Merge branch 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm

Pull ARM development updates from Russell King:
 "Included in this update:

   - moving PSCI code from ARM64/ARM to drivers/

   - removal of some architecture internals from global kernel view

   - addition of software based "privileged no access" support using the
     old domains register to turn off the ability for kernel
     loads/stores to access userspace.  Only the proper accessors will
     be usable.

   - addition of early fixup support for early console

   - re-addition (and reimplementation) of OMAP special interconnect
     barrier

   - removal of finish_arch_switch()

   - only expose cpuX/online in sysfs if hotpluggable

   - a number of code cleanups"

* 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm: (41 commits)
  ARM: software-based priviledged-no-access support
  ARM: entry: provide uaccess assembly macro hooks
  ARM: entry: get rid of multiple macro definitions
  ARM: 8421/1: smp: Collapse arch_cpu_idle_dead() into cpu_die()
  ARM: uaccess: provide uaccess_save_and_enable() and uaccess_restore()
  ARM: mm: improve do_ldrd_abort macro
  ARM: entry: ensure that IRQs are enabled when calling syscall_trace_exit()
  ARM: entry: efficiency cleanups
  ARM: entry: get rid of asm_trace_hardirqs_on_cond
  ARM: uaccess: simplify user access assembly
  ARM: domains: remove DOMAIN_TABLE
  ARM: domains: keep vectors in separate domain
  ARM: domains: get rid of manager mode for user domain
  ARM: domains: move initial domain setting value to asm/domains.h
  ARM: domains: provide domain_mask()
  ARM: domains: switch to keeping domain value in register
  ARM: 8419/1: dma-mapping: harmonize definition of DMA_ERROR_CODE
  ARM: 8417/1: refactor bitops functions with BIT_MASK() and BIT_WORD()
  ARM: 8416/1: Feroceon: use of_iomap() to map register base
  ARM: 8415/1: early fixmap support for earlycon
  ...

19 files changed, 222 insertions, 1326 deletions

diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index e69f7a19735d..af9e59bf3831 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -71,8 +71,7 @@ obj-$(CONFIG_CPU_PJ4)		+= pj4-cp0.o
 obj-$(CONFIG_CPU_PJ4B)		+= pj4-cp0.o
 obj-$(CONFIG_IWMMXT)		+= iwmmxt.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_regs.o perf_callchain.o
-obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o \
-				   perf_event_xscale.o perf_event_v6.o \
+obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event_xscale.o perf_event_v6.o \
 				   perf_event_v7.o
 CFLAGS_pj4-cp0.o		:= -marm
 AFLAGS_iwmmxt.o			:= -Wa,-mcpu=iwmmxt
@@ -89,7 +88,7 @@ obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 
 obj-$(CONFIG_ARM_VIRT_EXT)	+= hyp-stub.o
 ifeq ($(CONFIG_ARM_PSCI),y)
-obj-y				+= psci.o psci-call.o
+obj-y				+= psci-call.o
 obj-$(CONFIG_SMP)		+= psci_smp.o
 endif
 
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index 5e5a51a99e68..f89811fb9a55 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -97,9 +97,9 @@ EXPORT_SYMBOL(mmiocpy);
 #ifdef CONFIG_MMU
 EXPORT_SYMBOL(copy_page);
 
-EXPORT_SYMBOL(__copy_from_user);
-EXPORT_SYMBOL(__copy_to_user);
-EXPORT_SYMBOL(__clear_user);
+EXPORT_SYMBOL(arm_copy_from_user);
+EXPORT_SYMBOL(arm_copy_to_user);
+EXPORT_SYMBOL(arm_clear_user);
 
 EXPORT_SYMBOL(__get_user_1);
 EXPORT_SYMBOL(__get_user_2);
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index cb4fb1e69778..3e1c26eb32b4 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -149,10 +149,10 @@ ENDPROC(__und_invalid)
 #define SPFIX(code...)
 #endif
 
-	.macro	svc_entry, stack_hole=0, trace=1
+	.macro	svc_entry, stack_hole=0, trace=1, uaccess=1
  UNWIND(.fnstart		)
  UNWIND(.save {r0 - pc}		)
-	sub	sp, sp, #(S_FRAME_SIZE + \stack_hole - 4)
+	sub	sp, sp, #(S_FRAME_SIZE + 8 + \stack_hole - 4)
 #ifdef CONFIG_THUMB2_KERNEL
  SPFIX(	str	r0, [sp]	)	@ temporarily saved
  SPFIX(	mov	r0, sp		)
@@ -167,7 +167,7 @@ ENDPROC(__und_invalid)
 	ldmia	r0, {r3 - r5}
 	add	r7, sp, #S_SP - 4	@ here for interlock avoidance
 	mov	r6, #-1			@  ""  ""      ""       ""
-	add	r2, sp, #(S_FRAME_SIZE + \stack_hole - 4)
+	add	r2, sp, #(S_FRAME_SIZE + 8 + \stack_hole - 4)
  SPFIX(	addeq	r2, r2, #4	)
 	str	r3, [sp, #-4]!		@ save the "real" r0 copied
 					@ from the exception stack
@@ -185,6 +185,11 @@ ENDPROC(__und_invalid)
 	@
 	stmia	r7, {r2 - r6}
 
+	uaccess_save r0
+	.if \uaccess
+	uaccess_disable r0
+	.endif
+
 	.if \trace
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
@@ -194,7 +199,7 @@ ENDPROC(__und_invalid)
 
 	.align	5
 __dabt_svc:
-	svc_entry
+	svc_entry uaccess=0
 	mov	r2, sp
 	dabt_helper
  THUMB(	ldr	r5, [sp, #S_PSR]	)	@ potentially updated CPSR
@@ -368,7 +373,7 @@ ENDPROC(__fiq_abt)
 #error "sizeof(struct pt_regs) must be a multiple of 8"
 #endif
 
-	.macro	usr_entry, trace=1
+	.macro	usr_entry, trace=1, uaccess=1
  UNWIND(.fnstart	)
  UNWIND(.cantunwind	)	@ don't unwind the user space
 	sub	sp, sp, #S_FRAME_SIZE
@@ -400,6 +405,10 @@ ENDPROC(__fiq_abt)
  ARM(	stmdb	r0, {sp, lr}^			)
  THUMB(	store_user_sp_lr r0, r1, S_SP - S_PC	)
 
+	.if \uaccess
+	uaccess_disable ip
+	.endif
+
 	@ Enable the alignment trap while in kernel mode
  ATRAP(	teq	r8, r7)
  ATRAP( mcrne	p15, 0, r8, c1, c0, 0)
@@ -435,7 +444,7 @@ ENDPROC(__fiq_abt)
 
 	.align	5
 __dabt_usr:
-	usr_entry
+	usr_entry uaccess=0
 	kuser_cmpxchg_check
 	mov	r2, sp
 	dabt_helper
@@ -458,7 +467,7 @@ ENDPROC(__irq_usr)
 
 	.align	5
 __und_usr:
-	usr_entry
+	usr_entry uaccess=0
 
 	mov	r2, r4
 	mov	r3, r5
@@ -484,6 +493,8 @@ __und_usr:
 1:	ldrt	r0, [r4]
  ARM_BE8(rev	r0, r0)				@ little endian instruction
 
+	uaccess_disable ip
+
 	@ r0 = 32-bit ARM instruction which caused the exception
 	@ r2 = PC value for the following instruction (:= regs->ARM_pc)
 	@ r4 = PC value for the faulting instruction
@@ -518,9 +529,10 @@ __und_usr_thumb:
 2:	ldrht	r5, [r4]
 ARM_BE8(rev16	r5, r5)				@ little endian instruction
 	cmp	r5, #0xe800			@ 32bit instruction if xx != 0
-	blo	__und_usr_fault_16		@ 16bit undefined instruction
+	blo	__und_usr_fault_16_pan		@ 16bit undefined instruction
 3:	ldrht	r0, [r2]
 ARM_BE8(rev16	r0, r0)				@ little endian instruction
+	uaccess_disable ip
 	add	r2, r2, #2			@ r2 is PC + 2, make it PC + 4
 	str	r2, [sp, #S_PC]			@ it's a 2x16bit instr, update
 	orr	r0, r0, r5, lsl #16
@@ -715,6 +727,8 @@ ENDPROC(no_fp)
 __und_usr_fault_32:
 	mov	r1, #4
 	b	1f
+__und_usr_fault_16_pan:
+	uaccess_disable ip
 __und_usr_fault_16:
 	mov	r1, #2
 1:	mov	r0, sp
@@ -770,6 +784,8 @@ ENTRY(__switch_to)
 	ldr	r4, [r2, #TI_TP_VALUE]
 	ldr	r5, [r2, #TI_TP_VALUE + 4]
 #ifdef CONFIG_CPU_USE_DOMAINS
+	mrc	p15, 0, r6, c3, c0, 0		@ Get domain register
+	str	r6, [r1, #TI_CPU_DOMAIN]	@ Save old domain register
 	ldr	r6, [r2, #TI_CPU_DOMAIN]
 #endif
 	switch_tls r1, r4, r5, r3, r7
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index b48dd4f37f80..30a7228eaceb 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -24,35 +24,55 @@
 
 
 	.align	5
+#if !(IS_ENABLED(CONFIG_TRACE_IRQFLAGS) || IS_ENABLED(CONFIG_CONTEXT_TRACKING))
 /*
- * This is the fast syscall return path.  We do as little as
- * possible here, and this includes saving r0 back into the SVC
- * stack.
+ * This is the fast syscall return path.  We do as little as possible here,
+ * such as avoiding writing r0 to the stack.  We only use this path if we
+ * have tracing and context tracking disabled - the overheads from those
+ * features make this path too inefficient.
  */
 ret_fast_syscall:
  UNWIND(.fnstart	)
  UNWIND(.cantunwind	)
-	disable_irq				@ disable interrupts
+	disable_irq_notrace			@ disable interrupts
 	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
-	tst	r1, #_TIF_SYSCALL_WORK
-	bne	__sys_trace_return
-	tst	r1, #_TIF_WORK_MASK
+	tst	r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
 	bne	fast_work_pending
-	asm_trace_hardirqs_on
 
 	/* perform architecture specific actions before user return */
 	arch_ret_to_user r1, lr
-	ct_user_enter
 
 	restore_user_regs fast = 1, offset = S_OFF
  UNWIND(.fnend		)
+ENDPROC(ret_fast_syscall)
 
-/*
- * Ok, we need to do extra processing, enter the slow path.
- */
+	/* Ok, we need to do extra processing, enter the slow path. */
 fast_work_pending:
 	str	r0, [sp, #S_R0+S_OFF]!		@ returned r0
-work_pending:
+	/* fall through to work_pending */
+#else
+/*
+ * The "replacement" ret_fast_syscall for when tracing or context tracking
+ * is enabled.  As we will need to call out to some C functions, we save
+ * r0 first to avoid needing to save registers around each C function call.
+ */
+ret_fast_syscall:
+ UNWIND(.fnstart	)
+ UNWIND(.cantunwind	)
+	str	r0, [sp, #S_R0 + S_OFF]!	@ save returned r0
+	disable_irq_notrace			@ disable interrupts
+	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
+	tst	r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
+	beq	no_work_pending
+ UNWIND(.fnend		)
+ENDPROC(ret_fast_syscall)
+
+	/* Slower path - fall through to work_pending */
+#endif
+
+	tst	r1, #_TIF_SYSCALL_WORK
+	bne	__sys_trace_return_nosave
+slow_work_pending:
 	mov	r0, sp				@ 'regs'
 	mov	r2, why				@ 'syscall'
 	bl	do_work_pending
@@ -65,16 +85,19 @@ ENDPROC(ret_fast_syscall)
 
 /*
  * "slow" syscall return path.  "why" tells us if this was a real syscall.
+ * IRQs may be enabled here, so always disable them.  Note that we use the
+ * "notrace" version to avoid calling into the tracing code unnecessarily.
+ * do_work_pending() will update this state if necessary.
  */
 ENTRY(ret_to_user)
 ret_slow_syscall:
-	disable_irq				@ disable interrupts
+	disable_irq_notrace			@ disable interrupts
 ENTRY(ret_to_user_from_irq)
 	ldr	r1, [tsk, #TI_FLAGS]
 	tst	r1, #_TIF_WORK_MASK
-	bne	work_pending
+	bne	slow_work_pending
 no_work_pending:
-	asm_trace_hardirqs_on
+	asm_trace_hardirqs_on save = 0
 
 	/* perform architecture specific actions before user return */
 	arch_ret_to_user r1, lr
@@ -174,6 +197,8 @@ ENTRY(vector_swi)
  USER(	ldr	scno, [lr, #-4]		)	@ get SWI instruction
 #endif
 
+	uaccess_disable tbl
+
 	adr	tbl, sys_call_table		@ load syscall table pointer
 
 #if defined(CONFIG_OABI_COMPAT)
@@ -252,6 +277,12 @@ __sys_trace_return:
 	bl	syscall_trace_exit
 	b	ret_slow_syscall
 
+__sys_trace_return_nosave:
+	enable_irq_notrace
+	mov	r0, sp
+	bl	syscall_trace_exit
+	b	ret_slow_syscall
+
 	.align	5
 #ifdef CONFIG_ALIGNMENT_TRAP
 	.type	__cr_alignment, #object
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 1a0045abead7..0d22ad206d52 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -196,7 +196,7 @@
 	msr	cpsr_c, \rtemp			@ switch back to the SVC mode
 	.endm
 
-#ifndef CONFIG_THUMB2_KERNEL
+
 	.macro	svc_exit, rpsr, irq = 0
 	.if	\irq != 0
 	@ IRQs already off
@@ -215,6 +215,10 @@
 	blne	trace_hardirqs_off
 #endif
 	.endif
+	uaccess_restore
+
+#ifndef CONFIG_THUMB2_KERNEL
+	@ ARM mode SVC restore
 	msr	spsr_cxsf, \rpsr
 #if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K)
 	@ We must avoid clrex due to Cortex-A15 erratum #830321
@@ -222,6 +226,20 @@
 	strex	r1, r2, [r0]			@ clear the exclusive monitor
 #endif
 	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
+#else
+	@ Thumb mode SVC restore
+	ldr	lr, [sp, #S_SP]			@ top of the stack
+	ldrd	r0, r1, [sp, #S_LR]		@ calling lr and pc
+
+	@ We must avoid clrex due to Cortex-A15 erratum #830321
+	strex	r2, r1, [sp, #S_LR]		@ clear the exclusive monitor
+
+	stmdb	lr!, {r0, r1, \rpsr}		@ calling lr and rfe context
+	ldmia	sp, {r0 - r12}
+	mov	sp, lr
+	ldr	lr, [sp], #4
+	rfeia	sp!
+#endif
 	.endm
 
 	@
@@ -241,6 +259,9 @@
 	@ on the stack remains correct).
 	@
 	.macro  svc_exit_via_fiq
+	uaccess_restore
+#ifndef CONFIG_THUMB2_KERNEL
+	@ ARM mode restore
 	mov	r0, sp
 	ldmib	r0, {r1 - r14}	@ abort is deadly from here onward (it will
 				@ clobber state restored below)
@@ -250,9 +271,27 @@
 	msr	spsr_cxsf, r9
 	ldr	r0, [r0, #S_R0]
 	ldmia	r8, {pc}^
+#else
+	@ Thumb mode restore
+	add	r0, sp, #S_R2
+	ldr	lr, [sp, #S_LR]
+	ldr	sp, [sp, #S_SP] @ abort is deadly from here onward (it will
+			        @ clobber state restored below)
+	ldmia	r0, {r2 - r12}
+	mov	r1, #FIQ_MODE | PSR_I_BIT | PSR_F_BIT
+	msr	cpsr_c, r1
+	sub	r0, #S_R2
+	add	r8, r0, #S_PC
+	ldmia	r0, {r0 - r1}
+	rfeia	r8
+#endif
 	.endm
 
+
 	.macro	restore_user_regs, fast = 0, offset = 0
+	uaccess_enable r1, isb=0
+#ifndef CONFIG_THUMB2_KERNEL
+	@ ARM mode restore
 	mov	r2, sp
 	ldr	r1, [r2, #\offset + S_PSR]	@ get calling cpsr
 	ldr	lr, [r2, #\offset + S_PC]!	@ get pc
@@ -270,72 +309,16 @@
 						@ after ldm {}^
 	add	sp, sp, #\offset + S_FRAME_SIZE
 	movs	pc, lr				@ return & move spsr_svc into cpsr
-	.endm
-
-#else	/* CONFIG_THUMB2_KERNEL */
-	.macro	svc_exit, rpsr, irq = 0
-	.if	\irq != 0
-	@ IRQs already off
-#ifdef CONFIG_TRACE_IRQFLAGS
-	@ The parent context IRQs must have been enabled to get here in
-	@ the first place, so there's no point checking the PSR I bit.
-	bl	trace_hardirqs_on
-#endif
-	.else
-	@ IRQs off again before pulling preserved data off the stack
-	disable_irq_notrace
-#ifdef CONFIG_TRACE_IRQFLAGS
-	tst	\rpsr, #PSR_I_BIT
-	bleq	trace_hardirqs_on
-	tst	\rpsr, #PSR_I_BIT
-	blne	trace_hardirqs_off
-#endif
-	.endif
-	ldr	lr, [sp, #S_SP]			@ top of the stack
-	ldrd	r0, r1, [sp, #S_LR]		@ calling lr and pc
-
-	@ We must avoid clrex due to Cortex-A15 erratum #830321
-	strex	r2, r1, [sp, #S_LR]		@ clear the exclusive monitor
-
-	stmdb	lr!, {r0, r1, \rpsr}		@ calling lr and rfe context
-	ldmia	sp, {r0 - r12}
-	mov	sp, lr
-	ldr	lr, [sp], #4
-	rfeia	sp!
-	.endm
-
-	@
-	@ svc_exit_via_fiq - like svc_exit but switches to FIQ mode before exit
-	@
-	@ For full details see non-Thumb implementation above.
-	@
-	.macro  svc_exit_via_fiq
-	add	r0, sp, #S_R2
-	ldr	lr, [sp, #S_LR]
-	ldr	sp, [sp, #S_SP] @ abort is deadly from here onward (it will
-			        @ clobber state restored below)
-	ldmia	r0, {r2 - r12}
-	mov	r1, #FIQ_MODE | PSR_I_BIT | PSR_F_BIT
-	msr	cpsr_c, r1
-	sub	r0, #S_R2
-	add	r8, r0, #S_PC
-	ldmia	r0, {r0 - r1}
-	rfeia	r8
-	.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
+#elif defined(CONFIG_CPU_V7M)
+	@ V7M restore.
+	@ Note that we don't need to do clrex here as clearing the local
+	@ monitor is part of the exception entry and exit sequence.
 	.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
+#else
+	@ Thumb mode restore
 	mov	r2, sp
 	load_user_sp_lr r2, r3, \offset + S_SP	@ calling sp, lr
 	ldr	r1, [sp, #\offset + S_PSR]	@ get calling cpsr
@@ -353,9 +336,8 @@
 	.endif
 	add	sp, sp, #S_FRAME_SIZE - S_SP
 	movs	pc, lr				@ return & move spsr_svc into cpsr
-	.endm
-#endif	/* ifdef CONFIG_CPU_V7M / else */
 #endif	/* !CONFIG_THUMB2_KERNEL */
+	.endm
 
 /*
  * Context tracking subsystem.  Used to instrument transitions
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 29e2991465cb..04286fd9e09c 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -464,10 +464,7 @@ __enable_mmu:
 #ifdef CONFIG_ARM_LPAE
 	mcrr	p15, 0, r4, r5, c2		@ load TTBR0
 #else
-	mov	r5, #(domain_val(DOMAIN_USER, DOMAIN_MANAGER) | \
-		      domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
-		      domain_val(DOMAIN_TABLE, DOMAIN_MANAGER) | \
-		      domain_val(DOMAIN_IO, DOMAIN_CLIENT))
+	mov	r5, #DACR_INIT
 	mcr	p15, 0, r5, c3, c0, 0		@ load domain access register
 	mcr	p15, 0, r4, c2, c0, 0		@ load page table pointer
 #endif
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index baf8edebe26f..5ff4826cb154 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -39,6 +39,7 @@
 #include <linux/export.h>
 
 #include <asm/hardware/cache-l2x0.h>
+#include <asm/outercache.h>
 #include <asm/exception.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/irq.h>
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
deleted file mode 100644
index 54272e0be713..000000000000
--- a/arch/arm/kernel/perf_event.c
+++ /dev/null
@@ -1,896 +0,0 @@
-#undef DEBUG
-
-/*
- * ARM performance counter support.
- *
- * Copyright (C) 2009 picoChip Designs, Ltd., Jamie Iles
- * Copyright (C) 2010 ARM Ltd., Will Deacon <will.deacon@arm.com>
- *
- * This code is based on the sparc64 perf event code, which is in turn based
- * on the x86 code.
- */
-#define pr_fmt(fmt) "hw perfevents: " fmt
-
-#include <linux/bitmap.h>
-#include <linux/cpumask.h>
-#include <linux/export.h>
-#include <linux/kernel.h>
-#include <linux/of.h>
-#include <linux/platform_device.h>
-#include <linux/slab.h>
-#include <linux/spinlock.h>
-#include <linux/irq.h>
-#include <linux/irqdesc.h>
-
-#include <asm/cputype.h>
-#include <asm/irq_regs.h>
-#include <asm/pmu.h>
-
-static int
-armpmu_map_cache_event(const unsigned (*cache_map)
-				      [PERF_COUNT_HW_CACHE_MAX]
-				      [PERF_COUNT_HW_CACHE_OP_MAX]
-				      [PERF_COUNT_HW_CACHE_RESULT_MAX],
-		       u64 config)
-{
-	unsigned int cache_type, cache_op, cache_result, ret;
-
-	cache_type = (config >>  0) & 0xff;
-	if (cache_type >= PERF_COUNT_HW_CACHE_MAX)
-		return -EINVAL;
-
-	cache_op = (config >>  8) & 0xff;
-	if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX)
-		return -EINVAL;
-
-	cache_result = (config >> 16) & 0xff;
-	if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
-		return -EINVAL;
-
-	ret = (int)(*cache_map)[cache_type][cache_op][cache_result];
-
-	if (ret == CACHE_OP_UNSUPPORTED)
-		return -ENOENT;
-
-	return ret;
-}
-
-static int
-armpmu_map_hw_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config)
-{
-	int mapping;
-
-	if (config >= PERF_COUNT_HW_MAX)
-		return -EINVAL;
-
-	mapping = (*event_map)[config];
-	return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping;
-}
-
-static int
-armpmu_map_raw_event(u32 raw_event_mask, u64 config)
-{
-	return (int)(config & raw_event_mask);
-}
-
-int
-armpmu_map_event(struct perf_event *event,
-		 const unsigned (*event_map)[PERF_COUNT_HW_MAX],
-		 const unsigned (*cache_map)
-				[PERF_COUNT_HW_CACHE_MAX]
-				[PERF_COUNT_HW_CACHE_OP_MAX]
-				[PERF_COUNT_HW_CACHE_RESULT_MAX],
-		 u32 raw_event_mask)
-{
-	u64 config = event->attr.config;
-	int type = event->attr.type;
-
-	if (type == event->pmu->type)
-		return armpmu_map_raw_event(raw_event_mask, config);
-
-	switch (type) {
-	case PERF_TYPE_HARDWARE:
-		return armpmu_map_hw_event(event_map, config);
-	case PERF_TYPE_HW_CACHE:
-		return armpmu_map_cache_event(cache_map, config);
-	case PERF_TYPE_RAW:
-		return armpmu_map_raw_event(raw_event_mask, config);
-	}
-
-	return -ENOENT;
-}
-
-int armpmu_event_set_period(struct perf_event *event)
-{
-	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
-	struct hw_perf_event *hwc = &event->hw;
-	s64 left = local64_read(&hwc->period_left);
-	s64 period = hwc->sample_period;
-	int ret = 0;
-
-	if (unlikely(left <= -period)) {
-		left = period;
-		local64_set(&hwc->period_left, left);
-		hwc->last_period = period;
-		ret = 1;
-	}
-
-	if (unlikely(left <= 0)) {
-		left += period;
-		local64_set(&hwc->period_left, left);
-		hwc->last_period = period;
-		ret = 1;
-	}
-
-	/*
-	 * Limit the maximum period to prevent the counter value
-	 * from overtaking the one we are about to program. In
-	 * effect we are reducing max_period to account for
-	 * interrupt latency (and we are being very conservative).
-	 */
-	if (left > (armpmu->max_period >> 1))
-		left = armpmu->max_period >> 1;
-
-	local64_set(&hwc->prev_count, (u64)-left);
-
-	armpmu->write_counter(event, (u64)(-left) & 0xffffffff);
-
-	perf_event_update_userpage(event);
-
-	return ret;
-}
-
-u64 armpmu_event_update(struct perf_event *event)
-{
-	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
-	struct hw_perf_event *hwc = &event->hw;
-	u64 delta, prev_raw_count, new_raw_count;
-
-again:
-	prev_raw_count = local64_read(&hwc->prev_count);
-	new_raw_count = armpmu->read_counter(event);
-
-	if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
-			     new_raw_count) != prev_raw_count)
-		goto again;
-
-	delta = (new_raw_count - prev_raw_count) & armpmu->max_period;
-
-	local64_add(delta, &event->count);
-	local64_sub(delta, &hwc->period_left);
-
-	return new_raw_count;
-}
-
-static void
-armpmu_read(struct perf_event *event)
-{
-	armpmu_event_update(event);
-}
-
-static void
-armpmu_stop(struct perf_event *event, int flags)
-{
-	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
-	struct hw_perf_event *hwc = &event->hw;
-
-	/*
-	 * ARM pmu always has to update the counter, so ignore
-	 * PERF_EF_UPDATE, see comments in armpmu_start().
-	 */
-	if (!(hwc->state & PERF_HES_STOPPED)) {
-		armpmu->disable(event);
-		armpmu_event_update(event);
-		hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
-	}
-}
-
-static void armpmu_start(struct perf_event *event, int flags)
-{
-	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
-	struct hw_perf_event *hwc = &event->hw;
-
-	/*
-	 * ARM pmu always has to reprogram the period, so ignore
-	 * PERF_EF_RELOAD, see the comment below.
-	 */
-	if (flags & PERF_EF_RELOAD)
-		WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
-
-	hwc->state = 0;
-	/*
-	 * Set the period again. Some counters can't be stopped, so when we
-	 * were stopped we simply disabled the IRQ source and the counter
-	 * may have been left counting. If we don't do this step then we may
-	 * get an interrupt too soon or *way* too late if the overflow has
-	 * happened since disabling.
-	 */
-	armpmu_event_set_period(event);
-	armpmu->enable(event);
-}
-
-static void
-armpmu_del(struct perf_event *event, int flags)
-{
-	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
-	struct pmu_hw_events *hw_events = this_cpu_ptr(armpmu->hw_events);
-	struct hw_perf_event *hwc = &event->hw;
-	int idx = hwc->idx;
-
-	armpmu_stop(event, PERF_EF_UPDATE);
-	hw_events->events[idx] = NULL;
-	clear_bit(idx, hw_events->used_mask);
-	if (armpmu->clear_event_idx)
-		armpmu->clear_event_idx(hw_events, event);
-
-	perf_event_update_userpage(event);
-}
-
-static int
-armpmu_add(struct perf_event *event, int flags)
-{
-	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
-	struct pmu_hw_events *hw_events = this_cpu_ptr(armpmu->hw_events);
-	struct hw_perf_event *hwc = &event->hw;
-	int idx;
-	int err = 0;
-
-	/* An event following a process won't be stopped earlier */
-	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus))
-		return -ENOENT;
-
-	perf_pmu_disable(event->pmu);
-
-	/* If we don't have a space for the counter then finish early. */
-	idx = armpmu->get_event_idx(hw_events, event);
-	if (idx < 0) {
-		err = idx;
-		goto out;
-	}
-
-	/*
-	 * If there is an event in the counter we are going to use then make
-	 * sure it is disabled.
-	 */
-	event->hw.idx = idx;
-	armpmu->disable(event);
-	hw_events->events[idx] = event;
-
-	hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
-	if (flags & PERF_EF_START)
-		armpmu_start(event, PERF_EF_RELOAD);
-
-	/* Propagate our changes to the userspace mapping. */
-	perf_event_update_userpage(event);
-
-out:
-	perf_pmu_enable(event->pmu);
-	return err;
-}
-
-static int
-validate_event(struct pmu *pmu, struct pmu_hw_events *hw_events,
-			       struct perf_event *event)
-{
-	struct arm_pmu *armpmu;
-
-	if (is_software_event(event))
-		return 1;
-
-	/*
-	 * Reject groups spanning multiple HW PMUs (e.g. CPU + CCI). The
-	 * core perf code won't check that the pmu->ctx == leader->ctx
-	 * until after pmu->event_init(event).
-	 */
-	if (event->pmu != pmu)
-		return 0;
-
-	if (event->state < PERF_EVENT_STATE_OFF)
-		return 1;
-
-	if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec)
-		return 1;
-
-	armpmu = to_arm_pmu(event->pmu);
-	return armpmu->get_event_idx(hw_events, event) >= 0;
-}
-
-static int
-validate_group(struct perf_event *event)
-{
-	struct perf_event *sibling, *leader = event->group_leader;
-	struct pmu_hw_events fake_pmu;
-
-	/*
-	 * Initialise the fake PMU. We only need to populate the
-	 * used_mask for the purposes of validation.
-	 */
-	memset(&fake_pmu.used_mask, 0, sizeof(fake_pmu.used_mask));
-
-	if (!validate_event(event->pmu, &fake_pmu, leader))
-		return -EINVAL;
-
-	list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
-		if (!validate_event(event->pmu, &fake_pmu, sibling))
-			return -EINVAL;
-	}
-
-	if (!validate_event(event->pmu, &fake_pmu, event))
-		return -EINVAL;
-
-	return 0;
-}
-
-static irqreturn_t armpmu_dispatch_irq(int irq, void *dev)
-{
-	struct arm_pmu *armpmu;
-	struct platform_device *plat_device;
-	struct arm_pmu_platdata *plat;
-	int ret;
-	u64 start_clock, finish_clock;
-
-	/*
-	 * we request the IRQ with a (possibly percpu) struct arm_pmu**, but
-	 * the handlers expect a struct arm_pmu*. The percpu_irq framework will
-	 * do any necessary shifting, we just need to perform the first
-	 * dereference.
-	 */
-	armpmu = *(void **)dev;
-	plat_device = armpmu->plat_device;
-	plat = dev_get_platdata(&plat_device->dev);
-
-	start_clock = sched_clock();
-	if (plat && plat->handle_irq)
-		ret = plat->handle_irq(irq, armpmu, armpmu->handle_irq);
-	else
-		ret = armpmu->handle_irq(irq, armpmu);
-	finish_clock = sched_clock();
-
-	perf_sample_event_took(finish_clock - start_clock);
-	return ret;
-}
-
-static void
-armpmu_release_hardware(struct arm_pmu *armpmu)
-{
-	armpmu->free_irq(armpmu);
-}
-
-static int
-armpmu_reserve_hardware(struct arm_pmu *armpmu)
-{
-	int err = armpmu->request_irq(armpmu, armpmu_dispatch_irq);
-	if (err) {
-		armpmu_release_hardware(armpmu);
-		return err;
-	}
-
-	return 0;
-}
-
-static void
-hw_perf_event_destroy(struct perf_event *event)
-{
-	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
-	atomic_t *active_events	 = &armpmu->active_events;
-	struct mutex *pmu_reserve_mutex = &armpmu->reserve_mutex;
-
-	if (atomic_dec_and_mutex_lock(active_events, pmu_reserve_mutex)) {
-		armpmu_release_hardware(armpmu);
-		mutex_unlock(pmu_reserve_mutex);
-	}
-}
-
-static int
-event_requires_mode_exclusion(struct perf_event_attr *attr)
-{
-	return attr->exclude_idle || attr->exclude_user ||
-	       attr->exclude_kernel || attr->exclude_hv;
-}
-
-static int
-__hw_perf_event_init(struct perf_event *event)
-{
-	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
-	struct hw_perf_event *hwc = &event->hw;
-	int mapping;
-
-	mapping = armpmu->map_event(event);
-
-	if (mapping < 0) {
-		pr_debug("event %x:%llx not supported\n", event->attr.type,
-			 event->attr.config);
-		return mapping;
-	}
-
-	/*
-	 * We don't assign an index until we actually place the event onto
-	 * hardware. Use -1 to signify that we haven't decided where to put it
-	 * yet. For SMP systems, each core has it's own PMU so we can't do any
-	 * clever allocation or constraints checking at this point.
-	 */
-	hwc->idx		= -1;
-	hwc->config_base	= 0;
-	hwc->config		= 0;
-	hwc->event_base		= 0;
-
-	/*
-	 * Check whether we need to exclude the counter from certain modes.
-	 */
-	if ((!armpmu->set_event_filter ||
-	     armpmu->set_event_filter(hwc, &event->attr)) &&
-	     event_requires_mode_exclusion(&event->attr)) {
-		pr_debug("ARM performance counters do not support "
-			 "mode exclusion\n");
-		return -EOPNOTSUPP;
-	}
-
-	/*
-	 * Store the event encoding into the config_base field.
-	 */
-	hwc->config_base	    |= (unsigned long)mapping;
-
-	if (!is_sampling_event(event)) {
-		/*
-		 * For non-sampling runs, limit the sample_period to half
-		 * of the counter width. That way, the new counter value
-		 * is far less likely to overtake the previous one unless
-		 * you have some serious IRQ latency issues.
-		 */
-		hwc->sample_period  = armpmu->max_period >> 1;
-		hwc->last_period    = hwc->sample_period;
-		local64_set(&hwc->period_left, hwc->sample_period);
-	}
-
-	if (event->group_leader != event) {
-		if (validate_group(event) != 0)
-			return -