Merge branch 'linus' into x86/fpu, to resolve conflicts

 Conflicts:
	arch/x86/kernel/fpu/core.c

Signed-off-by: Ingo Molnar <mingo@kernel.org>

7 files changed, 88 insertions, 28 deletions

diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
index 6e9c40eea208..69ccce308458 100644
--- a/virt/kvm/arm/pmu.c
+++ b/virt/kvm/arm/pmu.c
@@ -305,7 +305,7 @@ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val)
 			continue;
 		type = vcpu_sys_reg(vcpu, PMEVTYPER0_EL0 + i)
 		       & ARMV8_PMU_EVTYPE_EVENT;
-		if ((type == ARMV8_PMU_EVTYPE_EVENT_SW_INCR)
+		if ((type == ARMV8_PMUV3_PERFCTR_SW_INCR)
 		    && (enable & BIT(i))) {
 			reg = vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) + 1;
 			reg = lower_32_bits(reg);
@@ -379,7 +379,8 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
 	eventsel = data & ARMV8_PMU_EVTYPE_EVENT;
 
 	/* Software increment event does't need to be backed by a perf event */
-	if (eventsel == ARMV8_PMU_EVTYPE_EVENT_SW_INCR)
+	if (eventsel == ARMV8_PMUV3_PERFCTR_SW_INCR &&
+	    select_idx != ARMV8_PMU_CYCLE_IDX)
 		return;
 
 	memset(&attr, 0, sizeof(struct perf_event_attr));
@@ -391,7 +392,8 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
 	attr.exclude_kernel = data & ARMV8_PMU_EXCLUDE_EL1 ? 1 : 0;
 	attr.exclude_hv = 1; /* Don't count EL2 events */
 	attr.exclude_host = 1; /* Don't count host events */
-	attr.config = eventsel;
+	attr.config = (select_idx == ARMV8_PMU_CYCLE_IDX) ?
+		ARMV8_PMUV3_PERFCTR_CPU_CYCLES : eventsel;
 
 	counter = kvm_pmu_get_counter_value(vcpu, select_idx);
 	/* The initial sample period (overflow count) of an event. */
diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c
index e18b30ddcdce..ebe1b9fa3c4d 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.c
+++ b/virt/kvm/arm/vgic/vgic-mmio.c
@@ -453,17 +453,33 @@ struct vgic_io_device *kvm_to_vgic_iodev(const struct kvm_io_device *dev)
 	return container_of(dev, struct vgic_io_device, dev);
 }
 
-static bool check_region(const struct vgic_register_region *region,
+static bool check_region(const struct kvm *kvm,
+			 const struct vgic_register_region *region,
 			 gpa_t addr, int len)
 {
-	if ((region->access_flags & VGIC_ACCESS_8bit) && len == 1)
-		return true;
-	if ((region->access_flags & VGIC_ACCESS_32bit) &&
-	    len == sizeof(u32) && !(addr & 3))
-		return true;
-	if ((region->access_flags & VGIC_ACCESS_64bit) &&
-	    len == sizeof(u64) && !(addr & 7))
-		return true;
+	int flags, nr_irqs = kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS;
+
+	switch (len) {
+	case sizeof(u8):
+		flags = VGIC_ACCESS_8bit;
+		break;
+	case sizeof(u32):
+		flags = VGIC_ACCESS_32bit;
+		break;
+	case sizeof(u64):
+		flags = VGIC_ACCESS_64bit;
+		break;
+	default:
+		return false;
+	}
+
+	if ((region->access_flags & flags) && IS_ALIGNED(addr, len)) {
+		if (!region->bits_per_irq)
+			return true;
+
+		/* Do we access a non-allocated IRQ? */
+		return VGIC_ADDR_TO_INTID(addr, region->bits_per_irq) < nr_irqs;
+	}
 
 	return false;
 }
@@ -477,7 +493,7 @@ static int dispatch_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
 
 	region = vgic_find_mmio_region(iodev->regions, iodev->nr_regions,
 				       addr - iodev->base_addr);
-	if (!region || !check_region(region, addr, len)) {
+	if (!region || !check_region(vcpu->kvm, region, addr, len)) {
 		memset(val, 0, len);
 		return 0;
 	}
@@ -510,10 +526,7 @@ static int dispatch_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
 
 	region = vgic_find_mmio_region(iodev->regions, iodev->nr_regions,
 				       addr - iodev->base_addr);
-	if (!region)
-		return 0;
-
-	if (!check_region(region, addr, len))
+	if (!region || !check_region(vcpu->kvm, region, addr, len))
 		return 0;
 
 	switch (iodev->iodev_type) {
diff --git a/virt/kvm/arm/vgic/vgic-mmio.h b/virt/kvm/arm/vgic/vgic-mmio.h
index 4c34d39d44a0..84961b4e4422 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.h
+++ b/virt/kvm/arm/vgic/vgic-mmio.h
@@ -50,15 +50,15 @@ extern struct kvm_io_device_ops kvm_io_gic_ops;
 #define VGIC_ADDR_IRQ_MASK(bits) (((bits) * 1024 / 8) - 1)
 
 /*
- * (addr & mask) gives us the byte offset for the INT ID, so we want to
- * divide this with 'bytes per irq' to get the INT ID, which is given
- * by '(bits) / 8'.  But we do this with fixed-point-arithmetic and
- * take advantage of the fact that division by a fraction equals
- * multiplication with the inverted fraction, and scale up both the
- * numerator and denominator with 8 to support at most 64 bits per IRQ:
+ * (addr & mask) gives us the _byte_ offset for the INT ID.
+ * We multiply this by 8 the get the _bit_ offset, then divide this by
+ * the number of bits to learn the actual INT ID.
+ * But instead of a division (which requires a "long long div" implementation),
+ * we shift by the binary logarithm of <bits>.
+ * This assumes that <bits> is a power of two.
  */
 #define VGIC_ADDR_TO_INTID(addr, bits)  (((addr) & VGIC_ADDR_IRQ_MASK(bits)) * \
-					64 / (bits) / 8)
+					8 >> ilog2(bits))
 
 /*
  * Some VGIC registers store per-IRQ information, with a different number
diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c
index 2893d5ba523a..6440b56ec90e 100644
--- a/virt/kvm/arm/vgic/vgic.c
+++ b/virt/kvm/arm/vgic/vgic.c
@@ -273,6 +273,18 @@ retry:
 		 * no more work for us to do.
 		 */
 		spin_unlock(&irq->irq_lock);
+
+		/*
+		 * We have to kick the VCPU here, because we could be
+		 * queueing an edge-triggered interrupt for which we
+		 * get no EOI maintenance interrupt. In that case,
+		 * while the IRQ is already on the VCPU's AP list, the
+		 * VCPU could have EOI'ed the original interrupt and
+		 * won't see this one until it exits for some other
+		 * reason.
+		 */
+		if (vcpu)
+			kvm_vcpu_kick(vcpu);
 		return false;
 	}
 
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index 8035cc1eb955..efeceb0a222d 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -91,6 +91,7 @@ static void async_pf_execute(struct work_struct *work)
 
 	spin_lock(&vcpu->async_pf.lock);
 	list_add_tail(&apf->link, &vcpu->async_pf.done);
+	apf->vcpu = NULL;
 	spin_unlock(&vcpu->async_pf.lock);
 
 	/*
@@ -113,6 +114,8 @@ static void async_pf_execute(struct work_struct *work)
 
 void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
 {
+	spin_lock(&vcpu->async_pf.lock);
+
 	/* cancel outstanding work queue item */
 	while (!list_empty(&vcpu->async_pf.queue)) {
 		struct kvm_async_pf *work =
@@ -120,6 +123,14 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
 					 typeof(*work), queue);
 		list_del(&work->queue);
 
+		/*
+		 * We know it's present in vcpu->async_pf.done, do
+		 * nothing here.
+		 */
+		if (!work->vcpu)
+			continue;
+
+		spin_unlock(&vcpu->async_pf.lock);
 #ifdef CONFIG_KVM_ASYNC_PF_SYNC
 		flush_work(&work->work);
 #else
@@ -129,9 +140,9 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
 			kmem_cache_free(async_pf_cache, work);
 		}
 #endif
+		spin_lock(&vcpu->async_pf.lock);
 	}
 
-	spin_lock(&vcpu->async_pf.lock);
 	while (!list_empty(&vcpu->async_pf.done)) {
 		struct kvm_async_pf *work =
 			list_first_entry(&vcpu->async_pf.done,
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index f397e9b20370..a29786dd9522 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -42,6 +42,7 @@
 
 #ifdef CONFIG_HAVE_KVM_IRQFD
 
+static struct workqueue_struct *irqfd_cleanup_wq;
 
 static void
 irqfd_inject(struct work_struct *work)
@@ -167,7 +168,7 @@ irqfd_deactivate(struct kvm_kernel_irqfd *irqfd)
 
 	list_del_init(&irqfd->list);
 
-	schedule_work(&irqfd->shutdown);
+	queue_work(irqfd_cleanup_wq, &irqfd->shutdown);
 }
 
 int __attribute__((weak)) kvm_arch_set_irq_inatomic(
@@ -554,7 +555,7 @@ kvm_irqfd_deassign(struct kvm *kvm, struct kvm_irqfd *args)
 	 * so that we guarantee there will not be any more interrupts on this
 	 * gsi once this deassign function returns.
 	 */
-	flush_work(&irqfd->shutdown);
+	flush_workqueue(irqfd_cleanup_wq);
 
 	return 0;
 }
@@ -591,7 +592,7 @@ kvm_irqfd_release(struct kvm *kvm)
 	 * Block until we know all outstanding shutdown jobs have completed
 	 * since we do not take a kvm* reference.
 	 */
-	flush_work(&irqfd->shutdown);
+	flush_workqueue(irqfd_cleanup_wq);
 
 }
 
@@ -621,8 +622,23 @@ void kvm_irq_routing_update(struct kvm *kvm)
 	spin_unlock_irq(&kvm->irqfds.lock);
 }
 
+/*
+ * create a host-wide workqueue for issuing deferred shutdown requests
+ * aggregated from all vm* instances. We need our own isolated
+ * queue to ease flushing work items when a VM exits.
+ */
+int kvm_irqfd_init(void)
+{
+	irqfd_cleanup_wq = alloc_workqueue("kvm-irqfd-cleanup", 0, 0);
+	if (!irqfd_cleanup_wq)
+		return -ENOMEM;
+
+	return 0;
+}
+
 void kvm_irqfd_exit(void)
 {
+	destroy_workqueue(irqfd_cleanup_wq);
 }
 #endif
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 2907b7b78654..5c360347a1e9 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -3844,7 +3844,12 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 	 * kvm_arch_init makes sure there's at most one caller
 	 * for architectures that support multiple implementations,
 	 * like intel and amd on x86.
+	 * kvm_arch_init must be called before kvm_irqfd_init to avoid creating
+	 * conflicts in case kvm is already setup for another implementation.
 	 */
+	r = kvm_irqfd_init();
+	if (r)
+		goto out_irqfd;
 
 	if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) {
 		r = -ENOMEM;
@@ -3926,6 +3931,7 @@ out_free_0a:
 	free_cpumask_var(cpus_hardware_enabled);
 out_free_0:
 	kvm_irqfd_exit();
+out_irqfd:
 	kvm_arch_exit();
 out_fail:
 	return r;