Merge branches 'arnd-randcfg-fixes', 'debug', 'io' (early part), 'l2x0',...

Merge branches 'arnd-randcfg-fixes', 'debug', 'io' (early part), 'l2x0', 'p2v', 'pgt' (early part) and 'smp' into for-linus

Documentation/devicetree/bindings/arm/l2cc.txt

+* ARM L2 Cache Controller
+
+ARM cores often have a separate level 2 cache controller. There are various
+implementations of the L2 cache controller with compatible programming models.
+The ARM L2 cache representation in the device tree should be done as follows:
+
+Required properties:
+
+- compatible : should be one of:
+	"arm,pl310-cache"
+	"arm,l220-cache"
+	"arm,l210-cache"
+- cache-unified : Specifies the cache is a unified cache.
+- cache-level : Should be set to 2 for a level 2 cache.
+- reg : Physical base address and size of cache controller's memory mapped
+  registers.
+
+Optional properties:
+
+- arm,data-latency : Cycles of latency for Data RAM accesses. Specifies 3 cells of
+  read, write and setup latencies. Minimum valid values are 1. Controllers
+  without setup latency control should use a value of 0.
+- arm,tag-latency : Cycles of latency for Tag RAM accesses. Specifies 3 cells of
+  read, write and setup latencies. Controllers without setup latency control
+  should use 0. Controllers without separate read and write Tag RAM latency
+  values should only use the first cell.
+- arm,dirty-latency : Cycles of latency for Dirty RAMs. This is a single cell.
+- arm,filter-ranges : <start length> Starting address and length of window to
+  filter. Addresses in the filter window are directed to the M1 port. Other
+  addresses will go to the M0 port.
+- interrupts : 1 combined interrupt.
+
+Example:
+
+L2: cache-controller {
+        compatible = "arm,pl310-cache";
+        reg = <0xfff12000 0x1000>;
+        arm,data-latency = <1 1 1>;
+        arm,tag-latency = <2 2 2>;
+        arm,filter-latency = <0x80000000 0x8000000>;
+        cache-unified;
+        cache-level = <2>;
+	interrupts = <45>;
+};

arch/arm/Kconfig

@@ -3,7 +3,7 @@ config ARM
 	default y
 	select HAVE_AOUT
 	select HAVE_DMA_API_DEBUG
-	select HAVE_IDE
+	select HAVE_IDE if PCI || ISA || PCMCIA
 	select HAVE_MEMBLOCK
 	select RTC_LIB
 	select SYS_SUPPORTS_APM_EMULATION
@@ -195,7 +195,8 @@ config VECTORS_BASE
 	  The base address of exception vectors.
 
 config ARM_PATCH_PHYS_VIRT
-	bool "Patch physical to virtual translations at runtime"
+	bool "Patch physical to virtual translations at runtime" if EMBEDDED
+	default y
 	depends on !XIP_KERNEL && MMU
 	depends on !ARCH_REALVIEW || !SPARSEMEM
 	help
@@ -204,16 +205,12 @@ config ARM_PATCH_PHYS_VIRT
 	  kernel in system memory.
 
 	  This can only be used with non-XIP MMU kernels where the base
-	  of physical memory is at a 16MB boundary, or theoretically 64K
-	  for the MSM machine class.
+	  of physical memory is at a 16MB boundary.
+
+	  Only disable this option if you know that you do not require
+	  this feature (eg, building a kernel for a single machine) and
+	  you need to shrink the kernel to the minimal size.
 
-config ARM_PATCH_PHYS_VIRT_16BIT
-	def_bool y
-	depends on ARM_PATCH_PHYS_VIRT && ARCH_MSM
-	help
-	  This option extends the physical to virtual translation patching
-	  to allow physical memory down to a theoretical minimum of 64K
-	  boundaries.
 
 source "init/Kconfig"
 
@@ -301,7 +298,6 @@ config ARCH_AT91
 	select ARCH_REQUIRE_GPIOLIB
 	select HAVE_CLK
 	select CLKDEV_LOOKUP
-	select ARM_PATCH_PHYS_VIRT if MMU
 	help
 	  This enables support for systems based on the Atmel AT91RM9200,
 	  AT91SAM9 and AT91CAP9 processors.
@@ -385,6 +381,7 @@ config ARCH_FOOTBRIDGE
 	select CPU_SA110
 	select FOOTBRIDGE
 	select GENERIC_CLOCKEVENTS
+	select HAVE_IDE
 	help
 	  Support for systems based on the DC21285 companion chip
 	  ("FootBridge"), such as the Simtec CATS and the Rebel NetWinder.
@@ -631,6 +628,8 @@ config ARCH_PXA
 	select SPARSE_IRQ
 	select AUTO_ZRELADDR
 	select MULTI_IRQ_HANDLER
+	select ARM_CPU_SUSPEND if PM
+	select HAVE_IDE
 	help
 	  Support for Intel/Marvell's PXA2xx/PXA3xx processor line.
 
@@ -671,6 +670,7 @@ config ARCH_RPC
 	select NO_IOPORT
 	select ARCH_SPARSEMEM_ENABLE
 	select ARCH_USES_GETTIMEOFFSET
+	select HAVE_IDE
 	help
 	  On the Acorn Risc-PC, Linux can support the internal IDE disk and
 	  CD-ROM interface, serial and parallel port, and the floppy drive.
@@ -689,6 +689,7 @@ config ARCH_SA1100
 	select HAVE_SCHED_CLOCK
 	select TICK_ONESHOT
 	select ARCH_REQUIRE_GPIOLIB
+	select HAVE_IDE
 	help
 	  Support for StrongARM 11x0 based boards.
 
@@ -1375,6 +1376,7 @@ config SMP
 		 MACH_REALVIEW_PB11MP || MACH_REALVIEW_PBX || ARCH_OMAP4 || \
 		 ARCH_EXYNOS4 || ARCH_TEGRA || ARCH_U8500 || ARCH_VEXPRESS_CA9X4 || \
 		 ARCH_MSM_SCORPIONMP || ARCH_SHMOBILE
+	depends on MMU
 	select USE_GENERIC_SMP_HELPERS
 	select HAVE_ARM_SCU if !ARCH_MSM_SCORPIONMP
 	help
@@ -1407,6 +1409,31 @@ config SMP_ON_UP
 
 	  If you don't know what to do here, say Y.
 
+config ARM_CPU_TOPOLOGY
+	bool "Support cpu topology definition"
+	depends on SMP && CPU_V7
+	default y
+	help
+	  Support ARM cpu topology definition. The MPIDR register defines
+	  affinity between processors which is then used to describe the cpu
+	  topology of an ARM System.
+
+config SCHED_MC
+	bool "Multi-core scheduler support"
+	depends on ARM_CPU_TOPOLOGY
+	help
+	  Multi-core scheduler support improves the CPU scheduler's decision
+	  making when dealing with multi-core CPU chips at a cost of slightly
+	  increased overhead in some places. If unsure say N here.
+
+config SCHED_SMT
+	bool "SMT scheduler support"
+	depends on ARM_CPU_TOPOLOGY
+	help
+	  Improves the CPU scheduler's decision making when dealing with
+	  MultiThreading at a cost of slightly increased overhead in some
+	  places. If unsure say N here.
+
 config HAVE_ARM_SCU
 	bool
 	help
@@ -1482,6 +1509,7 @@ config THUMB2_KERNEL
 	depends on CPU_V7 && !CPU_V6 && !CPU_V6K && EXPERIMENTAL
 	select AEABI
 	select ARM_ASM_UNIFIED
+	select ARM_UNWIND
 	help
 	  By enabling this option, the kernel will be compiled in
 	  Thumb-2 mode. A compiler/assembler that understand the unified
@@ -2101,6 +2129,9 @@ config ARCH_SUSPEND_POSSIBLE
 		CPU_V6 || CPU_V6K || CPU_V7 || CPU_XSC3 || CPU_XSCALE
 	def_bool y
 
+config ARM_CPU_SUSPEND
+	def_bool PM_SLEEP
+
 endmenu
 
 source "net/Kconfig"

arch/arm/Kconfig.debug

@@ -65,57 +65,86 @@ config DEBUG_USER
 
 # These options are only for real kernel hackers who want to get their hands dirty.
 config DEBUG_LL
-	bool "Kernel low-level debugging functions"
+	bool "Kernel low-level debugging functions (read help!)"
 	depends on DEBUG_KERNEL
 	help
 	  Say Y here to include definitions of printascii, printch, printhex
 	  in the kernel.  This is helpful if you are debugging code that
 	  executes before the console is initialized.
 
-config EARLY_PRINTK
-	bool "Early printk"
+	  Note that selecting this option will limit the kernel to a single
+	  UART definition, as specified below. Attempting to boot the kernel
+	  image on a different platform *will not work*, so this option should
+	  not be enabled for kernels that are intended to be portable.
+
+choice
+	prompt "Kernel low-level debugging port"
 	depends on DEBUG_LL
+
+	config DEBUG_LL_UART_NONE
+		bool "No low-level debugging UART"
 		help
-	  Say Y here if you want to have an early console using the
-	  kernel low-level debugging functions. Add earlyprintk to your
-	  kernel parameters to enable this console.
+		  Say Y here if your platform doesn't provide a UART option
+		  below. This relies on your platform choosing the right UART
+		  definition internally in order for low-level debugging to
+		  work.
 
-config DEBUG_ICEDCC
+	config DEBUG_ICEDCC
 		bool "Kernel low-level debugging via EmbeddedICE DCC channel"
-	depends on DEBUG_LL
 		help
-	  Say Y here if you want the debug print routines to direct their
-	  output to the EmbeddedICE macrocell's DCC channel using
+		  Say Y here if you want the debug print routines to direct
+		  their output to the EmbeddedICE macrocell's DCC channel using
 		  co-processor 14. This is known to work on the ARM9 style ICE
 		  channel and on the XScale with the PEEDI.
 
-	  It does include a timeout to ensure that the system does not
-	  totally freeze when there is nothing connected to read.
+		  Note that the system will appear to hang during boot if there
+		  is nothing connected to read from the DCC.
 
-config OC_ETM
-	bool "On-chip ETM and ETB"
-	select ARM_AMBA
+	config DEBUG_FOOTBRIDGE_COM1
+		bool "Kernel low-level debugging messages via footbridge 8250 at PCI COM1"
+		depends on FOOTBRIDGE
 		help
-	  Enables the on-chip embedded trace macrocell and embedded trace
-	  buffer driver that will allow you to collect traces of the
-	  kernel code.
+		  Say Y here if you want the debug print routines to direct
+		  their output to the 8250 at PCI COM1.
 
-config DEBUG_DC21285_PORT
+	config DEBUG_DC21285_PORT
 		bool "Kernel low-level debugging messages via footbridge serial port"
-	depends on DEBUG_LL && FOOTBRIDGE
+		depends on FOOTBRIDGE
+		help
+		  Say Y here if you want the debug print routines to direct
+		  their output to the serial port in the DC21285 (Footbridge).
+
+	config DEBUG_CLPS711X_UART1
+		bool "Kernel low-level debugging messages via UART1"
+		depends on ARCH_CLPS711X
 		help
-	  Say Y here if you want the debug print routines to direct their
-	  output to the serial port in the DC21285 (Footbridge). Saying N
-	  will cause the debug messages to appear on the first 16550
-	  serial port.
+		  Say Y here if you want the debug print routines to direct
+		  their output to the first serial port on these devices.
 
-config DEBUG_CLPS711X_UART2
+	config DEBUG_CLPS711X_UART2
 		bool "Kernel low-level debugging messages via UART2"
-	depends on DEBUG_LL && ARCH_CLPS711X
+		depends on ARCH_CLPS711X
 		help
-	  Say Y here if you want the debug print routines to direct their
-	  output to the second serial port on these devices.  Saying N will
-	  cause the debug messages to appear on the first serial port.
+		  Say Y here if you want the debug print routines to direct
+		  their output to the second serial port on these devices.
+
+endchoice
+
+config EARLY_PRINTK
+	bool "Early printk"
+	depends on DEBUG_LL
+	help
+	  Say Y here if you want to have an early console using the
+	  kernel low-level debugging functions. Add earlyprintk to your
+	  kernel parameters to enable this console.
+
+config OC_ETM
+	bool "On-chip ETM and ETB"
+	depends on ARM_AMBA
+	help
+	  Enables the on-chip embedded trace macrocell and embedded trace
+	  buffer driver that will allow you to collect traces of the
+	  kernel code.
 
 config DEBUG_S3C_UART
 	depends on PLAT_SAMSUNG

arch/arm/Makefile

@@ -128,6 +128,9 @@ textofs-$(CONFIG_PM_H1940)      := 0x00108000
 ifeq ($(CONFIG_ARCH_SA1100),y)
 textofs-$(CONFIG_SA1111) := 0x00208000
 endif
+textofs-$(CONFIG_ARCH_MSM7X30) := 0x00208000
+textofs-$(CONFIG_ARCH_MSM8X60) := 0x00208000
+textofs-$(CONFIG_ARCH_MSM8960) := 0x00208000
 
 # Machine directory name.  This list is sorted alphanumerically
 # by CONFIG_* macro name.

arch/arm/common/gic.c

@@ -180,7 +180,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 		return -EINVAL;
 
 	mask = 0xff << shift;
-	bit = 1 << (cpu + shift);
+	bit = 1 << (cpu_logical_map(cpu) + shift);
 
 	spin_lock(&irq_controller_lock);
 	val = readl_relaxed(reg) & ~mask;
@@ -259,9 +259,15 @@ static void __init gic_dist_init(struct gic_chip_data *gic,
 	unsigned int irq_start)
 {
 	unsigned int gic_irqs, irq_limit, i;
+	u32 cpumask;
 	void __iomem *base = gic->dist_base;
-	u32 cpumask = 1 << smp_processor_id();
+	u32 cpu = 0;
 
+#ifdef CONFIG_SMP
+	cpu = cpu_logical_map(smp_processor_id());
+#endif
+
+	cpumask = 1 << cpu;
 	cpumask |= cpumask << 8;
 	cpumask |= cpumask << 16;
 
@@ -382,7 +388,12 @@ void __cpuinit gic_enable_ppi(unsigned int irq)
 #ifdef CONFIG_SMP
 void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 {
-	unsigned long map = *cpus_addr(*mask);
+	int cpu;
+	unsigned long map = 0;
+
+	/* Convert our logical CPU mask into a physical one. */
+	for_each_cpu(cpu, mask)
+		map |= 1 << cpu_logical_map(cpu);
 
 	/*
 	 * Ensure that stores to Normal memory are visible to the

arch/arm/common/vic.c

@@ -346,7 +346,8 @@ void __init vic_init(void __iomem *base, unsigned int irq_start,
 
 	/* Identify which VIC cell this one is, by reading the ID */
 	for (i = 0; i < 4; i++) {
-		u32 addr = ((u32)base & PAGE_MASK) + 0xfe0 + (i * 4);
+		void __iomem *addr;
+		addr = (void __iomem *)((u32)base & PAGE_MASK) + 0xfe0 + (i * 4);
 		cellid |= (readl(addr) & 0xff) << (8 * i);
 	}
 	vendor = (cellid >> 12) & 0xff;

arch/arm/include/asm/cputype.h

@@ -8,6 +8,7 @@
 #define CPUID_CACHETYPE	1
 #define CPUID_TCM	2
 #define CPUID_TLBTYPE	3
+#define CPUID_MPIDR	5
 
 #define CPUID_EXT_PFR0	"c1, 0"
 #define CPUID_EXT_PFR1	"c1, 1"
@@ -70,6 +71,11 @@ static inline unsigned int __attribute_const__ read_cpuid_tcmstatus(void)
 	return read_cpuid(CPUID_TCM);
 }
 
+static inline unsigned int __attribute_const__ read_cpuid_mpidr(void)
+{
+	return read_cpuid(CPUID_MPIDR);
+}
+
 /*
  * Intel's XScale3 core supports some v6 features (supersections, L2)
  * but advertises itself as v5 as it does not support the v6 ISA.  For

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

@@ -32,7 +32,7 @@ static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
 
 static inline void *dma_to_virt(struct device *dev, dma_addr_t addr)
 {
-	return (void *)__bus_to_virt(addr);
+	return (void *)__bus_to_virt((unsigned long)addr);
 }
 
 static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)

arch/arm/include/asm/ecard.h

@@ -161,7 +161,6 @@ struct expansion_card {
 
 	/* Private internal data */
 	const char		*card_desc;	/* Card description		*/
-	CONST unsigned int	podaddr;	/* Base Linux address for card	*/
 	CONST loader_t		loader;		/* loader program */
 	u64			dma_mask;
 };

arch/arm/include/asm/exception.h

+/*
+ * Annotations for marking C functions as exception handlers.
+ *
+ * These should only be used for C functions that are called from the low
+ * level exception entry code and not any intervening C code.
+ */
+#ifndef __ASM_ARM_EXCEPTION_H
+#define __ASM_ARM_EXCEPTION_H
+
+#include <linux/ftrace.h>
+
+#define __exception	__attribute__((section(".exception.text")))
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+#define __exception_irq_entry	__irq_entry
+#else
+#define __exception_irq_entry	__exception
+#endif
+
+#endif /* __ASM_ARM_EXCEPTION_H */

arch/arm/include/asm/hardware/cache-l2x0.h

@@ -52,6 +52,8 @@
 #define L2X0_LOCKDOWN_WAY_D_BASE	0x900
 #define L2X0_LOCKDOWN_WAY_I_BASE	0x904
 #define L2X0_LOCKDOWN_STRIDE		0x08
+#define L2X0_ADDR_FILTER_START		0xC00
+#define L2X0_ADDR_FILTER_END		0xC04
 #define L2X0_TEST_OPERATION		0xF00
 #define L2X0_LINE_DATA			0xF10
 #define L2X0_LINE_TAG			0xF30
@@ -65,8 +67,23 @@
 #define L2X0_CACHE_ID_PART_MASK		(0xf << 6)
 #define L2X0_CACHE_ID_PART_L210		(1 << 6)
 #define L2X0_CACHE_ID_PART_L310		(3 << 6)
+#define L2X0_CACHE_ID_RTL_MASK          0x3f
+#define L2X0_CACHE_ID_RTL_R0P0          0x0
+#define L2X0_CACHE_ID_RTL_R1P0          0x2
+#define L2X0_CACHE_ID_RTL_R2P0          0x4
+#define L2X0_CACHE_ID_RTL_R3P0          0x5
+#define L2X0_CACHE_ID_RTL_R3P1          0x6
+#define L2X0_CACHE_ID_RTL_R3P2          0x8
 
 #define L2X0_AUX_CTRL_MASK			0xc0000fff
+#define L2X0_AUX_CTRL_DATA_RD_LATENCY_SHIFT	0
+#define L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK	0x7
+#define L2X0_AUX_CTRL_DATA_WR_LATENCY_SHIFT	3
+#define L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK	(0x7 << 3)
+#define L2X0_AUX_CTRL_TAG_LATENCY_SHIFT		6
+#define L2X0_AUX_CTRL_TAG_LATENCY_MASK		(0x7 << 6)
+#define L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT	9
+#define L2X0_AUX_CTRL_DIRTY_LATENCY_MASK	(0x7 << 9)
 #define L2X0_AUX_CTRL_ASSOCIATIVITY_SHIFT	16
 #define L2X0_AUX_CTRL_WAY_SIZE_SHIFT		17
 #define L2X0_AUX_CTRL_WAY_SIZE_MASK		(0x7 << 17)
@@ -77,8 +94,33 @@
 #define L2X0_AUX_CTRL_INSTR_PREFETCH_SHIFT	29
 #define L2X0_AUX_CTRL_EARLY_BRESP_SHIFT		30
 
+#define L2X0_LATENCY_CTRL_SETUP_SHIFT	0
+#define L2X0_LATENCY_CTRL_RD_SHIFT	4
+#define L2X0_LATENCY_CTRL_WR_SHIFT	8
+
+#define L2X0_ADDR_FILTER_EN		1
+
 #ifndef __ASSEMBLY__
 extern void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask);
+extern int l2x0_of_init(__u32 aux_val, __u32 aux_mask);
+
+struct l2x0_regs {
+	unsigned long phy_base;
+	unsigned long aux_ctrl;
+	/*
+	 * Whether the following registers need to be saved/restored
+	 * depends on platform
+	 */
+	unsigned long tag_latency;
+	unsigned long data_latency;
+	unsigned long filter_start;
+	unsigned long filter_end;
+	unsigned long prefetch_ctrl;
+	unsigned long pwr_ctrl;
+};
+
+extern struct l2x0_regs l2x0_saved_regs;
+
 #endif
 
 #endif

arch/arm/include/asm/io.h

@@ -109,6 +109,27 @@ static inline void __iomem *__typesafe_io(unsigned long addr)
  */
 #include <mach/io.h>
 
+/*
+ * This is the limit of PC card/PCI/ISA IO space, which is by default
+ * 64K if we have PC card, PCI or ISA support.  Otherwise, default to
+ * zero to prevent ISA/PCI drivers claiming IO space (and potentially
+ * oopsing.)
+ *
+ * Only set this larger if you really need inb() et.al. to operate over
+ * a larger address space.  Note that SOC_COMMON ioremaps each sockets
+ * IO space area, and so inb() et.al. must be defined to operate as per
+ * readb() et.al. on such platforms.
+ */
+#ifndef IO_SPACE_LIMIT
+#if defined(CONFIG_PCMCIA_SOC_COMMON) || defined(CONFIG_PCMCIA_SOC_COMMON_MODULE)
+#define IO_SPACE_LIMIT ((resource_size_t)0xffffffff)
+#elif defined(CONFIG_PCI) || defined(CONFIG_ISA) || defined(CONFIG_PCCARD)
+#define IO_SPACE_LIMIT ((resource_size_t)0xffff)
+#else
+#define IO_SPACE_LIMIT ((resource_size_t)0)
+#endif
+#endif
+
 /*
  *  IO port access primitives
  *  -------------------------
@@ -260,10 +281,16 @@ extern void _memset_io(volatile void __iomem *, int, size_t);
 #define ioread16(p)	({ unsigned int __v = le16_to_cpu((__force __le16)__raw_readw(p)); __iormb(); __v; })
 #define ioread32(p)	({ unsigned int __v = le32_to_cpu((__force __le32)__raw_readl(p)); __iormb(); __v; })
 
+#define ioread16be(p)	({ unsigned int __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(); __v; })
+#define ioread32be(p)	({ unsigned int __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(); __v; })
+
 #define iowrite8(v,p)	({ __iowmb(); (void)__raw_writeb(v, p); })
 #define iowrite16(v,p)	({ __iowmb(); (void)__raw_writew((__force __u16)cpu_to_le16(v), p); })
 #define iowrite32(v,p)	({ __iowmb(); (void)__raw_writel((__force __u32)cpu_to_le32(v), p); })
 
+#define iowrite16be(v,p) ({ __iowmb(); (void)__raw_writew((__force __u16)cpu_to_be16(v), p); })
+#define iowrite32be(v,p) ({ __iowmb(); (void)__raw_writel((__force __u32)cpu_to_be32(v), p); })
+
 #define ioread8_rep(p,d,c)	__raw_readsb(p,d,c)
 #define ioread16_rep(p,d,c)	__raw_readsw(p,d,c)
 #define ioread32_rep(p,d,c)	__raw_readsl(p,d,c)

arch/arm/include/asm/localtimer.h

@@ -24,6 +24,10 @@ void percpu_timer_setup(void);
  */
 asmlinkage void do_local_timer(struct pt_regs *);
 
+/*
+ * Called from C code
+ */
+void handle_local_timer(struct pt_regs *);
 
 #ifdef CONFIG_LOCAL_TIMERS
 

arch/arm/include/asm/memory.h

@@ -160,7 +160,6 @@
  * so that all we need to do is modify the 8-bit constant field.
  */
 #define __PV_BITS_31_24	0x81000000
-#define __PV_BITS_23_16	0x00810000
 
 extern unsigned long __pv_phys_offset;
 #define PHYS_OFFSET __pv_phys_offset
@@ -178,9 +177,6 @@ static inline unsigned long __virt_to_phys(unsigned long x)
 {
 	unsigned long t;
 	__pv_stub(x, t, "add", __PV_BITS_31_24);
-#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT
-	__pv_stub(t, t, "add", __PV_BITS_23_16);
-#endif
 	return t;
 }
 
@@ -188,9 +184,6 @@ static inline unsigned long __phys_to_virt(unsigned long x)
 {
 	unsigned long t;
 	__pv_stub(x, t, "sub", __PV_BITS_31_24);
-#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT
-	__pv_stub(t, t, "sub", __PV_BITS_23_16);
-#endif
 	return t;
 }
 #else

arch/arm/include/asm/module.h

@@ -31,11 +31,7 @@ struct mod_arch_specific {
 
 /* Add __virt_to_phys patching state as well */
 #ifdef CONFIG_ARM_PATCH_PHYS_VIRT
-#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT
-#define MODULE_ARCH_VERMAGIC_P2V "p2v16 "
-#else
 #define MODULE_ARCH_VERMAGIC_P2V "p2v8 "
-#endif
 #else
 #define MODULE_ARCH_VERMAGIC_P2V ""
 #endif

arch/arm/include/asm/outercache.h

@@ -34,6 +34,7 @@ struct outer_cache_fns {
 	void (*sync)(void);
 #endif
 	void (*set_debug)(unsigned long);
+	void (*resume)(void);
 };
 
 #ifdef CONFIG_OUTER_CACHE
@@ -74,6 +75,12 @@ static inline void outer_disable(void)
 		outer_cache.disable();
 }
 
+static inline void outer_resume(void)
+{
+	if (outer_cache.resume)
+		outer_cache.resume();
+}
+
 #else
 
 static inline void outer_inv_range(phys_addr_t start, phys_addr_t end)

arch/arm/include/asm/page.h

@@ -151,47 +151,7 @@ extern void __cpu_copy_user_highpage(struct page *to, struct page *from,
 #define clear_page(page)	memset((void *)(page), 0, PAGE_SIZE)
 extern void copy_page(void *to, const void *from);
 
-typedef unsigned long pteval_t;
-
-#undef STRICT_MM_TYPECHECKS
-
-#ifdef STRICT_MM_TYPECHECKS
-/*
- * These are used to make use of C type-checking..
- */
-typedef struct { pteval_t pte; } pte_t;
-typedef struct { unsigned long pmd; } pmd_t;
-typedef struct { unsigned long pgd[2]; } pgd_t;
-typedef struct { unsigned long pgprot; } pgprot_t;
-
-#define pte_val(x)      ((x).pte)
-#define pmd_val(x)      ((x).pmd)
-#define pgd_val(x)	((x).pgd[0])
-#define pgprot_val(x)   ((x).pgprot)
-
-#define __pte(x)        ((pte_t) { (x) } )
-#define __pmd(x)        ((pmd_t) { (x) } )
-#define __pgprot(x)     ((pgprot_t) { (x) } )
-
-#else
-/*
- * .. while these make it easier on the compiler
- */
-typedef pteval_t pte_t;
-typedef unsigned long pmd_t;
-typedef unsigned long pgd_t[2];
-typedef unsigned long pgprot_t;
-
-#define pte_val(x)      (x)
-#define pmd_val(x)      (x)
-#define pgd_val(x)	((x)[0])
-#define pgprot_val(x)   (x)
-
-#define __pte(x)        (x)
-#define __pmd(x)        (x)
-#define __pgprot(x)     (x)
-
-#endif /* STRICT_MM_TYPECHECKS */
+#include <asm/pgtable-2level-types.h>
 
 #endif /* CONFIG_MMU */
 

arch/arm/include/asm/pgalloc.h

@@ -105,9 +105,9 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
 }
 
 static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t pte,
-	unsigned long prot)
+				  pmdval_t prot)
 {
-	unsigned long pmdval = (pte + PTE_HWTABLE_OFF) | prot;
+	pmdval_t pmdval = (pte + PTE_HWTABLE_OFF) | prot;
 	pmdp[0] = __pmd(pmdval);
 	pmdp[1] = __pmd(pmdval + 256 * sizeof(pte_t));
 	flush_pmd_entry(pmdp);

arch/arm/include/asm/pgtable-2level-hwdef.h

+/*
+ *  arch/arm/include/asm/pgtable-2level-hwdef.h
+ *
+ *  Copyright (C) 1995-2002 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 _ASM_PGTABLE_2LEVEL_HWDEF_H
+#define _ASM_PGTABLE_2LEVEL_HWDEF_H
+
+/*
+ * Hardware page table definitions.
+ *
+ * + Level 1 descriptor (PMD)
+ *   - common
+ */
+#define PMD_TYPE_MASK		(_AT(pmdval_t, 3) << 0)
+#define PMD_TYPE_FAULT		(_AT(pmdval_t, 0) << 0)
+#define PMD_TYPE_TABLE		(_AT(pmdval_t, 1) << 0)
+#define PMD_TYPE_SECT		(_AT(pmdval_t, 2) << 0)
+#define PMD_BIT4		(_AT(pmdval_t, 1) << 4)
+#define PMD_DOMAIN(x)		(_AT(pmdval_t, (x)) << 5)
+#define PMD_PROTECTION		(_AT(pmdval_t, 1) << 9)		/* v5 */
+/*
+ *   - section
+ */
+#define PMD_SECT_BUFFERABLE	(_AT(pmdval_t, 1) << 2)
+#define PMD_SECT_CACHEABLE	(_AT(pmdval_t, 1) << 3)
+#define PMD_SECT_XN		(_AT(pmdval_t, 1) << 4)		/* v6 */
+#define PMD_SECT_AP_WRITE	(_AT(pmdval_t, 1) << 10)
+#define PMD_SECT_AP_READ	(_AT(pmdval_t, 1) << 11)
+#define PMD_SECT_TEX(x)		(_AT(pmdval_t, (x)) << 12)	/* v5 */
+#define PMD_SECT_APX		(_AT(pmdval_t, 1) << 15)	/* v6 */
+#define PMD_SECT_S		(_AT(pmdval_t, 1) << 16)	/* v6 */
+#define PMD_SECT_nG		(_AT(pmdval_t, 1) << 17)	/* v6 */
+#define PMD_SECT_SUPER		(_AT(pmdval_t, 1) << 18)	/* v6 */
+#define PMD_SECT_AF		(_AT(pmdval_t, 0))
+
+#define PMD_SECT_UNCACHED	(_AT(pmdval_t, 0))
+#define PMD_SECT_BUFFERED	(PMD_SECT_BUFFERABLE)
+#define PMD_SECT_WT		(PMD_SECT_CACHEABLE)
+#define PMD_SECT_WB		(PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
+#define PMD_SECT_MINICACHE	(PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE)
+#define PMD_SECT_WBWA		(PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
+#define PMD_SECT_NONSHARED_DEV	(PMD_SECT_TEX(2))
+
+/*
+ *   - coarse table (not used)
+ */
+
+/*
+ * + Level 2 descriptor (PTE)
+ *   - common
+ */
+#define PTE_TYPE_MASK		(_AT(pteval_t, 3) << 0)
+#define PTE_TYPE_FAULT		(_AT(pteval_t, 0) << 0)
+#define PTE_TYPE_LARGE		(_AT(pteval_t, 1) << 0)
+#define PTE_TYPE_SMALL		(_AT(pteval_t, 2) << 0)
+#define PTE_TYPE_EXT		(_AT(pteval_t, 3) << 0)		/* v5 */
+#define PTE_BUFFERABLE		(_AT(pteval_t, 1) << 2)
+#define PTE_CACHEABLE		(_AT(pteval_t, 1) << 3)
+
+/*
+ *   - extended small page/tiny page
+ */
+#define PTE_EXT_XN		(_AT(pteval_t, 1) << 0)		/* v6 */
+#define PTE_EXT_AP_MASK		(_AT(pteval_t, 3) << 4)
+#define PTE_EXT_AP0		(_AT(pteval_t, 1) << 4)
+#define PTE_EXT_AP1		(_AT(pteval_t, 2) << 4)
+#define PTE_EXT_AP_UNO_SRO	(_AT(pteval_t, 0) << 4)
+#define PTE_EXT_AP_UNO_SRW	(PTE_EXT_AP0)
+#define PTE_EXT_AP_URO_SRW	(PTE_EXT_AP1)
+#define PTE_EXT_AP_URW_SRW	(PTE_EXT_AP1|PTE_EXT_AP0)
+#define PTE_EXT_TEX(x)		(_AT(pteval_t, (x)) << 6)	/* v5 */
+#define PTE_EXT_APX		(_AT(pteval_t, 1) << 9)		/* v6 */
+#define PTE_EXT_COHERENT	(_AT(pteval_t, 1) << 9)		/* XScale3 */
+#define PTE_EXT_SHARED		(_AT(pteval_t, 1) << 10)	/* v6 */
+#define PTE_EXT_NG		(_AT(pteval_t, 1) << 11)	/* v6 */
+
+/*
+ *   - small page
+ */
+#define PTE_SMALL_AP_MASK	(_AT(pteval_t, 0xff) << 4)
+#define PTE_SMALL_AP_UNO_SRO	(_AT(pteval_t, 0x00) << 4)
+#define PTE_SMALL_AP_UNO_SRW	(_AT(pteval_t, 0x55) << 4)
+#define PTE_SMALL_AP_URO_SRW	(_AT(pteval_t, 0xaa) << 4)
+#define PTE_SMALL_AP_URW_SRW	(_AT(pteval_t, 0xff) << 4)
+
+#define PHYS_MASK		(~0UL)
+
+#endif

arch/arm/include/asm/pgtable-2level-types.h

+/*
+ * arch/arm/include/asm/pgtable-2level-types.h
+ *
+ * Copyright (C) 1995-2003 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+#ifndef _ASM_PGTABLE_2LEVEL_TYPES_H
+#define _ASM_PGTABLE_2LEVEL_TYPES_H
+
+#include <asm/types.h>
+
+typedef u32 pteval_t;
+typedef u32 pmdval_t;
+
+#undef STRICT_MM_TYPECHECKS
+
+#ifdef STRICT_MM_TYPECHECKS
+/*
+ * These are used to make use of C type-checking..
+ */
+typedef struct { pteval_t pte; } pte_t;
+typedef struct { pmdval_t pmd; } pmd_t;
+typedef struct { pmdval_t pgd[2]; } pgd_t;
+typedef struct { pteval_t pgprot; } pgprot_t;
+
+#define pte_val(x)      ((x).pte)
+#define pmd_val(x)      ((x).pmd)
+#define pgd_val(x)	((x).pgd[0])
+#define pgprot_val(x)   ((x).pgprot)
+
+#define __pte(x)        ((pte_t) { (x) } )
+#define __pmd(x)        ((pmd_t) { (x) } )
+#define __pgprot(x)     ((pgprot_t) { (x) } )
+
+#else
+/*
+ * .. while these make it easier on the compiler
+ */
+typedef pteval_t pte_t;
+typedef pmdval_t pmd_t;
+typedef pmdval_t pgd_t[2];
+typedef pteval_t pgprot_t;
+
+#define pte_val(x)      (x)
+#define pmd_val(x)      (x)
+#define pgd_val(x)	((x)[0])
+#define pgprot_val(x)   (x)
+
+#define __pte(x)        (x)
+#define __pmd(x)        (x)
+#define __pgprot(x)     (x)
+
+#endif /* STRICT_MM_TYPECHECKS */
+
+#endif	/* _ASM_PGTABLE_2LEVEL_TYPES_H */

arch/arm/include/asm/pgtable-2level.h

+/*
+ *  arch/arm/include/asm/pgtable-2level.h
+ *
+ *  Copyright (C) 1995-2002 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 _ASM_PGTABLE_2LEVEL_H
+#define _ASM_PGTABLE_2LEVEL_H
+
+/*
+ * Hardware-wise, we have a two level page table structure, where the first
+ * level has 4096 entries, and the second level has 256 entries.  Each entry
+ * is one 32-bit word.  Most of the bits in the second level entry are used
+ * by hardware, and there aren't any "accessed" and "dirty" bits.
+ *
+ * Linux on the other hand has a three level page table structure, which can
+ * be wrapped to fit a two level page table structure easily - using the PGD
+ * and PTE only.  However, Linux also expects one "PTE" table per page, and
+ * at least a "dirty" bit.
+ *
+ * Therefore, we tweak the implementation slightly - we tell Linux that we
+ * have 2048 entries in the first level, each of which is 8 bytes (iow, two
+ * hardware pointers to the second level.)  The second level contains two
+ * hardware PTE tables arranged contiguously, preceded by Linux versions
+ * which contain the state information Linux needs.  We, therefore, end up
+ * with 512 entries in the "PTE" level.
+ *
+ * This leads to the page tables having the following layout:
+ *
+ *    pgd             pte
+ * |        |
+ * +--------+
+ * |        |       +------------+ +0
+ * +- - - - +       | Linux pt 0 |
+ * |        |       +------------+ +1024
+ * +--------+ +0    | Linux pt 1 |
+ * |        |-----> +------------+ +2048
+ * +- - - - + +4    |  h/w pt 0  |
+ * |        |-----> +------------+ +3072
+ * +--------+ +8    |  h/w pt 1  |
+ * |        |       +------------+ +4096
+ *
+ * See L_PTE_xxx below for definitions of bits in the "Linux pt", and
+ * PTE_xxx for definitions of bits appearing in the "h/w pt".
+ *
+ * PMD_xxx definitions refer to bits in the first level page table.
+ *
+ * The "dirty" bit is emulated by only granting hardware write permission
+ * iff the page is marked "writable" and "dirty" in the Linux PTE.  This
+ * means that a write to a clean page will cause a permission fault, and
+ * the Linux MM layer will mark the page dirty via handle_pte_fault().
+ * For the hardware to notice the permission change, the TLB entry must
+ * be flushed, and ptep_set_access_flags() does that for us.
+ *
+ * The "accessed" or "young" bit is emulated by a similar method; we only
+ * allow accesses to the page if the "young" bit is set.  Accesses to the
+ * page will cause a fault, and handle_pte_fault() will set the young bit
+ * for us as long as the page is marked present in the corresponding Linux
+ * PTE entry.  Again, ptep_set_access_flags() will ensure that the TLB is
+ * up to date.
+ *
+ * However, when the "young" bit is cleared, we deny access to the page
+ * by clearing the hardware PTE.  Currently Linux does not flush the TLB
+ * for us in this case, which means the TLB will retain the transation
+ * until either the TLB entry is evicted under pressure, or a context
+ * switch which changes the user space mapping occurs.
+ */
+#define PTRS_PER_PTE		512
+#define PTRS_PER_PMD		1
+#define PTRS_PER_PGD		2048
+
+#define PTE_HWTABLE_PTRS	(PTRS_PER_PTE)
+#define PTE_HWTABLE_OFF		(PTE_HWTABLE_PTRS * sizeof(pte_t))
+#define PTE_HWTABLE_SIZE	(PTRS_PER_PTE * sizeof(u32))
+
+/*
+ * PMD_SHIFT determines the size of the area a second-level page table can map
+ * PGDIR_SHIFT determines what a third-level page table entry can map
+ */
+#define PMD_SHIFT		21
+#define PGDIR_SHIFT		21
+
+#define PMD_SIZE		(1UL << PMD_SHIFT)
+#define PMD_MASK		(~(PMD_SIZE-1))
+#define PGDIR_SIZE		(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK		(~(PGDIR_SIZE-1))
+
+/*
+ * section address mask and size definitions.
+ */
+#define SECTION_SHIFT		20
+#define SECTION_SIZE		(1UL << SECTION_SHIFT)
+#define SECTION_MASK		(~(SECTION_SIZE-1))
+
+/*
+ * ARMv6 supersection address mask and size definitions.
+ */
+#define SUPERSECTION_SHIFT	24
+#define SUPERSECTION_SIZE	(1UL << SUPERSECTION_SHIFT)
+#define SUPERSECTION_MASK	(~(SUPERSECTION_SIZE-1))
+
+#define USER_PTRS_PER_PGD	(TASK_SIZE / PGDIR_SIZE)
+
+/*
+ * "Linux" PTE definitions.
+ *
+ * We keep two sets of PTEs - the hardware and the linux version.
+ * This allows greater flexibility in the way we map the Linux bits
+ * onto the hardware tables, and allows us to have YOUNG and DIRTY
+ * bits.
+ *
+ * The PTE table pointer refers to the hardware entries; the "Linux"
+ * entries are stored 1024 bytes below.
+ */
+#define L_PTE_PRESENT		(_AT(pteval_t, 1) << 0)
+#define L_PTE_YOUNG		(_AT(pteval_t, 1) << 1)
+#define L_PTE_FILE		(_AT(pteval_t, 1) << 2)	/* only when !PRESENT */
+#define L_PTE_DIRTY		(_AT(pteval_t, 1) << 6)
+#define L_PTE_RDONLY		(_AT(pteval_t, 1) << 7)
+#define L_PTE_USER		(_AT(pteval_t, 1) << 8)
+#define L_PTE_XN		(_AT(pteval_t, 1) << 9)
+#define L_PTE_SHARED		(_AT(pteval_t, 1) << 10)	/* shared(v6), coherent(xsc3) */
+
+/*
+ * These are the memory types, defined to be compatible with
+ * pre-ARMv6 CPUs cacheable and bufferable bits:   XXCB
+ */
+#define L_PTE_MT_UNCACHED	(_AT(pteval_t, 0x00) << 2)	/* 0000 */
+#define L_PTE_MT_BUFFERABLE	(_AT(pteval_t, 0x01) << 2)	/* 0001 */
+#define L_PTE_MT_WRITETHROUGH	(_AT(pteval_t, 0x02) << 2)	/* 0010 */
+#define L_PTE_MT_WRITEBACK	(_AT(pteval_t, 0x03) << 2)	/* 0011 */
+#define L_PTE_MT_MINICACHE	(_AT(pteval_t, 0x06) << 2)	/* 0110 (sa1100, xscale) */
+#define L_PTE_MT_WRITEALLOC	(_AT(pteval_t, 0x07) << 2)	/* 0111 */
+#define L_PTE_MT_DEV_SHARED	(_AT(pteval_t, 0x04) << 2)	/* 0100 */
+#define L_PTE_MT_DEV_NONSHARED	(_AT(pteval_t, 0x0c) << 2)	/* 1100 */
+#define L_PTE_MT_DEV_WC		(_AT(pteval_t, 0x09) << 2)	/* 1001 */
+#define L_PTE_MT_DEV_CACHED	(_AT(pteval_t, 0x0b) << 2)	/* 1011 */
+#define L_PTE_MT_MASK		(_AT(pteval_t, 0x0f) << 2)
+
+#endif /* _ASM_PGTABLE_2LEVEL_H */

arch/arm/include/asm/pgtable-hwdef.h

@@ -10,81 +10,6 @@
 #ifndef _ASMARM_PGTABLE_HWDEF_H
 #define _ASMARM_PGTABLE_HWDEF_H
 
-/*
- * Hardware page table definitions.
- *
- * + Level 1 descriptor (PMD)
- *   - common
- */
-#define PMD_TYPE_MASK		(3 << 0)
-#define PMD_TYPE_FAULT		(0 << 0)
-#define PMD_TYPE_TABLE		(1 << 0)
-#define PMD_TYPE_SECT		(2 << 0)
-#define PMD_BIT4		(1 << 4)
-#define PMD_DOMAIN(x)		((x) << 5)
-#define PMD_PROTECTION		(1 << 9)	/* v5 */
-/*
- *   - section
- */
-#define PMD_SECT_BUFFERABLE	(1 << 2)
-#define PMD_SECT_CACHEABLE	(1 << 3)
-#define PMD_SECT_XN		(1 << 4)	/* v6 */
-#define PMD_SECT_AP_WRITE	(1 << 10)
-#define PMD_SECT_AP_READ	(1 << 11)
-#define PMD_SECT_TEX(x)		((x) << 12)	/* v5 */
-#define PMD_SECT_APX		(1 << 15)	/* v6 */
-#define PMD_SECT_S		(1 << 16)	/* v6 */
-#define PMD_SECT_nG		(1 << 17)	/* v6 */
-#define PMD_SECT_SUPER		(1 << 18)	/* v6 */
-
-#define PMD_SECT_UNCACHED	(0)
-#define PMD_SECT_BUFFERED	(PMD_SECT_BUFFERABLE)
-#define PMD_SECT_WT		(PMD_SECT_CACHEABLE)
-#define PMD_SECT_WB		(PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
-#define PMD_SECT_MINICACHE	(PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE)
-#define PMD_SECT_WBWA		(PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
-#define PMD_SECT_NONSHARED_DEV	(PMD_SECT_TEX(2))
-
-/*
- *   - coarse table (not used)
- */
-
-/*
- * + Level 2 descriptor (PTE)
- *   - common
- */
-#define PTE_TYPE_MASK		(3 << 0)
-#define PTE_TYPE_FAULT		(0 << 0)
-#define PTE_TYPE_LARGE		(1 << 0)
-#define PTE_TYPE_SMALL		(2 << 0)
-#define PTE_TYPE_EXT		(3 << 0)	/* v5 */
-#define PTE_BUFFERABLE		(1 << 2)
-#define PTE_CACHEABLE		(1 << 3)
-
-/*
- *   - extended small page/tiny page
- */
-#define PTE_EXT_XN		(1 << 0)	/* v6 */
-#define PTE_EXT_AP_MASK		(3 << 4)
-#define PTE_EXT_AP0		(1 << 4)
-#define PTE_EXT_AP1		(2 << 4)
-#define PTE_EXT_AP_UNO_SRO	(0 << 4)
-#define PTE_EXT_AP_UNO_SRW	(PTE_EXT_AP0)
-#define PTE_EXT_AP_URO_SRW	(PTE_EXT_AP1)
-#define PTE_EXT_AP_URW_SRW	(PTE_EXT_AP1|PTE_EXT_AP0)
-#define PTE_EXT_TEX(x)		((x) << 6)	/* v5 */
-#define PTE_EXT_APX		(1 << 9)	/* v6 */
-#define PTE_EXT_COHERENT	(1 << 9)	/* XScale3 */
-#define PTE_EXT_SHARED		(1 << 10)	/* v6 */
-#define PTE_EXT_NG		(1 << 11)	/* v6 */
-
-/*
- *   - small page
- */
-#define PTE_SMALL_AP_MASK	(0xff << 4)
-#define PTE_SMALL_AP_UNO_SRO	(0x00 << 4)
-#define PTE_SMALL_AP_UNO_SRW	(0x55 << 4)
-#define PTE_SMALL_AP_URO_SRW	(0xaa << 4)
-#define PTE_SMALL_AP_URW_SRW	(0xff << 4)
+#include <asm/pgtable-2level-hwdef.h>
 
 #endif

arch/arm/include/asm/pgtable.h

@@ -24,6 +24,8 @@
 #include <mach/vmalloc.h>
 #include <asm/pgtable-hwdef.h>
 
+#include <asm/pgtable-2level.h>
+
 /*
  * Just any arbitrary offset to the start of the vmalloc VM area: the
  * current 8MB value just means that there will be a 8MB "hole" after the
@@ -41,79 +43,6 @@
 #define VMALLOC_START		(((unsigned long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))
 #endif
 
-/*
- * Hardware-wise, we have a two level page table structure, where the first
- * level has 4096 entries, and the second level has 256 entries.  Each entry
- * is one 32-bit word.  Most of the bits in the second level entry are used
- * by hardware, and there aren't any "accessed" and "dirty" bits.
- *
- * Linux on the other hand has a three level page table structure, which can
- * be wrapped to fit a two level page table structure easily - using the PGD
- * and PTE only.  However, Linux also expects one "PTE" table per page, and
- * at least a "dirty" bit.
- *
- * Therefore, we tweak the implementation slightly - we tell Linux that we
- * have 2048 entries in the first level, each of which is 8 bytes (iow, two
- * hardware pointers to the second level.)  The second level contains two
- * hardware PTE tables arranged contiguously, preceded by Linux versions
- * which contain the state information Linux needs.  We, therefore, end up
- * with 512 entries in the "PTE" level.
- *
- * This leads to the page tables having the following layout:
- *
- *    pgd             pte
- * |        |
- * +--------+
- * |        |       +------------+ +0
- * +- - - - +       | Linux pt 0 |
- * |        |       +------------+ +1024
- * +--------+ +0    | Linux pt 1 |
- * |        |-----> +------------+ +2048
- * +- - - - + +4    |  h/w pt 0  |
- * |        |-----> +------------+ +3072
- * +--------+ +8    |  h/w pt 1  |
- * |        |       +------------+ +4096
- *
- * See L_PTE_xxx below for definitions of bits in the "Linux pt", and
- * PTE_xxx for definitions of bits appearing in the "h/w pt".
- *
- * PMD_xxx definitions refer to bits in the first level page table.
- *
- * The "dirty" bit is emulated by only granting hardware write permission
- * iff the page is marked "writable" and "dirty" in the Linux PTE.  This
- * means that a write to a clean page will cause a permission fault, and
- * the Linux MM layer will mark the page dirty via handle_pte_fault().
- * For the hardware to notice the permission change, the TLB entry must
- * be flushed, and ptep_set_access_flags() does that for us.
- *
- * The "accessed" or "young" bit is emulated by a similar method; we only
- * allow accesses to the page if the "young" bit is set.  Accesses to the
- * page will cause a fault, and handle_pte_fault() will set the young bit
- * for us as long as the page is marked present in the corresponding Linux
- * PTE entry.  Again, ptep_set_access_flags() will ensure that the TLB is
- * up to date.
- *
- * However, when the "young" bit is cleared, we deny access to the page
- * by clearing the hardware PTE.  Currently Linux does not flush the TLB
- * for us in this case, which means the TLB will retain the transation
- * until either the TLB entry is evicted under pressure, or a context
- * switch which changes the user space mapping occurs.
- */
-#define PTRS_PER_PTE		512
-#define PTRS_PER_PMD		1
-#define PTRS_PER_PGD		2048
-
-#define PTE_HWTABLE_PTRS	(PTRS_PER_PTE)
-#define PTE_HWTABLE_OFF		(PTE_HWTABLE_PTRS * sizeof(pte_t))
-#define PTE_HWTABLE_SIZE	(PTRS_PER_PTE * sizeof(u32))
-
-/*
- * PMD_SHIFT determines the size of the area a second-level page table can map
- * PGDIR_SHIFT determines what a third-level page table entry can map
- */
-#define PMD_SHIFT		21
-#define PGDIR_SHIFT		21
-
 #define LIBRARY_TEXT_START	0x0c000000
 
 #ifndef __ASSEMBLY__
@@ -124,12 +53,6 @@ extern void __pgd_error(const char *file, int line, pgd_t);
 #define pte_ERROR(pte)		__pte_error(__FILE__, __LINE__, pte)
 #define pmd_ERROR(pmd)		__pmd_error(__FILE__, __LINE__, pmd)
 #define pgd_ERROR(pgd)		__pgd_error(__FILE__, __LINE__, pgd)
-#endif /* !__ASSEMBLY__ */
-
-#define PMD_SIZE		(1UL << PMD_SHIFT)
-#define PMD_MASK		(~(PMD_SIZE-1))
-#define PGDIR_SIZE		(1UL << PGDIR_SHIFT)
-#define PGDIR_MASK		(~(PGDIR_SIZE-1))
 
 /*
  * This is the lowest virtual address we can permit any user space
@@ -138,60 +61,6 @@ extern void __pgd_error(const char *file, int line, pgd_t);
  */
 #define FIRST_USER_ADDRESS	PAGE_SIZE
 
-#define USER_PTRS_PER_PGD	(TASK_SIZE / PGDIR_SIZE)
-
-/*
- * section address mask and size definitions.
- */
-#define SECTION_SHIFT		20
-#define SECTION_SIZE		(1UL << SECTION_SHIFT)
-#define SECTION_MASK		(~(SECTION_SIZE-1))
-
-/*
- * ARMv6 supersection address mask and size definitions.
- */
-#define SUPERSECTION_SHIFT	24
-#define SUPERSECTION_SIZE	(1UL << SUPERSECTION_SHIFT)
-#define SUPERSECTION_MASK	(~(SUPERSECTION_SIZE-1))
-
-/*
- * "Linux" PTE definitions.
- *
- * We keep two sets of PTEs - the hardware and the linux version.
- * This allows greater flexibility in the way we map the Linux bits
- * onto the hardware tables, and allows us to have YOUNG and DIRTY
- * bits.
- *
- * The PTE table pointer refers to the hardware entries; the "Linux"
- * entries are stored 1024 bytes below.
- */
-#define L_PTE_PRESENT		(_AT(pteval_t, 1) << 0)
-#define L_PTE_YOUNG		(_AT(pteval_t, 1) << 1)
-#define L_PTE_FILE		(_AT(pteval_t, 1) << 2)	/* only when !PRESENT */
-#define L_PTE_DIRTY		(_AT(pteval_t, 1) << 6)
-#define L_PTE_RDONLY		(_AT(pteval_t, 1) << 7)
-#define L_PTE_USER		(_AT(pteval_t, 1) << 8)
-#define L_PTE_XN		(_AT(pteval_t, 1) << 9)
-#define L_PTE_SHARED		(_AT(pteval_t, 1) << 10)	/* shared(v6), coherent(xsc3) */
-
-/*
- * These are the memory types, defined to be compatible with
- * pre-ARMv6 CPUs cacheable and bufferable bits:   XXCB
- */
-#define L_PTE_MT_UNCACHED	(_AT(pteval_t, 0x00) << 2)	/* 0000 */
-#define L_PTE_MT_BUFFERABLE	(_AT(pteval_t, 0x01) << 2)	/* 0001 */
-#define L_PTE_MT_WRITETHROUGH	(_AT(pteval_t, 0x02) << 2)	/* 0010 */
-#define L_PTE_MT_WRITEBACK	(_AT(pteval_t, 0x03) << 2)	/* 0011 */
-#define L_PTE_MT_MINICACHE	(_AT(pteval_t, 0x06) << 2)	/* 0110 (sa1100, xscale) */
-#define L_PTE_MT_WRITEALLOC	(_AT(pteval_t, 0x07) << 2)	/* 0111 */
-#define L_PTE_MT_DEV_SHARED	(_AT(pteval_t, 0x04) << 2)	/* 0100 */
-#define L_PTE_MT_DEV_NONSHARED	(_AT(pteval_t, 0x0c) << 2)	/* 1100 */
-#define L_PTE_MT_DEV_WC		(_AT(pteval_t, 0x09) << 2)	/* 1001 */
-#define L_PTE_MT_DEV_CACHED	(_AT(pteval_t, 0x0b) << 2)	/* 1011 */
-#define L_PTE_MT_MASK		(_AT(pteval_t, 0x0f) << 2)
-
-#ifndef __ASSEMBLY__
-
 /*
  * The pgprot_* and protection_map entries will be fixed up in runtime
  * to include the cachable and bufferable bits based on memory policy,
@@ -327,10 +196,10 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 
 static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 {
-	return __va(pmd_val(pmd) & PAGE_MASK);
+	return __va(pmd_val(pmd) & PHYS_MASK & (s32)PAGE_MASK);
 }
 
-#define pmd_page(pmd)		pfn_to_page(__phys_to_pfn(pmd_val(pmd)))
+#define pmd_page(pmd)		pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK))
 
 /* we don't need complex calculations here as the pmd is folded into the pgd */
 #define pmd_addr_end(addr,end)	(end)
@@ -351,7 +220,7 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 #define pte_offset_map(pmd,addr)	(__pte_map(pmd) + pte_index(addr))
 #define pte_unmap(pte)			__pte_unmap(pte)
 
-#define pte_pfn(pte)		(pte_val(pte) >> PAGE_SHIFT)
+#define pte_pfn(pte)		((pte_val(pte) & PHYS_MASK) >> PAGE_SHIFT)
 #define pfn_pte(pfn,prot)	__pte(__pfn_to_phys(pfn) | pgprot_val(prot))
 
 #define pte_page(pte)		pfn_to_page(pte_pfn(pte))

arch/arm/include/asm/smp.h

@@ -32,6 +32,11 @@ extern void show_ipi_list(struct seq_file *, int);
  */
 asmlinkage void do_IPI(int ipinr, struct pt_regs *regs);
 
+/*
+ * Called from C code, this handles an IPI.
+ */
+void handle_IPI(int ipinr, struct pt_regs *regs);
+
 /*
  * Setup the set of possible CPUs (via set_cpu_possible)
  */
@@ -65,6 +70,12 @@ extern void platform_secondary_init(unsigned int cpu);
  */
 extern void platform_smp_prepare_cpus(unsigned int);
 
+/*
+ * Logical CPU mapping.
+ */
+extern int __cpu_logical_map[NR_CPUS];
+#define cpu_logical_map(cpu)	__cpu_logical_map[cpu]
+
 /*
  * Initial data for bringing up a secondary CPU.
  */

arch/arm/include/asm/system.h

@@ -62,13 +62,6 @@
 
 #include <asm/outercache.h>
 
-#define __exception	__attribute__((section(".exception.text")))
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-#define __exception_irq_entry	__irq_entry
-#else
-#define __exception_irq_entry	__exception
-#endif
-
 struct thread_info;
 struct task_struct;
 

arch/arm/include/asm/tlbflush.h

@@ -471,7 +471,7 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
  *	these operations.  This is typically used when we are removing
  *	PMD entries.
  */
-static inline void flush_pmd_entry(pmd_t *pmd)
+static inline void flush_pmd_entry(void *pmd)
 {
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
@@ -487,7 +487,7 @@ static inline void flush_pmd_entry(pmd_t *pmd)
 		dsb();
 }
 
-static inline void clean_pmd_entry(pmd_t *pmd)
+static inline void clean_pmd_entry(void *pmd)
 {
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 

arch/arm/include/asm/topology.h

 #ifndef _ASM_ARM_TOPOLOGY_H
 #define _ASM_ARM_TOPOLOGY_H
 
+#ifdef CONFIG_ARM_CPU_TOPOLOGY
+
+#include <linux/cpumask.h>
+
+struct cputopo_arm {
+	int thread_id;
+	int core_id;
+	int socket_id;
+	cpumask_t thread_sibling;
+	cpumask_t core_sibling;
+};
+
+extern struct cputopo_arm cpu_topology[NR_CPUS];
+
+#define topology_physical_package_id(cpu)	(cpu_topology[cpu].socket_id)
+#define topology_core_id(cpu)		(cpu_topology[cpu].core_id)
+#define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
+#define topology_thread_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
+
+#define mc_capable()	(cpu_topology[0].socket_id != -1)
+#define smt_capable()	(cpu_topology[0].thread_id != -1)
+
+void init_cpu_topology(void);
+void store_cpu_topology(unsigned int cpuid);
+const struct cpumask *cpu_coregroup_mask(unsigned int cpu);
+
+#else
+
+static inline void init_cpu_topology(void) { }
+static inline void store_cpu_topology(unsigned int cpuid) { }
+
+#endif
+
 #include <asm-generic/topology.h>
 
 #endif /* _ASM_ARM_TOPOLOGY_H */

arch/arm/kernel/Makefile

@@ -29,7 +29,7 @@ obj-$(CONFIG_MODULES)		+= armksyms.o module.o
 obj-$(CONFIG_ARTHUR)		+= arthur.o
 obj-$(CONFIG_ISA_DMA)		+= dma-isa.o
 obj-$(CONFIG_PCI)		+= bios32.o isa.o
-obj-$(CONFIG_PM_SLEEP)		+= sleep.o
+obj-$(CONFIG_ARM_CPU_SUSPEND)	+= sleep.o
 obj-$(CONFIG_HAVE_SCHED_CLOCK)	+= sched_clock.o
 obj-$(CONFIG_SMP)		+= smp.o smp_tlb.o
 obj-$(CONFIG_HAVE_ARM_SCU)	+= smp_scu.o
@@ -66,6 +66,7 @@ obj-$(CONFIG_IWMMXT)		+= iwmmxt.o
 obj-$(CONFIG_CPU_HAS_PMU)	+= pmu.o
 obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o
 AFLAGS_iwmmxt.o			:= -Wa,-mcpu=iwmmxt
+obj-$(CONFIG_ARM_CPU_TOPOLOGY)  += topology.o
 
 ifneq ($(CONFIG_ARCH_EBSA110),y)
   obj-y		+= io.o

arch/arm/kernel/asm-offsets.c

@@ -20,6 +20,7 @@
 #include <asm/thread_info.h>
 #include <asm/memory.h>
 #include <asm/procinfo.h>
+#include <asm/hardware/cache-l2x0.h>
 #include <linux/kbuild.h>
 
 /*
@@ -92,6 +93,17 @@ int main(void)
   DEFINE(S_OLD_R0,		offsetof(struct pt_regs, ARM_ORIG_r0));
   DEFINE(S_FRAME_SIZE,		sizeof(struct pt_regs));
   BLANK();
+#ifdef CONFIG_CACHE_L2X0
+  DEFINE(L2X0_R_PHY_BASE,	offsetof(struct l2x0_regs, phy_base));
+  DEFINE(L2X0_R_AUX_CTRL,	offsetof(struct l2x0_regs, aux_ctrl));
+  DEFINE(L2X0_R_TAG_LATENCY,	offsetof(struct l2x0_regs, tag_latency));
+  DEFINE(L2X0_R_DATA_LATENCY,	offsetof(struct l2x0_regs, data_latency));
+  DEFINE(L2X0_R_FILTER_START,	offsetof(struct l2x0_regs, filter_start));
+  DEFINE(L2X0_R_FILTER_END,	offsetof(struct l2x0_regs, filter_end));
+  DEFINE(L2X0_R_PREFETCH_CTRL,	offsetof(struct l2x0_regs, prefetch_ctrl));
+  DEFINE(L2X0_R_PWR_CTRL,	offsetof(struct l2x0_regs, pwr_ctrl));
+  BLANK();
+#endif
 #ifdef CONFIG_CPU_HAS_ASID
   DEFINE(MM_CONTEXT_ID,		offsetof(struct mm_struct, context.id));
   BLANK();

arch/arm/kernel/bios32.c

@@ -412,6 +412,9 @@ void pcibios_fixup_bus(struct pci_bus *bus)
 	printk(KERN_INFO "PCI: bus%d: Fast back to back transfers %sabled\n",
 		bus->number, (features & PCI_COMMAND_FAST_BACK) ? "en" : "dis");
 }
+#ifdef CONFIG_HOTPLUG
+EXPORT_SYMBOL(pcibios_fixup_bus);
+#endif
 
 /*
  * Convert from Linux-centric to bus-centric addresses for bridge devices.
@@ -431,6 +434,7 @@ pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region,
 	region->start = res->start - offset;
 	region->end   = res->end - offset;
 }
+EXPORT_SYMBOL(pcibios_resource_to_bus);
 
 void __devinit
 pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res,
@@ -447,12 +451,7 @@ pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res,
 	res->start = region->start + offset;
 	res->end   = region->end + offset;
 }
-
-#ifdef CONFIG_HOTPLUG
-EXPORT_SYMBOL(pcibios_fixup_bus);
-EXPORT_SYMBOL(pcibios_resource_to_bus);
 EXPORT_SYMBOL(pcibios_bus_to_resource);
-#endif
 
 /*
  * Swizzle the device pin each time we cross a bridge.

arch/arm/kernel/ecard.c

@@ -237,7 +237,7 @@ static void ecard_init_pgtables(struct mm_struct *mm)
 
 	memcpy(dst_pgd, src_pgd, sizeof(pgd_t) * (IO_SIZE / PGDIR_SIZE));
 
-	src_pgd = pgd_offset(mm, EASI_BASE);
+	src_pgd = pgd_offset(mm, (unsigned long)EASI_BASE);
 	dst_pgd = pgd_offset(mm, EASI_START);
 
 	memcpy(dst_pgd, src_pgd, sizeof(pgd_t) * (EASI_SIZE / PGDIR_SIZE));
@@ -674,44 +674,37 @@ static int __init ecard_probeirqhw(void)
 #define ecard_probeirqhw() (0)
 #endif
 
-#ifndef IO_EC_MEMC8_BASE
-#define IO_EC_MEMC8_BASE 0
-#endif
-
-static unsigned int __ecard_address(ecard_t *ec, card_type_t type, card_speed_t speed)
+static void __iomem *__ecard_address(ecard_t *ec, card_type_t type, card_speed_t speed)
 {
-	unsigned long address = 0;
+	void __iomem *address = NULL;
 	int slot = ec->slot_no;
 
 	if (ec->slot_no == 8)
-		return IO_EC_MEMC8_BASE;
+		return ECARD_MEMC8_BASE;
 
 	ectcr &= ~(1 << slot);
 
 	switch (type) {
 	case ECARD_MEMC:
 		if (slot < 4)
-			address = IO_EC_MEMC_BASE + (slot << 12);
+			address = ECARD_MEMC_BASE + (slot << 14);
 		break;
 
 	case ECARD_IOC:
 		if (slot < 4)
-			address = IO_EC_IOC_BASE + (slot << 12);
-#ifdef IO_EC_IOC4_BASE
+			address = ECARD_IOC_BASE + (slot << 14);
 		else
-			address = IO_EC_IOC4_BASE + ((slot - 4) << 12);
-#endif
+			address = ECARD_IOC4_BASE + ((slot - 4) << 14);
 		if (address)
-			address +=  speed << 17;
+			address += speed << 19;
 		break;
 
-#ifdef IO_EC_EASI_BASE
 	case ECARD_EASI:
-		address = IO_EC_EASI_BASE + (slot << 22);
+		address = ECARD_EASI_BASE + (slot << 24);
 		if (speed == ECARD_FAST)
 			ectcr |= 1 << slot;
 		break;
-#endif
+
 	default:
 		break;
 	}
@@ -990,6 +983,7 @@ ecard_probe(int slot, card_type_t type)
 	ecard_t **ecp;
 	ecard_t *ec;
 	struct ex_ecid cid;
+	void __iomem *addr;
 	int i, rc;
 
 	ec = ecard_alloc_card(type, slot);
@@ -999,7 +993,7 @@ ecard_probe(int slot, card_type_t type)
 	}
 
 	rc = -ENODEV;
-	if ((ec->podaddr = __ecard_address(ec, type, ECARD_SYNC)) == 0)
+	if ((addr = __ecard_address(ec, type, ECARD_SYNC)) == NULL)
 		goto nodev;
 
 	cid.r_zero = 1;
@@ -1019,7 +1013,7 @@ ecard_probe(int slot, card_type_t type)
 	ec->cid.fiqmask = cid.r_fiqmask;
 	ec->cid.fiqoff  = ecard_gets24(cid.r_fiqoff);
 	ec->fiqaddr	=
-	ec->irqaddr	= (void __iomem *)ioaddr(ec->podaddr);
+	ec->irqaddr	= addr;
 
 	if (ec->cid.is) {
 		ec->irqmask = ec->cid.irqmask;
@@ -1048,10 +1042,8 @@ ecard_probe(int slot, card_type_t type)
 		set_irq_flags(ec->irq, IRQF_VALID);
 	}
 
-#ifdef IO_EC_MEMC8_BASE
 	if (slot == 8)
 		ec->irq = 11;
-#endif
 #ifdef CONFIG_ARCH_RPC
 	/* On RiscPC, only first two slots have DMA capability */
 	if (slot < 2)
@@ -1097,9 +1089,7 @@ static int __init ecard_init(void)
 			ecard_probe(slot, ECARD_IOC);
 	}
 
-#ifdef IO_EC_MEMC8_BASE
 	ecard_probe(8, ECARD_IOC);
-#endif
 
 	irqhw = ecard_probeirqhw();
 

arch/arm/kernel/head.S

@@ -21,6 +21,7 @@
 #include <asm/memory.h>
 #include <asm/thread_info.h>
 #include <asm/system.h>
+#include <asm/pgtable.h>
 
 #ifdef CONFIG_DEBUG_LL
 #include <mach/debug-macro.S>
@@ -38,11 +39,14 @@
 #error KERNEL_RAM_VADDR must start at 0xXXXX8000
 #endif
 
+#define PG_DIR_SIZE	0x4000
+#define PMD_ORDER	2
+
 	.globl	swapper_pg_dir
-	.equ	swapper_pg_dir, KERNEL_RAM_VADDR - 0x4000
+	.equ	swapper_pg_dir, KERNEL_RAM_VADDR - PG_DIR_SIZE
 
 	.macro	pgtbl, rd, phys
-	add	\rd, \phys, #TEXT_OFFSET - 0x4000
+	add	\rd, \phys, #TEXT_OFFSET - PG_DIR_SIZE
 	.endm
 
 #ifdef CONFIG_XIP_KERNEL
@@ -148,11 +152,11 @@ __create_page_tables:
 	pgtbl	r4, r8				@ page table address
 
 	/*
-	 * Clear the 16K level 1 swapper page table
+	 * Clear the swapper page table
 	 */
 	mov	r0, r4
 	mov	r3, #0
-	add	r6, r0, #0x4000
+	add	r6, r0, #PG_DIR_SIZE
 1:	str	r3, [r0], #4
 	str	r3, [r0], #4
 	str	r3, [r0], #4
@@ -171,30 +175,30 @@ __create_page_tables:
 	sub	r0, r0, r3			@ virt->phys offset
 	add	r5, r5, r0			@ phys __enable_mmu
 	add	r6, r6, r0			@ phys __enable_mmu_end
-	mov	r5, r5, lsr #20
-	mov	r6, r6, lsr #20
+	mov	r5, r5, lsr #SECTION_SHIFT
+	mov	r6, r6, lsr #SECTION_SHIFT
 
-1:	orr	r3, r7, r5, lsl #20		@ flags + kernel base
-	str	r3, [r4, r5, lsl #2]		@ identity mapping
-	teq	r5, r6
-	addne	r5, r5, #1			@ next section
-	bne	1b
+1:	orr	r3, r7, r5, lsl #SECTION_SHIFT	@ flags + kernel base
+	str	r3, [r4, r5, lsl #PMD_ORDER]	@ identity mapping
+	cmp	r5, r6
+	addlo	r5, r5, #1			@ next section
+	blo	1b
 
 	/*
 	 * Now setup the pagetables for our kernel direct
 	 * mapped region.
 	 */
 	mov	r3, pc
-	mov	r3, r3, lsr #20
-	orr	r3, r7, r3, lsl #20
-	add	r0, r4,  #(KERNEL_START & 0xff000000) >> 18
-	str	r3, [r0, #(KERNEL_START & 0x00f00000) >> 18]!
+	mov	r3, r3, lsr #SECTION_SHIFT
+	orr	r3, r7, r3, lsl #SECTION_SHIFT
+	add	r0, r4,  #(KERNEL_START & 0xff000000) >> (SECTION_SHIFT - PMD_ORDER)
+	str	r3, [r0, #((KERNEL_START & 0x00f00000) >> SECTION_SHIFT) << PMD_ORDER]!
 	ldr	r6, =(KERNEL_END - 1)
-	add	r0, r0, #4
-	add	r6, r4, r6, lsr #18
+	add	r0, r0, #1 << PMD_ORDER
+	add	r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ORDER)
 1:	cmp	r0, r6
-	add	r3, r3, #1 << 20
-	strls	r3, [r0], #4
+	add	r3, r3, #1 << SECTION_SHIFT
+	strls	r3, [r0], #1 << PMD_ORDER
 	bls	1b
 
 #ifdef CONFIG_XIP_KERNEL
@@ -203,11 +207,11 @@ __create_page_tables:
 	 */
 	add	r3, r8, #TEXT_OFFSET
 	orr	r3, r3, r7
-	add	r0, r4,  #(KERNEL_RAM_VADDR & 0xff000000) >> 18
-	str	r3, [r0, #(KERNEL_RAM_VADDR & 0x00f00000) >> 18]!
+	add	r0, r4,  #(KERNEL_RAM_VADDR & 0xff000000) >> (SECTION_SHIFT - PMD_ORDER)
+	str	r3, [r0, #(KERNEL_RAM_VADDR & 0x00f00000) >> (SECTION_SHIFT - PMD_ORDER)]!
 	ldr	r6, =(_end - 1)
 	add	r0, r0, #4
-	add	r6, r4, r6, lsr #18
+	add	r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ORDER)
 1:	cmp	r0, r6
 	add	r3, r3, #1 << 20
 	strls	r3, [r0], #4
@@ -218,12 +222,12 @@ __create_page_tables:
 	 * Then map boot params address in r2 or
 	 * the first 1MB of ram if boot params address is not specified.
 	 */
-	mov	r0, r2, lsr #20
-	movs	r0, r0, lsl #20
+	mov	r0, r2, lsr #SECTION_SHIFT
+	movs	r0, r0, lsl #SECTION_SHIFT
 	moveq	r0, r8
 	sub	r3, r0, r8
 	add	r3, r3, #PAGE_OFFSET
-	add	r3, r4, r3, lsr #18
+	add	r3, r4, r3, lsr #(SECTION_SHIFT - PMD_ORDER)
 	orr	r6, r7, r0
 	str	r6, [r3]
 
@@ -236,21 +240,21 @@ __create_page_tables:
 	 */
 	addruart r7, r3
 
-	mov	r3, r3, lsr #20
-	mov	r3, r3, lsl #2
+	mov	r3, r3, lsr #SECTION_SHIFT
+	mov	r3, r3, lsl #PMD_ORDER
 
 	add	r0, r4, r3
 	rsb	r3, r3, #0x4000			@ PTRS_PER_PGD*sizeof(long)
 	cmp	r3, #0x0800			@ limit to 512MB
 	movhi	r3, #0x0800
 	add	r6, r0, r3
-	mov	r3, r7, lsr #20
+	mov	r3, r7, lsr #SECTION_SHIFT
 	ldr	r7, [r10, #PROCINFO_IO_MMUFLAGS] @ io_mmuflags
-	orr	r3, r7, r3, lsl #20
+	orr	r3, r7, r3, lsl #SECTION_SHIFT
 1:	str	r3, [r0], #4
-	add	r3, r3, #1 << 20
-	teq	r0, r6
-	bne	1b
+	add	r3, r3, #1 << SECTION_SHIFT
+	cmp	r0, r6
+	blo	1b
 
 #else /* CONFIG_DEBUG_ICEDCC */
 	/* we don't need any serial debugging mappings for ICEDCC */
@@ -262,7 +266,7 @@ __create_page_tables:
 	 * If we're using the NetWinder or CATS, we also need to map
 	 * in the 16550-type serial port for the debug messages
 	 */
-	add	r0, r4, #0xff000000 >> 18
+	add	r0, r4, #0xff000000 >> (SECTION_SHIFT - PMD_ORDER)
 	orr	r3, r7, #0x7c000000
 	str	r3, [r0]
 #endif
@@ -272,10 +276,10 @@ __create_page_tables:
 	 * Similar reasons here - for debug.  This is
 	 * only for Acorn RiscPC architectures.
 	 */
-	add	r0, r4, #0x02000000 >> 18
+	add	r0, r4, #0x02000000 >> (SECTION_SHIFT - PMD_ORDER)
 	orr	r3, r7, #0x02000000
 	str	r3, [r0]
-	add	r0, r4, #0xd8000000 >> 18
+	add	r0, r4, #0xd8000000 >> (SECTION_SHIFT - PMD_ORDER)
 	str	r3, [r0]
 #endif
 #endif
@@ -488,13 +492,8 @@ __fixup_pv_table:
 	add	r5, r5, r3	@ adjust table end address
 	add	r7, r7, r3	@ adjust __pv_phys_offset address
 	str	r8, [r7]	@ save computed PHYS_OFFSET to __pv_phys_offset
-#ifndef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT
 	mov	r6, r3, lsr #24	@ constant for add/sub instructions
 	teq	r3, r6, lsl #24 @ must be 16MiB aligned
-#else
-	mov	r6, r3, lsr #16	@ constant for add/sub instructions
-	teq	r3, r6, lsl #16	@ must be 64kiB aligned
-#endif
 THUMB(	it	ne		@ cross section branch )
 	bne	__error
 	str	r6, [r7, #4]	@ save to __pv_offset
@@ -510,20 +509,8 @@ ENDPROC(__fixup_pv_table)
 	.text
 __fixup_a_pv_table:
 #ifdef CONFIG_THUMB2_KERNEL
-#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT
-	lsls	r0, r6, #24
-	lsr	r6, #8
-	beq	1f
-	clz	r7, r0
-	lsr	r0, #24
-	lsl	r0, r7
-	bic	r0, 0x0080
-	lsrs	r7, #1
-	orrcs   r0, #0x0080
-	orr	r0, r0, r7, lsl #12
-#endif
-1:	lsls	r6, #24
-	beq	4f
+	lsls	r6, #24
+	beq	2f
 	clz	r7, r6
 	lsr	r6, #24
 	lsl	r6, r7
@@ -532,43 +519,25 @@ __fixup_a_pv_table:
 	orrcs	r6, #0x0080
 	orr	r6, r6, r7, lsl #12
 	orr	r6, #0x4000
-	b	4f
-2:	@ at this point the C flag is always clear
-	add     r7, r3
-#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT
-	ldrh	ip, [r7]
-	tst	ip, 0x0400	@ the i bit tells us LS or MS byte
-	beq	3f
-	cmp	r0, #0		@ set C flag, and ...
-	biceq	ip, 0x0400	@ immediate zero value has a special encoding
-	streqh	ip, [r7]	@ that requires the i bit cleared
-#endif
-3:	ldrh	ip, [r7, #2]
+	b	2f
+1:	add     r7, r3
+	ldrh	ip, [r7, #2]
 	and	ip, 0x8f00
-	orrcc	ip, r6	@ mask in offset bits 31-24
-	orrcs	ip, r0	@ mask in offset bits 23-16
+	orr	ip, r6	@ mask in offset bits 31-24
 	strh	ip, [r7, #2]
-4:	cmp	r4, r5
+2:	cmp	r4, r5
 	ldrcc	r7, [r4], #4	@ use branch for delay slot
-	bcc	2b
+	bcc	1b
 	bx	lr
 #else
-#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT
-	and	r0, r6, #255	@ offset bits 23-16
-	mov	r6, r6, lsr #8	@ offset bits 31-24
-#else
-	mov	r0, #0		@ just in case...
-#endif
-	b	3f
-2:	ldr	ip, [r7, r3]
+	b	2f
+1:	ldr	ip, [r7, r3]
 	bic	ip, ip, #0x000000ff
-	tst	ip, #0x400	@ rotate shift tells us LS or MS byte
-	orrne	ip, ip, r6	@ mask in offset bits 31-24
-	orreq	ip, ip, r0	@ mask in offset bits 23-16
+	orr	ip, ip, r6	@ mask in offset bits 31-24
 	str	ip, [r7, r3]
-3:	cmp	r4, r5
+2:	cmp	r4, r5
 	ldrcc	r7, [r4], #4	@ use branch for delay slot
-	bcc	2b
+	bcc	1b
 	mov	pc, lr
 #endif
 ENDPROC(__fixup_a_pv_table)

arch/arm/kernel/irq.c

@@ -35,8 +35,8 @@
 #include <linux/list.h>
 #include <linux/kallsyms.h>
 #include <linux/proc_fs.h>
-#include <linux/ftrace.h>
 
+#include <asm/exception.h>
 #include <asm/system.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/irq.h>

arch/arm/kernel/module.c

@@ -33,7 +33,7 @@
  * recompiling the whole kernel when CONFIG_XIP_KERNEL is turned on/off.
  */
 #undef MODULES_VADDR
-#define MODULES_VADDR	(((unsigned long)_etext + ~PGDIR_MASK) & PGDIR_MASK)
+#define MODULES_VADDR	(((unsigned long)_etext + ~PMD_MASK) & PMD_MASK)
 #endif
 
 #ifdef CONFIG_MMU

arch/arm/kernel/smp.c

@@ -16,7 +16,6 @@
 #include <linux/cache.h>
 #include <linux/profile.h>
 #include <linux/errno.h>
-#include <linux/ftrace.h>
 #include <linux/mm.h>
 #include <linux/err.h>
 #include <linux/cpu.h>
@@ -31,6 +30,8 @@
 #include <asm/cacheflush.h>
 #include <asm/cpu.h>
 #include <asm/cputype.h>
+#include <asm/exception.h>
+#include <asm/topology.h>
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -39,6 +40,7 @@
 #include <asm/tlbflush.h>
 #include <asm/ptrace.h>
 #include <asm/localtimer.h>
+#include <asm/smp_plat.h>
 
 /*
  * as from 2.5, kernels no longer have an init_tasks structure
@@ -259,6 +261,20 @@ void __ref cpu_die(void)
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
+int __cpu_logical_map[NR_CPUS];
+
+void __init smp_setup_processor_id(void)
+{
+	int i;
+	u32 cpu = is_smp() ? read_cpuid_mpidr() & 0xff : 0;
+
+	cpu_logical_map(0) = cpu;
+	for (i = 1; i < NR_CPUS; ++i)
+		cpu_logical_map(i) = i == cpu ? 0 : i;
+
+	printk(KERN_INFO "Booting Linux on physical CPU %d\n", cpu);
+}
+
 /*
  * Called by both boot and secondaries to move global data into
  * per-processor storage.
@@ -268,6 +284,8 @@ static void __cpuinit smp_store_cpu_info(unsigned int cpuid)
 	struct cpuinfo_arm *cpu_info = &per_cpu(cpu_data, cpuid);
 
 	cpu_info->loops_per_jiffy = loops_per_jiffy;
+
+	store_cpu_topology(cpuid);
 }
 
 /*
@@ -358,6 +376,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 {
 	unsigned int ncores = num_possible_cpus();
 
+	init_cpu_topology();
+
 	smp_store_cpu_info(smp_processor_id());
 
 	/*
@@ -459,6 +479,11 @@ static void ipi_timer(void)
 
 #ifdef CONFIG_LOCAL_TIMERS
 asmlinkage void __exception_irq_entry do_local_timer(struct pt_regs *regs)
+{
+	handle_local_timer(regs);
+}
+
+void handle_local_timer(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 	int cpu = smp_processor_id();
@@ -566,6 +591,11 @@ static void ipi_cpu_stop(unsigned int cpu)
  * Main handler for inter-processor interrupts
  */
 asmlinkage void __exception_irq_entry do_IPI(int ipinr, struct pt_regs *regs)
+{
+	handle_IPI(ipinr, regs);
+}
+
+void handle_IPI(int ipinr, struct pt_regs *regs)
 {
 	unsigned int cpu = smp_processor_id();
 	struct pt_regs *old_regs = set_irq_regs(regs);

arch/arm/kernel/smp_scu.c

@@ -34,7 +34,7 @@ unsigned int __init scu_get_core_count(void __iomem *scu_base)
 /*
  * Enable the SCU
  */
-void __init scu_enable(void __iomem *scu_base)
+void scu_enable(void __iomem *scu_base)
 {
 	u32 scu_ctrl;
 

arch/arm/kernel/time.c

@@ -39,13 +39,11 @@
  */
 static struct sys_timer *system_timer;
 
-#if defined(CONFIG_RTC_DRV_CMOS) || defined(CONFIG_RTC_DRV_CMOS_MODULE)
+#if defined(CONFIG_RTC_DRV_CMOS) || defined(CONFIG_RTC_DRV_CMOS_MODULE) || \
+    defined(CONFIG_NVRAM) || defined(CONFIG_NVRAM_MODULE)
 /* this needs a better home */
 DEFINE_SPINLOCK(rtc_lock);
-
-#ifdef CONFIG_RTC_DRV_CMOS_MODULE
 EXPORT_SYMBOL(rtc_lock);
-#endif
 #endif	/* pc-style 'CMOS' RTC support */
 
 /* change this if you have some constant time drift */

arch/arm/kernel/topology.c

+/*
+ * arch/arm/kernel/topology.c
+ *
+ * Copyright (C) 2011 Linaro Limited.
+ * Written by: Vincent Guittot
+ *
+ * based on arch/sh/kernel/topology.c
+ *
+ * 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.
+ */
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/init.h>
+#include <linux/percpu.h>
+#include <linux/node.h>
+#include <linux/nodemask.h>
+#include <linux/sched.h>
+
+#include <asm/cputype.h>
+#include <asm/topology.h>
+
+#define MPIDR_SMP_BITMASK (0x3 << 30)
+#define MPIDR_SMP_VALUE (0x2 << 30)
+
+#define MPIDR_MT_BITMASK (0x1 << 24)
+
+/*
+ * These masks reflect the current use of the affinity levels.
+ * The affinity level can be up to 16 bits according to ARM ARM
+ */
+
+#define MPIDR_LEVEL0_MASK 0x3
+#define MPIDR_LEVEL0_SHIFT 0
+
+#define MPIDR_LEVEL1_MASK 0xF
+#define MPIDR_LEVEL1_SHIFT 8
+
+#define MPIDR_LEVEL2_MASK 0xFF
+#define MPIDR_LEVEL2_SHIFT 16
+
+struct cputopo_arm cpu_topology[NR_CPUS];
+
+const struct cpumask *cpu_coregroup_mask(unsigned int cpu)
+{
+	return &cpu_topology[cpu].core_sibling;
+}
+
+/*
+ * store_cpu_topology is called at boot when only one cpu is running
+ * and with the mutex cpu_hotplug.lock locked, when several cpus have booted,
+ * which prevents simultaneous write access to cpu_topology array
+ */
+void store_cpu_topology(unsigned int cpuid)
+{
+	struct cputopo_arm *cpuid_topo = &cpu_topology[cpuid];
+	unsigned int mpidr;
+	unsigned int cpu;
+
+	/* If the cpu topology has been already set, just return */
+	if (cpuid_topo->core_id != -1)
+		return;
+
+	mpidr = read_cpuid_mpidr();
+
+	/* create cpu topology mapping */
+	if ((mpidr & MPIDR_SMP_BITMASK) == MPIDR_SMP_VALUE) {
+		/*
+		 * This is a multiprocessor system
+		 * multiprocessor format & multiprocessor mode field are set
+		 */
+
+		if (mpidr & MPIDR_MT_BITMASK) {
+			/* core performance interdependency */
+			cpuid_topo->thread_id = (mpidr >> MPIDR_LEVEL0_SHIFT)
+				& MPIDR_LEVEL0_MASK;
+			cpuid_topo->core_id = (mpidr >> MPIDR_LEVEL1_SHIFT)
+				& MPIDR_LEVEL1_MASK;
+			cpuid_topo->socket_id = (mpidr >> MPIDR_LEVEL2_SHIFT)
+				& MPIDR_LEVEL2_MASK;
+		} else {
+			/* largely independent cores */
+			cpuid_topo->thread_id = -1;
+			cpuid_topo->core_id = (mpidr >> MPIDR_LEVEL0_SHIFT)
+				& MPIDR_LEVEL0_MASK;
+			cpuid_topo->socket_id = (mpidr >> MPIDR_LEVEL1_SHIFT)
+				& MPIDR_LEVEL1_MASK;
+		}
+	} else {
+		/*
+		 * This is an uniprocessor system
+		 * we are in multiprocessor format but uniprocessor system
+		 * or in the old uniprocessor format
+		 */
+		cpuid_topo->thread_id = -1;
+		cpuid_topo->core_id = 0;
+		cpuid_topo->socket_id = -1;
+	}
+
+	/* update core and thread sibling masks */
+	for_each_possible_cpu(cpu) {
+		struct cputopo_arm *cpu_topo = &cpu_topology[cpu];
+
+		if (cpuid_topo->socket_id == cpu_topo->socket_id) {
+			cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
+			if (cpu != cpuid)
+				cpumask_set_cpu(cpu,
+					&cpuid_topo->core_sibling);
+
+			if (cpuid_topo->core_id == cpu_topo->core_id) {
+				cpumask_set_cpu(cpuid,
+					&cpu_topo->thread_sibling);
+				if (cpu != cpuid)
+					cpumask_set_cpu(cpu,
+						&cpuid_topo->thread_sibling);
+			}
+		}
+	}
+	smp_wmb();
+
+	printk(KERN_INFO "CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n",
+		cpuid, cpu_topology[cpuid].thread_id,
+		cpu_topology[cpuid].core_id,
+		cpu_topology[cpuid].socket_id, mpidr);
+}
+
+/*
+ * init_cpu_topology is called at boot when only one cpu is running
+ * which prevent simultaneous write access to cpu_topology array
+ */
+void init_cpu_topology(void)
+{
+	unsigned int cpu;
+
+	/* init core mask */
+	for_each_possible_cpu(cpu) {
+		struct cputopo_arm *cpu_topo = &(cpu_topology[cpu]);
+
+		cpu_topo->thread_id = -1;
+		cpu_topo->core_id =  -1;
+		cpu_topo->socket_id = -1;
+		cpumask_clear(&cpu_topo->core_sibling);
+		cpumask_clear(&cpu_topo->thread_sibling);
+	}
+	smp_wmb();
+}

arch/arm/kernel/traps.c

@@ -27,6 +27,7 @@
 
 #include <linux/atomic.h>
 #include <asm/cacheflush.h>
+#include <asm/exception.h>
 #include <asm/system.h>
 #include <asm/unistd.h>
 #include <asm/traps.h>

arch/arm/lib/uaccess_with_memcpy.c

@@ -17,6 +17,7 @@
 #include <linux/sched.h>
 #include <linux/hardirq.h> /* for in_atomic() */
 #include <linux/gfp.h>
+#include <linux/highmem.h>
 #include <asm/current.h>
 #include <asm/page.h>
 

arch/arm/mach-ebsa110/include/mach/io.h

@@ -13,8 +13,6 @@
 #ifndef __ASM_ARM_ARCH_IO_H
 #define __ASM_ARM_ARCH_IO_H
 
-#define IO_SPACE_LIMIT 0xffff
-
 u8 __inb8(unsigned int port);
 void __outb8(u8  val, unsigned int port);
 

arch/arm/mach-exynos4/Kconfig

@@ -12,6 +12,7 @@ if ARCH_EXYNOS4
 config CPU_EXYNOS4210
 	bool
 	select S3C_PL330_DMA
+	select ARM_CPU_SUSPEND if PM
 	help
 	  Enable EXYNOS4210 CPU support
 

arch/arm/mach-exynos4/platsmp.c

@@ -193,12 +193,10 @@ void __init smp_init_cpus(void)
 	ncores = scu_base ? scu_get_core_count(scu_base) : 1;
 
 	/* sanity check */
-	if (ncores > NR_CPUS) {
-		printk(KERN_WARNING
-		       "EXYNOS4: no. of cores (%d) greater than configured "
-		       "maximum of %d - clipping\n",
-		       ncores, NR_CPUS);
-		ncores = NR_CPUS;
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
+			ncores, nr_cpu_ids);
+		ncores = nr_cpu_ids;
 	}
 
 	for (i = 0; i < ncores; i++)

arch/arm/mach-footbridge/include/mach/io.h

@@ -23,8 +23,6 @@
 #define PCIO_SIZE       0x00100000
 #define PCIO_BASE       MMU_IO(0xff000000, 0x7c000000)
 
-#define IO_SPACE_LIMIT 0xffff
-
 /*
  * Translation of various region addresses to virtual addresses
  */

arch/arm/mach-integrator/include/mach/io.h

@@ -20,8 +20,6 @@
 #ifndef __ASM_ARM_ARCH_IO_H
 #define __ASM_ARM_ARCH_IO_H
 
-#define IO_SPACE_LIMIT 0xffff
-
 /*
  * WARNING: this has to mirror definitions in platform.h
  */

arch/arm/mach-ixp4xx/include/mach/io.h

@@ -17,8 +17,6 @@
 
 #include <mach/hardware.h>
 
-#define IO_SPACE_LIMIT 0x0000ffff
-
 extern int (*ixp4xx_pci_read)(u32 addr, u32 cmd, u32* data);
 extern int ixp4xx_pci_write(u32 addr, u32 cmd, u32 data);
 

arch/arm/mach-msm/board-msm7x30.c

@@ -24,6 +24,7 @@
 #include <linux/smsc911x.h>
 #include <linux/usb/msm_hsusb.h>
 #include <linux/clkdev.h>
+#include <linux/memblock.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
@@ -42,6 +43,21 @@
 
 extern struct sys_timer msm_timer;
 
+static void __init msm7x30_fixup(struct machine_desc *desc, struct tag *tag,
+			 char **cmdline, struct meminfo *mi)
+{
+	for (; tag->hdr.size; tag = tag_next(tag))
+		if (tag->hdr.tag == ATAG_MEM && tag->u.mem.start == 0x200000) {
+			tag->u.mem.start = 0;
+			tag->u.mem.size += SZ_2M;
+		}
+}
+
+static void __init msm7x30_reserve(void)
+{
+	memblock_remove(0x0, SZ_2M);
+}
+
 static int hsusb_phy_init_seq[] = {
 	0x30, 0x32,	/* Enable and set Pre-Emphasis Depth to 20% */
 	0x02, 0x36,	/* Disable CDR Auto Reset feature */
@@ -107,6 +123,8 @@ static void __init msm7x30_map_io(void)
 
 MACHINE_START(MSM7X30_SURF, "QCT MSM7X30 SURF")
 	.boot_params = PLAT_PHYS_OFFSET + 0x100,
+	.fixup = msm7x30_fixup,
+	.reserve = msm7x30_reserve,
 	.map_io = msm7x30_map_io,
 	.init_irq = msm7x30_init_irq,
 	.init_machine = msm7x30_init,
@@ -115,6 +133,8 @@ MACHINE_END
 
 MACHINE_START(MSM7X30_FFA, "QCT MSM7X30 FFA")
 	.boot_params = PLAT_PHYS_OFFSET + 0x100,
+	.fixup = msm7x30_fixup,
+	.reserve = msm7x30_reserve,
 	.map_io = msm7x30_map_io,
 	.init_irq = msm7x30_init_irq,
 	.init_machine = msm7x30_init,
@@ -123,6 +143,8 @@ MACHINE_END
 
 MACHINE_START(MSM7X30_FLUID, "QCT MSM7X30 FLUID")
 	.boot_params = PLAT_PHYS_OFFSET + 0x100,
+	.fixup = msm7x30_fixup,
+	.reserve = msm7x30_reserve,
 	.map_io = msm7x30_map_io,
 	.init_irq = msm7x30_init_irq,
 	.init_machine = msm7x30_init,

arch/arm/mach-msm/board-msm8960.c

@@ -20,16 +20,34 @@
 #include <linux/io.h>
 #include <linux/irq.h>
 #include <linux/clkdev.h>
+#include <linux/memblock.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/hardware/gic.h>
+#include <asm/setup.h>
 
 #include <mach/board.h>
 #include <mach/msm_iomap.h>
 
 #include "devices.h"
 
+static void __init msm8960_fixup(struct machine_desc *desc, struct tag *tag,
+			 char **cmdline, struct meminfo *mi)
+{
+	for (; tag->hdr.size; tag = tag_next(tag))
+		if (tag->hdr.tag == ATAG_MEM &&
+				tag->u.mem.start == 0x40200000) {
+			tag->u.mem.start = 0x40000000;
+			tag->u.mem.size += SZ_2M;
+		}
+}
+
+static void __init msm8960_reserve(void)
+{
+	memblock_remove(0x40000000, SZ_2M);
+}
+
 static void __init msm8960_map_io(void)
 {
 	msm_map_msm8960_io();
@@ -76,6 +94,8 @@ static void __init msm8960_rumi3_init(void)
 }
 
 MACHINE_START(MSM8960_SIM, "QCT MSM8960 SIMULATOR")
+	.fixup = msm8960_fixup,
+	.reserve = msm8960_reserve,
 	.map_io = msm8960_map_io,
 	.init_irq = msm8960_init_irq,
 	.timer = &msm_timer,
@@ -83,6 +103,8 @@ MACHINE_START(MSM8960_SIM, "QCT MSM8960 SIMULATOR")
 MACHINE_END
 
 MACHINE_START(MSM8960_RUMI3, "QCT MSM8960 RUMI3")
+	.fixup = msm8960_fixup,
+	.reserve = msm8960_reserve,
 	.map_io = msm8960_map_io,
 	.init_irq = msm8960_init_irq,
 	.timer = &msm_timer,

arch/arm/mach-msm/board-msm8x60.c

@@ -20,14 +20,31 @@
 #include <linux/platform_device.h>
 #include <linux/io.h>
 #include <linux/irq.h>
+#include <linux/memblock.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/hardware/gic.h>
+#include <asm/setup.h>
 
 #include <mach/board.h>
 #include <mach/msm_iomap.h>
 
+static void __init msm8x60_fixup(struct machine_desc *desc, struct tag *tag,
+			 char **cmdline, struct meminfo *mi)
+{
+	for (; tag->hdr.size; tag = tag_next(tag))
+		if (tag->hdr.tag == ATAG_MEM &&
+				tag->u.mem.start == 0x40200000) {
+			tag->u.mem.start = 0x40000000;
+			tag->u.mem.size += SZ_2M;
+		}
+}
+
+static void __init msm8x60_reserve(void)
+{
+	memblock_remove(0x40000000, SZ_2M);
+}
 
 static void __init msm8x60_map_io(void)
 {
@@ -65,6 +82,8 @@ static void __init msm8x60_init(void)
 }
 
 MACHINE_START(MSM8X60_RUMI3, "QCT MSM8X60 RUMI3")
+	.fixup = msm8x60_fixup,
+	.reserve = msm8x60_reserve,
 	.map_io = msm8x60_map_io,
 	.init_irq = msm8x60_init_irq,
 	.init_machine = msm8x60_init,
@@ -72,6 +91,8 @@ MACHINE_START(MSM8X60_RUMI3, "QCT MSM8X60 RUMI3")
 MACHINE_END
 
 MACHINE_START(MSM8X60_SURF, "QCT MSM8X60 SURF")
+	.fixup = msm8x60_fixup,
+	.reserve = msm8x60_reserve,
 	.map_io = msm8x60_map_io,
 	.init_irq = msm8x60_init_irq,
 	.init_machine = msm8x60_init,
@@ -79,6 +100,8 @@ MACHINE_START(MSM8X60_SURF, "QCT MSM8X60 SURF")
 MACHINE_END
 
 MACHINE_START(MSM8X60_SIM, "QCT MSM8X60 SIMULATOR")
+	.fixup = msm8x60_fixup,
+	.reserve = msm8x60_reserve,
 	.map_io = msm8x60_map_io,
 	.init_irq = msm8x60_init_irq,
 	.init_machine = msm8x60_init,
@@ -86,6 +109,8 @@ MACHINE_START(MSM8X60_SIM, "QCT MSM8X60 SIMULATOR")
 MACHINE_END
 
 MACHINE_START(MSM8X60_FFA, "QCT MSM8X60 FFA")
+	.fixup = msm8x60_fixup,
+	.reserve = msm8x60_reserve,
 	.map_io = msm8x60_map_io,
 	.init_irq = msm8x60_init_irq,
 	.init_machine = msm8x60_init,

arch/arm/mach-msm/include/mach/memory.h

@@ -22,11 +22,11 @@
 #elif defined(CONFIG_ARCH_QSD8X50)
 #define PLAT_PHYS_OFFSET		UL(0x20000000)
 #elif defined(CONFIG_ARCH_MSM7X30)
-#define PLAT_PHYS_OFFSET		UL(0x00200000)
+#define PLAT_PHYS_OFFSET		UL(0x00000000)
 #elif defined(CONFIG_ARCH_MSM8X60)
-#define PLAT_PHYS_OFFSET		UL(0x40200000)
+#define PLAT_PHYS_OFFSET		UL(0x40000000)
 #elif defined(CONFIG_ARCH_MSM8960)
-#define PLAT_PHYS_OFFSET		UL(0x40200000)
+#define PLAT_PHYS_OFFSET		UL(0x40000000)
 #else
 #define PLAT_PHYS_OFFSET		UL(0x10000000)
 #endif

arch/arm/mach-msm/platsmp.c

@@ -156,6 +156,12 @@ void __init smp_init_cpus(void)
 {
 	unsigned int i, ncores = get_core_count();
 
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
+			ncores, nr_cpu_ids);
+		ncores = nr_cpu_ids;
+	}
+
 	for (i = 0; i < ncores; i++)
 		set_cpu_possible(i, true);
 

arch/arm/mach-omap2/Kconfig

@@ -36,6 +36,7 @@ config ARCH_OMAP3
 	select ARM_L1_CACHE_SHIFT_6 if !ARCH_OMAP4
 	select ARCH_HAS_OPP
 	select PM_OPP if PM
+	select ARM_CPU_SUSPEND if PM
 
 config ARCH_OMAP4
 	bool "TI OMAP4"
@@ -50,6 +51,7 @@ config ARCH_OMAP4
 	select ARCH_HAS_OPP
 	select PM_OPP if PM
 	select USB_ARCH_HAS_EHCI
+	select ARM_CPU_SUSPEND if PM
 
 comment "OMAP Core Type"
 	depends on ARCH_OMAP2

arch/arm/mach-omap2/omap-smp.c

@@ -109,12 +109,10 @@ void __init smp_init_cpus(void)
 	ncores = scu_get_core_count(scu_base);
 
 	/* sanity check */
-	if (ncores > NR_CPUS) {
-		printk(KERN_WARNING
-		       "OMAP4: no. of cores (%d) greater than configured "
-		       "maximum of %d - clipping\n",
-		       ncores, NR_CPUS);
-		ncores = NR_CPUS;
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
+			ncores, nr_cpu_ids);
+		ncores = nr_cpu_ids;
 	}
 
 	for (i = 0; i < ncores; i++)

arch/arm/mach-pxa/irq.c

@@ -19,6 +19,8 @@
 #include <linux/io.h>
 #include <linux/irq.h>
 
+#include <asm/exception.h>
+
 #include <mach/hardware.h>
 #include <mach/irqs.h>
 #include <mach/gpio.h>

arch/arm/mach-realview/platsmp.c

@@ -52,12 +52,10 @@ void __init smp_init_cpus(void)
 	ncores = scu_base ? scu_get_core_count(scu_base) : 1;
 
 	/* sanity check */
-	if (ncores > NR_CPUS) {
-		printk(KERN_WARNING
-		       "Realview: no. of cores (%d) greater than configured "
-		       "maximum of %d - clipping\n",
-		       ncores, NR_CPUS);
-		ncores = NR_CPUS;
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
+			ncores, nr_cpu_ids);
+		ncores = nr_cpu_ids;
 	}
 
 	for (i = 0; i < ncores; i++)

arch/arm/mach-rpc/include/mach/hardware.h

@@ -36,7 +36,7 @@
 
 #define EASI_SIZE		0x08000000	/* EASI I/O */
 #define EASI_START		0x08000000
-#define EASI_BASE		0xe5000000
+#define EASI_BASE		IOMEM(0xe5000000)
 
 #define IO_START		0x03000000	/* I/O */
 #define IO_SIZE			0x01000000
@@ -51,21 +51,20 @@
 /*
  * IO Addresses
  */
-#define VIDC_BASE		IOMEM(0xe0400000)
-#define EXPMASK_BASE		0xe0360000
-#define IOMD_BASE		IOMEM(0xe0200000)
-#define IOC_BASE		IOMEM(0xe0200000)
-#define PCIO_BASE		IOMEM(0xe0010000)
-#define FLOPPYDMA_BASE		IOMEM(0xe002a000)
+#define ECARD_EASI_BASE		(EASI_BASE)
+#define VIDC_BASE		(IO_BASE + 0x00400000)
+#define EXPMASK_BASE		(IO_BASE + 0x00360000)
+#define ECARD_IOC4_BASE		(IO_BASE + 0x00270000)
+#define ECARD_IOC_BASE		(IO_BASE + 0x00240000)
+#define IOMD_BASE		(IO_BASE + 0x00200000)
+#define IOC_BASE		(IO_BASE + 0x00200000)
+#define ECARD_MEMC8_BASE	(IO_BASE + 0x0002b000)
+#define FLOPPYDMA_BASE		(IO_BASE + 0x0002a000)
+#define PCIO_BASE		(IO_BASE + 0x00010000)
+#define ECARD_MEMC_BASE		(IO_BASE + 0x00000000)
 
 #define vidc_writel(val)	__raw_writel(val, VIDC_BASE)
 
-#define IO_EC_EASI_BASE		0x81400000
-#define IO_EC_IOC4_BASE		0x8009c000
-#define IO_EC_IOC_BASE		0x80090000
-#define IO_EC_MEMC8_BASE	0x8000ac00
-#define IO_EC_MEMC_BASE		0x80000000
-
 #define NETSLOT_BASE		0x0302b000
 #define NETSLOT_SIZE		0x00001000
 

arch/arm/mach-rpc/include/mach/io.h

@@ -15,195 +15,18 @@
 
 #include <mach/hardware.h>
 
-#define IO_SPACE_LIMIT 0xffffffff
+#define IO_SPACE_LIMIT 0xffff
 
 /*
- * We use two different types of addressing - PC style addresses, and ARM
- * addresses.  PC style accesses the PC hardware with the normal PC IO
- * addresses, eg 0x3f8 for serial#1.  ARM addresses are 0x80000000+
- * and are translated to the start of IO.  Note that all addresses are
- * shifted left!
- */
-#define __PORT_PCIO(x)	(!((x) & 0x80000000))
-
-/*
- * Dynamic IO functions.
- */
-static inline void __outb (unsigned int value, unsigned int port)
-{
-	unsigned long temp;
-	__asm__ __volatile__(
-	"tst	%2, #0x80000000\n\t"
-	"mov	%0, %4\n\t"
-	"addeq	%0, %0, %3\n\t"
-	"strb	%1, [%0, %2, lsl #2]	@ outb"
-	: "=&r" (temp)
-	: "r" (value), "r" (port), "Ir" (PCIO_BASE - IO_BASE), "Ir" (IO_BASE)
-	: "cc");
-}
-
-static inline void __outw (unsigned int value, unsigned int port)
-{
-	unsigned long temp;
-	__asm__ __volatile__(
-	"tst	%2, #0x80000000\n\t"
-	"mov	%0, %4\n\t"
-	"addeq	%0, %0, %3\n\t"
-	"str	%1, [%0, %2, lsl #2]	@ outw"
-	: "=&r" (temp)
-	: "r" (value|value<<16), "r" (port), "Ir" (PCIO_BASE - IO_BASE), "Ir" (IO_BASE)
-	: "cc");
-}
-
-static inline void __outl (unsigned int value, unsigned int port)
-{
-	unsigned long temp;
-	__asm__ __volatile__(
-	"tst	%2, #0x80000000\n\t"
-	"mov	%0, %4\n\t"
-	"addeq	%0, %0, %3\n\t"
-	"str	%1, [%0, %2, lsl #2]	@ outl"
-	: "=&r" (temp)
-	: "r" (value), "r" (port), "Ir" (PCIO_BASE - IO_BASE), "Ir" (IO_BASE)
-	: "cc");
-}
-
-#define DECLARE_DYN_IN(sz,fnsuffix,instr)					\
-static inline unsigned sz __in##fnsuffix (unsigned int port)		\
-{										\
-	unsigned long temp, value;						\
-	__asm__ __volatile__(							\
-	"tst	%2, #0x80000000\n\t"						\
-	"mov	%0, %4\n\t"							\
-	"addeq	%0, %0, %3\n\t"							\
-	"ldr" instr "	%1, [%0, %2, lsl #2]	@ in" #fnsuffix			\
-	: "=&r" (temp), "=r" (value)						\
-	: "r" (port), "Ir" (PCIO_BASE - IO_BASE), "Ir" (IO_BASE)		\
-	: "cc");								\
-	return (unsigned sz)value;						\
-}
-
-static inline void __iomem *__deprecated __ioaddr(unsigned int port)
-{
-	void __iomem *ret;
-	if (__PORT_PCIO(port))
-		ret = PCIO_BASE;
-	else
-		ret = IO_BASE;
-	return ret + (port << 2);
-}
-
-#define DECLARE_IO(sz,fnsuffix,instr)	\
-	DECLARE_DYN_IN(sz,fnsuffix,instr)
-
-DECLARE_IO(char,b,"b")
-DECLARE_IO(short,w,"")
-DECLARE_IO(int,l,"")
-
-#undef DECLARE_IO
-#undef DECLARE_DYN_IN
-
-/*
- * Constant address IO functions
+ * We need PC style IO addressing for:
+ *  - floppy (at 0x3f2,0x3f4,0x3f5,0x3f7)
+ *  - parport (at 0x278-0x27a, 0x27b-0x27f, 0x778-0x77a)
+ *  - 8250 serial (only for compile)
  *
- * These have to be macros for the 'J' constraint to work -
- * +/-4096 immediate operand.
+ * These peripherals are found in an area of MMIO which looks very much
+ * like an ISA bus, but with registers at the low byte of each word.
  */
-#define __outbc(value,port)							\
-({										\
-	if (__PORT_PCIO((port)))						\
-		__asm__ __volatile__(						\
-		"strb	%0, [%1, %2]	@ outbc"				\
-		: : "r" (value), "r" (PCIO_BASE), "Jr" ((port) << 2));		\
-	else									\
-		__asm__ __volatile__(						\
-		"strb	%0, [%1, %2]	@ outbc"				\
-		: : "r" (value), "r" (IO_BASE), "r" ((port) << 2));		\
-})
-
-#define __inbc(port)								\
-({										\
-	unsigned char result;							\
-	if (__PORT_PCIO((port)))						\
-		__asm__ __volatile__(						\
-		"ldrb	%0, [%1, %2]	@ inbc"					\
-		: "=r" (result) : "r" (PCIO_BASE), "Jr" ((port) << 2));		\
-	else									\
-		__asm__ __volatile__(						\
-		"ldrb	%0, [%1, %2]	@ inbc"					\
-		: "=r" (result) : "r" (IO_BASE), "r" ((port) << 2));		\
-	result;									\
-})
-
-#define __outwc(value,port)							\
-({										\
-	unsigned long __v = value;						\
-	if (__PORT_PCIO((port)))						\
-		__asm__ __volatile__(						\
-		"str	%0, [%1, %2]	@ outwc"				\
-		: : "r" (__v|__v<<16), "r" (PCIO_BASE), "Jr" ((port) << 2));	\
-	else									\
-		__asm__ __volatile__(						\
-		"str	%0, [%1, %2]	@ outwc"				\
-		: : "r" (__v|__v<<16), "r" (IO_BASE), "r" ((port) << 2));		\
-})
-
-#define __inwc(port)								\
-({										\
-	unsigned short result;							\
-	if (__PORT_PCIO((port)))						\
-		__asm__ __volatile__(						\
-		"ldr	%0, [%1, %2]	@ inwc"					\
-		: "=r" (result) : "r" (PCIO_BASE), "Jr" ((port) << 2));		\
-	else									\
-		__asm__ __volatile__(						\
-		"ldr	%0, [%1, %2]	@ inwc"					\
-		: "=r" (result) : "r" (IO_BASE), "r" ((port) << 2));		\
-	result & 0xffff;							\
-})
-
-#define __outlc(value,port)							\
-({										\
-	unsigned long __v = value;						\
-	if (__PORT_PCIO((port)))						\
-		__asm__ __volatile__(						\
-		"str	%0, [%1, %2]	@ outlc"				\
-		: : "r" (__v), "r" (PCIO_BASE), "Jr" ((port) << 2));		\
-	else									\
-		__asm__ __volatile__(						\
-		"str	%0, [%1, %2]	@ outlc"				\
-		: : "r" (__v), "r" (IO_BASE), "r" ((port) << 2));		\
-})
-
-#define __inlc(port)								\
-({										\
-	unsigned long result;							\
-	if (__PORT_PCIO((port)))						\
-		__asm__ __volatile__(						\
-		"ldr	%0, [%1, %2]	@ inlc"					\
-		: "=r" (result) : "r" (PCIO_BASE), "Jr" ((port) << 2));		\
-	else									\
-		__asm__ __volatile__(						\
-		"ldr	%0, [%1, %2]	@ inlc"					\
-		: "=r" (result) : "r" (IO_BASE), "r" ((port) << 2));		\
-	result;									\
-})
-
-#define inb(p)	 	(__builtin_constant_p((p)) ? __inbc(p)    : __inb(p))
-#define inw(p)	 	(__builtin_constant_p((p)) ? __inwc(p)    : __inw(p))
-#define inl(p)	 	(__builtin_constant_p((p)) ? __inlc(p)    : __inl(p))
-#define outb(v,p)	(__builtin_constant_p((p)) ? __outbc(v,p) : __outb(v,p))
-#define outw(v,p)	(__builtin_constant_p((p)) ? __outwc(v,p) : __outw(v,p))
-#define outl(v,p)	(__builtin_constant_p((p)) ? __outlc(v,p) : __outl(v,p))
-
-/* the following macro is deprecated */
-#define ioaddr(port)	((unsigned long)__ioaddr((port)))
-
-#define insb(p,d,l)	__raw_readsb(__ioaddr(p),d,l)
-#define insw(p,d,l)	__raw_readsw(__ioaddr(p),d,l)
-
-#define outsb(p,d,l)	__raw_writesb(__ioaddr(p),d,l)
-#define outsw(p,d,l)	__raw_writesw(__ioaddr(p),d,l)
+#define __io(a)		(PCIO_BASE + ((a) << 2))
 
 /*
  * 1:1 mapping for ioremapped regions.

arch/arm/mach-rpc/riscpc.c

@@ -74,7 +74,7 @@ static struct map_desc rpc_io_desc[] __initdata = {
 		.length		= 	IO_SIZE	 ,
 		.type		= MT_DEVICE
 	}, {	/* EASI space	*/
-		.virtual	= EASI_BASE,
+		.virtual	= (unsigned long)EASI_BASE,
 		.pfn		= __phys_to_pfn(EASI_START),
 		.length		= EASI_SIZE,
 		.type		= MT_DEVICE

arch/arm/mach-s3c2410/include/mach/io.h

@@ -199,8 +199,6 @@ DECLARE_IO(int,l,"")
 #define outw(v,p)	(__builtin_constant_p((p)) ? __outwc(v,p) : __outw(v,p))
 #define outl(v,p)	(__builtin_constant_p((p)) ? __outlc(v,p) : __outl(v,p))
 #define __ioaddr(p)	(__builtin_constant_p((p)) ? __ioaddr(p)  : __ioaddrc(p))
-/* the following macro is deprecated */
-#define ioaddr(port)	__ioaddr((port))
 
 #define insb(p,d,l)	__raw_readsb(__ioaddr(p),d,l)
 #define insw(p,d,l)	__raw_readsw(__ioaddr(p),d,l)

arch/arm/mach-sa1100/include/mach/io.h

@@ -10,11 +10,9 @@
 #ifndef __ASM_ARM_ARCH_IO_H
 #define __ASM_ARM_ARCH_IO_H
 
-#define IO_SPACE_LIMIT 0xffffffff
-
 /*
- * We don't actually have real ISA nor PCI buses, but there is so many 
- * drivers out there that might just work if we fake them...
+ * __io() is required to be an equivalent mapping to __mem_pci() for
+ * SOC_COMMON to work.
  */
 #define __io(a)		__typesafe_io(a)
 #define __mem_pci(a)	(a)

arch/arm/mach-shmobile/platsmp.c

@@ -56,6 +56,12 @@ void __init smp_init_cpus(void)
 	unsigned int ncores = shmobile_smp_get_core_count();
 	unsigned int i;
 
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
+			ncores, nr_cpu_ids);
+		ncores = nr_cpu_ids;
+	}
+
 	for (i = 0; i < ncores; i++)
 		set_cpu_possible(i, true);
 

arch/arm/mach-tegra/platsmp.c

@@ -114,10 +114,10 @@ void __init smp_init_cpus(void)
 {
 	unsigned int i, ncores = scu_get_core_count(scu_base);
 
-	if (ncores > NR_CPUS) {
-		printk(KERN_ERR "Tegra: no. of cores (%u) greater than configured (%u), clipping\n",
-			ncores, NR_CPUS);
-		ncores = NR_CPUS;
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
+			ncores, nr_cpu_ids);
+		ncores = nr_cpu_ids;
 	}
 
 	for (i = 0; i < ncores; i++)

arch/arm/mach-ux500/platsmp.c

@@ -156,12 +156,10 @@ void __init smp_init_cpus(void)
 	ncores = scu_base ? scu_get_core_count(scu_base) : 1;
 
 	/* sanity check */
-	if (ncores > NR_CPUS) {
-		printk(KERN_WARNING
-		       "U8500: no. of cores (%d) greater than configured "
-		       "maximum of %d - clipping\n",
-		       ncores, NR_CPUS);
-		ncores = NR_CPUS;
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
+			ncores, nr_cpu_ids);
+		ncores = nr_cpu_ids;
 	}
 
 	for (i = 0; i < ncores; i++)

arch/arm/mach-vexpress/ct-ca9x4.c

@@ -221,6 +221,12 @@ static void ct_ca9x4_init_cpu_map(void)
 {
 	int i, ncores = scu_get_core_count(MMIO_P2V(A9_MPCORE_SCU));
 
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
+			ncores, nr_cpu_ids);
+		ncores = nr_cpu_ids;
+	}
+
 	for (i = 0; i < ncores; ++i)
 		set_cpu_possible(i, true);
 

arch/arm/mach-vexpress/include/mach/io.h

@@ -20,8 +20,6 @@
 #ifndef __ASM_ARM_ARCH_IO_H
 #define __ASM_ARM_ARCH_IO_H
 
-#define IO_SPACE_LIMIT 0xffffffff
-
 #define __io(a)		__typesafe_io(a)
 #define __mem_pci(a)	(a)
 

arch/arm/mach-vt8500/include/mach/io.h

@@ -20,8 +20,6 @@
 #ifndef __ASM_ARM_ARCH_IO_H
 #define __ASM_ARM_ARCH_IO_H
 
-#define IO_SPACE_LIMIT 0xffff
-
 #define __io(a)		__typesafe_io((a) + 0xf0000000)
 #define __mem_pci(a)	(a)
 

arch/arm/mm/alignment.c

@@ -86,16 +86,6 @@ core_param(alignment, ai_usermode, int, 0600);
 #define UM_FIXUP	(1 << 1)
 #define UM_SIGNAL	(1 << 2)
 
-#ifdef CONFIG_PROC_FS
-static const char *usermode_action[] = {
-	"ignored",
-	"warn",
-	"fixup",
-	"fixup+warn",
-	"signal",
-	"signal+warn"
-};
-
 /* Return true if and only if the ARMv6 unaligned access model is in use. */
 static bool cpu_is_v6_unaligned(void)
 {
@@ -123,6 +113,16 @@ static int safe_usermode(int new_usermode, bool warn)
 	return new_usermode;
 }
 
+#ifdef CONFIG_PROC_FS
+static const char *usermode_action[] = {
+	"ignored",
+	"warn",
+	"fixup",
+	"fixup+warn",
+	"signal",
+	"signal+warn"
+};
+
 static int alignment_proc_show(struct seq_file *m, void *v)
 {
 	seq_printf(m, "User:\t\t%lu\n", ai_user);

arch/arm/mm/cache-l2x0.c

@@ -16,9 +16,12 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
+#include <linux/err.h>
 #include <linux/init.h>
 #include <linux/spinlock.h>
 #include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
 
 #include <asm/cacheflush.h>
 #include <asm/hardware/cache-l2x0.h>
@@ -30,11 +33,19 @@ static DEFINE_SPINLOCK(l2x0_lock);
 static uint32_t l2x0_way_mask;	/* Bitmask of active ways */
 static uint32_t l2x0_size;
 
+struct l2x0_regs l2x0_saved_regs;
+
+struct l2x0_of_data {
+	void (*setup)(const struct device_node *, __u32 *, __u32 *);
+	void (*save)(void);
+	void (*resume)(void);
+};
+
 static inline void cache_wait_way(void __iomem *reg, unsigned long mask)
 {
 	/* wait for cache operation by line or way to complete */
 	while (readl_relaxed(reg) & mask)
-		;
+		cpu_relax();
 }
 
 #ifdef CONFIG_CACHE_PL310
@@ -277,7 +288,7 @@ static void l2x0_disable(void)
 	spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
-static void __init l2x0_unlock(__u32 cache_id)
+static void l2x0_unlock(__u32 cache_id)
 {
 	int lockregs;
 	int i;
@@ -353,6 +364,8 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask)
 		/* l2x0 controller is disabled */
 		writel_relaxed(aux, l2x0_base + L2X0_AUX_CTRL);
 
+		l2x0_saved_regs.aux_ctrl = aux;
+
 		l2x0_inv_all();
 
 		/* enable L2X0 */
@@ -372,3 +385,202 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask)
 	printk(KERN_INFO "l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x, Cache size: %d B\n",
 			ways, cache_id, aux, l2x0_size);
 }
+
+#ifdef CONFIG_OF
+static void __init l2x0_of_setup(const struct device_node *np,
+				 __u32 *aux_val, __u32 *aux_mask)
+{
+	u32 data[2] = { 0, 0 };
+	u32 tag = 0;
+	u32 dirty = 0;
+	u32 val = 0, mask = 0;
+
+	of_property_read_u32(np, "arm,tag-latency", &tag);
+	if (tag) {
+		mask |= L2X0_AUX_CTRL_TAG_LATENCY_MASK;
+		val |= (tag - 1) << L2X0_AUX_CTRL_TAG_LATENCY_SHIFT;
+	}
+
+	of_property_read_u32_array(np, "arm,data-latency",
+				   data, ARRAY_SIZE(data));
+	if (data[0] && data[1]) {
+		mask |= L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK |
+			L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK;
+		val |= ((data[0] - 1) << L2X0_AUX_CTRL_DATA_RD_LATENCY_SHIFT) |
+		       ((data[1] - 1) << L2X0_AUX_CTRL_DATA_WR_LATENCY_SHIFT);
+	}
+
+	of_property_read_u32(np, "arm,dirty-latency", &dirty);
+	if (dirty) {
+		mask |= L2X0_AUX_CTRL_DIRTY_LATENCY_MASK;
+		val |= (dirty - 1) << L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT;
+	}
+
+	*aux_val &= ~mask;
+	*aux_val |= val;
+	*aux_mask &= ~mask;
+}
+
+static void __init pl310_of_setup(const struct device_node *np,
+				  __u32 *aux_val, __u32 *aux_mask)
+{
+	u32 data[3] = { 0, 0, 0 };
+	u32 tag[3] = { 0, 0, 0 };
+	u32 filter[2] = { 0, 0 };
+
+	of_property_read_u32_array(np, "arm,tag-latency", tag, ARRAY_SIZE(tag));
+	if (tag[0] && tag[1] && tag[2])
+		writel_relaxed(
+			((tag[0] - 1) << L2X0_LATENCY_CTRL_RD_SHIFT) |
+			((tag[1] - 1) << L2X0_LATENCY_CTRL_WR_SHIFT) |
+			((tag[2] - 1) << L2X0_LATENCY_CTRL_SETUP_SHIFT),
+			l2x0_base + L2X0_TAG_LATENCY_CTRL);
+
+	of_property_read_u32_array(np, "arm,data-latency",
+				   data, ARRAY_SIZE(data));
+	if (data[0] && data[1] && data[2])
+		writel_relaxed(
+			((data[0] - 1) << L2X0_LATENCY_CTRL_RD_SHIFT) |
+			((data[1] - 1) << L2X0_LATENCY_CTRL_WR_SHIFT) |
+			((data[2] - 1) << L2X0_LATENCY_CTRL_SETUP_SHIFT),
+			l2x0_base + L2X0_DATA_LATENCY_CTRL);
+
+	of_property_read_u32_array(np, "arm,filter-ranges",
+				   filter, ARRAY_SIZE(filter));
+	if (filter[1]) {
+		writel_relaxed(ALIGN(filter[0] + filter[1], SZ_1M),
+			       l2x0_base + L2X0_ADDR_FILTER_END);
+		writel_relaxed((filter[0] & ~(SZ_1M - 1)) | L2X0_ADDR_FILTER_EN,
+			       l2x0_base + L2X0_ADDR_FILTER_START);
+	}
+}
+
+static void __init pl310_save(void)
+{
+	u32 l2x0_revision = readl_relaxed(l2x0_base + L2X0_CACHE_ID) &
+		L2X0_CACHE_ID_RTL_MASK;
+
+	l2x0_saved_regs.tag_latency = readl_relaxed(l2x0_base +
+		L2X0_TAG_LATENCY_CTRL);
+	l2x0_saved_regs.data_latency = readl_relaxed(l2x0_base +
+		L2X0_DATA_LATENCY_CTRL);
+	l2x0_saved_regs.filter_end = readl_relaxed(l2x0_base +
+		L2X0_ADDR_FILTER_END);
+	l2x0_saved_regs.filter_start = readl_relaxed(l2x0_base +
+		L2X0_ADDR_FILTER_START);
+
+	if (l2x0_revision >= L2X0_CACHE_ID_RTL_R2P0) {
+		/*
+		 * From r2p0, there is Prefetch offset/control register
+		 */
+		l2x0_saved_regs.prefetch_ctrl = readl_relaxed(l2x0_base +
+			L2X0_PREFETCH_CTRL);
+		/*
+		 * From r3p0, there is Power control register
+		 */
+		if (l2x0_revision >= L2X0_CACHE_ID_RTL_R3P0)
+			l2x0_saved_regs.pwr_ctrl = readl_relaxed(l2x0_base +
+				L2X0_POWER_CTRL);
+	}
+}
+
+static void l2x0_resume(void)
+{
+	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) {
+		/* restore aux ctrl and enable l2 */
+		l2x0_unlock(readl_relaxed(l2x0_base + L2X0_CACHE_ID));
+
+		writel_relaxed(l2x0_saved_regs.aux_ctrl, l2x0_base +
+			L2X0_AUX_CTRL);
+
+		l2x0_inv_all();
+
+		writel_relaxed(1, l2x0_base + L2X0_CTRL);
+	}
+}
+
+static void pl310_resume(void)
+{
+	u32 l2x0_revision;
+
+	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) {
+		/* restore pl310 setup */
+		writel_relaxed(l2x0_saved_regs.tag_latency,
+			l2x0_base + L2X0_TAG_LATENCY_CTRL);
+		writel_relaxed(l2x0_saved_regs.data_latency,
+			l2x0_base + L2X0_DATA_LATENCY_CTRL);
+		writel_relaxed(l2x0_saved_regs.filter_end,
+			l2x0_base + L2X0_ADDR_FILTER_END);
+		writel_relaxed(l2x0_saved_regs.filter_start,
+			l2x0_base + L2X0_ADDR_FILTER_START);
+
+		l2x0_revision = readl_relaxed(l2x0_base + L2X0_CACHE_ID) &
+			L2X0_CACHE_ID_RTL_MASK;
+
+		if (l2x0_revision >= L2X0_CACHE_ID_RTL_R2P0) {
+			writel_relaxed(l2x0_saved_regs.prefetch_ctrl,
+				l2x0_base + L2X0_PREFETCH_CTRL);
+			if (l2x0_revision >= L2X0_CACHE_ID_RTL_R3P0)
+				writel_relaxed(l2x0_saved_regs.pwr_ctrl,
+					l2x0_base + L2X0_POWER_CTRL);
+		}
+	}
+
+	l2x0_resume();
+}
+
+static const struct l2x0_of_data pl310_data = {
+	pl310_of_setup,
+	pl310_save,
+	pl310_resume,
+};
+
+static const struct l2x0_of_data l2x0_data = {
+	l2x0_of_setup,
+	NULL,
+	l2x0_resume,
+};
+
+static const struct of_device_id l2x0_ids[] __initconst = {
+	{ .compatible = "arm,pl310-cache", .data = (void *)&pl310_data },
+	{ .compatible = "arm,l220-cache", .data = (void *)&l2x0_data },
+	{ .compatible = "arm,l210-cache", .data = (void *)&l2x0_data },
+	{}
+};
+
+int __init l2x0_of_init(__u32 aux_val, __u32 aux_mask)
+{
+	struct device_node *np;
+	struct l2x0_of_data *data;
+	struct resource res;
+
+	np = of_find_matching_node(NULL, l2x0_ids);
+	if (!np)
+		return -ENODEV;
+
+	if (of_address_to_resource(np, 0, &res))
+		return -ENODEV;
+
+	l2x0_base = ioremap(res.start, resource_size(&res));
+	if (!l2x0_base)
+		return -ENOMEM;
+
+	l2x0_saved_regs.phy_base = res.start;
+
+	data = of_match_node(l2x0_ids, np)->data;
+
+	/* L2 configuration can only be changed if the cache is disabled */
+	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) {
+		if (data->setup)
+			data->setup(np, &aux_val, &aux_mask);
+	}
+
+	if (data->save)
+		data->save();
+
+	l2x0_init(l2x0_base, aux_val, aux_mask);
+
+	outer_cache.resume = data->resume;
+	return 0;
+}
+#endif

arch/arm/mm/dma-mapping.c

@@ -123,8 +123,8 @@ static void __dma_free_buffer(struct page *page, size_t size)
 #endif
 
 #define CONSISTENT_OFFSET(x)	(((unsigned long)(x) - CONSISTENT_BASE) >> PAGE_SHIFT)
-#define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PGDIR_SHIFT)
-#define NUM_CONSISTENT_PTES (CONSISTENT_DMA_SIZE >> PGDIR_SHIFT)
+#define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PMD_SHIFT)
+#define NUM_CONSISTENT_PTES (CONSISTENT_DMA_SIZE >> PMD_SHIFT)
 
 /*
  * These are the page tables (2MB each) covering uncached, DMA consistent allocations
@@ -183,7 +183,7 @@ static int __init consistent_init(void)
 		}
 
 		consistent_pte[i++] = pte;
-		base += (1 << PGDIR_SHIFT);
+		base += PMD_SIZE;
 	} while (base < CONSISTENT_END);
 
 	return ret;

arch/arm/mm/fault.c

@@ -20,6 +20,7 @@
 #include <linux/highmem.h>
 #include <linux/perf_event.h>
 
+#include <asm/exception.h>
 #include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>

arch/arm/mm/mm.h

@@ -12,8 +12,8 @@ static inline pmd_t *pmd_off_k(unsigned long virt)
 
 struct mem_type {
 	pteval_t prot_pte;
-	unsigned int prot_l1;
-	unsigned int prot_sect;
+	pmdval_t prot_l1;
+	pmdval_t prot_sect;
 	unsigned int domain;
 };
 

arch/arm/mm/mmu.c

@@ -60,7 +60,7 @@ EXPORT_SYMBOL(pgprot_kernel);
 struct cachepolicy {
 	const char	policy[16];
 	unsigned int	cr_mask;
-	unsigned int	pmd;
+	pmdval_t	pmd;
 	pteval_t	pte;
 };
 
@@ -288,7 +288,7 @@ static void __init build_mem_type_table(void)
 {
 	struct cachepolicy *cp;
 	unsigned int cr = get_cr();
-	unsigned int user_pgprot, kern_pgprot, vecs_pgprot;
+	pteval_t user_pgprot, kern_pgprot, vecs_pgprot;
 	int cpu_arch = cpu_architecture();
 	int i;
 
@@ -863,14 +863,14 @@ static inline void prepare_page_table(void)
 	/*
 	 * Clear out all the mappings below the kernel image.
 	 */
-	for (addr = 0; addr < MODULES_VADDR; addr += PGDIR_SIZE)
+	for (addr = 0; addr < MODULES_VADDR; addr += PMD_SIZE)
 		pmd_clear(pmd_off_k(addr));
 
 #ifdef CONFIG_XIP_KERNEL
 	/* The XIP kernel is mapped in the module area -- skip over it */
-	addr = ((unsigned long)_etext + PGDIR_SIZE - 1) & PGDIR_MASK;
+	addr = ((unsigned long)_etext + PMD_SIZE - 1) & PMD_MASK;
 #endif
-	for ( ; addr < PAGE_OFFSET; addr += PGDIR_SIZE)
+	for ( ; addr < PAGE_OFFSET; addr += PMD_SIZE)
 		pmd_clear(pmd_off_k(addr));
 
 	/*
@@ -885,10 +885,12 @@ static inline void prepare_page_table(void)
 	 * memory bank, up to the end of the vmalloc region.
 	 */
 	for (addr = __phys_to_virt(end);
-	     addr < VMALLOC_END; addr += PGDIR_SIZE)
+	     addr < VMALLOC_END; addr += PMD_SIZE)
 		pmd_clear(pmd_off_k(addr));
 }
 
+#define SWAPPER_PG_DIR_SIZE	(PTRS_PER_PGD * sizeof(pgd_t))
+
 /*
  * Reserve the special regions of memory
  */
@@ -898,7 +900,7 @@ void __init arm_mm_memblock_reserve(void)
 	 * Reserve the page tables.  These are already in use,
 	 * and can only be in node 0.
 	 */
-	memblock_reserve(__pa(swapper_pg_dir), PTRS_PER_PGD * sizeof(pgd_t));
+	memblock_reserve(__pa(swapper_pg_dir), SWAPPER_PG_DIR_SIZE);
 
 #ifdef CONFIG_SA1111
 	/*
@@ -926,7 +928,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
 	 */
 	vectors_page = early_alloc(PAGE_SIZE);
 
-	for (addr = VMALLOC_END; addr; addr += PGDIR_SIZE)
+	for (addr = VMALLOC_END; addr; addr += PMD_SIZE)
 		pmd_clear(pmd_off_k(addr));
 
 	/*

arch/arm/mm/proc-v7.S

@@ -218,7 +218,7 @@ ENDPROC(cpu_v7_set_pte_ext)
 /* Suspend/resume support: derived from arch/arm/mach-s5pv210/sleep.S */
 .globl	cpu_v7_suspend_size
 .equ	cpu_v7_suspend_size, 4 * 9
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_v7_do_suspend)
 	stmfd	sp!, {r4 - r11, lr}
 	mrc	p15, 0, r4, c13, c0, 0	@ FCSE/PID

arch/arm/plat-omap/Kconfig

@@ -14,6 +14,7 @@ config ARCH_OMAP1
 	select CLKDEV_LOOKUP
 	select CLKSRC_MMIO
 	select GENERIC_IRQ_CHIP
+	select HAVE_IDE
 	help
 	  "Systems based on omap7xx, omap15xx or omap16xx"
 

arch/arm/vfp/Makefile

@@ -7,7 +7,7 @@
 # ccflags-y := -DDEBUG
 # asflags-y := -DDEBUG
 
-KBUILD_AFLAGS	:=$(KBUILD_AFLAGS:-msoft-float=-Wa,-mfpu=softvfp+vfp)
+KBUILD_AFLAGS	:=$(KBUILD_AFLAGS:-msoft-float=-Wa,-mfpu=softvfp+vfp -mfloat-abi=soft)
 LDFLAGS		+=--no-warn-mismatch
 
 obj-y			+= vfp.o

lib/Kconfig.debug

@@ -1081,7 +1081,7 @@ config FAULT_INJECTION_STACKTRACE_FILTER
 	depends on FAULT_INJECTION_DEBUG_FS && STACKTRACE_SUPPORT
 	depends on !X86_64
 	select STACKTRACE
-	select FRAME_POINTER if !PPC && !S390 && !MICROBLAZE
+	select FRAME_POINTER if !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND
 	help
 	  Provide stacktrace filter for fault-injection capabilities
 
@@ -1091,7 +1091,7 @@ config LATENCYTOP
 	depends on DEBUG_KERNEL
 	depends on STACKTRACE_SUPPORT
 	depends on PROC_FS
-	select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE
+	select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND
 	select KALLSYMS
 	select KALLSYMS_ALL
 	select STACKTRACE