blink, [sp, 4]
 	j       [blink]
 
-END(__switch_to)
+END_CFI(__switch_to)
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index 2efb0625..1eea99b 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -35,7 +35,7 @@
 	btst r10, TIF_SYSCALL_TRACE
 	bnz  tracesys_exit
 
-	b ret_from_system_call
+	b .Lret_from_system_call
 END(sys_clone_wrapper)
 
 ENTRY(ret_from_fork)
@@ -61,18 +61,6 @@
 	b    ret_from_exception
 END(ret_from_fork)
 
-#ifdef CONFIG_ARC_DW2_UNWIND
-; Workaround for bug 94179 (STAR ):
-; Despite -fasynchronous-unwind-tables, linker is not making dwarf2 unwinder
-; section (.debug_frame) as loadable. So we force it here.
-; This also fixes STAR 9000487933 where the prev-workaround (objcopy --setflag)
-; would not work after a clean build due to kernel build system dependencies.
-.section .debug_frame, "wa",@progbits
-
-; Reset to .text as this file is included in entry-<isa>.S
-.section .text, "ax",@progbits
-#endif
-
 ;################### Non TLB Exception Handling #############################
 
 ; ---------------------------------------------
@@ -260,20 +248,18 @@
 	; syscall num shd not exceed the total system calls avail
 	cmp     r8,  NR_syscalls
 	mov.hi  r0, -ENOSYS
-	bhi     ret_from_system_call
+	bhi     .Lret_from_system_call
 
 	; Offset into the syscall_table and call handler
 	ld.as   r9,[sys_call_table, r8]
 	jl      [r9]        ; Entry into Sys Call Handler
 
-	; fall through to ret_from_system_call
-END(EV_Trap)
-
-ENTRY(ret_from_system_call)
+.Lret_from_system_call:
 
 	st  r0, [sp, PT_r0]     ; sys call return value in pt_regs
 
-	; fall through yet again to ret_from_exception
+	; fall through to ret_from_exception
+END(EV_Trap)
 
 ;############# Return from Intr/Excp/Trap (Linux Specifics) ##############
 ;
diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c
index 6c24faf..62b59409 100644
--- a/arch/arc/kernel/intc-arcv2.c
+++ b/arch/arc/kernel/intc-arcv2.c
@@ -74,7 +74,7 @@
 	tmp = read_aux_reg(0xa);
 	tmp |= STATUS_AD_MASK | (irq_prio << 1);
 	tmp &= ~STATUS_IE_MASK;
-	asm volatile("flag %0	\n"::"r"(tmp));
+	asm volatile("kflag %0	\n"::"r"(tmp));
 }
 
 static void arcv2_irq_mask(struct irq_data *data)
diff --git a/arch/arc/kernel/module.c b/arch/arc/kernel/module.c
index 376e046..9a28497 100644
--- a/arch/arc/kernel/module.c
+++ b/arch/arc/kernel/module.c
@@ -22,13 +22,9 @@
 	*(addr + 1) = (value & 0xffff);
 }
 
-/* ARC specific section quirks - before relocation loop in generic loader
- *
- * For dwarf unwinding out of modules, this needs to
- * 1. Ensure the .debug_frame is allocatable (ARC Linker bug: despite
- *    -fasynchronous-unwind-tables it doesn't).
- * 2. Since we are iterating thru sec hdr tbl anyways, make a note of
- *    the exact section index, for later use.
+/*
+ * This gets called before relocation loop in generic loader
+ * Make a note of the section index of unwinding section
  */
 int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
 			      char *secstr, struct module *mod)
@@ -40,8 +36,7 @@
 	mod->arch.unw_info = NULL;
 
 	for (i = 1; i < hdr->e_shnum; i++) {
-		if (strcmp(secstr+sechdrs[i].sh_name, ".debug_frame") == 0) {
-			sechdrs[i].sh_flags |= SHF_ALLOC;
+		if (strcmp(secstr+sechdrs[i].sh_name, ".eh_frame") == 0) {
 			mod->arch.unw_sec_idx = i;
 			break;
 		}
@@ -106,10 +101,12 @@
 		 */
 		relo_type = ELF32_R_TYPE(rel_entry[i].r_info);
 
-		if (likely(R_ARC_32_ME == relo_type))
+		if (likely(R_ARC_32_ME == relo_type))	/* ME ( S + A ) */
 			arc_write_me((unsigned short *)location, relocation);
-		else if (R_ARC_32 == relo_type)
+		else if (R_ARC_32 == relo_type)		/* ( S + A ) */
 			*((Elf32_Addr *) location) = relocation;
+		else if (R_ARC_32_PCREL == relo_type)	/* ( S + A ) - PDATA ) */
+			*((Elf32_Addr *) location) = relocation - location;
 		else
 			goto relo_err;
 
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index 08f03d9..2ce24e7 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -179,8 +179,8 @@
 		if (arc_pmu->ev_hw_idx[event->attr.config] < 0)
 			return -ENOENT;
 		hwc->config |= arc_pmu->ev_hw_idx[event->attr.config];
-		pr_debug("init event %d with h/w %d \'%s\'\n",
-			 (int) event->attr.config, (int) hwc->config,
+		pr_debug("init event %d with h/w %08x \'%s\'\n",
+			 (int)event->attr.config, (int)hwc->config,
 			 arc_pmu_ev_hw_map[event->attr.config]);
 		return 0;
 
@@ -189,6 +189,8 @@
 		if (ret < 0)
 			return ret;
 		hwc->config |= arc_pmu->ev_hw_idx[ret];
+		pr_debug("init cache event with h/w %08x \'%s\'\n",
+			 (int)hwc->config, arc_pmu_ev_hw_map[ret]);
 		return 0;
 	default:
 		return -ENOENT;
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index f52a0d0d..3df7f9c 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -171,6 +171,7 @@
 #else
 	{ {0x50, "ARC HS38 R2.0"}, 0x51},
 	{ {0x52, "ARC HS38 R2.1"}, 0x52},
+	{ {0x53, "ARC HS38 R3.0"}, 0x53},
 #endif
 	{ {0x00, NULL		} }
 };
@@ -272,8 +273,8 @@
 	FIX_PTR(cpu);
 
 	n += scnprintf(buf + n, len - n,
-		       "Vector Table\t: %#x\nUncached Base\t: %#lx\n",
-		       cpu->vec_base, perip_base);
+		       "Vector Table\t: %#x\nPeripherals\t: %#lx:%#lx\n",
+		       cpu->vec_base, perip_base, perip_end);
 
 	if (cpu->extn.fpu_sp || cpu->extn.fpu_dp)
 		n += scnprintf(buf + n, len - n, "FPU\t\t: %s%s\n",
diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c
index 0587bf1..61fd1ce 100644
--- a/arch/arc/kernel/unwind.c
+++ b/arch/arc/kernel/unwind.c
@@ -111,6 +111,8 @@
 #define DW_EH_PE_indirect 0x80
 #define DW_EH_PE_omit     0xff
 
+#define CIE_ID	0
+
 typedef unsigned long uleb128_t;
 typedef signed long sleb128_t;
 
@@ -232,6 +234,7 @@
 
 static const u32 bad_cie, not_fde;
 static const u32 *cie_for_fde(const u32 *fde, const struct unwind_table *);
+static const u32 *__cie_for_fde(const u32 *fde);
 static signed fde_pointer_type(const u32 *cie);
 
 struct eh_frame_hdr_table_entry {
@@ -338,10 +341,9 @@
 	for (fde = table->address, tableSize = table->size, n = 0;
 	     tableSize;
 	     tableSize -= sizeof(*fde) + *fde, fde += 1 + *fde / sizeof(*fde)) {
-		/* const u32 *cie = fde + 1 - fde[1] / sizeof(*fde); */
-		const u32 *cie = (const u32 *)(fde[1]);
+		const u32 *cie = __cie_for_fde(fde);
 
-		if (fde[1] == 0xffffffff)
+		if (fde[1] == CIE_ID)
 			continue;	/* this is a CIE */
 		ptr = (const u8 *)(fde + 2);
 		header->table[n].start = read_pointer(&ptr,
@@ -504,6 +506,15 @@
 	return value;
 }
 
+static const u32 *__cie_for_fde(const u32 *fde)
+{
+	const u32 *cie;
+
+	cie = fde + 1 - fde[1] / sizeof(*fde);
+
+	return cie;
+}
+
 static const u32 *cie_for_fde(const u32 *fde, const struct unwind_table *table)
 {
 	const u32 *cie;
@@ -511,19 +522,18 @@
 	if (!*fde || (*fde & (sizeof(*fde) - 1)))
 		return &bad_cie;
 
-	if (fde[1] == 0xffffffff)
+	if (fde[1] == CIE_ID)
 		return &not_fde;	/* this is a CIE */
 
 	if ((fde[1] & (sizeof(*fde) - 1)))
 /* || fde[1] > (unsigned long)(fde + 1) - (unsigned long)table->address) */
 		return NULL;	/* this is not a valid FDE */
 
-	/* cie = fde + 1 - fde[1] / sizeof(*fde); */
-	cie = (u32 *) fde[1];
+	cie = __cie_for_fde(fde);
 
 	if (*cie <= sizeof(*cie) + 4 || *cie >= fde[1] - sizeof(*fde)
 	    || (*cie & (sizeof(*cie) - 1))
-	    || (cie[1] != 0xffffffff))
+	    || (cie[1] != CIE_ID))
 		return NULL;	/* this is not a (valid) CIE */
 	return cie;
 }
diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S
index 894e696..3661107 100644
--- a/arch/arc/kernel/vmlinux.lds.S
+++ b/arch/arc/kernel/vmlinux.lds.S
@@ -82,14 +82,6 @@
 
 	PERCPU_SECTION(L1_CACHE_BYTES)
 
-	/*
-	 * .exit.text is discard at runtime, not link time, to deal with
-	 * references from .debug_frame
-	 * It will be init freed, being inside [__init_start : __init_end]
-	 */
-	.exit.text : { EXIT_TEXT }
-	.exit.data : { EXIT_DATA }
-
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;
 
@@ -120,18 +112,13 @@
 
 #ifdef CONFIG_ARC_DW2_UNWIND
 	. = ALIGN(PAGE_SIZE);
-	.debug_frame  : {
+	.eh_frame  : {
 		__start_unwind = .;
-		*(.debug_frame)
+		*(.eh_frame)
 		__end_unwind = .;
 	}
-	/*
-	 * gcc 4.8 generates this for -fasynchonous-unwind-tables,
-	 * while we still use the .debug_frame based unwinder
-	 */
-	/DISCARD/ : {	*(.eh_frame) }
 #else
-	/DISCARD/ : {	*(.debug_frame) }
+	/DISCARD/ : {	*(.eh_frame) }
 #endif
 
 	NOTES
@@ -148,7 +135,7 @@
 	}
 
 #ifndef CONFIG_DEBUG_INFO
-	/* open-coded because we need .debug_frame seperately for unwinding */
+	/DISCARD/ : { *(.debug_frame) }
 	/DISCARD/ : { *(.debug_aranges) }
 	/DISCARD/ : { *(.debug_pubnames) }
 	/DISCARD/ : { *(.debug_info) }
diff --git a/arch/arc/lib/memcmp.S b/arch/arc/lib/memcmp.S
index a4015e7..21a1030 100644
--- a/arch/arc/lib/memcmp.S
+++ b/arch/arc/lib/memcmp.S
@@ -16,7 +16,7 @@
 #define SHIFT r2
 #endif
 
-ENTRY(memcmp)
+ENTRY_CFI(memcmp)
 	or	r12,r0,r1
 	asl_s	r12,r12,30
 	sub	r3,r2,1
@@ -149,4 +149,4 @@
 .Lnil:
 	j_s.d	[blink]
 	mov	r0,0
-END(memcmp)
+END_CFI(memcmp)
diff --git a/arch/arc/lib/memcpy-700.S b/arch/arc/lib/memcpy-700.S
index 3222573..ba0becc 100644
--- a/arch/arc/lib/memcpy-700.S
+++ b/arch/arc/lib/memcpy-700.S
@@ -8,7 +8,7 @@
 
 #include <linux/linkage.h>
 
-ENTRY(memcpy)
+ENTRY_CFI(memcpy)
 	or	r3,r0,r1
 	asl_s	r3,r3,30
 	mov_s	r5,r0
@@ -63,4 +63,4 @@
 .Lendbloop:
 	j_s.d	[blink]
 	stb	r12,[r5,0]
-END(memcpy)
+END_CFI(memcpy)
diff --git a/arch/arc/lib/memcpy-archs.S b/arch/arc/lib/memcpy-archs.S
index f96c75e..d61044d 100644
--- a/arch/arc/lib/memcpy-archs.S
+++ b/arch/arc/lib/memcpy-archs.S
@@ -40,7 +40,7 @@
 # define ZOLAND			0xF
 #endif
 
-ENTRY(memcpy)
+ENTRY_CFI(memcpy)
 	prefetch [r1]		; Prefetch the read location
 	prefetchw [r0]		; Prefetch the write location
 	mov.f	0, r2
@@ -233,4 +233,4 @@
 .Lcopybytewise_3:
 	j	[blink]
 
-END(memcpy)
+END_CFI(memcpy)
diff --git a/arch/arc/lib/memset-archs.S b/arch/arc/lib/memset-archs.S
index 365b183..62ad4bc 100644
--- a/arch/arc/lib/memset-archs.S
+++ b/arch/arc/lib/memset-archs.S
@@ -10,7 +10,7 @@
 
 #undef PREALLOC_NOT_AVAIL
 
-ENTRY(memset)
+ENTRY_CFI(memset)
 	prefetchw [r0]		; Prefetch the write location
 	mov.f	0, r2
 ;;; if size is zero
@@ -112,11 +112,11 @@
 
 	j	[blink]
 
-END(memset)
+END_CFI(memset)
 
-ENTRY(memzero)
+ENTRY_CFI(memzero)
     ; adjust bzero args to memset args
     mov r2, r1
     b.d  memset    ;tail call so need to tinker with blink
     mov r1, 0
-END(memzero)
+END_CFI(memzero)
diff --git a/arch/arc/lib/memset.S b/arch/arc/lib/memset.S
index d36bd43..cf736f9 100644
--- a/arch/arc/lib/memset.S
+++ b/arch/arc/lib/memset.S
@@ -10,7 +10,7 @@
 
 #define SMALL	7 /* Must be at least 6 to deal with alignment/loop issues.  */
 
-ENTRY(memset)
+ENTRY_CFI(memset)
 	mov_s	r4,r0
 	or	r12,r0,r2
 	bmsk.f	r12,r12,1
@@ -46,14 +46,14 @@
 	stb.ab	r1,[r4,1]
 .Ltiny_end:
 	j_s	[blink]
-END(memset)
+END_CFI(memset)
 
 ; memzero: @r0 = mem, @r1 = size_t
 ; memset:  @r0 = mem, @r1 = char, @r2 = size_t
 
-ENTRY(memzero)
+ENTRY_CFI(memzero)
     ; adjust bzero args to memset args
     mov r2, r1
     mov r1, 0
     b  memset    ;tail call so need to tinker with blink
-END(memzero)
+END_CFI(memzero)
diff --git a/arch/arc/lib/strchr-700.S b/arch/arc/lib/strchr-700.S
index b725d58..2d300da 100644
--- a/arch/arc/lib/strchr-700.S
+++ b/arch/arc/lib/strchr-700.S
@@ -13,7 +13,7 @@
 
 #include <linux/linkage.h>
 
-ENTRY(strchr)
+ENTRY_CFI(strchr)
 	extb_s	r1,r1
 	asl	r5,r1,8
 	bmsk	r2,r0,1
@@ -130,4 +130,4 @@
 	j_s.d	[blink]
 	mov.mi	r0,0
 #endif /* ENDIAN */
-END(strchr)
+END_CFI(strchr)
diff --git a/arch/arc/lib/strcmp-archs.S b/arch/arc/lib/strcmp-archs.S
index 4f338ee..fae9e82 100644
--- a/arch/arc/lib/strcmp-archs.S
+++ b/arch/arc/lib/strcmp-archs.S
@@ -8,7 +8,7 @@
 
 #include <linux/linkage.h>
 
-ENTRY(strcmp)
+ENTRY_CFI(strcmp)
 	or	r2, r0, r1
 	bmsk_s	r2, r2, 1
 	brne	r2, 0, @.Lcharloop
@@ -75,4 +75,4 @@
 .Lcmpend:
 	j_s.d	[blink]
 	sub	r0, r2, r3
-END(strcmp)
+END_CFI(strcmp)
diff --git a/arch/arc/lib/strcmp.S b/arch/arc/lib/strcmp.S
index 3544600..fb20096 100644
--- a/arch/arc/lib/strcmp.S
+++ b/arch/arc/lib/strcmp.S
@@ -15,7 +15,7 @@
 
 #include <linux/linkage.h>
 
-ENTRY(strcmp)
+ENTRY_CFI(strcmp)
 	or	r2,r0,r1
 	bmsk_s	r2,r2,1
 	brne	r2,0,.Lcharloop
@@ -93,4 +93,4 @@
 .Lcmpend:
 	j_s.d	[blink]
 	sub	r0,r2,r3
-END(strcmp)
+END_CFI(strcmp)
diff --git a/arch/arc/lib/strcpy-700.S b/arch/arc/lib/strcpy-700.S
index 8422f38..6a6c155 100644
--- a/arch/arc/lib/strcpy-700.S
+++ b/arch/arc/lib/strcpy-700.S
@@ -18,7 +18,7 @@
 
 #include <linux/linkage.h>
 
-ENTRY(strcpy)
+ENTRY_CFI(strcpy)
 	or	r2,r0,r1
 	bmsk_s	r2,r2,1
 	brne.d	r2,0,charloop
@@ -67,4 +67,4 @@
 	brne.d	r3,0,charloop
 	stb.ab	r3,[r10,1]
 	j	[blink]
-END(strcpy)
+END_CFI(strcpy)
diff --git a/arch/arc/lib/strlen.S b/arch/arc/lib/strlen.S
index 53cfd56..839b44b 100644
--- a/arch/arc/lib/strlen.S
+++ b/arch/arc/lib/strlen.S
@@ -8,7 +8,7 @@
 
 #include <linux/linkage.h>
 
-ENTRY(strlen)
+ENTRY_CFI(strlen)
 	or	r3,r0,7
 	ld	r2,[r3,-7]
 	ld.a	r6,[r3,-3]
@@ -80,4 +80,4 @@
 .Learly_end:
 	b.d	.Lend
 	sub_s.ne r1,r1,r1
-END(strlen)
+END_CFI(strlen)
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index 0b10efe..97dddbe 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -25,6 +25,7 @@
 int ioc_exists;
 volatile int slc_enable = 1, ioc_enable = 1;
 unsigned long perip_base = ARC_UNCACHED_ADDR_SPACE; /* legacy value for boot */
+unsigned long perip_end = 0xFFFFFFFF; /* legacy value */
 
 void (*_cache_line_loop_ic_fn)(phys_addr_t paddr, unsigned long vaddr,
 			       unsigned long sz, const int cacheop);
@@ -76,7 +77,6 @@
 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 {
@@ -95,6 +95,15 @@
 #endif
 	} cbcr;
 
+	struct bcr_volatile {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+		unsigned int start:4, limit:4, pad:22, order:1, disable:1;
+#else
+		unsigned int disable:1, order:1, pad:22, limit:4, start:4;
+#endif
+	} vol;
+
+
 	READ_BCR(ARC_REG_SLC_BCR, sbcr);
 	if (sbcr.ver) {
 		READ_BCR(ARC_REG_SLC_CFG, slc_cfg);
@@ -107,10 +116,14 @@
 	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;
+	/* HS 2.0 didn't have AUX_VOL */
+	if (cpuinfo_arc700[cpu].core.family > 0x51) {
+		READ_BCR(AUX_VOL, vol);
+		perip_base = vol.start << 28;
+		/* HS 3.0 has limit and strict-ordering fields */
+		if (cpuinfo_arc700[cpu].core.family > 0x52)
+			perip_end = (vol.limit << 28) - 1;
+	}
 }
 
 void read_decode_cache_bcr(void)
diff --git a/arch/arc/mm/ioremap.c b/arch/arc/mm/ioremap.c
index f52b7db6..9881bd7 100644
--- a/arch/arc/mm/ioremap.c
+++ b/arch/arc/mm/ioremap.c
@@ -19,7 +19,7 @@
 	if (is_isa_arcompact()) {
 		if (paddr >= ARC_UNCACHED_ADDR_SPACE)
 			return true;
-	} else if (paddr >= perip_base && paddr <= 0xFFFFFFFF) {
+	} else if (paddr >= perip_base && paddr <= perip_end) {
 		return true;
 	}
 
diff --git a/arch/arc/plat-sim/platform.c b/arch/arc/plat-sim/platform.c
index e4fe514..aea8738 100644
--- a/arch/arc/plat-sim/platform.c
+++ b/arch/arc/plat-sim/platform.c
@@ -24,6 +24,7 @@
 	"snps,nsim_hs",
 	"snps,nsimosci",
 	"snps,nsimosci_hs",
+	"snps,zebu_hs",
 	NULL,
 };