Merge branch 'for-next' of git://git.pengutronix.de/git/ukl/linux into devel-stable

Pull ARM-v7M support from Uwe Kleine-König:
"All but the last patch were in next since next-20130418 without issues.
The last patch fixes a problem in combination with

  8164f7af (ARM: 7680/1: Detect support for SDIV/UDIV from ISAR0 register)

which triggers a WARN_ON without an implemented read_cpuid_ext.

The branch merges fine into v3.10-rc1 and I'd be happy if you pulled it
for 3.11-rc1. The only missing piece to be able to run a Cortex-M3 is
the irqchip driver that will go in via Thomas Gleixner and platform
specific stuff."

arch/arm/Kconfig

@@ -9,7 +9,7 @@ config ARM
 	select BUILDTIME_EXTABLE_SORT if MMU
 	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select DCACHE_WORD_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && !CPU_BIG_ENDIAN && MMU
-	select GENERIC_ATOMIC64 if (CPU_V6 || !CPU_32v6K || !AEABI)
+	select GENERIC_ATOMIC64 if (CPU_V7M || CPU_V6 || !CPU_32v6K || !AEABI)
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
@@ -1585,7 +1585,7 @@ config SCHED_HRTICK
 
 config THUMB2_KERNEL
 	bool "Compile the kernel in Thumb-2 mode" if !CPU_THUMBONLY
-	depends on CPU_V7 && !CPU_V6 && !CPU_V6K
+	depends on (CPU_V7 || CPU_V7M) && !CPU_V6 && !CPU_V6K
 	default y if CPU_THUMBONLY
 	select AEABI
 	select ARM_ASM_UNIFIED

arch/arm/Kconfig-nommu

@@ -28,7 +28,7 @@ config FLASH_SIZE
 config PROCESSOR_ID
 	hex 'Hard wire the processor ID'
 	default 0x00007700
-	depends on !CPU_CP15
+	depends on !(CPU_CP15 || CPU_V7M)
 	help
 	  If processor has no CP15 register, this processor ID is
 	  used instead of the auto-probing which utilizes the register.

arch/arm/Makefile

@@ -59,6 +59,7 @@ comma = ,
 # Note that GCC does not numerically define an architecture version
 # macro, but instead defines a whole series of macros which makes
 # testing for a specific architecture or later rather impossible.
+arch-$(CONFIG_CPU_32v7M)	:=-D__LINUX_ARM_ARCH__=7 -march=armv7-m -Wa,-march=armv7-m
 arch-$(CONFIG_CPU_32v7)		:=-D__LINUX_ARM_ARCH__=7 $(call cc-option,-march=armv7-a,-march=armv5t -Wa$(comma)-march=armv7-a)
 arch-$(CONFIG_CPU_32v6)		:=-D__LINUX_ARM_ARCH__=6 $(call cc-option,-march=armv6,-march=armv5t -Wa$(comma)-march=armv6)
 # Only override the compiler option if ARMv6. The ARMv6K extensions are

arch/arm/include/asm/assembler.h

@@ -136,7 +136,11 @@
  * assumes FIQs are enabled, and that the processor is in SVC mode.
  */
 	.macro	save_and_disable_irqs, oldcpsr
+#ifdef CONFIG_CPU_V7M
+	mrs	\oldcpsr, primask
+#else
 	mrs	\oldcpsr, cpsr
+#endif
 	disable_irq
 	.endm
 
@@ -150,7 +154,11 @@
  * guarantee that this will preserve the flags.
  */
 	.macro	restore_irqs_notrace, oldcpsr
+#ifdef CONFIG_CPU_V7M
+	msr	primask, \oldcpsr
+#else
 	msr	cpsr_c, \oldcpsr
+#endif
 	.endm
 
 	.macro restore_irqs, oldcpsr
@@ -229,7 +237,14 @@
 #endif
 	.endm
 
-#ifdef CONFIG_THUMB2_KERNEL
+#if defined(CONFIG_CPU_V7M)
+	/*
+	 * setmode is used to assert to be in svc mode during boot. For v7-M
+	 * this is done in __v7m_setup, so setmode can be empty here.
+	 */
+	.macro	setmode, mode, reg
+	.endm
+#elif defined(CONFIG_THUMB2_KERNEL)
 	.macro	setmode, mode, reg
 	mov	\reg, #\mode
 	msr	cpsr_c, \reg

arch/arm/include/asm/cputype.h

@@ -10,6 +10,22 @@
 #define CPUID_TLBTYPE	3
 #define CPUID_MPIDR	5
 
+#ifdef CONFIG_CPU_V7M
+#define CPUID_EXT_PFR0	0x40
+#define CPUID_EXT_PFR1	0x44
+#define CPUID_EXT_DFR0	0x48
+#define CPUID_EXT_AFR0	0x4c
+#define CPUID_EXT_MMFR0	0x50
+#define CPUID_EXT_MMFR1	0x54
+#define CPUID_EXT_MMFR2	0x58
+#define CPUID_EXT_MMFR3	0x5c
+#define CPUID_EXT_ISAR0	0x60
+#define CPUID_EXT_ISAR1	0x64
+#define CPUID_EXT_ISAR2	0x68
+#define CPUID_EXT_ISAR3	0x6c
+#define CPUID_EXT_ISAR4	0x70
+#define CPUID_EXT_ISAR5	0x74
+#else
 #define CPUID_EXT_PFR0	"c1, 0"
 #define CPUID_EXT_PFR1	"c1, 1"
 #define CPUID_EXT_DFR0	"c1, 2"
@@ -24,6 +40,7 @@
 #define CPUID_EXT_ISAR3	"c2, 3"
 #define CPUID_EXT_ISAR4	"c2, 4"
 #define CPUID_EXT_ISAR5	"c2, 5"
+#endif
 
 #define MPIDR_SMP_BITMASK (0x3 << 30)
 #define MPIDR_SMP_VALUE (0x2 << 30)
@@ -79,7 +96,23 @@ extern unsigned int processor_id;
 		__val;							\
 	})
 
-#else /* ifdef CONFIG_CPU_CP15 */
+#elif defined(CONFIG_CPU_V7M)
+
+#include <asm/io.h>
+#include <asm/v7m.h>
+
+#define read_cpuid(reg)							\
+	({								\
+		WARN_ON_ONCE(1);					\
+		0;							\
+	})
+
+static inline unsigned int __attribute_const__ read_cpuid_ext(unsigned offset)
+{
+	return readl(BASEADDR_V7M_SCB + offset);
+}
+
+#else /* ifdef CONFIG_CPU_CP15 / elif defined (CONFIG_CPU_V7M) */
 
 /*
  * read_cpuid and read_cpuid_ext should only ever be called on machines that
@@ -106,7 +139,14 @@ static inline unsigned int __attribute_const__ read_cpuid_id(void)
 	return read_cpuid(CPUID_ID);
 }
 
-#else /* ifdef CONFIG_CPU_CP15 */
+#elif defined(CONFIG_CPU_V7M)
+
+static inline unsigned int __attribute_const__ read_cpuid_id(void)
+{
+	return readl(BASEADDR_V7M_SCB + V7M_SCB_CPUID);
+}
+
+#else /* ifdef CONFIG_CPU_CP15 / elif defined(CONFIG_CPU_V7M) */
 
 static inline unsigned int __attribute_const__ read_cpuid_id(void)
 {

arch/arm/include/asm/glue-cache.h

@@ -117,10 +117,37 @@
 # endif
 #endif
 
+#if defined(CONFIG_CPU_V7M)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE nop
+# endif
+#endif
+
 #if !defined(_CACHE) && !defined(MULTI_CACHE)
 #error Unknown cache maintenance model
 #endif
 
+#ifndef __ASSEMBLER__
+extern inline void nop_flush_icache_all(void) { }
+extern inline void nop_flush_kern_cache_all(void) { }
+extern inline void nop_flush_kern_cache_louis(void) { }
+extern inline void nop_flush_user_cache_all(void) { }
+extern inline void nop_flush_user_cache_range(unsigned long a,
+		unsigned long b, unsigned int c) { }
+
+extern inline void nop_coherent_kern_range(unsigned long a, unsigned long b) { }
+extern inline int nop_coherent_user_range(unsigned long a,
+		unsigned long b) { return 0; }
+extern inline void nop_flush_kern_dcache_area(void *a, size_t s) { }
+
+extern inline void nop_dma_flush_range(const void *a, const void *b) { }
+
+extern inline void nop_dma_map_area(const void *s, size_t l, int f) { }
+extern inline void nop_dma_unmap_area(const void *s, size_t l, int f) { }
+#endif
+
 #ifndef MULTI_CACHE
 #define __cpuc_flush_icache_all		__glue(_CACHE,_flush_icache_all)
 #define __cpuc_flush_kern_all		__glue(_CACHE,_flush_kern_cache_all)

arch/arm/include/asm/glue-df.h

@@ -95,6 +95,14 @@
 # endif
 #endif
 
+#ifdef CONFIG_CPU_ABRT_NOMMU
+# ifdef CPU_DABORT_HANDLER
+#  define MULTI_DABORT 1
+# else
+#  define CPU_DABORT_HANDLER nommu_early_abort
+# endif
+#endif
+
 #ifndef CPU_DABORT_HANDLER
 #error Unknown data abort handler type
 #endif

arch/arm/include/asm/glue-proc.h

@@ -230,6 +230,15 @@
 # endif
 #endif
 
+#ifdef CONFIG_CPU_V7M
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_v7m
+# endif
+#endif
+
 #ifndef MULTI_CPU
 #define cpu_proc_init			__glue(CPU_NAME,_proc_init)
 #define cpu_proc_fin			__glue(CPU_NAME,_proc_fin)

arch/arm/include/asm/irqflags.h

@@ -8,6 +8,16 @@
 /*
  * CPU interrupt mask handling.
  */
+#ifdef CONFIG_CPU_V7M
+#define IRQMASK_REG_NAME_R "primask"
+#define IRQMASK_REG_NAME_W "primask"
+#define IRQMASK_I_BIT	1
+#else
+#define IRQMASK_REG_NAME_R "cpsr"
+#define IRQMASK_REG_NAME_W "cpsr_c"
+#define IRQMASK_I_BIT	PSR_I_BIT
+#endif
+
 #if __LINUX_ARM_ARCH__ >= 6
 
 static inline unsigned long arch_local_irq_save(void)
@@ -15,7 +25,7 @@ static inline unsigned long arch_local_irq_save(void)
 	unsigned long flags;
 
 	asm volatile(
-		"	mrs	%0, cpsr	@ arch_local_irq_save\n"
+		"	mrs	%0, " IRQMASK_REG_NAME_R "	@ arch_local_irq_save\n"
 		"	cpsid	i"
 		: "=r" (flags) : : "memory", "cc");
 	return flags;
@@ -129,7 +139,7 @@ static inline unsigned long arch_local_save_flags(void)
 {
 	unsigned long flags;
 	asm volatile(
-		"	mrs	%0, cpsr	@ local_save_flags"
+		"	mrs	%0, " IRQMASK_REG_NAME_R "	@ local_save_flags"
 		: "=r" (flags) : : "memory", "cc");
 	return flags;
 }
@@ -140,7 +150,7 @@ static inline unsigned long arch_local_save_flags(void)
 static inline void arch_local_irq_restore(unsigned long flags)
 {
 	asm volatile(
-		"	msr	cpsr_c, %0	@ local_irq_restore"
+		"	msr	" IRQMASK_REG_NAME_W ", %0	@ local_irq_restore"
 		:
 		: "r" (flags)
 		: "memory", "cc");
@@ -148,8 +158,8 @@ static inline void arch_local_irq_restore(unsigned long flags)
 
 static inline int arch_irqs_disabled_flags(unsigned long flags)
 {
-	return flags & PSR_I_BIT;
+	return flags & IRQMASK_I_BIT;
 }
 
-#endif
-#endif
+#endif /* ifdef __KERNEL__ */
+#endif /* ifndef __ASM_ARM_IRQFLAGS_H */

arch/arm/include/asm/ptrace.h

@@ -45,6 +45,7 @@ struct pt_regs {
  */
 static inline int valid_user_regs(struct pt_regs *regs)
 {
+#ifndef CONFIG_CPU_V7M
 	unsigned long mode = regs->ARM_cpsr & MODE_MASK;
 
 	/*
@@ -67,6 +68,9 @@ static inline int valid_user_regs(struct pt_regs *regs)
 		regs->ARM_cpsr |= USR_MODE;
 
 	return 0;
+#else /* ifndef CONFIG_CPU_V7M */
+	return 1;
+#endif
 }
 
 static inline long regs_return_value(struct pt_regs *regs)

arch/arm/include/asm/system_info.h

@@ -11,6 +11,7 @@
 #define CPU_ARCH_ARMv5TEJ	7
 #define CPU_ARCH_ARMv6		8
 #define CPU_ARCH_ARMv7		9
+#define CPU_ARCH_ARMv7M		10
 
 #ifndef __ASSEMBLY__
 

arch/arm/include/asm/v7m.h

+/*
+ * Common defines for v7m cpus
+ */
+#define V7M_SCS_ICTR			IOMEM(0xe000e004)
+#define V7M_SCS_ICTR_INTLINESNUM_MASK		0x0000000f
+
+#define BASEADDR_V7M_SCB		IOMEM(0xe000ed00)
+
+#define V7M_SCB_CPUID			0x00
+
+#define V7M_SCB_ICSR			0x04
+#define V7M_SCB_ICSR_PENDSVSET			(1 << 28)
+#define V7M_SCB_ICSR_PENDSVCLR			(1 << 27)
+#define V7M_SCB_ICSR_RETTOBASE			(1 << 11)
+
+#define V7M_SCB_VTOR			0x08
+
+#define V7M_SCB_SCR			0x10
+#define V7M_SCB_SCR_SLEEPDEEP			(1 << 2)
+
+#define V7M_SCB_CCR			0x14
+#define V7M_SCB_CCR_STKALIGN			(1 << 9)
+
+#define V7M_SCB_SHPR2			0x1c
+#define V7M_SCB_SHPR3			0x20
+
+#define V7M_SCB_SHCSR			0x24
+#define V7M_SCB_SHCSR_USGFAULTENA		(1 << 18)
+#define V7M_SCB_SHCSR_BUSFAULTENA		(1 << 17)
+#define V7M_SCB_SHCSR_MEMFAULTENA		(1 << 16)
+
+#define V7M_xPSR_FRAMEPTRALIGN			0x00000200
+#define V7M_xPSR_EXCEPTIONNO			0x000001ff
+
+/*
+ * When branching to an address that has bits [31:28] == 0xf an exception return
+ * occurs. Bits [27:5] are reserved (SBOP). If the processor implements the FP
+ * extension Bit [4] defines if the exception frame has space allocated for FP
+ * state information, SBOP otherwise. Bit [3] defines the mode that is returned
+ * to (0 -> handler mode; 1 -> thread mode). Bit [2] defines which sp is used
+ * (0 -> msp; 1 -> psp). Bits [1:0] are fixed to 0b01.
+ */
+#define EXC_RET_STACK_MASK			0x00000004
+#define EXC_RET_THREADMODE_PROCESSSTACK		0xfffffffd

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

@@ -34,28 +34,47 @@
 
 /*
  * PSR bits
+ * Note on V7M there is no mode contained in the PSR
  */
 #define USR26_MODE	0x00000000
 #define FIQ26_MODE	0x00000001
 #define IRQ26_MODE	0x00000002
 #define SVC26_MODE	0x00000003
+#if defined(__KERNEL__) && defined(CONFIG_CPU_V7M)
+/*
+ * Use 0 here to get code right that creates a userspace
+ * or kernel space thread.
+ */
+#define USR_MODE	0x00000000
+#define SVC_MODE	0x00000000
+#else
 #define USR_MODE	0x00000010
+#define SVC_MODE	0x00000013
+#endif
 #define FIQ_MODE	0x00000011
 #define IRQ_MODE	0x00000012
-#define SVC_MODE	0x00000013
 #define ABT_MODE	0x00000017
 #define HYP_MODE	0x0000001a
 #define UND_MODE	0x0000001b
 #define SYSTEM_MODE	0x0000001f
 #define MODE32_BIT	0x00000010
 #define MODE_MASK	0x0000001f
-#define PSR_T_BIT	0x00000020
-#define PSR_F_BIT	0x00000040
-#define PSR_I_BIT	0x00000080
-#define PSR_A_BIT	0x00000100
-#define PSR_E_BIT	0x00000200
-#define PSR_J_BIT	0x01000000
-#define PSR_Q_BIT	0x08000000
+
+#define V4_PSR_T_BIT	0x00000020	/* >= V4T, but not V7M */
+#define V7M_PSR_T_BIT	0x01000000
+#if defined(__KERNEL__) && defined(CONFIG_CPU_V7M)
+#define PSR_T_BIT	V7M_PSR_T_BIT
+#else
+/* for compatibility */
+#define PSR_T_BIT	V4_PSR_T_BIT
+#endif
+
+#define PSR_F_BIT	0x00000040	/* >= V4, but not V7M */
+#define PSR_I_BIT	0x00000080	/* >= V4, but not V7M */
+#define PSR_A_BIT	0x00000100	/* >= V6, but not V7M */
+#define PSR_E_BIT	0x00000200	/* >= V6, but not V7M */
+#define PSR_J_BIT	0x01000000	/* >= V5J, but not V7M */
+#define PSR_Q_BIT	0x08000000	/* >= V5E, including V7M */
 #define PSR_V_BIT	0x10000000
 #define PSR_C_BIT	0x20000000
 #define PSR_Z_BIT	0x40000000

arch/arm/kernel/Makefile

@@ -15,7 +15,7 @@ CFLAGS_REMOVE_return_address.o = -pg
 
 # Object file lists.
 
-obj-y		:= elf.o entry-armv.o entry-common.o irq.o opcodes.o \
+obj-y		:= elf.o entry-common.o irq.o opcodes.o \
 		   process.o ptrace.o return_address.o sched_clock.o \
 		   setup.o signal.o stacktrace.o sys_arm.o time.o traps.o
 
@@ -23,6 +23,12 @@ obj-$(CONFIG_ATAGS)		+= atags_parse.o
 obj-$(CONFIG_ATAGS_PROC)	+= atags_proc.o
 obj-$(CONFIG_DEPRECATED_PARAM_STRUCT) += atags_compat.o
 
+ifeq ($(CONFIG_CPU_V7M),y)
+obj-y		+= entry-v7m.o
+else
+obj-y		+= entry-armv.o
+endif
+
 obj-$(CONFIG_OC_ETM)		+= etm.o
 obj-$(CONFIG_CPU_IDLE)		+= cpuidle.o
 obj-$(CONFIG_ISA_DMA_API)	+= dma.o

arch/arm/kernel/entry-common.S

@@ -350,6 +350,9 @@ ENDPROC(ftrace_stub)
 
 	.align	5
 ENTRY(vector_swi)
+#ifdef CONFIG_CPU_V7M
+	v7m_exception_entry
+#else
 	sub	sp, sp, #S_FRAME_SIZE
 	stmia	sp, {r0 - r12}			@ Calling r0 - r12
  ARM(	add	r8, sp, #S_PC		)
@@ -360,6 +363,7 @@ ENTRY(vector_swi)
 	str	lr, [sp, #S_PC]			@ Save calling PC
 	str	r8, [sp, #S_PSR]		@ Save CPSR
 	str	r0, [sp, #S_OLD_R0]		@ Save OLD_R0
+#endif
 	zero_fp
 
 	/*

arch/arm/kernel/entry-header.S

@@ -5,6 +5,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/errno.h>
 #include <asm/thread_info.h>
+#include <asm/v7m.h>
 
 @ Bad Abort numbers
 @ -----------------
@@ -44,6 +45,116 @@
 #endif
 	.endm
 
+#ifdef CONFIG_CPU_V7M
+/*
+ * ARMv7-M exception entry/exit macros.
+ *
+ * xPSR, ReturnAddress(), LR (R14), R12, R3, R2, R1, and R0 are
+ * automatically saved on the current stack (32 words) before
+ * switching to the exception stack (SP_main).
+ *
+ * If exception is taken while in user mode, SP_main is
+ * empty. Otherwise, SP_main is aligned to 64 bit automatically
+ * (CCR.STKALIGN set).
+ *
+ * Linux assumes that the interrupts are disabled when entering an
+ * exception handler and it may BUG if this is not the case. Interrupts
+ * are disabled during entry and reenabled in the exit macro.
+ *
+ * v7m_exception_slow_exit is used when returning from SVC or PendSV.
+ * When returning to kernel mode, we don't return from exception.
+ */
+	.macro	v7m_exception_entry
+	@ determine the location of the registers saved by the core during
+	@ exception entry. Depending on the mode the cpu was in when the
+	@ exception happend that is either on the main or the process stack.
+	@ Bit 2 of EXC_RETURN stored in the lr register specifies which stack
+	@ was used.
+	tst	lr, #EXC_RET_STACK_MASK
+	mrsne	r12, psp
+	moveq	r12, sp
+
+	@ we cannot rely on r0-r3 and r12 matching the value saved in the
+	@ exception frame because of tail-chaining. So these have to be
+	@ reloaded.
+	ldmia	r12!, {r0-r3}
+
+	@ Linux expects to have irqs off. Do it here before taking stack space
+	cpsid	i
+
+	sub	sp, #S_FRAME_SIZE-S_IP
+	stmdb	sp!, {r0-r11}
+
+	@ load saved r12, lr, return address and xPSR.
+	@ r0-r7 are used for signals and never touched from now on. Clobbering
+	@ r8-r12 is OK.
+	mov	r9, r12
+	ldmia	r9!, {r8, r10-r12}
+
+	@ calculate the original stack pointer value.
+	@ r9 currently points to the memory location just above the auto saved
+	@ xPSR.
+	@ The cpu might automatically 8-byte align the stack. Bit 9
+	@ of the saved xPSR specifies if stack aligning took place. In this case
+	@ another 32-bit value is included in the stack.
+
+	tst	r12, V7M_xPSR_FRAMEPTRALIGN
+	addne	r9, r9, #4
+
+	@ store saved r12 using str to have a register to hold the base for stm
+	str	r8, [sp, #S_IP]
+	add	r8, sp, #S_SP
+	@ store r13-r15, xPSR
+	stmia	r8!, {r9-r12}
+	@ store old_r0
+	str	r0, [r8]
+	.endm
+
+        /*
+	 * PENDSV and SVCALL are configured to have the same exception
+	 * priorities. As a kernel thread runs at SVCALL execution priority it
+	 * can never be preempted and so we will never have to return to a
+	 * kernel thread here.
+         */
+	.macro	v7m_exception_slow_exit ret_r0
+	cpsid	i
+	ldr	lr, =EXC_RET_THREADMODE_PROCESSSTACK
+
+	@ read original r12, sp, lr, pc and xPSR
+	add	r12, sp, #S_IP
+	ldmia	r12, {r1-r5}
+
+	@ an exception frame is always 8-byte aligned. To tell the hardware if
+	@ the sp to be restored is aligned or not set bit 9 of the saved xPSR
+	@ accordingly.
+	tst	r2, #4
+	subne	r2, r2, #4
+	orrne	r5, V7M_xPSR_FRAMEPTRALIGN
+	biceq	r5, V7M_xPSR_FRAMEPTRALIGN
+
+	@ write basic exception frame
+	stmdb	r2!, {r1, r3-r5}
+	ldmia	sp, {r1, r3-r5}
+	.if	\ret_r0
+	stmdb	r2!, {r0, r3-r5}
+	.else
+	stmdb	r2!, {r1, r3-r5}
+	.endif
+
+	@ restore process sp
+	msr	psp, r2
+
+	@ restore original r4-r11
+	ldmia	sp!, {r0-r11}
+
+	@ restore main sp
+	add	sp, sp, #S_FRAME_SIZE-S_IP
+
+	cpsie	i
+	bx	lr
+	.endm
+#endif	/* CONFIG_CPU_V7M */
+
 	@
 	@ Store/load the USER SP and LR registers by switching to the SYS
 	@ mode. Useful in Thumb-2 mode where "stm/ldm rd, {sp, lr}^" is not
@@ -165,6 +276,18 @@
 	rfeia	sp!
 	.endm
 
+#ifdef CONFIG_CPU_V7M
+	/*
+	 * Note we don't need to do clrex here as clearing the local monitor is
+	 * part of each exception entry and exit sequence.
+	 */
+	.macro	restore_user_regs, fast = 0, offset = 0
+	.if	\offset
+	add	sp, #\offset
+	.endif
+	v7m_exception_slow_exit ret_r0 = \fast
+	.endm
+#else	/* ifdef CONFIG_CPU_V7M */
 	.macro	restore_user_regs, fast = 0, offset = 0
 	clrex					@ clear the exclusive monitor
 	mov	r2, sp
@@ -181,6 +304,7 @@
 	add	sp, sp, #S_FRAME_SIZE - S_SP
 	movs	pc, lr				@ return & move spsr_svc into cpsr
 	.endm
+#endif	/* ifdef CONFIG_CPU_V7M / else */
 
 	.macro	get_thread_info, rd
 	mov	\rd, sp

arch/arm/kernel/entry-v7m.S

+/*
+ * linux/arch/arm/kernel/entry-v7m.S
+ *
+ * Copyright (C) 2008 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Low-level vector interface routines for the ARMv7-M architecture
+ */
+#include <asm/memory.h>
+#include <asm/glue.h>
+#include <asm/thread_notify.h>
+#include <asm/v7m.h>
+
+#include <mach/entry-macro.S>
+
+#include "entry-header.S"
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+#error "CONFIG_TRACE_IRQFLAGS not supported on the current ARMv7M implementation"
+#endif
+
+__invalid_entry:
+	v7m_exception_entry
+	adr	r0, strerr
+	mrs	r1, ipsr
+	mov	r2, lr
+	bl	printk
+	mov	r0, sp
+	bl	show_regs
+1:	b	1b
+ENDPROC(__invalid_entry)
+
+strerr:	.asciz	"\nUnhandled exception: IPSR = %08lx LR = %08lx\n"
+
+	.align	2
+__irq_entry:
+	v7m_exception_entry
+
+	@
+	@ Invoke the IRQ handler
+	@
+	mrs	r0, ipsr
+	ldr	r1, =V7M_xPSR_EXCEPTIONNO
+	and	r0, r1
+	sub	r0, #16
+	mov	r1, sp
+	stmdb	sp!, {lr}
+	@ routine called with r0 = irq number, r1 = struct pt_regs *
+	bl	nvic_do_IRQ
+
+	pop	{lr}
+	@
+	@ Check for any pending work if returning to user
+	@
+	ldr	r1, =BASEADDR_V7M_SCB
+	ldr	r0, [r1, V7M_SCB_ICSR]
+	tst	r0, V7M_SCB_ICSR_RETTOBASE
+	beq	2f
+
+	get_thread_info tsk
+	ldr	r2, [tsk, #TI_FLAGS]
+	tst	r2, #_TIF_WORK_MASK
+	beq	2f			@ no work pending
+	mov	r0, #V7M_SCB_ICSR_PENDSVSET
+	str	r0, [r1, V7M_SCB_ICSR]	@ raise PendSV
+
+2:
+	@ registers r0-r3 and r12 are automatically restored on exception
+	@ return. r4-r7 were not clobbered in v7m_exception_entry so for
+	@ correctness they don't need to be restored. So only r8-r11 must be
+	@ restored here. The easiest way to do so is to restore r0-r7, too.
+	ldmia	sp!, {r0-r11}
+	add	sp, #S_FRAME_SIZE-S_IP
+	cpsie	i
+	bx	lr
+ENDPROC(__irq_entry)
+
+__pendsv_entry:
+	v7m_exception_entry
+
+	ldr	r1, =BASEADDR_V7M_SCB
+	mov	r0, #V7M_SCB_ICSR_PENDSVCLR
+	str	r0, [r1, V7M_SCB_ICSR]	@ clear PendSV
+
+	@ execute the pending work, including reschedule
+	get_thread_info tsk
+	mov	why, #0
+	b	ret_to_user
+ENDPROC(__pendsv_entry)
+
+/*
+ * Register switch for ARMv7-M processors.
+ * r0 = previous task_struct, r1 = previous thread_info, r2 = next thread_info
+ * previous and next are guaranteed not to be the same.
+ */
+ENTRY(__switch_to)
+	.fnstart
+	.cantunwind
+	add	ip, r1, #TI_CPU_SAVE
+	stmia	ip!, {r4 - r11}		@ Store most regs on stack
+	str	sp, [ip], #4
+	str	lr, [ip], #4
+	mov	r5, r0
+	add	r4, r2, #TI_CPU_SAVE
+	ldr	r0, =thread_notify_head
+	mov	r1, #THREAD_NOTIFY_SWITCH
+	bl	atomic_notifier_call_chain
+	mov	ip, r4
+	mov	r0, r5
+	ldmia	ip!, {r4 - r11}		@ Load all regs saved previously
+	ldr	sp, [ip]
+	ldr	pc, [ip, #4]!
+	.fnend
+ENDPROC(__switch_to)
+
+	.data
+	.align	8
+/*
+ * Vector table (64 words => 256 bytes natural alignment)
+ */
+ENTRY(vector_table)
+	.long	0			@ 0 - Reset stack pointer
+	.long	__invalid_entry		@ 1 - Reset
+	.long	__invalid_entry		@ 2 - NMI
+	.long	__invalid_entry		@ 3 - HardFault
+	.long	__invalid_entry		@ 4 - MemManage
+	.long	__invalid_entry		@ 5 - BusFault
+	.long	__invalid_entry		@ 6 - UsageFault
+	.long	__invalid_entry		@ 7 - Reserved
+	.long	__invalid_entry		@ 8 - Reserved
+	.long	__invalid_entry		@ 9 - Reserved
+	.long	__invalid_entry		@ 10 - Reserved
+	.long	vector_swi		@ 11 - SVCall
+	.long	__invalid_entry		@ 12 - Debug Monitor
+	.long	__invalid_entry		@ 13 - Reserved
+	.long	__pendsv_entry		@ 14 - PendSV
+	.long	__invalid_entry		@ 15 - SysTick
+	.rept	64 - 16
+	.long	__irq_entry		@ 16..64 - External Interrupts
+	.endr

arch/arm/kernel/head-nommu.S

@@ -19,6 +19,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/cp15.h>
 #include <asm/thread_info.h>
+#include <asm/v7m.h>
 
 /*
  * Kernel startup entry point.
@@ -50,10 +51,13 @@ ENTRY(stext)
 
 	setmode	PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 @ ensure svc mode
 						@ and irqs disabled
-#ifndef CONFIG_CPU_CP15
-	ldr	r9, =CONFIG_PROCESSOR_ID
-#else
+#if defined(CONFIG_CPU_CP15)
 	mrc	p15, 0, r9, c0, c0		@ get processor id
+#elif defined(CONFIG_CPU_V7M)
+	ldr	r9, =BASEADDR_V7M_SCB
+	ldr	r9, [r9, V7M_SCB_CPUID]
+#else
+	ldr	r9, =CONFIG_PROCESSOR_ID
 #endif
 	bl	__lookup_processor_type		@ r5=procinfo r9=cpuid
 	movs	r10, r5				@ invalid processor (r5=0)?

arch/arm/kernel/setup.c

@@ -128,7 +128,9 @@ struct stack {
 	u32 und[3];
 } ____cacheline_aligned;
 
+#ifndef CONFIG_CPU_V7M
 static struct stack stacks[NR_CPUS];
+#endif
 
 char elf_platform[ELF_PLATFORM_SIZE];
 EXPORT_SYMBOL(elf_platform);
@@ -207,7 +209,7 @@ static const char *proc_arch[] = {
 	"5TEJ",
 	"6TEJ",
 	"7",
-	"?(11)",
+	"7M",
 	"?(12)",
 	"?(13)",
 	"?(14)",
@@ -216,6 +218,12 @@ static const char *proc_arch[] = {
 	"?(17)",
 };
 
+#ifdef CONFIG_CPU_V7M
+static int __get_cpu_architecture(void)
+{
+	return CPU_ARCH_ARMv7M;
+}
+#else
 static int __get_cpu_architecture(void)
 {
 	int cpu_arch;
@@ -248,6 +256,7 @@ static int __get_cpu_architecture(void)
 
 	return cpu_arch;
 }
+#endif
 
 int __pure cpu_architecture(void)
 {
@@ -293,7 +302,9 @@ static void __init cacheid_init(void)
 {
 	unsigned int arch = cpu_architecture();
 
-	if (arch >= CPU_ARCH_ARMv6) {
+	if (arch == CPU_ARCH_ARMv7M) {
+		cacheid = 0;
+	} else if (arch >= CPU_ARCH_ARMv6) {
 		unsigned int cachetype = read_cpuid_cachetype();
 		if ((cachetype & (7 << 29)) == 4 << 29) {
 			/* ARMv7 register format */
@@ -392,6 +403,7 @@ static void __init feat_v6_fixup(void)
  */
 void notrace cpu_init(void)
 {
+#ifndef CONFIG_CPU_V7M
 	unsigned int cpu = smp_processor_id();
 	struct stack *stk = &stacks[cpu];
 
@@ -442,6 +454,7 @@ void notrace cpu_init(void)
 	      "I" (offsetof(struct stack, und[0])),
 	      PLC (PSR_F_BIT | PSR_I_BIT | SVC_MODE)
 	    : "r14");
+#endif
 }
 
 int __cpu_logical_map[NR_CPUS];

arch/arm/kernel/traps.c

@@ -812,6 +812,7 @@ static void __init kuser_get_tls_init(unsigned long vectors)
 
 void __init early_trap_init(void *vectors_base)
 {
+#ifndef CONFIG_CPU_V7M
 	unsigned long vectors = (unsigned long)vectors_base;
 	extern char __stubs_start[], __stubs_end[];
 	extern char __vectors_start[], __vectors_end[];
@@ -843,4 +844,11 @@ void __init early_trap_init(void *vectors_base)
 
 	flush_icache_range(vectors, vectors + PAGE_SIZE);
 	modify_domain(DOMAIN_USER, DOMAIN_CLIENT);
+#else /* ifndef CONFIG_CPU_V7M */
+	/*
+	 * on V7-M there is no need to copy the vector table to a dedicated
+	 * memory area. The address is configurable and so a table in the kernel
+	 * image can be used.
+	 */
+#endif
 }

arch/arm/mm/Kconfig

@@ -397,6 +397,15 @@ config CPU_V7
 	select CPU_PABRT_V7
 	select CPU_TLB_V7 if MMU
 
+# ARMv7M
+config CPU_V7M
+	bool
+	select CPU_32v7M
+	select CPU_ABRT_NOMMU
+	select CPU_CACHE_NOP
+	select CPU_PABRT_LEGACY
+	select CPU_THUMBONLY
+
 config CPU_THUMBONLY
 	bool
 	# There are no CPUs available with MMU that don't implement an ARM ISA:
@@ -441,6 +450,9 @@ config CPU_32v6K
 config CPU_32v7
 	bool
 
+config CPU_32v7M
+	bool
+
 # The abort model
 config CPU_ABRT_NOMMU
 	bool
@@ -491,6 +503,9 @@ config CPU_CACHE_V6
 config CPU_CACHE_V7
 	bool
 
+config CPU_CACHE_NOP
+	bool
+
 config CPU_CACHE_VIVT
 	bool
 
@@ -613,7 +628,11 @@ config ARCH_DMA_ADDR_T_64BIT
 
 config ARM_THUMB
 	bool "Support Thumb user binaries" if !CPU_THUMBONLY
-	depends on CPU_ARM720T || CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM946E || CPU_ARM1020 || CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_V6 || CPU_V6K || CPU_V7 || CPU_FEROCEON
+	depends on CPU_ARM720T || CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || \
+		CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM946E || \
+		CPU_ARM1020 || CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || \
+		CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_V6 || CPU_V6K || \
+		CPU_V7 || CPU_FEROCEON || CPU_V7M
 	default y
 	help
 	  Say Y if you want to include kernel support for running user space

arch/arm/mm/Makefile

@@ -39,6 +39,7 @@ obj-$(CONFIG_CPU_CACHE_V4WB)	+= cache-v4wb.o
 obj-$(CONFIG_CPU_CACHE_V6)	+= cache-v6.o
 obj-$(CONFIG_CPU_CACHE_V7)	+= cache-v7.o
 obj-$(CONFIG_CPU_CACHE_FA)	+= cache-fa.o
+obj-$(CONFIG_CPU_CACHE_NOP)	+= cache-nop.o
 
 AFLAGS_cache-v6.o	:=-Wa,-march=armv6
 AFLAGS_cache-v7.o	:=-Wa,-march=armv7-a
@@ -87,6 +88,7 @@ obj-$(CONFIG_CPU_FEROCEON)	+= proc-feroceon.o
 obj-$(CONFIG_CPU_V6)		+= proc-v6.o
 obj-$(CONFIG_CPU_V6K)		+= proc-v6.o
 obj-$(CONFIG_CPU_V7)		+= proc-v7.o
+obj-$(CONFIG_CPU_V7M)		+= proc-v7m.o
 
 AFLAGS_proc-v6.o	:=-Wa,-march=armv6
 AFLAGS_proc-v7.o	:=-Wa,-march=armv7-a

arch/arm/mm/cache-nop.S

+/*
+ * 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.
+ */
+#include <linux/linkage.h>
+#include <linux/init.h>
+
+#include "proc-macros.S"
+
+ENTRY(nop_flush_icache_all)
+	mov	pc, lr
+ENDPROC(nop_flush_icache_all)
+
+	.globl nop_flush_kern_cache_all
+	.equ nop_flush_kern_cache_all, nop_flush_icache_all
+
+	.globl nop_flush_kern_cache_louis
+	.equ nop_flush_kern_cache_louis, nop_flush_icache_all
+
+	.globl nop_flush_user_cache_all
+	.equ nop_flush_user_cache_all, nop_flush_icache_all
+
+	.globl nop_flush_user_cache_range
+	.equ nop_flush_user_cache_range, nop_flush_icache_all
+
+	.globl nop_coherent_kern_range
+	.equ nop_coherent_kern_range, nop_flush_icache_all
+
+ENTRY(nop_coherent_user_range)
+	mov	r0, 0
+	mov	pc, lr
+ENDPROC(nop_coherent_user_range)
+
+	.globl nop_flush_kern_dcache_area
+	.equ nop_flush_kern_dcache_area, nop_flush_icache_all
+
+	.globl nop_dma_flush_range
+	.equ nop_dma_flush_range, nop_flush_icache_all
+
+	.globl nop_dma_map_area
+	.equ nop_dma_map_area, nop_flush_icache_all
+
+	.globl nop_dma_unmap_area
+	.equ nop_dma_unmap_area, nop_flush_icache_all
+
+	__INITDATA
+
+	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
+	define_cache_functions nop

arch/arm/mm/nommu.c

@@ -20,12 +20,19 @@
 
 void __init arm_mm_memblock_reserve(void)
 {
+#ifndef CONFIG_CPU_V7M
 	/*
 	 * Register the exception vector page.
 	 * some architectures which the DRAM is the exception vector to trap,
 	 * alloc_page breaks with error, although it is not NULL, but "0."
 	 */
 	memblock_reserve(CONFIG_VECTORS_BASE, PAGE_SIZE);
+#else /* ifndef CONFIG_CPU_V7M */
+	/*
+	 * There is no dedicated vector page on V7-M. So nothing needs to be
+	 * reserved here.
+	 */
+#endif
 }
 
 void __init sanity_check_meminfo(void)

arch/arm/mm/proc-v7m.S

+/*
+ *  linux/arch/arm/mm/proc-v7m.S
+ *
+ *  Copyright (C) 2008 ARM Ltd.
+ *  Copyright (C) 2001 Deep Blue Solutions Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ *  This is the "shell" of the ARMv7-M processor support.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/v7m.h>
+#include "proc-macros.S"
+
+ENTRY(cpu_v7m_proc_init)
+	mov	pc, lr
+ENDPROC(cpu_v7m_proc_init)
+
+ENTRY(cpu_v7m_proc_fin)
+	mov	pc, lr
+ENDPROC(cpu_v7m_proc_fin)
+
+/*
+ *	cpu_v7m_reset(loc)
+ *
+ *	Perform a soft reset of the system.  Put the CPU into the
+ *	same state as it would be if it had been reset, and branch
+ *	to what would be the reset vector.
+ *
+ *	- loc   - location to jump to for soft reset
+ */
+	.align	5
+ENTRY(cpu_v7m_reset)
+	mov	pc, r0
+ENDPROC(cpu_v7m_reset)
+
+/*
+ *	cpu_v7m_do_idle()
+ *
+ *	Idle the processor (eg, wait for interrupt).
+ *
+ *	IRQs are already disabled.
+ */
+ENTRY(cpu_v7m_do_idle)
+	wfi
+	mov	pc, lr
+ENDPROC(cpu_v7m_do_idle)
+
+ENTRY(cpu_v7m_dcache_clean_area)
+	mov	pc, lr
+ENDPROC(cpu_v7m_dcache_clean_area)
+
+/*
+ * There is no MMU, so here is nothing to do.
+ */
+ENTRY(cpu_v7m_switch_mm)
+	mov	pc, lr
+ENDPROC(cpu_v7m_switch_mm)
+
+.globl	cpu_v7m_suspend_size
+.equ	cpu_v7m_suspend_size, 0
+
+#ifdef CONFIG_ARM_CPU_SUSPEND
+ENTRY(cpu_v7m_do_suspend)
+	mov	pc, lr
+ENDPROC(cpu_v7m_do_suspend)
+
+ENTRY(cpu_v7m_do_resume)
+	mov	pc, lr
+ENDPROC(cpu_v7m_do_resume)
+#endif
+
+	.section ".text.init", #alloc, #execinstr
+
+/*
+ *	__v7m_setup
+ *
+ *	This should be able to cover all ARMv7-M cores.
+ */
+__v7m_setup:
+	@ Configure the vector table base address
+	ldr	r0, =BASEADDR_V7M_SCB
+	ldr	r12, =vector_table
+	str	r12, [r0, V7M_SCB_VTOR]
+
+	@ enable UsageFault, BusFault and MemManage fault.
+	ldr	r5, [r0, #V7M_SCB_SHCSR]
+	orr	r5, #(V7M_SCB_SHCSR_USGFAULTENA | V7M_SCB_SHCSR_BUSFAULTENA | V7M_SCB_SHCSR_MEMFAULTENA)
+	str	r5, [r0, #V7M_SCB_SHCSR]
+
+	@ Lower the priority of the SVC and PendSV exceptions
+	mov	r5, #0x80000000
+	str	r5, [r0, V7M_SCB_SHPR2]	@ set SVC priority
+	mov	r5, #0x00800000
+	str	r5, [r0, V7M_SCB_SHPR3]	@ set PendSV priority
+
+	@ SVC to run the kernel in this mode
+	adr	r1, BSYM(1f)
+	ldr	r5, [r12, #11 * 4]	@ read the SVC vector entry
+	str	r1, [r12, #11 * 4]	@ write the temporary SVC vector entry
+	mov	r6, lr			@ save LR
+	mov	r7, sp			@ save SP
+	ldr	sp, =__v7m_setup_stack_top
+	cpsie	i
+	svc	#0
+1:	cpsid	i
+	str	r5, [r12, #11 * 4]	@ restore the original SVC vector entry
+	mov	lr, r6			@ restore LR
+	mov	sp, r7			@ restore SP
+
+	@ Special-purpose control register
+	mov	r1, #1
+	msr	control, r1		@ Thread mode has unpriviledged access
+
+	@ Configure the System Control Register to ensure 8-byte stack alignment
+	@ Note the STKALIGN bit is either RW or RAO.
+	ldr	r12, [r0, V7M_SCB_CCR]	@ system control register
+	orr	r12, #V7M_SCB_CCR_STKALIGN
+	str	r12, [r0, V7M_SCB_CCR]
+	mov	pc, lr
+ENDPROC(__v7m_setup)
+
+	define_processor_functions v7m, dabort=nommu_early_abort, pabort=legacy_pabort, nommu=1
+
+	.section ".rodata"
+	string cpu_arch_name, "armv7m"
+	string cpu_elf_name "v7m"
+	string cpu_v7m_name "ARMv7-M"
+
+	.section ".proc.info.init", #alloc, #execinstr
+
+	/*
+	 * Match any ARMv7-M processor core.
+	 */
+	.type	__v7m_proc_info, #object
+__v7m_proc_info:
+	.long	0x000f0000		@ Required ID value
+	.long	0x000f0000		@ Mask for ID
+	.long   0			@ proc_info_list.__cpu_mm_mmu_flags
+	.long   0			@ proc_info_list.__cpu_io_mmu_flags
+	b	__v7m_setup		@ proc_info_list.__cpu_flush
+	.long	cpu_arch_name
+	.long	cpu_elf_name
+	.long	HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT
+	.long	cpu_v7m_name
+	.long	v7m_processor_functions	@ proc_info_list.proc
+	.long	0			@ proc_info_list.tlb
+	.long	0			@ proc_info_list.user
+	.long	nop_cache_fns		@ proc_info_list.cache
+	.size	__v7m_proc_info, . - __v7m_proc_info
+
+__v7m_setup_stack:
+	.space	4 * 8				@ 8 registers
+__v7m_setup_stack_top: