Merge tag 'kvm-4.15-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Radim Krčmář:
 "First batch of KVM changes for 4.15

  Common:
   - Python 3 support in kvm_stat
   - Accounting of slabs to kmemcg

  ARM:
   - Optimized arch timer handling for KVM/ARM
   - Improvements to the VGIC ITS code and introduction of an ITS reset
     ioctl
   - Unification of the 32-bit fault injection logic
   - More exact external abort matching logic

  PPC:
   - Support for running hashed page table (HPT) MMU mode on a host that
     is using the radix MMU mode; single threaded mode on POWER 9 is
     added as a pre-requisite
   - Resolution of merge conflicts with the last second 4.14 HPT fixes
   - Fixes and cleanups

  s390:
   - Some initial preparation patches for exitless interrupts and crypto
   - New capability for AIS migration
   - Fixes

  x86:
   - Improved emulation of LAPIC timer mode changes, MCi_STATUS MSRs,
     and after-reset state
   - Refined dependencies for VMX features
   - Fixes for nested SMI injection
   - A lot of cleanups"

* tag 'kvm-4.15-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (89 commits)
  KVM: s390: provide a capability for AIS state migration
  KVM: s390: clear_io_irq() requests are not expected for adapter interrupts
  KVM: s390: abstract conversion between isc and enum irq_types
  KVM: s390: vsie: use common code functions for pinning
  KVM: s390: SIE considerations for AP Queue virtualization
  KVM: s390: document memory ordering for kvm_s390_vcpu_wakeup
  KVM: PPC: Book3S HV: Cosmetic post-merge cleanups
  KVM: arm/arm64: fix the incompatible matching for external abort
  KVM: arm/arm64: Unify 32bit fault injection
  KVM: arm/arm64: vgic-its: Implement KVM_DEV_ARM_ITS_CTRL_RESET
  KVM: arm/arm64: Document KVM_DEV_ARM_ITS_CTRL_RESET
  KVM: arm/arm64: vgic-its: Free caches when GITS_BASER Valid bit is cleared
  KVM: arm/arm64: vgic-its: New helper functions to free the caches
  KVM: arm/arm64: vgic-its: Remove kvm_its_unmap_device
  arm/arm64: KVM: Load the timer state when enabling the timer
  KVM: arm/arm64: Rework kvm_timer_should_fire
  KVM: arm/arm64: Get rid of kvm_timer_flush_hwstate
  KVM: arm/arm64: Avoid phys timer emulation in vcpu entry/exit
  KVM: arm/arm64: Move phys_timer_emulate function
  KVM: arm/arm64: Use kvm_arm_timer_set/get_reg for guest register traps
  ...

1 files changed, 106 insertions, 93 deletions

diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c
index 547f12dc4d54..d2a99ab0ade7 100644
--- a/virt/kvm/arm/vgic/vgic-its.c
+++ b/virt/kvm/arm/vgic/vgic-its.c
@@ -278,6 +278,7 @@ static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq,
 	u64 propbase = GICR_PROPBASER_ADDRESS(kvm->arch.vgic.propbaser);
 	u8 prop;
 	int ret;
+	unsigned long flags;
 
 	ret = kvm_read_guest(kvm, propbase + irq->intid - GIC_LPI_OFFSET,
 			     &prop, 1);
@@ -285,15 +286,15 @@ static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq,
 	if (ret)
 		return ret;
 
-	spin_lock(&irq->irq_lock);
+	spin_lock_irqsave(&irq->irq_lock, flags);
 
 	if (!filter_vcpu || filter_vcpu == irq->target_vcpu) {
 		irq->priority = LPI_PROP_PRIORITY(prop);
 		irq->enabled = LPI_PROP_ENABLE_BIT(prop);
 
-		vgic_queue_irq_unlock(kvm, irq);
+		vgic_queue_irq_unlock(kvm, irq, flags);
 	} else {
-		spin_unlock(&irq->irq_lock);
+		spin_unlock_irqrestore(&irq->irq_lock, flags);
 	}
 
 	return 0;
@@ -393,6 +394,7 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu)
 	int ret = 0;
 	u32 *intids;
 	int nr_irqs, i;
+	unsigned long flags;
 
 	nr_irqs = vgic_copy_lpi_list(vcpu, &intids);
 	if (nr_irqs < 0)
@@ -420,9 +422,9 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu)
 		}
 
 		irq = vgic_get_irq(vcpu->kvm, NULL, intids[i]);
-		spin_lock(&irq->irq_lock);
+		spin_lock_irqsave(&irq->irq_lock, flags);
 		irq->pending_latch = pendmask & (1U << bit_nr);
-		vgic_queue_irq_unlock(vcpu->kvm, irq);
+		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
 		vgic_put_irq(vcpu->kvm, irq);
 	}
 
@@ -515,6 +517,7 @@ static int vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its,
 {
 	struct kvm_vcpu *vcpu;
 	struct its_ite *ite;
+	unsigned long flags;
 
 	if (!its->enabled)
 		return -EBUSY;
@@ -530,9 +533,9 @@ static int vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its,
 	if (!vcpu->arch.vgic_cpu.lpis_enabled)
 		return -EBUSY;
 
-	spin_lock(&ite->irq->irq_lock);
+	spin_lock_irqsave(&ite->irq->irq_lock, flags);
 	ite->irq->pending_latch = true;
-	vgic_queue_irq_unlock(kvm, ite->irq);
+	vgic_queue_irq_unlock(kvm, ite->irq, flags);
 
 	return 0;
 }
@@ -894,7 +897,7 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its,
 }
 
 /* Requires the its_lock to be held. */
-static void vgic_its_unmap_device(struct kvm *kvm, struct its_device *device)
+static void vgic_its_free_device(struct kvm *kvm, struct its_device *device)
 {
 	struct its_ite *ite, *temp;
 
@@ -910,6 +913,24 @@ static void vgic_its_unmap_device(struct kvm *kvm, struct its_device *device)
 	kfree(device);
 }
 
+/* its lock must be held */
+static void vgic_its_free_device_list(struct kvm *kvm, struct vgic_its *its)
+{
+	struct its_device *cur, *temp;
+
+	list_for_each_entry_safe(cur, temp, &its->device_list, dev_list)
+		vgic_its_free_device(kvm, cur);
+}
+
+/* its lock must be held */
+static void vgic_its_free_collection_list(struct kvm *kvm, struct vgic_its *its)
+{
+	struct its_collection *cur, *temp;
+
+	list_for_each_entry_safe(cur, temp, &its->collection_list, coll_list)
+		vgic_its_free_collection(its, cur->collection_id);
+}
+
 /* Must be called with its_lock mutex held */
 static struct its_device *vgic_its_alloc_device(struct vgic_its *its,
 						u32 device_id, gpa_t itt_addr,
@@ -957,7 +978,7 @@ static int vgic_its_cmd_handle_mapd(struct kvm *kvm, struct vgic_its *its,
 	 * by removing the mapping and re-establishing it.
 	 */
 	if (device)
-		vgic_its_unmap_device(kvm, device);
+		vgic_its_free_device(kvm, device);
 
 	/*
 	 * The spec does not say whether unmapping a not-mapped device
@@ -1410,7 +1431,7 @@ static void vgic_mmio_write_its_baser(struct kvm *kvm,
 				      unsigned long val)
 {
 	const struct vgic_its_abi *abi = vgic_its_get_abi(its);
-	u64 entry_size, device_type;
+	u64 entry_size, table_type;
 	u64 reg, *regptr, clearbits = 0;
 
 	/* When GITS_CTLR.Enable is 1, we ignore write accesses. */
@@ -1421,12 +1442,12 @@ static void vgic_mmio_write_its_baser(struct kvm *kvm,
 	case 0:
 		regptr = &its->baser_device_table;
 		entry_size = abi->dte_esz;
-		device_type = GITS_BASER_TYPE_DEVICE;
+		table_type = GITS_BASER_TYPE_DEVICE;
 		break;
 	case 1:
 		regptr = &its->baser_coll_table;
 		entry_size = abi->cte_esz;
-		device_type = GITS_BASER_TYPE_COLLECTION;
+		table_type = GITS_BASER_TYPE_COLLECTION;
 		clearbits = GITS_BASER_INDIRECT;
 		break;
 	default:
@@ -1438,10 +1459,24 @@ static void vgic_mmio_write_its_baser(struct kvm *kvm,
 	reg &= ~clearbits;
 
 	reg |= (entry_size - 1) << GITS_BASER_ENTRY_SIZE_SHIFT;
-	reg |= device_type << GITS_BASER_TYPE_SHIFT;
+	reg |= table_type << GITS_BASER_TYPE_SHIFT;
 	reg = vgic_sanitise_its_baser(reg);
 
 	*regptr = reg;
+
+	if (!(reg & GITS_BASER_VALID)) {
+		/* Take the its_lock to prevent a race with a save/restore */
+		mutex_lock(&its->its_lock);
+		switch (table_type) {
+		case GITS_BASER_TYPE_DEVICE:
+			vgic_its_free_device_list(kvm, its);
+			break;
+		case GITS_BASER_TYPE_COLLECTION:
+			vgic_its_free_collection_list(kvm, its);
+			break;
+		}
+		mutex_unlock(&its->its_lock);
+	}
 }
 
 static unsigned long vgic_mmio_read_its_ctlr(struct kvm *vcpu,
@@ -1623,46 +1658,17 @@ static int vgic_its_create(struct kvm_device *dev, u32 type)
 	return vgic_its_set_abi(its, NR_ITS_ABIS - 1);
 }
 
-static void vgic_its_free_device(struct kvm *kvm, struct its_device *dev)
-{
-	struct its_ite *ite, *tmp;
-
-	list_for_each_entry_safe(ite, tmp, &dev->itt_head, ite_list)
-		its_free_ite(kvm, ite);
-	list_del(&dev->dev_list);
-	kfree(dev);
-}
-
 static void vgic_its_destroy(struct kvm_device *kvm_dev)
 {
 	struct kvm *kvm = kvm_dev->kvm;
 	struct vgic_its *its = kvm_dev->private;
-	struct list_head *cur, *temp;
-
-	/*
-	 * We may end up here without the lists ever having been initialized.
-	 * Check this and bail out early to avoid dereferencing a NULL pointer.
-	 */
-	if (!its->device_list.next)
-		return;
 
 	mutex_lock(&its->its_lock);
-	list_for_each_safe(cur, temp, &its->device_list) {
-		struct its_device *dev;
 
-		dev = list_entry(cur, struct its_device, dev_list);
-		vgic_its_free_device(kvm, dev);
-	}
+	vgic_its_free_device_list(kvm, its);
+	vgic_its_free_collection_list(kvm, its);
 
-	list_for_each_safe(cur, temp, &its->collection_list) {
-		struct its_collection *coll;
-
-		coll = list_entry(cur, struct its_collection, coll_list);
-		list_del(cur);
-		kfree(coll);
-	}
 	mutex_unlock(&its->its_lock);
-
 	kfree(its);
 }
 
@@ -2290,29 +2296,13 @@ static int vgic_its_restore_collection_table(struct vgic_its *its)
  */
 static int vgic_its_save_tables_v0(struct vgic_its *its)
 {
-	struct kvm *kvm = its->dev->kvm;
 	int ret;
 
-	mutex_lock(&kvm->lock);
-	mutex_lock(&its->its_lock);
-
-	if (!lock_all_vcpus(kvm)) {
-		mutex_unlock(&its->its_lock);
-		mutex_unlock(&kvm->lock);
-		return -EBUSY;
-	}
-
 	ret = vgic_its_save_device_tables(its);
 	if (ret)
-		goto out;
-
-	ret = vgic_its_save_collection_table(its);
+		return ret;
 
-out:
-	unlock_all_vcpus(kvm);
-	mutex_unlock(&its->its_lock);
-	mutex_unlock(&kvm->lock);
-	return ret;
+	return vgic_its_save_collection_table(its);
 }
 
 /**
@@ -2322,29 +2312,13 @@ out:
  */
 static int vgic_its_restore_tables_v0(struct vgic_its *its)
 {
-	struct kvm *kvm = its->dev->kvm;
 	int ret;
 
-	mutex_lock(&kvm->lock);
-	mutex_lock(&its->its_lock);
-
-	if (!lock_all_vcpus(kvm)) {
-		mutex_unlock(&its->its_lock);
-		mutex_unlock(&kvm->lock);
-		return -EBUSY;
-	}
-
 	ret = vgic_its_restore_collection_table(its);
 	if (ret)
-		goto out;
-
-	ret = vgic_its_restore_device_tables(its);
-out:
-	unlock_all_vcpus(kvm);
-	mutex_unlock(&its->its_lock);
-	mutex_unlock(&kvm->lock);
+		return ret;
 
-	return ret;
+	return vgic_its_restore_device_tables(its);
 }
 
 static int vgic_its_commit_v0(struct vgic_its *its)
@@ -2363,6 +2337,19 @@ static int vgic_its_commit_v0(struct vgic_its *its)
 	return 0;
 }
 
+static void vgic_its_reset(struct kvm *kvm, struct vgic_its *its)
+{
+	/* We need to keep the ABI specific field values */
+	its->baser_coll_table &= ~GITS_BASER_VALID;
+	its->baser_device_table &= ~GITS_BASER_VALID;
+	its->cbaser = 0;
+	its->creadr = 0;
+	its->cwriter = 0;
+	its->enabled = 0;
+	vgic_its_free_device_list(kvm, its);
+	vgic_its_free_collection_list(kvm, its);
+}
+
 static int vgic_its_has_attr(struct kvm_device *dev,
 			     struct kvm_device_attr *attr)
 {
@@ -2377,6 +2364,8 @@ static int vgic_its_has_attr(struct kvm_device *dev,
 		switch (attr->attr) {
 		case KVM_DEV_ARM_VGIC_CTRL_INIT:
 			return 0;
+		case KVM_DEV_ARM_ITS_CTRL_RESET:
+			return 0;
 		case KVM_DEV_ARM_ITS_SAVE_TABLES:
 			return 0;
 		case KVM_DEV_ARM_ITS_RESTORE_TABLES:
@@ -2389,6 +2378,41 @@ static int vgic_its_has_attr(struct kvm_device *dev,
 	return -ENXIO;
 }
 
+static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr)
+{
+	const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+	int ret = 0;
+
+	if (attr == KVM_DEV_ARM_VGIC_CTRL_INIT) /* Nothing to do */
+		return 0;
+
+	mutex_lock(&kvm->lock);
+	mutex_lock(&its->its_lock);
+
+	if (!lock_all_vcpus(kvm)) {
+		mutex_unlock(&its->its_lock);
+		mutex_unlock(&kvm->lock);
+		return -EBUSY;
+	}
+
+	switch (attr) {
+	case KVM_DEV_ARM_ITS_CTRL_RESET:
+		vgic_its_reset(kvm, its);
+		break;
+	case KVM_DEV_ARM_ITS_SAVE_TABLES:
+		ret = abi->save_tables(its);
+		break;
+	case KVM_DEV_ARM_ITS_RESTORE_TABLES:
+		ret = abi->restore_tables(its);
+		break;
+	}
+
+	unlock_all_vcpus(kvm);
+	mutex_unlock(&its->its_lock);
+	mutex_unlock(&kvm->lock);
+	return ret;
+}
+
 static int vgic_its_set_attr(struct kvm_device *dev,
 			     struct kvm_device_attr *attr)
 {
@@ -2414,19 +2438,8 @@ static int vgic_its_set_attr(struct kvm_device *dev,
 
 		return vgic_register_its_iodev(dev->kvm, its, addr);
 	}
-	case KVM_DEV_ARM_VGIC_GRP_CTRL: {
-		const struct vgic_its_abi *abi = vgic_its_get_abi(its);
-
-		switch (attr->attr) {
-		case KVM_DEV_ARM_VGIC_CTRL_INIT:
-			/* Nothing to do */
-			return 0;
-		case KVM_DEV_ARM_ITS_SAVE_TABLES:
-			return abi->save_tables(its);
-		case KVM_DEV_ARM_ITS_RESTORE_TABLES:
-			return abi->restore_tables(its);
-		}
-	}
+	case KVM_DEV_ARM_VGIC_GRP_CTRL:
+		return vgic_its_ctrl(dev->kvm, its, attr->attr);
 	case KVM_DEV_ARM_VGIC_GRP_ITS_REGS: {
 		u64 __user *uaddr = (u64 __user *)(long)attr->addr;
 		u64 reg;