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

Pull arm64 updates from Will Deacon:
 "Here are the core arm64 updates for 4.1.

  Highlights include a significant rework to head.S (allowing us to boot
  on machines with physical memory at a really high address), an AES
  performance boost on Cortex-A57 and the ability to run a 32-bit
  userspace with 64k pages (although this requires said userspace to be
  built with a recent binutils).

  The head.S rework spilt over into KVM, so there are some changes under
  arch/arm/ which have been acked by Marc Zyngier (KVM co-maintainer).
  In particular, the linker script changes caused us some issues in
  -next, so there are a few merge commits where we had to apply fixes on
  top of a stable branch.

  Other changes include:

   - AES performance boost for Cortex-A57
   - AArch32 (compat) userspace with 64k pages
   - Cortex-A53 erratum workaround for #845719
   - defconfig updates (new platforms, PCI, ...)"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (39 commits)
  arm64: fix midr range for Cortex-A57 erratum 832075
  arm64: errata: add workaround for cortex-a53 erratum #845719
  arm64: Use bool function return values of true/false not 1/0
  arm64: defconfig: updates for 4.1
  arm64: Extract feature parsing code from cpu_errata.c
  arm64: alternative: Allow immediate branch as alternative instruction
  arm64: insn: Add aarch64_insn_decode_immediate
  ARM: kvm: round HYP section to page size instead of log2 upper bound
  ARM: kvm: assert on HYP section boundaries not actual code size
  arm64: head.S: ensure idmap_t0sz is visible
  arm64: pmu: add support for interrupt-affinity property
  dt: pmu: extend ARM PMU binding to allow for explicit interrupt affinity
  arm64: head.S: ensure visibility of page tables
  arm64: KVM: use ID map with increased VA range if required
  arm64: mm: increase VA range of identity map
  ARM: kvm: implement replacement for ld's LOG2CEIL()
  arm64: proc: remove unused cpu_get_pgd macro
  arm64: enforce x1|x2|x3 == 0 upon kernel entry as per boot protocol
  arm64: remove __calc_phys_offset
  arm64: merge __enable_mmu and __turn_mmu_on
  ...

1 files changed, 68 insertions, 10 deletions

diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 25a5308744b1..195991dadc37 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -25,8 +25,10 @@
 #include <linux/irq.h>
 #include <linux/kernel.h>
 #include <linux/export.h>
+#include <linux/of.h>
 #include <linux/perf_event.h>
 #include <linux/platform_device.h>
+#include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/uaccess.h>
 
@@ -322,22 +324,31 @@ out:
 }
 
 static int
-validate_event(struct pmu_hw_events *hw_events,
-	       struct perf_event *event)
+validate_event(struct pmu *pmu, struct pmu_hw_events *hw_events,
+				struct perf_event *event)
 {
-	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
+	struct arm_pmu *armpmu;
 	struct hw_perf_event fake_event = event->hw;
 	struct pmu *leader_pmu = event->group_leader->pmu;
 
 	if (is_software_event(event))
 		return 1;
 
+	/*
+	 * Reject groups spanning multiple HW PMUs (e.g. CPU + CCI). The
+	 * core perf code won't check that the pmu->ctx == leader->ctx
+	 * until after pmu->event_init(event).
+	 */
+	if (event->pmu != pmu)
+		return 0;
+
 	if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF)
 		return 1;
 
 	if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec)
 		return 1;
 
+	armpmu = to_arm_pmu(event->pmu);
 	return armpmu->get_event_idx(hw_events, &fake_event) >= 0;
 }
 
@@ -355,15 +366,15 @@ validate_group(struct perf_event *event)
 	memset(fake_used_mask, 0, sizeof(fake_used_mask));
 	fake_pmu.used_mask = fake_used_mask;
 
-	if (!validate_event(&fake_pmu, leader))
+	if (!validate_event(event->pmu, &fake_pmu, leader))
 		return -EINVAL;
 
 	list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
-		if (!validate_event(&fake_pmu, sibling))
+		if (!validate_event(event->pmu, &fake_pmu, sibling))
 			return -EINVAL;
 	}
 
-	if (!validate_event(&fake_pmu, event))
+	if (!validate_event(event->pmu, &fake_pmu, event))
 		return -EINVAL;
 
 	return 0;
@@ -396,7 +407,12 @@ armpmu_release_hardware(struct arm_pmu *armpmu)
 		free_percpu_irq(irq, &cpu_hw_events);
 	} else {
 		for (i = 0; i < irqs; ++i) {
-			if (!cpumask_test_and_clear_cpu(i, &armpmu->active_irqs))
+			int cpu = i;
+
+			if (armpmu->irq_affinity)
+				cpu = armpmu->irq_affinity[i];
+
+			if (!cpumask_test_and_clear_cpu(cpu, &armpmu->active_irqs))
 				continue;
 			irq = platform_get_irq(pmu_device, i);
 			if (irq > 0)
@@ -450,19 +466,24 @@ armpmu_reserve_hardware(struct arm_pmu *armpmu)
 		on_each_cpu(armpmu_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 (armpmu->irq_affinity)
+				cpu = armpmu->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(i)) && irqs > 1) {
+			if (irq_set_affinity(irq, cpumask_of(cpu)) && irqs > 1) {
 				pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
-						irq, i);
+						irq, cpu);
 				continue;
 			}
 
@@ -476,7 +497,7 @@ armpmu_reserve_hardware(struct arm_pmu *armpmu)
 				return err;
 			}
 
-			cpumask_set_cpu(i, &armpmu->active_irqs);
+			cpumask_set_cpu(cpu, &armpmu->active_irqs);
 		}
 	}
 
@@ -1289,9 +1310,46 @@ static const struct of_device_id armpmu_of_device_ids[] = {
 
 static int armpmu_device_probe(struct platform_device *pdev)
 {
+	int i, *irqs;
+
 	if (!cpu_pmu)
 		return -ENODEV;
 
+	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(dn), 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);
+
 	cpu_pmu->plat_device = pdev;
 	return 0;
 }