Merge branches 'at91', 'dcache', 'ftrace', 'hwbpt', 'misc', 'mmci', 's3c', 'st-ux' and 'unwind' into devel

arch/arm/include/asm/assembler.h

@@ -154,16 +154,39 @@
 	.long	9999b,9001f;			\
 	.popsection
 
+#ifdef CONFIG_SMP
+#define ALT_SMP(instr...)					\
+9998:	instr
+#define ALT_UP(instr...)					\
+	.pushsection ".alt.smp.init", "a"			;\
+	.long	9998b						;\
+	instr							;\
+	.popsection
+#define ALT_UP_B(label)					\
+	.equ	up_b_offset, label - 9998b			;\
+	.pushsection ".alt.smp.init", "a"			;\
+	.long	9998b						;\
+	b	. + up_b_offset					;\
+	.popsection
+#else
+#define ALT_SMP(instr...)
+#define ALT_UP(instr...) instr
+#define ALT_UP_B(label) b label
+#endif
+
 /*
  * SMP data memory barrier
  */
 	.macro	smp_dmb
 #ifdef CONFIG_SMP
 #if __LINUX_ARM_ARCH__ >= 7
-	dmb
+	ALT_SMP(dmb)
 #elif __LINUX_ARM_ARCH__ == 6
-	mcr	p15, 0, r0, c7, c10, 5	@ dmb
+	ALT_SMP(mcr	p15, 0, r0, c7, c10, 5)	@ dmb
+#else
+#error Incompatible SMP platform
 #endif
+	ALT_UP(nop)
 #endif
 	.endm
 

arch/arm/include/asm/cacheflush.h

@@ -137,10 +137,10 @@
 #endif
 
 /*
- * This flag is used to indicate that the page pointed to by a pte
- * is dirty and requires cleaning before returning it to the user.
+ * This flag is used to indicate that the page pointed to by a pte is clean
+ * and does not require cleaning before returning it to the user.
  */
-#define PG_dcache_dirty PG_arch_1
+#define PG_dcache_clean PG_arch_1
 
 /*
  *	MM Cache Management
@@ -156,6 +156,12 @@
  *	Please note that the implementation of these, and the required
  *	effects are cache-type (VIVT/VIPT/PIPT) specific.
  *
+ *	flush_icache_all()
+ *
+ *		Unconditionally clean and invalidate the entire icache.
+ *		Currently only needed for cache-v6.S and cache-v7.S, see
+ *		__flush_icache_all for the generic implementation.
+ *
  *	flush_kern_all()
  *
  *		Unconditionally clean and invalidate the entire cache.
@@ -206,6 +212,7 @@
  */
 
 struct cpu_cache_fns {
+	void (*flush_icache_all)(void);
 	void (*flush_kern_all)(void);
 	void (*flush_user_all)(void);
 	void (*flush_user_range)(unsigned long, unsigned long, unsigned int);
@@ -227,6 +234,7 @@ struct cpu_cache_fns {
 
 extern struct cpu_cache_fns cpu_cache;
 
+#define __cpuc_flush_icache_all		cpu_cache.flush_icache_all
 #define __cpuc_flush_kern_all		cpu_cache.flush_kern_all
 #define __cpuc_flush_user_all		cpu_cache.flush_user_all
 #define __cpuc_flush_user_range		cpu_cache.flush_user_range
@@ -246,6 +254,7 @@ extern struct cpu_cache_fns cpu_cache;
 
 #else
 
+#define __cpuc_flush_icache_all		__glue(_CACHE,_flush_icache_all)
 #define __cpuc_flush_kern_all		__glue(_CACHE,_flush_kern_cache_all)
 #define __cpuc_flush_user_all		__glue(_CACHE,_flush_user_cache_all)
 #define __cpuc_flush_user_range		__glue(_CACHE,_flush_user_cache_range)
@@ -253,6 +262,7 @@ extern struct cpu_cache_fns cpu_cache;
 #define __cpuc_coherent_user_range	__glue(_CACHE,_coherent_user_range)
 #define __cpuc_flush_dcache_area	__glue(_CACHE,_flush_kern_dcache_area)
 
+extern void __cpuc_flush_icache_all(void);
 extern void __cpuc_flush_kern_all(void);
 extern void __cpuc_flush_user_all(void);
 extern void __cpuc_flush_user_range(unsigned long, unsigned long, unsigned int);
@@ -291,6 +301,37 @@ extern void copy_to_user_page(struct vm_area_struct *, struct page *,
 /*
  * Convert calls to our calling convention.
  */
+
+/* Invalidate I-cache */
+#define __flush_icache_all_generic()					\
+	asm("mcr	p15, 0, %0, c7, c5, 0"				\
+	    : : "r" (0));
+
+/* Invalidate I-cache inner shareable */
+#define __flush_icache_all_v7_smp()					\
+	asm("mcr	p15, 0, %0, c7, c1, 0"				\
+	    : : "r" (0));
+
+/*
+ * Optimized __flush_icache_all for the common cases. Note that UP ARMv7
+ * will fall through to use __flush_icache_all_generic.
+ */
+#if (defined(CONFIG_CPU_V7) && defined(CONFIG_CPU_V6)) ||		\
+	defined(CONFIG_SMP_ON_UP)
+#define __flush_icache_preferred	__cpuc_flush_icache_all
+#elif __LINUX_ARM_ARCH__ >= 7 && defined(CONFIG_SMP)
+#define __flush_icache_preferred	__flush_icache_all_v7_smp
+#elif __LINUX_ARM_ARCH__ == 6 && defined(CONFIG_ARM_ERRATA_411920)
+#define __flush_icache_preferred	__cpuc_flush_icache_all
+#else
+#define __flush_icache_preferred	__flush_icache_all_generic
+#endif
+
+static inline void __flush_icache_all(void)
+{
+	__flush_icache_preferred();
+}
+
 #define flush_cache_all()		__cpuc_flush_kern_all()
 
 static inline void vivt_flush_cache_mm(struct mm_struct *mm)
@@ -366,21 +407,6 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 extern void flush_dcache_page(struct page *);
 
-static inline void __flush_icache_all(void)
-{
-#ifdef CONFIG_ARM_ERRATA_411920
-	extern void v6_icache_inval_all(void);
-	v6_icache_inval_all();
-#elif defined(CONFIG_SMP) && __LINUX_ARM_ARCH__ >= 7
-	asm("mcr	p15, 0, %0, c7, c1, 0	@ invalidate I-cache inner shareable\n"
-	    :
-	    : "r" (0));
-#else
-	asm("mcr	p15, 0, %0, c7, c5, 0	@ invalidate I-cache\n"
-	    :
-	    : "r" (0));
-#endif
-}
 static inline void flush_kernel_vmap_range(void *addr, int size)
 {
 	if ((cache_is_vivt() || cache_is_vipt_aliasing()))
@@ -405,9 +431,6 @@ static inline void flush_anon_page(struct vm_area_struct *vma,
 #define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
 static inline void flush_kernel_dcache_page(struct page *page)
 {
-	/* highmem pages are always flushed upon kunmap already */
-	if ((cache_is_vivt() || cache_is_vipt_aliasing()) && !PageHighMem(page))
-		__cpuc_flush_dcache_area(page_address(page), PAGE_SIZE);
 }
 
 #define flush_dcache_mmap_lock(mapping) \

arch/arm/include/asm/cachetype.h

@@ -6,6 +6,7 @@
 #define CACHEID_VIPT_ALIASING		(1 << 2)
 #define CACHEID_VIPT			(CACHEID_VIPT_ALIASING|CACHEID_VIPT_NONALIASING)
 #define CACHEID_ASID_TAGGED		(1 << 3)
+#define CACHEID_VIPT_I_ALIASING		(1 << 4)
 
 extern unsigned int cacheid;
 
@@ -14,15 +15,18 @@ extern unsigned int cacheid;
 #define cache_is_vipt_nonaliasing()	cacheid_is(CACHEID_VIPT_NONALIASING)
 #define cache_is_vipt_aliasing()	cacheid_is(CACHEID_VIPT_ALIASING)
 #define icache_is_vivt_asid_tagged()	cacheid_is(CACHEID_ASID_TAGGED)
+#define icache_is_vipt_aliasing()	cacheid_is(CACHEID_VIPT_I_ALIASING)
 
 /*
  * __LINUX_ARM_ARCH__ is the minimum supported CPU architecture
  * Mask out support which will never be present on newer CPUs.
  * - v6+ is never VIVT
- * - v7+ VIPT never aliases
+ * - v7+ VIPT never aliases on D-side
  */
 #if __LINUX_ARM_ARCH__ >= 7
-#define __CACHEID_ARCH_MIN	(CACHEID_VIPT_NONALIASING | CACHEID_ASID_TAGGED)
+#define __CACHEID_ARCH_MIN	(CACHEID_VIPT_NONALIASING |\
+				 CACHEID_ASID_TAGGED |\
+				 CACHEID_VIPT_I_ALIASING)
 #elif __LINUX_ARM_ARCH__ >= 6
 #define	__CACHEID_ARCH_MIN	(~CACHEID_VIVT)
 #else

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

@@ -288,15 +288,7 @@ extern void dmabounce_unregister_dev(struct device *);
  * DMA access and 1 if the buffer needs to be bounced.
  *
  */
-#ifdef CONFIG_SA1111
 extern int dma_needs_bounce(struct device*, dma_addr_t, size_t);
-#else
-static inline int dma_needs_bounce(struct device *dev, dma_addr_t addr,
-				   size_t size)
-{
-	return 0;
-}
-#endif
 
 /*
  * The DMA API, implemented by dmabounce.c.  See below for descriptions.

arch/arm/include/asm/ftrace.h

@@ -2,12 +2,30 @@
 #define _ASM_ARM_FTRACE
 
 #ifdef CONFIG_FUNCTION_TRACER
-#define MCOUNT_ADDR		((long)(mcount))
+#define MCOUNT_ADDR		((unsigned long)(__gnu_mcount_nc))
 #define MCOUNT_INSN_SIZE	4 /* sizeof mcount call */
 
 #ifndef __ASSEMBLY__
 extern void mcount(void);
 extern void __gnu_mcount_nc(void);
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+struct dyn_arch_ftrace {
+#ifdef CONFIG_OLD_MCOUNT
+	bool	old_mcount;
+#endif
+};
+
+static inline unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	/* With Thumb-2, the recorded addresses have the lsb set */
+	return addr & ~1;
+}
+
+extern void ftrace_caller_old(void);
+extern void ftrace_call_old(void);
+#endif
+
 #endif
 
 #endif

arch/arm/include/asm/hardware/coresight.h

@@ -21,18 +21,6 @@
 #define TRACER_RUNNING		BIT(TRACER_RUNNING_BIT)
 #define TRACER_CYCLE_ACC	BIT(TRACER_CYCLE_ACC_BIT)
 
-struct tracectx {
-	unsigned int	etb_bufsz;
-	void __iomem	*etb_regs;
-	void __iomem	*etm_regs;
-	unsigned long	flags;
-	int		ncmppairs;
-	int		etm_portsz;
-	struct device	*dev;
-	struct clk	*emu_clk;
-	struct mutex	mutex;
-};
-
 #define TRACER_TIMEOUT 10000
 
 #define etm_writel(t, v, x) \
@@ -112,10 +100,10 @@ struct tracectx {
 
 /* ETM status register, "ETM Architecture", 3.3.2 */
 #define ETMR_STATUS		(0x10)
-#define ETMST_OVERFLOW		(1 << 0)
-#define ETMST_PROGBIT		(1 << 1)
-#define ETMST_STARTSTOP		(1 << 2)
-#define ETMST_TRIGGER		(1 << 3)
+#define ETMST_OVERFLOW		BIT(0)
+#define ETMST_PROGBIT		BIT(1)
+#define ETMST_STARTSTOP		BIT(2)
+#define ETMST_TRIGGER		BIT(3)
 
 #define etm_progbit(t)		(etm_readl((t), ETMR_STATUS) & ETMST_PROGBIT)
 #define etm_started(t)		(etm_readl((t), ETMR_STATUS) & ETMST_STARTSTOP)
@@ -123,7 +111,7 @@ struct tracectx {
 
 #define ETMR_TRACEENCTRL2	0x1c
 #define ETMR_TRACEENCTRL	0x24
-#define ETMTE_INCLEXCL		(1 << 24)
+#define ETMTE_INCLEXCL		BIT(24)
 #define ETMR_TRACEENEVT		0x20
 #define ETMCTRL_OPTS		(ETMCTRL_DO_CPRT | \
 				ETMCTRL_DATA_DO_ADDR | \
@@ -146,12 +134,12 @@ struct tracectx {
 #define ETBR_CTRL		0x20
 #define ETBR_FORMATTERCTRL	0x304
 #define ETBFF_ENFTC		1
-#define ETBFF_ENFCONT		(1 << 1)
-#define ETBFF_FONFLIN		(1 << 4)
-#define ETBFF_MANUAL_FLUSH	(1 << 6)
-#define ETBFF_TRIGIN		(1 << 8)
-#define ETBFF_TRIGEVT		(1 << 9)
-#define ETBFF_TRIGFL		(1 << 10)
+#define ETBFF_ENFCONT		BIT(1)
+#define ETBFF_FONFLIN		BIT(4)
+#define ETBFF_MANUAL_FLUSH	BIT(6)
+#define ETBFF_TRIGIN		BIT(8)
+#define ETBFF_TRIGEVT		BIT(9)
+#define ETBFF_TRIGFL		BIT(10)
 
 #define etb_writel(t, v, x) \
 	(__raw_writel((v), (t)->etb_regs + (x)))

arch/arm/include/asm/hw_breakpoint.h

@@ -0,0 +1,133 @@
+#ifndef _ARM_HW_BREAKPOINT_H
+#define _ARM_HW_BREAKPOINT_H
+
+#ifdef __KERNEL__
+
+struct task_struct;
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+
+struct arch_hw_breakpoint_ctrl {
+		u32 __reserved	: 9,
+		mismatch	: 1,
+				: 9,
+		len		: 8,
+		type		: 2,
+		privilege	: 2,
+		enabled		: 1;
+};
+
+struct arch_hw_breakpoint {
+	u32	address;
+	u32	trigger;
+	struct perf_event *suspended_wp;
+	struct arch_hw_breakpoint_ctrl ctrl;
+};
+
+static inline u32 encode_ctrl_reg(struct arch_hw_breakpoint_ctrl ctrl)
+{
+	return (ctrl.mismatch << 22) | (ctrl.len << 5) | (ctrl.type << 3) |
+		(ctrl.privilege << 1) | ctrl.enabled;
+}
+
+static inline void decode_ctrl_reg(u32 reg,
+				   struct arch_hw_breakpoint_ctrl *ctrl)
+{
+	ctrl->enabled	= reg & 0x1;
+	reg >>= 1;
+	ctrl->privilege	= reg & 0x3;
+	reg >>= 2;
+	ctrl->type	= reg & 0x3;
+	reg >>= 2;
+	ctrl->len	= reg & 0xff;
+	reg >>= 17;
+	ctrl->mismatch	= reg & 0x1;
+}
+
+/* Debug architecture numbers. */
+#define ARM_DEBUG_ARCH_RESERVED	0	/* In case of ptrace ABI updates. */
+#define ARM_DEBUG_ARCH_V6	1
+#define ARM_DEBUG_ARCH_V6_1	2
+#define ARM_DEBUG_ARCH_V7_ECP14	3
+#define ARM_DEBUG_ARCH_V7_MM	4
+
+/* Breakpoint */
+#define ARM_BREAKPOINT_EXECUTE	0
+
+/* Watchpoints */
+#define ARM_BREAKPOINT_LOAD	1
+#define ARM_BREAKPOINT_STORE	2
+
+/* Privilege Levels */
+#define ARM_BREAKPOINT_PRIV	1
+#define ARM_BREAKPOINT_USER	2
+
+/* Lengths */
+#define ARM_BREAKPOINT_LEN_1	0x1
+#define ARM_BREAKPOINT_LEN_2	0x3
+#define ARM_BREAKPOINT_LEN_4	0xf
+#define ARM_BREAKPOINT_LEN_8	0xff
+
+/* Limits */
+#define ARM_MAX_BRP		16
+#define ARM_MAX_WRP		16
+#define ARM_MAX_HBP_SLOTS	(ARM_MAX_BRP + ARM_MAX_WRP)
+
+/* DSCR method of entry bits. */
+#define ARM_DSCR_MOE(x)			((x >> 2) & 0xf)
+#define ARM_ENTRY_BREAKPOINT		0x1
+#define ARM_ENTRY_ASYNC_WATCHPOINT	0x2
+#define ARM_ENTRY_SYNC_WATCHPOINT	0xa
+
+/* DSCR monitor/halting bits. */
+#define ARM_DSCR_HDBGEN		(1 << 14)
+#define ARM_DSCR_MDBGEN		(1 << 15)
+
+/* opcode2 numbers for the co-processor instructions. */
+#define ARM_OP2_BVR		4
+#define ARM_OP2_BCR		5
+#define ARM_OP2_WVR		6
+#define ARM_OP2_WCR		7
+
+/* Base register numbers for the debug registers. */
+#define ARM_BASE_BVR		64
+#define ARM_BASE_BCR		80
+#define ARM_BASE_WVR		96
+#define ARM_BASE_WCR		112
+
+/* Accessor macros for the debug registers. */
+#define ARM_DBG_READ(M, OP2, VAL) do {\
+	asm volatile("mrc p14, 0, %0, c0," #M ", " #OP2 : "=r" (VAL));\
+} while (0)
+
+#define ARM_DBG_WRITE(M, OP2, VAL) do {\
+	asm volatile("mcr p14, 0, %0, c0," #M ", " #OP2 : : "r" (VAL));\
+} while (0)
+
+struct notifier_block;
+struct perf_event;
+struct pmu;
+
+extern struct pmu perf_ops_bp;
+extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
+				  int *gen_len, int *gen_type);
+extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
+extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
+extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
+					   unsigned long val, void *data);
+
+extern u8 arch_get_debug_arch(void);
+extern u8 arch_get_max_wp_len(void);
+extern void clear_ptrace_hw_breakpoint(struct task_struct *tsk);
+
+int arch_install_hw_breakpoint(struct perf_event *bp);
+void arch_uninstall_hw_breakpoint(struct perf_event *bp);
+void hw_breakpoint_pmu_read(struct perf_event *bp);
+int hw_breakpoint_slots(int type);
+
+#else
+static inline void clear_ptrace_hw_breakpoint(struct task_struct *tsk) {}
+
+#endif	/* CONFIG_HAVE_HW_BREAKPOINT */
+#endif	/* __KERNEL__ */
+#endif	/* _ARM_HW_BREAKPOINT_H */

arch/arm/include/asm/module.h

@@ -7,20 +7,27 @@
 
 struct unwind_table;
 
-struct mod_arch_specific
-{
 #ifdef CONFIG_ARM_UNWIND
-	Elf_Shdr *unw_sec_init;
-	Elf_Shdr *unw_sec_devinit;
-	Elf_Shdr *unw_sec_core;
-	Elf_Shdr *sec_init_text;
-	Elf_Shdr *sec_devinit_text;
-	Elf_Shdr *sec_core_text;
-	struct unwind_table *unwind_init;
-	struct unwind_table *unwind_devinit;
-	struct unwind_table *unwind_core;
-#endif
+struct arm_unwind_mapping {
+	Elf_Shdr *unw_sec;
+	Elf_Shdr *sec_text;
+	struct unwind_table *unwind;
 };
+enum {
+	ARM_SEC_INIT,
+	ARM_SEC_DEVINIT,
+	ARM_SEC_CORE,
+	ARM_SEC_EXIT,
+	ARM_SEC_DEVEXIT,
+	ARM_SEC_MAX,
+};
+struct mod_arch_specific {
+	struct arm_unwind_mapping map[ARM_SEC_MAX];
+};
+#else
+struct mod_arch_specific {
+};
+#endif
 
 /*
  * Include the ARM architecture version.

arch/arm/include/asm/perf_event.h

@@ -17,7 +17,7 @@
  * counter interrupts are regular interrupts and not an NMI. This
  * means that when we receive the interrupt we can call
  * perf_event_do_pending() that handles all of the work with
- * interrupts enabled.
+ * interrupts disabled.
  */
 static inline void
 set_perf_event_pending(void)

arch/arm/include/asm/pgtable.h

@@ -278,9 +278,24 @@ extern struct page *empty_zero_page;
 
 #define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext)
 
-#define set_pte_at(mm,addr,ptep,pteval) do { \
-	set_pte_ext(ptep, pteval, (addr) >= TASK_SIZE ? 0 : PTE_EXT_NG); \
- } while (0)
+#if __LINUX_ARM_ARCH__ < 6
+static inline void __sync_icache_dcache(pte_t pteval)
+{
+}
+#else
+extern void __sync_icache_dcache(pte_t pteval);
+#endif
+
+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, pte_t pteval)
+{
+	if (addr >= TASK_SIZE)
+		set_pte_ext(ptep, pteval, 0);
+	else {
+		__sync_icache_dcache(pteval);
+		set_pte_ext(ptep, pteval, PTE_EXT_NG);
+	}
+}
 
 /*
  * The following only work if pte_present() is true.
@@ -290,8 +305,13 @@ extern struct page *empty_zero_page;
 #define pte_write(pte)		(pte_val(pte) & L_PTE_WRITE)
 #define pte_dirty(pte)		(pte_val(pte) & L_PTE_DIRTY)
 #define pte_young(pte)		(pte_val(pte) & L_PTE_YOUNG)
+#define pte_exec(pte)		(pte_val(pte) & L_PTE_EXEC)
 #define pte_special(pte)	(0)
 
+#define pte_present_user(pte) \
+	((pte_val(pte) & (L_PTE_PRESENT | L_PTE_USER)) == \
+	 (L_PTE_PRESENT | L_PTE_USER))
+
 #define PTE_BIT_FUNC(fn,op) \
 static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; }
 
@@ -317,6 +337,10 @@ static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
 #ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
 #define pgprot_dmacoherent(prot) \
 	__pgprot_modify(prot, L_PTE_MT_MASK|L_PTE_EXEC, L_PTE_MT_BUFFERABLE)
+#define __HAVE_PHYS_MEM_ACCESS_PROT
+struct file;
+extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+				     unsigned long size, pgprot_t vma_prot);
 #else
 #define pgprot_dmacoherent(prot) \
 	__pgprot_modify(prot, L_PTE_MT_MASK|L_PTE_EXEC, L_PTE_MT_UNCACHED)

arch/arm/include/asm/processor.h

@@ -19,6 +19,7 @@
 
 #ifdef __KERNEL__
 
+#include <asm/hw_breakpoint.h>
 #include <asm/ptrace.h>
 #include <asm/types.h>
 
@@ -41,6 +42,9 @@ struct debug_entry {
 struct debug_info {
 	int			nsaved;
 	struct debug_entry	bp[2];
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+	struct perf_event	*hbp[ARM_MAX_HBP_SLOTS];
+#endif
 };
 
 struct thread_struct {

arch/arm/include/asm/ptrace.h

@@ -29,6 +29,8 @@
 #define PTRACE_SETCRUNCHREGS	26
 #define PTRACE_GETVFPREGS	27
 #define PTRACE_SETVFPREGS	28
+#define PTRACE_GETHBPREGS	29
+#define PTRACE_SETHBPREGS	30
 
 /*
  * PSR bits

arch/arm/include/asm/smp_mpidr.h

@@ -0,0 +1,17 @@
+#ifndef ASMARM_SMP_MIDR_H
+#define ASMARM_SMP_MIDR_H
+
+#define hard_smp_processor_id()						\
+	({								\
+		unsigned int cpunum;					\
+		__asm__("\n"						\
+			"1:	mrc p15, 0, %0, c0, c0, 5\n"		\
+			"	.pushsection \".alt.smp.init\", \"a\"\n"\
+			"	.long	1b\n"				\
+			"	mov	%0, #0\n"			\
+			"	.popsection"				\
+			: "=r" (cpunum));				\
+		cpunum &= 0x0F;						\
+	})
+
+#endif

arch/arm/include/asm/smp_plat.h

@@ -7,15 +7,40 @@
 
 #include <asm/cputype.h>
 
+/*
+ * Return true if we are running on a SMP platform
+ */
+static inline bool is_smp(void)
+{
+#ifndef CONFIG_SMP
+	return false;
+#elif defined(CONFIG_SMP_ON_UP)
+	extern unsigned int smp_on_up;
+	return !!smp_on_up;
+#else
+	return true;
+#endif
+}
+
 /* all SMP configurations have the extended CPUID registers */
 static inline int tlb_ops_need_broadcast(void)
 {
+	if (!is_smp())
+		return 0;
+
 	return ((read_cpuid_ext(CPUID_EXT_MMFR3) >> 12) & 0xf) < 2;
 }
 
+#if !defined(CONFIG_SMP) || __LINUX_ARM_ARCH__ >= 7
+#define cache_ops_need_broadcast()	0
+#else
 static inline int cache_ops_need_broadcast(void)
 {
+	if (!is_smp())
+		return 0;
+
 	return ((read_cpuid_ext(CPUID_EXT_MMFR3) >> 12) & 0xf) < 1;
 }
+#endif
 
 #endif

arch/arm/include/asm/system.h

@@ -85,6 +85,10 @@ void hook_fault_code(int nr, int (*fn)(unsigned long, unsigned int,
 				       struct pt_regs *),
 		     int sig, int code, const char *name);
 
+void hook_ifault_code(int nr, int (*fn)(unsigned long, unsigned int,
+				       struct pt_regs *),
+		     int sig, int code, const char *name);
+
 #define xchg(ptr,x) \
 	((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
 
@@ -325,6 +329,8 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 extern void disable_hlt(void);
 extern void enable_hlt(void);
 
+void cpu_idle_wait(void);
+
 #include <asm-generic/cmpxchg-local.h>
 
 #if __LINUX_ARM_ARCH__ < 6

arch/arm/include/asm/tlbflush.h

@@ -70,6 +70,10 @@
 #undef _TLB
 #undef MULTI_TLB
 
+#ifdef CONFIG_SMP_ON_UP
+#define MULTI_TLB 1
+#endif
+
 #define v3_tlb_flags	(TLB_V3_FULL | TLB_V3_PAGE)
 
 #ifdef CONFIG_CPU_TLB_V3
@@ -185,17 +189,23 @@
 # define v6wbi_always_flags	(-1UL)
 #endif
 
-#ifdef CONFIG_SMP
-#define v7wbi_tlb_flags (TLB_WB | TLB_DCLEAN | TLB_V7_IS_BTB | \
+#define v7wbi_tlb_flags_smp	(TLB_WB | TLB_DCLEAN | TLB_V7_IS_BTB | \
 			 TLB_V7_UIS_FULL | TLB_V7_UIS_PAGE | TLB_V7_UIS_ASID)
-#else
-#define v7wbi_tlb_flags (TLB_WB | TLB_DCLEAN | TLB_BTB | \
+#define v7wbi_tlb_flags_up	(TLB_WB | TLB_DCLEAN | TLB_BTB | \
 			 TLB_V6_U_FULL | TLB_V6_U_PAGE | TLB_V6_U_ASID)
-#endif
 
 #ifdef CONFIG_CPU_TLB_V7
-# define v7wbi_possible_flags	v7wbi_tlb_flags
-# define v7wbi_always_flags	v7wbi_tlb_flags
+
+# ifdef CONFIG_SMP_ON_UP
+#  define v7wbi_possible_flags	(v7wbi_tlb_flags_smp | v7wbi_tlb_flags_up)
+#  define v7wbi_always_flags	(v7wbi_tlb_flags_smp & v7wbi_tlb_flags_up)
+# elif defined(CONFIG_SMP)
+#  define v7wbi_possible_flags	v7wbi_tlb_flags_smp
+#  define v7wbi_always_flags	v7wbi_tlb_flags_smp
+# else
+#  define v7wbi_possible_flags	v7wbi_tlb_flags_up
+#  define v7wbi_always_flags	v7wbi_tlb_flags_up
+# endif
 # ifdef _TLB
 #  define MULTI_TLB 1
 # else
@@ -560,12 +570,20 @@ extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
 #endif
 
 /*
- * if PG_dcache_dirty is set for the page, we need to ensure that any
+ * If PG_dcache_clean is not set for the page, we need to ensure that any
  * cache entries for the kernels virtual memory range are written
- * back to the page.
+ * back to the page. On ARMv6 and later, the cache coherency is handled via
+ * the set_pte_at() function.
  */
+#if __LINUX_ARM_ARCH__ < 6
 extern void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
 	pte_t *ptep);
+#else
+static inline void update_mmu_cache(struct vm_area_struct *vma,
+				    unsigned long addr, pte_t *ptep)
+{
+}
+#endif
 
 #endif
 

arch/arm/include/asm/unistd.h

@@ -393,6 +393,9 @@
 #define __NR_perf_event_open		(__NR_SYSCALL_BASE+364)
 #define __NR_recvmmsg			(__NR_SYSCALL_BASE+365)
 #define __NR_accept4			(__NR_SYSCALL_BASE+366)
+#define __NR_fanotify_init		(__NR_SYSCALL_BASE+367)
+#define __NR_fanotify_mark		(__NR_SYSCALL_BASE+368)
+#define __NR_prlimit64			(__NR_SYSCALL_BASE+369)
 
 /*
  * The following SWIs are ARM private.