Merge tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 fixes from Catalin Marinas:
 "arm64 and perf fixes:

   - build error when accessing MPIDR_HWID_BITMASK from .S

   - fix CTR_EL0 field definitions

   - remove/disable some kernel messages on user faults (unhandled
     signals, unimplemented syscalls)

   - fix kernel page fault in unwind_frame() with function graph tracing

   - fix perf sleeping while atomic errors when booting with ACPI"

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: fix unwind_frame() for filtered out fn for function graph tracing
  arm64: Enforce BBM for huge IO/VMAP mappings
  arm64: perf: correct PMUVer probing
  arm_pmu: acpi: request IRQs up-front
  arm_pmu: note IRQs and PMUs per-cpu
  arm_pmu: explicitly enable/disable SPIs at hotplug
  arm_pmu: acpi: check for mismatched PPIs
  arm_pmu: add armpmu_alloc_atomic()
  arm_pmu: fold platform helpers into platform code
  arm_pmu: kill arm_pmu_platdata
  ARM: ux500: remove PMU IRQ bouncer
  arm64: __show_regs: Only resolve kernel symbols when running at EL1
  arm64: Remove unimplemented syscall log message
  arm64: Disable unhandled signal log messages by default
  arm64: cpufeature: Fix CTR_EL0 field definitions
  arm64: uaccess: Formalise types for access_ok()
  arm64: Fix compilation error while accessing MPIDR_HWID_BITMASK from .S files

3 files changed, 135 insertions, 101 deletions

diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index 7bc5eee96b31..0c2ed11c0603 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 @@ err_out:
 	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 @@ out:
 	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 705f1a390e31..0f197516d708 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());
@@ -140,6 +148,35 @@ static struct arm_pmu *arm_pmu_acpi_find_alloc_pmu(void)
 }
 
 /*
+ * 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
  * affinity and so on.
@@ -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 46501cc79fd7..7729eda5909d 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)