diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c
index 57058ac46f49733887e439012afa3247f03e1737..7e5d7a083707074b639dc35ba18c40a14312a38c 100644
--- a/arch/arm/mach-ux500/cpu-db8500.c
+++ b/arch/arm/mach-ux500/cpu-db8500.c
@@ -23,7 +23,6 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
-#include <linux/perf/arm_pmu.h>
 #include <linux/regulator/machine.h>
 
 #include <asm/outercache.h>
@@ -112,37 +111,6 @@ static void ux500_restart(enum reboot_mode mode, const char *cmd)
 	prcmu_system_reset(0);
 }
 
-/*
- * The PMU IRQ lines of two cores are wired together into a single interrupt.
- * Bounce the interrupt to the other core if it's not ours.
- */
-static irqreturn_t db8500_pmu_handler(int irq, void *dev, irq_handler_t handler)
-{
-	irqreturn_t ret = handler(irq, dev);
-	int other = !smp_processor_id();
-
-	if (ret == IRQ_NONE && cpu_online(other))
-		irq_set_affinity(irq, cpumask_of(other));
-
-	/*
-	 * We should be able to get away with the amount of IRQ_NONEs we give,
-	 * while still having the spurious IRQ detection code kick in if the
-	 * interrupt really starts hitting spuriously.
-	 */
-	return ret;
-}
-
-static struct arm_pmu_platdata db8500_pmu_platdata = {
-	.handle_irq		= db8500_pmu_handler,
-	.irq_flags		= IRQF_NOBALANCING | IRQF_NO_THREAD,
-};
-
-static struct of_dev_auxdata u8500_auxdata_lookup[] __initdata = {
-	/* Requires call-back bindings. */
-	OF_DEV_AUXDATA("arm,cortex-a9-pmu", 0, "arm-pmu", &db8500_pmu_platdata),
-	{},
-};
-
 static struct of_dev_auxdata u8540_auxdata_lookup[] __initdata = {
 	OF_DEV_AUXDATA("stericsson,db8500-prcmu", 0x80157000, "db8500-prcmu", NULL),
 	{},
@@ -165,9 +133,6 @@ static void __init u8500_init_machine(void)
 	if (of_machine_is_compatible("st-ericsson,u8540"))
 		of_platform_populate(NULL, u8500_local_bus_nodes,
 				     u8540_auxdata_lookup, NULL);
-	else
-		of_platform_populate(NULL, u8500_local_bus_nodes,
-				     u8500_auxdata_lookup, NULL);
 }
 
 static const char * stericsson_dt_platform_compat[] = {
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index eda8c5f629fc8553af2cdccaede5dfd209cecf94..350c76a1d15ba7b6d8935928305aa80f53d9649e 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -20,7 +20,7 @@
 
 #define MPIDR_UP_BITMASK	(0x1 << 30)
 #define MPIDR_MT_BITMASK	(0x1 << 24)
-#define MPIDR_HWID_BITMASK	0xff00ffffffUL
+#define MPIDR_HWID_BITMASK	UL(0xff00ffffff)
 
 #define MPIDR_LEVEL_BITS_SHIFT	3
 #define MPIDR_LEVEL_BITS	(1 << MPIDR_LEVEL_BITS_SHIFT)
diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h
index 472ef944e93260be2faad4182431331e21bc3569..902f9edacbea94b96a85321ff79d45e8ac59fd73 100644
--- a/arch/arm64/include/asm/stacktrace.h
+++ b/arch/arm64/include/asm/stacktrace.h
@@ -28,7 +28,7 @@ struct stackframe {
 	unsigned long fp;
 	unsigned long pc;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	unsigned int graph;
+	int graph;
 #endif
 };
 
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 543e11f0f657e932aa17916a0750f7d83cf5d7b8..e66b0fca99c2f9e500788db6fa2e24693ade11c3 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -72,15 +72,15 @@ static inline void set_fs(mm_segment_t fs)
  * This is equivalent to the following test:
  * (u65)addr + (u65)size <= (u65)current->addr_limit + 1
  */
-static inline unsigned long __range_ok(unsigned long addr, unsigned long size)
+static inline unsigned long __range_ok(const void __user *addr, unsigned long size)
 {
-	unsigned long limit = current_thread_info()->addr_limit;
+	unsigned long ret, limit = current_thread_info()->addr_limit;
 
 	__chk_user_ptr(addr);
 	asm volatile(
 	// A + B <= C + 1 for all A,B,C, in four easy steps:
 	// 1: X = A + B; X' = X % 2^64
-	"	adds	%0, %0, %2\n"
+	"	adds	%0, %3, %2\n"
 	// 2: Set C = 0 if X > 2^64, to guarantee X' > C in step 4
 	"	csel	%1, xzr, %1, hi\n"
 	// 3: Set X' = ~0 if X >= 2^64. For X == 2^64, this decrements X'
@@ -92,9 +92,9 @@ static inline unsigned long __range_ok(unsigned long addr, unsigned long size)
 	//    testing X' - C == 0, subject to the previous adjustments.
 	"	sbcs	xzr, %0, %1\n"
 	"	cset	%0, ls\n"
-	: "+r" (addr), "+r" (limit) : "Ir" (size) : "cc");
+	: "=&r" (ret), "+r" (limit) : "Ir" (size), "0" (addr) : "cc");
 
-	return addr;
+	return ret;
 }
 
 /*
@@ -104,7 +104,7 @@ static inline unsigned long __range_ok(unsigned long addr, unsigned long size)
  */
 #define untagged_addr(addr)		sign_extend64(addr, 55)
 
-#define access_ok(type, addr, size)	__range_ok((unsigned long)(addr), size)
+#define access_ok(type, addr, size)	__range_ok(addr, size)
 #define user_addr_max			get_fs
 
 #define _ASM_EXTABLE(from, to)						\
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index c33b5e4010ab7660140025f9c17d6be10b66706d..68450e954d47d7d241740d0de4ca3b9d2df53b75 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -370,6 +370,7 @@ static unsigned int __kprobes aarch32_check_condition(u32 opcode, u32 psr)
 static int swp_handler(struct pt_regs *regs, u32 instr)
 {
 	u32 destreg, data, type, address = 0;
+	const void __user *user_ptr;
 	int rn, rt2, res = 0;
 
 	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, regs->pc);
@@ -401,7 +402,8 @@ static int swp_handler(struct pt_regs *regs, u32 instr)
 		aarch32_insn_extract_reg_num(instr, A32_RT2_OFFSET), data);
 
 	/* Check access in reasonable access range for both SWP and SWPB */
-	if (!access_ok(VERIFY_WRITE, (address & ~3), 4)) {
+	user_ptr = (const void __user *)(unsigned long)(address & ~3);
+	if (!access_ok(VERIFY_WRITE, user_ptr, 4)) {
 		pr_debug("SWP{B} emulation: access to 0x%08x not allowed!\n",
 			address);
 		goto fault;
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 29b1f873e337fb6a423c3406c02d43af18bc4847..2985a067fc131c468b7213ed1a5b0ec6548fb1c8 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -199,9 +199,11 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = {
 };
 
 static const struct arm64_ftr_bits ftr_ctr[] = {
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, 31, 1, 1),	/* RAO */
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, 31, 1, 1),		/* RES1 */
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 29, 1, 1),	/* DIC */
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 28, 1, 1),	/* IDC */
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, 24, 4, 0),	/* CWG */
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0),	/* ERG */
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, 20, 4, 0),	/* ERG */
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 1),	/* DminLine */
 	/*
 	 * Linux can handle differing I-cache policies. Userspace JITs will
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 75b220ba73a3234b7815062537e9367d36e6a040..85a251b6dfa840dd41e852683cec4032b6a9f0d9 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -908,9 +908,9 @@ static void __armv8pmu_probe_pmu(void *info)
 	int pmuver;
 
 	dfr0 = read_sysreg(id_aa64dfr0_el1);
-	pmuver = cpuid_feature_extract_signed_field(dfr0,
+	pmuver = cpuid_feature_extract_unsigned_field(dfr0,
 			ID_AA64DFR0_PMUVER_SHIFT);
-	if (pmuver < 1)
+	if (pmuver == 0xf || pmuver == 0)
 		return;
 
 	probe->present = true;
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index ad8aeb098b31ed5887aa98a438622bb2304abe97..c0da6efe546558a0b4fc7c75c63a585ff37832ea 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -220,8 +220,15 @@ void __show_regs(struct pt_regs *regs)
 
 	show_regs_print_info(KERN_DEFAULT);
 	print_pstate(regs);
-	printk("pc : %pS\n", (void *)regs->pc);
-	printk("lr : %pS\n", (void *)lr);
+
+	if (!user_mode(regs)) {
+		printk("pc : %pS\n", (void *)regs->pc);
+		printk("lr : %pS\n", (void *)lr);
+	} else {
+		printk("pc : %016llx\n", regs->pc);
+		printk("lr : %016llx\n", lr);
+	}
+
 	printk("sp : %016llx\n", sp);
 
 	i = top_reg;
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 76809ccd309ccaf330e45ac4b814922ae5949624..d5718a060672e1696618904c8844447daa042007 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -59,6 +59,11 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	if (tsk->ret_stack &&
 			(frame->pc == (unsigned long)return_to_handler)) {
+		if (WARN_ON_ONCE(frame->graph == -1))
+			return -EINVAL;
+		if (frame->graph < -1)
+			frame->graph += FTRACE_NOTRACE_DEPTH;
+
 		/*
 		 * This is a case where function graph tracer has
 		 * modified a return address (LR) in a stack frame
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index 8b8bbd3eaa52cc8df71d66ab1063427232319692..a382b2a1b84e3204b5794fb5f367ac15a0bddf43 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -57,7 +57,7 @@ do_compat_cache_op(unsigned long start, unsigned long end, int flags)
 	if (end < start || flags)
 		return -EINVAL;
 
-	if (!access_ok(VERIFY_READ, start, end - start))
+	if (!access_ok(VERIFY_READ, (const void __user *)start, end - start))
 		return -EFAULT;
 
 	return __do_compat_cache_op(start, end);
diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c
index a4391280fba9631d69cf8bda434c307956b92668..f258636273c9588dca80420341a3627cfdd61d2c 100644
--- a/arch/arm64/kernel/time.c
+++ b/arch/arm64/kernel/time.c
@@ -52,7 +52,7 @@ unsigned long profile_pc(struct pt_regs *regs)
 	frame.fp = regs->regs[29];
 	frame.pc = regs->pc;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	frame.graph = -1; /* no task info */
+	frame.graph = current->curr_ret_stack;
 #endif
 	do {
 		int ret = unwind_frame(NULL, &frame);
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index bbb0fde2780ef780cd3c2de7a071691556d5ce6d..eb2d15147e8d3bb2be8731400990f18979022fce 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -57,7 +57,7 @@ static const char *handler[]= {
 	"Error"
 };
 
-int show_unhandled_signals = 1;
+int show_unhandled_signals = 0;
 
 static void dump_backtrace_entry(unsigned long where)
 {
@@ -526,14 +526,6 @@ asmlinkage long do_ni_syscall(struct pt_regs *regs)
 	}
 #endif
 
-	if (show_unhandled_signals_ratelimited()) {
-		pr_info("%s[%d]: syscall %d\n", current->comm,
-			task_pid_nr(current), regs->syscallno);
-		dump_instr("", regs);
-		if (user_mode(regs))
-			__show_regs(regs);
-	}
-
 	return sys_ni_syscall();
 }
 
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 3161b853f29e1d35a21b0da5a01f571c995616f3..84a019f5502293dbe0c28cc078465e4ddd6c2096 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -933,6 +933,11 @@ int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot)
 {
 	pgprot_t sect_prot = __pgprot(PUD_TYPE_SECT |
 					pgprot_val(mk_sect_prot(prot)));
+
+	/* ioremap_page_range doesn't honour BBM */
+	if (pud_present(READ_ONCE(*pudp)))
+		return 0;
+
 	BUG_ON(phys & ~PUD_MASK);
 	set_pud(pudp, pfn_pud(__phys_to_pfn(phys), sect_prot));
 	return 1;
@@ -942,6 +947,11 @@ int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot)
 {
 	pgprot_t sect_prot = __pgprot(PMD_TYPE_SECT |
 					pgprot_val(mk_sect_prot(prot)));
+
+	/* ioremap_page_range doesn't honour BBM */
+	if (pmd_present(READ_ONCE(*pmdp)))
+		return 0;
+
 	BUG_ON(phys & ~PMD_MASK);
 	set_pmd(pmdp, pfn_pmd(__phys_to_pfn(phys), sect_prot));
 	return 1;
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index 7bc5eee96b310756f625499b805385f2ea95689a..0c2ed11c0603015e10c3995f21a768801fe90427 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -17,7 +17,6 @@
 #include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/perf/arm_pmu.h>
-#include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/sched/clock.h>
 #include <linux/spinlock.h>
@@ -26,6 +25,9 @@
 
 #include <asm/irq_regs.h>
 
+static DEFINE_PER_CPU(struct arm_pmu *, cpu_armpmu);
+static DEFINE_PER_CPU(int, cpu_irq);
+
 static int
 armpmu_map_cache_event(const unsigned (*cache_map)
 				      [PERF_COUNT_HW_CACHE_MAX]
@@ -320,17 +322,9 @@ validate_group(struct perf_event *event)
 	return 0;
 }
 
-static struct arm_pmu_platdata *armpmu_get_platdata(struct arm_pmu *armpmu)
-{
-	struct platform_device *pdev = armpmu->plat_device;
-
-	return pdev ? dev_get_platdata(&pdev->dev) : NULL;
-}
-
 static irqreturn_t armpmu_dispatch_irq(int irq, void *dev)
 {
 	struct arm_pmu *armpmu;
-	struct arm_pmu_platdata *plat;
 	int ret;
 	u64 start_clock, finish_clock;
 
@@ -341,14 +335,11 @@ static irqreturn_t armpmu_dispatch_irq(int irq, void *dev)
 	 * dereference.
 	 */
 	armpmu = *(void **)dev;
-
-	plat = armpmu_get_platdata(armpmu);
+	if (WARN_ON_ONCE(!armpmu))
+		return IRQ_NONE;
 
 	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);
+	ret = armpmu->handle_irq(irq, armpmu);
 	finish_clock = sched_clock();
 
 	perf_sample_event_took(finish_clock - start_clock);
@@ -531,54 +522,41 @@ int perf_num_counters(void)
 }
 EXPORT_SYMBOL_GPL(perf_num_counters);
 
-void armpmu_free_irq(struct arm_pmu *armpmu, int cpu)
+static int armpmu_count_irq_users(const int irq)
 {
-	struct pmu_hw_events __percpu *hw_events = armpmu->hw_events;
-	int irq = per_cpu(hw_events->irq, cpu);
+	int cpu, count = 0;
 
-	if (!cpumask_test_and_clear_cpu(cpu, &armpmu->active_irqs))
-		return;
-
-	if (irq_is_percpu_devid(irq)) {
-		free_percpu_irq(irq, &hw_events->percpu_pmu);
-		cpumask_clear(&armpmu->active_irqs);
-		return;
+	for_each_possible_cpu(cpu) {
+		if (per_cpu(cpu_irq, cpu) == irq)
+			count++;
 	}
 
-	free_irq(irq, per_cpu_ptr(&hw_events->percpu_pmu, cpu));
+	return count;
 }
 
-void armpmu_free_irqs(struct arm_pmu *armpmu)
+void armpmu_free_irq(int irq, int cpu)
 {
-	int cpu;
+	if (per_cpu(cpu_irq, cpu) == 0)
+		return;
+	if (WARN_ON(irq != per_cpu(cpu_irq, cpu)))
+		return;
+
+	if (!irq_is_percpu_devid(irq))
+		free_irq(irq, per_cpu_ptr(&cpu_armpmu, cpu));
+	else if (armpmu_count_irq_users(irq) == 1)
+		free_percpu_irq(irq, &cpu_armpmu);
 
-	for_each_cpu(cpu, &armpmu->supported_cpus)
-		armpmu_free_irq(armpmu, cpu);
+	per_cpu(cpu_irq, cpu) = 0;
 }
 
-int armpmu_request_irq(struct arm_pmu *armpmu, int cpu)
+int armpmu_request_irq(int irq, int cpu)
 {
 	int err = 0;
-	struct pmu_hw_events __percpu *hw_events = armpmu->hw_events;
 	const irq_handler_t handler = armpmu_dispatch_irq;
-	int irq = per_cpu(hw_events->irq, cpu);
 	if (!irq)
 		return 0;
 
-	if (irq_is_percpu_devid(irq) && cpumask_empty(&armpmu->active_irqs)) {
-		err = request_percpu_irq(irq, handler, "arm-pmu",
-					 &hw_events->percpu_pmu);
-	} else if (irq_is_percpu_devid(irq)) {
-		int other_cpu = cpumask_first(&armpmu->active_irqs);
-		int other_irq = per_cpu(hw_events->irq, other_cpu);
-
-		if (irq != other_irq) {
-			pr_warn("mismatched PPIs detected.\n");
-			err = -EINVAL;
-			goto err_out;
-		}
-	} else {
-		struct arm_pmu_platdata *platdata = armpmu_get_platdata(armpmu);
+	if (!irq_is_percpu_devid(irq)) {
 		unsigned long irq_flags;
 
 		err = irq_force_affinity(irq, cpumask_of(cpu));
@@ -589,22 +567,22 @@ int armpmu_request_irq(struct arm_pmu *armpmu, int cpu)
 			goto err_out;
 		}
 
-		if (platdata && platdata->irq_flags) {
-			irq_flags = platdata->irq_flags;
-		} else {
-			irq_flags = IRQF_PERCPU |
-				    IRQF_NOBALANCING |
-				    IRQF_NO_THREAD;
-		}
+		irq_flags = IRQF_PERCPU |
+			    IRQF_NOBALANCING |
+			    IRQF_NO_THREAD;
 
+		irq_set_status_flags(irq, IRQ_NOAUTOEN);
 		err = request_irq(irq, handler, irq_flags, "arm-pmu",
-				  per_cpu_ptr(&hw_events->percpu_pmu, cpu));
+				  per_cpu_ptr(&cpu_armpmu, cpu));
+	} else if (armpmu_count_irq_users(irq) == 0) {
+		err = request_percpu_irq(irq, handler, "arm-pmu",
+					 &cpu_armpmu);
 	}
 
 	if (err)
 		goto err_out;
 
-	cpumask_set_cpu(cpu, &armpmu->active_irqs);
+	per_cpu(cpu_irq, cpu) = irq;
 	return 0;
 
 err_out:
@@ -612,19 +590,6 @@ int armpmu_request_irq(struct arm_pmu *armpmu, int cpu)
 	return err;
 }
 
-int armpmu_request_irqs(struct arm_pmu *armpmu)
-{
-	int cpu, err;
-
-	for_each_cpu(cpu, &armpmu->supported_cpus) {
-		err = armpmu_request_irq(armpmu, cpu);
-		if (err)
-			break;
-	}
-
-	return err;
-}
-
 static int armpmu_get_cpu_irq(struct arm_pmu *pmu, int cpu)
 {
 	struct pmu_hw_events __percpu *hw_events = pmu->hw_events;
@@ -647,12 +612,14 @@ static int arm_perf_starting_cpu(unsigned int cpu, struct hlist_node *node)
 	if (pmu->reset)
 		pmu->reset(pmu);
 
+	per_cpu(cpu_armpmu, cpu) = pmu;
+
 	irq = armpmu_get_cpu_irq(pmu, cpu);
 	if (irq) {
-		if (irq_is_percpu_devid(irq)) {
+		if (irq_is_percpu_devid(irq))
 			enable_percpu_irq(irq, IRQ_TYPE_NONE);
-			return 0;
-		}
+		else
+			enable_irq(irq);
 	}
 
 	return 0;
@@ -667,8 +634,14 @@ static int arm_perf_teardown_cpu(unsigned int cpu, struct hlist_node *node)
 		return 0;
 
 	irq = armpmu_get_cpu_irq(pmu, cpu);
-	if (irq && irq_is_percpu_devid(irq))
-		disable_percpu_irq(irq);
+	if (irq) {
+		if (irq_is_percpu_devid(irq))
+			disable_percpu_irq(irq);
+		else
+			disable_irq(irq);
+	}
+
+	per_cpu(cpu_armpmu, cpu) = NULL;
 
 	return 0;
 }
@@ -800,18 +773,18 @@ static void cpu_pmu_destroy(struct arm_pmu *cpu_pmu)
 					    &cpu_pmu->node);
 }
 
-struct arm_pmu *armpmu_alloc(void)
+static struct arm_pmu *__armpmu_alloc(gfp_t flags)
 {
 	struct arm_pmu *pmu;
 	int cpu;
 
-	pmu = kzalloc(sizeof(*pmu), GFP_KERNEL);
+	pmu = kzalloc(sizeof(*pmu), flags);
 	if (!pmu) {
 		pr_info("failed to allocate PMU device!\n");
 		goto out;
 	}
 
-	pmu->hw_events = alloc_percpu(struct pmu_hw_events);
+	pmu->hw_events = alloc_percpu_gfp(struct pmu_hw_events, flags);
 	if (!pmu->hw_events) {
 		pr_info("failed to allocate per-cpu PMU data.\n");
 		goto out_free_pmu;
@@ -857,6 +830,17 @@ struct arm_pmu *armpmu_alloc(void)
 	return NULL;
 }
 
+struct arm_pmu *armpmu_alloc(void)
+{
+	return __armpmu_alloc(GFP_KERNEL);
+}
+
+struct arm_pmu *armpmu_alloc_atomic(void)
+{
+	return __armpmu_alloc(GFP_ATOMIC);
+}
+
+
 void armpmu_free(struct arm_pmu *pmu)
 {
 	free_percpu(pmu->hw_events);
diff --git a/drivers/perf/arm_pmu_acpi.c b/drivers/perf/arm_pmu_acpi.c
index 705f1a390e3123a2d305e0468cec8194d972ed39..0f197516d7089cf970926501aca996a9ab79a7f8 100644
--- a/drivers/perf/arm_pmu_acpi.c
+++ b/drivers/perf/arm_pmu_acpi.c
@@ -11,6 +11,8 @@
 #include <linux/acpi.h>
 #include <linux/cpumask.h>
 #include <linux/init.h>
+#include <linux/irq.h>
+#include <linux/irqdesc.h>
 #include <linux/percpu.h>
 #include <linux/perf/arm_pmu.h>
 
@@ -87,7 +89,13 @@ static int arm_pmu_acpi_parse_irqs(void)
 			pr_warn("No ACPI PMU IRQ for CPU%d\n", cpu);
 		}
 
+		/*
+		 * Log and request the IRQ so the core arm_pmu code can manage
+		 * it. We'll have to sanity-check IRQs later when we associate
+		 * them with their PMUs.
+		 */
 		per_cpu(pmu_irqs, cpu) = irq;
+		armpmu_request_irq(irq, cpu);
 	}
 
 	return 0;
@@ -127,7 +135,7 @@ static struct arm_pmu *arm_pmu_acpi_find_alloc_pmu(void)
 		return pmu;
 	}
 
-	pmu = armpmu_alloc();
+	pmu = armpmu_alloc_atomic();
 	if (!pmu) {
 		pr_warn("Unable to allocate PMU for CPU%d\n",
 			smp_processor_id());
@@ -139,6 +147,35 @@ static struct arm_pmu *arm_pmu_acpi_find_alloc_pmu(void)
 	return pmu;
 }
 
+/*
+ * Check whether the new IRQ is compatible with those already associated with
+ * the PMU (e.g. we don't have mismatched PPIs).
+ */
+static bool pmu_irq_matches(struct arm_pmu *pmu, int irq)
+{
+	struct pmu_hw_events __percpu *hw_events = pmu->hw_events;
+	int cpu;
+
+	if (!irq)
+		return true;
+
+	for_each_cpu(cpu, &pmu->supported_cpus) {
+		int other_irq = per_cpu(hw_events->irq, cpu);
+		if (!other_irq)
+			continue;
+
+		if (irq == other_irq)
+			continue;
+		if (!irq_is_percpu_devid(irq) && !irq_is_percpu_devid(other_irq))
+			continue;
+
+		pr_warn("mismatched PPIs detected\n");
+		return false;
+	}
+
+	return true;
+}
+
 /*
  * This must run before the common arm_pmu hotplug logic, so that we can
  * associate a CPU and its interrupt before the common code tries to manage the
@@ -164,19 +201,14 @@ static int arm_pmu_acpi_cpu_starting(unsigned int cpu)
 	if (!pmu)
 		return -ENOMEM;
 
-	cpumask_set_cpu(cpu, &pmu->supported_cpus);
-
 	per_cpu(probed_pmus, cpu) = pmu;
 
-	/*
-	 * Log and request the IRQ so the core arm_pmu code can manage it.  In
-	 * some situations (e.g. mismatched PPIs), we may fail to request the
-	 * IRQ. However, it may be too late for us to do anything about it.
-	 * The common ARM PMU code will log a warning in this case.
-	 */
-	hw_events = pmu->hw_events;
-	per_cpu(hw_events->irq, cpu) = irq;
-	armpmu_request_irq(pmu, cpu);
+	if (pmu_irq_matches(pmu, irq)) {
+		hw_events = pmu->hw_events;
+		per_cpu(hw_events->irq, cpu) = irq;
+	}
+
+	cpumask_set_cpu(cpu, &pmu->supported_cpus);
 
 	/*
 	 * Ideally, we'd probe the PMU here when we find the first matching
@@ -247,11 +279,6 @@ static int arm_pmu_acpi_init(void)
 	if (acpi_disabled)
 		return 0;
 
-	/*
-	 * We can't request IRQs yet, since we don't know the cookie value
-	 * until we know which CPUs share the same logical PMU. We'll handle
-	 * that in arm_pmu_acpi_cpu_starting().
-	 */
 	ret = arm_pmu_acpi_parse_irqs();
 	if (ret)
 		return ret;
diff --git a/drivers/perf/arm_pmu_platform.c b/drivers/perf/arm_pmu_platform.c
index 46501cc79fd7c3f3b0ac4557ce4a06811636f338..7729eda5909df180ae686ee8206e35a75b9ca476 100644
--- a/drivers/perf/arm_pmu_platform.c
+++ b/drivers/perf/arm_pmu_platform.c
@@ -127,13 +127,6 @@ static int pmu_parse_irqs(struct arm_pmu *pmu)
 			pdev->dev.of_node);
 	}
 
-	/*
-	 * Some platforms have all PMU IRQs OR'd into a single IRQ, with a
-	 * special platdata function that attempts to demux them.
-	 */
-	if (dev_get_platdata(&pdev->dev))
-		cpumask_setall(&pmu->supported_cpus);
-
 	for (i = 0; i < num_irqs; i++) {
 		int cpu, irq;
 
@@ -164,6 +157,36 @@ static int pmu_parse_irqs(struct arm_pmu *pmu)
 	return 0;
 }
 
+static int armpmu_request_irqs(struct arm_pmu *armpmu)
+{
+	struct pmu_hw_events __percpu *hw_events = armpmu->hw_events;
+	int cpu, err;
+
+	for_each_cpu(cpu, &armpmu->supported_cpus) {
+		int irq = per_cpu(hw_events->irq, cpu);
+		if (!irq)
+			continue;
+
+		err = armpmu_request_irq(irq, cpu);
+		if (err)
+			break;
+	}
+
+	return err;
+}
+
+static void armpmu_free_irqs(struct arm_pmu *armpmu)
+{
+	int cpu;
+	struct pmu_hw_events __percpu *hw_events = armpmu->hw_events;
+
+	for_each_cpu(cpu, &armpmu->supported_cpus) {
+		int irq = per_cpu(hw_events->irq, cpu);
+
+		armpmu_free_irq(irq, cpu);
+	}
+}
+
 int arm_pmu_device_probe(struct platform_device *pdev,
 			 const struct of_device_id *of_table,
 			 const struct pmu_probe_info *probe_table)
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index af0f44effd44abc067d7f31e498c433fd061725e..40036a57d072f28dbdd9de54e7d1972d37072d64 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -14,26 +14,10 @@
 
 #include <linux/interrupt.h>
 #include <linux/perf_event.h>
+#include <linux/platform_device.h>
 #include <linux/sysfs.h>
 #include <asm/cputype.h>
 
-/*
- * struct arm_pmu_platdata - ARM PMU platform data
- *
- * @handle_irq: an optional handler which will be called from the
- *	interrupt and passed the address of the low level handler,
- *	and can be used to implement any platform specific handling
- *	before or after calling it.
- *
- * @irq_flags: if non-zero, these flags will be passed to request_irq
- *             when requesting interrupts for this PMU device.
- */
-struct arm_pmu_platdata {
-	irqreturn_t (*handle_irq)(int irq, void *dev,
-				  irq_handler_t pmu_handler);
-	unsigned long irq_flags;
-};
-
 #ifdef CONFIG_ARM_PMU
 
 /*
@@ -92,7 +76,6 @@ enum armpmu_attr_groups {
 
 struct arm_pmu {
 	struct pmu	pmu;
-	cpumask_t	active_irqs;
 	cpumask_t	supported_cpus;
 	char		*name;
 	irqreturn_t	(*handle_irq)(int irq_num, void *dev);
@@ -174,12 +157,11 @@ static inline int arm_pmu_acpi_probe(armpmu_init_fn init_fn) { return 0; }
 
 /* Internal functions only for core arm_pmu code */
 struct arm_pmu *armpmu_alloc(void);
+struct arm_pmu *armpmu_alloc_atomic(void);
 void armpmu_free(struct arm_pmu *pmu);
 int armpmu_register(struct arm_pmu *pmu);
-int armpmu_request_irqs(struct arm_pmu *armpmu);
-void armpmu_free_irqs(struct arm_pmu *armpmu);
-int armpmu_request_irq(struct arm_pmu *armpmu, int cpu);
-void armpmu_free_irq(struct arm_pmu *armpmu, int cpu);
+int armpmu_request_irq(int irq, int cpu);
+void armpmu_free_irq(int irq, int cpu);
 
 #define ARMV8_PMU_PDEV_NAME "armv8-pmu"