Merge branches 'fixes' and 'ioremap' into for-linus

22 files changed, 942 insertions, 609 deletions

diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 752725dcbf42..e69f7a19735d 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -34,6 +34,7 @@ obj-$(CONFIG_CPU_IDLE)		+= cpuidle.o
 obj-$(CONFIG_ISA_DMA_API)	+= dma.o
 obj-$(CONFIG_FIQ)		+= fiq.o fiqasm.o
 obj-$(CONFIG_MODULES)		+= armksyms.o module.o
+obj-$(CONFIG_ARM_MODULE_PLTS)	+= module-plts.o
 obj-$(CONFIG_ISA_DMA)		+= dma-isa.o
 obj-$(CONFIG_PCI)		+= bios32.o isa.o
 obj-$(CONFIG_ARM_CPU_SUSPEND)	+= sleep.o suspend.o
@@ -70,7 +71,9 @@ 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-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o perf_event_cpu.o
+obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o \
+				   perf_event_xscale.o perf_event_v6.o \
+				   perf_event_v7.o
 CFLAGS_pj4-cp0.o		:= -marm
 AFLAGS_iwmmxt.o			:= -Wa,-mcpu=iwmmxt
 obj-$(CONFIG_ARM_CPU_TOPOLOGY)  += topology.o
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index a88671cfe1ff..5e5a51a99e68 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -50,6 +50,9 @@ extern void __aeabi_ulcmp(void);
 
 extern void fpundefinstr(void);
 
+void mmioset(void *, unsigned int, size_t);
+void mmiocpy(void *, const void *, size_t);
+
 	/* platform dependent support */
 EXPORT_SYMBOL(arm_delay_ops);
 
@@ -88,6 +91,9 @@ EXPORT_SYMBOL(memmove);
 EXPORT_SYMBOL(memchr);
 EXPORT_SYMBOL(__memzero);
 
+EXPORT_SYMBOL(mmioset);
+EXPORT_SYMBOL(mmiocpy);
+
 #ifdef CONFIG_MMU
 EXPORT_SYMBOL(copy_page);
 
diff --git a/arch/arm/kernel/debug.S b/arch/arm/kernel/debug.S
index 78c91b5f97d4..ea9646cc2a0e 100644
--- a/arch/arm/kernel/debug.S
+++ b/arch/arm/kernel/debug.S
@@ -35,7 +35,7 @@
 
 #else /* !CONFIG_MMU */
 		.macro	addruart_current, rx, tmp1, tmp2
-		addruart	\rx, \tmp1
+		addruart	\rx, \tmp1, \tmp2
 		.endm
 
 #endif /* CONFIG_MMU */
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index dba6cf65c9e4..7335fc60d6cd 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -40,7 +40,7 @@
 #ifdef CONFIG_MULTI_IRQ_HANDLER
 	ldr	r1, =handle_arch_irq
 	mov	r0, sp
-	adr	lr, BSYM(9997f)
+	badr	lr, 9997f
 	ldr	pc, [r1]
 #else
 	arch_irq_handler_default
@@ -273,7 +273,7 @@ __und_svc:
 	str	r4, [sp, #S_PC]
 	orr	r0, r9, r0, lsl #16
 #endif
-	adr	r9, BSYM(__und_svc_finish)
+	badr	r9, __und_svc_finish
 	mov	r2, r4
 	bl	call_fpe
 
@@ -469,7 +469,7 @@ __und_usr:
 	@ instruction, or the more conventional lr if we are to treat
 	@ this as a real undefined instruction
 	@
-	adr	r9, BSYM(ret_from_exception)
+	badr	r9, ret_from_exception
 
 	@ IRQs must be enabled before attempting to read the instruction from
 	@ user space since that could cause a page/translation fault if the
@@ -486,7 +486,7 @@ __und_usr:
 	@ r2 = PC value for the following instruction (:= regs->ARM_pc)
 	@ r4 = PC value for the faulting instruction
 	@ lr = 32-bit undefined instruction function
-	adr	lr, BSYM(__und_usr_fault_32)
+	badr	lr, __und_usr_fault_32
 	b	call_fpe
 
 __und_usr_thumb:
@@ -522,7 +522,7 @@ ARM_BE8(rev16	r0, r0)				@ little endian instruction
 	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
-	adr	lr, BSYM(__und_usr_fault_32)
+	badr	lr, __und_usr_fault_32
 	@ r0 = the two 16-bit Thumb instructions which caused the exception
 	@ r2 = PC value for the following Thumb instruction (:= regs->ARM_pc)
 	@ r4 = PC value for the first 16-bit Thumb instruction
@@ -716,7 +716,7 @@ __und_usr_fault_32:
 __und_usr_fault_16:
 	mov	r1, #2
 1:	mov	r0, sp
-	adr	lr, BSYM(ret_from_exception)
+	badr	lr, ret_from_exception
 	b	__und_fault
 ENDPROC(__und_usr_fault_32)
 ENDPROC(__und_usr_fault_16)
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 4e7f40c577e6..92828a1dec80 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -90,7 +90,7 @@ ENTRY(ret_from_fork)
 	bl	schedule_tail
 	cmp	r5, #0
 	movne	r0, r4
-	adrne	lr, BSYM(1f)
+	badrne	lr, 1f
 	retne	r5
 1:	get_thread_info tsk
 	b	ret_slow_syscall
@@ -198,7 +198,7 @@ local_restart:
 	bne	__sys_trace
 
 	cmp	scno, #NR_syscalls		@ check upper syscall limit
-	adr	lr, BSYM(ret_fast_syscall)	@ return address
+	badr	lr, ret_fast_syscall		@ return address
 	ldrcc	pc, [tbl, scno, lsl #2]		@ call sys_* routine
 
 	add	r1, sp, #S_OFF
@@ -233,7 +233,7 @@ __sys_trace:
 	add	r0, sp, #S_OFF
 	bl	syscall_trace_enter
 
-	adr	lr, BSYM(__sys_trace_return)	@ return address
+	badr	lr, __sys_trace_return		@ return address
 	mov	scno, r0			@ syscall number (possibly new)
 	add	r1, sp, #S_R0 + S_OFF		@ pointer to regs
 	cmp	scno, #NR_syscalls		@ check upper syscall limit
diff --git a/arch/arm/kernel/entry-ftrace.S b/arch/arm/kernel/entry-ftrace.S
index fe57c73e70a4..c73c4030ca5d 100644
--- a/arch/arm/kernel/entry-ftrace.S
+++ b/arch/arm/kernel/entry-ftrace.S
@@ -87,7 +87,7 @@
 
 1: 	mcount_get_lr	r1			@ lr of instrumented func
 	mcount_adjust_addr	r0, lr		@ instrumented function
-	adr	lr, BSYM(2f)
+	badr	lr, 2f
 	mov	pc, r2
 2:	mcount_exit
 .endm
diff --git a/arch/arm/kernel/entry-v7m.S b/arch/arm/kernel/entry-v7m.S
index 8944f4991c3c..b6c8bb9315e7 100644
--- a/arch/arm/kernel/entry-v7m.S
+++ b/arch/arm/kernel/entry-v7m.S
@@ -117,9 +117,14 @@ ENTRY(__switch_to)
 ENDPROC(__switch_to)
 
 	.data
-	.align	8
+#if CONFIG_CPU_V7M_NUM_IRQ <= 112
+	.align	9
+#else
+	.align	10
+#endif
+
 /*
- * Vector table (64 words => 256 bytes natural alignment)
+ * Vector table (Natural alignment need to be ensured)
  */
 ENTRY(vector_table)
 	.long	0			@ 0 - Reset stack pointer
@@ -138,6 +143,6 @@ ENTRY(vector_table)
 	.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
+	.rept	CONFIG_CPU_V7M_NUM_IRQ
+	.long	__irq_entry		@ External Interrupts
 	.endr
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index aebfbf79a1a3..9b8c5a113434 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -46,7 +46,7 @@ ENTRY(stext)
 	.arm
 ENTRY(stext)
 
- THUMB(	adr	r9, BSYM(1f)	)	@ Kernel is always entered in ARM.
+ THUMB(	badr	r9, 1f		)	@ Kernel is always entered in ARM.
  THUMB(	bx	r9		)	@ If this is a Thumb-2 kernel,
  THUMB(	.thumb			)	@ switch to Thumb now.
  THUMB(1:			)
@@ -77,13 +77,13 @@ ENTRY(stext)
 	orr	r6, r6, #(1 << MPU_RSR_EN)	@ Set region enabled bit
 	bl	__setup_mpu
 #endif
-	ldr	r13, =__mmap_switched		@ address to jump to after
-						@ initialising sctlr
-	adr	lr, BSYM(1f)			@ return (PIC) address
+
+	badr	lr, 1f				@ return (PIC) address
 	ldr	r12, [r10, #PROCINFO_INITFUNC]
 	add	r12, r12, r10
 	ret	r12
- 1:	b	__after_proc_init
+1:	bl	__after_proc_init
+	b	__mmap_switched
 ENDPROC(stext)
 
 #ifdef CONFIG_SMP
@@ -106,8 +106,7 @@ ENTRY(secondary_startup)
 	movs	r10, r5				@ invalid processor?
 	beq	__error_p			@ yes, error 'p'
 
-	adr	r4, __secondary_data
-	ldmia	r4, {r7, r12}
+	ldr	r7, __secondary_data
 
 #ifdef CONFIG_ARM_MPU
 	/* Use MPU region info supplied by __cpu_up */
@@ -115,23 +114,19 @@ ENTRY(secondary_startup)
 	bl      __setup_mpu			@ Initialize the MPU
 #endif
 
-	adr	lr, BSYM(__after_proc_init)	@ return address
-	mov	r13, r12			@ __secondary_switched address
+	badr	lr, 1f				@ return (PIC) address
 	ldr	r12, [r10, #PROCINFO_INITFUNC]
 	add	r12, r12, r10
 	ret	r12
-ENDPROC(secondary_startup)
-
-ENTRY(__secondary_switched)
-	ldr	sp, [r7, #8]			@ set up the stack pointer
+1:	bl	__after_proc_init
+	ldr	sp, [r7, #12]			@ set up the stack pointer
 	mov	fp, #0
 	b	secondary_start_kernel
-ENDPROC(__secondary_switched)
+ENDPROC(secondary_startup)
 
 	.type	__secondary_data, %object
 __secondary_data:
 	.long	secondary_data
-	.long	__secondary_switched
 #endif /* CONFIG_SMP */
 
 /*
@@ -164,7 +159,7 @@ __after_proc_init:
 #endif
 	mcr	p15, 0, r0, c1, c0, 0		@ write control reg
 #endif /* CONFIG_CPU_CP15 */
-	ret	r13
+	ret	lr
 ENDPROC(__after_proc_init)
 	.ltorg
 
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 3637973a9708..bd755d97e459 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -80,7 +80,7 @@
 ENTRY(stext)
  ARM_BE8(setend	be )			@ ensure we are in BE8 mode
 
- THUMB(	adr	r9, BSYM(1f)	)	@ Kernel is always entered in ARM.
+ THUMB(	badr	r9, 1f		)	@ Kernel is always entered in ARM.
  THUMB(	bx	r9		)	@ If this is a Thumb-2 kernel,
  THUMB(	.thumb			)	@ switch to Thumb now.
  THUMB(1:			)
@@ -131,13 +131,30 @@ ENTRY(stext)
 	 * The following calls CPU specific code in a position independent
 	 * manner.  See arch/arm/mm/proc-*.S for details.  r10 = base of
 	 * xxx_proc_info structure selected by __lookup_processor_type
-	 * above.  On return, the CPU will be ready for the MMU to be
-	 * turned on, and r0 will hold the CPU control register value.
+	 * above.
+	 *
+	 * The processor init function will be called with:
+	 *  r1 - machine type
+	 *  r2 - boot data (atags/dt) pointer
+	 *  r4 - translation table base (low word)
+	 *  r5 - translation table base (high word, if LPAE)
+	 *  r8 - translation table base 1 (pfn if LPAE)
+	 *  r9 - cpuid
+	 *  r13 - virtual address for __enable_mmu -> __turn_mmu_on
+	 *
+	 * On return, the CPU will be ready for the MMU to be turned on,
+	 * r0 will hold the CPU control register value, r1, r2, r4, and
+	 * r9 will be preserved.  r5 will also be preserved if LPAE.
 	 */
 	ldr	r13, =__mmap_switched		@ address to jump to after
 						@ mmu has been enabled
-	adr	lr, BSYM(1f)			@ return (PIC) address
+	badr	lr, 1f				@ return (PIC) address
+#ifdef CONFIG_ARM_LPAE
+	mov	r5, #0				@ high TTBR0
+	mov	r8, r4, lsr #12			@ TTBR1 is swapper_pg_dir pfn
+#else
 	mov	r8, r4				@ set TTBR1 to swapper_pg_dir
+#endif
 	ldr	r12, [r10, #PROCINFO_INITFUNC]
 	add	r12, r12, r10
 	ret	r12
@@ -158,7 +175,7 @@ ENDPROC(stext)
  *
  * Returns:
  *  r0, r3, r5-r7 corrupted
- *  r4 = page table (see ARCH_PGD_SHIFT in asm/memory.h)
+ *  r4 = physical page table address
  */
 __create_page_tables:
 	pgtbl	r4, r8				@ page table address
@@ -333,7 +350,6 @@ __create_page_tables:
 #endif
 #ifdef CONFIG_ARM_LPAE
 	sub	r4, r4, #0x1000		@ point to the PGD table
-	mov	r4, r4, lsr #ARCH_PGD_SHIFT
 #endif
 	ret	lr
 ENDPROC(__create_page_tables)
@@ -346,9 +362,9 @@ __turn_mmu_on_loc:
 
 #if defined(CONFIG_SMP)
 	.text
-ENTRY(secondary_startup_arm)
 	.arm
- THUMB(	adr	r9, BSYM(1f)	)	@ Kernel is entered in ARM.
+ENTRY(secondary_startup_arm)
+ THUMB(	badr	r9, 1f		)	@ Kernel is entered in ARM.
  THUMB(	bx	r9		)	@ If this is a Thumb-2 kernel,
  THUMB(	.thumb			)	@ switch to Thumb now.
  THUMB(1:			)
@@ -381,10 +397,10 @@ ENTRY(secondary_startup)
 	adr	r4, __secondary_data
 	ldmia	r4, {r5, r7, r12}		@ address to jump to after
 	sub	lr, r4, r5			@ mmu has been enabled
-	ldr	r4, [r7, lr]			@ get secondary_data.pgdir
-	add	r7, r7, #4
-	ldr	r8, [r7, lr]			@ get secondary_data.swapper_pg_dir
-	adr	lr, BSYM(__enable_mmu)		@ return address
+	add	r3, r7, lr
+	ldrd	r4, [r3, #0]			@ get secondary_data.pgdir
+	ldr	r8, [r3, #8]			@ get secondary_data.swapper_pg_dir
+	badr	lr, __enable_mmu		@ return address
 	mov	r13, r12			@ __secondary_switched address
 	ldr	r12, [r10, #PROCINFO_INITFUNC]
 	add	r12, r12, r10			@ initialise processor
@@ -397,7 +413,7 @@ ENDPROC(secondary_startup_arm)
 	 * r6  = &secondary_data
 	 */
 ENTRY(__secondary_switched)
-	ldr	sp, [r7, #4]			@ get secondary_data.stack
+	ldr	sp, [r7, #12]			@ get secondary_data.stack
 	mov	fp, #0
 	b	secondary_start_kernel
 ENDPROC(__secondary_switched)
@@ -416,12 +432,14 @@ __secondary_data:
 /*
  * Setup common bits before finally enabling the MMU.  Essentially
  * this is just loading the page table pointer and domain access
- * registers.
+ * registers.  All these registers need to be preserved by the
+ * processor setup function (or set in the case of r0)
  *
  *  r0  = cp#15 control register
  *  r1  = machine ID
  *  r2  = atags or dtb pointer
- *  r4  = page table (see ARCH_PGD_SHIFT in asm/memory.h)
+ *  r4  = TTBR pointer (low word)
+ *  r5  = TTBR pointer (high word if LPAE)
  *  r9  = processor ID
  *  r13 = *virtual* address to jump to upon completion
  */
@@ -440,7 +458,9 @@ __enable_mmu:
 #ifdef CONFIG_CPU_ICACHE_DISABLE
 	bic	r0, r0, #CR_I
 #endif
-#ifndef CONFIG_ARM_LPAE
+#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) | \
diff --git a/arch/arm/kernel/module-plts.c b/arch/arm/kernel/module-plts.c
new file mode 100644
index 000000000000..097e2e201b9f
--- /dev/null
+++ b/arch/arm/kernel/module-plts.c
@@ -0,0 +1,183 @@
+/*
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * 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/elf.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <asm/cache.h>
+#include <asm/opcodes.h>
+
+#define PLT_ENT_STRIDE		L1_CACHE_BYTES
+#define PLT_ENT_COUNT		(PLT_ENT_STRIDE / sizeof(u32))
+#define PLT_ENT_SIZE		(sizeof(struct plt_entries) / PLT_ENT_COUNT)
+
+#ifdef CONFIG_THUMB2_KERNEL
+#define PLT_ENT_LDR		__opcode_to_mem_thumb32(0xf8dff000 | \
+							(PLT_ENT_STRIDE - 4))
+#else
+#define PLT_ENT_LDR		__opcode_to_mem_arm(0xe59ff000 | \
+						    (PLT_ENT_STRIDE - 8))
+#endif
+
+struct plt_entries {
+	u32	ldr[PLT_ENT_COUNT];
+	u32	lit[PLT_ENT_COUNT];
+};
+
+static bool in_init(const struct module *mod, u32 addr)
+{
+	return addr - (u32)mod->module_init < mod->init_size;
+}
+
+u32 get_module_plt(struct module *mod, unsigned long loc, Elf32_Addr val)
+{
+	struct plt_entries *plt, *plt_end;
+	int c, *count;
+
+	if (in_init(mod, loc)) {
+		plt = (void *)mod->arch.init_plt->sh_addr;
+		plt_end = (void *)plt + mod->arch.init_plt->sh_size;
+		count = &mod->arch.init_plt_count;
+	} else {
+		plt = (void *)mod->arch.core_plt->sh_addr;
+		plt_end = (void *)plt + mod->arch.core_plt->sh_size;
+		count = &mod->arch.core_plt_count;
+	}
+
+	/* Look for an existing entry pointing to 'val' */
+	for (c = *count; plt < plt_end; c -= PLT_ENT_COUNT, plt++) {
+		int i;
+
+		if (!c) {
+			/* Populate a new set of entries */
+			*plt = (struct plt_entries){
+				{ [0 ... PLT_ENT_COUNT - 1] = PLT_ENT_LDR, },
+				{ val, }
+			};
+			++*count;
+			return (u32)plt->ldr;
+		}
+		for (i = 0; i < PLT_ENT_COUNT; i++) {
+			if (!plt->lit[i]) {
+				plt->lit[i] = val;
+				++*count;
+			}
+			if (plt->lit[i] == val)
+				return (u32)&plt->ldr[i];
+		}
+	}
+	BUG();
+}
+
+static int duplicate_rel(Elf32_Addr base, const Elf32_Rel *rel, int num,
+			   u32 mask)
+{
+	u32 *loc1, *loc2;
+	int i;
+
+	for (i = 0; i < num; i++) {
+		if (rel[i].r_info != rel[num].r_info)
+			continue;
+
+		/*
+		 * Identical relocation types against identical symbols can
+		 * still result in different PLT entries if the addend in the
+		 * place is different. So resolve the target of the relocation
+		 * to compare the values.
+		 */
+		loc1 = (u32 *)(base + rel[i].r_offset);
+		loc2 = (u32 *)(base + rel[num].r_offset);
+		if (((*loc1 ^ *loc2) & mask) == 0)
+			return 1;
+	}
+	return 0;
+}
+
+/* Count how many PLT entries we may need */
+static unsigned int count_plts(Elf32_Addr base, const Elf32_Rel *rel, int num)
+{
+	unsigned int ret = 0;
+	int i;
+
+	/*
+	 * Sure, this is order(n^2), but it's usually short, and not
+	 * time critical
+	 */
+	for (i = 0; i < num; i++)
+		switch (ELF32_R_TYPE(rel[i].r_info)) {
+		case R_ARM_CALL:
+		case R_ARM_PC24:
+		case R_ARM_JUMP24:
+			if (!duplicate_rel(base, rel, i,
+					   __opcode_to_mem_arm(0x00ffffff)))
+				ret++;
+			break;
+#ifdef CONFIG_THUMB2_KERNEL
+		case R_ARM_THM_CALL:
+		case R_ARM_THM_JUMP24:
+			if (!duplicate_rel(base, rel, i,
+					   __opcode_to_mem_thumb32(0x07ff2fff)))
+				ret++;
+#endif
+		}
+	return ret;
+}
+
+int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
+			      char *secstrings, struct module *mod)
+{
+	unsigned long core_plts = 0, init_plts = 0;
+	Elf32_Shdr *s, *sechdrs_end = sechdrs + ehdr->e_shnum;
+
+	/*
+	 * To store the PLTs, we expand the .text section for core module code
+	 * and the .init.text section for initialization code.
+	 */
+	for (s = sechdrs; s < sechdrs_end; ++s)
+		if (strcmp(".core.plt", secstrings + s->sh_name) == 0)
+			mod->arch.core_plt = s;
+		else if (strcmp(".init.plt", secstrings + s->sh_name) == 0)
+			mod->arch.init_plt = s;
+
+	if (!mod->arch.core_plt || !mod->arch.init_plt) {
+		pr_err("%s: sections missing\n", mod->name);
+		return -ENOEXEC;
+	}
+
+	for (s = sechdrs + 1; s < sechdrs_end; ++s) {
+		const Elf32_Rel *rels = (void *)ehdr + s->sh_offset;
+		int numrels = s->sh_size / sizeof(Elf32_Rel);
+		Elf32_Shdr *dstsec = sechdrs + s->sh_info;
+
+		if (s->sh_type != SHT_REL)
+			continue;
+
+		if (strstr(secstrings + s->sh_name, ".init"))
+			init_plts += count_plts(dstsec->sh_addr, rels, numrels);
+		else
+			core_plts += count_plts(dstsec->sh_addr, rels, numrels);
+	}
+
+	mod->arch.core_plt->sh_type = SHT_NOBITS;
+	mod->arch.core_plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+	mod->arch.core_plt->sh_addralign = L1_CACHE_BYTES;
+	mod->arch.core_plt->sh_size = round_up(core_plts * PLT_ENT_SIZE,
+					       sizeof(struct plt_entries));
+	mod->arch.core_plt_count = 0;
+
+	mod->arch.init_plt->sh_type = SHT_NOBITS;
+	mod->arch.init_plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+	mod->arch.init_plt->sh_addralign = L1_CACHE_BYTES;
+	mod->arch.init_plt->sh_size = round_up(init_plts * PLT_ENT_SIZE,
+					       sizeof(struct plt_entries));
+	mod->arch.init_plt_count = 0;
+	pr_debug("%s: core.plt=%x, init.plt=%x\n", __func__,
+		 mod->arch.core_plt->sh_size, mod->arch.init_plt->sh_size);
+	return 0;
+}
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index af791f4a6205..efdddcb97dd1 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -40,7 +40,12 @@
 #ifdef CONFIG_MMU
 void *module_alloc(unsigned long size)
 {
-	return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END,
+	void *p = __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END,
+				GFP_KERNEL, PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
+				__builtin_return_address(0));
+	if (!IS_ENABLED(CONFIG_ARM_MODULE_PLTS) || p)
+		return p;
+	return __vmalloc_node_range(size, 1,  VMALLOC_START, VMALLOC_END,
 				GFP_KERNEL, PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
 				__builtin_return_address(0));
 }
@@ -110,6 +115,20 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 				offset -= 0x04000000;
 
 			offset += sym->st_value - loc;
+
+			/*
+			 * Route through a PLT entry if 'offset' exceeds the
+			 * supported range. Note that 'offset + loc + 8'
+			 * contains the absolute jump target, i.e.,
+			 * @sym + addend, corrected for the +8 PC bias.
+			 */
+			if (IS_ENABLED(CONFIG_ARM_MODULE_PLTS) &&
+			    (offset <= (s32)0xfe000000 ||
+			     offset >= (s32)0x02000000))
+				offset = get_module_plt(module, loc,
+							offset + loc + 8)
+					 - loc - 8;
+
 			if (offset <= (s32)0xfe000000 ||
 			    offset >= (s32)0x02000000) {
 				pr_err("%s: section %u reloc %u sym '%s': relocation %u out of range (%#lx -> %#x)\n",
@@ -203,6 +222,17 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 				offset -= 0x02000000;
 			offset += sym->st_value - loc;
 
+			/*
+			 * Route through a PLT entry if 'offset' exceeds the
+			 * supported range.
+			 */
+			if (IS_ENABLED(CONFIG_ARM_MODULE_PLTS) &&
+			    (offset <= (s32)0xff000000 ||
+			     offset >= (s32)0x01000000))
+				offset = get_module_plt(module, loc,
+							offset + loc + 4)
+					 - loc - 4;
+
 			if (offset <= (s32)0xff000000 ||
 			    offset >= (s32)0x01000000) {
 				pr_err("%s: section %u reloc %u sym '%s': relocation %u out of range (%#lx -> %#x)\n",
diff --git a/arch/arm/kernel/module.lds b/arch/arm/kernel/module.lds
new file mode 100644
index 000000000000..3682fa107918
--- /dev/null
+++ b/arch/arm/kernel/module.lds
@@ -0,0 +1,4 @@
+SECTIONS {
+        .core.plt : { BYTE(0) }
+        .init.plt : { BYTE(0) }
+}
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 4a86a0133ac3..357f57ea83f4 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -11,12 +11,18 @@
  */
 #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/pm_runtime.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>
 
@@ -229,6 +235,10 @@ armpmu_add(struct perf_event *event, int flags)
 	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. */
@@ -344,20 +354,12 @@ static void
 armpmu_release_hardware(struct arm_pmu *armpmu)
 {
 	armpmu->free_irq(armpmu);
-	pm_runtime_put_sync(&armpmu->plat_device->dev);
 }
 
 static int
 armpmu_reserve_hardware(struct arm_pmu *armpmu)
 {
-	int err;
-	struct platform_device *pmu_device = armpmu->plat_device;
-
-	if (!pmu_device)
-		return -ENODEV;
-
-	pm_runtime_get_sync(&pmu_device->dev);
-	err = armpmu->request_irq(armpmu, armpmu_dispatch_irq);
+	int err = armpmu->request_irq(armpmu, armpmu_dispatch_irq);
 	if (err) {
 		armpmu_release_hardware(armpmu);
 		return err;
@@ -454,6 +456,17 @@ static int armpmu_event_init(struct perf_event *event)
 	int err = 0;
 	atomic_t *active_events = &armpmu->active_events;
 
+	/*
+	 * Reject CPU-affine events for CPUs that are of a different class to
+	 * that which this PMU handles. Process-following events (where
+	 * event->cpu == -1) can be migrated between CPUs, and thus we have to
+	 * reject them later (in armpmu_add) if they're scheduled on a
+	 * different class of CPU.
+	 */
+	if (event->cpu != -1 &&
+		!cpumask_test_cpu(event->cpu, &armpmu->supported_cpus))
+		return -ENOENT;
+
 	/* does not support taken branch sampling */
 	if (has_branch_stack(event))
 		return -EOPNOTSUPP;
@@ -489,6 +502,10 @@ static void armpmu_enable(struct pmu *pmu)
 	struct pmu_hw_events *hw_events = this_cpu_ptr(armpmu->hw_events);
 	int enabled = bitmap_weight(hw_events->used_mask, armpmu->num_events);
 
+	/* For task-bound events we may be called on other CPUs */
+	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus))
+		return;
+
 	if (enabled)
 		armpmu->start(armpmu);
 }
@@ -496,34 +513,25 @@ static void armpmu_enable(struct pmu *pmu)
 static void armpmu_disable(struct pmu *pmu)
 {
 	struct arm_pmu *armpmu = to_arm_pmu(pmu);
-	armpmu->stop(armpmu);
-}
-
-#ifdef CONFIG_PM
-static int armpmu_runtime_resume(struct device *dev)
-{
-	struct arm_pmu_platdata *plat = dev_get_platdata(dev);
 
-	if (plat && plat->runtime_resume)
-		return plat->runtime_resume(dev);
+	/* For task-bound events we may be called on other CPUs */
+	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus))
+		return;
 
-	return 0;
+	armpmu->stop(armpmu);
 }
 
-static int armpmu_runtime_suspend(struct device *dev)
+/*
+ * In heterogeneous systems, events are specific to a particular
+ * microarchitecture, and aren't suitable for another. Thus, only match CPUs of
+ * the same microarchitecture.
+ */
+static int armpmu_filter_match(struct perf_event *event)
 {
-	struct arm_pmu_platdata *plat = dev_get_platdata(dev);
-
-	if (plat && plat->runtime_suspend)
-		return plat->runtime_suspend(dev);
-
-	return 0;
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
+	unsigned int cpu = smp_processor_id();
+	return cpumask_test_cpu(cpu, &armpmu->supported_cpus);
 }
-#endif
-
-const struct dev_pm_ops armpmu_dev_pm_ops = {
-	SET_RUNTIME_PM_OPS(armpmu_runtime_suspend, armpmu_runtime_resume, NULL)
-};
 
 static void armpmu_init(struct arm_pmu *armpmu)
 {
@@ -539,15 +547,349 @@ static void armpmu_init(struct arm_pmu *armpmu)
 		.start		= armpmu_start,
 		.stop		= armpmu_stop,
 		.read		= armpmu_read,
+		.filter_match	= armpmu_filter_match,
 	};
 }
 
 int armpmu_register(struct arm_pmu *armpmu, int type)
 {
 	armpmu_init(armpmu);
-	pm_runtime_enable(&armpmu->plat_device->dev);
 	pr_info("enabled with %s PMU driver, %d counters available\n",
 			armpmu->name, armpmu->num_events);
 	return perf_pmu_register(&armpmu->pmu, armpmu->name, type);
 }
 
+/* Set at runtime when we know what CPU type we are. */
+static struct arm_pmu *__oprofile_cpu_pmu;
+
+/*
+ * Despite the names, these two functions are CPU-specific and are used
+ * by the OProfile/perf code.
+ */
+const char *perf_pmu_name(void)
+{
+	if (!__oprofile_cpu_pmu)
+		return NULL;
+
+	return __oprofile_cpu_pmu->name;
+}
+EXPORT_SYMBOL_GPL(perf_pmu_name);
+
+int perf_num_counters(void)
+{
+	int max_events = 0;
+
+	if (__oprofile_cpu_pmu != NULL)
+		max_events = __oprofile_cpu_pmu->num_events;
+
+	return max_events;
+}
+EXPORT_SYMBOL_GPL(perf_num_counters);
+
+static void cpu_pmu_enable_percpu_irq(void *data)
+{
+	int irq = *(int *)data;
+
+	enable_percpu_irq(irq, IRQ_TYPE_NONE);
+}
+
+static void cpu_pmu_disable_percpu_irq(void *data)
+{
+	int irq = *(int *)data;
+
+	disable_percpu_irq(irq);
+}
+
+static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu)
+{
+	int i, irq, irqs;
+	struct platform_device *pmu_device = cpu_pmu->plat_device;
+	struct pmu_hw_events __percpu *hw_events = cpu_pmu->hw_events;
+
+	irqs = min(pmu_device->num_resources, num_possible_cpus());
+
+	irq = platform_get_irq(pmu_device, 0);
+	if (irq >= 0 && irq_is_percpu(irq)) {
+		on_each_cpu(cpu_pmu_disable_percpu_irq, &irq, 1);
+		free_percpu_irq(irq, &hw_events->percpu_pmu);
+	} else {
+		for (i = 0; i < irqs; ++i) {
+			int cpu = i;
+
+			if (cpu_pmu->irq_affinity)
+				cpu = cpu_pmu->irq_affinity[i];
+
+			if (!cpumask_test_and_clear_cpu(cpu, &cpu_pmu->active_irqs))
+				continue;
+			irq = platform_get_irq(pmu_device, i);
+			if (irq >= 0)
+				free_irq(irq, per_cpu_ptr(&hw_events->percpu_pmu, cpu));
+		}
+	}
+}
+
+static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
+{
+	int i, err, irq, irqs;
+	struct platform_device *pmu_device = cpu_pmu->plat_device;
+	struct pmu_hw_events __percpu *hw_events = cpu_pmu->hw_events;
+
+	if (!pmu_device)
+		return -ENODEV;
+
+	irqs = min(pmu_device->num_resources, num_possible_cpus());
+	if (irqs < 1) {
+		pr_warn_once("perf/ARM: No irqs for PMU defined, sampling events not supported\n");
+		return 0;
+	}
+
+	irq = platform_get_irq(pmu_device, 0);
+	if (irq >= 0 && irq_is_percpu(irq)) {
+		err = request_percpu_irq(irq, handler, "arm-pmu",
+					 &hw_events->percpu_pmu);
+		if (err) {
+			pr_err("unable to request IRQ%d for ARM PMU counters\n",
+				irq);
+			return err;
+		}
+		on_each_cpu(cpu_pmu_enable_percpu_irq, &irq, 1);
+	} else {
+		for (i = 0; i < irqs; ++i) {
+			int cpu = i;
+
+			err = 0;
+			irq = platform_get_irq(pmu_device, i);
+			if (irq < 0)
+				continue;
+
+			if (cpu_pmu->irq_affinity)
+				cpu = cpu_pmu->irq_affinity[i];
+
+			/*
+			 * If we have a single PMU interrupt that we can't shift,
+			 * assume that we're running on a uniprocessor machine and
+			 * continue. Otherwise, continue without this interrupt.
+			 */
+			if (irq_set_affinity(irq, cpumask_of(cpu)) && irqs > 1) {
+				pr_warn("unable to set irq affinity (irq=%d, cpu=%u)\n",
+					irq, cpu);
+				continue;
+			}
+
+			err = request_irq(irq, handler,
+					  IRQF_NOBALANCING | IRQF_NO_THREAD, "arm-pmu",
+					  per_cpu_ptr(&hw_events->percpu_pmu, cpu));
+			if (err) {
+				pr_err("unable to request IRQ%d for ARM PMU counters\n",
+					irq);
+				return err;
+			}
+
+			cpumask_set_cpu(cpu, &cpu_pmu->active_irqs);
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * PMU hardware loses all context when a CPU goes offline.
+ * When a CPU is hotplugged back in, since some hardware registers are
+ * UNKNOWN at reset, the PMU must be explicitly reset to avoid reading
+ * junk values out of them.
+ */
+static int cpu_pmu_notify(struct notifier_block *b, unsigned long action,
+			  void *hcpu)
+{
+	int cpu = (unsigned long)hcpu;
+	struct arm_pmu *pmu = container_of(b, struct arm_pmu, hotplug_nb);
+
+	if ((action & ~CPU_TASKS_FROZEN) != CPU_STARTING)
+		return NOTIFY_DONE;
+
+	if (!cpumask_test_cpu(cpu, &pmu->supported_cpus))
+		return NOTIFY_DONE;
+
+	if (pmu->reset)
+		pmu->reset(pmu);
+	else
+		return NOTIFY_DONE;
+
+	return NOTIFY_OK;
+}
+
+static int cpu_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	int err;
+	int cpu;
+	struct pmu_hw_events __percpu *cpu_hw_events;
+
+	cpu_hw_events = alloc_percpu(struct pmu_hw_events);
+	if (!cpu_hw_events)
+		return -ENOMEM;
+
+	cpu_pmu->hotplug_nb.notifier_call = cpu_pmu_notify;
+	err = register_cpu_notifier(&cpu_pmu->hotplug_nb);
+	if (err)
+		goto out_hw_events;
+
+	for_each_possible_cpu(cpu) {
+		struct pmu_hw_events *events = per_cpu_ptr(cpu_hw_events, cpu);
+		raw_spin_lock_init(&events->pmu_lock);
+		events->percpu_pmu = cpu_pmu;
+	}
+
+	cpu_pmu->hw_events	= cpu_hw_events;
+	cpu_pmu->request_irq	= cpu_pmu_request_irq;
+	cpu_pmu->free_irq	= cpu_pmu_free_irq;
+
+	/* Ensure the PMU has sane values out of reset. */
+	if (cpu_pmu->reset)
+		on_each_cpu_mask(&cpu_pmu->supported_cpus, cpu_pmu->reset,
+			 cpu_pmu, 1);
+
+	/* If no interrupts available, set the corresponding capability flag */
+	if (!platform_get_irq(cpu_pmu->plat_device, 0))
+		cpu_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+
+	return 0;
+
+out_hw_events:
+	free_percpu(cpu_hw_events);
+	return err;
+}
+
+static void cpu_pmu_destroy(struct arm_pmu *cpu_pmu)
+{
+	unregister_cpu_notifier(&cpu_pmu->hotplug_nb);
+	free_percpu(cpu_pmu->hw_events);
+}
+
+/*
+ * CPU PMU identification and probing.
+ */
+static int probe_current_pmu(struct arm_pmu *pmu,
+			     const struct pmu_probe_info *info)
+{
+	int cpu = get_cpu();
+	unsigned int cpuid = read_cpuid_id();
+	int ret = -ENODEV;
+
+	pr_info("probing PMU on CPU %d\n", cpu);
+
+	for (; info->init != NULL; info++) {
+		if ((cpuid & info->mask) != info->cpuid)
+			continue;
+		ret = info->init(pmu);
+		break;
+	}
+
+	put_cpu();
+	return ret;
+}
+
+static int of_pmu_irq_cfg(struct arm_pmu *pmu)
+{
+	int i, irq, *irqs;
+	struct platform_device *pdev = pmu->plat_device;
+
+	/* Don't bother with PPIs; they're already affine */
+	irq = platform_get_irq(pdev, 0);
+	if (irq >= 0 && irq_is_percpu(irq))
+		return 0;
+
+	irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
+	if (!irqs)
+		return -ENOMEM;
+
+	for (i = 0; i < pdev->num_resources; ++i) {
+		struct device_node *dn;
+		int cpu;
+
+		dn = of_parse_phandle(pdev->dev.of_node, "interrupt-affinity",
+				      i);
+		if (!dn) {
+			pr_warn("Failed to parse %s/interrupt-affinity[%d]\n",
+				of_node_full_name(pdev->dev.of_node), i);
+			break;
+		}
+
+		for_each_possible_cpu(cpu)
+			if (arch_find_n_match_cpu_physical_id(dn, cpu, NULL))
+				break;
+
+		of_node_put(dn);
+		if (cpu >= nr_cpu_ids) {
+			pr_warn("Failed to find logical CPU for %s\n",
+				dn->name);
+			break;
+		}
+
+		irqs[i] = cpu;
+		cpumask_set_cpu(cpu, &pmu->supported_cpus);
+	}
+
+	if (i == pdev->num_resources) {
+		pmu->irq_affinity = irqs;
+	} else {
+		kfree(irqs);
+		cpumask_setall(&pmu->supported_cpus);
+	}
+
+	return 0;
+}
+
+int arm_pmu_device_probe(struct platform_device *pdev,
+			 const struct of_device_id *of_table,
+			 const struct pmu_probe_info *probe_table)
+{
+	const struct of_device_id *of_id;
+	const int (*init_fn)(struct arm_pmu *);
+	struct device_node *node = pdev->dev.of_node;
+	struct arm_pmu *pmu;
+	int ret = -ENODEV;
+
+	pmu = kzalloc(sizeof(struct arm_pmu), GFP_KERNEL);
+	if (!pmu) {
+		pr_info("failed to allocate PMU device!\n");
+		return -ENOMEM;
+	}
+
+	if (!__oprofile_cpu_pmu)
+		__oprofile_cpu_pmu = pmu;
+
+	pmu->plat_device = pdev;
+
+	if (node && (of_id = of_match_node(of_table, pdev->dev.of_node))) {
+		init_fn = of_id->data;
+
+		ret = of_pmu_irq_cfg(pmu);
+		if (!ret)
+			ret = init_fn(pmu);
+	} else {
+		ret = probe_current_pmu(pmu, probe_table);
+		cpumask_setall(&pmu->supported_cpus);
+	}
+
+	if (ret) {
+		pr_info("failed to probe PMU!\n");
+		goto out_free;
+	}
+
+	ret = cpu_pmu_init(pmu);
+	if (ret)
+		goto out_free;
+
+	ret = armpmu_register(pmu, -1);
+	if (ret)
+		goto out_destroy;
+
+	return 0;
+
+out_destroy:
+	cpu_pmu_destroy(pmu);
+out_free:
+	pr_info("failed to register PMU devices!\n");
+	kfree(pmu);
+	return ret;
+}
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
deleted file mode 100644
index 3b8c2833c537..000000000000
--- a/arch/arm/kernel/perf_event_cpu.c
+++ /dev/null
@@ -1,421 +0,0 @@
-/*
- * 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.
- *
- * Copyright (C) 2012 ARM Limited
- *
- * Author: Will Deacon <will.deacon@arm.com>
- */
-#define pr_fmt(fmt) "CPU PMU: " fmt
-
-#include <linux/bitmap.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>
-
-/* Set at runtime when we know what CPU type we are. */
-static struct arm_pmu *cpu_pmu;
-
-/*
- * Despite the names, these two functions are CPU-specific and are used
- * by the OProfile/perf code.
- */
-const char *perf_pmu_name(void)
-{
-	if (!cpu_pmu)
-		return NULL;
-
-	return cpu_pmu->name;
-}
-EXPORT_SYMBOL_GPL(perf_pmu_name);
-
-int perf_num_counters(void)
-{
-	int max_events = 0;
-
-	if (cpu_pmu != NULL)
-		max_events = cpu_pmu->num_events;
-
-	return max_events;
-}
-EXPORT_SYMBOL_GPL(perf_num_counters);
-
-/* Include the PMU-specific implementations. */
-#include "perf_event_xscale.c"
-#include "perf_event_v6.c"
-#include "perf_event_v7.c"
-
-static void cpu_pmu_enable_percpu_irq(void *data)
-{
-	int irq = *(int *)data;
-
-	enable_percpu_irq(irq, IRQ_TYPE_NONE);
-}
-
-static void cpu_pmu_disable_percpu_irq(void *data)
-{
-	int irq = *(int *)data;
-
-	disable_percpu_irq(irq);
-}
-
-static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu)
-{
-	int i, irq, irqs;
-	struct platform_device *pmu_device = cpu_pmu->plat_device;
-	struct pmu_hw_events __percpu *hw_events = cpu_pmu->hw_events;
-
-	irqs = min(pmu_device->num_resources, num_possible_cpus());
-
-	irq = platform_get_irq(pmu_device, 0);
-	if (irq >= 0 && irq_is_percpu(irq)) {
-		on_each_cpu(cpu_pmu_disable_percpu_irq, &irq, 1);
-		free_percpu_irq(irq, &hw_events->percpu_pmu);
-	} else {
-		for (i = 0; i < irqs; ++i) {
-			int cpu = i;
-
-			if (cpu_pmu->irq_affinity)
-				cpu = cpu_pmu->irq_affinity[i];
-
-			if (!cpumask_test_and_clear_cpu(cpu, &cpu_pmu->active_irqs))
-				continue;
-			irq = platform_get_irq(pmu_device, i);
-			if (irq >= 0)
-				free_irq(irq, per_cpu_ptr(&hw_events->percpu_pmu, cpu));
-		}
-	}
-}
-
-static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
-{
-	int i, err, irq, irqs;
-	struct platform_device *pmu_device = cpu_pmu->plat_device;
-	struct pmu_hw_events __percpu *hw_events = cpu_pmu->hw_events;
-
-	if (!pmu_device)
-		return -ENODEV;
-
-	irqs = min(pmu_device->num_resources, num_possible_cpus());
-	if (irqs < 1) {
-		pr_warn_once("perf/ARM: No irqs for PMU defined, sampling events not supported\n");
-		return 0;
-	}
-
-	irq = platform_get_irq(pmu_device, 0);
-	if (irq >= 0 && irq_is_percpu(irq)) {
-		err = request_percpu_irq(irq, handler, "arm-pmu",
-					 &hw_events->percpu_pmu);
-		if (err) {
-			pr_err("unable to request IRQ%d for ARM PMU counters\n",
-				irq);
-			return err;
-		}
-		on_each_cpu(cpu_pmu_enable_percpu_irq, &irq, 1);
-	} else {
-		for (i = 0; i < irqs; ++i) {
-			int cpu = i;
-
-			err = 0;
-			irq = platform_get_irq(pmu_device, i);
-			if (irq < 0)
-				continue;
-
-			if (cpu_pmu->irq_affinity)
-				cpu = cpu_pmu->irq_affinity[i];
-
-			/*
-			 * If we have a single PMU interrupt that we can't shift,
-			 * assume that we're running on a uniprocessor machine and
-			 * continue. Otherwise, continue without this interrupt.
-			 */
-			if (irq_set_affinity(irq, cpumask_of(cpu)) && irqs > 1) {
-				pr_warn("unable to set irq affinity (irq=%d, cpu=%u)\n",
-					irq, cpu);
-				continue;
-			}
-
-			err = request_irq(irq, handler,
-					  IRQF_NOBALANCING | IRQF_NO_THREAD, "arm-pmu",
-					  per_cpu_ptr(&hw_events->percpu_pmu, cpu));
-			if (err) {
-				pr_err("unable to request IRQ%d for ARM PMU counters\n",
-					irq);
-				return err;
-			}
-
-			cpumask_set_cpu(cpu, &cpu_pmu->active_irqs);
-		}
-	}
-
-	return 0;
-}
-
-/*
- * PMU hardware loses all context when a CPU goes offline.
- * When a CPU is hotplugged back in, since some hardware registers are
- * UNKNOWN at reset, the PMU must be explicitly reset to avoid reading
- * junk values out of them.
- */
-static int cpu_pmu_notify(struct notifier_block *b, unsigned long action,
-			  void *hcpu)
-{
-	struct arm_pmu *pmu = container_of(b, struct arm_pmu, hotplug_nb);
-
-	if ((action & ~CPU_TASKS_FROZEN) != CPU_STARTING)
-		return NOTIFY_DONE;
-
-	if (pmu->reset)
-		pmu->reset(pmu);
-	else
-		return NOTIFY_DONE;
-
-	return NOTIFY_OK;
-}
-
-static int cpu_pmu_init(struct arm_pmu *cpu_pmu)
-{
-	int err;
-	int cpu;
-	struct pmu_hw_events __percpu *cpu_hw_events;
-
-	cpu_hw_events = alloc_percpu(struct pmu_hw_events);
-	if (!cpu_hw_events)
-		return -ENOMEM;
-
-	cpu_pmu->hotplug_nb.notifier_call = cpu_pmu_notify;
-	err = register_cpu_notifier(&cpu_pmu->hotplug_nb);
-	if (err)
-		goto out_hw_events;
-
-	for_each_possible_cpu(cpu) {
-		struct pmu_hw_events *events = per_cpu_ptr(cpu_hw_events, cpu);
-		raw_spin_lock_init(&events->pmu_lock);
-		events->percpu_pmu = cpu_pmu;
-	}
-
-	cpu_pmu->hw_events	= cpu_hw_events;
-	cpu_pmu->request_irq	= cpu_pmu_request_irq;
-	cpu_pmu->free_irq	= cpu_pmu_free_irq;
-
-	/* Ensure the PMU has sane values out of reset. */
-	if (cpu_pmu->reset)
-		on_each_cpu(cpu_pmu->reset, cpu_pmu, 1);
-
-	/* If no interrupts available, set the corresponding capability flag */
-	if (!platform_get_irq(cpu_pmu->plat_device, 0))
-		cpu_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
-
-	return 0;
-
-out_hw_events:
-	free_percpu(cpu_hw_events);
-	return err;
-}
-
-static void cpu_pmu_destroy(struct arm_pmu *cpu_pmu)
-{
-	unregister_cpu_notifier(&cpu_pmu->hotplug_nb);
-	free_percpu(cpu_pmu->hw_events);
-}
-
-/*
- * PMU platform driver and devicetree bindings.
- */
-static const struct of_device_id cpu_pmu_of_device_ids[] = {
-	{.compatible = "arm,cortex-a17-pmu",	.data = armv7_a17_pmu_init},
-	{.compatible = "arm,cortex-a15-pmu",	.data = armv7_a15_pmu_init},
-	{.compatible = "arm,cortex-a12-pmu",	.data = armv7_a12_pmu_init},
-	{.compatible = "arm,cortex-a9-pmu",	.data = armv7_a9_pmu_init},
-	{.compatible = "arm,cortex-a8-pmu",	.data = armv7_a8_pmu_init},
-	{.compatible = "arm,cortex-a7-pmu",	.data = armv7_a7_pmu_init},
-	{.compatible = "arm,cortex-a5-pmu",	.data = armv7_a5_pmu_init},
-	{.compatible = "arm,arm11mpcore-pmu",	.data = armv6mpcore_pmu_init},
-	{.compatible = "arm,arm1176-pmu",	.data = armv6_1176_pmu_init},
-	{.compatible = "arm,arm1136-pmu",	.data = armv6_1136_pmu_init},
-	{.compatible = "qcom,krait-pmu",	.data = krait_pmu_init},
-	{.compatible = "qcom,scorpion-pmu",	.data = scorpion_pmu_init},
-	{.compatible = "qcom,scorpion-mp-pmu",	.data = scorpion_mp_pmu_init},
-	{},
-};
-
-static struct platform_device_id cpu_pmu_plat_device_ids[] = {
-	{.name = "arm-pmu"},
-	{.name = "armv6-pmu"},
-	{.name = "armv7-pmu"},
-	{.name = "xscale-pmu"},
-	{},
-};
-
-static const struct pmu_probe_info pmu_probe_table[] = {
-	ARM_PMU_PROBE(ARM_CPU_PART_ARM1136, armv6_1136_pmu_init),
-	ARM_PMU_PROBE(ARM_CPU_PART_ARM1156, armv6_1156_pmu_init),
-	ARM_PMU_PROBE(ARM_CPU_PART_ARM1176, armv6_1176_pmu_init),
-	ARM_PMU_PROBE(ARM_CPU_PART_ARM11MPCORE, armv6mpcore_pmu_init),
-	ARM_PMU_PROBE(ARM_CPU_PART_CORTEX_A8, armv7_a8_pmu_init),
-	ARM_PMU_PROBE(ARM_CPU_PART_CORTEX_A9, armv7_a9_pmu_init),
-	XSCALE_PMU_PROBE(ARM_CPU_XSCALE_ARCH_V1, xscale1pmu_init),
-	XSCALE_PMU_PROBE(ARM_CPU_XSCALE_ARCH_V2, xscale2pmu_init),
-	{ /* sentinel value */ }
-};
-
-/*
- * CPU PMU identification and probing.
- */
-static int probe_current_pmu(struct arm_pmu *pmu)
-{
-	int cpu = get_cpu();
-	unsigned int cpuid = read_cpuid_id();
-	int ret = -ENODEV;
-	const struct pmu_probe_info *info;
-
-	pr_info("probing PMU on CPU %d\n", cpu);
-
-	for (info = pmu_probe_table; info->init != NULL; info++) {
-		if ((cpuid & info->mask) != info->cpuid)
-			continue;
-		ret = info->init(pmu);
-		break;
-	}
-
-	put_cpu();
-	return ret;
-}
-
-static int of_pmu_irq_cfg(struct platform_device *pdev)
-{
-	int i, irq;
-	int *irqs;
-
-	/* Don't bother with PPIs; they're already affine */
-	irq = platform_get_irq(pdev, 0);
-	if (irq >= 0 && irq_is_percpu(irq))
-		return 0;
-
-	irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
-	if (!irqs)
-		return -ENOMEM;
-
-	for (i = 0; i < pdev->num_resources; ++i) {
-		struct device_node *dn;
-		int cpu;
-
-		dn = of_parse_phandle(pdev->dev.of_node, "interrupt-affinity",
-				      i);
-		if (!dn) {
-			pr_warn("Failed to parse %s/interrupt-affinity[%d]\n",
-				of_node_full_name(pdev->dev.of_node), i);
-			break;
-		}
-
-		for_each_possible_cpu(cpu)
-			if (arch_find_n_match_cpu_physical_id(dn, cpu, NULL))
-				break;
-
-		of_node_put(dn);
-		if (cpu >= nr_cpu_ids) {
-			pr_warn("Failed to find logical CPU for %s\n",
-				dn->name);
-			break;
-		}
-
-		irqs[i] = cpu;
-	}
-
-	if (i == pdev->num_resources)
-		cpu_pmu->irq_affinity = irqs;
-	else
-		kfree(irqs);
-
-	return 0;
-}
-
-static int cpu_pmu_device_probe(struct platform_device *pdev)
-{
-	const struct of_device_id *of_id;
-	const int (*init_fn)(struct arm_pmu *);
-	struct device_node *node = pdev->dev.of_node;
-	struct arm_pmu *pmu;
-	int ret = -ENODEV;
-
-	if (cpu_pmu) {
-		pr_info("attempt to register multiple PMU devices!\n");
-		return -ENOSPC;
-	}
-
-	pmu = kzalloc(sizeof(struct arm_pmu), GFP_KERNEL);
-	if (!pmu) {
-		pr_info("failed to allocate PMU device!\n");
-		return -ENOMEM;
-	}
-
-	cpu_pmu = pmu;
-	cpu_pmu->plat_device = pdev;
-
-	if (node && (of_id = of_match_node(cpu_pmu_of_device_ids, pdev->dev.of_node))) {
-		init_fn = of_id->data;
-
-		ret = of_pmu_irq_cfg(pdev);
-		if (!ret)
-			ret = init_fn(pmu);
-	} else {
-		ret = probe_current_pmu(pmu);
-	}
-
-	if (ret) {
-		pr_info("failed to probe PMU!\n");
-		goto out_free;
-	}
-
-	ret = cpu_pmu_init(cpu_pmu);
-	if (ret)
-		goto out_free;
-
-	ret = armpmu_register(cpu_pmu, -1);
-	if (ret)
-		goto out_destroy;
-
-	return 0;
-
-out_destroy:
-	cpu_pmu_destroy(cpu_pmu);
-out_free:
-	pr_info("failed to register PMU devices!\n");
-	kfree(pmu);
-	return ret;
-}
-
-static struct platform_driver cpu_pmu_driver = {
-	.driver		= {
-		.name	= "arm-pmu",
-		.pm	= &armpmu_dev_pm_ops,
-		.of_match_table = cpu_pmu_of_device_ids,
-	},
-	.probe		= cpu_pmu_device_probe,
-	.id_table	= cpu_pmu_plat_device_ids,
-};
-
-static int __init register_pmu_driver(void)
-{
-	return platform_driver_register(&cpu_pmu_driver);
-}
-device_initcall(register_pmu_driver);
diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index f2ffd5c542ed..09f83e414a72 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -31,6 +31,14 @@
  */
 
 #if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K)
+
+#include <asm/cputype.h>
+#include <asm/irq_regs.h>
+#include <asm/pmu.h>
+
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
 enum armv6_perf_types {
 	ARMV6_PERFCTR_ICACHE_MISS	    = 0x0,
 	ARMV6_PERFCTR_IBUF_STALL	    = 0x1,
@@ -543,24 +551,39 @@ static int armv6mpcore_pmu_init(struct arm_pmu *cpu_pmu)
 
 	return 0;
 }
-#else
-static int armv6_1136_pmu_init(struct arm_pmu *cpu_pmu)
-{
-	return -ENODEV;
-}
 
-static int armv6_1156_pmu_init(struct arm_pmu *cpu_pmu)
-{
-	return -ENODEV;
-}
+static struct of_device_id armv6_pmu_of_device_ids[] = {
+	{.compatible = "arm,arm11mpcore-pmu",	.data = armv6mpcore_pmu_init},
+	{.compatible = "arm,arm1176-pmu",	.data = armv6_1176_pmu_init},
+	{.compatible = "arm,arm1136-pmu",	.data = armv6_1136_pmu_init},
+	{ /* sentinel value */ }
+};
 
-static int armv6_1176_pmu_init(struct arm_pmu *cpu_pmu)
+static const struct pmu_probe_info armv6_pmu_probe_table[] = {
+	ARM_PMU_PROBE(ARM_CPU_PART_ARM1136, armv6_1136_pmu_init),
+	ARM_PMU_PROBE(ARM_CPU_PART_ARM1156, armv6_1156_pmu_init),
+	ARM_PMU_PROBE(ARM_CPU_PART_ARM1176, armv6_1176_pmu_init),
+	ARM_PMU_PROBE(ARM_CPU_PART_ARM11MPCORE, armv6mpcore_pmu_init),
+	{ /* sentinel value */ }
+};
+
+static int armv6_pmu_device_probe(struct platform_device *pdev)
 {
-	return -ENODEV;
+	return arm_pmu_device_probe(pdev, armv6_pmu_of_device_ids,
+				    armv6_pmu_probe_table);
 }
 
-static int armv6mpcore_pmu_init(struct arm_pmu *cpu_pmu)
+static struct platform_driver armv6_pmu_driver = {
+	.driver		= {
+		.name	= "armv6-pmu",
+		.of_match_table = armv6_pmu_of_device_ids,
+	},
+	.probe		= armv6_pmu_device_probe,
+};
+
+static int __init register_armv6_pmu_driver(void)
 {
-	return -ENODEV;
+	return platform_driver_register(&armv6_pmu_driver);
 }
+device_initcall(register_armv6_pmu_driver);
 #endif	/* CONFIG_CPU_V6 || CONFIG_CPU_V6K */
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index f4207a4dcb01..f9b37f876e20 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -19,9 +19,15 @@
 #ifdef CONFIG_CPU_V7
 
 #include <asm/cp15.h>
+#include <asm/cputype.h>
+#include <asm/irq_regs.h>
+#include <asm/pmu.h>
 #include <asm/vfp.h>
 #include "../vfp/vfpinstr.h"
 
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
 /*
  * Common ARMv7 event types
  *
@@ -1056,15 +1062,22 @@ static void armv7pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->max_period	= (1LLU << 32) - 1;
 };
 
-static u32 armv7_read_num_pmnc_events(void)
+static void armv7_read_num_pmnc_events(void *info)
 {
-	u32 nb_cnt;
+	int *nb_cnt = info;
 
 	/* Read the nb of CNTx counters supported from PMNC */
-	nb_cnt = (armv7_pmnc_read() >> ARMV7_PMNC_N_SHIFT) & ARMV7_PMNC_N_MASK;
+	*nb_cnt = (armv7_pmnc_read() >> ARMV7_PMNC_N_SHIFT) & ARMV7_PMNC_N_MASK;
 
-	/* Add the CPU cycles counter and return */
-	return nb_cnt + 1;
+	/* Add the CPU cycles counter */
+	*nb_cnt += 1;
+}
+
+static int armv7_probe_num_events(struct arm_pmu *arm_pmu)
+{
+	return smp_call_function_any(&arm_pmu->supported_cpus,
+				     armv7_read_num_pmnc_events,
+				     &arm_pmu->num_events, 1);
 }
 
 static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu)
@@ -1072,8 +1085,7 @@ static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu)
 	armv7pmu_init(cpu_pmu);
 	cpu_pmu->name		= "armv7_cortex_a8";
 	cpu_pmu->map_event	= armv7_a8_map_event;
-	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
-	return 0;
+	return armv7_probe_num_events(cpu_pmu);
 }
 
 static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu)
@@ -1081,8 +1093,7 @@ static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu)
 	armv7pmu_init(cpu_pmu);
 	cpu_pmu->name		= "armv7_cortex_a9";
 	cpu_pmu->map_event	= armv7_a9_map_event;
-	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
-	return 0;
+	return armv7_probe_num_events(cpu_pmu);
 }
 
 static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu)
@@ -1090,8 +1101,7 @@ static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu)
 	armv7pmu_init(cpu_pmu);
 	cpu_pmu->name		= "armv7_cortex_a5";
 	cpu_pmu->map_event	= armv7_a5_map_event;
-	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
-	return 0;
+	return armv7_probe_num_events(cpu_pmu);
 }
 
 static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu)
@@ -1099,9 +1109,8 @@ static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu)
 	armv7pmu_init(cpu_pmu);
 	cpu_pmu->name		= "armv7_cortex_a15";
 	cpu_pmu->map_event	= armv7_a15_map_event;
-	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
-	return 0;
+	return armv7_probe_num_events(cpu_pmu);
 }
 
 static int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu)
@@ -1109,9 +1118,8 @@ static int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu)
 	armv7pmu_init(cpu_pmu);
 	cpu_pmu->name		= "armv7_cortex_a7";
 	cpu_pmu->map_event	= armv7_a7_map_event;
-	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
-	return 0;
+	return armv7_probe_num_events(cpu_pmu);
 }
 
 static int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu)
@@ -1119,16 +1127,15 @@ static int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu)
 	armv7pmu_init(cpu_pmu);
 	cpu_pmu->name		= "armv7_cortex_a12";
 	cpu_pmu->map_event	= armv7_a12_map_event;
-	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
-	return 0;
+	return armv7_probe_num_events(cpu_pmu);
 }
 
 static int armv7_a17_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	armv7_a12_pmu_init(cpu_pmu);
+	int ret = armv7_a12_pmu_init(cpu_pmu);
 	cpu_pmu->name = "armv7_cortex_a17";
-	return 0;
+	return ret;
 }
 
 /*
@@ -1508,14 +1515,13 @@ static int krait_pmu_init(struct arm_pmu *cpu_pmu)
 		cpu_pmu->map_event = krait_map_event_no_branch;
 	else
 		cpu_pmu->map_event = krait_map_event;
-	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
 	cpu_pmu->reset		= krait_pmu_reset;
 	cpu_pmu->enable		= krait_pmu_enable_event;
 	cpu_pmu->disable	= krait_pmu_disable_event;
 	cpu_pmu->get_event_idx	= krait_pmu_get_event_idx;
 	cpu_pmu->clear_event_idx = krait_pmu_clear_event_idx;
-	return 0;
+	return armv7_probe_num_events(cpu_pmu);
 }
 
 /*
@@ -1833,13 +1839,12 @@ static int scorpion_pmu_init(struct arm_pmu *cpu_pmu)
 	armv7pmu_init(cpu_pmu);
 	cpu_pmu->name		= "armv7_scorpion";
 	cpu_pmu->map_event	= scorpion_map_event;
-	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	cpu_pmu->reset		= scorpion_pmu_reset;
 	cpu_pmu->enable		= scorpion_pmu_enable_event;
 	cpu_pmu->disable	= scorpion_pmu_disable_event;
 	cpu_pmu->get_event_idx	= scorpion_pmu_get_event_idx;
 	cpu_pmu->clear_event_idx = scorpion_pmu_clear_event_idx;
-	return 0;
+	return armv7_probe_num_events(cpu_pmu);
 }
 
 static int scorpion_mp_pmu_init(struct arm_pmu *cpu_pmu)
@@ -1847,62 +1852,52 @@ static int scorpion_mp_pmu_init(struct arm_pmu *cpu_pmu)
 	armv7pmu_init(cpu_pmu);
 	cpu_pmu->name		= "armv7_scorpion_mp";
 	cpu_pmu->map_event	= scorpion_map_event;
-	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	cpu_pmu->reset		= scorpion_pmu_reset;
 	cpu_pmu->enable		= scorpion_pmu_enable_event;
 	cpu_pmu->disable	= scorpion_pmu_disable_event;
 	cpu_pmu->get_event_idx	= scorpion_pmu_get_event_idx;
 	cpu_pmu->clear_event_idx = scorpion_pmu_clear_event_idx;
-	return 0;
-}
-#else
-static inline int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu)
-{
-	return -ENODEV;
-}
-
-static inline int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu)
-{
-	return -ENODEV;
-}
-
-static inline int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu)
-{
-	return -ENODEV;
-}
-
-static inline int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu)
-{
-	return -ENODEV;
-}
-
-static inline int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu)
-{
-	return -ENODEV;
-}
+	return armv7_probe_num_events(cpu_pmu);
+}
+
+static const struct of_device_id armv7_pmu_of_device_ids[] = {
+	{.compatible = "arm,cortex-a17-pmu",	.data = armv7_a17_pmu_init},
+	{.compatible = "arm,cortex-a15-pmu",	.data = armv7_a15_pmu_init},
+	{.compatible = "arm,cortex-a12-pmu",	.data = armv7_a12_pmu_init},
+	{.compatible = "arm,cortex-a9-pmu",	.data = armv7_a9_pmu_init},
+	{.compatible = "arm,cortex-a8-pmu",	.data = armv7_a8_pmu_init},
+	{.compatible = "arm,cortex-a7-pmu",	.data = armv7_a7_pmu_init},
+	{.compatible = "arm,cortex-a5-pmu",	.data = armv7_a5_pmu_init},
+	{.compatible = "qcom,krait-pmu",	.data = krait_pmu_init},
+	{.compatible = "qcom,scorpion-pmu",	.data = scorpion_pmu_init},
+	{.compatible = "qcom,scorpion-mp-pmu",	.data = scorpion_mp_pmu_init},
+	{},
+};
 
-static inline int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu)
-{
-	return -ENODEV;
-}
+static const struct pmu_probe_info armv7_pmu_probe_table[] = {
+	ARM_PMU_PROBE(ARM_CPU_PART_CORTEX_A8, armv7_a8_pmu_init),
+	ARM_PMU_PROBE(ARM_CPU_PART_CORTEX_A9, armv7_a9_pmu_init),
+	{ /* sentinel value */ }
+};
 
-static inline int armv7_a17_pmu_init(struct arm_pmu *cpu_pmu)
-{
-	return -ENODEV;
-}
 
-static inline int krait_pmu_init(struct arm_pmu *cpu_pmu)
+static int armv7_pmu_device_probe(struct platform_device *pdev)
 {
-	return -ENODEV;
+	return arm_pmu_device_probe(pdev, armv7_pmu_of_device_ids,
+				    armv7_pmu_probe_table);
 }
 
-static inline int scorpion_pmu_init(struct arm_pmu *cpu_pmu)
-{
-	return -ENODEV;
-}
+static struct platform_driver armv7_pmu_driver = {
+	.driver		= {
+		.name	= "armv7-pmu",
+		.of_match_table = armv7_pmu_of_device_ids,
+	},
+	.probe		= armv7_pmu_device_probe,
+};
 
-static inline int scorpion_mp_pmu_init(struct arm_pmu *cpu_pmu)
+static int __init register_armv7_pmu_driver(void)
 {
-	return -ENODEV;
+	return platform_driver_register(&armv7_pmu_driver);
 }
+device_initcall(register_armv7_pmu_driver);
 #endif	/* CONFIG_CPU_V7 */
diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c
index 8af9f1f82c68..304d056d5b25 100644
--- a/arch/arm/kernel/perf_event_xscale.c
+++ b/arch/arm/kernel/perf_event_xscale.c
@@ -13,6 +13,14 @@
  */
 
 #ifdef CONFIG_CPU_XSCALE
+
+#include <asm/cputype.h>
+#include <asm/irq_regs.h>
+#include <asm/pmu.h>
+
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
 enum xscale_perf_types {
 	XSCALE_PERFCTR_ICACHE_MISS		= 0x00,
 	XSCALE_PERFCTR_ICACHE_NO_DELIVER	= 0x01,
@@ -740,14 +748,28 @@ static int xscale2pmu_init(struct arm_pmu *cpu_pmu)
 
 	return 0;
 }
-#else
-static inline int xscale1pmu_init(struct arm_pmu *cpu_pmu)
+
+static const struct pmu_probe_info xscale_pmu_probe_table[] = {
+	XSCALE_PMU_PROBE(ARM_CPU_XSCALE_ARCH_V1, xscale1pmu_init),
+	XSCALE_PMU_PROBE(ARM_CPU_XSCALE_ARCH_V2, xscale2pmu_init),
+	{ /* sentinel value */ }
+};
+
+static int xscale_pmu_device_probe(struct platform_device *pdev)
 {
-	return -ENODEV;
+	return arm_pmu_device_probe(pdev, NULL, xscale_pmu_probe_table);
 }
 
-static inline int xscale2pmu_init(struct arm_pmu *cpu_pmu)
+static struct platform_driver xscale_pmu_driver = {
+	.driver		= {
+		.name	= "xscale-pmu",
+	},
+	.probe		= xscale_pmu_device_probe,
+};
+
+static int __init register_xscale_pmu_driver(void)
 {
-	return -ENODEV;
+	return platform_driver_register(&xscale_pmu_driver);
 }
+device_initcall(register_xscale_pmu_driver);
 #endif	/* CONFIG_CPU_XSCALE */
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 6c777e908a24..e6d8c7658ffd 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -75,8 +75,7 @@ __setup("fpe=", fpe_setup);
 
 extern void init_default_cache_policy(unsigned long);
 extern void paging_init(const struct machine_desc *desc);
-extern void early_paging_init(const struct machine_desc *,
-			      struct proc_info_list *);
+extern void early_paging_init(const struct machine_desc *);
 extern void sanity_check_meminfo(void);
 extern enum reboot_mode reboot_mode;
 extern void setup_dma_zone(const struct machine_desc *desc);
@@ -93,6 +92,9 @@ unsigned int __atags_pointer __initdata;
 unsigned int system_rev;
 EXPORT_SYMBOL(system_rev);
 
+const char *system_serial;
+EXPORT_SYMBOL(system_serial);
+
 unsigned int system_serial_low;
 EXPORT_SYMBOL(system_serial_low);
 
@@ -839,8 +841,25 @@ arch_initcall(customize_machine);
 
 static int __init init_machine_late(void)
 {
+	struct device_node *root;
+	int ret;
+
 	if (machine_desc->init_late)
 		machine_desc->init_late();
+
+	root = of_find_node_by_path("/");
+	if (root) {
+		ret = of_property_read_string(root, "serial-number",
+					      &system_serial);
+		if (ret)
+			system_serial = NULL;
+	}
+
+	if (!system_serial)
+		system_serial = kasprintf(GFP_KERNEL, "%08x%08x",
+					  system_serial_high,
+					  system_serial_low);
+
 	return 0;
 }
 late_initcall(init_machine_late);
@@ -936,7 +955,9 @@ void __init setup_arch(char **cmdline_p)
 
 	parse_early_param();
 
-	early_paging_init(mdesc, lookup_processor_type(read_cpuid_id()));
+#ifdef CONFIG_MMU
+	early_paging_init(mdesc);
+#endif
 	setup_dma_zone(mdesc);
 	sanity_check_meminfo();
 	arm_memblock_init(mdesc);
@@ -1109,8 +1130,7 @@ static int c_show(struct seq_file *m, void *v)
 
 	seq_printf(m, "Hardware\t: %s\n", machine_name);
 	seq_printf(m, "Revision\t: %04x\n", system_rev);
-	seq_printf(m, "Serial\t\t: %08x%08x\n",
-		   system_serial_high, system_serial_low);
+	seq_printf(m, "Serial\t\t: %s\n", system_serial);
 
 	return 0;
 }
diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S
index 7d37bfc50830..0f6c1000582c 100644
--- a/arch/arm/kernel/sleep.S
+++ b/arch/arm/kernel/sleep.S
@@ -81,7 +81,7 @@ ENTRY(__cpu_suspend)
 	mov	r1, r4			@ size of save block
 	add	r0, sp, #8		@ pointer to save block
 	bl	__cpu_suspend_save
-	adr	lr, BSYM(cpu_suspend_abort)
+	badr	lr, cpu_suspend_abort
 	ldmfd	sp!, {r0, pc}		@ call suspend fn
 ENDPROC(__cpu_suspend)
 	.ltorg
@@ -118,6 +118,16 @@ ENDPROC(cpu_resume_after_mmu)
 
 	.text
 	.align
+
+#ifdef CONFIG_MMU
+	.arm
+ENTRY(cpu_resume_arm)
+ THUMB(	badr	r9, 1f		)	@ Kernel is entered in ARM.
+ THUMB(	bx	r9		)	@ If this is a Thumb-2 kernel,
+ THUMB(	.thumb			)	@ switch to Thumb now.
+ THUMB(1:			)
+#endif
+
 ENTRY(cpu_resume)
 ARM_BE8(setend be)			@ ensure we are in BE mode
 #ifdef CONFIG_ARM_VIRT_EXT
@@ -150,6 +160,10 @@ THUMB(	mov	sp, r2			)
 THUMB(	bx	r3			)
 ENDPROC(cpu_resume)
 
+#ifdef CONFIG_MMU
+ENDPROC(cpu_resume_arm)
+#endif
+
 	.align 2
 _sleep_save_sp:
 	.long	sleep_save_sp - .
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index f11d82527076..3d6b7821cff8 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -86,9 +86,11 @@ void __init smp_set_ops(struct smp_operations *ops)
 
 static unsigned long get_arch_pgd(pgd_t *pgd)
 {
-	phys_addr_t pgdir = virt_to_idmap(pgd);
-	BUG_ON(pgdir & ARCH_PGD_MASK);
-	return pgdir >> ARCH_PGD_SHIFT;
+#ifdef CONFIG_ARM_LPAE
+	return __phys_to_pfn(virt_to_phys(pgd));
+#else
+	return virt_to_phys(pgd);
+#endif
 }
 
 int __cpu_up(unsigned int cpu, struct task_struct *idle)
@@ -108,7 +110,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 #endif
 
 #ifdef CONFIG_MMU
-	secondary_data.pgdir = get_arch_pgd(idmap_pgd);
+	secondary_data.pgdir = virt_to_phys(idmap_pgd);
 	secondary_data.swapper_pg_dir = get_arch_pgd(swapper_pg_dir);
 #endif
 	sync_cache_w(&secondary_data);
diff --git a/arch/arm/kernel/tcm.c b/arch/arm/kernel/tcm.c
index 7a3be1d4d0b1..b10e1360762e 100644
--- a/arch/arm/kernel/tcm.c
+++ b/arch/arm/kernel/tcm.c
@@ -17,6 +17,9 @@
 #include <asm/mach/map.h>
 #include <asm/memory.h>
 #include <asm/system_info.h>
+#include <asm/traps.h>
+
+#define TCMTR_FORMAT_MASK	0xe0000000U
 
 static struct gen_pool *tcm_pool;
 static bool dtcm_present;
@@ -176,6 +179,77 @@ static int __init setup_tcm_bank(u8 type, u8 bank, u8 banks,
 }
 
 /*
+ * When we are running in the non-secure world and the secure world
+ * has not explicitly given us access to the TCM we will get an
+ * undefined error when reading the TCM region register in the
+ * setup_tcm_bank function (above).
+ *
+ * There are two variants of this register read that we need to trap,
+ * the read for the data TCM and the read for the instruction TCM:
+ *  c0370628:       ee196f11        mrc     15, 0, r6, cr9, cr1, {0}
+ *  c0370674:       ee196f31        mrc     15, 0, r6, cr9, cr1, {1}
+ *
+ * Our undef hook mask explicitly matches all fields of the encoded
+ * instruction other than the destination register.  The mask also
+ * only allows operand 2 to have the values 0 or 1.
+ *
+ * The undefined hook is defined as __init and __initdata, and therefore
+ * must be removed before tcm_init returns.
+ *
+ * In this particular case (MRC with ARM condition code ALways) the
+ * Thumb-2 and ARM instruction encoding are identical, so this hook
+ * will work on a Thumb-2 kernel.
+ *
+ * See A8.8.107, DDI0406C_C ARM Architecture Reference Manual, Encoding
+ * T1/A1 for the bit-by-bit details.
+ *
+ *  mrc   p15, 0, XX, c9, c1, 0
+ *  mrc   p15, 0, XX, c9, c1, 1
+ *   |  |  |   |   |   |   |  +---- opc2           0|1 = 000|001
+ *   |  |  |   |   |   |   +------- CRm              0 = 0001
+ *   |  |  |   |   |   +----------- CRn              0 = 1001
+ *   |  |  |   |   +--------------- Rt               ? = ????
+ *   |  |  |   +------------------- opc1             0 =  000
+ *   |  |  +----------------------- coproc          15 = 1111
+ *   |  +-------------------------- condition   ALways = 1110
+ *   +----------------------------- instruction    MRC = 1110
+ *
+ * Encoding this as per A8.8.107 of DDI0406C, Encoding T1/A1, yields:
+ *  1111 1111 1111 1111 0000 1111 1101 1111 Required Mask
+ *  1110 1110 0001 1001 ???? 1111 0001 0001 mrc p15, 0, XX, c9, c1, 0
+ *  1110 1110 0001 1001 ???? 1111 0011 0001 mrc p15, 0, XX, c9, c1, 1
+ *  [  ] [  ] [ ]| [  ] [  ] [  ] [ ]| +--- CRm
+ *    |    |   | |   |    |    |   | +----- SBO
+ *    |    |   | |   |    |    |   +------- opc2
+ *    |    |   | |   |    |    +----------- coproc
+ *    |    |   | |   |    +---------------- Rt
+ *    |    |   | |   +--------------------- CRn
+ *    |    |   | +------------------------- SBO
+ *    |    |   +--------------------------- opc1
+ *    |    +------------------------------- instruction
+ *    +------------------------------------ condition
+ */
+#define TCM_REGION_READ_MASK		0xffff0fdf
+#define TCM_REGION_READ_INSTR		0xee190f11
+#define DEST_REG_SHIFT			12
+#define DEST_REG_MASK			0xf
+
+static int __init tcm_handler(struct pt_regs *regs, unsigned int instr)
+{
+	regs->uregs[(instr >> DEST_REG_SHIFT) & DEST_REG_MASK] = 0;
+	regs->ARM_pc += 4;
+	return 0;
+}
+
+static struct undef_hook tcm_hook __initdata = {
+	.instr_mask	= TCM_REGION_READ_MASK,
+	.instr_val	= TCM_REGION_READ_INSTR,
+	.cpsr_mask	= MODE_MASK,
+	.cpsr_val	= SVC_MODE,
+	.fn		= tcm_handler
+};
+
+/*
  * This initializes the TCM memory
  */
 void __init tcm_init(void)
@@ -204,9 +278,18 @@ void __init tcm_init(void)
 	}
 
 	tcm_status = read_cpuid_tcmstatus();
+
+	/*
+	 * This code only supports v6-compatible TCMTR implementations.
+	 */
+	if (tcm_status & TCMTR_FORMAT_MASK)
+		return;
+
 	dtcm_banks = (tcm_status >> 16) & 0x03;
 	itcm_banks = (tcm_status & 0x03);
 
+	register_undef_hook(&tcm_hook);
+
 	/* Values greater than 2 for D/ITCM banks are "reserved" */
 	if (dtcm_banks > 2)
 		dtcm_banks = 0;
@@ -218,7 +301,7 @@ void __init tcm_init(void)
 		for (i = 0; i < dtcm_banks; i++) {
 			ret = setup_tcm_bank(0, i, dtcm_banks, &dtcm_end);
 			if (ret)
-				return;
+				goto unregister;
 		}
 		/* This means you compiled more code than fits into DTCM */
 		if (dtcm_code_sz > (dtcm_end - DTCM_OFFSET)) {
@@ -227,6 +310,12 @@ void __init tcm_init(void)
 				dtcm_code_sz, (dtcm_end - DTCM_OFFSET));
 			goto no_dtcm;
 		}
+		/*
+		 * This means that the DTCM sizes were 0 or the DTCM banks
+		 * were inaccessible due to TrustZone configuration.
+		 */
+		if (!(dtcm_end - DTCM_OFFSET))
+			goto no_dtcm;
 		dtcm_res.end = dtcm_end - 1;
 		request_resource(&iomem_resource, &dtcm_res);
 		dtcm_iomap[0].length = dtcm_end - DTCM_OFFSET;
@@ -250,15 +339,21 @@ no_dtcm:
 		for (i = 0; i < itcm_banks; i++) {
 			ret = setup_tcm_bank(1, i, itcm_banks, &itcm_end);
 			if (ret)
-				return;
+				goto unregister;
 		}
 		/* This means you compiled more code than fits into ITCM */
 		if (itcm_code_sz > (itcm_end - ITCM_OFFSET)) {
 			pr_info("CPU ITCM: %u bytes of code compiled to "
 				"ITCM but only %lu bytes of ITCM present\n",
 				itcm_code_sz, (itcm_end - ITCM_OFFSET));
-			return;
+			goto unregister;
 		}
+		/*
+		 * This means that the ITCM sizes were 0 or the ITCM banks
+		 * were inaccessible due to TrustZone configuration.
+		 */
+		if (!(itcm_end - ITCM_OFFSET))
+			goto unregister;
 		itcm_res.end = itcm_end - 1;
 		request_resource(&iomem_resource, &itcm_res);
 		itcm_iomap[0].length = itcm_end - ITCM_OFFSET;
@@ -275,6 +370,9 @@ no_dtcm:
 		pr_info("CPU ITCM: %u bytes of code compiled to ITCM but no "
 			"ITCM banks present in CPU\n", itcm_code_sz);
 	}
+
+unregister:
+	unregister_undef_hook(&tcm_hook);
 }
 
 /*
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 3dce1a342030..d358226236f2 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -749,14 +749,6 @@ late_initcall(arm_mrc_hook_init);
 
 #endif
 
-void __bad_xchg(volatile void *ptr, int size)
-{
-	pr_err("xchg: bad data size: pc 0x%p, ptr 0x%p, size %d\n",
-	       __builtin_return_address(0), ptr, size);
-	BUG();
-}
-EXPORT_SYMBOL(__bad_xchg);
-
 /*
  * A data abort trap was taken, but we did not handle the instruction.
  * Try to abort the user program, or panic if it was the kernel.