ImgTec Meta architecture changes for v3.9-rc1

This adds core architecture support for Imagination's Meta processor
 cores, followed by some later miscellaneous arch/metag cleanups and
 fixes which I kept separate to ease review:
 
  - Support for basic Meta 1 (ATP) and Meta 2 (HTP) core architecture
  - A few fixes all over, particularly for symbol prefixes
  - A few privilege protection fixes
  - Several cleanups (setup.c includes, split out a lot of metag_ksyms.c)
  - Fix some missing exports
  - Convert hugetlb to use vm_unmapped_area()
  - Copy device tree to non-init memory
  - Provide dma_get_sgtable()
 
 Signed-off-by: James Hogan <james.hogan@imgtec.com>
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1.4.13 (GNU/Linux)
 
 iQIcBAABAgAGBQJRMmVXAAoJEKHZs+irPybfivgP/inEXqJyfw59omQdjwvYcU/a
 /u0MJ3UKSNS3U+HknfaFCy/Nwk1dqPLjqqyVC1V6AbUPBXlaEwGcimlNRx2uRjdq
 Uh96upMLHsNuF/xiiR477g3RwY0egIJdM1R1bGi3mZ3vVrNQGF+wbni6f61xCWGz
 M/4rDglpQvE79oLhYdgj6tidZtHQT0YWtERA9W90zkQWXGYmpFPKBKbfZAi5+rKQ
 U6Gpg26orUugzXNaxltJEYKE8gjLTppEabx8DARnItZ4zCMy4dw5RBJ35RFvQw6e
 eSmfgTy9w9WqBMY2+QMSgU0KQt1IITCzX7OlOXC0jALQJXoU0WWbOELlBVQLCwF1
 T0OcR/5ZP/hIlOk5Dh+e9U3AtbASXdMtqA0ZUe78woH1CBf7Nc/0c0vRg23EdMh8
 lnHDJxT/UqskoOYLI4kgWbEdLDy4uTh19U2pVi7VCo7ksLB9Bj9Xc8VSKgscSXTl
 OwzN+c4Jgtu8FDFTp+Af4AT8pYGJ08j8L2ErsV2sOv3Q44U5WXdrMz3GSgwXj8+4
 wZk3HvdkQVkMD5sJCUZgAswaN6BnbB0pHdCz4wMQ8jR/Ogs015Ipk64Ecym9S/4n
 uES7PnDtt/4lb5EyX2ScbvdnZTAFTaaP7OOhC77BOQvbQjIW1tkAcxWJqRry86uS
 iM0BFgK6Ohx3geqa5Ft0
 =65cR
 -----END PGP SIGNATURE-----

Merge tag 'metag-v3.9-rc1-v4' of git://git.kernel.org/pub/scm/linux/kernel/git/jhogan/metag

Pull new ImgTec Meta architecture from James Hogan:
 "This adds core architecture support for Imagination's Meta processor
  cores, followed by some later miscellaneous arch/metag cleanups and
  fixes which I kept separate to ease review:

   - Support for basic Meta 1 (ATP) and Meta 2 (HTP) core architecture
   - A few fixes all over, particularly for symbol prefixes
   - A few privilege protection fixes
   - Several cleanups (setup.c includes, split out a lot of
     metag_ksyms.c)
   - Fix some missing exports
   - Convert hugetlb to use vm_unmapped_area()
   - Copy device tree to non-init memory
   - Provide dma_get_sgtable()"

* tag 'metag-v3.9-rc1-v4' of git://git.kernel.org/pub/scm/linux/kernel/git/jhogan/metag: (61 commits)
  metag: Provide dma_get_sgtable()
  metag: prom.h: remove declaration of metag_dt_memblock_reserve()
  metag: copy devicetree to non-init memory
  metag: cleanup metag_ksyms.c includes
  metag: move mm/init.c exports out of metag_ksyms.c
  metag: move usercopy.c exports out of metag_ksyms.c
  metag: move setup.c exports out of metag_ksyms.c
  metag: move kick.c exports out of metag_ksyms.c
  metag: move traps.c exports out of metag_ksyms.c
  metag: move irq enable out of irqflags.h on SMP
  genksyms: fix metag symbol prefix on crc symbols
  metag: hugetlb: convert to vm_unmapped_area()
  metag: export clear_page and copy_page
  metag: export metag_code_cache_flush_all
  metag: protect more non-MMU memory regions
  metag: make TXPRIVEXT bits explicit
  metag: kernel/setup.c: sort includes
  perf: Enable building perf tools for Meta
  metag: add boot time LNKGET/LNKSET check
  metag: add __init to metag_cache_probe()
  ...

Documentation/00-INDEX

@@ -299,6 +299,8 @@ memory-hotplug.txt
 	- Hotpluggable memory support, how to use and current status.
 memory.txt
 	- info on typical Linux memory problems.
+metag/
+	- directory with info about Linux on Meta architecture.
 mips/
 	- directory with info about Linux on MIPS architecture.
 misc-devices/

Documentation/devicetree/bindings/metag/meta-intc.txt

@@ -0,0 +1,82 @@
+* Meta External Trigger Controller Binding
+
+This binding specifies what properties must be available in the device tree
+representation of a Meta external trigger controller.
+
+Required properties:
+
+    - compatible: Specifies the compatibility list for the interrupt controller.
+      The type shall be <string> and the value shall include "img,meta-intc".
+
+    - num-banks: Specifies the number of interrupt banks (each of which can
+      handle 32 interrupt sources).
+
+    - interrupt-controller: The presence of this property identifies the node
+      as an interupt controller. No property value shall be defined.
+
+    - #interrupt-cells: Specifies the number of cells needed to encode an
+      interrupt source. The type shall be a <u32> and the value shall be 2.
+
+    - #address-cells: Specifies the number of cells needed to encode an
+      address. The type shall be <u32> and the value shall be 0. As such,
+      'interrupt-map' nodes do not have to specify a parent unit address.
+
+Optional properties:
+
+    - no-mask: The controller doesn't have any mask registers.
+
+* Interrupt Specifier Definition
+
+  Interrupt specifiers consists of 2 cells encoded as follows:
+
+    - <1st-cell>: The interrupt-number that identifies the interrupt source.
+
+    - <2nd-cell>: The Linux interrupt flags containing level-sense information,
+                  encoded as follows:
+                    1 = edge triggered
+                    4 = level-sensitive
+
+* Examples
+
+Example 1:
+
+	/*
+	 * Meta external trigger block
+	 */
+	intc: intc {
+		// This is an interrupt controller node.
+		interrupt-controller;
+
+		// No address cells so that 'interrupt-map' nodes which
+		// reference this interrupt controller node do not need a parent
+		// address specifier.
+		#address-cells = <0>;
+
+		// Two cells to encode interrupt sources.
+		#interrupt-cells = <2>;
+
+		// Number of interrupt banks
+		num-banks = <2>;
+
+		// No HWMASKEXT is available (specify on Chorus2 and Comet ES1)
+		no-mask;
+
+		// Compatible with Meta hardware trigger block.
+		compatible = "img,meta-intc";
+	};
+
+Example 2:
+
+	/*
+	 * An interrupt generating device that is wired to a Meta external
+	 * trigger block.
+	 */
+	uart1: uart@0x02004c00 {
+		// Interrupt source '5' that is level-sensitive.
+		// Note that there are only two cells as specified in the
+		// interrupt parent's '#interrupt-cells' property.
+		interrupts = <5 4 /* level */>;
+
+		// The interrupt controller that this device is wired to.
+		interrupt-parent = <&intc>;
+	};

Documentation/kernel-parameters.txt

@@ -978,6 +978,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			       If specified, z/VM IUCV HVC accepts connections
 			       from listed z/VM user IDs only.
 
+	hwthread_map=	[METAG] Comma-separated list of Linux cpu id to
+			        hardware thread id mappings.
+				Format: <cpu>:<hwthread>
+
 	keep_bootcon	[KNL]
 			Do not unregister boot console at start. This is only
 			useful for debugging when something happens in the window

Documentation/metag/00-INDEX

@@ -0,0 +1,4 @@
+00-INDEX
+	- this file
+kernel-ABI.txt
+	- Documents metag ABI details

Documentation/metag/kernel-ABI.txt

@@ -0,0 +1,256 @@
+			==========================
+			KERNEL ABIS FOR METAG ARCH
+			==========================
+
+This document describes the Linux ABIs for the metag architecture, and has the
+following sections:
+
+ (*) Outline of registers
+ (*) Userland registers
+ (*) Kernel registers
+ (*) System call ABI
+ (*) Calling conventions
+
+
+====================
+OUTLINE OF REGISTERS
+====================
+
+The main Meta core registers are arranged in units:
+
+	UNIT	Type	DESCRIPTION	GP	EXT	PRIV	GLOBAL
+	=======	=======	===============	=======	=======	=======	=======
+	CT	Special	Control unit
+	D0	General	Data unit 0	0-7	8-15	16-31	16-31
+	D1	General	Data unit 1	0-7	8-15	16-31	16-31
+	A0	General	Address unit 0	0-3	4-7	 8-15	 8-15
+	A1	General	Address unit 1	0-3	4-7	 8-15	 8-15
+	PC	Special	PC unit		0		 1
+	PORT	Special	Ports
+	TR	Special	Trigger unit			 0-7
+	TT	Special	Trace unit			 0-5
+	FX	General	FP unit			0-15
+
+GP registers form part of the main context.
+
+Extended context registers (EXT) may not be present on all hardware threads and
+can be context switched if support is enabled and the appropriate bits are set
+in e.g. the D0.8 register to indicate what extended state to preserve.
+
+Global registers are shared between threads and are privilege protected.
+
+See arch/metag/include/asm/metag_regs.h for definitions relating to core
+registers and the fields and bits they contain. See the TRMs for further details
+about special registers.
+
+Several special registers are preserved in the main context, these are the
+interesting ones:
+
+	REG	(ALIAS)		PURPOSE
+	=======================	===============================================
+	CT.1	(TXMODE)	Processor mode bits (particularly for DSP)
+	CT.2	(TXSTATUS)	Condition flags and LSM_STEP (MGET/MSET step)
+	CT.3	(TXRPT)		Branch repeat counter
+	PC.0	(PC)		Program counter
+
+Some of the general registers have special purposes in the ABI and therefore
+have aliases:
+
+	D0 REG	(ALIAS)	PURPOSE		D1 REG	(ALIAS)	PURPOSE
+	===============	===============	===============	=======================
+	D0.0	(D0Re0)	32bit result	D1.0	(D1Re0)	Top half of 64bit result
+	D0.1	(D0Ar6)	Argument 6	D1.1	(D1Ar5)	Argument 5
+	D0.2	(D0Ar4)	Argument 4	D1.2	(D1Ar3)	Argument 3
+	D0.3	(D0Ar2)	Argument 2	D1.3	(D1Ar1)	Argument 1
+	D0.4	(D0FrT)	Frame temp	D1.4	(D1RtP)	Return pointer
+	D0.5		Call preserved	D1.5		Call preserved
+	D0.6		Call preserved	D1.6		Call preserved
+	D0.7		Call preserved	D1.7		Call preserved
+
+	A0 REG	(ALIAS)	PURPOSE		A1 REG	(ALIAS)	PURPOSE
+	===============	===============	===============	=======================
+	A0.0	(A0StP)	Stack pointer	A1.0	(A1GbP)	Global base pointer
+	A0.1	(A0FrP)	Frame pointer	A1.1	(A1LbP)	Local base pointer
+	A0.2				A1.2
+	A0.3				A1.3
+
+
+==================
+USERLAND REGISTERS
+==================
+
+All the general purpose D0, D1, A0, A1 registers are preserved when entering the
+kernel (including asynchronous events such as interrupts and timer ticks) except
+the following which have special purposes in the ABI:
+
+	REGISTERS	WHEN	STATUS		PURPOSE
+	===============	=======	===============	===============================
+	D0.8		DSP	Preserved	ECH, determines what extended
+						DSP state to preserve.
+	A0.0	(A0StP)	ALWAYS	Preserved	Stack >= A0StP may be clobbered
+						at any time by the creation of a
+						signal frame.
+	A1.0	(A1GbP)	SMP	Clobbered	Used as temporary for loading
+						kernel stack pointer and saving
+						core context.
+	A0.15		!SMP	Protected	Stores kernel stack pointer.
+	A1.15		ALWAYS	Protected	Stores kernel base pointer.
+
+On UP A0.15 is used to store the kernel stack pointer for storing the userland
+context. A0.15 is global between hardware threads though which means it cannot
+be used on SMP for this purpose. Since no protected local registers are
+available A1GbP is reserved for use as a temporary to allow a percpu stack
+pointer to be loaded for storing the rest of the context.
+
+
+================
+KERNEL REGISTERS
+================
+
+When in the kernel the following registers have special purposes in the ABI:
+
+	REGISTERS	WHEN	STATUS		PURPOSE
+	===============	=======	===============	===============================
+	A0.0	(A0StP)	ALWAYS	Preserved	Stack >= A0StP may be clobbered
+						at any time by the creation of
+						an irq signal frame.
+	A1.0	(A1GbP)	ALWAYS	Preserved	Reserved (kernel base pointer).
+
+
+===============
+SYSTEM CALL ABI
+===============
+
+When a system call is made, the following registers are effective:
+
+	REGISTERS	CALL			RETURN
+	===============	=======================	===============================
+	D0.0	(D0Re0)				Return value (or -errno)
+	D1.0	(D1Re0)	System call number	Clobbered
+	D0.1	(D0Ar6)	Syscall arg #6		Preserved
+	D1.1	(D1Ar5)	Syscall arg #5		Preserved
+	D0.2	(D0Ar4)	Syscall arg #4		Preserved
+	D1.2	(D1Ar3)	Syscall arg #3		Preserved
+	D0.3	(D0Ar2)	Syscall arg #2		Preserved
+	D1.3	(D1Ar1)	Syscall arg #1		Preserved
+
+Due to the limited number of argument registers and some system calls with badly
+aligned 64-bit arguments, 64-bit values are always packed in consecutive
+arguments, even if this is contrary to the normal calling conventions (where the
+two halves would go in a matching pair of data registers).
+
+For example fadvise64_64 usually has the signature:
+
+	long sys_fadvise64_64(i32 fd, i64 offs, i64 len, i32 advice);
+
+But for metag fadvise64_64 is wrapped so that the 64-bit arguments are packed:
+
+	long sys_fadvise64_64_metag(i32 fd,      i32 offs_lo,
+				    i32 offs_hi, i32 len_lo,
+				    i32 len_hi,  i32 advice)
+
+So the arguments are packed in the registers like this:
+
+	D0 REG	(ALIAS)	VALUE		D1 REG	(ALIAS)	VALUE
+	===============	===============	===============	=======================
+	D0.1	(D0Ar6)	advice		D1.1	(D1Ar5)	hi(len)
+	D0.2	(D0Ar4)	lo(len)		D1.2	(D1Ar3)	hi(offs)
+	D0.3	(D0Ar2)	lo(offs)	D1.3	(D1Ar1)	fd
+
+
+===================
+CALLING CONVENTIONS
+===================
+
+These calling conventions apply to both user and kernel code. The stack grows
+from low addresses to high addresses in the metag ABI. The stack pointer (A0StP)
+should always point to the next free address on the stack and should at all
+times be 64-bit aligned. The following registers are effective at the point of a
+call:
+
+	REGISTERS	CALL			RETURN
+	===============	=======================	===============================
+	D0.0	(D0Re0)				32bit return value
+	D1.0	(D1Re0)				Upper half of 64bit return value
+	D0.1	(D0Ar6)	32bit argument #6	Clobbered
+	D1.1	(D1Ar5)	32bit argument #5	Clobbered
+	D0.2	(D0Ar4)	32bit argument #4	Clobbered
+	D1.2	(D1Ar3)	32bit argument #3	Clobbered
+	D0.3	(D0Ar2)	32bit argument #2	Clobbered
+	D1.3	(D1Ar1)	32bit argument #1	Clobbered
+	D0.4	(D0FrT)				Clobbered
+	D1.4	(D1RtP)	Return pointer		Clobbered
+	D{0-1}.{5-7}				Preserved
+	A0.0	(A0StP)	Stack pointer		Preserved
+	A1.0	(A0GbP)				Preserved
+	A0.1	(A0FrP)	Frame pointer		Preserved
+	A1.1	(A0LbP)				Preserved
+	A{0-1},{2-3}				Clobbered
+
+64-bit arguments are placed in matching pairs of registers (i.e. the same
+register number in both D0 and D1 units), with the least significant half in D0
+and the most significant half in D1, leaving a gap where necessary. Futher
+arguments are stored on the stack in reverse order (earlier arguments at higher
+addresses):
+
+	ADDRESS		0     1     2     3	4     5     6     7
+	===============	===== ===== ===== =====	===== ===== ===== =====
+	A0StP       -->
+	A0StP-0x08	32bit argument #8	32bit argument #7
+	A0StP-0x10	32bit argument #10	32bit argument #9
+
+Function prologues tend to look a bit like this:
+
+	/* If frame pointer in use, move it to frame temp register so it can be
+	   easily pushed onto stack */
+	MOV	D0FrT,A0FrP
+
+	/* If frame pointer in use, set it to stack pointer */
+	ADD	A0FrP,A0StP,#0
+
+	/* Preserve D0FrT, D1RtP, D{0-1}.{5-7} on stack, incrementing A0StP */
+	MSETL	[A0StP++],D0FrT,D0.5,D0.6,D0.7
+
+	/* Allocate some stack space for local variables */
+	ADD	A0StP,A0StP,#0x10
+
+At this point the stack would look like this:
+
+	ADDRESS		0     1     2     3	4     5     6     7
+	===============	===== ===== ===== =====	===== ===== ===== =====
+	A0StP       -->
+	A0StP-0x08
+	A0StP-0x10
+	A0StP-0x18	Old D0.7		Old D1.7
+	A0StP-0x20	Old D0.6		Old D1.6
+	A0StP-0x28	Old D0.5		Old D1.5
+	A0FrP       -->	Old A0FrP (frame ptr)	Old D1RtP (return ptr)
+	A0FrP-0x08	32bit argument #8	32bit argument #7
+	A0FrP-0x10	32bit argument #10	32bit argument #9
+
+Function epilogues tend to differ depending on the use of a frame pointer. An
+example of a frame pointer epilogue:
+
+	/* Restore D0FrT, D1RtP, D{0-1}.{5-7} from stack, incrementing A0FrP */
+	MGETL	D0FrT,D0.5,D0.6,D0.7,[A0FrP++]
+	/* Restore stack pointer to where frame pointer was before increment */
+	SUB	A0StP,A0FrP,#0x20
+	/* Restore frame pointer from frame temp */
+	MOV	A0FrP,D0FrT
+	/* Return to caller via restored return pointer */
+	MOV	PC,D1RtP
+
+If the function hasn't touched the frame pointer, MGETL cannot be safely used
+with A0StP as it always increments and that would expose the stack to clobbering
+by interrupts (kernel) or signals (user). Therefore it's common to see the MGETL
+split into separate GETL instructions:
+
+	/* Restore D0FrT, D1RtP, D{0-1}.{5-7} from stack */
+	GETL	D0FrT,D1RtP,[A0StP+#-0x30]
+	GETL	D0.5,D1.5,[A0StP+#-0x28]
+	GETL	D0.6,D1.6,[A0StP+#-0x20]
+	GETL	D0.7,D1.7,[A0StP+#-0x18]
+	/* Restore stack pointer */
+	SUB	A0StP,A0StP,#0x30
+	/* Return to caller via restored return pointer */
+	MOV	PC,D1RtP

MAINTAINERS

@@ -5204,6 +5204,18 @@ F:	drivers/mtd/
 F:	include/linux/mtd/
 F:	include/uapi/mtd/
 
+METAG ARCHITECTURE
+M:	James Hogan <james.hogan@imgtec.com>
+S:	Supported
+F:	arch/metag/
+F:	Documentation/metag/
+F:	Documentation/devicetree/bindings/metag/
+F:	drivers/clocksource/metag_generic.c
+F:	drivers/irqchip/irq-metag.c
+F:	drivers/irqchip/irq-metag-ext.c
+F:	drivers/tty/metag_da.c
+F:	fs/imgdafs/
+
 MICROBLAZE ARCHITECTURE
 M:	Michal Simek <monstr@monstr.eu>
 L:	microblaze-uclinux@itee.uq.edu.au (moderated for non-subscribers)

arch/Kconfig

@@ -103,6 +103,22 @@ config UPROBES
 
 	  If in doubt, say "N".
 
+config HAVE_64BIT_ALIGNED_ACCESS
+	def_bool 64BIT && !HAVE_EFFICIENT_UNALIGNED_ACCESS
+	help
+	  Some architectures require 64 bit accesses to be 64 bit
+	  aligned, which also requires structs containing 64 bit values
+	  to be 64 bit aligned too. This includes some 32 bit
+	  architectures which can do 64 bit accesses, as well as 64 bit
+	  architectures without unaligned access.
+
+	  This symbol should be selected by an architecture if 64 bit
+	  accesses are required to be 64 bit aligned in this way even
+	  though it is not a 64 bit architecture.
+
+	  See Documentation/unaligned-memory-access.txt for more
+	  information on the topic of unaligned memory accesses.
+
 config HAVE_EFFICIENT_UNALIGNED_ACCESS
 	bool
 	help

arch/metag/Kconfig

@@ -0,0 +1,290 @@
+config SYMBOL_PREFIX
+	string
+	default "_"
+
+config METAG
+	def_bool y
+	select EMBEDDED
+	select GENERIC_ATOMIC64
+	select GENERIC_CLOCKEVENTS
+	select GENERIC_IRQ_SHOW
+	select GENERIC_SMP_IDLE_THREAD
+	select HAVE_64BIT_ALIGNED_ACCESS
+	select HAVE_ARCH_TRACEHOOK
+	select HAVE_C_RECORDMCOUNT
+	select HAVE_DEBUG_KMEMLEAK
+	select HAVE_DYNAMIC_FTRACE
+	select HAVE_FTRACE_MCOUNT_RECORD
+	select HAVE_FUNCTION_TRACER
+	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
+	select HAVE_GENERIC_HARDIRQS
+	select HAVE_KERNEL_BZIP2
+	select HAVE_KERNEL_GZIP
+	select HAVE_KERNEL_LZO
+	select HAVE_KERNEL_XZ
+	select HAVE_MEMBLOCK
+	select HAVE_MEMBLOCK_NODE_MAP
+	select HAVE_MOD_ARCH_SPECIFIC
+	select HAVE_PERF_EVENTS
+	select HAVE_SYSCALL_TRACEPOINTS
+	select IRQ_DOMAIN
+	select MODULES_USE_ELF_RELA
+	select OF
+	select OF_EARLY_FLATTREE
+	select SPARSE_IRQ
+
+config STACKTRACE_SUPPORT
+	def_bool y
+
+config LOCKDEP_SUPPORT
+	def_bool y
+
+config HAVE_LATENCYTOP_SUPPORT
+	def_bool y
+
+config RWSEM_GENERIC_SPINLOCK
+	def_bool y
+
+config RWSEM_XCHGADD_ALGORITHM
+	bool
+
+config GENERIC_HWEIGHT
+	def_bool y
+
+config GENERIC_CALIBRATE_DELAY
+	def_bool y
+
+config GENERIC_GPIO
+	def_bool n
+
+config NO_IOPORT
+	def_bool y
+
+source "init/Kconfig"
+
+source "kernel/Kconfig.freezer"
+
+menu "Processor type and features"
+
+config MMU
+	def_bool y
+
+config STACK_GROWSUP
+	def_bool y
+
+config HOTPLUG_CPU
+	bool "Enable CPU hotplug support"
+	depends on SMP
+	help
+	  Say Y here to allow turning CPUs off and on. CPUs can be
+	  controlled through /sys/devices/system/cpu.
+
+	  Say N if you want to disable CPU hotplug.
+
+config HIGHMEM
+	bool "High Memory Support"
+	help
+	  The address space of Meta processors is only 4 Gigabytes large
+	  and it has to accommodate user address space, kernel address
+	  space as well as some memory mapped IO. That means that, if you
+	  have a large amount of physical memory and/or IO, not all of the
+	  memory can be "permanently mapped" by the kernel. The physical
+	  memory that is not permanently mapped is called "high memory".
+
+	  Depending on the selected kernel/user memory split, minimum
+	  vmalloc space and actual amount of RAM, you may not need this
+	  option which should result in a slightly faster kernel.
+
+	  If unsure, say n.
+
+source "arch/metag/mm/Kconfig"
+
+source "arch/metag/Kconfig.soc"
+
+config METAG_META12
+	bool
+	help
+	  Select this from the SoC config symbol to indicate that it contains a
+	  Meta 1.2 core.
+
+config METAG_META21
+	bool
+	help
+	  Select this from the SoC config symbol to indicate that it contains a
+	  Meta 2.1 core.
+
+config SMP
+	bool "Symmetric multi-processing support"
+	depends on METAG_META21 && METAG_META21_MMU
+	select USE_GENERIC_SMP_HELPERS
+	help
+	  This enables support for systems with more than one thread running
+	  Linux. If you have a system with only one thread running Linux,
+	  say N. Otherwise, say Y.
+
+config NR_CPUS
+	int "Maximum number of CPUs (2-4)" if SMP
+	range 2 4 if SMP
+	default "1" if !SMP
+	default "4" if SMP
+
+config METAG_SMP_WRITE_REORDERING
+	bool
+	help
+	  This attempts to prevent cache-memory incoherence due to external
+	  reordering of writes from different hardware threads when SMP is
+	  enabled. It adds fences (system event 0) to smp_mb and smp_rmb in an
+	  attempt to catch some of the cases, and also before writes to shared
+	  memory in LOCK1 protected atomics and spinlocks.
+	  This will not completely prevent cache incoherency on affected cores.
+
+config METAG_LNKGET_AROUND_CACHE
+	bool
+	depends on METAG_META21
+	help
+	  This indicates that the LNKGET/LNKSET instructions go around the
+	  cache, which requires some extra cache flushes when the memory needs
+	  to be accessed by normal GET/SET instructions too.
+
+choice
+	prompt "Atomicity primitive"
+	default METAG_ATOMICITY_LNKGET
+	help
+	  This option selects the mechanism for performing atomic operations.
+
+config METAG_ATOMICITY_IRQSOFF
+	depends on !SMP
+	bool "irqsoff"
+	help
+	  This option disables interrupts to achieve atomicity. This mechanism
+	  is not SMP-safe.
+
+config METAG_ATOMICITY_LNKGET
+	depends on METAG_META21
+	bool "lnkget/lnkset"
+	help
+	  This option uses the LNKGET and LNKSET instructions to achieve
+	  atomicity. LNKGET/LNKSET are load-link/store-conditional instructions.
+	  Choose this option if your system requires low latency.
+
+config METAG_ATOMICITY_LOCK1
+	depends on SMP
+	bool "lock1"
+	help
+	  This option uses the LOCK1 instruction for atomicity. This is mainly
+	  provided as a debugging aid if the lnkget/lnkset atomicity primitive
+	  isn't working properly.
+
+endchoice
+
+config METAG_FPU
+	bool "FPU Support"
+	depends on METAG_META21
+	default y
+	help
+	  This option allows processes to use FPU hardware available with this
+	  CPU. If this option is not enabled FPU registers will not be saved
+	  and restored on context-switch.
+
+	  If you plan on running programs which are compiled to use hard floats
+	  say Y here.
+
+config METAG_DSP
+	bool "DSP Support"
+	help
+	  This option allows processes to use DSP hardware available
+	  with this CPU. If this option is not enabled DSP registers
+	  will not be saved and restored on context-switch.
+
+	  If you plan on running DSP programs say Y here.
+
+config METAG_PERFCOUNTER_IRQS
+	bool "PerfCounters interrupt support"
+	depends on METAG_META21
+	help
+	  This option enables using interrupts to collect information from
+	  Performance Counters. This option is supported in new META21
+	  (starting from HTP265).
+
+	  When disabled, Performance Counters information will be collected
+	  based on Timer Interrupt.
+
+config METAG_DA
+	bool "DA support"
+	help
+	  Say Y if you plan to use a DA debug adapter with Linux. The presence
+	  of the DA will be detected automatically at boot, so it is safe to say
+	  Y to this option even when booting without a DA.
+
+	  This enables support for services provided by DA JTAG debug adapters,
+	  such as:
+	  - communication over DA channels (such as the console driver).
+	  - use of the DA filesystem.
+
+menu "Boot options"
+
+config METAG_BUILTIN_DTB
+	bool "Embed DTB in kernel image"
+	default y
+	help
+	  Embeds a device tree binary in the kernel image.
+
+config METAG_BUILTIN_DTB_NAME
+	string "Built in DTB"
+	depends on METAG_BUILTIN_DTB
+	help
+	  Set the name of the DTB to embed (leave blank to pick one
+	  automatically based on kernel configuration).
+
+config CMDLINE_BOOL
+	bool "Default bootloader kernel arguments"
+
+config CMDLINE
+	string "Kernel command line"
+	depends on CMDLINE_BOOL
+	help
+	  On some architectures there is currently no way for the boot loader
+	  to pass arguments to the kernel. For these architectures, you should
+	  supply some command-line options at build time by entering them
+	  here.
+
+config CMDLINE_FORCE
+	bool "Force default kernel command string"
+	depends on CMDLINE_BOOL
+	help
+	  Set this to have arguments from the default kernel command string
+	  override those passed by the boot loader.
+
+endmenu
+
+source "kernel/Kconfig.preempt"
+
+source kernel/Kconfig.hz
+
+endmenu
+
+menu "Power management options"
+
+source kernel/power/Kconfig
+
+endmenu
+
+menu "Executable file formats"
+
+source "fs/Kconfig.binfmt"
+
+endmenu
+
+source "net/Kconfig"
+
+source "drivers/Kconfig"
+
+source "fs/Kconfig"
+
+source "arch/metag/Kconfig.debug"
+
+source "security/Kconfig"
+
+source "crypto/Kconfig"
+
+source "lib/Kconfig"

arch/metag/Kconfig.debug

@@ -0,0 +1,40 @@
+menu "Kernel hacking"
+
+config TRACE_IRQFLAGS_SUPPORT
+	bool
+	default y
+
+source "lib/Kconfig.debug"
+
+config DEBUG_STACKOVERFLOW
+	bool "Check for stack overflows"
+	depends on DEBUG_KERNEL
+	help
+	  This option will cause messages to be printed if free stack space
+	  drops below a certain limit.
+
+config 4KSTACKS
+	bool "Use 4Kb for kernel stacks instead of 8Kb"
+	depends on DEBUG_KERNEL
+	help
+	  If you say Y here the kernel will use a 4Kb stacksize for the
+	  kernel stack attached to each process/thread. This facilitates
+	  running more threads on a system and also reduces the pressure
+	  on the VM subsystem for higher order allocations. This option
+	  will also use IRQ stacks to compensate for the reduced stackspace.
+
+config METAG_FUNCTION_TRACE
+	bool "Output Meta real-time trace data for function entry/exit"
+	help
+	  If you say Y here the kernel will use the Meta hardware trace
+	  unit to output information about function entry and exit that
+	  can be used by a debugger for profiling and call-graphs.
+
+config METAG_POISON_CATCH_BUFFERS
+	bool "Poison catch buffer contents on kernel entry"
+	help
+	  If you say Y here the kernel will write poison data to the
+	  catch buffer registers on kernel entry. This will make any
+	  problem with catch buffer handling much more apparent.
+
+endmenu

arch/metag/Kconfig.soc

@@ -0,0 +1,55 @@
+choice
+	prompt "SoC Type"
+	default META21_FPGA
+
+config META12_FPGA
+	bool "Meta 1.2 FPGA"
+	select METAG_META12
+	help
+	  This is a Meta 1.2 FPGA bitstream, just a bare CPU.
+
+config META21_FPGA
+	bool "Meta 2.1 FPGA"
+	select METAG_META21
+	help
+	  This is a Meta 2.1 FPGA bitstream, just a bare CPU.
+
+endchoice
+
+menu "SoC configuration"
+
+if METAG_META21
+
+# Meta 2.x specific options
+
+config METAG_META21_MMU
+	bool "Meta 2.x MMU mode"
+	default y
+	help
+	  Use the Meta 2.x MMU in extended mode.
+
+config METAG_UNALIGNED
+	bool "Meta 2.x unaligned access checking"
+	default y
+	help
+	  All memory accesses will be checked for alignment and an exception
+	  raised on unaligned accesses. This feature does cost performance
+	  but without it there will be no notification of this type of error.
+
+config METAG_USER_TCM
+	bool "Meta on-chip memory support for userland"
+	select GENERIC_ALLOCATOR
+	default y
+	help
+	  Allow the on-chip memories of Meta SoCs to be used by user
+	  applications.
+
+endif
+
+config METAG_HALT_ON_PANIC
+	bool "Halt the core on panic"
+	help
+	  Halt the core when a panic occurs. This is useful when running
+	  pre-production silicon or in an FPGA environment.
+
+endmenu

arch/metag/Makefile

@@ -0,0 +1,87 @@
+#
+# metag/Makefile
+#
+# This file is included by the global makefile so that you can add your own
+# architecture-specific flags and dependencies. Remember to do have actions
+# for "archclean" cleaning up for this architecture.
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License.  See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+# Copyright (C) 1994 by Linus Torvalds
+#               2007,2008,2012 by Imagination Technologies Ltd.
+#
+
+LDFLAGS					:=
+OBJCOPYFLAGS				:= -O binary -R .note -R .comment -S
+
+checkflags-$(CONFIG_METAG_META12)	+= -DMETAC_1_2
+checkflags-$(CONFIG_METAG_META21)	+= -DMETAC_2_1
+CHECKFLAGS				+= -D__metag__ $(checkflags-y)
+
+KBUILD_DEFCONFIG			:= meta2_defconfig
+
+sflags-$(CONFIG_METAG_META12)		+= -mmetac=1.2
+ifeq ($(CONFIG_METAG_META12),y)
+# Only use TBI API 1.4 if DSP is enabled for META12 cores
+sflags-$(CONFIG_METAG_DSP)		+= -DTBI_1_4
+endif
+sflags-$(CONFIG_METAG_META21)		+= -mmetac=2.1 -DTBI_1_4
+
+cflags-$(CONFIG_METAG_FUNCTION_TRACE)	+= -mhwtrace-leaf -mhwtrace-retpc
+cflags-$(CONFIG_METAG_META21)		+= -mextensions=bex
+
+KBUILD_CFLAGS				+= -pipe
+KBUILD_CFLAGS				+= -ffunction-sections
+
+KBUILD_CFLAGS				+= $(sflags-y) $(cflags-y)
+KBUILD_AFLAGS				+= $(sflags-y)
+
+LDFLAGS_vmlinux				:= $(ldflags-y)
+
+head-y					:= arch/metag/kernel/head.o
+
+core-y					+= arch/metag/boot/dts/
+core-y					+= arch/metag/kernel/
+core-y					+= arch/metag/mm/
+
+libs-y					+= arch/metag/lib/
+libs-y					+= arch/metag/tbx/
+
+boot					:= arch/metag/boot
+
+boot_targets				+= uImage
+boot_targets				+= uImage.gz
+boot_targets				+= uImage.bz2
+boot_targets				+= uImage.xz
+boot_targets				+= uImage.lzo
+boot_targets				+= uImage.bin
+boot_targets				+= vmlinux.bin
+
+PHONY					+= $(boot_targets)
+
+all: vmlinux.bin
+
+$(boot_targets): vmlinux
+	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
+
+%.dtb %.dtb.S %.dtb.o: scripts
+	$(Q)$(MAKE) $(build)=$(boot)/dts $(boot)/dts/$@
+
+dtbs: scripts
+	$(Q)$(MAKE) $(build)=$(boot)/dts dtbs
+
+archclean:
+	$(Q)$(MAKE) $(clean)=$(boot)
+
+define archhelp
+  echo  '* vmlinux.bin	- Binary kernel image (arch/$(ARCH)/boot/vmlinux.bin)'
+  @echo '  uImage  	- Alias to bootable U-Boot image'
+  @echo '  uImage.bin	- Kernel-only image for U-Boot (bin)'
+  @echo '  uImage.gz	- Kernel-only image for U-Boot (gzip)'
+  @echo '  uImage.bz2	- Kernel-only image for U-Boot (bzip2)'
+  @echo '  uImage.xz	- Kernel-only image for U-Boot (xz)'
+  @echo '  uImage.lzo	- Kernel-only image for U-Boot (lzo)'
+  @echo '  dtbs		- Build device tree blobs for enabled boards'
+endef

arch/metag/boot/.gitignore

@@ -0,0 +1,4 @@
+vmlinux*
+uImage*
+ramdisk.*
+*.dtb

arch/metag/boot/Makefile

@@ -0,0 +1,68 @@
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License.  See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+# Copyright (C) 2007,2012  Imagination Technologies Ltd.
+#
+
+suffix-y := bin
+suffix-$(CONFIG_KERNEL_GZIP)	:= gz
+suffix-$(CONFIG_KERNEL_BZIP2)	:= bz2
+suffix-$(CONFIG_KERNEL_XZ)	:= xz
+suffix-$(CONFIG_KERNEL_LZO)	:= lzo
+
+targets += vmlinux.bin
+targets += uImage
+targets += uImage.gz
+targets += uImage.bz2
+targets += uImage.xz
+targets += uImage.lzo
+targets += uImage.bin
+
+extra-y += vmlinux.bin
+extra-y += vmlinux.bin.gz
+extra-y += vmlinux.bin.bz2
+extra-y += vmlinux.bin.xz
+extra-y += vmlinux.bin.lzo
+
+UIMAGE_LOADADDR = $(CONFIG_PAGE_OFFSET)
+
+ifeq ($(CONFIG_FUNCTION_TRACER),y)
+orig_cflags := $(KBUILD_CFLAGS)
+KBUILD_CFLAGS = $(subst -pg, , $(orig_cflags))
+endif
+
+$(obj)/vmlinux.bin: vmlinux FORCE
+	$(call if_changed,objcopy)
+
+$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
+	$(call if_changed,gzip)
+
+$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin FORCE
+	$(call if_changed,bzip2)
+
+$(obj)/vmlinux.bin.xz: $(obj)/vmlinux.bin FORCE
+	$(call if_changed,xzkern)
+
+$(obj)/vmlinux.bin.lzo: $(obj)/vmlinux.bin FORCE
+	$(call if_changed,lzo)
+
+$(obj)/uImage.gz: $(obj)/vmlinux.bin.gz FORCE
+	$(call if_changed,uimage,gzip)
+
+$(obj)/uImage.bz2: $(obj)/vmlinux.bin.bz2 FORCE
+	$(call if_changed,uimage,bzip2)
+
+$(obj)/uImage.xz: $(obj)/vmlinux.bin.xz FORCE
+	$(call if_changed,uimage,xz)
+
+$(obj)/uImage.lzo: $(obj)/vmlinux.bin.lzo FORCE
+	$(call if_changed,uimage,lzo)
+
+$(obj)/uImage.bin: $(obj)/vmlinux.bin FORCE
+	$(call if_changed,uimage,none)
+
+$(obj)/uImage: $(obj)/uImage.$(suffix-y)
+	@ln -sf $(notdir $<) $@
+	@echo '  Image $@ is ready'

arch/metag/boot/dts/Makefile

@@ -0,0 +1,16 @@
+dtb-y	+= skeleton.dtb
+
+# Built-in dtb
+builtindtb-y				:= skeleton
+
+ifneq ($(CONFIG_METAG_BUILTIN_DTB_NAME),"")
+	builtindtb-y			:= $(CONFIG_METAG_BUILTIN_DTB_NAME)
+endif
+obj-$(CONFIG_METAG_BUILTIN_DTB)	+= $(patsubst "%",%,$(builtindtb-y)).dtb.o
+
+targets	+= dtbs
+targets	+= $(dtb-y)
+
+dtbs: $(addprefix $(obj)/, $(dtb-y))
+
+clean-files += *.dtb

arch/metag/boot/dts/skeleton.dts

@@ -0,0 +1,10 @@
+/*
+ * Copyright (C) 2012 Imagination Technologies Ltd.
+ *
+ * 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.dtsi"

arch/metag/boot/dts/skeleton.dtsi

@@ -0,0 +1,14 @@
+/*
+ * Skeleton device tree; the bare minimum needed to boot; just include and
+ * add a compatible value.  The bootloader will typically populate the memory
+ * node.
+ */
+
+/ {
+	compatible = "img,meta";
+	#address-cells = <1>;
+	#size-cells = <1>;
+	chosen { };
+	aliases { };
+	memory { device_type = "memory"; reg = <0 0>; };
+};

arch/metag/configs/meta1_defconfig

@@ -0,0 +1,40 @@
+# CONFIG_LOCALVERSION_AUTO is not set
+# CONFIG_SWAP is not set
+CONFIG_LOG_BUF_SHIFT=13
+CONFIG_SYSFS_DEPRECATED=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_KALLSYMS_ALL=y
+# CONFIG_ELF_CORE is not set
+CONFIG_SLAB=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
+# CONFIG_MSDOS_PARTITION is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+# CONFIG_IOSCHED_CFQ is not set
+CONFIG_FLATMEM_MANUAL=y
+CONFIG_META12_FPGA=y
+CONFIG_METAG_DA=y
+CONFIG_HZ_100=y
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_FW_LOADER is not set
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_COUNT=1
+CONFIG_BLK_DEV_RAM_SIZE=16384
+# CONFIG_INPUT is not set
+# CONFIG_SERIO is not set
+# CONFIG_VT is not set
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_DA_TTY=y
+CONFIG_DA_CONSOLE=y
+# CONFIG_DEVKMEM is not set
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_DNOTIFY is not set
+CONFIG_TMPFS=y
+# CONFIG_MISC_FILESYSTEMS is not set
+# CONFIG_SCHED_DEBUG is not set
+CONFIG_DEBUG_INFO=y

arch/metag/configs/meta2_defconfig

@@ -0,0 +1,41 @@
+# CONFIG_LOCALVERSION_AUTO is not set
+# CONFIG_SWAP is not set
+CONFIG_SYSVIPC=y
+CONFIG_LOG_BUF_SHIFT=13
+CONFIG_SYSFS_DEPRECATED=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_KALLSYMS_ALL=y
+# CONFIG_ELF_CORE is not set
+CONFIG_SLAB=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
+# CONFIG_MSDOS_PARTITION is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+# CONFIG_IOSCHED_CFQ is not set
+CONFIG_METAG_L2C=y
+CONFIG_FLATMEM_MANUAL=y
+CONFIG_METAG_HALT_ON_PANIC=y
+CONFIG_METAG_DA=y
+CONFIG_HZ_100=y
+CONFIG_DEVTMPFS=y
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_FW_LOADER is not set
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_COUNT=1
+CONFIG_BLK_DEV_RAM_SIZE=16384
+# CONFIG_INPUT is not set
+# CONFIG_SERIO is not set
+# CONFIG_VT is not set
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_DA_TTY=y
+CONFIG_DA_CONSOLE=y
+# CONFIG_DEVKMEM is not set
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_DNOTIFY is not set
+CONFIG_TMPFS=y
+# CONFIG_MISC_FILESYSTEMS is not set
+# CONFIG_SCHED_DEBUG is not set
+CONFIG_DEBUG_INFO=y

arch/metag/configs/meta2_smp_defconfig

@@ -0,0 +1,42 @@
+# CONFIG_LOCALVERSION_AUTO is not set
+# CONFIG_SWAP is not set
+CONFIG_SYSVIPC=y
+CONFIG_LOG_BUF_SHIFT=13
+CONFIG_SYSFS_DEPRECATED=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_KALLSYMS_ALL=y
+# CONFIG_ELF_CORE is not set
+CONFIG_SLAB=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
+# CONFIG_MSDOS_PARTITION is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+# CONFIG_IOSCHED_CFQ is not set
+CONFIG_METAG_L2C=y
+CONFIG_FLATMEM_MANUAL=y
+CONFIG_METAG_HALT_ON_PANIC=y
+CONFIG_SMP=y
+CONFIG_METAG_DA=y
+CONFIG_HZ_100=y
+CONFIG_DEVTMPFS=y
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_FW_LOADER is not set
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_COUNT=1
+CONFIG_BLK_DEV_RAM_SIZE=16384
+# CONFIG_INPUT is not set
+# CONFIG_SERIO is not set
+# CONFIG_VT is not set
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_DA_TTY=y
+CONFIG_DA_CONSOLE=y
+# CONFIG_DEVKMEM is not set
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_DNOTIFY is not set
+CONFIG_TMPFS=y
+# CONFIG_MISC_FILESYSTEMS is not set
+# CONFIG_SCHED_DEBUG is not set
+CONFIG_DEBUG_INFO=y

arch/metag/include/asm/Kbuild

@@ -0,0 +1,54 @@
+generic-y += auxvec.h
+generic-y += bitsperlong.h
+generic-y += bugs.h
+generic-y += clkdev.h
+generic-y += cputime.h
+generic-y += current.h
+generic-y += device.h
+generic-y += dma.h
+generic-y += emergency-restart.h
+generic-y += errno.h
+generic-y += exec.h
+generic-y += fb.h
+generic-y += fcntl.h
+generic-y += futex.h
+generic-y += hardirq.h
+generic-y += hw_irq.h
+generic-y += ioctl.h
+generic-y += ioctls.h
+generic-y += ipcbuf.h
+generic-y += irq_regs.h
+generic-y += kdebug.h
+generic-y += kmap_types.h
+generic-y += kvm_para.h
+generic-y += local.h
+generic-y += local64.h
+generic-y += msgbuf.h
+generic-y += mutex.h
+generic-y += param.h
+generic-y += pci.h
+generic-y += percpu.h
+generic-y += poll.h
+generic-y += posix_types.h
+generic-y += scatterlist.h
+generic-y += sections.h
+generic-y += sembuf.h
+generic-y += serial.h
+generic-y += shmbuf.h
+generic-y += shmparam.h
+generic-y += signal.h
+generic-y += socket.h
+generic-y += sockios.h
+generic-y += stat.h
+generic-y += statfs.h
+generic-y += switch_to.h
+generic-y += termbits.h
+generic-y += termios.h
+generic-y += timex.h
+generic-y += trace_clock.h
+generic-y += types.h
+generic-y += ucontext.h
+generic-y += unaligned.h
+generic-y += user.h
+generic-y += vga.h
+generic-y += xor.h

arch/metag/include/asm/atomic.h

@@ -0,0 +1,53 @@
+#ifndef __ASM_METAG_ATOMIC_H
+#define __ASM_METAG_ATOMIC_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <asm/cmpxchg.h>
+
+#if defined(CONFIG_METAG_ATOMICITY_IRQSOFF)
+/* The simple UP case. */
+#include <asm-generic/atomic.h>
+#else
+
+#if defined(CONFIG_METAG_ATOMICITY_LOCK1)
+#include <asm/atomic_lock1.h>
+#else
+#include <asm/atomic_lnkget.h>
+#endif
+
+#define atomic_add_negative(a, v)       (atomic_add_return((a), (v)) < 0)
+
+#define atomic_dec_return(v) atomic_sub_return(1, (v))
+#define atomic_inc_return(v) atomic_add_return(1, (v))
+
+/*
+ * atomic_inc_and_test - increment and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
+
+#define atomic_sub_and_test(i, v) (atomic_sub_return((i), (v)) == 0)
+#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0)
+
+#define atomic_inc(v) atomic_add(1, (v))
+#define atomic_dec(v) atomic_sub(1, (v))
+
+#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
+
+#define smp_mb__before_atomic_dec()	barrier()
+#define smp_mb__after_atomic_dec()	barrier()
+#define smp_mb__before_atomic_inc()	barrier()
+#define smp_mb__after_atomic_inc()	barrier()
+
+#endif
+
+#define atomic_dec_if_positive(v)       atomic_sub_if_positive(1, v)
+
+#include <asm-generic/atomic64.h>
+
+#endif /* __ASM_METAG_ATOMIC_H */

arch/metag/include/asm/atomic_lnkget.h

@@ -0,0 +1,234 @@
+#ifndef __ASM_METAG_ATOMIC_LNKGET_H
+#define __ASM_METAG_ATOMIC_LNKGET_H
+
+#define ATOMIC_INIT(i)	{ (i) }
+
+#define atomic_set(v, i)		((v)->counter = (i))
+
+#include <linux/compiler.h>
+
+#include <asm/barrier.h>
+
+/*
+ * None of these asm statements clobber memory as LNKSET writes around
+ * the cache so the memory it modifies cannot safely be read by any means
+ * other than these accessors.
+ */
+
+static inline int atomic_read(const atomic_t *v)
+{
+	int temp;
+
+	asm volatile (
+		"LNKGETD %0, [%1]\n"
+		: "=da" (temp)
+		: "da" (&v->counter));
+
+	return temp;
+}
+
+static inline void atomic_add(int i, atomic_t *v)
+{
+	int temp;
+
+	asm volatile (
+		"1:	LNKGETD %0, [%1]\n"
+		"	ADD	%0, %0, %2\n"
+		"	LNKSETD [%1], %0\n"
+		"	DEFR	%0, TXSTAT\n"
+		"	ANDT	%0, %0, #HI(0x3f000000)\n"
+		"	CMPT	%0, #HI(0x02000000)\n"
+		"	BNZ	1b\n"
+		: "=&d" (temp)
+		: "da" (&v->counter), "bd" (i)
+		: "cc");
+}
+
+static inline void atomic_sub(int i, atomic_t *v)
+{
+	int temp;
+
+	asm volatile (
+		"1:	LNKGETD %0, [%1]\n"
+		"	SUB	%0, %0, %2\n"
+		"	LNKSETD [%1], %0\n"
+		"	DEFR	%0, TXSTAT\n"
+		"	ANDT	%0, %0, #HI(0x3f000000)\n"
+		"	CMPT	%0, #HI(0x02000000)\n"
+		"	BNZ 1b\n"
+		: "=&d" (temp)
+		: "da" (&v->counter), "bd" (i)
+		: "cc");
+}
+
+static inline int atomic_add_return(int i, atomic_t *v)
+{
+	int result, temp;
+
+	smp_mb();
+
+	asm volatile (
+		"1:	LNKGETD %1, [%2]\n"
+		"	ADD	%1, %1, %3\n"
+		"	LNKSETD [%2], %1\n"
+		"	DEFR	%0, TXSTAT\n"
+		"	ANDT	%0, %0, #HI(0x3f000000)\n"
+		"	CMPT	%0, #HI(0x02000000)\n"
+		"	BNZ 1b\n"
+		: "=&d" (temp), "=&da" (result)
+		: "da" (&v->counter), "bd" (i)
+		: "cc");
+
+	smp_mb();
+
+	return result;
+}
+
+static inline int atomic_sub_return(int i, atomic_t *v)
+{
+	int result, temp;
+
+	smp_mb();
+
+	asm volatile (
+		"1:	LNKGETD %1, [%2]\n"
+		"	SUB	%1, %1, %3\n"
+		"	LNKSETD [%2], %1\n"
+		"	DEFR	%0, TXSTAT\n"
+		"	ANDT	%0, %0, #HI(0x3f000000)\n"
+		"	CMPT	%0, #HI(0x02000000)\n"
+		"	BNZ	1b\n"
+		: "=&d" (temp), "=&da" (result)
+		: "da" (&v->counter), "bd" (i)
+		: "cc");
+
+	smp_mb();
+
+	return result;
+}
+
+static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
+{
+	int temp;
+
+	asm volatile (
+		"1:	LNKGETD %0, [%1]\n"
+		"	AND	%0, %0, %2\n"
+		"	LNKSETD	[%1] %0\n"
+		"	DEFR	%0, TXSTAT\n"
+		"	ANDT	%0, %0, #HI(0x3f000000)\n"
+		"	CMPT	%0, #HI(0x02000000)\n"
+		"	BNZ	1b\n"
+		: "=&d" (temp)
+		: "da" (&v->counter), "bd" (~mask)
+		: "cc");
+}
+
+static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
+{
+	int temp;
+
+	asm volatile (
+		"1:	LNKGETD %0, [%1]\n"
+		"	OR	%0, %0, %2\n"
+		"	LNKSETD	[%1], %0\n"
+		"	DEFR	%0, TXSTAT\n"
+		"	ANDT	%0, %0, #HI(0x3f000000)\n"
+		"	CMPT	%0, #HI(0x02000000)\n"
+		"	BNZ	1b\n"
+		: "=&d" (temp)
+		: "da" (&v->counter), "bd" (mask)
+		: "cc");
+}
+
+static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
+{
+	int result, temp;
+
+	smp_mb();
+
+	asm volatile (
+		"1:	LNKGETD	%1, [%2]\n"
+		"	CMP	%1, %3\n"
+		"	LNKSETDEQ [%2], %4\n"
+		"	BNE	2f\n"
+		"	DEFR	%0, TXSTAT\n"
+		"	ANDT	%0, %0, #HI(0x3f000000)\n"
+		"	CMPT	%0, #HI(0x02000000)\n"
+		"	BNZ	1b\n"
+		"2:\n"
+		: "=&d" (temp), "=&d" (result)
+		: "da" (&v->counter), "bd" (old), "da" (new)
+		: "cc");
+
+	smp_mb();
+
+	return result;
+}
+
+static inline int atomic_xchg(atomic_t *v, int new)
+{
+	int temp, old;
+
+	asm volatile (
+		"1:	LNKGETD %1, [%2]\n"
+		"	LNKSETD	[%2], %3\n"
+		"	DEFR	%0, TXSTAT\n"
+		"	ANDT	%0, %0, #HI(0x3f000000)\n"
+		"	CMPT	%0, #HI(0x02000000)\n"
+		"	BNZ	1b\n"
+		: "=&d" (temp), "=&d" (old)
+		: "da" (&v->counter), "da" (new)
+		: "cc");
+
+	return old;
+}
+
+static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+{
+	int result, temp;
+
+	smp_mb();
+
+	asm volatile (
+		"1:	LNKGETD %1, [%2]\n"
+		"	CMP	%1, %3\n"
+		"	ADD	%0, %1, %4\n"
+		"	LNKSETDNE [%2], %0\n"
+		"	BEQ	2f\n"
+		"	DEFR	%0, TXSTAT\n"
+		"	ANDT	%0, %0, #HI(0x3f000000)\n"
+		"	CMPT	%0, #HI(0x02000000)\n"
+		"	BNZ	1b\n"
+		"2:\n"
+		: "=&d" (temp), "=&d" (result)
+		: "da" (&v->counter), "bd" (u), "bd" (a)
+		: "cc");
+
+	smp_mb();
+
+	return result;
+}
+
+static inline int atomic_sub_if_positive(int i, atomic_t *v)
+{
+	int result, temp;
+
+	asm volatile (
+		"1:	LNKGETD %1, [%2]\n"
+		"	SUBS	%1, %1, %3\n"
+		"	LNKSETDGE [%2], %1\n"
+		"	BLT	2f\n"
+		"	DEFR	%0, TXSTAT\n"
+		"	ANDT	%0, %0, #HI(0x3f000000)\n"
+		"	CMPT	%0, #HI(0x02000000)\n"
+		"	BNZ	1b\n"
+		"2:\n"
+		: "=&d" (temp), "=&da" (result)
+		: "da" (&v->counter), "bd" (i)
+		: "cc");
+
+	return result;
+}
+
+#endif /* __ASM_METAG_ATOMIC_LNKGET_H */

arch/metag/include/asm/atomic_lock1.h

@@ -0,0 +1,160 @@
+#ifndef __ASM_METAG_ATOMIC_LOCK1_H
+#define __ASM_METAG_ATOMIC_LOCK1_H
+
+#define ATOMIC_INIT(i)	{ (i) }
+
+#include <linux/compiler.h>
+
+#include <asm/barrier.h>
+#include <asm/global_lock.h>
+
+static inline int atomic_read(const atomic_t *v)
+{
+	return (v)->counter;
+}
+
+/*
+ * atomic_set needs to be take the lock to protect atomic_add_unless from a
+ * possible race, as it reads the counter twice:
+ *
+ *  CPU0                               CPU1
+ *  atomic_add_unless(1, 0)
+ *    ret = v->counter (non-zero)
+ *    if (ret != u)                    v->counter = 0
+ *      v->counter += 1 (counter set to 1)
+ *
+ * Making atomic_set take the lock ensures that ordering and logical
+ * consistency is preserved.
+ */
+static inline int atomic_set(atomic_t *v, int i)
+{
+	unsigned long flags;
+
+	__global_lock1(flags);
+	fence();
+	v->counter = i;
+	__global_unlock1(flags);
+	return i;
+}
+
+static inline void atomic_add(int i, atomic_t *v)
+{
+	unsigned long flags;
+
+	__global_lock1(flags);
+	fence();
+	v->counter += i;
+	__global_unlock1(flags);
+}
+
+static inline void atomic_sub(int i, atomic_t *v)
+{
+	unsigned long flags;
+
+	__global_lock1(flags);
+	fence();
+	v->counter -= i;
+	__global_unlock1(flags);
+}
+
+static inline int atomic_add_return(int i, atomic_t *v)
+{
+	unsigned long result;
+	unsigned long flags;
+
+	__global_lock1(flags);
+	result = v->counter;
+	result += i;
+	fence();
+	v->counter = result;
+	__global_unlock1(flags);
+
+	return result;
+}
+
+static inline int atomic_sub_return(int i, atomic_t *v)
+{
+	unsigned long result;
+	unsigned long flags;
+
+	__global_lock1(flags);
+	result = v->counter;
+	result -= i;
+	fence();
+	v->counter = result;
+	__global_unlock1(flags);
+
+	return result;
+}
+
+static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
+{
+	unsigned long flags;
+
+	__global_lock1(flags);
+	fence();
+	v->counter &= ~mask;
+	__global_unlock1(flags);
+}
+
+static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
+{
+	unsigned long flags;
+
+	__global_lock1(flags);
+	fence();
+	v->counter |= mask;
+	__global_unlock1(flags);
+}
+
+static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
+{
+	int ret;
+	unsigned long flags;
+
+	__global_lock1(flags);
+	ret = v->counter;
+	if (ret == old) {
+		fence();
+		v->counter = new;
+	}
+	__global_unlock1(flags);
+
+	return ret;
+}
+
+#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
+
+static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+{
+	int ret;
+	unsigned long flags;
+
+	__global_lock1(flags);
+	ret = v->counter;
+	if (ret != u) {
+		fence();
+		v->counter += a;
+	}
+	__global_unlock1(flags);
+
+	return ret;
+}
+
+static inline int atomic_sub_if_positive(int i, atomic_t *v)
+{
+	int ret;
+	unsigned long flags;
+
+	__global_lock1(flags);
+	ret = v->counter - 1;
+	if (ret >= 0) {
+		fence();
+		v->counter = ret;
+	}
+	__global_unlock1(flags);
+
+	return ret;
+}
+
+#endif /* __ASM_METAG_ATOMIC_LOCK1_H */

arch/metag/include/asm/barrier.h

@@ -0,0 +1,85 @@
+#ifndef _ASM_METAG_BARRIER_H
+#define _ASM_METAG_BARRIER_H
+
+#include <asm/metag_mem.h>
+
+#define nop()		asm volatile ("NOP")
+#define mb()		wmb()
+#define rmb()		barrier()
+
+#ifdef CONFIG_METAG_META21
+
+/* HTP and above have a system event to fence writes */
+static inline void wr_fence(void)
+{
+	volatile int *flushptr = (volatile int *) LINSYSEVENT_WR_FENCE;
+	barrier();
+	*flushptr = 0;
+}
+
+#else /* CONFIG_METAG_META21 */
+
+/*
+ * ATP doesn't have system event to fence writes, so it is necessary to flush
+ * the processor write queues as well as possibly the write combiner (depending
+ * on the page being written).
+ * To ensure the write queues are flushed we do 4 writes to a system event
+ * register (in this case write combiner flush) which will also flush the write
+ * combiner.
+ */
+static inline void wr_fence(void)
+{
+	volatile int *flushptr = (volatile int *) LINSYSEVENT_WR_COMBINE_FLUSH;
+	barrier();
+	*flushptr = 0;
+	*flushptr = 0;
+	*flushptr = 0;
+	*flushptr = 0;
+}
+
+#endif /* !CONFIG_METAG_META21 */
+
+static inline void wmb(void)
+{
+	/* flush writes through the write combiner */
+	wr_fence();
+}
+
+#define read_barrier_depends()  do { } while (0)
+
+#ifndef CONFIG_SMP
+#define fence()		do { } while (0)
+#define smp_mb()        barrier()
+#define smp_rmb()       barrier()
+#define smp_wmb()       barrier()
+#else
+
+#ifdef CONFIG_METAG_SMP_WRITE_REORDERING
+/*
+ * Write to the atomic memory unlock system event register (command 0). This is
+ * needed before a write to shared memory in a critical section, to prevent
+ * external reordering of writes before the fence on other threads with writes
+ * after the fence on this thread (and to prevent the ensuing cache-memory
+ * incoherence). It is therefore ineffective if used after and on the same
+ * thread as a write.
+ */
+static inline void fence(void)
+{
+	volatile int *flushptr = (volatile int *) LINSYSEVENT_WR_ATOMIC_UNLOCK;
+	barrier();
+	*flushptr = 0;
+}
+#define smp_mb()        fence()
+#define smp_rmb()       fence()
+#define smp_wmb()       barrier()
+#else
+#define fence()		do { } while (0)
+#define smp_mb()        barrier()
+#define smp_rmb()       barrier()
+#define smp_wmb()       barrier()
+#endif
+#endif
+#define smp_read_barrier_depends()     do { } while (0)
+#define set_mb(var, value) do { var = value; smp_mb(); } while (0)
+
+#endif /* _ASM_METAG_BARRIER_H */

arch/metag/include/asm/bitops.h

@@ -0,0 +1,132 @@
+#ifndef __ASM_METAG_BITOPS_H
+#define __ASM_METAG_BITOPS_H
+
+#include <linux/compiler.h>
+#include <asm/barrier.h>
+#include <asm/global_lock.h>
+
+/*
+ * clear_bit() doesn't provide any barrier for the compiler.
+ */
+#define smp_mb__before_clear_bit()	barrier()
+#define smp_mb__after_clear_bit()	barrier()
+
+#ifdef CONFIG_SMP
+/*
+ * These functions are the basis of our bit ops.
+ */
+static inline void set_bit(unsigned int bit, volatile unsigned long *p)
+{
+	unsigned long flags;
+	unsigned long mask = 1UL << (bit & 31);
+
+	p += bit >> 5;
+
+	__global_lock1(flags);
+	fence();
+	*p |= mask;
+	__global_unlock1(flags);
+}
+
+static inline void clear_bit(unsigned int bit, volatile unsigned long *p)
+{
+	unsigned long flags;
+	unsigned long mask = 1UL << (bit & 31);
+
+	p += bit >> 5;
+
+	__global_lock1(flags);
+	fence();
+	*p &= ~mask;
+	__global_unlock1(flags);
+}
+
+static inline void change_bit(unsigned int bit, volatile unsigned long *p)
+{
+	unsigned long flags;
+	unsigned long mask = 1UL << (bit & 31);
+
+	p += bit >> 5;
+
+	__global_lock1(flags);
+	fence();
+	*p ^= mask;
+	__global_unlock1(flags);
+}
+
+static inline int test_and_set_bit(unsigned int bit, volatile unsigned long *p)
+{
+	unsigned long flags;
+	unsigned long old;
+	unsigned long mask = 1UL << (bit & 31);
+
+	p += bit >> 5;
+
+	__global_lock1(flags);
+	old = *p;
+	if (!(old & mask)) {
+		fence();
+		*p = old | mask;
+	}
+	__global_unlock1(flags);
+
+	return (old & mask) != 0;
+}
+
+static inline int test_and_clear_bit(unsigned int bit,
+				     volatile unsigned long *p)
+{
+	unsigned long flags;
+	unsigned long old;
+	unsigned long mask = 1UL << (bit & 31);
+
+	p += bit >> 5;
+
+	__global_lock1(flags);
+	old = *p;
+	if (old & mask) {
+		fence();
+		*p = old & ~mask;
+	}
+	__global_unlock1(flags);
+
+	return (old & mask) != 0;
+}
+
+static inline int test_and_change_bit(unsigned int bit,
+				      volatile unsigned long *p)
+{
+	unsigned long flags;
+	unsigned long old;
+	unsigned long mask = 1UL << (bit & 31);
+
+	p += bit >> 5;
+
+	__global_lock1(flags);
+	fence();
+	old = *p;
+	*p = old ^ mask;
+	__global_unlock1(flags);
+
+	return (old & mask) != 0;
+}
+
+#else
+#include <asm-generic/bitops/atomic.h>
+#endif /* CONFIG_SMP */
+
+#include <asm-generic/bitops/non-atomic.h>
+#include <asm-generic/bitops/find.h>
+#include <asm-generic/bitops/ffs.h>
+#include <asm-generic/bitops/__ffs.h>
+#include <asm-generic/bitops/ffz.h>
+#include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
+#include <asm-generic/bitops/fls64.h>
+#include <asm-generic/bitops/hweight.h>
+#include <asm-generic/bitops/lock.h>
+#include <asm-generic/bitops/sched.h>
+#include <asm-generic/bitops/le.h>
+#include <asm-generic/bitops/ext2-atomic.h>
+
+#endif /* __ASM_METAG_BITOPS_H */

arch/metag/include/asm/bug.h

@@ -0,0 +1,12 @@
+#ifndef _ASM_METAG_BUG_H
+#define _ASM_METAG_BUG_H
+
+#include <asm-generic/bug.h>
+
+struct pt_regs;
+
+extern const char *trap_name(int trapno);
+extern void die(const char *str, struct pt_regs *regs, long err,
+		unsigned long addr) __attribute__ ((noreturn));
+
+#endif

arch/metag/include/asm/cache.h

@@ -0,0 +1,23 @@
+#ifndef __ASM_METAG_CACHE_H
+#define __ASM_METAG_CACHE_H
+
+/* L1 cache line size (64 bytes) */
+#define L1_CACHE_SHIFT		6
+#define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
+
+/* Meta requires large data items to be 8 byte aligned. */
+#define ARCH_SLAB_MINALIGN	8
+
+/*
+ * With an L2 cache, we may invalidate dirty lines, so we need to ensure DMA
+ * buffers have cache line alignment.
+ */
+#ifdef CONFIG_METAG_L2C
+#define ARCH_DMA_MINALIGN	L1_CACHE_BYTES
+#else
+#define ARCH_DMA_MINALIGN	8
+#endif
+
+#define __read_mostly __attribute__((__section__(".data..read_mostly")))
+
+#endif

arch/metag/include/asm/cacheflush.h

@@ -0,0 +1,250 @@
+#ifndef _METAG_CACHEFLUSH_H
+#define _METAG_CACHEFLUSH_H
+
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/io.h>
+
+#include <asm/l2cache.h>
+#include <asm/metag_isa.h>
+#include <asm/metag_mem.h>
+
+void metag_cache_probe(void);
+
+void metag_data_cache_flush_all(const void *start);
+void metag_code_cache_flush_all(const void *start);
+
+/*
+ * Routines to flush physical cache lines that may be used to cache data or code
+ * normally accessed via the linear address range supplied. The region flushed
+ * must either lie in local or global address space determined by the top bit of
+ * the pStart address. If Bytes is >= 4K then the whole of the related cache
+ * state will be flushed rather than a limited range.
+ */
+void metag_data_cache_flush(const void *start, int bytes);
+void metag_code_cache_flush(const void *start, int bytes);
+
+#ifdef CONFIG_METAG_META12
+
+/* Write through, virtually tagged, split I/D cache. */
+
+static inline void __flush_cache_all(void)
+{
+	metag_code_cache_flush_all((void *) PAGE_OFFSET);
+	metag_data_cache_flush_all((void *) PAGE_OFFSET);
+}
+
+#define flush_cache_all() __flush_cache_all()
+
+/* flush the entire user address space referenced in this mm structure */
+static inline void flush_cache_mm(struct mm_struct *mm)
+{
+	if (mm == current->mm)
+		__flush_cache_all();
+}
+
+#define flush_cache_dup_mm(mm) flush_cache_mm(mm)
+
+/* flush a range of addresses from this mm */
+static inline void flush_cache_range(struct vm_area_struct *vma,
+				     unsigned long start, unsigned long end)
+{
+	flush_cache_mm(vma->vm_mm);
+}
+
+static inline void flush_cache_page(struct vm_area_struct *vma,
+				    unsigned long vmaddr, unsigned long pfn)
+{
+	flush_cache_mm(vma->vm_mm);
+}
+
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE	1
+static inline void flush_dcache_page(struct page *page)
+{
+	metag_data_cache_flush_all((void *) PAGE_OFFSET);
+}
+
+#define flush_dcache_mmap_lock(mapping)		do { } while (0)
+#define flush_dcache_mmap_unlock(mapping)	do { } while (0)
+
+static inline void flush_icache_page(struct vm_area_struct *vma,
+				     struct page *page)
+{
+	metag_code_cache_flush(page_to_virt(page), PAGE_SIZE);
+}
+
+static inline void flush_cache_vmap(unsigned long start, unsigned long end)
+{
+	metag_data_cache_flush_all((void *) PAGE_OFFSET);
+}
+
+static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
+{
+	metag_data_cache_flush_all((void *) PAGE_OFFSET);
+}
+
+#else
+
+/* Write through, physically tagged, split I/D cache. */
+
+#define flush_cache_all()			do { } while (0)
+#define flush_cache_mm(mm)			do { } while (0)
+#define flush_cache_dup_mm(mm)			do { } while (0)
+#define flush_cache_range(vma, start, end)	do { } while (0)
+#define flush_cache_page(vma, vmaddr, pfn)	do { } while (0)
+#define flush_dcache_mmap_lock(mapping)		do { } while (0)
+#define flush_dcache_mmap_unlock(mapping)	do { } while (0)
+#define flush_icache_page(vma, pg)		do { } while (0)
+#define flush_cache_vmap(start, end)		do { } while (0)
+#define flush_cache_vunmap(start, end)		do { } while (0)
+
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE	1
+static inline void flush_dcache_page(struct page *page)
+{
+	/* FIXME: We can do better than this. All we are trying to do is
+	 * make the i-cache coherent, we should use the PG_arch_1 bit like
+	 * e.g. powerpc.
+	 */
+#ifdef CONFIG_SMP
+	metag_out32(1, SYSC_ICACHE_FLUSH);
+#else
+	metag_code_cache_flush_all((void *) PAGE_OFFSET);
+#endif
+}
+
+#endif
+
+/* Push n pages at kernel virtual address and clear the icache */
+static inline void flush_icache_range(unsigned long address,
+				      unsigned long endaddr)
+{
+#ifdef CONFIG_SMP
+	metag_out32(1, SYSC_ICACHE_FLUSH);
+#else
+	metag_code_cache_flush((void *) address, endaddr - address);
+#endif
+}
+
+static inline void flush_cache_sigtramp(unsigned long addr, int size)
+{
+	/*
+	 * Flush the icache in case there was previously some code
+	 * fetched from this address, perhaps a previous sigtramp.
+	 *
+	 * We don't need to flush the dcache, it's write through and
+	 * we just wrote the sigtramp code through it.
+	 */
+#ifdef CONFIG_SMP
+	metag_out32(1, SYSC_ICACHE_FLUSH);
+#else
+	metag_code_cache_flush((void *) addr, size);
+#endif
+}
+
+#ifdef CONFIG_METAG_L2C
+
+/*
+ * Perform a single specific CACHEWD operation on an address, masking lower bits
+ * of address first.
+ */
+static inline void cachewd_line(void *addr, unsigned int data)
+{
+	unsigned long masked = (unsigned long)addr & -0x40;
+	__builtin_meta2_cachewd((void *)masked, data);
+}
+
+/* Perform a certain CACHEW op on each cache line in a range */
+static inline void cachew_region_op(void *start, unsigned long size,
+				    unsigned int op)
+{
+	unsigned long offset = (unsigned long)start & 0x3f;
+	int i;
+	if (offset) {
+		size += offset;
+		start -= offset;
+	}
+	i = (size - 1) >> 6;
+	do {
+		__builtin_meta2_cachewd(start, op);
+		start += 0x40;
+	} while (i--);
+}
+
+/* prevent write fence and flushbacks being reordered in L2 */
+static inline void l2c_fence_flush(void *addr)
+{
+	/*
+	 * Synchronise by reading back and re-flushing.
+	 * It is assumed this access will miss, as the caller should have just
+	 * flushed the cache line.
+	 */
+	(void)(volatile u8 *)addr;
+	cachewd_line(addr, CACHEW_FLUSH_L1D_L2);
+}
+
+/* prevent write fence and writebacks being reordered in L2 */
+static inline void l2c_fence(void *addr)
+{
+	/*
+	 * A write back has occurred, but not necessarily an invalidate, so the
+	 * readback in l2c_fence_flush() would hit in the cache and have no
+	 * effect. Therefore fully flush the line first.
+	 */
+	cachewd_line(addr, CACHEW_FLUSH_L1D_L2);
+	l2c_fence_flush(addr);
+}
+
+/* Used to keep memory consistent when doing DMA. */
+static inline void flush_dcache_region(void *start, unsigned long size)
+{
+	/* metag_data_cache_flush won't flush L2 cache lines if size >= 4096 */
+	if (meta_l2c_is_enabled()) {
+		cachew_region_op(start, size, CACHEW_FLUSH_L1D_L2);
+		if (meta_l2c_is_writeback())
+			l2c_fence_flush(start + size - 1);
+	} else {
+		metag_data_cache_flush(start, size);
+	}
+}
+
+/* Write back dirty lines to memory (or do nothing if no writeback caches) */
+static inline void writeback_dcache_region(void *start, unsigned long size)
+{
+	if (meta_l2c_is_enabled() && meta_l2c_is_writeback()) {
+		cachew_region_op(start, size, CACHEW_WRITEBACK_L1D_L2);
+		l2c_fence(start + size - 1);
+	}
+}
+
+/* Invalidate (may also write back if necessary) */
+static inline void invalidate_dcache_region(void *start, unsigned long size)
+{
+	if (meta_l2c_is_enabled())
+		cachew_region_op(start, size, CACHEW_INVALIDATE_L1D_L2);
+	else
+		metag_data_cache_flush(start, size);
+}
+#else
+#define flush_dcache_region(s, l)	metag_data_cache_flush((s), (l))
+#define writeback_dcache_region(s, l)	do {} while (0)
+#define invalidate_dcache_region(s, l)	flush_dcache_region((s), (l))
+#endif
+
+static inline void copy_to_user_page(struct vm_area_struct *vma,
+				     struct page *page, unsigned long vaddr,
+				     void *dst, const void *src,
+				     unsigned long len)
+{
+	memcpy(dst, src, len);
+	flush_icache_range((unsigned long)dst, (unsigned long)dst + len);
+}
+
+static inline void copy_from_user_page(struct vm_area_struct *vma,
+				       struct page *page, unsigned long vaddr,
+				       void *dst, const void *src,
+				       unsigned long len)
+{
+	memcpy(dst, src, len);
+}
+
+#endif /* _METAG_CACHEFLUSH_H */

arch/metag/include/asm/cachepart.h

@@ -0,0 +1,42 @@
+/*
+ * Meta cache partition manipulation.
+ *
+ * Copyright 2010 Imagination Technologies Ltd.
+ */
+
+#ifndef _METAG_CACHEPART_H_
+#define _METAG_CACHEPART_H_
+
+/**
+ * get_dcache_size() - Get size of data cache.
+ */
+unsigned int get_dcache_size(void);
+
+/**
+ * get_icache_size() - Get size of code cache.
+ */
+unsigned int get_icache_size(void);
+
+/**
+ * get_global_dcache_size() - Get the thread's global dcache.
+ *
+ * Returns the size of the current thread's global dcache partition.
+ */
+unsigned int get_global_dcache_size(void);
+
+/**
+ * get_global_icache_size() - Get the thread's global icache.
+ *
+ * Returns the size of the current thread's global icache partition.
+ */
+unsigned int get_global_icache_size(void);
+
+/**
+ * check_for_dache_aliasing() - Ensure that the bootloader has configured the
+ * dache and icache properly to avoid aliasing
+ * @thread_id: Hardware thread ID
+ *
+ */
+void check_for_cache_aliasing(int thread_id);
+
+#endif

arch/metag/include/asm/checksum.h

@@ -0,0 +1,92 @@
+#ifndef _METAG_CHECKSUM_H
+#define _METAG_CHECKSUM_H
+
+/*
+ * computes the checksum of a memory block at buff, length len,
+ * and adds in "sum" (32-bit)
+ *
+ * returns a 32-bit number suitable for feeding into itself
+ * or csum_tcpudp_magic
+ *
+ * this function must be called with even lengths, except
+ * for the last fragment, which may be odd
+ *
+ * it's best to have buff aligned on a 32-bit boundary
+ */
+extern __wsum csum_partial(const void *buff, int len, __wsum sum);
+
+/*
+ * the same as csum_partial, but copies from src while it
+ * checksums
+ *
+ * here even more important to align src and dst on a 32-bit (or even
+ * better 64-bit) boundary
+ */
+extern __wsum csum_partial_copy(const void *src, void *dst, int len,
+				__wsum sum);
+
+/*
+ * the same as csum_partial_copy, but copies from user space.
+ *
+ * here even more important to align src and dst on a 32-bit (or even
+ * better 64-bit) boundary
+ */
+extern __wsum csum_partial_copy_from_user(const void __user *src, void *dst,
+					int len, __wsum sum, int *csum_err);
+
+#define csum_partial_copy_nocheck(src, dst, len, sum)	\
+	csum_partial_copy((src), (dst), (len), (sum))
+
+/*
+ * Fold a partial checksum
+ */
+static inline __sum16 csum_fold(__wsum csum)
+{
+	u32 sum = (__force u32)csum;
+	sum = (sum & 0xffff) + (sum >> 16);
+	sum = (sum & 0xffff) + (sum >> 16);
+	return (__force __sum16)~sum;
+}
+
+/*
+ * This is a version of ip_compute_csum() optimized for IP headers,
+ * which always checksum on 4 octet boundaries.
+ */
+extern __sum16 ip_fast_csum(const void *iph, unsigned int ihl);
+
+/*
+ * computes the checksum of the TCP/UDP pseudo-header
+ * returns a 16-bit checksum, already complemented
+ */
+static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
+					unsigned short len,
+					unsigned short proto,
+					__wsum sum)
+{
+	unsigned long len_proto = (proto + len) << 8;
+	asm ("ADD    %0, %0, %1\n"
+	     "ADDS   %0, %0, %2\n"
+	     "ADDCS  %0, %0, #1\n"
+	     "ADDS   %0, %0, %3\n"
+	     "ADDCS  %0, %0, #1\n"
+	     : "=d" (sum)
+	     : "d" (daddr), "d" (saddr), "d" (len_proto),
+	       "0" (sum)
+	     : "cc");
+	return sum;
+}
+
+static inline __sum16
+csum_tcpudp_magic(__be32 saddr, __be32 daddr, unsigned short len,
+		  unsigned short proto, __wsum sum)
+{
+	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
+}
+
+/*
+ * this routine is used for miscellaneous IP-like checksums, mainly
+ * in icmp.c
+ */
+extern __sum16 ip_compute_csum(const void *buff, int len);
+
+#endif /* _METAG_CHECKSUM_H */

arch/metag/include/asm/clock.h

@@ -0,0 +1,51 @@
+/*
+ * arch/metag/include/asm/clock.h
+ *
+ * Copyright (C) 2012 Imagination Technologies Ltd.
+ *
+ * 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 _METAG_CLOCK_H_
+#define _METAG_CLOCK_H_
+
+#include <asm/mach/arch.h>
+
+/**
+ * struct meta_clock_desc - Meta Core clock callbacks.
+ * @get_core_freq:	Get the frequency of the Meta core. If this is NULL, the
+ *			core frequency will be determined like this:
+ *			Meta 1: based on loops_per_jiffy.
+ *			Meta 2: (EXPAND_TIMER_DIV + 1) MHz.
+ */
+struct meta_clock_desc {
+	unsigned long		(*get_core_freq)(void);
+};
+
+extern struct meta_clock_desc _meta_clock;
+
+/*
+ * Set up the default clock, ensuring all callbacks are valid - only accessible
+ * during boot.
+ */
+void setup_meta_clocks(struct meta_clock_desc *desc);
+
+/**
+ * get_coreclock() - Get the frequency of the Meta core clock.
+ *
+ * Returns:	The Meta core clock frequency in Hz.
+ */
+static inline unsigned long get_coreclock(void)
+{
+	/*
+	 * Use the current clock callback. If set correctly this will provide
+	 * the most accurate frequency as it can be calculated directly from the
+	 * PLL configuration. otherwise a default callback will have been set
+	 * instead.
+	 */
+	return _meta_clock.get_core_freq();
+}
+
+#endif /* _METAG_CLOCK_H_ */

arch/metag/include/asm/cmpxchg.h

@@ -0,0 +1,65 @@
+#ifndef __ASM_METAG_CMPXCHG_H
+#define __ASM_METAG_CMPXCHG_H
+
+#include <asm/barrier.h>
+
+#if defined(CONFIG_METAG_ATOMICITY_IRQSOFF)
+#include <asm/cmpxchg_irq.h>
+#elif defined(CONFIG_METAG_ATOMICITY_LOCK1)
+#include <asm/cmpxchg_lock1.h>
+#elif defined(CONFIG_METAG_ATOMICITY_LNKGET)
+#include <asm/cmpxchg_lnkget.h>
+#endif
+
+extern void __xchg_called_with_bad_pointer(void);
+
+#define __xchg(ptr, x, size)				\
+({							\
+	unsigned long __xchg__res;			\
+	volatile void *__xchg_ptr = (ptr);		\
+	switch (size) {					\
+	case 4:						\
+		__xchg__res = xchg_u32(__xchg_ptr, x);	\
+		break;					\
+	case 1:						\
+		__xchg__res = xchg_u8(__xchg_ptr, x);	\
+		break;					\
+	default:					\
+		__xchg_called_with_bad_pointer();	\
+		__xchg__res = x;			\
+		break;					\
+	}						\
+							\
+	__xchg__res;					\
+})
+
+#define xchg(ptr, x)	\
+	((__typeof__(*(ptr)))__xchg((ptr), (unsigned long)(x), sizeof(*(ptr))))
+
+/* This function doesn't exist, so you'll get a linker error
+ * if something tries to do an invalid cmpxchg(). */
+extern void __cmpxchg_called_with_bad_pointer(void);
+
+static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
+				      unsigned long new, int size)
+{
+	switch (size) {
+	case 4:
+		return __cmpxchg_u32(ptr, old, new);
+	}
+	__cmpxchg_called_with_bad_pointer();
+	return old;
+}
+
+#define __HAVE_ARCH_CMPXCHG 1
+
+#define cmpxchg(ptr, o, n)						\
+	({								\
+		__typeof__(*(ptr)) _o_ = (o);				\
+		__typeof__(*(ptr)) _n_ = (n);				\
+		(__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_, \
+					       (unsigned long)_n_,	\
+					       sizeof(*(ptr)));		\
+	})
+
+#endif /* __ASM_METAG_CMPXCHG_H */

arch/metag/include/asm/cmpxchg_irq.h

@@ -0,0 +1,42 @@
+#ifndef __ASM_METAG_CMPXCHG_IRQ_H
+#define __ASM_METAG_CMPXCHG_IRQ_H
+
+#include <linux/irqflags.h>
+
+static inline unsigned long xchg_u32(volatile u32 *m, unsigned long val)
+{
+	unsigned long flags, retval;
+
+	local_irq_save(flags);
+	retval = *m;
+	*m = val;
+	local_irq_restore(flags);
+	return retval;
+}
+
+static inline unsigned long xchg_u8(volatile u8 *m, unsigned long val)
+{
+	unsigned long flags, retval;
+
+	local_irq_save(flags);
+	retval = *m;
+	*m = val & 0xff;
+	local_irq_restore(flags);
+	return retval;
+}
+
+static inline unsigned long __cmpxchg_u32(volatile int *m, unsigned long old,
+					  unsigned long new)
+{
+	__u32 retval;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	retval = *m;
+	if (retval == old)
+		*m = new;
+	local_irq_restore(flags);       /* implies memory barrier  */
+	return retval;
+}
+
+#endif /* __ASM_METAG_CMPXCHG_IRQ_H */

arch/metag/include/asm/cmpxchg_lnkget.h

@@ -0,0 +1,86 @@
+#ifndef __ASM_METAG_CMPXCHG_LNKGET_H
+#define __ASM_METAG_CMPXCHG_LNKGET_H
+
+static inline unsigned long xchg_u32(volatile u32 *m, unsigned long val)
+{
+	int temp, old;
+
+	smp_mb();
+
+	asm volatile (
+		      "1:	LNKGETD %1, [%2]\n"
+		      "	LNKSETD	[%2], %3\n"
+		      "	DEFR	%0, TXSTAT\n"
+		      "	ANDT	%0, %0, #HI(0x3f000000)\n"
+		      "	CMPT	%0, #HI(0x02000000)\n"
+		      "	BNZ	1b\n"
+#ifdef CONFIG_METAG_LNKGET_AROUND_CACHE
+		      "	DCACHE	[%2], %0\n"
+#endif
+		      : "=&d" (temp), "=&d" (old)
+		      : "da" (m), "da" (val)
+		      : "cc"
+		      );
+
+	smp_mb();
+
+	return old;
+}
+
+static inline unsigned long xchg_u8(volatile u8 *m, unsigned long val)
+{
+	int temp, old;
+
+	smp_mb();
+
+	asm volatile (
+		      "1:	LNKGETD %1, [%2]\n"
+		      "	LNKSETD	[%2], %3\n"
+		      "	DEFR	%0, TXSTAT\n"
+		      "	ANDT	%0, %0, #HI(0x3f000000)\n"
+		      "	CMPT	%0, #HI(0x02000000)\n"
+		      "	BNZ	1b\n"
+#ifdef CONFIG_METAG_LNKGET_AROUND_CACHE
+		      "	DCACHE	[%2], %0\n"
+#endif
+		      : "=&d" (temp), "=&d" (old)
+		      : "da" (m), "da" (val & 0xff)
+		      : "cc"
+		      );
+
+	smp_mb();
+
+	return old;
+}
+
+static inline unsigned long __cmpxchg_u32(volatile int *m, unsigned long old,
+					  unsigned long new)
+{
+	__u32 retval, temp;
+
+	smp_mb();
+
+	asm volatile (
+		      "1:	LNKGETD	%1, [%2]\n"
+		      "	CMP	%1, %3\n"
+		      "	LNKSETDEQ [%2], %4\n"
+		      "	BNE	2f\n"
+		      "	DEFR	%0, TXSTAT\n"
+		      "	ANDT	%0, %0, #HI(0x3f000000)\n"
+		      "	CMPT	%0, #HI(0x02000000)\n"
+		      "	BNZ	1b\n"
+#ifdef CONFIG_METAG_LNKGET_AROUND_CACHE
+		      "	DCACHE	[%2], %0\n"
+#endif
+		      "2:\n"
+		      : "=&d" (temp), "=&da" (retval)
+		      : "da" (m), "bd" (old), "da" (new)
+		      : "cc"
+		      );
+
+	smp_mb();
+
+	return retval;
+}
+
+#endif /* __ASM_METAG_CMPXCHG_LNKGET_H */

arch/metag/include/asm/cmpxchg_lock1.h

@@ -0,0 +1,48 @@
+#ifndef __ASM_METAG_CMPXCHG_LOCK1_H
+#define __ASM_METAG_CMPXCHG_LOCK1_H
+
+#include <asm/global_lock.h>
+
+/* Use LOCK2 as these have to be atomic w.r.t. ordinary accesses. */
+
+static inline unsigned long xchg_u32(volatile u32 *m, unsigned long val)
+{
+	unsigned long flags, retval;
+
+	__global_lock2(flags);
+	fence();
+	retval = *m;
+	*m = val;
+	__global_unlock2(flags);
+	return retval;
+}
+
+static inline unsigned long xchg_u8(volatile u8 *m, unsigned long val)
+{
+	unsigned long flags, retval;
+
+	__global_lock2(flags);
+	fence();
+	retval = *m;
+	*m = val & 0xff;
+	__global_unlock2(flags);
+	return retval;
+}
+
+static inline unsigned long __cmpxchg_u32(volatile int *m, unsigned long old,
+					  unsigned long new)
+{
+	__u32 retval;
+	unsigned long flags;
+
+	__global_lock2(flags);
+	retval = *m;
+	if (retval == old) {
+		fence();
+		*m = new;
+	}
+	__global_unlock2(flags);
+	return retval;
+}
+
+#endif /* __ASM_METAG_CMPXCHG_LOCK1_H */

arch/metag/include/asm/core_reg.h

@@ -0,0 +1,35 @@
+#ifndef __ASM_METAG_CORE_REG_H_
+#define __ASM_METAG_CORE_REG_H_
+
+#include <asm/metag_regs.h>
+
+extern void core_reg_write(int unit, int reg, int thread, unsigned int val);
+extern unsigned int core_reg_read(int unit, int reg, int thread);
+
+/*
+ * These macros allow direct access from C to any register known to the
+ * assembler. Example candidates are TXTACTCYC, TXIDLECYC, and TXPRIVEXT.
+ */
+
+#define __core_reg_get(reg) ({						\
+	unsigned int __grvalue;						\
+	asm volatile("MOV	%0," #reg				\
+		     : "=r" (__grvalue));				\
+	__grvalue;							\
+})
+
+#define __core_reg_set(reg, value) do {					\
+	unsigned int __srvalue = (value);				\
+	asm volatile("MOV	" #reg ",%0"				\
+		     :							\
+		     : "r" (__srvalue));				\
+} while (0)
+
+#define __core_reg_swap(reg, value) do {				\
+	unsigned int __srvalue = (value);				\
+	asm volatile("SWAP	" #reg ",%0"				\
+		     : "+r" (__srvalue));				\
+	(value) = __srvalue;						\
+} while (0)
+
+#endif

arch/metag/include/asm/cpu.h

@@ -0,0 +1,14 @@
+#ifndef _ASM_METAG_CPU_H
+#define _ASM_METAG_CPU_H
+
+#include <linux/percpu.h>
+
+struct cpuinfo_metag {
+	struct cpu cpu;
+#ifdef CONFIG_SMP
+	unsigned long loops_per_jiffy;
+#endif
+};
+
+DECLARE_PER_CPU(struct cpuinfo_metag, cpu_data);
+#endif /* _ASM_METAG_CPU_H */

arch/metag/include/asm/da.h

@@ -0,0 +1,43 @@
+/*
+ * Meta DA JTAG debugger control.
+ *
+ * Copyright 2012 Imagination Technologies Ltd.
+ */
+
+#ifndef _METAG_DA_H_
+#define _METAG_DA_H_
+
+#ifdef CONFIG_METAG_DA
+
+#include <linux/init.h>
+#include <linux/types.h>
+
+extern bool _metag_da_present;
+
+/**
+ * metag_da_enabled() - Find whether a DA is currently enabled.
+ *
+ * Returns:	true if a DA was detected, false if not.
+ */
+static inline bool metag_da_enabled(void)
+{
+	return _metag_da_present;
+}
+
+/**
+ * metag_da_probe() - Try and detect a connected DA.
+ *
+ * This is used at start up to detect whether a DA is active.
+ *
+ * Returns:	0 on detection, -err otherwise.
+ */
+int __init metag_da_probe(void);
+
+#else /* !CONFIG_METAG_DA */
+
+#define metag_da_enabled() false
+#define metag_da_probe() do {} while (0)
+
+#endif
+
+#endif /* _METAG_DA_H_ */

arch/metag/include/asm/delay.h

@@ -0,0 +1,29 @@
+#ifndef _METAG_DELAY_H
+#define _METAG_DELAY_H
+
+/*
+ * Copyright (C) 1993 Linus Torvalds
+ *
+ * Delay routines calling functions in arch/metag/lib/delay.c
+ */
+
+/* Undefined functions to get compile-time errors */
+extern void __bad_udelay(void);
+extern void __bad_ndelay(void);
+
+extern void __udelay(unsigned long usecs);
+extern void __ndelay(unsigned long nsecs);
+extern void __const_udelay(unsigned long xloops);
+extern void __delay(unsigned long loops);
+
+/* 0x10c7 is 2**32 / 1000000 (rounded up) */
+#define udelay(n) (__builtin_constant_p(n) ? \
+	((n) > 20000 ? __bad_udelay() : __const_udelay((n) * 0x10c7ul)) : \
+	__udelay(n))
+
+/* 0x5 is 2**32 / 1000000000 (rounded up) */
+#define ndelay(n) (__builtin_constant_p(n) ? \
+	((n) > 20000 ? __bad_ndelay() : __const_udelay((n) * 5ul)) : \
+	__ndelay(n))
+
+#endif /* _METAG_DELAY_H */

arch/metag/include/asm/div64.h

@@ -0,0 +1,12 @@
+#ifndef __ASM_DIV64_H__
+#define __ASM_DIV64_H__
+
+#include <asm-generic/div64.h>
+
+extern u64 div_u64(u64 dividend, u64 divisor);
+extern s64 div_s64(s64 dividend, s64 divisor);
+
+#define div_u64 div_u64
+#define div_s64 div_s64
+
+#endif

arch/metag/include/asm/dma-mapping.h

@@ -0,0 +1,190 @@
+#ifndef _ASM_METAG_DMA_MAPPING_H
+#define _ASM_METAG_DMA_MAPPING_H
+
+#include <linux/mm.h>
+
+#include <asm/cache.h>
+#include <asm/io.h>
+#include <linux/scatterlist.h>
+#include <asm/bug.h>
+
+#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
+#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
+
+void *dma_alloc_coherent(struct device *dev, size_t size,
+			 dma_addr_t *dma_handle, gfp_t flag);
+
+void dma_free_coherent(struct device *dev, size_t size,
+		       void *vaddr, dma_addr_t dma_handle);
+
+void dma_sync_for_device(void *vaddr, size_t size, int dma_direction);
+void dma_sync_for_cpu(void *vaddr, size_t size, int dma_direction);
+
+int dma_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
+		      void *cpu_addr, dma_addr_t dma_addr, size_t size);
+
+int dma_mmap_writecombine(struct device *dev, struct vm_area_struct *vma,
+			  void *cpu_addr, dma_addr_t dma_addr, size_t size);
+
+static inline dma_addr_t
+dma_map_single(struct device *dev, void *ptr, size_t size,
+	       enum dma_data_direction direction)
+{
+	BUG_ON(!valid_dma_direction(direction));
+	WARN_ON(size == 0);
+	dma_sync_for_device(ptr, size, direction);
+	return virt_to_phys(ptr);
+}
+
+static inline void
+dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
+		 enum dma_data_direction direction)
+{
+	BUG_ON(!valid_dma_direction(direction));
+	dma_sync_for_cpu(phys_to_virt(dma_addr), size, direction);
+}
+
+static inline int
+dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
+	   enum dma_data_direction direction)
+{
+	struct scatterlist *sg;
+	int i;
+
+	BUG_ON(!valid_dma_direction(direction));
+	WARN_ON(nents == 0 || sglist[0].length == 0);
+
+	for_each_sg(sglist, sg, nents, i) {
+		BUG_ON(!sg_page(sg));
+
+		sg->dma_address = sg_phys(sg);
+		dma_sync_for_device(sg_virt(sg), sg->length, direction);
+	}
+
+	return nents;
+}
+
+static inline dma_addr_t
+dma_map_page(struct device *dev, struct page *page, unsigned long offset,
+	     size_t size, enum dma_data_direction direction)
+{
+	BUG_ON(!valid_dma_direction(direction));
+	dma_sync_for_device((void *)(page_to_phys(page) + offset), size,
+			    direction);
+	return page_to_phys(page) + offset;
+}
+
+static inline void
+dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
+	       enum dma_data_direction direction)
+{
+	BUG_ON(!valid_dma_direction(direction));
+	dma_sync_for_cpu(phys_to_virt(dma_address), size, direction);
+}
+
+
+static inline void
+dma_unmap_sg(struct device *dev, struct scatterlist *sglist, int nhwentries,
+	     enum dma_data_direction direction)
+{
+	struct scatterlist *sg;
+	int i;
+
+	BUG_ON(!valid_dma_direction(direction));
+	WARN_ON(nhwentries == 0 || sglist[0].length == 0);
+
+	for_each_sg(sglist, sg, nhwentries, i) {
+		BUG_ON(!sg_page(sg));
+
+		sg->dma_address = sg_phys(sg);
+		dma_sync_for_cpu(sg_virt(sg), sg->length, direction);
+	}
+}
+
+static inline void
+dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size,
+			enum dma_data_direction direction)
+{
+	dma_sync_for_cpu(phys_to_virt(dma_handle), size, direction);
+}
+
+static inline void
+dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle,
+			   size_t size, enum dma_data_direction direction)
+{
+	dma_sync_for_device(phys_to_virt(dma_handle), size, direction);
+}
+
+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_sync_for_cpu(phys_to_virt(dma_handle)+offset, size,
+			 direction);
+}
+
+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_sync_for_device(phys_to_virt(dma_handle)+offset, size,
+			    direction);
+}
+
+static inline void
+dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems,
+		    enum dma_data_direction direction)
+{
+	int i;
+	for (i = 0; i < nelems; i++, sg++)
+		dma_sync_for_cpu(sg_virt(sg), sg->length, direction);
+}
+
+static inline void
+dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems,
+		       enum dma_data_direction direction)
+{
+	int i;
+	for (i = 0; i < nelems; i++, sg++)
+		dma_sync_for_device(sg_virt(sg), sg->length, direction);
+}
+
+static inline int
+dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return 0;
+}
+
+#define dma_supported(dev, mask)        (1)
+
+static inline int
+dma_set_mask(struct device *dev, u64 mask)
+{
+	if (!dev->dma_mask || !dma_supported(dev, mask))
+		return -EIO;
+
+	*dev->dma_mask = mask;
+
+	return 0;
+}
+
+/*
+ * dma_alloc_noncoherent() returns non-cacheable memory, so there's no need to
+ * do any flushing here.
+ */
+static inline void
+dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+	       enum dma_data_direction direction)
+{
+}
+
+/* drivers/base/dma-mapping.c */
+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_get_sgtable(d, t, v, h, s) dma_common_get_sgtable(d, t, v, h, s)
+
+#endif

arch/metag/include/asm/elf.h

@@ -0,0 +1,128 @@
+#ifndef __ASM_METAG_ELF_H
+#define __ASM_METAG_ELF_H
+
+#define EM_METAG      174
+
+/* Meta relocations */
+#define R_METAG_HIADDR16                 0
+#define R_METAG_LOADDR16                 1
+#define R_METAG_ADDR32                   2
+#define R_METAG_NONE                     3
+#define R_METAG_RELBRANCH                4
+#define R_METAG_GETSETOFF                5
+
+/* Backward compatability */
+#define R_METAG_REG32OP1                 6
+#define R_METAG_REG32OP2                 7
+#define R_METAG_REG32OP3                 8
+#define R_METAG_REG16OP1                 9
+#define R_METAG_REG16OP2                10
+#define R_METAG_REG16OP3                11
+#define R_METAG_REG32OP4                12
+
+#define R_METAG_HIOG                    13
+#define R_METAG_LOOG                    14
+
+/* GNU */
+#define R_METAG_GNU_VTINHERIT           30
+#define R_METAG_GNU_VTENTRY             31
+
+/* PIC relocations */
+#define R_METAG_HI16_GOTOFF             32
+#define R_METAG_LO16_GOTOFF             33
+#define R_METAG_GETSET_GOTOFF           34
+#define R_METAG_GETSET_GOT              35
+#define R_METAG_HI16_GOTPC              36
+#define R_METAG_LO16_GOTPC              37
+#define R_METAG_HI16_PLT                38
+#define R_METAG_LO16_PLT                39
+#define R_METAG_RELBRANCH_PLT           40
+#define R_METAG_GOTOFF                  41
+#define R_METAG_PLT                     42
+#define R_METAG_COPY                    43
+#define R_METAG_JMP_SLOT                44
+#define R_METAG_RELATIVE                45
+#define R_METAG_GLOB_DAT                46
+
+/*
+ * ELF register definitions.
+ */
+
+#include <asm/page.h>
+#include <asm/processor.h>
+#include <asm/ptrace.h>
+#include <asm/user.h>
+
+typedef unsigned long elf_greg_t;
+
+#define ELF_NGREG (sizeof(struct user_gp_regs) / sizeof(elf_greg_t))
+typedef elf_greg_t elf_gregset_t[ELF_NGREG];
+
+typedef unsigned long elf_fpregset_t;
+
+/*
+ * This is used to ensure we don't load something for the wrong architecture.
+ */
+#define elf_check_arch(x) ((x)->e_machine == EM_METAG)
+
+/*
+ * These are used to set parameters in the core dumps.
+ */
+#define ELF_CLASS	ELFCLASS32
+#define ELF_DATA	ELFDATA2LSB
+#define ELF_ARCH	EM_METAG
+
+#define ELF_PLAT_INIT(_r, load_addr)	\
+	do { _r->ctx.AX[0].U0 = 0; } while (0)
+
+#define USE_ELF_CORE_DUMP
+#define CORE_DUMP_USE_REGSET
+#define ELF_EXEC_PAGESIZE	PAGE_SIZE
+
+/* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
+   use of this is to invoke "./ld.so someprog" to test out a new version of
+   the loader.  We need to make sure that it is out of the way of the program
+   that it will "exec", and that there is sufficient room for the brk.  */
+
+#define ELF_ET_DYN_BASE         0x08000000UL
+
+#define ELF_CORE_COPY_REGS(_dest, _regs)			\
+	memcpy((char *)&_dest, (char *)_regs, sizeof(struct pt_regs));
+
+/* This yields a mask that user programs can use to figure out what
+   instruction set this cpu supports.  */
+
+#define ELF_HWCAP	(0)
+
+/* This yields a string that ld.so will use to load implementation
+   specific libraries for optimization.  This is more specific in
+   intent than poking at uname or /proc/cpuinfo.  */
+
+#define ELF_PLATFORM  (NULL)
+
+#define SET_PERSONALITY(ex) \
+	set_personality(PER_LINUX | (current->personality & (~PER_MASK)))
+
+#define STACK_RND_MASK (0)
+
+#ifdef CONFIG_METAG_USER_TCM
+
+struct elf32_phdr;
+struct file;
+
+unsigned long __metag_elf_map(struct file *filep, unsigned long addr,
+			      struct elf32_phdr *eppnt, int prot, int type,
+			      unsigned long total_size);
+
+static inline unsigned long metag_elf_map(struct file *filep,
+					  unsigned long addr,
+					  struct elf32_phdr *eppnt, int prot,
+					  int type, unsigned long total_size)
+{
+	return __metag_elf_map(filep, addr, eppnt, prot, type, total_size);
+}
+#define elf_map metag_elf_map
+
+#endif
+
+#endif

arch/metag/include/asm/fixmap.h

@@ -0,0 +1,99 @@
+/*
+ * fixmap.h: compile-time virtual memory allocation
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1998 Ingo Molnar
+ *
+ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
+ */
+
+#ifndef _ASM_FIXMAP_H
+#define _ASM_FIXMAP_H
+
+#include <asm/pgtable.h>
+#ifdef CONFIG_HIGHMEM
+#include <linux/threads.h>
+#include <asm/kmap_types.h>
+#endif
+
+/*
+ * Here we define all the compile-time 'special' virtual
+ * addresses. The point is to have a constant address at
+ * compile time, but to set the physical address only
+ * in the boot process. We allocate these special  addresses
+ * from the end of the consistent memory region backwards.
+ * Also this lets us do fail-safe vmalloc(), we
+ * can guarantee that these special addresses and
+ * vmalloc()-ed addresses never overlap.
+ *
+ * these 'compile-time allocated' memory buffers are
+ * fixed-size 4k pages. (or larger if used with an increment
+ * higher than 1) use fixmap_set(idx,phys) to associate
+ * physical memory with fixmap indices.
+ *
+ * TLB entries of such buffers will not be flushed across
+ * task switches.
+ */
+enum fixed_addresses {
+#define FIX_N_COLOURS 8
+#ifdef CONFIG_HIGHMEM
+	/* reserved pte's for temporary kernel mappings */
+	FIX_KMAP_BEGIN,
+	FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
+#endif
+	__end_of_fixed_addresses
+};
+
+#define FIXADDR_TOP     (CONSISTENT_START - PAGE_SIZE)
+#define FIXADDR_SIZE	(__end_of_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_START	((FIXADDR_TOP - FIXADDR_SIZE) & PMD_MASK)
+
+#define __fix_to_virt(x)	(FIXADDR_TOP - ((x) << PAGE_SHIFT))
+#define __virt_to_fix(x)	((FIXADDR_TOP - ((x)&PAGE_MASK)) >> PAGE_SHIFT)
+
+extern void __this_fixmap_does_not_exist(void);
+/*
+ * 'index to address' translation. If anyone tries to use the idx
+ * directly without tranlation, we catch the bug with a NULL-deference
+ * kernel oops. Illegal ranges of incoming indices are caught too.
+ */
+static inline unsigned long fix_to_virt(const unsigned int idx)
+{
+	/*
+	 * this branch gets completely eliminated after inlining,
+	 * except when someone tries to use fixaddr indices in an
+	 * illegal way. (such as mixing up address types or using
+	 * out-of-range indices).
+	 *
+	 * If it doesn't get removed, the linker will complain
+	 * loudly with a reasonably clear error message..
+	 */
+	if (idx >= __end_of_fixed_addresses)
+		__this_fixmap_does_not_exist();
+
+	return __fix_to_virt(idx);
+}
+
+static inline unsigned long virt_to_fix(const unsigned long vaddr)
+{
+	BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START);
+	return __virt_to_fix(vaddr);
+}
+
+#define kmap_get_fixmap_pte(vaddr) \
+	pte_offset_kernel( \
+		pmd_offset(pud_offset(pgd_offset_k(vaddr), (vaddr)), (vaddr)), \
+		(vaddr) \
+	)
+
+/*
+ * Called from pgtable_init()
+ */
+extern void fixrange_init(unsigned long start, unsigned long end,
+	pgd_t *pgd_base);
+
+
+#endif

arch/metag/include/asm/ftrace.h

@@ -0,0 +1,23 @@
+#ifndef _ASM_METAG_FTRACE
+#define _ASM_METAG_FTRACE
+
+#ifdef CONFIG_FUNCTION_TRACER
+#define MCOUNT_INSN_SIZE	8 /* sizeof mcount call */
+
+#ifndef __ASSEMBLY__
+extern void mcount_wrapper(void);
+#define MCOUNT_ADDR		((long)(mcount_wrapper))
+
+static inline unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	return addr;
+}
+
+struct dyn_arch_ftrace {
+	/* No extra data needed on metag */
+};
+#endif /* __ASSEMBLY__ */
+
+#endif /* CONFIG_FUNCTION_TRACER */
+
+#endif /* _ASM_METAG_FTRACE */

arch/metag/include/asm/global_lock.h

@@ -0,0 +1,100 @@
+#ifndef __ASM_METAG_GLOBAL_LOCK_H
+#define __ASM_METAG_GLOBAL_LOCK_H
+
+#include <asm/metag_mem.h>
+
+/**
+ * __global_lock1() - Acquire global voluntary lock (LOCK1).
+ * @flags:	Variable to store flags into.
+ *
+ * Acquires the Meta global voluntary lock (LOCK1), also taking care to disable
+ * all triggers so we cannot be interrupted, and to enforce a compiler barrier
+ * so that the compiler cannot reorder memory accesses across the lock.
+ *
+ * No other hardware thread will be able to acquire the voluntary or exclusive
+ * locks until the voluntary lock is released with @__global_unlock1, but they
+ * may continue to execute as long as they aren't trying to acquire either of
+ * the locks.
+ */
+#define __global_lock1(flags) do {					\
+	unsigned int __trval;						\
+	asm volatile("MOV	%0,#0\n\t"				\
+		     "SWAP	%0,TXMASKI\n\t"				\
+		     "LOCK1"						\
+		     : "=r" (__trval)					\
+		     :							\
+		     : "memory");					\
+	(flags) = __trval;						\
+} while (0)
+
+/**
+ * __global_unlock1() - Release global voluntary lock (LOCK1).
+ * @flags:	Variable to restore flags from.
+ *
+ * Releases the Meta global voluntary lock (LOCK1) acquired with
+ * @__global_lock1, also taking care to re-enable triggers, and to enforce a
+ * compiler barrier so that the compiler cannot reorder memory accesses across
+ * the unlock.
+ *
+ * This immediately allows another hardware thread to acquire the voluntary or
+ * exclusive locks.
+ */
+#define __global_unlock1(flags) do {					\
+	unsigned int __trval = (flags);					\
+	asm volatile("LOCK0\n\t"					\
+		     "MOV	TXMASKI,%0"				\
+		     :							\
+		     : "r" (__trval)					\
+		     : "memory");					\
+} while (0)
+
+/**
+ * __global_lock2() - Acquire global exclusive lock (LOCK2).
+ * @flags:	Variable to store flags into.
+ *
+ * Acquires the Meta global voluntary lock and global exclusive lock (LOCK2),
+ * also taking care to disable all triggers so we cannot be interrupted, to take
+ * the atomic lock (system event) and to enforce a compiler barrier so that the
+ * compiler cannot reorder memory accesses across the lock.
+ *
+ * No other hardware thread will be able to execute code until the locks are
+ * released with @__global_unlock2.
+ */
+#define __global_lock2(flags) do {					\
+	unsigned int __trval;						\
+	unsigned int __aloc_hi = LINSYSEVENT_WR_ATOMIC_LOCK & 0xFFFF0000; \
+	asm volatile("MOV	%0,#0\n\t"				\
+		     "SWAP	%0,TXMASKI\n\t"				\
+		     "LOCK2\n\t"					\
+		     "SETD	[%1+#0x40],D1RtP"			\
+		     : "=r&" (__trval)					\
+		     : "u" (__aloc_hi)					\
+		     : "memory");					\
+	(flags) = __trval;						\
+} while (0)
+
+/**
+ * __global_unlock2() - Release global exclusive lock (LOCK2).
+ * @flags:	Variable to restore flags from.
+ *
+ * Releases the Meta global exclusive lock (LOCK2) and global voluntary lock
+ * acquired with @__global_lock2, also taking care to release the atomic lock
+ * (system event), re-enable triggers, and to enforce a compiler barrier so that
+ * the compiler cannot reorder memory accesses across the unlock.
+ *
+ * This immediately allows other hardware threads to continue executing and one
+ * of them to acquire locks.
+ */
+#define __global_unlock2(flags) do {					\
+	unsigned int __trval = (flags);					\
+	unsigned int __alock_hi = LINSYSEVENT_WR_ATOMIC_LOCK & 0xFFFF0000; \
+	asm volatile("SETD	[%1+#0x00],D1RtP\n\t"			\
+		     "LOCK0\n\t"					\
+		     "MOV	TXMASKI,%0"				\
+		     :							\
+		     : "r" (__trval),					\
+		       "u" (__alock_hi)					\
+		     : "memory");					\
+} while (0)
+
+#endif /* __ASM_METAG_GLOBAL_LOCK_H */

arch/metag/include/asm/gpio.h

@@ -0,0 +1,4 @@
+#ifndef __LINUX_GPIO_H
+#warning Include linux/gpio.h instead of asm/gpio.h
+#include <linux/gpio.h>
+#endif

arch/metag/include/asm/highmem.h

@@ -0,0 +1,62 @@
+#ifndef _ASM_HIGHMEM_H
+#define _ASM_HIGHMEM_H
+
+#include <asm/cacheflush.h>
+#include <asm/kmap_types.h>
+#include <asm/fixmap.h>
+
+/*
+ * Right now we initialize only a single pte table. It can be extended
+ * easily, subsequent pte tables have to be allocated in one physical
+ * chunk of RAM.
+ */
+/*
+ * Ordering is (from lower to higher memory addresses):
+ *
+ * high_memory
+ *			Persistent kmap area
+ * PKMAP_BASE
+ *			fixed_addresses
+ * FIXADDR_START
+ * FIXADDR_TOP
+ *			Vmalloc area
+ * VMALLOC_START
+ * VMALLOC_END
+ */
+#define PKMAP_BASE		(FIXADDR_START - PMD_SIZE)
+#define LAST_PKMAP		PTRS_PER_PTE
+#define LAST_PKMAP_MASK		(LAST_PKMAP - 1)
+#define PKMAP_NR(virt)		(((virt) - PKMAP_BASE) >> PAGE_SHIFT)
+#define PKMAP_ADDR(nr)		(PKMAP_BASE + ((nr) << PAGE_SHIFT))
+
+#define kmap_prot		PAGE_KERNEL
+
+static inline void flush_cache_kmaps(void)
+{
+	flush_cache_all();
+}
+
+/* declarations for highmem.c */
+extern unsigned long highstart_pfn, highend_pfn;
+
+extern pte_t *pkmap_page_table;
+
+extern void *kmap_high(struct page *page);
+extern void kunmap_high(struct page *page);
+
+extern void kmap_init(void);
+
+/*
+ * The following functions are already defined by <linux/highmem.h>
+ * when CONFIG_HIGHMEM is not set.
+ */
+#ifdef CONFIG_HIGHMEM
+extern void *kmap(struct page *page);
+extern void kunmap(struct page *page);
+extern void *kmap_atomic(struct page *page);
+extern void __kunmap_atomic(void *kvaddr);
+extern void *kmap_atomic_pfn(unsigned long pfn);
+extern struct page *kmap_atomic_to_page(void *ptr);
+#endif
+
+#endif

arch/metag/include/asm/hugetlb.h

@@ -0,0 +1,86 @@
+#ifndef _ASM_METAG_HUGETLB_H
+#define _ASM_METAG_HUGETLB_H
+
+#include <asm/page.h>
+
+
+static inline int is_hugepage_only_range(struct mm_struct *mm,
+					 unsigned long addr,
+					 unsigned long len) {
+	return 0;
+}
+
+int prepare_hugepage_range(struct file *file, unsigned long addr,
+						unsigned long len);
+
+static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
+{
+}
+
+static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
+					  unsigned long addr, unsigned long end,
+					  unsigned long floor,
+					  unsigned long ceiling)
+{
+	free_pgd_range(tlb, addr, end, floor, ceiling);
+}
+
+static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+				   pte_t *ptep, pte_t pte)
+{
+	set_pte_at(mm, addr, ptep, pte);
+}
+
+static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+					    unsigned long addr, pte_t *ptep)
+{
+	return ptep_get_and_clear(mm, addr, ptep);
+}
+
+static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep)
+{
+}
+
+static inline int huge_pte_none(pte_t pte)
+{
+	return pte_none(pte);
+}
+
+static inline pte_t huge_pte_wrprotect(pte_t pte)
+{
+	return pte_wrprotect(pte);
+}
+
+static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
+					   unsigned long addr, pte_t *ptep)
+{
+	ptep_set_wrprotect(mm, addr, ptep);
+}
+
+static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+					     unsigned long addr, pte_t *ptep,
+					     pte_t pte, int dirty)
+{
+	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
+}
+
+static inline pte_t huge_ptep_get(pte_t *ptep)
+{
+	return *ptep;
+}
+
+static inline int arch_prepare_hugepage(struct page *page)
+{
+	return 0;
+}
+
+static inline void arch_release_hugepage(struct page *page)
+{
+}
+
+static inline void arch_clear_hugepage_flags(struct page *page)
+{
+}
+
+#endif /* _ASM_METAG_HUGETLB_H */

arch/metag/include/asm/hwthread.h

@@ -0,0 +1,40 @@
+/*
+ * Copyright (C) 2008 Imagination Technologies
+ */
+#ifndef __METAG_HWTHREAD_H
+#define __METAG_HWTHREAD_H
+
+#include <linux/bug.h>
+#include <linux/io.h>
+
+#include <asm/metag_mem.h>
+
+#define BAD_HWTHREAD_ID		(0xFFU)
+#define BAD_CPU_ID		(0xFFU)
+
+extern u8 cpu_2_hwthread_id[];
+extern u8 hwthread_id_2_cpu[];
+
+/*
+ * Each hardware thread's Control Unit registers are memory-mapped
+ * and can therefore be accessed by any other hardware thread.
+ *
+ * This helper function returns the memory address where "thread"'s
+ * register "regnum" is mapped.
+ */
+static inline
+void __iomem *__CU_addr(unsigned int thread, unsigned int regnum)
+{
+	unsigned int base, thread_offset, thread_regnum;
+
+	WARN_ON(thread == BAD_HWTHREAD_ID);
+
+	base = T0UCTREG0;	/* Control unit base */
+
+	thread_offset = TnUCTRX_STRIDE * thread;
+	thread_regnum = TXUCTREGn_STRIDE * regnum;
+
+	return (void __iomem *)(base + thread_offset + thread_regnum);
+}
+
+#endif /* __METAG_HWTHREAD_H */

arch/metag/include/asm/io.h

@@ -0,0 +1,165 @@
+#ifndef _ASM_METAG_IO_H
+#define _ASM_METAG_IO_H
+
+#include <linux/types.h>
+
+#define IO_SPACE_LIMIT  0
+
+#define page_to_bus page_to_phys
+#define bus_to_page phys_to_page
+
+/*
+ * Generic I/O
+ */
+
+#define __raw_readb __raw_readb
+static inline u8 __raw_readb(const volatile void __iomem *addr)
+{
+	u8 ret;
+	asm volatile("GETB %0,[%1]"
+		     : "=da" (ret)
+		     : "da" (addr)
+		     : "memory");
+	return ret;
+}
+
+#define __raw_readw __raw_readw
+static inline u16 __raw_readw(const volatile void __iomem *addr)
+{
+	u16 ret;
+	asm volatile("GETW %0,[%1]"
+		     : "=da" (ret)
+		     : "da" (addr)
+		     : "memory");
+	return ret;
+}
+
+#define __raw_readl __raw_readl
+static inline u32 __raw_readl(const volatile void __iomem *addr)
+{
+	u32 ret;
+	asm volatile("GETD %0,[%1]"
+		     : "=da" (ret)
+		     : "da" (addr)
+		     : "memory");
+	return ret;
+}
+
+#define __raw_readq __raw_readq
+static inline u64 __raw_readq(const volatile void __iomem *addr)
+{
+	u64 ret;
+	asm volatile("GETL %0,%t0,[%1]"
+		     : "=da" (ret)
+		     : "da" (addr)
+		     : "memory");
+	return ret;
+}
+
+#define __raw_writeb __raw_writeb
+static inline void __raw_writeb(u8 b, volatile void __iomem *addr)
+{
+	asm volatile("SETB [%0],%1"
+		     :
+		     : "da" (addr),
+		       "da" (b)
+		     : "memory");
+}
+
+#define __raw_writew __raw_writew
+static inline void __raw_writew(u16 b, volatile void __iomem *addr)
+{
+	asm volatile("SETW [%0],%1"
+		     :
+		     : "da" (addr),
+		       "da" (b)
+		     : "memory");
+}
+
+#define __raw_writel __raw_writel
+static inline void __raw_writel(u32 b, volatile void __iomem *addr)
+{
+	asm volatile("SETD [%0],%1"
+		     :
+		     : "da" (addr),
+		       "da" (b)
+		     : "memory");
+}
+
+#define __raw_writeq __raw_writeq
+static inline void __raw_writeq(u64 b, volatile void __iomem *addr)
+{
+	asm volatile("SETL [%0],%1,%t1"
+		     :
+		     : "da" (addr),
+		       "da" (b)
+		     : "memory");
+}
+
+/*
+ * The generic io.h can define all the other generic accessors
+ */
+
+#include <asm-generic/io.h>
+
+/*
+ * Despite being a 32bit architecture, Meta can do 64bit memory accesses
+ * (assuming the bus supports it).
+ */
+
+#define readq	__raw_readq
+#define writeq	__raw_writeq
+
+/*
+ * Meta specific I/O for accessing non-MMU areas.
+ *
+ * These can be provided with a physical address rather than an __iomem pointer
+ * and should only be used by core architecture code for accessing fixed core
+ * registers. Generic drivers should use ioremap and the generic I/O accessors.
+ */
+
+#define metag_in8(addr)		__raw_readb((volatile void __iomem *)(addr))
+#define metag_in16(addr)	__raw_readw((volatile void __iomem *)(addr))
+#define metag_in32(addr)	__raw_readl((volatile void __iomem *)(addr))
+#define metag_in64(addr)	__raw_readq((volatile void __iomem *)(addr))
+
+#define metag_out8(b, addr)	__raw_writeb(b, (volatile void __iomem *)(addr))
+#define metag_out16(b, addr)	__raw_writew(b, (volatile void __iomem *)(addr))
+#define metag_out32(b, addr)	__raw_writel(b, (volatile void __iomem *)(addr))
+#define metag_out64(b, addr)	__raw_writeq(b, (volatile void __iomem *)(addr))
+
+/*
+ * io remapping functions
+ */
+
+extern void __iomem *__ioremap(unsigned long offset,
+			       size_t size, unsigned long flags);
+extern void __iounmap(void __iomem *addr);
+
+/**
+ *	ioremap		-	map bus memory into CPU space
+ *	@offset:	bus address of the memory
+ *	@size:		size of the resource to map
+ *
+ *	ioremap performs a platform specific sequence of operations to
+ *	make bus memory CPU accessible via the readb/readw/readl/writeb/
+ *	writew/writel functions and the other mmio helpers. The returned
+ *	address is not guaranteed to be usable directly as a virtual
+ *	address.
+ */
+#define ioremap(offset, size)                   \
+	__ioremap((offset), (size), 0)
+
+#define ioremap_nocache(offset, size)           \
+	__ioremap((offset), (size), 0)
+
+#define ioremap_cached(offset, size)            \
+	__ioremap((offset), (size), _PAGE_CACHEABLE)
+
+#define ioremap_wc(offset, size)                \
+	__ioremap((offset), (size), _PAGE_WR_COMBINE)
+
+#define iounmap(addr)                           \
+	__iounmap(addr)
+
+#endif  /* _ASM_METAG_IO_H */

arch/metag/include/asm/irq.h

@@ -0,0 +1,32 @@
+#ifndef __ASM_METAG_IRQ_H
+#define __ASM_METAG_IRQ_H
+
+#ifdef CONFIG_4KSTACKS
+extern void irq_ctx_init(int cpu);
+extern void irq_ctx_exit(int cpu);
+# define __ARCH_HAS_DO_SOFTIRQ
+#else
+# define irq_ctx_init(cpu) do { } while (0)
+# define irq_ctx_exit(cpu) do { } while (0)
+#endif
+
+void tbi_startup_interrupt(int);
+void tbi_shutdown_interrupt(int);
+
+struct pt_regs;
+
+int tbisig_map(unsigned int hw);
+extern void do_IRQ(int irq, struct pt_regs *regs);
+
+#ifdef CONFIG_METAG_SUSPEND_MEM
+int traps_save_context(void);
+int traps_restore_context(void);
+#endif
+
+#include <asm-generic/irq.h>
+
+#ifdef CONFIG_HOTPLUG_CPU
+extern void migrate_irqs(void);
+#endif
+
+#endif /* __ASM_METAG_IRQ_H */

arch/metag/include/asm/irqflags.h

@@ -0,0 +1,93 @@
+/*
+ * IRQ flags handling
+ *
+ * This file gets included from lowlevel asm headers too, to provide
+ * wrapped versions of the local_irq_*() APIs, based on the
+ * raw_local_irq_*() functions from the lowlevel headers.
+ */
+#ifndef _ASM_IRQFLAGS_H
+#define _ASM_IRQFLAGS_H
+
+#ifndef __ASSEMBLY__
+
+#include <asm/core_reg.h>
+#include <asm/metag_regs.h>
+
+#define INTS_OFF_MASK TXSTATI_BGNDHALT_BIT
+
+#ifdef CONFIG_SMP
+extern unsigned int get_trigger_mask(void);
+#else
+
+extern unsigned int global_trigger_mask;
+
+static inline unsigned int get_trigger_mask(void)
+{
+	return global_trigger_mask;
+}
+#endif
+
+static inline unsigned long arch_local_save_flags(void)
+{
+	return __core_reg_get(TXMASKI);
+}
+
+static inline int arch_irqs_disabled_flags(unsigned long flags)
+{
+	return (flags & ~INTS_OFF_MASK) == 0;
+}
+
+static inline int arch_irqs_disabled(void)
+{
+	unsigned long flags = arch_local_save_flags();
+
+	return arch_irqs_disabled_flags(flags);
+}
+
+static inline unsigned long __irqs_disabled(void)
+{
+	/*
+	 * We shouldn't enable exceptions if they are not already
+	 * enabled. This is required for chancalls to work correctly.
+	 */
+	return arch_local_save_flags() & INTS_OFF_MASK;
+}
+
+/*
+ * For spinlocks, etc:
+ */
+static inline unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags = __irqs_disabled();
+
+	asm volatile("SWAP %0,TXMASKI\n" : "=r" (flags) : "0" (flags)
+		     : "memory");
+
+	return flags;
+}
+
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+	asm volatile("MOV TXMASKI,%0\n" : : "r" (flags) : "memory");
+}
+
+static inline void arch_local_irq_disable(void)
+{
+	unsigned long flags = __irqs_disabled();
+
+	asm volatile("MOV TXMASKI,%0\n" : : "r" (flags) : "memory");
+}
+
+#ifdef CONFIG_SMP
+/* Avoid circular include dependencies through <linux/preempt.h> */
+void arch_local_irq_enable(void);
+#else
+static inline void arch_local_irq_enable(void)
+{
+	arch_local_irq_restore(get_trigger_mask());
+}
+#endif
+
+#endif /* (__ASSEMBLY__) */
+
+#endif /* !(_ASM_IRQFLAGS_H) */

arch/metag/include/asm/l2cache.h

@@ -0,0 +1,258 @@
+#ifndef _METAG_L2CACHE_H
+#define _METAG_L2CACHE_H
+
+#ifdef CONFIG_METAG_L2C
+
+#include <asm/global_lock.h>
+#include <asm/io.h>
+
+/*
+ * Store the last known value of pfenable (we don't want prefetch enabled while
+ * L2 is off).
+ */
+extern int l2c_pfenable;
+
+/* defined in arch/metag/drivers/core-sysfs.c */
+extern struct sysdev_class cache_sysclass;
+
+static inline void wr_fence(void);
+
+/*
+ * Functions for reading of L2 cache configuration.
+ */
+
+/* Get raw L2 config register (CORE_CONFIG3) */
+static inline unsigned int meta_l2c_config(void)
+{
+	const unsigned int *corecfg3 = (const unsigned int *)METAC_CORE_CONFIG3;
+	return *corecfg3;
+}
+
+/* Get whether the L2 is present */
+static inline int meta_l2c_is_present(void)
+{
+	return meta_l2c_config() & METAC_CORECFG3_L2C_HAVE_L2C_BIT;
+}
+
+/* Get whether the L2 is configured for write-back instead of write-through */
+static inline int meta_l2c_is_writeback(void)
+{
+	return meta_l2c_config() & METAC_CORECFG3_L2C_MODE_BIT;
+}
+
+/* Get whether the L2 is unified instead of separated code/data */
+static inline int meta_l2c_is_unified(void)
+{
+	return meta_l2c_config() & METAC_CORECFG3_L2C_UNIFIED_BIT;
+}
+
+/* Get the L2 cache size in bytes */
+static inline unsigned int meta_l2c_size(void)
+{
+	unsigned int size_s;
+	if (!meta_l2c_is_present())
+		return 0;
+	size_s = (meta_l2c_config() & METAC_CORECFG3_L2C_SIZE_BITS)
+			>> METAC_CORECFG3_L2C_SIZE_S;
+	/* L2CSIZE is in KiB */
+	return 1024 << size_s;
+}
+
+/* Get the number of ways in the L2 cache */
+static inline unsigned int meta_l2c_ways(void)
+{
+	unsigned int ways_s;
+	if (!meta_l2c_is_present())
+		return 0;
+	ways_s = (meta_l2c_config() & METAC_CORECFG3_L2C_NUM_WAYS_BITS)
+			>> METAC_CORECFG3_L2C_NUM_WAYS_S;
+	return 0x1 << ways_s;
+}
+
+/* Get the line size of the L2 cache */
+static inline unsigned int meta_l2c_linesize(void)
+{
+	unsigned int line_size;
+	if (!meta_l2c_is_present())
+		return 0;
+	line_size = (meta_l2c_config() & METAC_CORECFG3_L2C_LINE_SIZE_BITS)
+			>> METAC_CORECFG3_L2C_LINE_SIZE_S;
+	switch (line_size) {
+	case METAC_CORECFG3_L2C_LINE_SIZE_64B:
+		return 64;
+	default:
+		return 0;
+	}
+}
+
+/* Get the revision ID of the L2 cache */
+static inline unsigned int meta_l2c_revision(void)
+{
+	return (meta_l2c_config() & METAC_CORECFG3_L2C_REV_ID_BITS)
+			>> METAC_CORECFG3_L2C_REV_ID_S;
+}
+
+
+/*
+ * Start an initialisation of the L2 cachelines and wait for completion.
+ * This should only be done in a LOCK1 or LOCK2 critical section while the L2
+ * is disabled.
+ */
+static inline void _meta_l2c_init(void)
+{
+	metag_out32(SYSC_L2C_INIT_INIT, SYSC_L2C_INIT);
+	while (metag_in32(SYSC_L2C_INIT) == SYSC_L2C_INIT_IN_PROGRESS)
+		/* do nothing */;
+}
+
+/*
+ * Start a writeback of dirty L2 cachelines and wait for completion.
+ * This should only be done in a LOCK1 or LOCK2 critical section.
+ */
+static inline void _meta_l2c_purge(void)
+{
+	metag_out32(SYSC_L2C_PURGE_PURGE, SYSC_L2C_PURGE);
+	while (metag_in32(SYSC_L2C_PURGE) == SYSC_L2C_PURGE_IN_PROGRESS)
+		/* do nothing */;
+}
+
+/* Set whether the L2 cache is enabled. */
+static inline void _meta_l2c_enable(int enabled)
+{
+	unsigned int enable;
+
+	enable = metag_in32(SYSC_L2C_ENABLE);
+	if (enabled)
+		enable |= SYSC_L2C_ENABLE_ENABLE_BIT;
+	else
+		enable &= ~SYSC_L2C_ENABLE_ENABLE_BIT;
+	metag_out32(enable, SYSC_L2C_ENABLE);
+}
+
+/* Set whether the L2 cache prefetch is enabled. */
+static inline void _meta_l2c_pf_enable(int pfenabled)
+{
+	unsigned int enable;
+
+	enable = metag_in32(SYSC_L2C_ENABLE);
+	if (pfenabled)
+		enable |= SYSC_L2C_ENABLE_PFENABLE_BIT;
+	else
+		enable &= ~SYSC_L2C_ENABLE_PFENABLE_BIT;
+	metag_out32(enable, SYSC_L2C_ENABLE);
+}
+
+/* Return whether the L2 cache is enabled */
+static inline int _meta_l2c_is_enabled(void)
+{
+	return metag_in32(SYSC_L2C_ENABLE) & SYSC_L2C_ENABLE_ENABLE_BIT;
+}
+
+/* Return whether the L2 cache prefetch is enabled */
+static inline int _meta_l2c_pf_is_enabled(void)
+{
+	return metag_in32(SYSC_L2C_ENABLE) & SYSC_L2C_ENABLE_PFENABLE_BIT;
+}
+
+
+/* Return whether the L2 cache is enabled */
+static inline int meta_l2c_is_enabled(void)
+{
+	int en;
+
+	/*
+	 * There is no need to lock at the moment, as the enable bit is never
+	 * intermediately changed, so we will never see an intermediate result.
+	 */
+	en = _meta_l2c_is_enabled();
+
+	return en;
+}
+
+/*
+ * Ensure the L2 cache is disabled.
+ * Return whether the L2 was previously disabled.
+ */
+int meta_l2c_disable(void);
+
+/*
+ * Ensure the L2 cache is enabled.
+ * Return whether the L2 was previously enabled.
+ */
+int meta_l2c_enable(void);
+
+/* Return whether the L2 cache prefetch is enabled */
+static inline int meta_l2c_pf_is_enabled(void)
+{
+	return l2c_pfenable;
+}
+
+/*
+ * Set whether the L2 cache prefetch is enabled.
+ * Return whether the L2 prefetch was previously enabled.
+ */
+int meta_l2c_pf_enable(int pfenable);
+
+/*
+ * Flush the L2 cache.
+ * Return 1 if the L2 is disabled.
+ */
+int meta_l2c_flush(void);
+
+/*
+ * Write back all dirty cache lines in the L2 cache.
+ * Return 1 if the L2 is disabled or there isn't any writeback.
+ */
+static inline int meta_l2c_writeback(void)
+{
+	unsigned long flags;
+	int en;
+
+	/* no need to purge if it's not a writeback cache */
+	if (!meta_l2c_is_writeback())
+		return 1;
+
+	/*
+	 * Purge only works if the L2 is enabled, and involves reading back to
+	 * detect completion, so keep this operation atomic with other threads.
+	 */
+	__global_lock1(flags);
+	en = meta_l2c_is_enabled();
+	if (likely(en)) {
+		wr_fence();
+		_meta_l2c_purge();
+	}
+	__global_unlock1(flags);
+
+	return !en;
+}
+
+#else /* CONFIG_METAG_L2C */
+
+#define meta_l2c_config()		0
+#define meta_l2c_is_present()		0
+#define meta_l2c_is_writeback()		0
+#define meta_l2c_is_unified()		0
+#define meta_l2c_size()			0
+#define meta_l2c_ways()			0
+#define meta_l2c_linesize()		0
+#define meta_l2c_revision()		0
+
+#define meta_l2c_is_enabled()		0
+#define _meta_l2c_pf_is_enabled()	0
+#define meta_l2c_pf_is_enabled()	0
+#define meta_l2c_disable()		1
+#define meta_l2c_enable()		0
+#define meta_l2c_pf_enable(X)		0
+static inline int meta_l2c_flush(void)
+{
+	return 1;
+}
+static inline int meta_l2c_writeback(void)
+{
+	return 1;
+}
+
+#endif /* CONFIG_METAG_L2C */
+
+#endif /* _METAG_L2CACHE_H */

arch/metag/include/asm/linkage.h

@@ -0,0 +1,7 @@
+#ifndef __ASM_LINKAGE_H
+#define __ASM_LINKAGE_H
+
+#define __ALIGN .p2align 2
+#define __ALIGN_STR ".p2align 2"
+
+#endif

arch/metag/include/asm/mach/arch.h

@@ -0,0 +1,86 @@
+/*
+ * arch/metag/include/asm/mach/arch.h
+ *
+ * Copyright (C) 2012 Imagination Technologies Ltd.
+ *
+ * based on the ARM version:
+ *  Copyright (C) 2000 Russell King
+ *
+ * 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 _METAG_MACH_ARCH_H_
+#define _METAG_MACH_ARCH_H_
+
+#include <linux/stddef.h>
+
+#include <asm/clock.h>
+
+/**
+ * struct machine_desc - Describes a board controlled by a Meta.
+ * @name:		Board/SoC name.
+ * @dt_compat:		Array of device tree 'compatible' strings.
+ * @clocks:		Clock callbacks.
+ *
+ * @nr_irqs:		Maximum number of IRQs.
+ *			If 0, defaults to NR_IRQS in asm-generic/irq.h.
+ *
+ * @init_early:		Early init callback.
+ * @init_irq:		IRQ init callback for setting up IRQ controllers.
+ * @init_machine:	Arch init callback for setting up devices.
+ * @init_late:		Late init callback.
+ *
+ * This structure is provided by each board which can be controlled by a Meta.
+ * It is chosen by matching the compatible strings in the device tree provided
+ * by the bootloader with the strings in @dt_compat, and sets up any aspects of
+ * the machine that aren't configured with device tree (yet).
+ */
+struct machine_desc {
+	const char		*name;
+	const char		**dt_compat;
+	struct meta_clock_desc	*clocks;
+
+	unsigned int		nr_irqs;
+
+	void			(*init_early)(void);
+	void			(*init_irq)(void);
+	void			(*init_machine)(void);
+	void			(*init_late)(void);
+};
+
+/*
+ * Current machine - only accessible during boot.
+ */
+extern struct machine_desc *machine_desc;
+
+/*
+ * Machine type table - also only accessible during boot
+ */
+extern struct machine_desc __arch_info_begin[], __arch_info_end[];
+#define for_each_machine_desc(p)			\
+	for (p = __arch_info_begin; p < __arch_info_end; p++)
+
+static inline struct machine_desc *default_machine_desc(void)
+{
+	/* the default machine is the last one linked in */
+	if (__arch_info_end - 1 < __arch_info_begin)
+		return NULL;
+	return __arch_info_end - 1;
+}
+
+/*
+ * Set of macros to define architecture features.  This is built into
+ * a table by the linker.
+ */
+#define MACHINE_START(_type, _name)			\
+static const struct machine_desc __mach_desc_##_type	\
+__used							\
+__attribute__((__section__(".arch.info.init"))) = {	\
+	.name		= _name,
+
+#define MACHINE_END				\
+};
+
+#endif /* _METAG_MACH_ARCH_H_ */

arch/metag/include/asm/metag_isa.h

@@ -0,0 +1,81 @@
+/*
+ * asm/metag_isa.h
+ *
+ * Copyright (C) 2000-2007, 2012 Imagination Technologies.
+ *
+ * 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.
+ *
+ * Various defines for Meta instruction set.
+ */
+
+#ifndef _ASM_METAG_ISA_H_
+#define _ASM_METAG_ISA_H_
+
+
+/* L1 cache layout */
+
+/* Data cache line size as bytes and shift */
+#define DCACHE_LINE_BYTES 64
+#define DCACHE_LINE_S     6
+
+/* Number of ways in the data cache */
+#define DCACHE_WAYS       4
+
+/* Instruction cache line size as bytes and shift */
+#define ICACHE_LINE_BYTES 64
+#define ICACHE_LINE_S     6
+
+/* Number of ways in the instruction cache */
+#define ICACHE_WAYS       4
+
+
+/*
+ * CACHEWD/CACHEWL instructions use the bottom 8 bits of the data presented to
+ * control the operation actually achieved.
+ */
+/* Use of these two bits should be discouraged since the bits dont have
+ * consistent meanings
+ */
+#define CACHEW_ICACHE_BIT           0x01
+#define CACHEW_TLBFLUSH_BIT         0x02
+
+#define CACHEW_FLUSH_L1D_L2         0x0
+#define CACHEW_INVALIDATE_L1I       0x1
+#define CACHEW_INVALIDATE_L1DTLB    0x2
+#define CACHEW_INVALIDATE_L1ITLB    0x3
+#define CACHEW_WRITEBACK_L1D_L2     0x4
+#define CACHEW_INVALIDATE_L1D       0x8
+#define CACHEW_INVALIDATE_L1D_L2    0xC
+
+/*
+ * CACHERD/CACHERL instructions use bits 3:5 of the address presented to
+ * control the operation achieved and hence the specific result.
+ */
+#define CACHER_ADDR_BITS            0xFFFFFFC0
+#define CACHER_OPER_BITS            0x00000030
+#define CACHER_OPER_S               4
+#define     CACHER_OPER_LINPHY          0
+#define CACHER_ICACHE_BIT           0x00000008
+#define CACHER_ICACHE_S             3
+
+/*
+ * CACHERD/CACHERL LINPHY Oper result is one/two 32-bit words
+ *
+ *  If CRLINPHY0_VAL_BIT (Bit 0) set then,
+ *      Lower 32-bits corresponds to MMCU_ENTRY_* above.
+ *      Upper 32-bits corresponds to CRLINPHY1_* values below (if requested).
+ *  else
+ *      Lower 32-bits corresponds to CRLINPHY0_* values below.
+ *      Upper 32-bits undefined.
+ */
+#define CRLINPHY0_VAL_BIT      0x00000001
+#define CRLINPHY0_FIRST_BIT    0x00000004 /* Set if VAL=0 due to first level */
+
+#define CRLINPHY1_READ_BIT     0x00000001 /* Set if reads permitted          */
+#define CRLINPHY1_SINGLE_BIT   0x00000004 /* Set if TLB does not cache entry */
+#define CRLINPHY1_PAGEMSK_BITS 0x0000FFF0 /* Set to ((2^n-1)>>12) value      */
+#define CRLINPHY1_PAGEMSK_S    4
+
+#endif /* _ASM_METAG_ISA_H_ */

arch/metag/include/asm/mman.h

@@ -0,0 +1,11 @@
+#ifndef __METAG_MMAN_H__
+#define __METAG_MMAN_H__
+
+#include <uapi/asm/mman.h>
+
+#ifndef __ASSEMBLY__
+#define arch_mmap_check metag_mmap_check
+int metag_mmap_check(unsigned long addr, unsigned long len,
+		     unsigned long flags);
+#endif
+#endif /* __METAG_MMAN_H__ */

arch/metag/include/asm/mmu.h

@@ -0,0 +1,77 @@
+#ifndef __MMU_H
+#define __MMU_H
+
+#ifdef CONFIG_METAG_USER_TCM
+#include <linux/list.h>
+#endif
+
+#ifdef CONFIG_HUGETLB_PAGE
+#include <asm/page.h>
+#endif
+
+typedef struct {
+	/* Software pgd base pointer used for Meta 1.x MMU. */
+	unsigned long pgd_base;
+#ifdef CONFIG_METAG_USER_TCM
+	struct list_head tcm;
+#endif
+#ifdef CONFIG_HUGETLB_PAGE
+#if HPAGE_SHIFT < HUGEPT_SHIFT
+	/* last partially filled huge page table address */
+	unsigned long part_huge;
+#endif
+#endif
+} mm_context_t;
+
+/* Given a virtual address, return the pte for the top level 4meg entry
+ * that maps that address.
+ * Returns 0 (an empty pte) if that range is not mapped.
+ */
+unsigned long mmu_read_first_level_page(unsigned long vaddr);
+
+/* Given a linear (virtual) address, return the second level 4k pte
+ * that maps that address.  Returns 0 if the address is not mapped.
+ */
+unsigned long mmu_read_second_level_page(unsigned long vaddr);
+
+/* Get the virtual base address of the MMU */
+unsigned long mmu_get_base(void);
+
+/* Initialize the MMU. */
+void mmu_init(unsigned long mem_end);
+
+#ifdef CONFIG_METAG_META21_MMU
+/*
+ * For cpu "cpu" calculate and return the address of the
+ * MMCU_TnLOCAL_TABLE_PHYS0 if running in local-space or
+ * MMCU_TnGLOBAL_TABLE_PHYS0 if running in global-space.
+ */
+static inline unsigned long mmu_phys0_addr(unsigned int cpu)
+{
+	unsigned long phys0;
+
+	phys0 = (MMCU_T0LOCAL_TABLE_PHYS0 +
+		(MMCU_TnX_TABLE_PHYSX_STRIDE * cpu)) +
+		(MMCU_TXG_TABLE_PHYSX_OFFSET * is_global_space(PAGE_OFFSET));
+
+	return phys0;
+}
+
+/*
+ * For cpu "cpu" calculate and return the address of the
+ * MMCU_TnLOCAL_TABLE_PHYS1 if running in local-space or
+ * MMCU_TnGLOBAL_TABLE_PHYS1 if running in global-space.
+ */
+static inline unsigned long mmu_phys1_addr(unsigned int cpu)
+{
+	unsigned long phys1;
+
+	phys1 = (MMCU_T0LOCAL_TABLE_PHYS1 +
+		(MMCU_TnX_TABLE_PHYSX_STRIDE * cpu)) +
+		(MMCU_TXG_TABLE_PHYSX_OFFSET * is_global_space(PAGE_OFFSET));
+
+	return phys1;
+}
+#endif /* CONFIG_METAG_META21_MMU */
+
+#endif

arch/metag/include/asm/mmu_context.h

@@ -0,0 +1,113 @@
+#ifndef __METAG_MMU_CONTEXT_H
+#define __METAG_MMU_CONTEXT_H
+
+#include <asm-generic/mm_hooks.h>
+
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
+
+#include <linux/io.h>
+
+static inline void enter_lazy_tlb(struct mm_struct *mm,
+				  struct task_struct *tsk)
+{
+}
+
+static inline int init_new_context(struct task_struct *tsk,
+				   struct mm_struct *mm)
+{
+#ifndef CONFIG_METAG_META21_MMU
+	/* We use context to store a pointer to the page holding the
+	 * pgd of a process while it is running. While a process is not
+	 * running the pgd and context fields should be equal.
+	 */
+	mm->context.pgd_base = (unsigned long) mm->pgd;
+#endif
+#ifdef CONFIG_METAG_USER_TCM
+	INIT_LIST_HEAD(&mm->context.tcm);
+#endif
+	return 0;
+}
+
+#ifdef CONFIG_METAG_USER_TCM
+
+#include <linux/slab.h>
+#include <asm/tcm.h>
+
+static inline void destroy_context(struct mm_struct *mm)
+{
+	struct tcm_allocation *pos, *n;
+
+	list_for_each_entry_safe(pos, n,  &mm->context.tcm, list) {
+		tcm_free(pos->tag, pos->addr, pos->size);
+		list_del(&pos->list);
+		kfree(pos);
+	}
+}
+#else
+#define destroy_context(mm)		do { } while (0)
+#endif
+
+#ifdef CONFIG_METAG_META21_MMU
+static inline void load_pgd(pgd_t *pgd, int thread)
+{
+	unsigned long phys0 = mmu_phys0_addr(thread);
+	unsigned long phys1 = mmu_phys1_addr(thread);
+
+	/*
+	 *  0x900 2Gb address space
+	 *  The permission bits apply to MMU table region which gives a 2MB
+	 *  window into physical memory. We especially don't want userland to be
+	 *  able to access this.
+	 */
+	metag_out32(0x900 | _PAGE_CACHEABLE | _PAGE_PRIV | _PAGE_WRITE |
+		    _PAGE_PRESENT, phys0);
+	/* Set new MMU base address */
+	metag_out32(__pa(pgd) & MMCU_TBLPHYS1_ADDR_BITS, phys1);
+}
+#endif
+
+static inline void switch_mmu(struct mm_struct *prev, struct mm_struct *next)
+{
+#ifdef CONFIG_METAG_META21_MMU
+	load_pgd(next->pgd, hard_processor_id());
+#else
+	unsigned int i;
+
+	/* prev->context == prev->pgd in the case where we are initially
+	   switching from the init task to the first process. */
+	if (prev->context.pgd_base != (unsigned long) prev->pgd) {
+		for (i = FIRST_USER_PGD_NR; i < USER_PTRS_PER_PGD; i++)
+			((pgd_t *) prev->context.pgd_base)[i] = prev->pgd[i];
+	} else
+		prev->pgd = (pgd_t *)mmu_get_base();
+
+	next->pgd = prev->pgd;
+	prev->pgd = (pgd_t *) prev->context.pgd_base;
+
+	for (i = FIRST_USER_PGD_NR; i < USER_PTRS_PER_PGD; i++)
+		next->pgd[i] = ((pgd_t *) next->context.pgd_base)[i];
+
+	flush_cache_all();
+#endif
+	flush_tlb_all();
+}
+
+static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
+			     struct task_struct *tsk)
+{
+	if (prev != next)
+		switch_mmu(prev, next);
+}
+
+static inline void activate_mm(struct mm_struct *prev_mm,
+			       struct mm_struct *next_mm)
+{
+	switch_mmu(prev_mm, next_mm);
+}
+
+#define deactivate_mm(tsk, mm)   do { } while (0)
+
+#endif

arch/metag/include/asm/mmzone.h

@@ -0,0 +1,42 @@
+#ifndef __ASM_METAG_MMZONE_H
+#define __ASM_METAG_MMZONE_H
+
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+#include <linux/numa.h>
+
+extern struct pglist_data *node_data[];
+#define NODE_DATA(nid)		(node_data[nid])
+
+static inline int pfn_to_nid(unsigned long pfn)
+{
+	int nid;
+
+	for (nid = 0; nid < MAX_NUMNODES; nid++)
+		if (pfn >= node_start_pfn(nid) && pfn <= node_end_pfn(nid))
+			break;
+
+	return nid;
+}
+
+static inline struct pglist_data *pfn_to_pgdat(unsigned long pfn)
+{
+	return NODE_DATA(pfn_to_nid(pfn));
+}
+
+/* arch/metag/mm/numa.c */
+void __init setup_bootmem_node(int nid, unsigned long start, unsigned long end);
+#else
+static inline void
+setup_bootmem_node(int nid, unsigned long start, unsigned long end)
+{
+}
+#endif /* CONFIG_NEED_MULTIPLE_NODES */
+
+#ifdef CONFIG_NUMA
+/* SoC specific mem init */
+void __init soc_mem_setup(void);
+#else
+static inline void __init soc_mem_setup(void) {};
+#endif
+
+#endif /* __ASM_METAG_MMZONE_H */

arch/metag/include/asm/module.h

@@ -0,0 +1,37 @@
+#ifndef _ASM_METAG_MODULE_H
+#define _ASM_METAG_MODULE_H
+
+#include <asm-generic/module.h>
+
+struct metag_plt_entry {
+	/* Indirect jump instruction sequence. */
+	unsigned long tramp[2];
+};
+
+struct mod_arch_specific {
+	/* Indices of PLT sections within module. */
+	unsigned int core_plt_section, init_plt_section;
+};
+
+#if defined CONFIG_METAG_META12
+#define MODULE_PROC_FAMILY "META 1.2 "
+#elif defined CONFIG_METAG_META21
+#define MODULE_PROC_FAMILY "META 2.1 "
+#else
+#define MODULE_PROC_FAMILY ""
+#endif
+
+#ifdef CONFIG_4KSTACKS
+#define MODULE_STACKSIZE "4KSTACKS "
+#else
+#define MODULE_STACKSIZE ""
+#endif
+
+#define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY MODULE_STACKSIZE
+
+#ifdef MODULE
+asm(".section .plt,\"ax\",@progbits; .balign 8; .previous");
+asm(".section .init.plt,\"ax\",@progbits; .balign 8; .previous");
+#endif
+
+#endif /* _ASM_METAG_MODULE_H */

arch/metag/include/asm/page.h

@@ -0,0 +1,128 @@
+#ifndef _METAG_PAGE_H
+#define _METAG_PAGE_H
+
+#include <linux/const.h>
+
+#include <asm/metag_mem.h>
+
+/* PAGE_SHIFT determines the page size */
+#if defined(CONFIG_PAGE_SIZE_4K)
+#define PAGE_SHIFT	12
+#elif defined(CONFIG_PAGE_SIZE_8K)
+#define PAGE_SHIFT	13
+#elif defined(CONFIG_PAGE_SIZE_16K)
+#define PAGE_SHIFT	14
+#endif
+
+#define PAGE_SIZE	(_AC(1, UL) << PAGE_SHIFT)
+#define PAGE_MASK	(~(PAGE_SIZE-1))
+
+#if defined(CONFIG_HUGETLB_PAGE_SIZE_8K)
+# define HPAGE_SHIFT	13
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_16K)
+# define HPAGE_SHIFT	14
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_32K)
+# define HPAGE_SHIFT	15
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_64K)
+# define HPAGE_SHIFT	16
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_128K)
+# define HPAGE_SHIFT	17
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_256K)
+# define HPAGE_SHIFT	18
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_512K)
+# define HPAGE_SHIFT	19
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_1M)
+# define HPAGE_SHIFT	20
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_2M)
+# define HPAGE_SHIFT	21
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_4M)
+# define HPAGE_SHIFT	22
+#endif
+
+#ifdef CONFIG_HUGETLB_PAGE
+# define HPAGE_SIZE		(1UL << HPAGE_SHIFT)
+# define HPAGE_MASK		(~(HPAGE_SIZE-1))
+# define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT-PAGE_SHIFT)
+/*
+ * We define our own hugetlb_get_unmapped_area so we don't corrupt 2nd level
+ * page tables with normal pages in them.
+ */
+# define HUGEPT_SHIFT		(22)
+# define HUGEPT_ALIGN		(1 << HUGEPT_SHIFT)
+# define HUGEPT_MASK		(HUGEPT_ALIGN - 1)
+# define ALIGN_HUGEPT(x)	ALIGN(x, HUGEPT_ALIGN)
+# define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
+#endif
+
+#ifndef __ASSEMBLY__
+
+/* On the Meta, we would like to know if the address (heap) we have is
+ * in local or global space.
+ */
+#define is_global_space(addr)	((addr) > 0x7fffffff)
+#define is_local_space(addr)	(!is_global_space(addr))
+
+extern void clear_page(void *to);
+extern void copy_page(void *to, void *from);
+
+#define clear_user_page(page, vaddr, pg)        clear_page(page)
+#define copy_user_page(to, from, vaddr, pg)     copy_page(to, from)
+
+/*
+ * These are used to make use of C type-checking..
+ */
+typedef struct { unsigned long pte; } pte_t;
+typedef struct { unsigned long pgd; } pgd_t;
+typedef struct { unsigned long pgprot; } pgprot_t;
+typedef struct page *pgtable_t;
+
+#define pte_val(x)	((x).pte)
+#define pgd_val(x)	((x).pgd)
+#define pgprot_val(x)	((x).pgprot)
+
+#define __pte(x)	((pte_t) { (x) })
+#define __pgd(x)	((pgd_t) { (x) })
+#define __pgprot(x)	((pgprot_t) { (x) })
+
+/* The kernel must now ALWAYS live at either 0xC0000000 or 0x40000000 - that
+ * being either global or local space.
+ */
+#define PAGE_OFFSET		(CONFIG_PAGE_OFFSET)
+
+#if PAGE_OFFSET >= LINGLOBAL_BASE
+#define META_MEMORY_BASE  LINGLOBAL_BASE
+#define META_MEMORY_LIMIT LINGLOBAL_LIMIT
+#else
+#define META_MEMORY_BASE  LINLOCAL_BASE
+#define META_MEMORY_LIMIT LINLOCAL_LIMIT
+#endif
+
+/* Offset between physical and virtual mapping of kernel memory. */
+extern unsigned int meta_memoffset;
+
+#define __pa(x) ((unsigned long)(((unsigned long)(x)) - meta_memoffset))
+#define __va(x) ((void *)((unsigned long)(((unsigned long)(x)) + meta_memoffset)))
+
+extern unsigned long pfn_base;
+#define ARCH_PFN_OFFSET         (pfn_base)
+#define virt_to_page(kaddr)     pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
+#define page_to_virt(page)      __va(page_to_pfn(page) << PAGE_SHIFT)
+#define virt_addr_valid(kaddr)  pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
+#define page_to_phys(page)      (page_to_pfn(page) << PAGE_SHIFT)
+#ifdef CONFIG_FLATMEM
+extern unsigned long max_pfn;
+extern unsigned long min_low_pfn;
+#define pfn_valid(pfn)		((pfn) >= min_low_pfn && (pfn) < max_pfn)
+#endif
+
+#define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
+
+#define VM_DATA_DEFAULT_FLAGS   (VM_READ | VM_WRITE | VM_EXEC | \
+				 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+
+#include <asm-generic/memory_model.h>
+#include <asm-generic/getorder.h>
+
+#endif /* __ASSMEBLY__ */
+
+#endif /* _METAG_PAGE_H */

arch/metag/include/asm/perf_event.h

@@ -0,0 +1,4 @@
+#ifndef __ASM_METAG_PERF_EVENT_H
+#define __ASM_METAG_PERF_EVENT_H
+
+#endif /* __ASM_METAG_PERF_EVENT_H */

arch/metag/include/asm/pgalloc.h

@@ -0,0 +1,79 @@
+#ifndef _METAG_PGALLOC_H
+#define _METAG_PGALLOC_H
+
+#include <linux/threads.h>
+#include <linux/mm.h>
+
+#define pmd_populate_kernel(mm, pmd, pte) \
+	set_pmd(pmd, __pmd(_PAGE_TABLE | __pa(pte)))
+
+#define pmd_populate(mm, pmd, pte) \
+	set_pmd(pmd, __pmd(_PAGE_TABLE | page_to_phys(pte)))
+
+#define pmd_pgtable(pmd) pmd_page(pmd)
+
+/*
+ * Allocate and free page tables.
+ */
+#ifdef CONFIG_METAG_META21_MMU
+static inline void pgd_ctor(pgd_t *pgd)
+{
+	memcpy(pgd + USER_PTRS_PER_PGD,
+	       swapper_pg_dir + USER_PTRS_PER_PGD,
+	       (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
+}
+#else
+#define pgd_ctor(x)	do { } while (0)
+#endif
+
+static inline pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+	pgd_t *pgd = (pgd_t *)get_zeroed_page(GFP_KERNEL);
+	if (pgd)
+		pgd_ctor(pgd);
+	return pgd;
+}
+
+static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+	free_page((unsigned long)pgd);
+}
+
+static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
+					  unsigned long address)
+{
+	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT |
+					      __GFP_ZERO);
+	return pte;
+}
+
+static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
+				      unsigned long address)
+{
+	struct page *pte;
+	pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO, 0);
+	if (pte)
+		pgtable_page_ctor(pte);
+	return pte;
+}
+
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+	free_page((unsigned long)pte);
+}
+
+static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
+{
+	pgtable_page_dtor(pte);
+	__free_page(pte);
+}
+
+#define __pte_free_tlb(tlb, pte, addr)				\
+	do {							\
+		pgtable_page_dtor(pte);				\
+		tlb_remove_page((tlb), (pte));			\
+	} while (0)
+
+#define check_pgt_cache()	do { } while (0)
+
+#endif

arch/metag/include/asm/pgtable.h

@@ -0,0 +1,370 @@
+/*
+ * Macros and functions to manipulate Meta page tables.
+ */
+
+#ifndef _METAG_PGTABLE_H
+#define _METAG_PGTABLE_H
+
+#include <asm-generic/pgtable-nopmd.h>
+
+/* Invalid regions on Meta: 0x00000000-0x001FFFFF and 0xFFFF0000-0xFFFFFFFF */
+#if PAGE_OFFSET >= LINGLOBAL_BASE
+#define CONSISTENT_START	0xF7000000
+#define CONSISTENT_END		0xF73FFFFF
+#define VMALLOC_START		0xF8000000
+#define VMALLOC_END		0xFFFEFFFF
+#else
+#define CONSISTENT_START	0x77000000
+#define CONSISTENT_END		0x773FFFFF
+#define VMALLOC_START		0x78000000
+#define VMALLOC_END		0x7FFFFFFF
+#endif
+
+/*
+ * Definitions for MMU descriptors
+ *
+ * These are the hardware bits in the MMCU pte entries.
+ * Derived from the Meta toolkit headers.
+ */
+#define _PAGE_PRESENT		MMCU_ENTRY_VAL_BIT
+#define _PAGE_WRITE		MMCU_ENTRY_WR_BIT
+#define _PAGE_PRIV		MMCU_ENTRY_PRIV_BIT
+/* Write combine bit - this can cause writes to occur out of order */
+#define _PAGE_WR_COMBINE	MMCU_ENTRY_WRC_BIT
+/* Sys coherent bit - this bit is never used by Linux */
+#define _PAGE_SYS_COHERENT	MMCU_ENTRY_SYS_BIT
+#define _PAGE_ALWAYS_ZERO_1	0x020
+#define _PAGE_CACHE_CTRL0	0x040
+#define _PAGE_CACHE_CTRL1	0x080
+#define _PAGE_ALWAYS_ZERO_2	0x100
+#define _PAGE_ALWAYS_ZERO_3	0x200
+#define _PAGE_ALWAYS_ZERO_4	0x400
+#define _PAGE_ALWAYS_ZERO_5	0x800
+
+/* These are software bits that we stuff into the gaps in the hardware
+ * pte entries that are not used.  Note, these DO get stored in the actual
+ * hardware, but the hardware just does not use them.
+ */
+#define _PAGE_ACCESSED		_PAGE_ALWAYS_ZERO_1
+#define _PAGE_DIRTY		_PAGE_ALWAYS_ZERO_2
+#define _PAGE_FILE		_PAGE_ALWAYS_ZERO_3
+
+/* Pages owned, and protected by, the kernel. */
+#define _PAGE_KERNEL		_PAGE_PRIV
+
+/* No cacheing of this page */
+#define _PAGE_CACHE_WIN0	(MMCU_CWIN_UNCACHED << MMCU_ENTRY_CWIN_S)
+/* burst cacheing - good for data streaming */
+#define _PAGE_CACHE_WIN1	(MMCU_CWIN_BURST << MMCU_ENTRY_CWIN_S)
+/* One cache way per thread */
+#define _PAGE_CACHE_WIN2	(MMCU_CWIN_C1SET << MMCU_ENTRY_CWIN_S)
+/* Full on cacheing */
+#define _PAGE_CACHE_WIN3	(MMCU_CWIN_CACHED << MMCU_ENTRY_CWIN_S)
+
+#define _PAGE_CACHEABLE		(_PAGE_CACHE_WIN3 | _PAGE_WR_COMBINE)
+
+/* which bits are used for cache control ... */
+#define _PAGE_CACHE_MASK	(_PAGE_CACHE_CTRL0 | _PAGE_CACHE_CTRL1 | \
+				 _PAGE_WR_COMBINE)
+
+/* This is a mask of the bits that pte_modify is allowed to change. */
+#define _PAGE_CHG_MASK		(PAGE_MASK)
+
+#define _PAGE_SZ_SHIFT		1
+#define _PAGE_SZ_4K		(0x0)
+#define _PAGE_SZ_8K		(0x1 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_16K		(0x2 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_32K		(0x3 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_64K		(0x4 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_128K		(0x5 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_256K		(0x6 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_512K		(0x7 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_1M		(0x8 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_2M		(0x9 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_4M		(0xa << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_MASK		(0xf << _PAGE_SZ_SHIFT)
+
+#if defined(CONFIG_PAGE_SIZE_4K)
+#define _PAGE_SZ		(_PAGE_SZ_4K)
+#elif defined(CONFIG_PAGE_SIZE_8K)
+#define _PAGE_SZ		(_PAGE_SZ_8K)
+#elif defined(CONFIG_PAGE_SIZE_16K)
+#define _PAGE_SZ		(_PAGE_SZ_16K)
+#endif
+#define _PAGE_TABLE		(_PAGE_SZ | _PAGE_PRESENT)
+
+#if defined(CONFIG_HUGETLB_PAGE_SIZE_8K)
+# define _PAGE_SZHUGE		(_PAGE_SZ_8K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_16K)
+# define _PAGE_SZHUGE		(_PAGE_SZ_16K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_32K)
+# define _PAGE_SZHUGE		(_PAGE_SZ_32K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_64K)
+# define _PAGE_SZHUGE		(_PAGE_SZ_64K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_128K)
+# define _PAGE_SZHUGE		(_PAGE_SZ_128K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_256K)
+# define _PAGE_SZHUGE		(_PAGE_SZ_256K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_512K)
+# define _PAGE_SZHUGE		(_PAGE_SZ_512K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_1M)
+# define _PAGE_SZHUGE		(_PAGE_SZ_1M)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_2M)
+# define _PAGE_SZHUGE		(_PAGE_SZ_2M)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_4M)
+# define _PAGE_SZHUGE		(_PAGE_SZ_4M)
+#endif
+
+/*
+ * The Linux memory management assumes a three-level page table setup. On
+ * Meta, we use that, but "fold" the mid level into the top-level page
+ * table.
+ */
+
+/* PGDIR_SHIFT determines the size of the area a second-level page table can
+ * map. This is always 4MB.
+ */
+
+#define PGDIR_SHIFT	22
+#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK	(~(PGDIR_SIZE-1))
+
+/*
+ * Entries per page directory level: we use a two-level, so
+ * we don't really have any PMD directory physically. First level tables
+ * always map 2Gb (local or global) at a granularity of 4MB, second-level
+ * tables map 4MB with a granularity between 4MB and 4kB (between 1 and
+ * 1024 entries).
+ */
+#define PTRS_PER_PTE	(PGDIR_SIZE/PAGE_SIZE)
+#define HPTRS_PER_PTE	(PGDIR_SIZE/HPAGE_SIZE)
+#define PTRS_PER_PGD	512
+
+#define USER_PTRS_PER_PGD	256
+#define FIRST_USER_ADDRESS	META_MEMORY_BASE
+#define FIRST_USER_PGD_NR	pgd_index(FIRST_USER_ADDRESS)
+
+#define PAGE_NONE	__pgprot(_PAGE_PRESENT | _PAGE_ACCESSED | \
+				 _PAGE_CACHEABLE)
+
+#define PAGE_SHARED	__pgprot(_PAGE_PRESENT | _PAGE_WRITE | \
+				 _PAGE_ACCESSED | _PAGE_CACHEABLE)
+#define PAGE_SHARED_C	PAGE_SHARED
+#define PAGE_COPY	__pgprot(_PAGE_PRESENT | _PAGE_ACCESSED | \
+				 _PAGE_CACHEABLE)
+#define PAGE_COPY_C	PAGE_COPY
+
+#define PAGE_READONLY	__pgprot(_PAGE_PRESENT | _PAGE_ACCESSED | \
+				 _PAGE_CACHEABLE)
+#define PAGE_KERNEL	__pgprot(_PAGE_PRESENT | _PAGE_DIRTY | \
+				 _PAGE_ACCESSED | _PAGE_WRITE | \
+				 _PAGE_CACHEABLE | _PAGE_KERNEL)
+
+#define __P000	PAGE_NONE
+#define __P001	PAGE_READONLY
+#define __P010	PAGE_COPY
+#define __P011	PAGE_COPY
+#define __P100	PAGE_READONLY
+#define __P101	PAGE_READONLY
+#define __P110	PAGE_COPY_C
+#define __P111	PAGE_COPY_C
+
+#define __S000	PAGE_NONE
+#define __S001	PAGE_READONLY
+#define __S010	PAGE_SHARED
+#define __S011	PAGE_SHARED
+#define __S100	PAGE_READONLY
+#define __S101	PAGE_READONLY
+#define __S110	PAGE_SHARED_C
+#define __S111	PAGE_SHARED_C
+
+#ifndef __ASSEMBLY__
+
+#include <asm/page.h>
+
+/* zero page used for uninitialized stuff */
+extern unsigned long empty_zero_page;
+#define ZERO_PAGE(vaddr)	(virt_to_page(empty_zero_page))
+
+/* Certain architectures need to do special things when pte's
+ * within a page table are directly modified.  Thus, the following
+ * hook is made available.
+ */
+#define set_pte(pteptr, pteval) ((*(pteptr)) = (pteval))
+#define set_pte_at(mm, addr, ptep, pteval) set_pte(ptep, pteval)
+
+#define set_pmd(pmdptr, pmdval) (*(pmdptr) = pmdval)
+
+#define pte_pfn(pte)		(pte_val(pte) >> PAGE_SHIFT)
+
+#define pfn_pte(pfn, prot)	__pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot))
+
+#define pte_none(x)		(!pte_val(x))
+#define pte_present(x)		(pte_val(x) & _PAGE_PRESENT)
+#define pte_clear(mm, addr, xp)	do { pte_val(*(xp)) = 0; } while (0)
+
+#define pmd_none(x)		(!pmd_val(x))
+#define pmd_bad(x)		((pmd_val(x) & ~(PAGE_MASK | _PAGE_SZ_MASK)) \
+					!= (_PAGE_TABLE & ~_PAGE_SZ_MASK))
+#define pmd_present(x)		(pmd_val(x) & _PAGE_PRESENT)
+#define pmd_clear(xp)		do { pmd_val(*(xp)) = 0; } while (0)
+
+#define pte_page(x)		pfn_to_page(pte_pfn(x))
+
+/*
+ * The following only work if pte_present() is true.
+ * Undefined behaviour if not..
+ */
+
+static inline int pte_write(pte_t pte)   { return pte_val(pte) & _PAGE_WRITE; }
+static inline int pte_dirty(pte_t pte)   { return pte_val(pte) & _PAGE_DIRTY; }
+static inline int pte_young(pte_t pte)   { return pte_val(pte) & _PAGE_ACCESSED; }
+static inline int pte_file(pte_t pte)    { return pte_val(pte) & _PAGE_FILE; }
+static inline int pte_special(pte_t pte) { return 0; }
+
+static inline pte_t pte_wrprotect(pte_t pte) { pte_val(pte) &= (~_PAGE_WRITE); return pte; }
+static inline pte_t pte_mkclean(pte_t pte)   { pte_val(pte) &= ~_PAGE_DIRTY; return pte; }
+static inline pte_t pte_mkold(pte_t pte)     { pte_val(pte) &= ~_PAGE_ACCESSED; return pte; }
+static inline pte_t pte_mkwrite(pte_t pte)   { pte_val(pte) |= _PAGE_WRITE; return pte; }
+static inline pte_t pte_mkdirty(pte_t pte)   { pte_val(pte) |= _PAGE_DIRTY; return pte; }
+static inline pte_t pte_mkyoung(pte_t pte)   { pte_val(pte) |= _PAGE_ACCESSED; return pte; }
+static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
+static inline pte_t pte_mkhuge(pte_t pte)    { return pte; }
+
+/*
+ * Macro and implementation to make a page protection as uncacheable.
+ */
+#define pgprot_writecombine(prot)					\
+	__pgprot(pgprot_val(prot) & ~(_PAGE_CACHE_CTRL1 | _PAGE_CACHE_CTRL0))
+
+#define pgprot_noncached(prot)						\
+	__pgprot(pgprot_val(prot) & ~_PAGE_CACHEABLE)
+
+
+/*
+ * Conversion functions: convert a page and protection to a page entry,
+ * and a page entry and page directory to the page they refer to.
+ */
+
+#define mk_pte(page, pgprot)	pfn_pte(page_to_pfn(page), (pgprot))
+
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+	pte_val(pte) = (pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot);
+	return pte;
+}
+
+static inline unsigned long pmd_page_vaddr(pmd_t pmd)
+{
+	unsigned long paddr = pmd_val(pmd) & PAGE_MASK;
+	if (!paddr)
+		return 0;
+	return (unsigned long)__va(paddr);
+}
+
+#define pmd_page(pmd)		(pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT))
+#define pmd_page_shift(pmd)	(12 + ((pmd_val(pmd) & _PAGE_SZ_MASK) \
+					>> _PAGE_SZ_SHIFT))
+#define pmd_num_ptrs(pmd)	(PGDIR_SIZE >> pmd_page_shift(pmd))
+
+/*
+ * Each pgd is only 2k, mapping 2Gb (local or global). If we're in global
+ * space drop the top bit before indexing the pgd.
+ */
+#if PAGE_OFFSET >= LINGLOBAL_BASE
+#define pgd_index(address)	((((address) & ~0x80000000) >> PGDIR_SHIFT) \
+							& (PTRS_PER_PGD-1))
+#else
+#define pgd_index(address)	(((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1))
+#endif
+
+#define pgd_offset(mm, address)	((mm)->pgd + pgd_index(address))
+
+#define pgd_offset_k(address)	pgd_offset(&init_mm, address)
+
+#define pmd_index(address)	(((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
+
+/* Find an entry in the second-level page table.. */
+#if !defined(CONFIG_HUGETLB_PAGE)
+  /* all pages are of size (1 << PAGE_SHIFT), so no need to read 1st level pt */
+# define pte_index(pmd, address) \
+	(((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+#else
+  /* some pages are huge, so read 1st level pt to find out */
+# define pte_index(pmd, address) \
+	(((address) >> pmd_page_shift(pmd)) & (pmd_num_ptrs(pmd) - 1))
+#endif
+#define pte_offset_kernel(dir, address) \
+	((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(*(dir), address))
+#define pte_offset_map(dir, address)		pte_offset_kernel(dir, address)
+#define pte_offset_map_nested(dir, address)	pte_offset_kernel(dir, address)
+
+#define pte_unmap(pte)		do { } while (0)
+#define pte_unmap_nested(pte)	do { } while (0)
+
+#define pte_ERROR(e) \
+	pr_err("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
+#define pgd_ERROR(e) \
+	pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
+
+/*
+ * Meta doesn't have any external MMU info: the kernel page
+ * tables contain all the necessary information.
+ */
+static inline void update_mmu_cache(struct vm_area_struct *vma,
+				    unsigned long address, pte_t *pte)
+{
+}
+
+/*
+ * Encode and decode a swap entry (must be !pte_none(e) && !pte_present(e))
+ * Since PAGE_PRESENT is bit 1, we can use the bits above that.
+ */
+#define __swp_type(x)			(((x).val >> 1) & 0xff)
+#define __swp_offset(x)			((x).val >> 10)
+#define __swp_entry(type, offset)	((swp_entry_t) { ((type) << 1) | \
+					 ((offset) << 10) })
+#define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) })
+#define __swp_entry_to_pte(x)		((pte_t) { (x).val })
+
+#define PTE_FILE_MAX_BITS	22
+#define pte_to_pgoff(x)		(pte_val(x) >> 10)
+#define pgoff_to_pte(x)		__pte(((x) << 10) | _PAGE_FILE)
+
+#define kern_addr_valid(addr)	(1)
+
+#define io_remap_pfn_range(vma, vaddr, pfn, size, prot)		\
+	remap_pfn_range(vma, vaddr, pfn, size, prot)
+
+/*
+ * No page table caches to initialise
+ */
+#define pgtable_cache_init()	do { } while (0)
+
+extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
+void paging_init(unsigned long mem_end);
+
+#ifdef CONFIG_METAG_META12
+/* This is a workaround for an issue in Meta 1 cores. These cores cache
+ * invalid entries in the TLB so we always need to flush whenever we add
+ * a new pte. Unfortunately we can only flush the whole TLB not shoot down
+ * single entries so this is sub-optimal. This implementation ensures that
+ * we will get a flush at the second attempt, so we may still get repeated
+ * faults, we just don't overflow the kernel stack handling them.
+ */
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+#define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
+({									  \
+	int __changed = !pte_same(*(__ptep), __entry);			  \
+	if (__changed) {						  \
+		set_pte_at((__vma)->vm_mm, (__address), __ptep, __entry); \
+	}								  \
+	flush_tlb_page(__vma, __address);				  \
+	__changed;							  \
+})
+#endif
+
+#include <asm-generic/pgtable.h>
+
+#endif /* __ASSEMBLY__ */
+#endif /* _METAG_PGTABLE_H */

arch/metag/include/asm/processor.h

@@ -0,0 +1,202 @@
+/*
+ * Copyright (C) 2005,2006,2007,2008 Imagination Technologies
+ */
+
+#ifndef __ASM_METAG_PROCESSOR_H
+#define __ASM_METAG_PROCESSOR_H
+
+#include <linux/atomic.h>
+
+#include <asm/page.h>
+#include <asm/ptrace.h>
+#include <asm/metag_regs.h>
+
+/*
+ * Default implementation of macro that returns current
+ * instruction pointer ("program counter").
+ */
+#define current_text_addr() ({ __label__ _l; _l: &&_l; })
+
+/* The task stops where the kernel starts */
+#define TASK_SIZE	PAGE_OFFSET
+/* Add an extra page of padding at the top of the stack for the guard page. */
+#define STACK_TOP	(TASK_SIZE - PAGE_SIZE)
+#define STACK_TOP_MAX	STACK_TOP
+
+/* This decides where the kernel will search for a free chunk of vm
+ * space during mmap's.
+ */
+#define TASK_UNMAPPED_BASE	META_MEMORY_BASE
+
+typedef struct {
+	unsigned long seg;
+} mm_segment_t;
+
+#ifdef CONFIG_METAG_FPU
+struct meta_fpu_context {
+	TBICTXEXTFPU fpstate;
+	union {
+		struct {
+			TBICTXEXTBB4 fx8_15;
+			TBICTXEXTFPACC fpacc;
+		} fx8_15;
+		struct {
+			TBICTXEXTFPACC fpacc;
+			TBICTXEXTBB4 unused;
+		} nofx8_15;
+	} extfpstate;
+	bool needs_restore;
+};
+#else
+struct meta_fpu_context {};
+#endif
+
+#ifdef CONFIG_METAG_DSP
+struct meta_ext_context {
+	struct {
+		TBIEXTCTX ctx;
+		TBICTXEXTBB8 bb8;
+		TBIDUAL ax[TBICTXEXTAXX_BYTES / sizeof(TBIDUAL)];
+		TBICTXEXTHL2 hl2;
+		TBICTXEXTTDPR ext;
+		TBICTXEXTRP6 rp;
+	} regs;
+
+	/* DSPRAM A and B save areas. */
+	void *ram[2];
+
+	/* ECH encoded size of DSPRAM save areas. */
+	unsigned int ram_sz[2];
+};
+#else
+struct meta_ext_context {};
+#endif
+
+struct thread_struct {
+	PTBICTX kernel_context;
+	/* A copy of the user process Sig.SaveMask. */
+	unsigned int user_flags;
+	struct meta_fpu_context *fpu_context;
+	void __user *tls_ptr;
+	unsigned short int_depth;
+	unsigned short txdefr_failure;
+	struct meta_ext_context *dsp_context;
+};
+
+#define INIT_THREAD  { \
+	NULL,			/* kernel_context */	\
+	0,			/* user_flags */	\
+	NULL,			/* fpu_context */	\
+	NULL,			/* tls_ptr */		\
+	1,			/* int_depth - we start in kernel */	\
+	0,			/* txdefr_failure */	\
+	NULL,			/* dsp_context */	\
+}
+
+/* Needed to make #define as we are referencing 'current', that is not visible
+ * yet.
+ *
+ * Stack layout is as below.
+
+      argc            argument counter (integer)
+      argv[0]         program name (pointer)
+      argv[1...N]     program args (pointers)
+      argv[argc-1]    end of args (integer)
+      NULL
+      env[0...N]      environment variables (pointers)
+      NULL
+
+ */
+#define start_thread(regs, pc, usp) do {				   \
+	unsigned int *argc = (unsigned int *) bprm->exec;		   \
+	set_fs(USER_DS);						   \
+	current->thread.int_depth = 1;					   \
+	/* Force this process down to user land */			   \
+	regs->ctx.SaveMask = TBICTX_PRIV_BIT;				   \
+	regs->ctx.CurrPC = pc;						   \
+	regs->ctx.AX[0].U0 = usp;					   \
+	regs->ctx.DX[3].U1 = *((int *)argc);			/* argc */ \
+	regs->ctx.DX[3].U0 = (int)((int *)argc + 1);		/* argv */ \
+	regs->ctx.DX[2].U1 = (int)((int *)argc +			   \
+				   regs->ctx.DX[3].U1 + 2);	/* envp */ \
+	regs->ctx.DX[2].U0 = 0;				   /* rtld_fini */ \
+} while (0)
+
+/* Forward declaration, a strange C thing */
+struct task_struct;
+
+/* Free all resources held by a thread. */
+static inline void release_thread(struct task_struct *dead_task)
+{
+}
+
+#define copy_segments(tsk, mm)		do { } while (0)
+#define release_segments(mm)		do { } while (0)
+
+extern void exit_thread(void);
+
+/*
+ * Return saved PC of a blocked thread.
+ */
+#define	thread_saved_pc(tsk)	\
+	((unsigned long)(tsk)->thread.kernel_context->CurrPC)
+#define thread_saved_sp(tsk)	\
+	((unsigned long)(tsk)->thread.kernel_context->AX[0].U0)
+#define thread_saved_fp(tsk)	\
+	((unsigned long)(tsk)->thread.kernel_context->AX[1].U0)
+
+unsigned long get_wchan(struct task_struct *p);
+
+#define	KSTK_EIP(tsk)	((tsk)->thread.kernel_context->CurrPC)
+#define	KSTK_ESP(tsk)	((tsk)->thread.kernel_context->AX[0].U0)
+
+#define user_stack_pointer(regs)        ((regs)->ctx.AX[0].U0)
+
+#define cpu_relax()     barrier()
+
+extern void setup_priv(void);
+
+static inline unsigned int hard_processor_id(void)
+{
+	unsigned int id;
+
+	asm volatile ("MOV	%0, TXENABLE\n"
+		      "AND	%0, %0, %1\n"
+		      "LSR	%0, %0, %2\n"
+		      : "=&d" (id)
+		      : "I" (TXENABLE_THREAD_BITS),
+			"K" (TXENABLE_THREAD_S)
+		      );
+
+	return id;
+}
+
+#define OP3_EXIT	0
+
+#define HALT_OK		0
+#define HALT_PANIC	-1
+
+/*
+ * Halt (stop) the hardware thread. This instruction sequence is the
+ * standard way to cause a Meta hardware thread to exit. The exit code
+ * is pushed onto the stack which is interpreted by the debug adapter.
+ */
+static inline void hard_processor_halt(int exit_code)
+{
+	asm volatile ("MOV	D1Ar1, %0\n"
+		      "MOV	D0Ar6, %1\n"
+		      "MSETL	[A0StP],D0Ar6,D0Ar4,D0Ar2\n"
+		      "1:\n"
+		      "SWITCH	#0xC30006\n"
+		      "B		1b\n"
+		      : : "r" (exit_code), "K" (OP3_EXIT));
+}
+
+/* Set these hooks to call SoC specific code to restart/halt/power off. */
+extern void (*soc_restart)(char *cmd);
+extern void (*soc_halt)(void);
+
+extern void show_trace(struct task_struct *tsk, unsigned long *sp,
+		       struct pt_regs *regs);
+
+#endif

arch/metag/include/asm/prom.h

@@ -0,0 +1,23 @@
+/*
+ *  arch/metag/include/asm/prom.h
+ *
+ *  Copyright (C) 2012 Imagination Technologies Ltd.
+ *
+ *  Based on ARM version:
+ *  Copyright (C) 2009 Canonical Ltd. <jeremy.kerr@canonical.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_METAG_PROM_H
+#define __ASM_METAG_PROM_H
+
+#include <asm/setup.h>
+#define HAVE_ARCH_DEVTREE_FIXUPS
+
+extern struct machine_desc *setup_machine_fdt(void *dt);
+extern void copy_fdt(void);
+
+#endif /* __ASM_METAG_PROM_H */

arch/metag/include/asm/ptrace.h

@@ -0,0 +1,60 @@
+#ifndef _METAG_PTRACE_H
+#define _METAG_PTRACE_H
+
+#include <linux/compiler.h>
+#include <uapi/asm/ptrace.h>
+#include <asm/tbx.h>
+
+#ifndef __ASSEMBLY__
+
+/* this struct defines the way the registers are stored on the
+   stack during a system call. */
+
+struct pt_regs {
+	TBICTX ctx;
+	TBICTXEXTCB0 extcb0[5];
+};
+
+#define user_mode(regs) (((regs)->ctx.SaveMask & TBICTX_PRIV_BIT) > 0)
+
+#define instruction_pointer(regs) ((unsigned long)(regs)->ctx.CurrPC)
+#define profile_pc(regs) instruction_pointer(regs)
+
+#define task_pt_regs(task) \
+	((struct pt_regs *)(task_stack_page(task) + \
+			    sizeof(struct thread_info)))
+
+#define current_pt_regs() \
+	((struct pt_regs *)((char *)current_thread_info() + \
+			    sizeof(struct thread_info)))
+
+int syscall_trace_enter(struct pt_regs *regs);
+void syscall_trace_leave(struct pt_regs *regs);
+
+/* copy a struct user_gp_regs out to user */
+int metag_gp_regs_copyout(const struct pt_regs *regs,
+			  unsigned int pos, unsigned int count,
+			  void *kbuf, void __user *ubuf);
+/* copy a struct user_gp_regs in from user */
+int metag_gp_regs_copyin(struct pt_regs *regs,
+			 unsigned int pos, unsigned int count,
+			 const void *kbuf, const void __user *ubuf);
+/* copy a struct user_cb_regs out to user */
+int metag_cb_regs_copyout(const struct pt_regs *regs,
+			  unsigned int pos, unsigned int count,
+			  void *kbuf, void __user *ubuf);
+/* copy a struct user_cb_regs in from user */
+int metag_cb_regs_copyin(struct pt_regs *regs,
+			 unsigned int pos, unsigned int count,
+			 const void *kbuf, const void __user *ubuf);
+/* copy a struct user_rp_state out to user */
+int metag_rp_state_copyout(const struct pt_regs *regs,
+			   unsigned int pos, unsigned int count,
+			   void *kbuf, void __user *ubuf);
+/* copy a struct user_rp_state in from user */
+int metag_rp_state_copyin(struct pt_regs *regs,
+			  unsigned int pos, unsigned int count,
+			  const void *kbuf, const void __user *ubuf);
+
+#endif /* __ASSEMBLY__ */
+#endif /* _METAG_PTRACE_H */

arch/metag/include/asm/setup.h

@@ -0,0 +1,8 @@
+#ifndef _ASM_METAG_SETUP_H
+#define _ASM_METAG_SETUP_H
+
+#include <uapi/asm/setup.h>
+
+void per_cpu_trap_init(unsigned long);
+extern void __init dump_machine_table(void);
+#endif /* _ASM_METAG_SETUP_H */

arch/metag/include/asm/smp.h

@@ -0,0 +1,29 @@
+#ifndef __ASM_SMP_H
+#define __ASM_SMP_H
+
+#include <linux/cpumask.h>
+
+#define raw_smp_processor_id() (current_thread_info()->cpu)
+
+enum ipi_msg_type {
+	IPI_CALL_FUNC,
+	IPI_CALL_FUNC_SINGLE,
+	IPI_RESCHEDULE,
+};
+
+extern void arch_send_call_function_single_ipi(int cpu);
+extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
+#define arch_send_call_function_ipi_mask arch_send_call_function_ipi_mask
+
+asmlinkage void secondary_start_kernel(void);
+
+extern void secondary_startup(void);
+
+#ifdef CONFIG_HOTPLUG_CPU
+extern void __cpu_die(unsigned int cpu);
+extern int __cpu_disable(void);
+extern void cpu_die(void);
+#endif
+
+extern void smp_init_cpus(void);
+#endif /* __ASM_SMP_H */

arch/metag/include/asm/sparsemem.h

@@ -0,0 +1,13 @@
+#ifndef __ASM_METAG_SPARSEMEM_H
+#define __ASM_METAG_SPARSEMEM_H
+
+/*
+ * SECTION_SIZE_BITS		2^N: how big each section will be
+ * MAX_PHYSADDR_BITS		2^N: how much physical address space we have
+ * MAX_PHYSMEM_BITS		2^N: how much memory we can have in that space
+ */
+#define SECTION_SIZE_BITS	26
+#define MAX_PHYSADDR_BITS	32
+#define MAX_PHYSMEM_BITS	32
+
+#endif /* __ASM_METAG_SPARSEMEM_H */

arch/metag/include/asm/spinlock.h

@@ -0,0 +1,22 @@
+#ifndef __ASM_SPINLOCK_H
+#define __ASM_SPINLOCK_H
+
+#ifdef CONFIG_METAG_ATOMICITY_LOCK1
+#include <asm/spinlock_lock1.h>
+#else
+#include <asm/spinlock_lnkget.h>
+#endif
+
+#define arch_spin_unlock_wait(lock) \
+	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
+
+#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
+
+#define	arch_read_lock_flags(lock, flags) arch_read_lock(lock)
+#define	arch_write_lock_flags(lock, flags) arch_write_lock(lock)
+
+#define arch_spin_relax(lock)	cpu_relax()
+#define arch_read_relax(lock)	cpu_relax()
+#define arch_write_relax(lock)	cpu_relax()
+
+#endif /* __ASM_SPINLOCK_H */

arch/metag/include/asm/spinlock_lnkget.h

@@ -0,0 +1,249 @@
+#ifndef __ASM_SPINLOCK_LNKGET_H
+#define __ASM_SPINLOCK_LNKGET_H
+
+/*
+ * None of these asm statements clobber memory as LNKSET writes around
+ * the cache so the memory it modifies cannot safely be read by any means
+ * other than these accessors.
+ */
+
+static inline int arch_spin_is_locked(arch_spinlock_t *lock)
+{
+	int ret;
+
+	asm volatile ("LNKGETD	%0, [%1]\n"
+		      "TST	%0, #1\n"
+		      "MOV	%0, #1\n"
+		      "XORZ      %0, %0, %0\n"
+		      : "=&d" (ret)
+		      : "da" (&lock->lock)
+		      : "cc");
+	return ret;
+}
+
+static inline void arch_spin_lock(arch_spinlock_t *lock)
+{
+	int tmp;
+
+	asm volatile ("1:     LNKGETD %0,[%1]\n"
+		      "       TST     %0, #1\n"
+		      "       ADD     %0, %0, #1\n"
+		      "       LNKSETDZ [%1], %0\n"
+		      "       BNZ     1b\n"
+		      "       DEFR    %0, TXSTAT\n"
+		      "       ANDT    %0, %0, #HI(0x3f000000)\n"
+		      "       CMPT    %0, #HI(0x02000000)\n"
+		      "       BNZ     1b\n"
+		      : "=&d" (tmp)
+		      : "da" (&lock->lock)
+		      : "cc");
+
+	smp_mb();
+}
+
+/* Returns 0 if failed to acquire lock */
+static inline int arch_spin_trylock(arch_spinlock_t *lock)
+{
+	int tmp;
+
+	asm volatile ("       LNKGETD %0,[%1]\n"
+		      "       TST     %0, #1\n"
+		      "       ADD     %0, %0, #1\n"
+		      "       LNKSETDZ [%1], %0\n"
+		      "       BNZ     1f\n"
+		      "       DEFR    %0, TXSTAT\n"
+		      "       ANDT    %0, %0, #HI(0x3f000000)\n"
+		      "       CMPT    %0, #HI(0x02000000)\n"
+		      "       MOV     %0, #1\n"
+		      "1:     XORNZ   %0, %0, %0\n"
+		      : "=&d" (tmp)
+		      : "da" (&lock->lock)
+		      : "cc");
+
+	smp_mb();
+
+	return tmp;
+}
+
+static inline void arch_spin_unlock(arch_spinlock_t *lock)
+{
+	smp_mb();
+
+	asm volatile ("       SETD    [%0], %1\n"
+		      :
+		      : "da" (&lock->lock), "da" (0)
+		      : "memory");
+}
+
+/*
+ * RWLOCKS
+ *
+ *
+ * Write locks are easy - we just set bit 31.  When unlocking, we can
+ * just write zero since the lock is exclusively held.
+ */
+
+static inline void arch_write_lock(arch_rwlock_t *rw)
+{
+	int tmp;
+
+	asm volatile ("1:     LNKGETD %0,[%1]\n"
+		      "       CMP     %0, #0\n"
+		      "       ADD     %0, %0, %2\n"
+		      "       LNKSETDZ [%1], %0\n"
+		      "       BNZ     1b\n"
+		      "       DEFR    %0, TXSTAT\n"
+		      "       ANDT    %0, %0, #HI(0x3f000000)\n"
+		      "       CMPT    %0, #HI(0x02000000)\n"
+		      "       BNZ     1b\n"
+		      : "=&d" (tmp)
+		      : "da" (&rw->lock), "bd" (0x80000000)
+		      : "cc");
+
+	smp_mb();
+}
+
+static inline int arch_write_trylock(arch_rwlock_t *rw)
+{
+	int tmp;
+
+	asm volatile ("       LNKGETD %0,[%1]\n"
+		      "       CMP     %0, #0\n"
+		      "       ADD     %0, %0, %2\n"
+		      "       LNKSETDZ [%1], %0\n"
+		      "       BNZ     1f\n"
+		      "       DEFR    %0, TXSTAT\n"
+		      "       ANDT    %0, %0, #HI(0x3f000000)\n"
+		      "       CMPT    %0, #HI(0x02000000)\n"
+		      "       MOV     %0,#1\n"
+		      "1:     XORNZ   %0, %0, %0\n"
+		      : "=&d" (tmp)
+		      : "da" (&rw->lock), "bd" (0x80000000)
+		      : "cc");
+
+	smp_mb();
+
+	return tmp;
+}
+
+static inline void arch_write_unlock(arch_rwlock_t *rw)
+{
+	smp_mb();
+
+	asm volatile ("       SETD    [%0], %1\n"
+		      :
+		      : "da" (&rw->lock), "da" (0)
+		      : "memory");
+}
+
+/* write_can_lock - would write_trylock() succeed? */
+static inline int arch_write_can_lock(arch_rwlock_t *rw)
+{
+	int ret;
+
+	asm volatile ("LNKGETD	%0, [%1]\n"
+		      "CMP	%0, #0\n"
+		      "MOV	%0, #1\n"
+		      "XORNZ     %0, %0, %0\n"
+		      : "=&d" (ret)
+		      : "da" (&rw->lock)
+		      : "cc");
+	return ret;
+}
+
+/*
+ * Read locks are a bit more hairy:
+ *  - Exclusively load the lock value.
+ *  - Increment it.
+ *  - Store new lock value if positive, and we still own this location.
+ *    If the value is negative, we've already failed.
+ *  - If we failed to store the value, we want a negative result.
+ *  - If we failed, try again.
+ * Unlocking is similarly hairy.  We may have multiple read locks
+ * currently active.  However, we know we won't have any write
+ * locks.
+ */
+static inline void arch_read_lock(arch_rwlock_t *rw)
+{
+	int tmp;
+
+	asm volatile ("1:     LNKGETD %0,[%1]\n"
+		      "       ADDS    %0, %0, #1\n"
+		      "       LNKSETDPL [%1], %0\n"
+		      "       BMI     1b\n"
+		      "       DEFR    %0, TXSTAT\n"
+		      "       ANDT    %0, %0, #HI(0x3f000000)\n"
+		      "       CMPT    %0, #HI(0x02000000)\n"
+		      "       BNZ     1b\n"
+		      : "=&d" (tmp)
+		      : "da" (&rw->lock)
+		      : "cc");
+
+	smp_mb();
+}
+
+static inline void arch_read_unlock(arch_rwlock_t *rw)
+{
+	int tmp;
+
+	smp_mb();
+
+	asm volatile ("1:     LNKGETD %0,[%1]\n"
+		      "       SUB     %0, %0, #1\n"
+		      "       LNKSETD [%1], %0\n"
+		      "       DEFR    %0, TXSTAT\n"
+		      "       ANDT    %0, %0, #HI(0x3f000000)\n"
+		      "       CMPT    %0, #HI(0x02000000)\n"
+		      "       BNZ     1b\n"
+		      : "=&d" (tmp)
+		      : "da" (&rw->lock)
+		      : "cc", "memory");
+}
+
+static inline int arch_read_trylock(arch_rwlock_t *rw)
+{
+	int tmp;
+
+	asm volatile ("       LNKGETD %0,[%1]\n"
+		      "       ADDS    %0, %0, #1\n"
+		      "       LNKSETDPL [%1], %0\n"
+		      "       BMI     1f\n"
+		      "       DEFR    %0, TXSTAT\n"
+		      "       ANDT    %0, %0, #HI(0x3f000000)\n"
+		      "       CMPT    %0, #HI(0x02000000)\n"
+		      "       MOV     %0,#1\n"
+		      "       BZ      2f\n"
+		      "1:     MOV     %0,#0\n"
+		      "2:\n"
+		      : "=&d" (tmp)
+		      : "da" (&rw->lock)
+		      : "cc");
+
+	smp_mb();
+
+	return tmp;
+}
+
+/* read_can_lock - would read_trylock() succeed? */
+static inline int arch_read_can_lock(arch_rwlock_t *rw)
+{
+	int tmp;
+
+	asm volatile ("LNKGETD	%0, [%1]\n"
+		      "CMP	%0, %2\n"
+		      "MOV	%0, #1\n"
+		      "XORZ	%0, %0, %0\n"
+		      : "=&d" (tmp)
+		      : "da" (&rw->lock), "bd" (0x80000000)
+		      : "cc");
+	return tmp;
+}
+
+#define	arch_read_lock_flags(lock, flags) arch_read_lock(lock)
+#define	arch_write_lock_flags(lock, flags) arch_write_lock(lock)
+
+#define arch_spin_relax(lock)	cpu_relax()
+#define arch_read_relax(lock)	cpu_relax()
+#define arch_write_relax(lock)	cpu_relax()
+
+#endif /* __ASM_SPINLOCK_LNKGET_H */

arch/metag/include/asm/spinlock_lock1.h

@@ -0,0 +1,184 @@
+#ifndef __ASM_SPINLOCK_LOCK1_H
+#define __ASM_SPINLOCK_LOCK1_H
+
+#include <asm/bug.h>
+#include <asm/global_lock.h>
+
+static inline int arch_spin_is_locked(arch_spinlock_t *lock)
+{
+	int ret;
+
+	barrier();
+	ret = lock->lock;
+	WARN_ON(ret != 0 && ret != 1);
+	return ret;
+}
+
+static inline void arch_spin_lock(arch_spinlock_t *lock)
+{
+	unsigned int we_won = 0;
+	unsigned long flags;
+
+again:
+	__global_lock1(flags);
+	if (lock->lock == 0) {
+		fence();
+		lock->lock = 1;
+		we_won = 1;
+	}
+	__global_unlock1(flags);
+	if (we_won == 0)
+		goto again;
+	WARN_ON(lock->lock != 1);
+}
+
+/* Returns 0 if failed to acquire lock */
+static inline int arch_spin_trylock(arch_spinlock_t *lock)
+{
+	unsigned long flags;
+	unsigned int ret;
+
+	__global_lock1(flags);
+	ret = lock->lock;
+	if (ret == 0) {
+		fence();
+		lock->lock = 1;
+	}
+	__global_unlock1(flags);
+	return (ret == 0);
+}
+
+static inline void arch_spin_unlock(arch_spinlock_t *lock)
+{
+	barrier();
+	WARN_ON(!lock->lock);
+	lock->lock = 0;
+}
+
+/*
+ * RWLOCKS
+ *
+ *
+ * Write locks are easy - we just set bit 31.  When unlocking, we can
+ * just write zero since the lock is exclusively held.
+ */
+
+static inline void arch_write_lock(arch_rwlock_t *rw)
+{
+	unsigned long flags;
+	unsigned int we_won = 0;
+
+again:
+	__global_lock1(flags);
+	if (rw->lock == 0) {
+		fence();
+		rw->lock = 0x80000000;
+		we_won = 1;
+	}
+	__global_unlock1(flags);
+	if (we_won == 0)
+		goto again;
+	WARN_ON(rw->lock != 0x80000000);
+}
+
+static inline int arch_write_trylock(arch_rwlock_t *rw)
+{
+	unsigned long flags;
+	unsigned int ret;
+
+	__global_lock1(flags);
+	ret = rw->lock;
+	if (ret == 0) {
+		fence();
+		rw->lock = 0x80000000;
+	}
+	__global_unlock1(flags);
+
+	return (ret == 0);
+}
+
+static inline void arch_write_unlock(arch_rwlock_t *rw)
+{
+	barrier();
+	WARN_ON(rw->lock != 0x80000000);
+	rw->lock = 0;
+}
+
+/* write_can_lock - would write_trylock() succeed? */
+static inline int arch_write_can_lock(arch_rwlock_t *rw)
+{
+	unsigned int ret;
+
+	barrier();
+	ret = rw->lock;
+	return (ret == 0);
+}
+
+/*
+ * Read locks are a bit more hairy:
+ *  - Exclusively load the lock value.
+ *  - Increment it.
+ *  - Store new lock value if positive, and we still own this location.
+ *    If the value is negative, we've already failed.
+ *  - If we failed to store the value, we want a negative result.
+ *  - If we failed, try again.
+ * Unlocking is similarly hairy.  We may have multiple read locks
+ * currently active.  However, we know we won't have any write
+ * locks.
+ */
+static inline void arch_read_lock(arch_rwlock_t *rw)
+{
+	unsigned long flags;
+	unsigned int we_won = 0, ret;
+
+again:
+	__global_lock1(flags);
+	ret = rw->lock;
+	if (ret < 0x80000000) {
+		fence();
+		rw->lock = ret + 1;
+		we_won = 1;
+	}
+	__global_unlock1(flags);
+	if (!we_won)
+		goto again;
+}
+
+static inline void arch_read_unlock(arch_rwlock_t *rw)
+{
+	unsigned long flags;
+	unsigned int ret;
+
+	__global_lock1(flags);
+	fence();
+	ret = rw->lock--;
+	__global_unlock1(flags);
+	WARN_ON(ret == 0);
+}
+
+static inline int arch_read_trylock(arch_rwlock_t *rw)
+{
+	unsigned long flags;
+	unsigned int ret;
+
+	__global_lock1(flags);
+	ret = rw->lock;
+	if (ret < 0x80000000) {
+		fence();
+		rw->lock = ret + 1;
+	}
+	__global_unlock1(flags);
+	return (ret < 0x80000000);
+}
+
+/* read_can_lock - would read_trylock() succeed? */
+static inline int arch_read_can_lock(arch_rwlock_t *rw)
+{
+	unsigned int ret;
+
+	barrier();
+	ret = rw->lock;
+	return (ret < 0x80000000);
+}
+
+#endif /* __ASM_SPINLOCK_LOCK1_H */

arch/metag/include/asm/spinlock_types.h

@@ -0,0 +1,20 @@
+#ifndef _ASM_METAG_SPINLOCK_TYPES_H
+#define _ASM_METAG_SPINLOCK_TYPES_H
+
+#ifndef __LINUX_SPINLOCK_TYPES_H
+# error "please don't include this file directly"
+#endif
+
+typedef struct {
+	volatile unsigned int lock;
+} arch_spinlock_t;
+
+#define __ARCH_SPIN_LOCK_UNLOCKED	{ 0 }
+
+typedef struct {
+	volatile unsigned int lock;
+} arch_rwlock_t;
+
+#define __ARCH_RW_LOCK_UNLOCKED		{ 0 }
+
+#endif /* _ASM_METAG_SPINLOCK_TYPES_H */

arch/metag/include/asm/stacktrace.h

@@ -0,0 +1,20 @@
+#ifndef __ASM_STACKTRACE_H
+#define __ASM_STACKTRACE_H
+
+struct stackframe {
+	unsigned long fp;
+	unsigned long sp;
+	unsigned long lr;
+	unsigned long pc;
+};
+
+struct metag_frame {
+	unsigned long fp;
+	unsigned long lr;
+};
+
+extern int unwind_frame(struct stackframe *frame);
+extern void walk_stackframe(struct stackframe *frame,
+			    int (*fn)(struct stackframe *, void *), void *data);
+
+#endif	/* __ASM_STACKTRACE_H */

arch/metag/include/asm/string.h

@@ -0,0 +1,13 @@
+#ifndef _METAG_STRING_H_
+#define _METAG_STRING_H_
+
+#define __HAVE_ARCH_MEMSET
+extern void *memset(void *__s, int __c, size_t __count);
+
+#define __HAVE_ARCH_MEMCPY
+void *memcpy(void *__to, __const__ void *__from, size_t __n);
+
+#define __HAVE_ARCH_MEMMOVE
+extern void *memmove(void *__dest, __const__ void *__src, size_t __n);
+
+#endif /* _METAG_STRING_H_ */

arch/metag/include/asm/switch.h

@@ -0,0 +1,21 @@
+/*
+ * Copyright (C) 2012 Imagination Technologies Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef _ASM_METAG_SWITCH_H
+#define _ASM_METAG_SWITCH_H
+
+/* metag SWITCH codes */
+#define __METAG_SW_PERM_BREAK	0x400002	/* compiled in breakpoint */
+#define __METAG_SW_SYS_LEGACY	0x440000	/* legacy system calls */
+#define __METAG_SW_SYS		0x440001	/* system calls */
+
+/* metag SWITCH instruction encoding */
+#define __METAG_SW_ENCODING(TYPE)	(0xaf000000 | (__METAG_SW_##TYPE))
+
+#endif /* _ASM_METAG_SWITCH_H */

arch/metag/include/asm/syscall.h

@@ -0,0 +1,104 @@
+/*
+ * Access to user system call parameters and results
+ *
+ * Copyright (C) 2008 Imagination Technologies Ltd.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License v.2.
+ *
+ * See asm-generic/syscall.h for descriptions of what we must do here.
+ */
+
+#ifndef _ASM_METAG_SYSCALL_H
+#define _ASM_METAG_SYSCALL_H
+
+#include <linux/sched.h>
+#include <linux/err.h>
+#include <linux/uaccess.h>
+
+#include <asm/switch.h>
+
+static inline long syscall_get_nr(struct task_struct *task,
+				  struct pt_regs *regs)
+{
+	unsigned long insn;
+
+	/*
+	 * FIXME there's no way to find out how we got here other than to
+	 * examine the memory at the PC to see if it is a syscall
+	 * SWITCH instruction.
+	 */
+	if (get_user(insn, (unsigned long *)(regs->ctx.CurrPC - 4)))
+		return -1;
+
+	if (insn == __METAG_SW_ENCODING(SYS))
+		return regs->ctx.DX[0].U1;
+	else
+		return -1L;
+}
+
+static inline void syscall_rollback(struct task_struct *task,
+				    struct pt_regs *regs)
+{
+	/* do nothing */
+}
+
+static inline long syscall_get_error(struct task_struct *task,
+				     struct pt_regs *regs)
+{
+	unsigned long error = regs->ctx.DX[0].U0;
+	return IS_ERR_VALUE(error) ? error : 0;
+}
+
+static inline long syscall_get_return_value(struct task_struct *task,
+					    struct pt_regs *regs)
+{
+	return regs->ctx.DX[0].U0;
+}
+
+static inline void syscall_set_return_value(struct task_struct *task,
+					    struct pt_regs *regs,
+					    int error, long val)
+{
+	regs->ctx.DX[0].U0 = (long) error ?: val;
+}
+
+static inline void syscall_get_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 unsigned long *args)
+{
+	unsigned int reg, j;
+	BUG_ON(i + n > 6);
+
+	for (j = i, reg = 6 - i; j < (i + n); j++, reg--) {
+		if (reg % 2)
+			args[j] = regs->ctx.DX[(reg + 1) / 2].U0;
+		else
+			args[j] = regs->ctx.DX[reg / 2].U1;
+	}
+}
+
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 const unsigned long *args)
+{
+	unsigned int reg;
+	BUG_ON(i + n > 6);
+
+	for (reg = 6 - i; i < (i + n); i++, reg--) {
+		if (reg % 2)
+			regs->ctx.DX[(reg + 1) / 2].U0 = args[i];
+		else
+			regs->ctx.DX[reg / 2].U1 = args[i];
+	}
+}
+
+#define NR_syscalls __NR_syscalls
+
+/* generic syscall table */
+extern const void *sys_call_table[];
+
+#endif	/* _ASM_METAG_SYSCALL_H */

arch/metag/include/asm/syscalls.h

@@ -0,0 +1,39 @@
+#ifndef _ASM_METAG_SYSCALLS_H
+#define _ASM_METAG_SYSCALLS_H
+
+#include <linux/compiler.h>
+#include <linux/linkage.h>
+#include <linux/types.h>
+#include <linux/signal.h>
+
+/* kernel/signal.c */
+#define sys_rt_sigreturn sys_rt_sigreturn
+asmlinkage long sys_rt_sigreturn(void);
+
+#include <asm-generic/syscalls.h>
+
+/* kernel/sys_metag.c */
+asmlinkage int sys_metag_setglobalbit(char __user *, int);
+asmlinkage void sys_metag_set_fpu_flags(unsigned int);
+asmlinkage int sys_metag_set_tls(void __user *);
+asmlinkage void *sys_metag_get_tls(void);
+
+asmlinkage long sys_truncate64_metag(const char __user *, unsigned long,
+				     unsigned long);
+asmlinkage long sys_ftruncate64_metag(unsigned int, unsigned long,
+				      unsigned long);
+asmlinkage long sys_fadvise64_64_metag(int, unsigned long, unsigned long,
+				       unsigned long, unsigned long, int);
+asmlinkage long sys_readahead_metag(int, unsigned long, unsigned long, size_t);
+asmlinkage ssize_t sys_pread64_metag(unsigned long, char __user *, size_t,
+				     unsigned long, unsigned long);
+asmlinkage ssize_t sys_pwrite64_metag(unsigned long, char __user *, size_t,
+				      unsigned long, unsigned long);
+asmlinkage long sys_sync_file_range_metag(int, unsigned long, unsigned long,
+					  unsigned long, unsigned long,
+					  unsigned int);
+
+int do_work_pending(struct pt_regs *regs, unsigned int thread_flags,
+		    int syscall);
+
+#endif /* _ASM_METAG_SYSCALLS_H */

arch/metag/include/asm/tcm.h

@@ -0,0 +1,30 @@
+#ifndef __ASM_TCM_H__
+#define __ASM_TCM_H__
+
+#include <linux/ioport.h>
+#include <linux/list.h>
+
+struct tcm_allocation {
+	struct list_head list;
+	unsigned int tag;
+	unsigned long addr;
+	unsigned long size;
+};
+
+/*
+ * TCM memory region descriptor.
+ */
+struct tcm_region {
+	unsigned int tag;
+	struct resource res;
+};
+
+#define TCM_INVALID_TAG	0xffffffff
+
+unsigned long tcm_alloc(unsigned int tag, size_t len);
+void tcm_free(unsigned int tag, unsigned long addr, size_t len);
+unsigned int tcm_lookup_tag(unsigned long p);
+
+int tcm_add_region(struct tcm_region *reg);
+
+#endif

arch/metag/include/asm/thread_info.h

@@ -0,0 +1,155 @@
+/* thread_info.h: Meta low-level thread information
+ *
+ * Copyright (C) 2002  David Howells (dhowells@redhat.com)
+ * - Incorporating suggestions made by Linus Torvalds and Dave Miller
+ *
+ * Meta port by Imagination Technologies
+ */
+
+#ifndef _ASM_THREAD_INFO_H
+#define _ASM_THREAD_INFO_H
+
+#include <linux/compiler.h>
+#include <asm/page.h>
+
+#ifndef __ASSEMBLY__
+#include <asm/processor.h>
+#endif
+
+/*
+ * low level task data that entry.S needs immediate access to
+ * - this struct should fit entirely inside of one cache line
+ * - this struct shares the supervisor stack pages
+ * - if the contents of this structure are changed, the assembly constants must
+ *   also be changed
+ */
+#ifndef __ASSEMBLY__
+
+/* This must be 8 byte aligned so we can ensure stack alignment. */
+struct thread_info {
+	struct task_struct *task;	/* main task structure */
+	struct exec_domain *exec_domain;	/* execution domain */
+	unsigned long flags;	/* low level flags */
+	unsigned long status;	/* thread-synchronous flags */
+	u32 cpu;		/* current CPU */
+	int preempt_count;	/* 0 => preemptable, <0 => BUG */
+
+	mm_segment_t addr_limit;	/* thread address space */
+	struct restart_block restart_block;
+
+	u8 supervisor_stack[0];
+};
+
+#else /* !__ASSEMBLY__ */
+
+#include <generated/asm-offsets.h>
+
+#endif
+
+#define PREEMPT_ACTIVE		0x10000000
+
+#ifdef CONFIG_4KSTACKS
+#define THREAD_SHIFT		12
+#else
+#define THREAD_SHIFT		13
+#endif
+
+#if THREAD_SHIFT >= PAGE_SHIFT
+#define THREAD_SIZE_ORDER	(THREAD_SHIFT - PAGE_SHIFT)
+#else
+#define THREAD_SIZE_ORDER	0
+#endif
+
+#define THREAD_SIZE		(PAGE_SIZE << THREAD_SIZE_ORDER)
+
+#define STACK_WARN		(THREAD_SIZE/8)
+/*
+ * macros/functions for gaining access to the thread information structure
+ */
+#ifndef __ASSEMBLY__
+
+#define INIT_THREAD_INFO(tsk)			\
+{						\
+	.task		= &tsk,			\
+	.exec_domain	= &default_exec_domain,	\
+	.flags		= 0,			\
+	.cpu		= 0,			\
+	.preempt_count	= INIT_PREEMPT_COUNT,	\
+	.addr_limit	= KERNEL_DS,		\
+	.restart_block = {			\
+		.fn = do_no_restart_syscall,	\
+	},					\
+}
+
+#define init_thread_info	(init_thread_union.thread_info)
+#define init_stack		(init_thread_union.stack)
+
+/* how to get the current stack pointer from C */
+register unsigned long current_stack_pointer asm("A0StP") __used;
+
+/* how to get the thread information struct from C */
+static inline struct thread_info *current_thread_info(void)
+{
+	return (struct thread_info *)(current_stack_pointer &
+				      ~(THREAD_SIZE - 1));
+}
+
+#define __HAVE_ARCH_KSTACK_END
+static inline int kstack_end(void *addr)
+{
+	return addr == (void *) (((unsigned long) addr & ~(THREAD_SIZE - 1))
+				 + sizeof(struct thread_info));
+}
+
+#endif
+
+/*
+ * thread information flags
+ * - these are process state flags that various assembly files may need to
+ *   access
+ * - pending work-to-be-done flags are in LSW
+ * - other flags in MSW
+ */
+#define TIF_SYSCALL_TRACE	0	/* syscall trace active */
+#define TIF_SIGPENDING		1	/* signal pending */
+#define TIF_NEED_RESCHED	2	/* rescheduling necessary */
+#define TIF_SINGLESTEP		3	/* restore singlestep on return to user
+					   mode */
+#define TIF_SYSCALL_AUDIT	4	/* syscall auditing active */
+#define TIF_SECCOMP		5	/* secure computing */
+#define TIF_RESTORE_SIGMASK	6	/* restore signal mask in do_signal() */
+#define TIF_NOTIFY_RESUME	7	/* callback before returning to user */
+#define TIF_POLLING_NRFLAG      8	/* true if poll_idle() is polling
+					   TIF_NEED_RESCHED */
+#define TIF_MEMDIE		9	/* is terminating due to OOM killer */
+#define TIF_SYSCALL_TRACEPOINT  10	/* syscall tracepoint instrumentation */
+
+
+#define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
+#define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
+#define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
+#define _TIF_SINGLESTEP		(1<<TIF_SINGLESTEP)
+#define _TIF_SYSCALL_AUDIT	(1<<TIF_SYSCALL_AUDIT)
+#define _TIF_SECCOMP		(1<<TIF_SECCOMP)
+#define _TIF_NOTIFY_RESUME	(1<<TIF_NOTIFY_RESUME)
+#define _TIF_RESTORE_SIGMASK	(1<<TIF_RESTORE_SIGMASK)
+#define _TIF_SYSCALL_TRACEPOINT	(1<<TIF_SYSCALL_TRACEPOINT)
+
+/* work to do in syscall trace */
+#define _TIF_WORK_SYSCALL_MASK	(_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP | \
+				 _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
+				 _TIF_SYSCALL_TRACEPOINT)
+
+/* work to do on any return to u-space */
+#define _TIF_ALLWORK_MASK	(_TIF_SYSCALL_TRACE | _TIF_SIGPENDING      | \
+				 _TIF_NEED_RESCHED  | _TIF_SYSCALL_AUDIT   | \
+				 _TIF_SINGLESTEP    | _TIF_RESTORE_SIGMASK | \
+				 _TIF_NOTIFY_RESUME)
+
+/* work to do on interrupt/exception return */
+#define _TIF_WORK_MASK		(_TIF_ALLWORK_MASK & ~(_TIF_SYSCALL_TRACE | \
+				 _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP))
+
+#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
+
+#endif /* _ASM_THREAD_INFO_H */

arch/metag/include/asm/tlb.h

@@ -0,0 +1,36 @@
+#ifndef __ASM_METAG_TLB_H
+#define __ASM_METAG_TLB_H
+
+#include <asm/cacheflush.h>
+#include <asm/page.h>
+
+/* Note, read http://lkml.org/lkml/2004/1/15/6 */
+
+#ifdef CONFIG_METAG_META12
+
+#define tlb_start_vma(tlb, vma)						      \
+	do {								      \
+		if (!tlb->fullmm)					      \
+			flush_cache_range(vma, vma->vm_start, vma->vm_end);   \
+	} while (0)
+
+#define tlb_end_vma(tlb, vma)						      \
+	do {								      \
+		if (!tlb->fullmm)					      \
+			flush_tlb_range(vma, vma->vm_start, vma->vm_end);     \
+	} while (0)
+
+
+#else
+
+#define tlb_start_vma(tlb, vma)			do { } while (0)
+#define tlb_end_vma(tlb, vma)			do { } while (0)
+
+#endif
+
+#define __tlb_remove_tlb_entry(tlb, pte, addr)	do { } while (0)
+#define tlb_flush(tlb)				flush_tlb_mm((tlb)->mm)
+
+#include <asm-generic/tlb.h>
+
+#endif

arch/metag/include/asm/tlbflush.h

@@ -0,0 +1,77 @@
+#ifndef __ASM_METAG_TLBFLUSH_H
+#define __ASM_METAG_TLBFLUSH_H
+
+#include <linux/io.h>
+#include <linux/sched.h>
+#include <asm/metag_mem.h>
+#include <asm/pgalloc.h>
+
+/*
+ * TLB flushing:
+ *
+ *  - flush_tlb() flushes the current mm struct TLBs
+ *  - flush_tlb_all() flushes all processes TLBs
+ *  - flush_tlb_mm(mm) flushes the specified mm context TLB's
+ *  - flush_tlb_page(vma, vmaddr) flushes one page
+ *  - flush_tlb_range(mm, start, end) flushes a range of pages
+ *  - flush_tlb_kernel_range(start, end) flushes a range of kernel pages
+ *  - flush_tlb_pgtables(mm, start, end) flushes a range of page tables
+ *
+ * FIXME: Meta 2 can flush single TLB entries.
+ *
+ */
+
+#if defined(CONFIG_METAG_META21) && !defined(CONFIG_SMP)
+static inline void __flush_tlb(void)
+{
+	/* flush TLB entries for just the current hardware thread */
+	int thread = hard_processor_id();
+	metag_out32(0, (LINSYSCFLUSH_TxMMCU_BASE +
+			LINSYSCFLUSH_TxMMCU_STRIDE * thread));
+}
+#else
+static inline void __flush_tlb(void)
+{
+	/* flush TLB entries for all hardware threads */
+	metag_out32(0, LINSYSCFLUSH_MMCU);
+}
+#endif /* defined(CONFIG_METAG_META21) && !defined(CONFIG_SMP) */
+
+#define flush_tlb() __flush_tlb()
+
+#define flush_tlb_all() __flush_tlb()
+
+#define local_flush_tlb_all() __flush_tlb()
+
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+	if (mm == current->active_mm)
+		__flush_tlb();
+}
+
+static inline void flush_tlb_page(struct vm_area_struct *vma,
+				  unsigned long addr)
+{
+	flush_tlb_mm(vma->vm_mm);
+}
+
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+				   unsigned long start, unsigned long end)
+{
+	flush_tlb_mm(vma->vm_mm);
+}
+
+static inline void flush_tlb_pgtables(struct mm_struct *mm,
+				      unsigned long start, unsigned long end)
+{
+	flush_tlb_mm(mm);
+}
+
+static inline void flush_tlb_kernel_range(unsigned long start,
+					  unsigned long end)
+{
+	flush_tlb_all();
+}
+
+#endif /* __ASM_METAG_TLBFLUSH_H */
+

arch/metag/include/asm/topology.h

@@ -0,0 +1,53 @@
+#ifndef _ASM_METAG_TOPOLOGY_H
+#define _ASM_METAG_TOPOLOGY_H
+
+#ifdef CONFIG_NUMA
+
+/* sched_domains SD_NODE_INIT for Meta machines */
+#define SD_NODE_INIT (struct sched_domain) {		\
+	.parent			= NULL,			\
+	.child			= NULL,			\
+	.groups			= NULL,			\
+	.min_interval		= 8,			\
+	.max_interval		= 32,			\
+	.busy_factor		= 32,			\
+	.imbalance_pct		= 125,			\
+	.cache_nice_tries	= 2,			\
+	.busy_idx		= 3,			\
+	.idle_idx		= 2,			\
+	.newidle_idx		= 0,			\
+	.wake_idx		= 0,			\
+	.forkexec_idx		= 0,			\
+	.flags			= SD_LOAD_BALANCE	\
+				| SD_BALANCE_FORK	\
+				| SD_BALANCE_EXEC	\
+				| SD_BALANCE_NEWIDLE	\
+				| SD_SERIALIZE,		\
+	.last_balance		= jiffies,		\
+	.balance_interval	= 1,			\
+	.nr_balance_failed	= 0,			\
+}
+
+#define cpu_to_node(cpu)	((void)(cpu), 0)
+#define parent_node(node)	((void)(node), 0)
+
+#define cpumask_of_node(node)	((void)node, cpu_online_mask)
+
+#define pcibus_to_node(bus)	((void)(bus), -1)
+#define cpumask_of_pcibus(bus)	(pcibus_to_node(bus) == -1 ? \
+					cpu_all_mask : \
+					cpumask_of_node(pcibus_to_node(bus)))
+
+#endif
+
+#define mc_capable()    (1)
+
+const struct cpumask *cpu_coregroup_mask(unsigned int cpu);
+
+extern cpumask_t cpu_core_map[NR_CPUS];
+
+#define topology_core_cpumask(cpu)	(&cpu_core_map[cpu])
+
+#include <asm-generic/topology.h>
+
+#endif /* _ASM_METAG_TOPOLOGY_H */

arch/metag/include/asm/traps.h

@@ -0,0 +1,48 @@
+/*
+ *  Copyright (C) 2005,2008 Imagination Technologies
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file COPYING in the main directory of this archive
+ * for more details.
+ */
+
+#ifndef _METAG_TBIVECTORS_H
+#define _METAG_TBIVECTORS_H
+
+#ifndef __ASSEMBLY__
+
+#include <asm/tbx.h>
+
+typedef TBIRES (*kick_irq_func_t)(TBIRES, int, int, int, PTBI, int *);
+
+extern TBIRES kick_handler(TBIRES, int, int, int, PTBI);
+struct kick_irq_handler {
+	struct list_head list;
+	kick_irq_func_t func;
+};
+
+extern void kick_register_func(struct kick_irq_handler *);
+extern void kick_unregister_func(struct kick_irq_handler *);
+
+extern void head_end(TBIRES, unsigned long);
+extern void restart_critical_section(TBIRES State);
+extern TBIRES tail_end_sys(TBIRES, int, int *);
+static inline TBIRES tail_end(TBIRES state)
+{
+	return tail_end_sys(state, -1, NULL);
+}
+
+DECLARE_PER_CPU(PTBI, pTBI);
+extern PTBI pTBI_get(unsigned int);
+
+extern int ret_from_fork(TBIRES arg);
+
+extern int do_page_fault(struct pt_regs *regs, unsigned long address,
+			 unsigned int write_access, unsigned int trapno);
+
+extern TBIRES __TBIUnExpXXX(TBIRES State, int SigNum, int Triggers, int Inst,
+			    PTBI pTBI);
+
+#endif
+
+#endif /* _METAG_TBIVECTORS_H */

arch/metag/include/asm/uaccess.h

@@ -0,0 +1,241 @@
+#ifndef __METAG_UACCESS_H
+#define __METAG_UACCESS_H
+
+/*
+ * User space memory access functions
+ */
+#include <linux/sched.h>
+
+#define VERIFY_READ	0
+#define VERIFY_WRITE	1
+
+/*
+ * The fs value determines whether argument validity checking should be
+ * performed or not.  If get_fs() == USER_DS, checking is performed, with
+ * get_fs() == KERNEL_DS, checking is bypassed.
+ *
+ * For historical reasons, these macros are grossly misnamed.
+ */
+
+#define MAKE_MM_SEG(s)  ((mm_segment_t) { (s) })
+
+#define KERNEL_DS       MAKE_MM_SEG(0xFFFFFFFF)
+#define USER_DS		MAKE_MM_SEG(PAGE_OFFSET)
+
+#define get_ds()	(KERNEL_DS)
+#define get_fs()        (current_thread_info()->addr_limit)
+#define set_fs(x)       (current_thread_info()->addr_limit = (x))
+
+#define segment_eq(a, b)	((a).seg == (b).seg)
+
+#define __kernel_ok (segment_eq(get_fs(), KERNEL_DS))
+/*
+ * Explicitly allow NULL pointers here. Parts of the kernel such
+ * as readv/writev use access_ok to validate pointers, but want
+ * to allow NULL pointers for various reasons. NULL pointers are
+ * safe to allow through because the first page is not mappable on
+ * Meta.
+ *
+ * We also wish to avoid letting user code access the system area
+ * and the kernel half of the address space.
+ */
+#define __user_bad(addr, size) (((addr) > 0 && (addr) < META_MEMORY_BASE) || \
+				((addr) > PAGE_OFFSET &&		\
+				 (addr) < LINCORE_BASE))
+
+static inline int __access_ok(unsigned long addr, unsigned long size)
+{
+	return __kernel_ok || !__user_bad(addr, size);
+}
+
+#define access_ok(type, addr, size) __access_ok((unsigned long)(addr),	\
+						(unsigned long)(size))
+
+static inline int verify_area(int type, const void *addr, unsigned long size)
+{
+	return access_ok(type, addr, size) ? 0 : -EFAULT;
+}
+
+/*
+ * The exception table consists of pairs of addresses: the first is the
+ * address of an instruction that is allowed to fault, and the second is
+ * the address at which the program should continue.  No registers are
+ * modified, so it is entirely up to the continuation code to figure out
+ * what to do.
+ *
+ * All the routines below use bits of fixup code that are out of line
+ * with the main instruction path.  This means when everything is well,
+ * we don't even have to jump over them.  Further, they do not intrude
+ * on our cache or tlb entries.
+ */
+struct exception_table_entry {
+	unsigned long insn, fixup;
+};
+
+extern int fixup_exception(struct pt_regs *regs);
+
+/*
+ * These are the main single-value transfer routines.  They automatically
+ * use the right size if we just have the right pointer type.
+ */
+
+#define put_user(x, ptr) \
+	__put_user_check((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
+#define __put_user(x, ptr) \
+	__put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
+
+extern void __put_user_bad(void);
+
+#define __put_user_nocheck(x, ptr, size)		\
+({                                                      \
+	long __pu_err;                                  \
+	__put_user_size((x), (ptr), (size), __pu_err);	\
+	__pu_err;                                       \
+})
+
+#define __put_user_check(x, ptr, size)				\
+({                                                              \
+	long __pu_err = -EFAULT;                                \
+	__typeof__(*(ptr)) __user *__pu_addr = (ptr);           \
+	if (access_ok(VERIFY_WRITE, __pu_addr, size))		\
+		__put_user_size((x), __pu_addr, (size), __pu_err);	\
+	__pu_err;                                               \
+})
+
+extern long __put_user_asm_b(unsigned int x, void __user *addr);
+extern long __put_user_asm_w(unsigned int x, void __user *addr);
+extern long __put_user_asm_d(unsigned int x, void __user *addr);
+extern long __put_user_asm_l(unsigned long long x, void __user *addr);
+
+#define __put_user_size(x, ptr, size, retval)			\
+do {                                                            \
+	retval = 0;                                             \
+	switch (size) {                                         \
+	case 1:								\
+		retval = __put_user_asm_b((unsigned int)x, ptr); break;	\
+	case 2:								\
+		retval = __put_user_asm_w((unsigned int)x, ptr); break;	\
+	case 4:								\
+		retval = __put_user_asm_d((unsigned int)x, ptr); break;	\
+	case 8:								\
+		retval = __put_user_asm_l((unsigned long long)x, ptr); break; \
+	default:							\
+		__put_user_bad();					\
+	}								\
+} while (0)
+
+#define get_user(x, ptr) \
+	__get_user_check((x), (ptr), sizeof(*(ptr)))
+#define __get_user(x, ptr) \
+	__get_user_nocheck((x), (ptr), sizeof(*(ptr)))
+
+extern long __get_user_bad(void);
+
+#define __get_user_nocheck(x, ptr, size)			\
+({                                                              \
+	long __gu_err, __gu_val;                                \
+	__get_user_size(__gu_val, (ptr), (size), __gu_err);	\
+	(x) = (__typeof__(*(ptr)))__gu_val;                     \
+	__gu_err;                                               \
+})
+
+#define __get_user_check(x, ptr, size)					\
+({                                                                      \
+	long __gu_err = -EFAULT, __gu_val = 0;                          \
+	const __typeof__(*(ptr)) __user *__gu_addr = (ptr);		\
+	if (access_ok(VERIFY_READ, __gu_addr, size))			\
+		__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
+	(x) = (__typeof__(*(ptr)))__gu_val;                             \
+	__gu_err;                                                       \
+})
+
+extern unsigned char __get_user_asm_b(const void __user *addr, long *err);
+extern unsigned short __get_user_asm_w(const void __user *addr, long *err);
+extern unsigned int __get_user_asm_d(const void __user *addr, long *err);
+
+#define __get_user_size(x, ptr, size, retval)			\
+do {                                                            \
+	retval = 0;                                             \
+	switch (size) {                                         \
+	case 1:							\
+		x = __get_user_asm_b(ptr, &retval); break;	\
+	case 2:							\
+		x = __get_user_asm_w(ptr, &retval); break;	\
+	case 4:							\
+		x = __get_user_asm_d(ptr, &retval); break;	\
+	default:						\
+		(x) = __get_user_bad();				\
+	}                                                       \
+} while (0)
+
+/*
+ * Copy a null terminated string from userspace.
+ *
+ * Must return:
+ * -EFAULT		for an exception
+ * count		if we hit the buffer limit
+ * bytes copied		if we hit a null byte
+ * (without the null byte)
+ */
+
+extern long __must_check __strncpy_from_user(char *dst, const char __user *src,
+					     long count);
+
+#define strncpy_from_user(dst, src, count) __strncpy_from_user(dst, src, count)
+
+/*
+ * Return the size of a string (including the ending 0)
+ *
+ * Return 0 on exception, a value greater than N if too long
+ */
+extern long __must_check strnlen_user(const char __user *src, long count);
+
+#define strlen_user(str) strnlen_user(str, 32767)
+
+extern unsigned long __must_check __copy_user_zeroing(void *to,
+						      const void __user *from,
+						      unsigned long n);
+
+static inline unsigned long
+copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	if (access_ok(VERIFY_READ, from, n))
+		return __copy_user_zeroing(to, from, n);
+	return n;
+}
+
+#define __copy_from_user(to, from, n) __copy_user_zeroing(to, from, n)
+#define __copy_from_user_inatomic __copy_from_user
+
+extern unsigned long __must_check __copy_user(void __user *to,
+					      const void *from,
+					      unsigned long n);
+
+static inline unsigned long copy_to_user(void __user *to, const void *from,
+					 unsigned long n)
+{
+	if (access_ok(VERIFY_WRITE, to, n))
+		return __copy_user(to, from, n);
+	return n;
+}
+
+#define __copy_to_user(to, from, n) __copy_user(to, from, n)
+#define __copy_to_user_inatomic __copy_to_user
+
+/*
+ * Zero Userspace
+ */
+
+extern unsigned long __must_check __do_clear_user(void __user *to,
+						  unsigned long n);
+
+static inline unsigned long clear_user(void __user *to, unsigned long n)
+{
+	if (access_ok(VERIFY_WRITE, to, n))
+		return __do_clear_user(to, n);
+	return n;
+}
+
+#define __clear_user(to, n)            __do_clear_user(to, n)
+
+#endif /* _METAG_UACCESS_H */

arch/metag/include/asm/unistd.h

@@ -0,0 +1,12 @@
+/*
+ * Copyright (C) 2012 Imagination Technologies Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <uapi/asm/unistd.h>
+
+#define __ARCH_WANT_SYS_CLONE

arch/metag/include/asm/user_gateway.h

@@ -0,0 +1,44 @@
+/*
+ * Copyright (C) 2010 Imagination Technologies
+ */
+
+#ifndef __ASM_METAG_USER_GATEWAY_H
+#define __ASM_METAG_USER_GATEWAY_H
+
+#include <asm/page.h>
+
+/* Page of kernel code accessible to userspace. */
+#define USER_GATEWAY_PAGE	0x6ffff000
+/* Offset of TLS pointer array in gateway page. */
+#define USER_GATEWAY_TLS	0x100
+
+#ifndef __ASSEMBLY__
+
+extern char __user_gateway_start;
+extern char __user_gateway_end;
+
+/* Kernel mapping of the gateway page. */
+extern void *gateway_page;
+
+static inline void set_gateway_tls(void __user *tls_ptr)
+{
+	void **gateway_tls = (void **)(gateway_page + USER_GATEWAY_TLS +
+				       hard_processor_id() * 4);
+
+	*gateway_tls = (__force void *)tls_ptr;
+#ifdef CONFIG_METAG_META12
+	/* Avoid cache aliases on virtually tagged cache. */
+	__builtin_dcache_flush((void *)USER_GATEWAY_PAGE + USER_GATEWAY_TLS +
+				       hard_processor_id() * sizeof(void *));
+#endif
+}
+
+extern int __kuser_get_tls(void);
+extern char *__kuser_get_tls_end[];
+
+extern int __kuser_cmpxchg(int, int, unsigned long *);
+extern char *__kuser_cmpxchg_end[];
+
+#endif
+
+#endif

arch/metag/include/uapi/asm/Kbuild

@@ -0,0 +1,13 @@
+# UAPI Header export list
+include include/uapi/asm-generic/Kbuild.asm
+
+header-y += byteorder.h
+header-y += ptrace.h
+header-y += resource.h
+header-y += sigcontext.h
+header-y += siginfo.h
+header-y += swab.h
+header-y += unistd.h
+
+generic-y += mman.h
+generic-y += setup.h

arch/metag/include/uapi/asm/byteorder.h

@@ -0,0 +1 @@
+#include <linux/byteorder/little_endian.h>

arch/metag/include/uapi/asm/ptrace.h

@@ -0,0 +1,113 @@
+#ifndef _UAPI_METAG_PTRACE_H
+#define _UAPI_METAG_PTRACE_H
+
+#ifndef __ASSEMBLY__
+
+/*
+ * These are the layouts of the regsets returned by the GETREGSET ptrace call
+ */
+
+/* user_gp_regs::status */
+
+/* CBMarker bit (indicates catch state / catch replay) */
+#define USER_GP_REGS_STATUS_CATCH_BIT		(1 << 22)
+#define USER_GP_REGS_STATUS_CATCH_S		22
+/* LSM_STEP field (load/store multiple step) */
+#define USER_GP_REGS_STATUS_LSM_STEP_BITS	(0x7 << 8)
+#define USER_GP_REGS_STATUS_LSM_STEP_S		8
+/* SCC bit (indicates split 16x16 condition flags) */
+#define USER_GP_REGS_STATUS_SCC_BIT		(1 << 4)
+#define USER_GP_REGS_STATUS_SCC_S		4
+
+/* normal condition flags */
+/* CF_Z bit (Zero flag) */
+#define USER_GP_REGS_STATUS_CF_Z_BIT		(1 << 3)
+#define USER_GP_REGS_STATUS_CF_Z_S		3
+/* CF_N bit (Negative flag) */
+#define USER_GP_REGS_STATUS_CF_N_BIT		(1 << 2)
+#define USER_GP_REGS_STATUS_CF_N_S		2
+/* CF_V bit (oVerflow flag) */
+#define USER_GP_REGS_STATUS_CF_V_BIT		(1 << 1)
+#define USER_GP_REGS_STATUS_CF_V_S		1
+/* CF_C bit (Carry flag) */
+#define USER_GP_REGS_STATUS_CF_C_BIT		(1 << 0)
+#define USER_GP_REGS_STATUS_CF_C_S		0
+
+/* split 16x16 condition flags */
+/* SCF_LZ bit (Low Zero flag) */
+#define USER_GP_REGS_STATUS_SCF_LZ_BIT		(1 << 3)
+#define USER_GP_REGS_STATUS_SCF_LZ_S		3
+/* SCF_HZ bit (High Zero flag) */
+#define USER_GP_REGS_STATUS_SCF_HZ_BIT		(1 << 2)
+#define USER_GP_REGS_STATUS_SCF_HZ_S		2
+/* SCF_HC bit (High Carry flag) */
+#define USER_GP_REGS_STATUS_SCF_HC_BIT		(1 << 1)
+#define USER_GP_REGS_STATUS_SCF_HC_S		1
+/* SCF_LC bit (Low Carry flag) */
+#define USER_GP_REGS_STATUS_SCF_LC_BIT		(1 << 0)
+#define USER_GP_REGS_STATUS_SCF_LC_S		0
+
+/**
+ * struct user_gp_regs - User general purpose registers
+ * @dx:		GP data unit regs (dx[reg][unit] = D{unit:0-1}.{reg:0-7})
+ * @ax:		GP address unit regs (ax[reg][unit] = A{unit:0-1}.{reg:0-3})
+ * @pc:		PC register
+ * @status:	TXSTATUS register (condition flags, LSM_STEP etc)
+ * @rpt:	TXRPT registers (branch repeat counter)
+ * @bpobits:	TXBPOBITS register ("branch prediction other" bits)
+ * @mode:	TXMODE register
+ * @_pad1:	Reserved padding to make sizeof obviously 64bit aligned
+ *
+ * This is the user-visible general purpose register state structure.
+ *
+ * It can be accessed through PTRACE_GETREGSET with NT_PRSTATUS.
+ *
+ * It is also used in the signal context.
+ */
+struct user_gp_regs {
+	unsigned long dx[8][2];
+	unsigned long ax[4][2];
+	unsigned long pc;
+	unsigned long status;
+	unsigned long rpt;
+	unsigned long bpobits;
+	unsigned long mode;
+	unsigned long _pad1;
+};
+
+/**
+ * struct user_cb_regs - User catch buffer registers
+ * @flags:	TXCATCH0 register (fault flags)
+ * @addr:	TXCATCH1 register (fault address)
+ * @data:	TXCATCH2 and TXCATCH3 registers (low and high data word)
+ *
+ * This is the user-visible catch buffer register state structure containing
+ * information about a failed memory access, and allowing the access to be
+ * modified and replayed.
+ *
+ * It can be accessed through PTRACE_GETREGSET with NT_METAG_CBUF.
+ */
+struct user_cb_regs {
+	unsigned long flags;
+	unsigned long addr;
+	unsigned long long data;
+};
+
+/**
+ * struct user_rp_state - User read pipeline state
+ * @entries:	Read pipeline entries
+ * @mask:	Mask of valid pipeline entries (RPMask from TXDIVTIME register)
+ *
+ * This is the user-visible read pipeline state structure containing the entries
+ * currently in the read pipeline and the mask of valid entries.
+ *
+ * It can be accessed through PTRACE_GETREGSET with NT_METAG_RPIPE.
+ */
+struct user_rp_state {
+	unsigned long long entries[6];
+	unsigned long mask;
+};
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _UAPI_METAG_PTRACE_H */

arch/metag/include/uapi/asm/resource.h

@@ -0,0 +1,7 @@
+#ifndef _UAPI_METAG_RESOURCE_H
+#define _UAPI_METAG_RESOURCE_H
+
+#define _STK_LIM_MAX    (1 << 28)
+#include <asm-generic/resource.h>
+
+#endif /* _UAPI_METAG_RESOURCE_H */

arch/metag/include/uapi/asm/sigcontext.h

@@ -0,0 +1,31 @@
+#ifndef _ASM_METAG_SIGCONTEXT_H
+#define _ASM_METAG_SIGCONTEXT_H
+
+#include <asm/ptrace.h>
+
+/*
+ * In a sigcontext structure we need to store the active state of the
+ * user process so that it does not get trashed when we call the signal
+ * handler. That not really the same as a user context that we are
+ * going to store on syscall etc.
+ */
+struct sigcontext {
+	struct user_gp_regs regs;	/* needs to be first */
+
+	/*
+	 * Catch registers describing a memory fault.
+	 * If USER_GP_REGS_STATUS_CATCH_BIT is set in regs.status then catch
+	 * buffers have been saved and will be replayed on sigreturn.
+	 * Clear that bit to discard the catch state instead of replaying it.
+	 */
+	struct user_cb_regs cb;
+
+	/*
+	 * Read pipeline state. This will get restored on sigreturn.
+	 */
+	struct user_rp_state rp;
+
+	unsigned long oldmask;
+};
+
+#endif

arch/metag/include/uapi/asm/siginfo.h

@@ -0,0 +1,8 @@
+#ifndef _METAG_SIGINFO_H
+#define _METAG_SIGINFO_H
+
+#define __ARCH_SI_TRAPNO
+
+#include <asm-generic/siginfo.h>
+
+#endif

arch/metag/include/uapi/asm/swab.h

@@ -0,0 +1,26 @@
+#ifndef __ASM_METAG_SWAB_H
+#define __ASM_METAG_SWAB_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <asm-generic/swab.h>
+
+static inline __attribute_const__ __u16 __arch_swab16(__u16 x)
+{
+	return __builtin_metag_bswaps(x);
+}
+#define __arch_swab16 __arch_swab16
+
+static inline __attribute_const__ __u32 __arch_swab32(__u32 x)
+{
+	return __builtin_metag_bswap(x);
+}
+#define __arch_swab32 __arch_swab32
+
+static inline __attribute_const__ __u64 __arch_swab64(__u64 x)
+{
+	return __builtin_metag_bswapll(x);
+}
+#define __arch_swab64 __arch_swab64
+
+#endif /* __ASM_METAG_SWAB_H */

arch/metag/include/uapi/asm/unistd.h

@@ -0,0 +1,21 @@
+/*
+ * Copyright (C) 2012 Imagination Technologies Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+/* Use the standard ABI for syscalls. */
+#include <asm-generic/unistd.h>
+
+/* metag-specific syscalls. */
+#define __NR_metag_setglobalbit		(__NR_arch_specific_syscall + 1)
+__SYSCALL(__NR_metag_setglobalbit, sys_metag_setglobalbit)
+#define __NR_metag_set_fpu_flags	(__NR_arch_specific_syscall + 2)
+__SYSCALL(__NR_metag_set_fpu_flags, sys_metag_set_fpu_flags)
+#define __NR_metag_set_tls		(__NR_arch_specific_syscall + 3)
+__SYSCALL(__NR_metag_set_tls, sys_metag_set_tls)
+#define __NR_metag_get_tls		(__NR_arch_specific_syscall + 4)
+__SYSCALL(__NR_metag_get_tls, sys_metag_get_tls)