summaryrefslogtreecommitdiffstats
path: root/virt
diff options
context:
space:
mode:
Diffstat (limited to '')
-rw-r--r--virt/Makefile2
-rw-r--r--virt/kvm/Kconfig65
-rw-r--r--virt/kvm/async_pf.c228
-rw-r--r--virt/kvm/async_pf.h24
-rw-r--r--virt/kvm/coalesced_mmio.c211
-rw-r--r--virt/kvm/coalesced_mmio.h39
-rw-r--r--virt/kvm/eventfd.c964
-rw-r--r--virt/kvm/irqchip.c240
-rw-r--r--virt/kvm/kvm_main.c5179
-rw-r--r--virt/kvm/vfio.c425
-rw-r--r--virt/kvm/vfio.h18
-rw-r--r--virt/lib/Kconfig3
-rw-r--r--virt/lib/Makefile2
-rw-r--r--virt/lib/irqbypass.c266
14 files changed, 7666 insertions, 0 deletions
diff --git a/virt/Makefile b/virt/Makefile
new file mode 100644
index 000000000..1cfea9436
--- /dev/null
+++ b/virt/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-y += lib/
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
new file mode 100644
index 000000000..1c37ccd5d
--- /dev/null
+++ b/virt/kvm/Kconfig
@@ -0,0 +1,65 @@
+# SPDX-License-Identifier: GPL-2.0
+# KVM common configuration items and defaults
+
+config HAVE_KVM
+ bool
+
+config HAVE_KVM_IRQCHIP
+ bool
+
+config HAVE_KVM_IRQFD
+ bool
+
+config HAVE_KVM_IRQ_ROUTING
+ bool
+
+config HAVE_KVM_EVENTFD
+ bool
+ select EVENTFD
+
+config KVM_MMIO
+ bool
+
+config KVM_ASYNC_PF
+ bool
+
+# Toggle to switch between direct notification and batch job
+config KVM_ASYNC_PF_SYNC
+ bool
+
+config HAVE_KVM_MSI
+ bool
+
+config HAVE_KVM_CPU_RELAX_INTERCEPT
+ bool
+
+config KVM_VFIO
+ bool
+
+config HAVE_KVM_ARCH_TLB_FLUSH_ALL
+ bool
+
+config HAVE_KVM_INVALID_WAKEUPS
+ bool
+
+config KVM_GENERIC_DIRTYLOG_READ_PROTECT
+ bool
+
+config KVM_COMPAT
+ def_bool y
+ depends on KVM && COMPAT && !(S390 || ARM64)
+
+config HAVE_KVM_IRQ_BYPASS
+ bool
+
+config HAVE_KVM_VCPU_ASYNC_IOCTL
+ bool
+
+config HAVE_KVM_VCPU_RUN_PID_CHANGE
+ bool
+
+config HAVE_KVM_NO_POLL
+ bool
+
+config KVM_XFER_TO_GUEST_WORK
+ bool
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
new file mode 100644
index 000000000..dd777688d
--- /dev/null
+++ b/virt/kvm/async_pf.c
@@ -0,0 +1,228 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * kvm asynchronous fault support
+ *
+ * Copyright 2010 Red Hat, Inc.
+ *
+ * Author:
+ * Gleb Natapov <gleb@redhat.com>
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/mmu_context.h>
+#include <linux/sched/mm.h>
+
+#include "async_pf.h"
+#include <trace/events/kvm.h>
+
+static struct kmem_cache *async_pf_cache;
+
+int kvm_async_pf_init(void)
+{
+ async_pf_cache = KMEM_CACHE(kvm_async_pf, 0);
+
+ if (!async_pf_cache)
+ return -ENOMEM;
+
+ return 0;
+}
+
+void kvm_async_pf_deinit(void)
+{
+ kmem_cache_destroy(async_pf_cache);
+ async_pf_cache = NULL;
+}
+
+void kvm_async_pf_vcpu_init(struct kvm_vcpu *vcpu)
+{
+ INIT_LIST_HEAD(&vcpu->async_pf.done);
+ INIT_LIST_HEAD(&vcpu->async_pf.queue);
+ spin_lock_init(&vcpu->async_pf.lock);
+}
+
+static void async_pf_execute(struct work_struct *work)
+{
+ struct kvm_async_pf *apf =
+ container_of(work, struct kvm_async_pf, work);
+ struct mm_struct *mm = apf->mm;
+ struct kvm_vcpu *vcpu = apf->vcpu;
+ unsigned long addr = apf->addr;
+ gpa_t cr2_or_gpa = apf->cr2_or_gpa;
+ int locked = 1;
+ bool first;
+
+ might_sleep();
+
+ /*
+ * This work is run asynchronously to the task which owns
+ * mm and might be done in another context, so we must
+ * access remotely.
+ */
+ mmap_read_lock(mm);
+ get_user_pages_remote(mm, addr, 1, FOLL_WRITE, NULL, NULL,
+ &locked);
+ if (locked)
+ mmap_read_unlock(mm);
+
+ if (IS_ENABLED(CONFIG_KVM_ASYNC_PF_SYNC))
+ kvm_arch_async_page_present(vcpu, apf);
+
+ spin_lock(&vcpu->async_pf.lock);
+ first = list_empty(&vcpu->async_pf.done);
+ list_add_tail(&apf->link, &vcpu->async_pf.done);
+ apf->vcpu = NULL;
+ spin_unlock(&vcpu->async_pf.lock);
+
+ if (!IS_ENABLED(CONFIG_KVM_ASYNC_PF_SYNC) && first)
+ kvm_arch_async_page_present_queued(vcpu);
+
+ /*
+ * apf may be freed by kvm_check_async_pf_completion() after
+ * this point
+ */
+
+ trace_kvm_async_pf_completed(addr, cr2_or_gpa);
+
+ rcuwait_wake_up(&vcpu->wait);
+
+ mmput(mm);
+ kvm_put_kvm(vcpu->kvm);
+}
+
+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 =
+ list_first_entry(&vcpu->async_pf.queue,
+ 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
+ if (cancel_work_sync(&work->work)) {
+ mmput(work->mm);
+ kvm_put_kvm(vcpu->kvm); /* == work->vcpu->kvm */
+ kmem_cache_free(async_pf_cache, work);
+ }
+#endif
+ 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,
+ typeof(*work), link);
+ list_del(&work->link);
+ kmem_cache_free(async_pf_cache, work);
+ }
+ spin_unlock(&vcpu->async_pf.lock);
+
+ vcpu->async_pf.queued = 0;
+}
+
+void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu)
+{
+ struct kvm_async_pf *work;
+
+ while (!list_empty_careful(&vcpu->async_pf.done) &&
+ kvm_arch_can_dequeue_async_page_present(vcpu)) {
+ spin_lock(&vcpu->async_pf.lock);
+ work = list_first_entry(&vcpu->async_pf.done, typeof(*work),
+ link);
+ list_del(&work->link);
+ spin_unlock(&vcpu->async_pf.lock);
+
+ kvm_arch_async_page_ready(vcpu, work);
+ if (!IS_ENABLED(CONFIG_KVM_ASYNC_PF_SYNC))
+ kvm_arch_async_page_present(vcpu, work);
+
+ list_del(&work->queue);
+ vcpu->async_pf.queued--;
+ kmem_cache_free(async_pf_cache, work);
+ }
+}
+
+/*
+ * Try to schedule a job to handle page fault asynchronously. Returns 'true' on
+ * success, 'false' on failure (page fault has to be handled synchronously).
+ */
+bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+ unsigned long hva, struct kvm_arch_async_pf *arch)
+{
+ struct kvm_async_pf *work;
+
+ if (vcpu->async_pf.queued >= ASYNC_PF_PER_VCPU)
+ return false;
+
+ /* Arch specific code should not do async PF in this case */
+ if (unlikely(kvm_is_error_hva(hva)))
+ return false;
+
+ /*
+ * do alloc nowait since if we are going to sleep anyway we
+ * may as well sleep faulting in page
+ */
+ work = kmem_cache_zalloc(async_pf_cache, GFP_NOWAIT | __GFP_NOWARN);
+ if (!work)
+ return false;
+
+ work->wakeup_all = false;
+ work->vcpu = vcpu;
+ work->cr2_or_gpa = cr2_or_gpa;
+ work->addr = hva;
+ work->arch = *arch;
+ work->mm = current->mm;
+ mmget(work->mm);
+ kvm_get_kvm(work->vcpu->kvm);
+
+ INIT_WORK(&work->work, async_pf_execute);
+
+ list_add_tail(&work->queue, &vcpu->async_pf.queue);
+ vcpu->async_pf.queued++;
+ work->notpresent_injected = kvm_arch_async_page_not_present(vcpu, work);
+
+ schedule_work(&work->work);
+
+ return true;
+}
+
+int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu)
+{
+ struct kvm_async_pf *work;
+ bool first;
+
+ if (!list_empty_careful(&vcpu->async_pf.done))
+ return 0;
+
+ work = kmem_cache_zalloc(async_pf_cache, GFP_ATOMIC);
+ if (!work)
+ return -ENOMEM;
+
+ work->wakeup_all = true;
+ INIT_LIST_HEAD(&work->queue); /* for list_del to work */
+
+ spin_lock(&vcpu->async_pf.lock);
+ first = list_empty(&vcpu->async_pf.done);
+ list_add_tail(&work->link, &vcpu->async_pf.done);
+ spin_unlock(&vcpu->async_pf.lock);
+
+ if (!IS_ENABLED(CONFIG_KVM_ASYNC_PF_SYNC) && first)
+ kvm_arch_async_page_present_queued(vcpu);
+
+ vcpu->async_pf.queued++;
+ return 0;
+}
diff --git a/virt/kvm/async_pf.h b/virt/kvm/async_pf.h
new file mode 100644
index 000000000..90d1a7d8c
--- /dev/null
+++ b/virt/kvm/async_pf.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * kvm asynchronous fault support
+ *
+ * Copyright 2010 Red Hat, Inc.
+ *
+ * Author:
+ * Gleb Natapov <gleb@redhat.com>
+ */
+
+#ifndef __KVM_ASYNC_PF_H__
+#define __KVM_ASYNC_PF_H__
+
+#ifdef CONFIG_KVM_ASYNC_PF
+int kvm_async_pf_init(void);
+void kvm_async_pf_deinit(void);
+void kvm_async_pf_vcpu_init(struct kvm_vcpu *vcpu);
+#else
+#define kvm_async_pf_init() (0)
+#define kvm_async_pf_deinit() do {} while (0)
+#define kvm_async_pf_vcpu_init(C) do {} while (0)
+#endif
+
+#endif
diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c
new file mode 100644
index 000000000..ce6f3b916
--- /dev/null
+++ b/virt/kvm/coalesced_mmio.c
@@ -0,0 +1,211 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KVM coalesced MMIO
+ *
+ * Copyright (c) 2008 Bull S.A.S.
+ * Copyright 2009 Red Hat, Inc. and/or its affiliates.
+ *
+ * Author: Laurent Vivier <Laurent.Vivier@bull.net>
+ *
+ */
+
+#include <kvm/iodev.h>
+
+#include <linux/kvm_host.h>
+#include <linux/slab.h>
+#include <linux/kvm.h>
+
+#include "coalesced_mmio.h"
+
+static inline struct kvm_coalesced_mmio_dev *to_mmio(struct kvm_io_device *dev)
+{
+ return container_of(dev, struct kvm_coalesced_mmio_dev, dev);
+}
+
+static int coalesced_mmio_in_range(struct kvm_coalesced_mmio_dev *dev,
+ gpa_t addr, int len)
+{
+ /* is it in a batchable area ?
+ * (addr,len) is fully included in
+ * (zone->addr, zone->size)
+ */
+ if (len < 0)
+ return 0;
+ if (addr + len < addr)
+ return 0;
+ if (addr < dev->zone.addr)
+ return 0;
+ if (addr + len > dev->zone.addr + dev->zone.size)
+ return 0;
+ return 1;
+}
+
+static int coalesced_mmio_has_room(struct kvm_coalesced_mmio_dev *dev, u32 last)
+{
+ struct kvm_coalesced_mmio_ring *ring;
+ unsigned avail;
+
+ /* Are we able to batch it ? */
+
+ /* last is the first free entry
+ * check if we don't meet the first used entry
+ * there is always one unused entry in the buffer
+ */
+ ring = dev->kvm->coalesced_mmio_ring;
+ avail = (ring->first - last - 1) % KVM_COALESCED_MMIO_MAX;
+ if (avail == 0) {
+ /* full */
+ return 0;
+ }
+
+ return 1;
+}
+
+static int coalesced_mmio_write(struct kvm_vcpu *vcpu,
+ struct kvm_io_device *this, gpa_t addr,
+ int len, const void *val)
+{
+ struct kvm_coalesced_mmio_dev *dev = to_mmio(this);
+ struct kvm_coalesced_mmio_ring *ring = dev->kvm->coalesced_mmio_ring;
+ __u32 insert;
+
+ if (!coalesced_mmio_in_range(dev, addr, len))
+ return -EOPNOTSUPP;
+
+ spin_lock(&dev->kvm->ring_lock);
+
+ insert = READ_ONCE(ring->last);
+ if (!coalesced_mmio_has_room(dev, insert) ||
+ insert >= KVM_COALESCED_MMIO_MAX) {
+ spin_unlock(&dev->kvm->ring_lock);
+ return -EOPNOTSUPP;
+ }
+
+ /* copy data in first free entry of the ring */
+
+ ring->coalesced_mmio[insert].phys_addr = addr;
+ ring->coalesced_mmio[insert].len = len;
+ memcpy(ring->coalesced_mmio[insert].data, val, len);
+ ring->coalesced_mmio[insert].pio = dev->zone.pio;
+ smp_wmb();
+ ring->last = (insert + 1) % KVM_COALESCED_MMIO_MAX;
+ spin_unlock(&dev->kvm->ring_lock);
+ return 0;
+}
+
+static void coalesced_mmio_destructor(struct kvm_io_device *this)
+{
+ struct kvm_coalesced_mmio_dev *dev = to_mmio(this);
+
+ list_del(&dev->list);
+
+ kfree(dev);
+}
+
+static const struct kvm_io_device_ops coalesced_mmio_ops = {
+ .write = coalesced_mmio_write,
+ .destructor = coalesced_mmio_destructor,
+};
+
+int kvm_coalesced_mmio_init(struct kvm *kvm)
+{
+ struct page *page;
+
+ page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+ if (!page)
+ return -ENOMEM;
+
+ kvm->coalesced_mmio_ring = page_address(page);
+
+ /*
+ * We're using this spinlock to sync access to the coalesced ring.
+ * The list doesn't need its own lock since device registration and
+ * unregistration should only happen when kvm->slots_lock is held.
+ */
+ spin_lock_init(&kvm->ring_lock);
+ INIT_LIST_HEAD(&kvm->coalesced_zones);
+
+ return 0;
+}
+
+void kvm_coalesced_mmio_free(struct kvm *kvm)
+{
+ if (kvm->coalesced_mmio_ring)
+ free_page((unsigned long)kvm->coalesced_mmio_ring);
+}
+
+int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm,
+ struct kvm_coalesced_mmio_zone *zone)
+{
+ int ret;
+ struct kvm_coalesced_mmio_dev *dev;
+
+ if (zone->pio != 1 && zone->pio != 0)
+ return -EINVAL;
+
+ dev = kzalloc(sizeof(struct kvm_coalesced_mmio_dev),
+ GFP_KERNEL_ACCOUNT);
+ if (!dev)
+ return -ENOMEM;
+
+ kvm_iodevice_init(&dev->dev, &coalesced_mmio_ops);
+ dev->kvm = kvm;
+ dev->zone = *zone;
+
+ mutex_lock(&kvm->slots_lock);
+ ret = kvm_io_bus_register_dev(kvm,
+ zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS,
+ zone->addr, zone->size, &dev->dev);
+ if (ret < 0)
+ goto out_free_dev;
+ list_add_tail(&dev->list, &kvm->coalesced_zones);
+ mutex_unlock(&kvm->slots_lock);
+
+ return 0;
+
+out_free_dev:
+ mutex_unlock(&kvm->slots_lock);
+ kfree(dev);
+
+ return ret;
+}
+
+int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
+ struct kvm_coalesced_mmio_zone *zone)
+{
+ struct kvm_coalesced_mmio_dev *dev, *tmp;
+ int r;
+
+ if (zone->pio != 1 && zone->pio != 0)
+ return -EINVAL;
+
+ mutex_lock(&kvm->slots_lock);
+
+ list_for_each_entry_safe(dev, tmp, &kvm->coalesced_zones, list) {
+ if (zone->pio == dev->zone.pio &&
+ coalesced_mmio_in_range(dev, zone->addr, zone->size)) {
+ r = kvm_io_bus_unregister_dev(kvm,
+ zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS, &dev->dev);
+
+ kvm_iodevice_destructor(&dev->dev);
+
+ /*
+ * On failure, unregister destroys all devices on the
+ * bus _except_ the target device, i.e. coalesced_zones
+ * has been modified. Bail after destroying the target
+ * device, there's no need to restart the walk as there
+ * aren't any zones left.
+ */
+ if (r)
+ break;
+ }
+ }
+
+ mutex_unlock(&kvm->slots_lock);
+
+ /*
+ * Ignore the result of kvm_io_bus_unregister_dev(), from userspace's
+ * perspective, the coalesced MMIO is most definitely unregistered.
+ */
+ return 0;
+}
diff --git a/virt/kvm/coalesced_mmio.h b/virt/kvm/coalesced_mmio.h
new file mode 100644
index 000000000..36f84264e
--- /dev/null
+++ b/virt/kvm/coalesced_mmio.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __KVM_COALESCED_MMIO_H__
+#define __KVM_COALESCED_MMIO_H__
+
+/*
+ * KVM coalesced MMIO
+ *
+ * Copyright (c) 2008 Bull S.A.S.
+ *
+ * Author: Laurent Vivier <Laurent.Vivier@bull.net>
+ *
+ */
+
+#ifdef CONFIG_KVM_MMIO
+
+#include <linux/list.h>
+
+struct kvm_coalesced_mmio_dev {
+ struct list_head list;
+ struct kvm_io_device dev;
+ struct kvm *kvm;
+ struct kvm_coalesced_mmio_zone zone;
+};
+
+int kvm_coalesced_mmio_init(struct kvm *kvm);
+void kvm_coalesced_mmio_free(struct kvm *kvm);
+int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm,
+ struct kvm_coalesced_mmio_zone *zone);
+int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
+ struct kvm_coalesced_mmio_zone *zone);
+
+#else
+
+static inline int kvm_coalesced_mmio_init(struct kvm *kvm) { return 0; }
+static inline void kvm_coalesced_mmio_free(struct kvm *kvm) { }
+
+#endif
+
+#endif
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
new file mode 100644
index 000000000..518cd8dc3
--- /dev/null
+++ b/virt/kvm/eventfd.c
@@ -0,0 +1,964 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * kvm eventfd support - use eventfd objects to signal various KVM events
+ *
+ * Copyright 2009 Novell. All Rights Reserved.
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
+ *
+ * Author:
+ * Gregory Haskins <ghaskins@novell.com>
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/kvm.h>
+#include <linux/kvm_irqfd.h>
+#include <linux/workqueue.h>
+#include <linux/syscalls.h>
+#include <linux/wait.h>
+#include <linux/poll.h>
+#include <linux/file.h>
+#include <linux/list.h>
+#include <linux/eventfd.h>
+#include <linux/kernel.h>
+#include <linux/srcu.h>
+#include <linux/slab.h>
+#include <linux/seqlock.h>
+#include <linux/irqbypass.h>
+#include <trace/events/kvm.h>
+
+#include <kvm/iodev.h>
+
+#ifdef CONFIG_HAVE_KVM_IRQFD
+
+static struct workqueue_struct *irqfd_cleanup_wq;
+
+bool __attribute__((weak))
+kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args)
+{
+ return true;
+}
+
+static void
+irqfd_inject(struct work_struct *work)
+{
+ struct kvm_kernel_irqfd *irqfd =
+ container_of(work, struct kvm_kernel_irqfd, inject);
+ struct kvm *kvm = irqfd->kvm;
+
+ if (!irqfd->resampler) {
+ kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 1,
+ false);
+ kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 0,
+ false);
+ } else
+ kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
+ irqfd->gsi, 1, false);
+}
+
+/*
+ * Since resampler irqfds share an IRQ source ID, we de-assert once
+ * then notify all of the resampler irqfds using this GSI. We can't
+ * do multiple de-asserts or we risk racing with incoming re-asserts.
+ */
+static void
+irqfd_resampler_ack(struct kvm_irq_ack_notifier *kian)
+{
+ struct kvm_kernel_irqfd_resampler *resampler;
+ struct kvm *kvm;
+ struct kvm_kernel_irqfd *irqfd;
+ int idx;
+
+ resampler = container_of(kian,
+ struct kvm_kernel_irqfd_resampler, notifier);
+ kvm = resampler->kvm;
+
+ kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
+ resampler->notifier.gsi, 0, false);
+
+ idx = srcu_read_lock(&kvm->irq_srcu);
+
+ list_for_each_entry_rcu(irqfd, &resampler->list, resampler_link)
+ eventfd_signal(irqfd->resamplefd, 1);
+
+ srcu_read_unlock(&kvm->irq_srcu, idx);
+}
+
+static void
+irqfd_resampler_shutdown(struct kvm_kernel_irqfd *irqfd)
+{
+ struct kvm_kernel_irqfd_resampler *resampler = irqfd->resampler;
+ struct kvm *kvm = resampler->kvm;
+
+ mutex_lock(&kvm->irqfds.resampler_lock);
+
+ list_del_rcu(&irqfd->resampler_link);
+ synchronize_srcu(&kvm->irq_srcu);
+
+ if (list_empty(&resampler->list)) {
+ list_del(&resampler->link);
+ kvm_unregister_irq_ack_notifier(kvm, &resampler->notifier);
+ kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
+ resampler->notifier.gsi, 0, false);
+ kfree(resampler);
+ }
+
+ mutex_unlock(&kvm->irqfds.resampler_lock);
+}
+
+/*
+ * Race-free decouple logic (ordering is critical)
+ */
+static void
+irqfd_shutdown(struct work_struct *work)
+{
+ struct kvm_kernel_irqfd *irqfd =
+ container_of(work, struct kvm_kernel_irqfd, shutdown);
+ struct kvm *kvm = irqfd->kvm;
+ u64 cnt;
+
+ /* Make sure irqfd has been initialized in assign path. */
+ synchronize_srcu(&kvm->irq_srcu);
+
+ /*
+ * Synchronize with the wait-queue and unhook ourselves to prevent
+ * further events.
+ */
+ eventfd_ctx_remove_wait_queue(irqfd->eventfd, &irqfd->wait, &cnt);
+
+ /*
+ * We know no new events will be scheduled at this point, so block
+ * until all previously outstanding events have completed
+ */
+ flush_work(&irqfd->inject);
+
+ if (irqfd->resampler) {
+ irqfd_resampler_shutdown(irqfd);
+ eventfd_ctx_put(irqfd->resamplefd);
+ }
+
+ /*
+ * It is now safe to release the object's resources
+ */
+#ifdef CONFIG_HAVE_KVM_IRQ_BYPASS
+ irq_bypass_unregister_consumer(&irqfd->consumer);
+#endif
+ eventfd_ctx_put(irqfd->eventfd);
+ kfree(irqfd);
+}
+
+
+/* assumes kvm->irqfds.lock is held */
+static bool
+irqfd_is_active(struct kvm_kernel_irqfd *irqfd)
+{
+ return list_empty(&irqfd->list) ? false : true;
+}
+
+/*
+ * Mark the irqfd as inactive and schedule it for removal
+ *
+ * assumes kvm->irqfds.lock is held
+ */
+static void
+irqfd_deactivate(struct kvm_kernel_irqfd *irqfd)
+{
+ BUG_ON(!irqfd_is_active(irqfd));
+
+ list_del_init(&irqfd->list);
+
+ queue_work(irqfd_cleanup_wq, &irqfd->shutdown);
+}
+
+int __attribute__((weak)) kvm_arch_set_irq_inatomic(
+ struct kvm_kernel_irq_routing_entry *irq,
+ struct kvm *kvm, int irq_source_id,
+ int level,
+ bool line_status)
+{
+ return -EWOULDBLOCK;
+}
+
+/*
+ * Called with wqh->lock held and interrupts disabled
+ */
+static int
+irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
+{
+ struct kvm_kernel_irqfd *irqfd =
+ container_of(wait, struct kvm_kernel_irqfd, wait);
+ __poll_t flags = key_to_poll(key);
+ struct kvm_kernel_irq_routing_entry irq;
+ struct kvm *kvm = irqfd->kvm;
+ unsigned seq;
+ int idx;
+
+ if (flags & EPOLLIN) {
+ idx = srcu_read_lock(&kvm->irq_srcu);
+ do {
+ seq = read_seqcount_begin(&irqfd->irq_entry_sc);
+ irq = irqfd->irq_entry;
+ } while (read_seqcount_retry(&irqfd->irq_entry_sc, seq));
+ /* An event has been signaled, inject an interrupt */
+ if (kvm_arch_set_irq_inatomic(&irq, kvm,
+ KVM_USERSPACE_IRQ_SOURCE_ID, 1,
+ false) == -EWOULDBLOCK)
+ schedule_work(&irqfd->inject);
+ srcu_read_unlock(&kvm->irq_srcu, idx);
+ }
+
+ if (flags & EPOLLHUP) {
+ /* The eventfd is closing, detach from KVM */
+ unsigned long iflags;
+
+ spin_lock_irqsave(&kvm->irqfds.lock, iflags);
+
+ /*
+ * We must check if someone deactivated the irqfd before
+ * we could acquire the irqfds.lock since the item is
+ * deactivated from the KVM side before it is unhooked from
+ * the wait-queue. If it is already deactivated, we can
+ * simply return knowing the other side will cleanup for us.
+ * We cannot race against the irqfd going away since the
+ * other side is required to acquire wqh->lock, which we hold
+ */
+ if (irqfd_is_active(irqfd))
+ irqfd_deactivate(irqfd);
+
+ spin_unlock_irqrestore(&kvm->irqfds.lock, iflags);
+ }
+
+ return 0;
+}
+
+static void
+irqfd_ptable_queue_proc(struct file *file, wait_queue_head_t *wqh,
+ poll_table *pt)
+{
+ struct kvm_kernel_irqfd *irqfd =
+ container_of(pt, struct kvm_kernel_irqfd, pt);
+ add_wait_queue(wqh, &irqfd->wait);
+}
+
+/* Must be called under irqfds.lock */
+static void irqfd_update(struct kvm *kvm, struct kvm_kernel_irqfd *irqfd)
+{
+ struct kvm_kernel_irq_routing_entry *e;
+ struct kvm_kernel_irq_routing_entry entries[KVM_NR_IRQCHIPS];
+ int n_entries;
+
+ n_entries = kvm_irq_map_gsi(kvm, entries, irqfd->gsi);
+
+ write_seqcount_begin(&irqfd->irq_entry_sc);
+
+ e = entries;
+ if (n_entries == 1)
+ irqfd->irq_entry = *e;
+ else
+ irqfd->irq_entry.type = 0;
+
+ write_seqcount_end(&irqfd->irq_entry_sc);
+}
+
+#ifdef CONFIG_HAVE_KVM_IRQ_BYPASS
+void __attribute__((weak)) kvm_arch_irq_bypass_stop(
+ struct irq_bypass_consumer *cons)
+{
+}
+
+void __attribute__((weak)) kvm_arch_irq_bypass_start(
+ struct irq_bypass_consumer *cons)
+{
+}
+
+int __attribute__((weak)) kvm_arch_update_irqfd_routing(
+ struct kvm *kvm, unsigned int host_irq,
+ uint32_t guest_irq, bool set)
+{
+ return 0;
+}
+#endif
+
+static int
+kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
+{
+ struct kvm_kernel_irqfd *irqfd, *tmp;
+ struct fd f;
+ struct eventfd_ctx *eventfd = NULL, *resamplefd = NULL;
+ int ret;
+ __poll_t events;
+ int idx;
+
+ if (!kvm_arch_intc_initialized(kvm))
+ return -EAGAIN;
+
+ if (!kvm_arch_irqfd_allowed(kvm, args))
+ return -EINVAL;
+
+ irqfd = kzalloc(sizeof(*irqfd), GFP_KERNEL_ACCOUNT);
+ if (!irqfd)
+ return -ENOMEM;
+
+ irqfd->kvm = kvm;
+ irqfd->gsi = args->gsi;
+ INIT_LIST_HEAD(&irqfd->list);
+ INIT_WORK(&irqfd->inject, irqfd_inject);
+ INIT_WORK(&irqfd->shutdown, irqfd_shutdown);
+ seqcount_spinlock_init(&irqfd->irq_entry_sc, &kvm->irqfds.lock);
+
+ f = fdget(args->fd);
+ if (!f.file) {
+ ret = -EBADF;
+ goto out;
+ }
+
+ eventfd = eventfd_ctx_fileget(f.file);
+ if (IS_ERR(eventfd)) {
+ ret = PTR_ERR(eventfd);
+ goto fail;
+ }
+
+ irqfd->eventfd = eventfd;
+
+ if (args->flags & KVM_IRQFD_FLAG_RESAMPLE) {
+ struct kvm_kernel_irqfd_resampler *resampler;
+
+ resamplefd = eventfd_ctx_fdget(args->resamplefd);
+ if (IS_ERR(resamplefd)) {
+ ret = PTR_ERR(resamplefd);
+ goto fail;
+ }
+
+ irqfd->resamplefd = resamplefd;
+ INIT_LIST_HEAD(&irqfd->resampler_link);
+
+ mutex_lock(&kvm->irqfds.resampler_lock);
+
+ list_for_each_entry(resampler,
+ &kvm->irqfds.resampler_list, link) {
+ if (resampler->notifier.gsi == irqfd->gsi) {
+ irqfd->resampler = resampler;
+ break;
+ }
+ }
+
+ if (!irqfd->resampler) {
+ resampler = kzalloc(sizeof(*resampler),
+ GFP_KERNEL_ACCOUNT);
+ if (!resampler) {
+ ret = -ENOMEM;
+ mutex_unlock(&kvm->irqfds.resampler_lock);
+ goto fail;
+ }
+
+ resampler->kvm = kvm;
+ INIT_LIST_HEAD(&resampler->list);
+ resampler->notifier.gsi = irqfd->gsi;
+ resampler->notifier.irq_acked = irqfd_resampler_ack;
+ INIT_LIST_HEAD(&resampler->link);
+
+ list_add(&resampler->link, &kvm->irqfds.resampler_list);
+ kvm_register_irq_ack_notifier(kvm,
+ &resampler->notifier);
+ irqfd->resampler = resampler;
+ }
+
+ list_add_rcu(&irqfd->resampler_link, &irqfd->resampler->list);
+ synchronize_srcu(&kvm->irq_srcu);
+
+ mutex_unlock(&kvm->irqfds.resampler_lock);
+ }
+
+ /*
+ * Install our own custom wake-up handling so we are notified via
+ * a callback whenever someone signals the underlying eventfd
+ */
+ init_waitqueue_func_entry(&irqfd->wait, irqfd_wakeup);
+ init_poll_funcptr(&irqfd->pt, irqfd_ptable_queue_proc);
+
+ spin_lock_irq(&kvm->irqfds.lock);
+
+ ret = 0;
+ list_for_each_entry(tmp, &kvm->irqfds.items, list) {
+ if (irqfd->eventfd != tmp->eventfd)
+ continue;
+ /* This fd is used for another irq already. */
+ ret = -EBUSY;
+ spin_unlock_irq(&kvm->irqfds.lock);
+ goto fail;
+ }
+
+ idx = srcu_read_lock(&kvm->irq_srcu);
+ irqfd_update(kvm, irqfd);
+
+ list_add_tail(&irqfd->list, &kvm->irqfds.items);
+
+ spin_unlock_irq(&kvm->irqfds.lock);
+
+ /*
+ * Check if there was an event already pending on the eventfd
+ * before we registered, and trigger it as if we didn't miss it.
+ */
+ events = vfs_poll(f.file, &irqfd->pt);
+
+ if (events & EPOLLIN)
+ schedule_work(&irqfd->inject);
+
+#ifdef CONFIG_HAVE_KVM_IRQ_BYPASS
+ if (kvm_arch_has_irq_bypass()) {
+ irqfd->consumer.token = (void *)irqfd->eventfd;
+ irqfd->consumer.add_producer = kvm_arch_irq_bypass_add_producer;
+ irqfd->consumer.del_producer = kvm_arch_irq_bypass_del_producer;
+ irqfd->consumer.stop = kvm_arch_irq_bypass_stop;
+ irqfd->consumer.start = kvm_arch_irq_bypass_start;
+ ret = irq_bypass_register_consumer(&irqfd->consumer);
+ if (ret)
+ pr_info("irq bypass consumer (token %p) registration fails: %d\n",
+ irqfd->consumer.token, ret);
+ }
+#endif
+
+ srcu_read_unlock(&kvm->irq_srcu, idx);
+
+ /*
+ * do not drop the file until the irqfd is fully initialized, otherwise
+ * we might race against the EPOLLHUP
+ */
+ fdput(f);
+ return 0;
+
+fail:
+ if (irqfd->resampler)
+ irqfd_resampler_shutdown(irqfd);
+
+ if (resamplefd && !IS_ERR(resamplefd))
+ eventfd_ctx_put(resamplefd);
+
+ if (eventfd && !IS_ERR(eventfd))
+ eventfd_ctx_put(eventfd);
+
+ fdput(f);
+
+out:
+ kfree(irqfd);
+ return ret;
+}
+
+bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin)
+{
+ struct kvm_irq_ack_notifier *kian;
+ int gsi, idx;
+
+ idx = srcu_read_lock(&kvm->irq_srcu);
+ gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
+ if (gsi != -1)
+ hlist_for_each_entry_srcu(kian, &kvm->irq_ack_notifier_list,
+ link, srcu_read_lock_held(&kvm->irq_srcu))
+ if (kian->gsi == gsi) {
+ srcu_read_unlock(&kvm->irq_srcu, idx);
+ return true;
+ }
+
+ srcu_read_unlock(&kvm->irq_srcu, idx);
+
+ return false;
+}
+EXPORT_SYMBOL_GPL(kvm_irq_has_notifier);
+
+void kvm_notify_acked_gsi(struct kvm *kvm, int gsi)
+{
+ struct kvm_irq_ack_notifier *kian;
+
+ hlist_for_each_entry_srcu(kian, &kvm->irq_ack_notifier_list,
+ link, srcu_read_lock_held(&kvm->irq_srcu))
+ if (kian->gsi == gsi)
+ kian->irq_acked(kian);
+}
+
+void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
+{
+ int gsi, idx;
+
+ trace_kvm_ack_irq(irqchip, pin);
+
+ idx = srcu_read_lock(&kvm->irq_srcu);
+ gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
+ if (gsi != -1)
+ kvm_notify_acked_gsi(kvm, gsi);
+ srcu_read_unlock(&kvm->irq_srcu, idx);
+}
+
+void kvm_register_irq_ack_notifier(struct kvm *kvm,
+ struct kvm_irq_ack_notifier *kian)
+{
+ mutex_lock(&kvm->irq_lock);
+ hlist_add_head_rcu(&kian->link, &kvm->irq_ack_notifier_list);
+ mutex_unlock(&kvm->irq_lock);
+ kvm_arch_post_irq_ack_notifier_list_update(kvm);
+}
+
+void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
+ struct kvm_irq_ack_notifier *kian)
+{
+ mutex_lock(&kvm->irq_lock);
+ hlist_del_init_rcu(&kian->link);
+ mutex_unlock(&kvm->irq_lock);
+ synchronize_srcu(&kvm->irq_srcu);
+ kvm_arch_post_irq_ack_notifier_list_update(kvm);
+}
+#endif
+
+void
+kvm_eventfd_init(struct kvm *kvm)
+{
+#ifdef CONFIG_HAVE_KVM_IRQFD
+ spin_lock_init(&kvm->irqfds.lock);
+ INIT_LIST_HEAD(&kvm->irqfds.items);
+ INIT_LIST_HEAD(&kvm->irqfds.resampler_list);
+ mutex_init(&kvm->irqfds.resampler_lock);
+#endif
+ INIT_LIST_HEAD(&kvm->ioeventfds);
+}
+
+#ifdef CONFIG_HAVE_KVM_IRQFD
+/*
+ * shutdown any irqfd's that match fd+gsi
+ */
+static int
+kvm_irqfd_deassign(struct kvm *kvm, struct kvm_irqfd *args)
+{
+ struct kvm_kernel_irqfd *irqfd, *tmp;
+ struct eventfd_ctx *eventfd;
+
+ eventfd = eventfd_ctx_fdget(args->fd);
+ if (IS_ERR(eventfd))
+ return PTR_ERR(eventfd);
+
+ spin_lock_irq(&kvm->irqfds.lock);
+
+ list_for_each_entry_safe(irqfd, tmp, &kvm->irqfds.items, list) {
+ if (irqfd->eventfd == eventfd && irqfd->gsi == args->gsi) {
+ /*
+ * This clearing of irq_entry.type is needed for when
+ * another thread calls kvm_irq_routing_update before
+ * we flush workqueue below (we synchronize with
+ * kvm_irq_routing_update using irqfds.lock).
+ */
+ write_seqcount_begin(&irqfd->irq_entry_sc);
+ irqfd->irq_entry.type = 0;
+ write_seqcount_end(&irqfd->irq_entry_sc);
+ irqfd_deactivate(irqfd);
+ }
+ }
+
+ spin_unlock_irq(&kvm->irqfds.lock);
+ eventfd_ctx_put(eventfd);
+
+ /*
+ * Block until we know all outstanding shutdown jobs have completed
+ * so that we guarantee there will not be any more interrupts on this
+ * gsi once this deassign function returns.
+ */
+ flush_workqueue(irqfd_cleanup_wq);
+
+ return 0;
+}
+
+int
+kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
+{
+ if (args->flags & ~(KVM_IRQFD_FLAG_DEASSIGN | KVM_IRQFD_FLAG_RESAMPLE))
+ return -EINVAL;
+
+ if (args->flags & KVM_IRQFD_FLAG_DEASSIGN)
+ return kvm_irqfd_deassign(kvm, args);
+
+ return kvm_irqfd_assign(kvm, args);
+}
+
+/*
+ * This function is called as the kvm VM fd is being released. Shutdown all
+ * irqfds that still remain open
+ */
+void
+kvm_irqfd_release(struct kvm *kvm)
+{
+ struct kvm_kernel_irqfd *irqfd, *tmp;
+
+ spin_lock_irq(&kvm->irqfds.lock);
+
+ list_for_each_entry_safe(irqfd, tmp, &kvm->irqfds.items, list)
+ irqfd_deactivate(irqfd);
+
+ spin_unlock_irq(&kvm->irqfds.lock);
+
+ /*
+ * Block until we know all outstanding shutdown jobs have completed
+ * since we do not take a kvm* reference.
+ */
+ flush_workqueue(irqfd_cleanup_wq);
+
+}
+
+/*
+ * Take note of a change in irq routing.
+ * Caller must invoke synchronize_srcu(&kvm->irq_srcu) afterwards.
+ */
+void kvm_irq_routing_update(struct kvm *kvm)
+{
+ struct kvm_kernel_irqfd *irqfd;
+
+ spin_lock_irq(&kvm->irqfds.lock);
+
+ list_for_each_entry(irqfd, &kvm->irqfds.items, list) {
+ irqfd_update(kvm, irqfd);
+
+#ifdef CONFIG_HAVE_KVM_IRQ_BYPASS
+ if (irqfd->producer) {
+ int ret = kvm_arch_update_irqfd_routing(
+ irqfd->kvm, irqfd->producer->irq,
+ irqfd->gsi, 1);
+ WARN_ON(ret);
+ }
+#endif
+ }
+
+ 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
+
+/*
+ * --------------------------------------------------------------------
+ * ioeventfd: translate a PIO/MMIO memory write to an eventfd signal.
+ *
+ * userspace can register a PIO/MMIO address with an eventfd for receiving
+ * notification when the memory has been touched.
+ * --------------------------------------------------------------------
+ */
+
+struct _ioeventfd {
+ struct list_head list;
+ u64 addr;
+ int length;
+ struct eventfd_ctx *eventfd;
+ u64 datamatch;
+ struct kvm_io_device dev;
+ u8 bus_idx;
+ bool wildcard;
+};
+
+static inline struct _ioeventfd *
+to_ioeventfd(struct kvm_io_device *dev)
+{
+ return container_of(dev, struct _ioeventfd, dev);
+}
+
+static void
+ioeventfd_release(struct _ioeventfd *p)
+{
+ eventfd_ctx_put(p->eventfd);
+ list_del(&p->list);
+ kfree(p);
+}
+
+static bool
+ioeventfd_in_range(struct _ioeventfd *p, gpa_t addr, int len, const void *val)
+{
+ u64 _val;
+
+ if (addr != p->addr)
+ /* address must be precise for a hit */
+ return false;
+
+ if (!p->length)
+ /* length = 0 means only look at the address, so always a hit */
+ return true;
+
+ if (len != p->length)
+ /* address-range must be precise for a hit */
+ return false;
+
+ if (p->wildcard)
+ /* all else equal, wildcard is always a hit */
+ return true;
+
+ /* otherwise, we have to actually compare the data */
+
+ BUG_ON(!IS_ALIGNED((unsigned long)val, len));
+
+ switch (len) {
+ case 1:
+ _val = *(u8 *)val;
+ break;
+ case 2:
+ _val = *(u16 *)val;
+ break;
+ case 4:
+ _val = *(u32 *)val;
+ break;
+ case 8:
+ _val = *(u64 *)val;
+ break;
+ default:
+ return false;
+ }
+
+ return _val == p->datamatch;
+}
+
+/* MMIO/PIO writes trigger an event if the addr/val match */
+static int
+ioeventfd_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t addr,
+ int len, const void *val)
+{
+ struct _ioeventfd *p = to_ioeventfd(this);
+
+ if (!ioeventfd_in_range(p, addr, len, val))
+ return -EOPNOTSUPP;
+
+ eventfd_signal(p->eventfd, 1);
+ return 0;
+}
+
+/*
+ * This function is called as KVM is completely shutting down. We do not
+ * need to worry about locking just nuke anything we have as quickly as possible
+ */
+static void
+ioeventfd_destructor(struct kvm_io_device *this)
+{
+ struct _ioeventfd *p = to_ioeventfd(this);
+
+ ioeventfd_release(p);
+}
+
+static const struct kvm_io_device_ops ioeventfd_ops = {
+ .write = ioeventfd_write,
+ .destructor = ioeventfd_destructor,
+};
+
+/* assumes kvm->slots_lock held */
+static bool
+ioeventfd_check_collision(struct kvm *kvm, struct _ioeventfd *p)
+{
+ struct _ioeventfd *_p;
+
+ list_for_each_entry(_p, &kvm->ioeventfds, list)
+ if (_p->bus_idx == p->bus_idx &&
+ _p->addr == p->addr &&
+ (!_p->length || !p->length ||
+ (_p->length == p->length &&
+ (_p->wildcard || p->wildcard ||
+ _p->datamatch == p->datamatch))))
+ return true;
+
+ return false;
+}
+
+static enum kvm_bus ioeventfd_bus_from_flags(__u32 flags)
+{
+ if (flags & KVM_IOEVENTFD_FLAG_PIO)
+ return KVM_PIO_BUS;
+ if (flags & KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY)
+ return KVM_VIRTIO_CCW_NOTIFY_BUS;
+ return KVM_MMIO_BUS;
+}
+
+static int kvm_assign_ioeventfd_idx(struct kvm *kvm,
+ enum kvm_bus bus_idx,
+ struct kvm_ioeventfd *args)
+{
+
+ struct eventfd_ctx *eventfd;
+ struct _ioeventfd *p;
+ int ret;
+
+ eventfd = eventfd_ctx_fdget(args->fd);
+ if (IS_ERR(eventfd))
+ return PTR_ERR(eventfd);
+
+ p = kzalloc(sizeof(*p), GFP_KERNEL_ACCOUNT);
+ if (!p) {
+ ret = -ENOMEM;
+ goto fail;
+ }
+
+ INIT_LIST_HEAD(&p->list);
+ p->addr = args->addr;
+ p->bus_idx = bus_idx;
+ p->length = args->len;
+ p->eventfd = eventfd;
+
+ /* The datamatch feature is optional, otherwise this is a wildcard */
+ if (args->flags & KVM_IOEVENTFD_FLAG_DATAMATCH)
+ p->datamatch = args->datamatch;
+ else
+ p->wildcard = true;
+
+ mutex_lock(&kvm->slots_lock);
+
+ /* Verify that there isn't a match already */
+ if (ioeventfd_check_collision(kvm, p)) {
+ ret = -EEXIST;
+ goto unlock_fail;
+ }
+
+ kvm_iodevice_init(&p->dev, &ioeventfd_ops);
+
+ ret = kvm_io_bus_register_dev(kvm, bus_idx, p->addr, p->length,
+ &p->dev);
+ if (ret < 0)
+ goto unlock_fail;
+
+ kvm_get_bus(kvm, bus_idx)->ioeventfd_count++;
+ list_add_tail(&p->list, &kvm->ioeventfds);
+
+ mutex_unlock(&kvm->slots_lock);
+
+ return 0;
+
+unlock_fail:
+ mutex_unlock(&kvm->slots_lock);
+
+fail:
+ kfree(p);
+ eventfd_ctx_put(eventfd);
+
+ return ret;
+}
+
+static int
+kvm_deassign_ioeventfd_idx(struct kvm *kvm, enum kvm_bus bus_idx,
+ struct kvm_ioeventfd *args)
+{
+ struct _ioeventfd *p, *tmp;
+ struct eventfd_ctx *eventfd;
+ struct kvm_io_bus *bus;
+ int ret = -ENOENT;
+ bool wildcard;
+
+ eventfd = eventfd_ctx_fdget(args->fd);
+ if (IS_ERR(eventfd))
+ return PTR_ERR(eventfd);
+
+ wildcard = !(args->flags & KVM_IOEVENTFD_FLAG_DATAMATCH);
+
+ mutex_lock(&kvm->slots_lock);
+
+ list_for_each_entry_safe(p, tmp, &kvm->ioeventfds, list) {
+
+ if (p->bus_idx != bus_idx ||
+ p->eventfd != eventfd ||
+ p->addr != args->addr ||
+ p->length != args->len ||
+ p->wildcard != wildcard)
+ continue;
+
+ if (!p->wildcard && p->datamatch != args->datamatch)
+ continue;
+
+ kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev);
+ bus = kvm_get_bus(kvm, bus_idx);
+ if (bus)
+ bus->ioeventfd_count--;
+ ioeventfd_release(p);
+ ret = 0;
+ break;
+ }
+
+ mutex_unlock(&kvm->slots_lock);
+
+ eventfd_ctx_put(eventfd);
+
+ return ret;
+}
+
+static int kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
+{
+ enum kvm_bus bus_idx = ioeventfd_bus_from_flags(args->flags);
+ int ret = kvm_deassign_ioeventfd_idx(kvm, bus_idx, args);
+
+ if (!args->len && bus_idx == KVM_MMIO_BUS)
+ kvm_deassign_ioeventfd_idx(kvm, KVM_FAST_MMIO_BUS, args);
+
+ return ret;
+}
+
+static int
+kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
+{
+ enum kvm_bus bus_idx;
+ int ret;
+
+ bus_idx = ioeventfd_bus_from_flags(args->flags);
+ /* must be natural-word sized, or 0 to ignore length */
+ switch (args->len) {
+ case 0:
+ case 1:
+ case 2:
+ case 4:
+ case 8:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ /* check for range overflow */
+ if (args->addr + args->len < args->addr)
+ return -EINVAL;
+
+ /* check for extra flags that we don't understand */
+ if (args->flags & ~KVM_IOEVENTFD_VALID_FLAG_MASK)
+ return -EINVAL;
+
+ /* ioeventfd with no length can't be combined with DATAMATCH */
+ if (!args->len && (args->flags & KVM_IOEVENTFD_FLAG_DATAMATCH))
+ return -EINVAL;
+
+ ret = kvm_assign_ioeventfd_idx(kvm, bus_idx, args);
+ if (ret)
+ goto fail;
+
+ /* When length is ignored, MMIO is also put on a separate bus, for
+ * faster lookups.
+ */
+ if (!args->len && bus_idx == KVM_MMIO_BUS) {
+ ret = kvm_assign_ioeventfd_idx(kvm, KVM_FAST_MMIO_BUS, args);
+ if (ret < 0)
+ goto fast_fail;
+ }
+
+ return 0;
+
+fast_fail:
+ kvm_deassign_ioeventfd_idx(kvm, bus_idx, args);
+fail:
+ return ret;
+}
+
+int
+kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
+{
+ if (args->flags & KVM_IOEVENTFD_FLAG_DEASSIGN)
+ return kvm_deassign_ioeventfd(kvm, args);
+
+ return kvm_assign_ioeventfd(kvm, args);
+}
diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c
new file mode 100644
index 000000000..58e4f88b2
--- /dev/null
+++ b/virt/kvm/irqchip.c
@@ -0,0 +1,240 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * irqchip.c: Common API for in kernel interrupt controllers
+ * Copyright (c) 2007, Intel Corporation.
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
+ * Copyright (c) 2013, Alexander Graf <agraf@suse.de>
+ *
+ * This file is derived from virt/kvm/irq_comm.c.
+ *
+ * Authors:
+ * Yaozu (Eddie) Dong <Eddie.dong@intel.com>
+ * Alexander Graf <agraf@suse.de>
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/slab.h>
+#include <linux/srcu.h>
+#include <linux/export.h>
+#include <trace/events/kvm.h>
+#include "irq.h"
+
+int kvm_irq_map_gsi(struct kvm *kvm,
+ struct kvm_kernel_irq_routing_entry *entries, int gsi)
+{
+ struct kvm_irq_routing_table *irq_rt;
+ struct kvm_kernel_irq_routing_entry *e;
+ int n = 0;
+
+ irq_rt = srcu_dereference_check(kvm->irq_routing, &kvm->irq_srcu,
+ lockdep_is_held(&kvm->irq_lock));
+ if (irq_rt && gsi < irq_rt->nr_rt_entries) {
+ hlist_for_each_entry(e, &irq_rt->map[gsi], link) {
+ entries[n] = *e;
+ ++n;
+ }
+ }
+
+ return n;
+}
+
+int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin)
+{
+ struct kvm_irq_routing_table *irq_rt;
+
+ irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
+ return irq_rt->chip[irqchip][pin];
+}
+
+int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi)
+{
+ struct kvm_kernel_irq_routing_entry route;
+
+ if (!irqchip_in_kernel(kvm) || (msi->flags & ~KVM_MSI_VALID_DEVID))
+ return -EINVAL;
+
+ route.msi.address_lo = msi->address_lo;
+ route.msi.address_hi = msi->address_hi;
+ route.msi.data = msi->data;
+ route.msi.flags = msi->flags;
+ route.msi.devid = msi->devid;
+
+ return kvm_set_msi(&route, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1, false);
+}
+
+/*
+ * Return value:
+ * < 0 Interrupt was ignored (masked or not delivered for other reasons)
+ * = 0 Interrupt was coalesced (previous irq is still pending)
+ * > 0 Number of CPUs interrupt was delivered to
+ */
+int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
+ bool line_status)
+{
+ struct kvm_kernel_irq_routing_entry irq_set[KVM_NR_IRQCHIPS];
+ int ret = -1, i, idx;
+
+ trace_kvm_set_irq(irq, level, irq_source_id);
+
+ /* Not possible to detect if the guest uses the PIC or the
+ * IOAPIC. So set the bit in both. The guest will ignore
+ * writes to the unused one.
+ */
+ idx = srcu_read_lock(&kvm->irq_srcu);
+ i = kvm_irq_map_gsi(kvm, irq_set, irq);
+ srcu_read_unlock(&kvm->irq_srcu, idx);
+
+ while (i--) {
+ int r;
+ r = irq_set[i].set(&irq_set[i], kvm, irq_source_id, level,
+ line_status);
+ if (r < 0)
+ continue;
+
+ ret = r + ((ret < 0) ? 0 : ret);
+ }
+
+ return ret;
+}
+
+static void free_irq_routing_table(struct kvm_irq_routing_table *rt)
+{
+ int i;
+
+ if (!rt)
+ return;
+
+ for (i = 0; i < rt->nr_rt_entries; ++i) {
+ struct kvm_kernel_irq_routing_entry *e;
+ struct hlist_node *n;
+
+ hlist_for_each_entry_safe(e, n, &rt->map[i], link) {
+ hlist_del(&e->link);
+ kfree(e);
+ }
+ }
+
+ kfree(rt);
+}
+
+void kvm_free_irq_routing(struct kvm *kvm)
+{
+ /* Called only during vm destruction. Nobody can use the pointer
+ at this stage */
+ struct kvm_irq_routing_table *rt = rcu_access_pointer(kvm->irq_routing);
+ free_irq_routing_table(rt);
+}
+
+static int setup_routing_entry(struct kvm *kvm,
+ struct kvm_irq_routing_table *rt,
+ struct kvm_kernel_irq_routing_entry *e,
+ const struct kvm_irq_routing_entry *ue)
+{
+ struct kvm_kernel_irq_routing_entry *ei;
+ int r;
+ u32 gsi = array_index_nospec(ue->gsi, KVM_MAX_IRQ_ROUTES);
+
+ /*
+ * Do not allow GSI to be mapped to the same irqchip more than once.
+ * Allow only one to one mapping between GSI and non-irqchip routing.
+ */
+ hlist_for_each_entry(ei, &rt->map[gsi], link)
+ if (ei->type != KVM_IRQ_ROUTING_IRQCHIP ||
+ ue->type != KVM_IRQ_ROUTING_IRQCHIP ||
+ ue->u.irqchip.irqchip == ei->irqchip.irqchip)
+ return -EINVAL;
+
+ e->gsi = gsi;
+ e->type = ue->type;
+ r = kvm_set_routing_entry(kvm, e, ue);
+ if (r)
+ return r;
+ if (e->type == KVM_IRQ_ROUTING_IRQCHIP)
+ rt->chip[e->irqchip.irqchip][e->irqchip.pin] = e->gsi;
+
+ hlist_add_head(&e->link, &rt->map[e->gsi]);
+
+ return 0;
+}
+
+void __attribute__((weak)) kvm_arch_irq_routing_update(struct kvm *kvm)
+{
+}
+
+bool __weak kvm_arch_can_set_irq_routing(struct kvm *kvm)
+{
+ return true;
+}
+
+int kvm_set_irq_routing(struct kvm *kvm,
+ const struct kvm_irq_routing_entry *ue,
+ unsigned nr,
+ unsigned flags)
+{
+ struct kvm_irq_routing_table *new, *old;
+ struct kvm_kernel_irq_routing_entry *e;
+ u32 i, j, nr_rt_entries = 0;
+ int r;
+
+ for (i = 0; i < nr; ++i) {
+ if (ue[i].gsi >= KVM_MAX_IRQ_ROUTES)
+ return -EINVAL;
+ nr_rt_entries = max(nr_rt_entries, ue[i].gsi);
+ }
+
+ nr_rt_entries += 1;
+
+ new = kzalloc(struct_size(new, map, nr_rt_entries), GFP_KERNEL_ACCOUNT);
+ if (!new)
+ return -ENOMEM;
+
+ new->nr_rt_entries = nr_rt_entries;
+ for (i = 0; i < KVM_NR_IRQCHIPS; i++)
+ for (j = 0; j < KVM_IRQCHIP_NUM_PINS; j++)
+ new->chip[i][j] = -1;
+
+ for (i = 0; i < nr; ++i) {
+ r = -ENOMEM;
+ e = kzalloc(sizeof(*e), GFP_KERNEL_ACCOUNT);
+ if (!e)
+ goto out;
+
+ r = -EINVAL;
+ switch (ue->type) {
+ case KVM_IRQ_ROUTING_MSI:
+ if (ue->flags & ~KVM_MSI_VALID_DEVID)
+ goto free_entry;
+ break;
+ default:
+ if (ue->flags)
+ goto free_entry;
+ break;
+ }
+ r = setup_routing_entry(kvm, new, e, ue);
+ if (r)
+ goto free_entry;
+ ++ue;
+ }
+
+ mutex_lock(&kvm->irq_lock);
+ old = rcu_dereference_protected(kvm->irq_routing, 1);
+ rcu_assign_pointer(kvm->irq_routing, new);
+ kvm_irq_routing_update(kvm);
+ kvm_arch_irq_routing_update(kvm);
+ mutex_unlock(&kvm->irq_lock);
+
+ kvm_arch_post_irq_routing_update(kvm);
+
+ synchronize_srcu_expedited(&kvm->irq_srcu);
+
+ new = old;
+ r = 0;
+ goto out;
+
+free_entry:
+ kfree(e);
+out:
+ free_irq_routing_table(new);
+
+ return r;
+}
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
new file mode 100644
index 000000000..356fd5d1a
--- /dev/null
+++ b/virt/kvm/kvm_main.c
@@ -0,0 +1,5179 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Kernel-based Virtual Machine driver for Linux
+ *
+ * This module enables machines with Intel VT-x extensions to run virtual
+ * machines without emulation or binary translation.
+ *
+ * Copyright (C) 2006 Qumranet, Inc.
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
+ *
+ * Authors:
+ * Avi Kivity <avi@qumranet.com>
+ * Yaniv Kamay <yaniv@qumranet.com>
+ */
+
+#include <kvm/iodev.h>
+
+#include <linux/kvm_host.h>
+#include <linux/kvm.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/percpu.h>
+#include <linux/mm.h>
+#include <linux/miscdevice.h>
+#include <linux/vmalloc.h>
+#include <linux/reboot.h>
+#include <linux/debugfs.h>
+#include <linux/highmem.h>
+#include <linux/file.h>
+#include <linux/syscore_ops.h>
+#include <linux/cpu.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/stat.h>
+#include <linux/cpumask.h>
+#include <linux/smp.h>
+#include <linux/anon_inodes.h>
+#include <linux/profile.h>
+#include <linux/kvm_para.h>
+#include <linux/pagemap.h>
+#include <linux/mman.h>
+#include <linux/swap.h>
+#include <linux/bitops.h>
+#include <linux/spinlock.h>
+#include <linux/compat.h>
+#include <linux/srcu.h>
+#include <linux/hugetlb.h>
+#include <linux/slab.h>
+#include <linux/sort.h>
+#include <linux/bsearch.h>
+#include <linux/io.h>
+#include <linux/lockdep.h>
+#include <linux/kthread.h>
+
+#include <asm/processor.h>
+#include <asm/ioctl.h>
+#include <linux/uaccess.h>
+
+#include "coalesced_mmio.h"
+#include "async_pf.h"
+#include "vfio.h"
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/kvm.h>
+
+/* Worst case buffer size needed for holding an integer. */
+#define ITOA_MAX_LEN 12
+
+MODULE_AUTHOR("Qumranet");
+MODULE_LICENSE("GPL");
+
+/* Architectures should define their poll value according to the halt latency */
+unsigned int halt_poll_ns = KVM_HALT_POLL_NS_DEFAULT;
+module_param(halt_poll_ns, uint, 0644);
+EXPORT_SYMBOL_GPL(halt_poll_ns);
+
+/* Default doubles per-vcpu halt_poll_ns. */
+unsigned int halt_poll_ns_grow = 2;
+module_param(halt_poll_ns_grow, uint, 0644);
+EXPORT_SYMBOL_GPL(halt_poll_ns_grow);
+
+/* The start value to grow halt_poll_ns from */
+unsigned int halt_poll_ns_grow_start = 10000; /* 10us */
+module_param(halt_poll_ns_grow_start, uint, 0644);
+EXPORT_SYMBOL_GPL(halt_poll_ns_grow_start);
+
+/* Default resets per-vcpu halt_poll_ns . */
+unsigned int halt_poll_ns_shrink;
+module_param(halt_poll_ns_shrink, uint, 0644);
+EXPORT_SYMBOL_GPL(halt_poll_ns_shrink);
+
+/*
+ * Ordering of locks:
+ *
+ * kvm->lock --> kvm->slots_lock --> kvm->irq_lock
+ */
+
+DEFINE_MUTEX(kvm_lock);
+static DEFINE_RAW_SPINLOCK(kvm_count_lock);
+LIST_HEAD(vm_list);
+
+static cpumask_var_t cpus_hardware_enabled;
+static int kvm_usage_count;
+static atomic_t hardware_enable_failed;
+
+static struct kmem_cache *kvm_vcpu_cache;
+
+static __read_mostly struct preempt_ops kvm_preempt_ops;
+static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_running_vcpu);
+
+struct dentry *kvm_debugfs_dir;
+EXPORT_SYMBOL_GPL(kvm_debugfs_dir);
+
+static int kvm_debugfs_num_entries;
+static const struct file_operations stat_fops_per_vm;
+
+static struct file_operations kvm_chardev_ops;
+
+static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
+ unsigned long arg);
+#ifdef CONFIG_KVM_COMPAT
+static long kvm_vcpu_compat_ioctl(struct file *file, unsigned int ioctl,
+ unsigned long arg);
+#define KVM_COMPAT(c) .compat_ioctl = (c)
+#else
+/*
+ * For architectures that don't implement a compat infrastructure,
+ * adopt a double line of defense:
+ * - Prevent a compat task from opening /dev/kvm
+ * - If the open has been done by a 64bit task, and the KVM fd
+ * passed to a compat task, let the ioctls fail.
+ */
+static long kvm_no_compat_ioctl(struct file *file, unsigned int ioctl,
+ unsigned long arg) { return -EINVAL; }
+
+static int kvm_no_compat_open(struct inode *inode, struct file *file)
+{
+ return is_compat_task() ? -ENODEV : 0;
+}
+#define KVM_COMPAT(c) .compat_ioctl = kvm_no_compat_ioctl, \
+ .open = kvm_no_compat_open
+#endif
+static int hardware_enable_all(void);
+static void hardware_disable_all(void);
+
+static void kvm_io_bus_destroy(struct kvm_io_bus *bus);
+
+__visible bool kvm_rebooting;
+EXPORT_SYMBOL_GPL(kvm_rebooting);
+
+#define KVM_EVENT_CREATE_VM 0
+#define KVM_EVENT_DESTROY_VM 1
+static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm);
+static unsigned long long kvm_createvm_count;
+static unsigned long long kvm_active_vms;
+
+static DEFINE_PER_CPU(cpumask_var_t, cpu_kick_mask);
+
+__weak void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
+ unsigned long start, unsigned long end)
+{
+}
+
+__weak void kvm_arch_guest_memory_reclaimed(struct kvm *kvm)
+{
+}
+
+bool kvm_is_zone_device_pfn(kvm_pfn_t pfn)
+{
+ /*
+ * The metadata used by is_zone_device_page() to determine whether or
+ * not a page is ZONE_DEVICE is guaranteed to be valid if and only if
+ * the device has been pinned, e.g. by get_user_pages(). WARN if the
+ * page_count() is zero to help detect bad usage of this helper.
+ */
+ if (!pfn_valid(pfn) || WARN_ON_ONCE(!page_count(pfn_to_page(pfn))))
+ return false;
+
+ return is_zone_device_page(pfn_to_page(pfn));
+}
+
+bool kvm_is_reserved_pfn(kvm_pfn_t pfn)
+{
+ /*
+ * ZONE_DEVICE pages currently set PG_reserved, but from a refcounting
+ * perspective they are "normal" pages, albeit with slightly different
+ * usage rules.
+ */
+ if (pfn_valid(pfn))
+ return PageReserved(pfn_to_page(pfn)) &&
+ !is_zero_pfn(pfn) &&
+ !kvm_is_zone_device_pfn(pfn);
+
+ return true;
+}
+
+bool kvm_is_transparent_hugepage(kvm_pfn_t pfn)
+{
+ struct page *page = pfn_to_page(pfn);
+
+ if (!PageTransCompoundMap(page))
+ return false;
+
+ return is_transparent_hugepage(compound_head(page));
+}
+
+/*
+ * Switches to specified vcpu, until a matching vcpu_put()
+ */
+void vcpu_load(struct kvm_vcpu *vcpu)
+{
+ int cpu = get_cpu();
+
+ __this_cpu_write(kvm_running_vcpu, vcpu);
+ preempt_notifier_register(&vcpu->preempt_notifier);
+ kvm_arch_vcpu_load(vcpu, cpu);
+ put_cpu();
+}
+EXPORT_SYMBOL_GPL(vcpu_load);
+
+void vcpu_put(struct kvm_vcpu *vcpu)
+{
+ preempt_disable();
+ kvm_arch_vcpu_put(vcpu);
+ preempt_notifier_unregister(&vcpu->preempt_notifier);
+ __this_cpu_write(kvm_running_vcpu, NULL);
+ preempt_enable();
+}
+EXPORT_SYMBOL_GPL(vcpu_put);
+
+/* TODO: merge with kvm_arch_vcpu_should_kick */
+static bool kvm_request_needs_ipi(struct kvm_vcpu *vcpu, unsigned req)
+{
+ int mode = kvm_vcpu_exiting_guest_mode(vcpu);
+
+ /*
+ * We need to wait for the VCPU to reenable interrupts and get out of
+ * READING_SHADOW_PAGE_TABLES mode.
+ */
+ if (req & KVM_REQUEST_WAIT)
+ return mode != OUTSIDE_GUEST_MODE;
+
+ /*
+ * Need to kick a running VCPU, but otherwise there is nothing to do.
+ */
+ return mode == IN_GUEST_MODE;
+}
+
+static void ack_flush(void *_completed)
+{
+}
+
+static inline bool kvm_kick_many_cpus(cpumask_var_t tmp, bool wait)
+{
+ const struct cpumask *cpus;
+
+ if (likely(cpumask_available(tmp)))
+ cpus = tmp;
+ else
+ cpus = cpu_online_mask;
+
+ if (cpumask_empty(cpus))
+ return false;
+
+ smp_call_function_many(cpus, ack_flush, NULL, wait);
+ return true;
+}
+
+static void kvm_make_vcpu_request(struct kvm *kvm, struct kvm_vcpu *vcpu,
+ unsigned int req, cpumask_var_t tmp,
+ int current_cpu)
+{
+ int cpu;
+
+ kvm_make_request(req, vcpu);
+
+ if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu))
+ return;
+
+ /*
+ * tmp can be "unavailable" if cpumasks are allocated off stack as
+ * allocation of the mask is deliberately not fatal and is handled by
+ * falling back to kicking all online CPUs.
+ */
+ if (!cpumask_available(tmp))
+ return;
+
+ /*
+ * Note, the vCPU could get migrated to a different pCPU at any point
+ * after kvm_request_needs_ipi(), which could result in sending an IPI
+ * to the previous pCPU. But, that's OK because the purpose of the IPI
+ * is to ensure the vCPU returns to OUTSIDE_GUEST_MODE, which is
+ * satisfied if the vCPU migrates. Entering READING_SHADOW_PAGE_TABLES
+ * after this point is also OK, as the requirement is only that KVM wait
+ * for vCPUs that were reading SPTEs _before_ any changes were
+ * finalized. See kvm_vcpu_kick() for more details on handling requests.
+ */
+ if (kvm_request_needs_ipi(vcpu, req)) {
+ cpu = READ_ONCE(vcpu->cpu);
+ if (cpu != -1 && cpu != current_cpu)
+ __cpumask_set_cpu(cpu, tmp);
+ }
+}
+
+bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
+ struct kvm_vcpu *except,
+ unsigned long *vcpu_bitmap, cpumask_var_t tmp)
+{
+ struct kvm_vcpu *vcpu;
+ int i, me;
+ bool called;
+
+ me = get_cpu();
+
+ for_each_set_bit(i, vcpu_bitmap, KVM_MAX_VCPUS) {
+ vcpu = kvm_get_vcpu(kvm, i);
+ if (!vcpu || vcpu == except)
+ continue;
+ kvm_make_vcpu_request(kvm, vcpu, req, tmp, me);
+ }
+
+ called = kvm_kick_many_cpus(tmp, !!(req & KVM_REQUEST_WAIT));
+ put_cpu();
+
+ return called;
+}
+
+bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req,
+ struct kvm_vcpu *except)
+{
+ struct kvm_vcpu *vcpu;
+ struct cpumask *cpus;
+ bool called;
+ int i, me;
+
+ me = get_cpu();
+
+ cpus = this_cpu_cpumask_var_ptr(cpu_kick_mask);
+ cpumask_clear(cpus);
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (vcpu == except)
+ continue;
+ kvm_make_vcpu_request(kvm, vcpu, req, cpus, me);
+ }
+
+ called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT));
+ put_cpu();
+
+ return called;
+}
+
+bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req)
+{
+ return kvm_make_all_cpus_request_except(kvm, req, NULL);
+}
+
+#ifndef CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL
+void kvm_flush_remote_tlbs(struct kvm *kvm)
+{
+ /*
+ * Read tlbs_dirty before setting KVM_REQ_TLB_FLUSH in
+ * kvm_make_all_cpus_request.
+ */
+ long dirty_count = smp_load_acquire(&kvm->tlbs_dirty);
+
+ /*
+ * We want to publish modifications to the page tables before reading
+ * mode. Pairs with a memory barrier in arch-specific code.
+ * - x86: smp_mb__after_srcu_read_unlock in vcpu_enter_guest
+ * and smp_mb in walk_shadow_page_lockless_begin/end.
+ * - powerpc: smp_mb in kvmppc_prepare_to_enter.
+ *
+ * There is already an smp_mb__after_atomic() before
+ * kvm_make_all_cpus_request() reads vcpu->mode. We reuse that
+ * barrier here.
+ */
+ if (!kvm_arch_flush_remote_tlb(kvm)
+ || kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
+ ++kvm->stat.remote_tlb_flush;
+ cmpxchg(&kvm->tlbs_dirty, dirty_count, 0);
+}
+EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs);
+#endif
+
+void kvm_reload_remote_mmus(struct kvm *kvm)
+{
+ kvm_make_all_cpus_request(kvm, KVM_REQ_MMU_RELOAD);
+}
+
+static void kvm_flush_shadow_all(struct kvm *kvm)
+{
+ kvm_arch_flush_shadow_all(kvm);
+ kvm_arch_guest_memory_reclaimed(kvm);
+}
+
+#ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE
+static inline void *mmu_memory_cache_alloc_obj(struct kvm_mmu_memory_cache *mc,
+ gfp_t gfp_flags)
+{
+ gfp_flags |= mc->gfp_zero;
+
+ if (mc->kmem_cache)
+ return kmem_cache_alloc(mc->kmem_cache, gfp_flags);
+ else
+ return (void *)__get_free_page(gfp_flags);
+}
+
+int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min)
+{
+ void *obj;
+
+ if (mc->nobjs >= min)
+ return 0;
+ while (mc->nobjs < ARRAY_SIZE(mc->objects)) {
+ obj = mmu_memory_cache_alloc_obj(mc, GFP_KERNEL_ACCOUNT);
+ if (!obj)
+ return mc->nobjs >= min ? 0 : -ENOMEM;
+ mc->objects[mc->nobjs++] = obj;
+ }
+ return 0;
+}
+
+int kvm_mmu_memory_cache_nr_free_objects(struct kvm_mmu_memory_cache *mc)
+{
+ return mc->nobjs;
+}
+
+void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc)
+{
+ while (mc->nobjs) {
+ if (mc->kmem_cache)
+ kmem_cache_free(mc->kmem_cache, mc->objects[--mc->nobjs]);
+ else
+ free_page((unsigned long)mc->objects[--mc->nobjs]);
+ }
+}
+
+void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)
+{
+ void *p;
+
+ if (WARN_ON(!mc->nobjs))
+ p = mmu_memory_cache_alloc_obj(mc, GFP_ATOMIC | __GFP_ACCOUNT);
+ else
+ p = mc->objects[--mc->nobjs];
+ BUG_ON(!p);
+ return p;
+}
+#endif
+
+static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
+{
+ mutex_init(&vcpu->mutex);
+ vcpu->cpu = -1;
+ vcpu->kvm = kvm;
+ vcpu->vcpu_id = id;
+ vcpu->pid = NULL;
+ rcuwait_init(&vcpu->wait);
+ kvm_async_pf_vcpu_init(vcpu);
+
+ vcpu->pre_pcpu = -1;
+ INIT_LIST_HEAD(&vcpu->blocked_vcpu_list);
+
+ kvm_vcpu_set_in_spin_loop(vcpu, false);
+ kvm_vcpu_set_dy_eligible(vcpu, false);
+ vcpu->preempted = false;
+ vcpu->ready = false;
+ preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops);
+}
+
+void kvm_vcpu_destroy(struct kvm_vcpu *vcpu)
+{
+ kvm_arch_vcpu_destroy(vcpu);
+
+ /*
+ * No need for rcu_read_lock as VCPU_RUN is the only place that changes
+ * the vcpu->pid pointer, and at destruction time all file descriptors
+ * are already gone.
+ */
+ put_pid(rcu_dereference_protected(vcpu->pid, 1));
+
+ free_page((unsigned long)vcpu->run);
+ kmem_cache_free(kvm_vcpu_cache, vcpu);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_destroy);
+
+#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn)
+{
+ return container_of(mn, struct kvm, mmu_notifier);
+}
+
+static void kvm_mmu_notifier_invalidate_range(struct mmu_notifier *mn,
+ struct mm_struct *mm,
+ unsigned long start, unsigned long end)
+{
+ struct kvm *kvm = mmu_notifier_to_kvm(mn);
+ int idx;
+
+ idx = srcu_read_lock(&kvm->srcu);
+ kvm_arch_mmu_notifier_invalidate_range(kvm, start, end);
+ srcu_read_unlock(&kvm->srcu, idx);
+}
+
+static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
+ struct mm_struct *mm,
+ unsigned long address,
+ pte_t pte)
+{
+ struct kvm *kvm = mmu_notifier_to_kvm(mn);
+ int idx;
+
+ idx = srcu_read_lock(&kvm->srcu);
+ spin_lock(&kvm->mmu_lock);
+ kvm->mmu_notifier_seq++;
+
+ if (kvm_set_spte_hva(kvm, address, pte))
+ kvm_flush_remote_tlbs(kvm);
+
+ spin_unlock(&kvm->mmu_lock);
+ srcu_read_unlock(&kvm->srcu, idx);
+}
+
+static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
+ const struct mmu_notifier_range *range)
+{
+ struct kvm *kvm = mmu_notifier_to_kvm(mn);
+ int need_tlb_flush = 0, idx;
+
+ idx = srcu_read_lock(&kvm->srcu);
+ spin_lock(&kvm->mmu_lock);
+ /*
+ * The count increase must become visible at unlock time as no
+ * spte can be established without taking the mmu_lock and
+ * count is also read inside the mmu_lock critical section.
+ */
+ kvm->mmu_notifier_count++;
+ need_tlb_flush = kvm_unmap_hva_range(kvm, range->start, range->end,
+ range->flags);
+ /* we've to flush the tlb before the pages can be freed */
+ if (need_tlb_flush || kvm->tlbs_dirty)
+ kvm_flush_remote_tlbs(kvm);
+
+ spin_unlock(&kvm->mmu_lock);
+ kvm_arch_guest_memory_reclaimed(kvm);
+ srcu_read_unlock(&kvm->srcu, idx);
+
+ return 0;
+}
+
+static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
+ const struct mmu_notifier_range *range)
+{
+ struct kvm *kvm = mmu_notifier_to_kvm(mn);
+
+ spin_lock(&kvm->mmu_lock);
+ /*
+ * This sequence increase will notify the kvm page fault that
+ * the page that is going to be mapped in the spte could have
+ * been freed.
+ */
+ kvm->mmu_notifier_seq++;
+ smp_wmb();
+ /*
+ * The above sequence increase must be visible before the
+ * below count decrease, which is ensured by the smp_wmb above
+ * in conjunction with the smp_rmb in mmu_notifier_retry().
+ */
+ kvm->mmu_notifier_count--;
+ spin_unlock(&kvm->mmu_lock);
+
+ BUG_ON(kvm->mmu_notifier_count < 0);
+}
+
+static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
+ struct mm_struct *mm,
+ unsigned long start,
+ unsigned long end)
+{
+ struct kvm *kvm = mmu_notifier_to_kvm(mn);
+ int young, idx;
+
+ idx = srcu_read_lock(&kvm->srcu);
+ spin_lock(&kvm->mmu_lock);
+
+ young = kvm_age_hva(kvm, start, end);
+ if (young)
+ kvm_flush_remote_tlbs(kvm);
+
+ spin_unlock(&kvm->mmu_lock);
+ srcu_read_unlock(&kvm->srcu, idx);
+
+ return young;
+}
+
+static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn,
+ struct mm_struct *mm,
+ unsigned long start,
+ unsigned long end)
+{
+ struct kvm *kvm = mmu_notifier_to_kvm(mn);
+ int young, idx;
+
+ idx = srcu_read_lock(&kvm->srcu);
+ spin_lock(&kvm->mmu_lock);
+ /*
+ * Even though we do not flush TLB, this will still adversely
+ * affect performance on pre-Haswell Intel EPT, where there is
+ * no EPT Access Bit to clear so that we have to tear down EPT
+ * tables instead. If we find this unacceptable, we can always
+ * add a parameter to kvm_age_hva so that it effectively doesn't
+ * do anything on clear_young.
+ *
+ * Also note that currently we never issue secondary TLB flushes
+ * from clear_young, leaving this job up to the regular system
+ * cadence. If we find this inaccurate, we might come up with a
+ * more sophisticated heuristic later.
+ */
+ young = kvm_age_hva(kvm, start, end);
+ spin_unlock(&kvm->mmu_lock);
+ srcu_read_unlock(&kvm->srcu, idx);
+
+ return young;
+}
+
+static int kvm_mmu_notifier_test_young(struct mmu_notifier *mn,
+ struct mm_struct *mm,
+ unsigned long address)
+{
+ struct kvm *kvm = mmu_notifier_to_kvm(mn);
+ int young, idx;
+
+ idx = srcu_read_lock(&kvm->srcu);
+ spin_lock(&kvm->mmu_lock);
+ young = kvm_test_age_hva(kvm, address);
+ spin_unlock(&kvm->mmu_lock);
+ srcu_read_unlock(&kvm->srcu, idx);
+
+ return young;
+}
+
+static void kvm_mmu_notifier_release(struct mmu_notifier *mn,
+ struct mm_struct *mm)
+{
+ struct kvm *kvm = mmu_notifier_to_kvm(mn);
+ int idx;
+
+ idx = srcu_read_lock(&kvm->srcu);
+ kvm_flush_shadow_all(kvm);
+ srcu_read_unlock(&kvm->srcu, idx);
+}
+
+static const struct mmu_notifier_ops kvm_mmu_notifier_ops = {
+ .invalidate_range = kvm_mmu_notifier_invalidate_range,
+ .invalidate_range_start = kvm_mmu_notifier_invalidate_range_start,
+ .invalidate_range_end = kvm_mmu_notifier_invalidate_range_end,
+ .clear_flush_young = kvm_mmu_notifier_clear_flush_young,
+ .clear_young = kvm_mmu_notifier_clear_young,
+ .test_young = kvm_mmu_notifier_test_young,
+ .change_pte = kvm_mmu_notifier_change_pte,
+ .release = kvm_mmu_notifier_release,
+};
+
+static int kvm_init_mmu_notifier(struct kvm *kvm)
+{
+ kvm->mmu_notifier.ops = &kvm_mmu_notifier_ops;
+ return mmu_notifier_register(&kvm->mmu_notifier, current->mm);
+}
+
+#else /* !(CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER) */
+
+static int kvm_init_mmu_notifier(struct kvm *kvm)
+{
+ return 0;
+}
+
+#endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */
+
+static struct kvm_memslots *kvm_alloc_memslots(void)
+{
+ int i;
+ struct kvm_memslots *slots;
+
+ slots = kvzalloc(sizeof(struct kvm_memslots), GFP_KERNEL_ACCOUNT);
+ if (!slots)
+ return NULL;
+
+ for (i = 0; i < KVM_MEM_SLOTS_NUM; i++)
+ slots->id_to_index[i] = -1;
+
+ return slots;
+}
+
+static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)
+{
+ if (!memslot->dirty_bitmap)
+ return;
+
+ kvfree(memslot->dirty_bitmap);
+ memslot->dirty_bitmap = NULL;
+}
+
+static void kvm_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot)
+{
+ kvm_destroy_dirty_bitmap(slot);
+
+ kvm_arch_free_memslot(kvm, slot);
+
+ slot->flags = 0;
+ slot->npages = 0;
+}
+
+static void kvm_free_memslots(struct kvm *kvm, struct kvm_memslots *slots)
+{
+ struct kvm_memory_slot *memslot;
+
+ if (!slots)
+ return;
+
+ kvm_for_each_memslot(memslot, slots)
+ kvm_free_memslot(kvm, memslot);
+
+ kvfree(slots);
+}
+
+static void kvm_destroy_vm_debugfs(struct kvm *kvm)
+{
+ int i;
+
+ if (!kvm->debugfs_dentry)
+ return;
+
+ debugfs_remove_recursive(kvm->debugfs_dentry);
+
+ if (kvm->debugfs_stat_data) {
+ for (i = 0; i < kvm_debugfs_num_entries; i++)
+ kfree(kvm->debugfs_stat_data[i]);
+ kfree(kvm->debugfs_stat_data);
+ }
+}
+
+static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
+{
+ static DEFINE_MUTEX(kvm_debugfs_lock);
+ struct dentry *dent;
+ char dir_name[ITOA_MAX_LEN * 2];
+ struct kvm_stat_data *stat_data;
+ struct kvm_stats_debugfs_item *p;
+
+ if (!debugfs_initialized())
+ return 0;
+
+ snprintf(dir_name, sizeof(dir_name), "%d-%d", task_pid_nr(current), fd);
+ mutex_lock(&kvm_debugfs_lock);
+ dent = debugfs_lookup(dir_name, kvm_debugfs_dir);
+ if (dent) {
+ pr_warn_ratelimited("KVM: debugfs: duplicate directory %s\n", dir_name);
+ dput(dent);
+ mutex_unlock(&kvm_debugfs_lock);
+ return 0;
+ }
+ dent = debugfs_create_dir(dir_name, kvm_debugfs_dir);
+ mutex_unlock(&kvm_debugfs_lock);
+ if (IS_ERR(dent))
+ return 0;
+
+ kvm->debugfs_dentry = dent;
+ kvm->debugfs_stat_data = kcalloc(kvm_debugfs_num_entries,
+ sizeof(*kvm->debugfs_stat_data),
+ GFP_KERNEL_ACCOUNT);
+ if (!kvm->debugfs_stat_data)
+ return -ENOMEM;
+
+ for (p = debugfs_entries; p->name; p++) {
+ stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT);
+ if (!stat_data)
+ return -ENOMEM;
+
+ stat_data->kvm = kvm;
+ stat_data->dbgfs_item = p;
+ kvm->debugfs_stat_data[p - debugfs_entries] = stat_data;
+ debugfs_create_file(p->name, KVM_DBGFS_GET_MODE(p),
+ kvm->debugfs_dentry, stat_data,
+ &stat_fops_per_vm);
+ }
+ return 0;
+}
+
+/*
+ * Called after the VM is otherwise initialized, but just before adding it to
+ * the vm_list.
+ */
+int __weak kvm_arch_post_init_vm(struct kvm *kvm)
+{
+ return 0;
+}
+
+/*
+ * Called just after removing the VM from the vm_list, but before doing any
+ * other destruction.
+ */
+void __weak kvm_arch_pre_destroy_vm(struct kvm *kvm)
+{
+}
+
+static struct kvm *kvm_create_vm(unsigned long type)
+{
+ struct kvm *kvm = kvm_arch_alloc_vm();
+ int r = -ENOMEM;
+ int i;
+
+ if (!kvm)
+ return ERR_PTR(-ENOMEM);
+
+ spin_lock_init(&kvm->mmu_lock);
+ mmgrab(current->mm);
+ kvm->mm = current->mm;
+ kvm_eventfd_init(kvm);
+ mutex_init(&kvm->lock);
+ mutex_init(&kvm->irq_lock);
+ mutex_init(&kvm->slots_lock);
+ INIT_LIST_HEAD(&kvm->devices);
+
+ BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX);
+
+ if (init_srcu_struct(&kvm->srcu))
+ goto out_err_no_srcu;
+ if (init_srcu_struct(&kvm->irq_srcu))
+ goto out_err_no_irq_srcu;
+
+ refcount_set(&kvm->users_count, 1);
+ for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+ struct kvm_memslots *slots = kvm_alloc_memslots();
+
+ if (!slots)
+ goto out_err_no_arch_destroy_vm;
+ /* Generations must be different for each address space. */
+ slots->generation = i;
+ rcu_assign_pointer(kvm->memslots[i], slots);
+ }
+
+ for (i = 0; i < KVM_NR_BUSES; i++) {
+ rcu_assign_pointer(kvm->buses[i],
+ kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL_ACCOUNT));
+ if (!kvm->buses[i])
+ goto out_err_no_arch_destroy_vm;
+ }
+
+ kvm->max_halt_poll_ns = halt_poll_ns;
+
+ r = kvm_arch_init_vm(kvm, type);
+ if (r)
+ goto out_err_no_arch_destroy_vm;
+
+ r = hardware_enable_all();
+ if (r)
+ goto out_err_no_disable;
+
+#ifdef CONFIG_HAVE_KVM_IRQFD
+ INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list);
+#endif
+
+ r = kvm_init_mmu_notifier(kvm);
+ if (r)
+ goto out_err_no_mmu_notifier;
+
+ r = kvm_arch_post_init_vm(kvm);
+ if (r)
+ goto out_err;
+
+ mutex_lock(&kvm_lock);
+ list_add(&kvm->vm_list, &vm_list);
+ mutex_unlock(&kvm_lock);
+
+ preempt_notifier_inc();
+
+ /*
+ * When the fd passed to this ioctl() is opened it pins the module,
+ * but try_module_get() also prevents getting a reference if the module
+ * is in MODULE_STATE_GOING (e.g. if someone ran "rmmod --wait").
+ */
+ if (!try_module_get(kvm_chardev_ops.owner)) {
+ r = -ENODEV;
+ goto out_err;
+ }
+
+ return kvm;
+
+out_err:
+#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+ if (kvm->mmu_notifier.ops)
+ mmu_notifier_unregister(&kvm->mmu_notifier, current->mm);
+#endif
+out_err_no_mmu_notifier:
+ hardware_disable_all();
+out_err_no_disable:
+ kvm_arch_destroy_vm(kvm);
+out_err_no_arch_destroy_vm:
+ WARN_ON_ONCE(!refcount_dec_and_test(&kvm->users_count));
+ for (i = 0; i < KVM_NR_BUSES; i++)
+ kfree(kvm_get_bus(kvm, i));
+ for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
+ kvm_free_memslots(kvm, __kvm_memslots(kvm, i));
+ cleanup_srcu_struct(&kvm->irq_srcu);
+out_err_no_irq_srcu:
+ cleanup_srcu_struct(&kvm->srcu);
+out_err_no_srcu:
+ kvm_arch_free_vm(kvm);
+ mmdrop(current->mm);
+ return ERR_PTR(r);
+}
+
+static void kvm_destroy_devices(struct kvm *kvm)
+{
+ struct kvm_device *dev, *tmp;
+
+ /*
+ * We do not need to take the kvm->lock here, because nobody else
+ * has a reference to the struct kvm at this point and therefore
+ * cannot access the devices list anyhow.
+ */
+ list_for_each_entry_safe(dev, tmp, &kvm->devices, vm_node) {
+ list_del(&dev->vm_node);
+ dev->ops->destroy(dev);
+ }
+}
+
+static void kvm_destroy_vm(struct kvm *kvm)
+{
+ int i;
+ struct mm_struct *mm = kvm->mm;
+
+ kvm_uevent_notify_change(KVM_EVENT_DESTROY_VM, kvm);
+ kvm_destroy_vm_debugfs(kvm);
+ kvm_arch_sync_events(kvm);
+ mutex_lock(&kvm_lock);
+ list_del(&kvm->vm_list);
+ mutex_unlock(&kvm_lock);
+ kvm_arch_pre_destroy_vm(kvm);
+
+ kvm_free_irq_routing(kvm);
+ for (i = 0; i < KVM_NR_BUSES; i++) {
+ struct kvm_io_bus *bus = kvm_get_bus(kvm, i);
+
+ if (bus)
+ kvm_io_bus_destroy(bus);
+ kvm->buses[i] = NULL;
+ }
+ kvm_coalesced_mmio_free(kvm);
+#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+ mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm);
+#else
+ kvm_flush_shadow_all(kvm);
+#endif
+ kvm_arch_destroy_vm(kvm);
+ kvm_destroy_devices(kvm);
+ for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
+ kvm_free_memslots(kvm, __kvm_memslots(kvm, i));
+ cleanup_srcu_struct(&kvm->irq_srcu);
+ cleanup_srcu_struct(&kvm->srcu);
+ kvm_arch_free_vm(kvm);
+ preempt_notifier_dec();
+ hardware_disable_all();
+ mmdrop(mm);
+ module_put(kvm_chardev_ops.owner);
+}
+
+void kvm_get_kvm(struct kvm *kvm)
+{
+ refcount_inc(&kvm->users_count);
+}
+EXPORT_SYMBOL_GPL(kvm_get_kvm);
+
+void kvm_put_kvm(struct kvm *kvm)
+{
+ if (refcount_dec_and_test(&kvm->users_count))
+ kvm_destroy_vm(kvm);
+}
+EXPORT_SYMBOL_GPL(kvm_put_kvm);
+
+/*
+ * Used to put a reference that was taken on behalf of an object associated
+ * with a user-visible file descriptor, e.g. a vcpu or device, if installation
+ * of the new file descriptor fails and the reference cannot be transferred to
+ * its final owner. In such cases, the caller is still actively using @kvm and
+ * will fail miserably if the refcount unexpectedly hits zero.
+ */
+void kvm_put_kvm_no_destroy(struct kvm *kvm)
+{
+ WARN_ON(refcount_dec_and_test(&kvm->users_count));
+}
+EXPORT_SYMBOL_GPL(kvm_put_kvm_no_destroy);
+
+static int kvm_vm_release(struct inode *inode, struct file *filp)
+{
+ struct kvm *kvm = filp->private_data;
+
+ kvm_irqfd_release(kvm);
+
+ kvm_put_kvm(kvm);
+ return 0;
+}
+
+/*
+ * Allocation size is twice as large as the actual dirty bitmap size.
+ * See kvm_vm_ioctl_get_dirty_log() why this is needed.
+ */
+static int kvm_alloc_dirty_bitmap(struct kvm_memory_slot *memslot)
+{
+ unsigned long dirty_bytes = 2 * kvm_dirty_bitmap_bytes(memslot);
+
+ memslot->dirty_bitmap = kvzalloc(dirty_bytes, GFP_KERNEL_ACCOUNT);
+ if (!memslot->dirty_bitmap)
+ return -ENOMEM;
+
+ return 0;
+}
+
+/*
+ * Delete a memslot by decrementing the number of used slots and shifting all
+ * other entries in the array forward one spot.
+ */
+static inline void kvm_memslot_delete(struct kvm_memslots *slots,
+ struct kvm_memory_slot *memslot)
+{
+ struct kvm_memory_slot *mslots = slots->memslots;
+ int i;
+
+ if (WARN_ON(slots->id_to_index[memslot->id] == -1))
+ return;
+
+ slots->used_slots--;
+
+ if (atomic_read(&slots->lru_slot) >= slots->used_slots)
+ atomic_set(&slots->lru_slot, 0);
+
+ for (i = slots->id_to_index[memslot->id]; i < slots->used_slots; i++) {
+ mslots[i] = mslots[i + 1];
+ slots->id_to_index[mslots[i].id] = i;
+ }
+ mslots[i] = *memslot;
+ slots->id_to_index[memslot->id] = -1;
+}
+
+/*
+ * "Insert" a new memslot by incrementing the number of used slots. Returns
+ * the new slot's initial index into the memslots array.
+ */
+static inline int kvm_memslot_insert_back(struct kvm_memslots *slots)
+{
+ return slots->used_slots++;
+}
+
+/*
+ * Move a changed memslot backwards in the array by shifting existing slots
+ * with a higher GFN toward the front of the array. Note, the changed memslot
+ * itself is not preserved in the array, i.e. not swapped at this time, only
+ * its new index into the array is tracked. Returns the changed memslot's
+ * current index into the memslots array.
+ */
+static inline int kvm_memslot_move_backward(struct kvm_memslots *slots,
+ struct kvm_memory_slot *memslot)
+{
+ struct kvm_memory_slot *mslots = slots->memslots;
+ int i;
+
+ if (WARN_ON_ONCE(slots->id_to_index[memslot->id] == -1) ||
+ WARN_ON_ONCE(!slots->used_slots))
+ return -1;
+
+ /*
+ * Move the target memslot backward in the array by shifting existing
+ * memslots with a higher GFN (than the target memslot) towards the
+ * front of the array.
+ */
+ for (i = slots->id_to_index[memslot->id]; i < slots->used_slots - 1; i++) {
+ if (memslot->base_gfn > mslots[i + 1].base_gfn)
+ break;
+
+ WARN_ON_ONCE(memslot->base_gfn == mslots[i + 1].base_gfn);
+
+ /* Shift the next memslot forward one and update its index. */
+ mslots[i] = mslots[i + 1];
+ slots->id_to_index[mslots[i].id] = i;
+ }
+ return i;
+}
+
+/*
+ * Move a changed memslot forwards in the array by shifting existing slots with
+ * a lower GFN toward the back of the array. Note, the changed memslot itself
+ * is not preserved in the array, i.e. not swapped at this time, only its new
+ * index into the array is tracked. Returns the changed memslot's final index
+ * into the memslots array.
+ */
+static inline int kvm_memslot_move_forward(struct kvm_memslots *slots,
+ struct kvm_memory_slot *memslot,
+ int start)
+{
+ struct kvm_memory_slot *mslots = slots->memslots;
+ int i;
+
+ for (i = start; i > 0; i--) {
+ if (memslot->base_gfn < mslots[i - 1].base_gfn)
+ break;
+
+ WARN_ON_ONCE(memslot->base_gfn == mslots[i - 1].base_gfn);
+
+ /* Shift the next memslot back one and update its index. */
+ mslots[i] = mslots[i - 1];
+ slots->id_to_index[mslots[i].id] = i;
+ }
+ return i;
+}
+
+/*
+ * Re-sort memslots based on their GFN to account for an added, deleted, or
+ * moved memslot. Sorting memslots by GFN allows using a binary search during
+ * memslot lookup.
+ *
+ * IMPORTANT: Slots are sorted from highest GFN to lowest GFN! I.e. the entry
+ * at memslots[0] has the highest GFN.
+ *
+ * The sorting algorithm takes advantage of having initially sorted memslots
+ * and knowing the position of the changed memslot. Sorting is also optimized
+ * by not swapping the updated memslot and instead only shifting other memslots
+ * and tracking the new index for the update memslot. Only once its final
+ * index is known is the updated memslot copied into its position in the array.
+ *
+ * - When deleting a memslot, the deleted memslot simply needs to be moved to
+ * the end of the array.
+ *
+ * - When creating a memslot, the algorithm "inserts" the new memslot at the
+ * end of the array and then it forward to its correct location.
+ *
+ * - When moving a memslot, the algorithm first moves the updated memslot
+ * backward to handle the scenario where the memslot's GFN was changed to a
+ * lower value. update_memslots() then falls through and runs the same flow
+ * as creating a memslot to move the memslot forward to handle the scenario
+ * where its GFN was changed to a higher value.
+ *
+ * Note, slots are sorted from highest->lowest instead of lowest->highest for
+ * historical reasons. Originally, invalid memslots where denoted by having
+ * GFN=0, thus sorting from highest->lowest naturally sorted invalid memslots
+ * to the end of the array. The current algorithm uses dedicated logic to
+ * delete a memslot and thus does not rely on invalid memslots having GFN=0.
+ *
+ * The other historical motiviation for highest->lowest was to improve the
+ * performance of memslot lookup. KVM originally used a linear search starting
+ * at memslots[0]. On x86, the largest memslot usually has one of the highest,
+ * if not *the* highest, GFN, as the bulk of the guest's RAM is located in a
+ * single memslot above the 4gb boundary. As the largest memslot is also the
+ * most likely to be referenced, sorting it to the front of the array was
+ * advantageous. The current binary search starts from the middle of the array
+ * and uses an LRU pointer to improve performance for all memslots and GFNs.
+ */
+static void update_memslots(struct kvm_memslots *slots,
+ struct kvm_memory_slot *memslot,
+ enum kvm_mr_change change)
+{
+ int i;
+
+ if (change == KVM_MR_DELETE) {
+ kvm_memslot_delete(slots, memslot);
+ } else {
+ if (change == KVM_MR_CREATE)
+ i = kvm_memslot_insert_back(slots);
+ else
+ i = kvm_memslot_move_backward(slots, memslot);
+ i = kvm_memslot_move_forward(slots, memslot, i);
+
+ /*
+ * Copy the memslot to its new position in memslots and update
+ * its index accordingly.
+ */
+ slots->memslots[i] = *memslot;
+ slots->id_to_index[memslot->id] = i;
+ }
+}
+
+static int check_memory_region_flags(const struct kvm_userspace_memory_region *mem)
+{
+ u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
+
+#ifdef __KVM_HAVE_READONLY_MEM
+ valid_flags |= KVM_MEM_READONLY;
+#endif
+
+ if (mem->flags & ~valid_flags)
+ return -EINVAL;
+
+ return 0;
+}
+
+static struct kvm_memslots *install_new_memslots(struct kvm *kvm,
+ int as_id, struct kvm_memslots *slots)
+{
+ struct kvm_memslots *old_memslots = __kvm_memslots(kvm, as_id);
+ u64 gen = old_memslots->generation;
+
+ WARN_ON(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS);
+ slots->generation = gen | KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS;
+
+ rcu_assign_pointer(kvm->memslots[as_id], slots);
+ synchronize_srcu_expedited(&kvm->srcu);
+
+ /*
+ * Increment the new memslot generation a second time, dropping the
+ * update in-progress flag and incrementing the generation based on
+ * the number of address spaces. This provides a unique and easily
+ * identifiable generation number while the memslots are in flux.
+ */
+ gen = slots->generation & ~KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS;
+
+ /*
+ * Generations must be unique even across address spaces. We do not need
+ * a global counter for that, instead the generation space is evenly split
+ * across address spaces. For example, with two address spaces, address
+ * space 0 will use generations 0, 2, 4, ... while address space 1 will
+ * use generations 1, 3, 5, ...
+ */
+ gen += KVM_ADDRESS_SPACE_NUM;
+
+ kvm_arch_memslots_updated(kvm, gen);
+
+ slots->generation = gen;
+
+ return old_memslots;
+}
+
+/*
+ * Note, at a minimum, the current number of used slots must be allocated, even
+ * when deleting a memslot, as we need a complete duplicate of the memslots for
+ * use when invalidating a memslot prior to deleting/moving the memslot.
+ */
+static struct kvm_memslots *kvm_dup_memslots(struct kvm_memslots *old,
+ enum kvm_mr_change change)
+{
+ struct kvm_memslots *slots;
+ size_t old_size, new_size;
+
+ old_size = sizeof(struct kvm_memslots) +
+ (sizeof(struct kvm_memory_slot) * old->used_slots);
+
+ if (change == KVM_MR_CREATE)
+ new_size = old_size + sizeof(struct kvm_memory_slot);
+ else
+ new_size = old_size;
+
+ slots = kvzalloc(new_size, GFP_KERNEL_ACCOUNT);
+ if (likely(slots))
+ memcpy(slots, old, old_size);
+
+ return slots;
+}
+
+static int kvm_set_memslot(struct kvm *kvm,
+ const struct kvm_userspace_memory_region *mem,
+ struct kvm_memory_slot *old,
+ struct kvm_memory_slot *new, int as_id,
+ enum kvm_mr_change change)
+{
+ struct kvm_memory_slot *slot;
+ struct kvm_memslots *slots;
+ int r;
+
+ slots = kvm_dup_memslots(__kvm_memslots(kvm, as_id), change);
+ if (!slots)
+ return -ENOMEM;
+
+ if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) {
+ /*
+ * Note, the INVALID flag needs to be in the appropriate entry
+ * in the freshly allocated memslots, not in @old or @new.
+ */
+ slot = id_to_memslot(slots, old->id);
+ slot->flags |= KVM_MEMSLOT_INVALID;
+
+ /*
+ * We can re-use the old memslots, the only difference from the
+ * newly installed memslots is the invalid flag, which will get
+ * dropped by update_memslots anyway. We'll also revert to the
+ * old memslots if preparing the new memory region fails.
+ */
+ slots = install_new_memslots(kvm, as_id, slots);
+
+ /* From this point no new shadow pages pointing to a deleted,
+ * or moved, memslot will be created.
+ *
+ * validation of sp->gfn happens in:
+ * - gfn_to_hva (kvm_read_guest, gfn_to_pfn)
+ * - kvm_is_visible_gfn (mmu_check_root)
+ */
+ kvm_arch_flush_shadow_memslot(kvm, slot);
+ kvm_arch_guest_memory_reclaimed(kvm);
+ }
+
+ r = kvm_arch_prepare_memory_region(kvm, new, mem, change);
+ if (r)
+ goto out_slots;
+
+ update_memslots(slots, new, change);
+ slots = install_new_memslots(kvm, as_id, slots);
+
+ kvm_arch_commit_memory_region(kvm, mem, old, new, change);
+
+ kvfree(slots);
+ return 0;
+
+out_slots:
+ if (change == KVM_MR_DELETE || change == KVM_MR_MOVE)
+ slots = install_new_memslots(kvm, as_id, slots);
+ kvfree(slots);
+ return r;
+}
+
+static int kvm_delete_memslot(struct kvm *kvm,
+ const struct kvm_userspace_memory_region *mem,
+ struct kvm_memory_slot *old, int as_id)
+{
+ struct kvm_memory_slot new;
+ int r;
+
+ if (!old->npages)
+ return -EINVAL;
+
+ memset(&new, 0, sizeof(new));
+ new.id = old->id;
+ /*
+ * This is only for debugging purpose; it should never be referenced
+ * for a removed memslot.
+ */
+ new.as_id = as_id;
+
+ r = kvm_set_memslot(kvm, mem, old, &new, as_id, KVM_MR_DELETE);
+ if (r)
+ return r;
+
+ kvm_free_memslot(kvm, old);
+ return 0;
+}
+
+/*
+ * Allocate some memory and give it an address in the guest physical address
+ * space.
+ *
+ * Discontiguous memory is allowed, mostly for framebuffers.
+ *
+ * Must be called holding kvm->slots_lock for write.
+ */
+int __kvm_set_memory_region(struct kvm *kvm,
+ const struct kvm_userspace_memory_region *mem)
+{
+ struct kvm_memory_slot old, new;
+ struct kvm_memory_slot *tmp;
+ enum kvm_mr_change change;
+ int as_id, id;
+ int r;
+
+ r = check_memory_region_flags(mem);
+ if (r)
+ return r;
+
+ as_id = mem->slot >> 16;
+ id = (u16)mem->slot;
+
+ /* General sanity checks */
+ if ((mem->memory_size & (PAGE_SIZE - 1)) ||
+ (mem->memory_size != (unsigned long)mem->memory_size))
+ return -EINVAL;
+ if (mem->guest_phys_addr & (PAGE_SIZE - 1))
+ return -EINVAL;
+ /* We can read the guest memory with __xxx_user() later on. */
+ if ((mem->userspace_addr & (PAGE_SIZE - 1)) ||
+ (mem->userspace_addr != untagged_addr(mem->userspace_addr)) ||
+ !access_ok((void __user *)(unsigned long)mem->userspace_addr,
+ mem->memory_size))
+ return -EINVAL;
+ if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_MEM_SLOTS_NUM)
+ return -EINVAL;
+ if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr)
+ return -EINVAL;
+
+ /*
+ * Make a full copy of the old memslot, the pointer will become stale
+ * when the memslots are re-sorted by update_memslots(), and the old
+ * memslot needs to be referenced after calling update_memslots(), e.g.
+ * to free its resources and for arch specific behavior.
+ */
+ tmp = id_to_memslot(__kvm_memslots(kvm, as_id), id);
+ if (tmp) {
+ old = *tmp;
+ tmp = NULL;
+ } else {
+ memset(&old, 0, sizeof(old));
+ old.id = id;
+ }
+
+ if (!mem->memory_size)
+ return kvm_delete_memslot(kvm, mem, &old, as_id);
+
+ new.as_id = as_id;
+ new.id = id;
+ new.base_gfn = mem->guest_phys_addr >> PAGE_SHIFT;
+ new.npages = mem->memory_size >> PAGE_SHIFT;
+ new.flags = mem->flags;
+ new.userspace_addr = mem->userspace_addr;
+
+ if (new.npages > KVM_MEM_MAX_NR_PAGES)
+ return -EINVAL;
+
+ if (!old.npages) {
+ change = KVM_MR_CREATE;
+ new.dirty_bitmap = NULL;
+ memset(&new.arch, 0, sizeof(new.arch));
+ } else { /* Modify an existing slot. */
+ if ((new.userspace_addr != old.userspace_addr) ||
+ (new.npages != old.npages) ||
+ ((new.flags ^ old.flags) & KVM_MEM_READONLY))
+ return -EINVAL;
+
+ if (new.base_gfn != old.base_gfn)
+ change = KVM_MR_MOVE;
+ else if (new.flags != old.flags)
+ change = KVM_MR_FLAGS_ONLY;
+ else /* Nothing to change. */
+ return 0;
+
+ /* Copy dirty_bitmap and arch from the current memslot. */
+ new.dirty_bitmap = old.dirty_bitmap;
+ memcpy(&new.arch, &old.arch, sizeof(new.arch));
+ }
+
+ if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) {
+ /* Check for overlaps */
+ kvm_for_each_memslot(tmp, __kvm_memslots(kvm, as_id)) {
+ if (tmp->id == id)
+ continue;
+ if (!((new.base_gfn + new.npages <= tmp->base_gfn) ||
+ (new.base_gfn >= tmp->base_gfn + tmp->npages)))
+ return -EEXIST;
+ }
+ }
+
+ /* Allocate/free page dirty bitmap as needed */
+ if (!(new.flags & KVM_MEM_LOG_DIRTY_PAGES))
+ new.dirty_bitmap = NULL;
+ else if (!new.dirty_bitmap) {
+ r = kvm_alloc_dirty_bitmap(&new);
+ if (r)
+ return r;
+
+ if (kvm_dirty_log_manual_protect_and_init_set(kvm))
+ bitmap_set(new.dirty_bitmap, 0, new.npages);
+ }
+
+ r = kvm_set_memslot(kvm, mem, &old, &new, as_id, change);
+ if (r)
+ goto out_bitmap;
+
+ if (old.dirty_bitmap && !new.dirty_bitmap)
+ kvm_destroy_dirty_bitmap(&old);
+ return 0;
+
+out_bitmap:
+ if (new.dirty_bitmap && !old.dirty_bitmap)
+ kvm_destroy_dirty_bitmap(&new);
+ return r;
+}
+EXPORT_SYMBOL_GPL(__kvm_set_memory_region);
+
+int kvm_set_memory_region(struct kvm *kvm,
+ const struct kvm_userspace_memory_region *mem)
+{
+ int r;
+
+ mutex_lock(&kvm->slots_lock);
+ r = __kvm_set_memory_region(kvm, mem);
+ mutex_unlock(&kvm->slots_lock);
+ return r;
+}
+EXPORT_SYMBOL_GPL(kvm_set_memory_region);
+
+static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
+ struct kvm_userspace_memory_region *mem)
+{
+ if ((u16)mem->slot >= KVM_USER_MEM_SLOTS)
+ return -EINVAL;
+
+ return kvm_set_memory_region(kvm, mem);
+}
+
+#ifndef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
+/**
+ * kvm_get_dirty_log - get a snapshot of dirty pages
+ * @kvm: pointer to kvm instance
+ * @log: slot id and address to which we copy the log
+ * @is_dirty: set to '1' if any dirty pages were found
+ * @memslot: set to the associated memslot, always valid on success
+ */
+int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log,
+ int *is_dirty, struct kvm_memory_slot **memslot)
+{
+ struct kvm_memslots *slots;
+ int i, as_id, id;
+ unsigned long n;
+ unsigned long any = 0;
+
+ *memslot = NULL;
+ *is_dirty = 0;
+
+ as_id = log->slot >> 16;
+ id = (u16)log->slot;
+ if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
+ return -EINVAL;
+
+ slots = __kvm_memslots(kvm, as_id);
+ *memslot = id_to_memslot(slots, id);
+ if (!(*memslot) || !(*memslot)->dirty_bitmap)
+ return -ENOENT;
+
+ kvm_arch_sync_dirty_log(kvm, *memslot);
+
+ n = kvm_dirty_bitmap_bytes(*memslot);
+
+ for (i = 0; !any && i < n/sizeof(long); ++i)
+ any = (*memslot)->dirty_bitmap[i];
+
+ if (copy_to_user(log->dirty_bitmap, (*memslot)->dirty_bitmap, n))
+ return -EFAULT;
+
+ if (any)
+ *is_dirty = 1;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_get_dirty_log);
+
+#else /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */
+/**
+ * kvm_get_dirty_log_protect - get a snapshot of dirty pages
+ * and reenable dirty page tracking for the corresponding pages.
+ * @kvm: pointer to kvm instance
+ * @log: slot id and address to which we copy the log
+ *
+ * We need to keep it in mind that VCPU threads can write to the bitmap
+ * concurrently. So, to avoid losing track of dirty pages we keep the
+ * following order:
+ *
+ * 1. Take a snapshot of the bit and clear it if needed.
+ * 2. Write protect the corresponding page.
+ * 3. Copy the snapshot to the userspace.
+ * 4. Upon return caller flushes TLB's if needed.
+ *
+ * Between 2 and 4, the guest may write to the page using the remaining TLB
+ * entry. This is not a problem because the page is reported dirty using
+ * the snapshot taken before and step 4 ensures that writes done after
+ * exiting to userspace will be logged for the next call.
+ *
+ */
+static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log)
+{
+ struct kvm_memslots *slots;
+ struct kvm_memory_slot *memslot;
+ int i, as_id, id;
+ unsigned long n;
+ unsigned long *dirty_bitmap;
+ unsigned long *dirty_bitmap_buffer;
+ bool flush;
+
+ as_id = log->slot >> 16;
+ id = (u16)log->slot;
+ if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
+ return -EINVAL;
+
+ slots = __kvm_memslots(kvm, as_id);
+ memslot = id_to_memslot(slots, id);
+ if (!memslot || !memslot->dirty_bitmap)
+ return -ENOENT;
+
+ dirty_bitmap = memslot->dirty_bitmap;
+
+ kvm_arch_sync_dirty_log(kvm, memslot);
+
+ n = kvm_dirty_bitmap_bytes(memslot);
+ flush = false;
+ if (kvm->manual_dirty_log_protect) {
+ /*
+ * Unlike kvm_get_dirty_log, we always return false in *flush,
+ * because no flush is needed until KVM_CLEAR_DIRTY_LOG. There
+ * is some code duplication between this function and
+ * kvm_get_dirty_log, but hopefully all architecture
+ * transition to kvm_get_dirty_log_protect and kvm_get_dirty_log
+ * can be eliminated.
+ */
+ dirty_bitmap_buffer = dirty_bitmap;
+ } else {
+ dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot);
+ memset(dirty_bitmap_buffer, 0, n);
+
+ spin_lock(&kvm->mmu_lock);
+ for (i = 0; i < n / sizeof(long); i++) {
+ unsigned long mask;
+ gfn_t offset;
+
+ if (!dirty_bitmap[i])
+ continue;
+
+ flush = true;
+ mask = xchg(&dirty_bitmap[i], 0);
+ dirty_bitmap_buffer[i] = mask;
+
+ offset = i * BITS_PER_LONG;
+ kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot,
+ offset, mask);
+ }
+ spin_unlock(&kvm->mmu_lock);
+ }
+
+ if (flush)
+ kvm_arch_flush_remote_tlbs_memslot(kvm, memslot);
+
+ if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n))
+ return -EFAULT;
+ return 0;
+}
+
+
+/**
+ * kvm_vm_ioctl_get_dirty_log - get and clear the log of dirty pages in a slot
+ * @kvm: kvm instance
+ * @log: slot id and address to which we copy the log
+ *
+ * Steps 1-4 below provide general overview of dirty page logging. See
+ * kvm_get_dirty_log_protect() function description for additional details.
+ *
+ * We call kvm_get_dirty_log_protect() to handle steps 1-3, upon return we
+ * always flush the TLB (step 4) even if previous step failed and the dirty
+ * bitmap may be corrupt. Regardless of previous outcome the KVM logging API
+ * does not preclude user space subsequent dirty log read. Flushing TLB ensures
+ * writes will be marked dirty for next log read.
+ *
+ * 1. Take a snapshot of the bit and clear it if needed.
+ * 2. Write protect the corresponding page.
+ * 3. Copy the snapshot to the userspace.
+ * 4. Flush TLB's if needed.
+ */
+static int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
+ struct kvm_dirty_log *log)
+{
+ int r;
+
+ mutex_lock(&kvm->slots_lock);
+
+ r = kvm_get_dirty_log_protect(kvm, log);
+
+ mutex_unlock(&kvm->slots_lock);
+ return r;
+}
+
+/**
+ * kvm_clear_dirty_log_protect - clear dirty bits in the bitmap
+ * and reenable dirty page tracking for the corresponding pages.
+ * @kvm: pointer to kvm instance
+ * @log: slot id and address from which to fetch the bitmap of dirty pages
+ */
+static int kvm_clear_dirty_log_protect(struct kvm *kvm,
+ struct kvm_clear_dirty_log *log)
+{
+ struct kvm_memslots *slots;
+ struct kvm_memory_slot *memslot;
+ int as_id, id;
+ gfn_t offset;
+ unsigned long i, n;
+ unsigned long *dirty_bitmap;
+ unsigned long *dirty_bitmap_buffer;
+ bool flush;
+
+ as_id = log->slot >> 16;
+ id = (u16)log->slot;
+ if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
+ return -EINVAL;
+
+ if (log->first_page & 63)
+ return -EINVAL;
+
+ slots = __kvm_memslots(kvm, as_id);
+ memslot = id_to_memslot(slots, id);
+ if (!memslot || !memslot->dirty_bitmap)
+ return -ENOENT;
+
+ dirty_bitmap = memslot->dirty_bitmap;
+
+ n = ALIGN(log->num_pages, BITS_PER_LONG) / 8;
+
+ if (log->first_page > memslot->npages ||
+ log->num_pages > memslot->npages - log->first_page ||
+ (log->num_pages < memslot->npages - log->first_page && (log->num_pages & 63)))
+ return -EINVAL;
+
+ kvm_arch_sync_dirty_log(kvm, memslot);
+
+ flush = false;
+ dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot);
+ if (copy_from_user(dirty_bitmap_buffer, log->dirty_bitmap, n))
+ return -EFAULT;
+
+ spin_lock(&kvm->mmu_lock);
+ for (offset = log->first_page, i = offset / BITS_PER_LONG,
+ n = DIV_ROUND_UP(log->num_pages, BITS_PER_LONG); n--;
+ i++, offset += BITS_PER_LONG) {
+ unsigned long mask = *dirty_bitmap_buffer++;
+ atomic_long_t *p = (atomic_long_t *) &dirty_bitmap[i];
+ if (!mask)
+ continue;
+
+ mask &= atomic_long_fetch_andnot(mask, p);
+
+ /*
+ * mask contains the bits that really have been cleared. This
+ * never includes any bits beyond the length of the memslot (if
+ * the length is not aligned to 64 pages), therefore it is not
+ * a problem if userspace sets them in log->dirty_bitmap.
+ */
+ if (mask) {
+ flush = true;
+ kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot,
+ offset, mask);
+ }
+ }
+ spin_unlock(&kvm->mmu_lock);
+
+ if (flush)
+ kvm_arch_flush_remote_tlbs_memslot(kvm, memslot);
+
+ return 0;
+}
+
+static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm,
+ struct kvm_clear_dirty_log *log)
+{
+ int r;
+
+ mutex_lock(&kvm->slots_lock);
+
+ r = kvm_clear_dirty_log_protect(kvm, log);
+
+ mutex_unlock(&kvm->slots_lock);
+ return r;
+}
+#endif /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */
+
+struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
+{
+ return __gfn_to_memslot(kvm_memslots(kvm), gfn);
+}
+EXPORT_SYMBOL_GPL(gfn_to_memslot);
+
+struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+ return __gfn_to_memslot(kvm_vcpu_memslots(vcpu), gfn);
+}
+
+bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
+{
+ struct kvm_memory_slot *memslot = gfn_to_memslot(kvm, gfn);
+
+ return kvm_is_visible_memslot(memslot);
+}
+EXPORT_SYMBOL_GPL(kvm_is_visible_gfn);
+
+bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+ struct kvm_memory_slot *memslot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
+
+ return kvm_is_visible_memslot(memslot);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_is_visible_gfn);
+
+unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+ struct vm_area_struct *vma;
+ unsigned long addr, size;
+
+ size = PAGE_SIZE;
+
+ addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gfn, NULL);
+ if (kvm_is_error_hva(addr))
+ return PAGE_SIZE;
+
+ mmap_read_lock(current->mm);
+ vma = find_vma(current->mm, addr);
+ if (!vma)
+ goto out;
+
+ size = vma_kernel_pagesize(vma);
+
+out:
+ mmap_read_unlock(current->mm);
+
+ return size;
+}
+
+static bool memslot_is_readonly(struct kvm_memory_slot *slot)
+{
+ return slot->flags & KVM_MEM_READONLY;
+}
+
+static unsigned long __gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn,
+ gfn_t *nr_pages, bool write)
+{
+ if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
+ return KVM_HVA_ERR_BAD;
+
+ if (memslot_is_readonly(slot) && write)
+ return KVM_HVA_ERR_RO_BAD;
+
+ if (nr_pages)
+ *nr_pages = slot->npages - (gfn - slot->base_gfn);
+
+ return __gfn_to_hva_memslot(slot, gfn);
+}
+
+static unsigned long gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn,
+ gfn_t *nr_pages)
+{
+ return __gfn_to_hva_many(slot, gfn, nr_pages, true);
+}
+
+unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot,
+ gfn_t gfn)
+{
+ return gfn_to_hva_many(slot, gfn, NULL);
+}
+EXPORT_SYMBOL_GPL(gfn_to_hva_memslot);
+
+unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
+{
+ return gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, NULL);
+}
+EXPORT_SYMBOL_GPL(gfn_to_hva);
+
+unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+ return gfn_to_hva_many(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn, NULL);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_hva);
+
+/*
+ * Return the hva of a @gfn and the R/W attribute if possible.
+ *
+ * @slot: the kvm_memory_slot which contains @gfn
+ * @gfn: the gfn to be translated
+ * @writable: used to return the read/write attribute of the @slot if the hva
+ * is valid and @writable is not NULL
+ */
+unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot,
+ gfn_t gfn, bool *writable)
+{
+ unsigned long hva = __gfn_to_hva_many(slot, gfn, NULL, false);
+
+ if (!kvm_is_error_hva(hva) && writable)
+ *writable = !memslot_is_readonly(slot);
+
+ return hva;
+}
+
+unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable)
+{
+ struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
+
+ return gfn_to_hva_memslot_prot(slot, gfn, writable);
+}
+
+unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable)
+{
+ struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
+
+ return gfn_to_hva_memslot_prot(slot, gfn, writable);
+}
+
+static inline int check_user_page_hwpoison(unsigned long addr)
+{
+ int rc, flags = FOLL_HWPOISON | FOLL_WRITE;
+
+ rc = get_user_pages(addr, 1, flags, NULL, NULL);
+ return rc == -EHWPOISON;
+}
+
+/*
+ * The fast path to get the writable pfn which will be stored in @pfn,
+ * true indicates success, otherwise false is returned. It's also the
+ * only part that runs if we can in atomic context.
+ */
+static bool hva_to_pfn_fast(unsigned long addr, bool write_fault,
+ bool *writable, kvm_pfn_t *pfn)
+{
+ struct page *page[1];
+
+ /*
+ * Fast pin a writable pfn only if it is a write fault request
+ * or the caller allows to map a writable pfn for a read fault
+ * request.
+ */
+ if (!(write_fault || writable))
+ return false;
+
+ if (get_user_page_fast_only(addr, FOLL_WRITE, page)) {
+ *pfn = page_to_pfn(page[0]);
+
+ if (writable)
+ *writable = true;
+ return true;
+ }
+
+ return false;
+}
+
+/*
+ * The slow path to get the pfn of the specified host virtual address,
+ * 1 indicates success, -errno is returned if error is detected.
+ */
+static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,
+ bool *writable, kvm_pfn_t *pfn)
+{
+ unsigned int flags = FOLL_HWPOISON;
+ struct page *page;
+ int npages = 0;
+
+ might_sleep();
+
+ if (writable)
+ *writable = write_fault;
+
+ if (write_fault)
+ flags |= FOLL_WRITE;
+ if (async)
+ flags |= FOLL_NOWAIT;
+
+ npages = get_user_pages_unlocked(addr, 1, &page, flags);
+ if (npages != 1)
+ return npages;
+
+ /* map read fault as writable if possible */
+ if (unlikely(!write_fault) && writable) {
+ struct page *wpage;
+
+ if (get_user_page_fast_only(addr, FOLL_WRITE, &wpage)) {
+ *writable = true;
+ put_page(page);
+ page = wpage;
+ }
+ }
+ *pfn = page_to_pfn(page);
+ return npages;
+}
+
+static bool vma_is_valid(struct vm_area_struct *vma, bool write_fault)
+{
+ if (unlikely(!(vma->vm_flags & VM_READ)))
+ return false;
+
+ if (write_fault && (unlikely(!(vma->vm_flags & VM_WRITE))))
+ return false;
+
+ return true;
+}
+
+static int kvm_try_get_pfn(kvm_pfn_t pfn)
+{
+ if (kvm_is_reserved_pfn(pfn))
+ return 1;
+ return get_page_unless_zero(pfn_to_page(pfn));
+}
+
+static int hva_to_pfn_remapped(struct vm_area_struct *vma,
+ unsigned long addr, bool *async,
+ bool write_fault, bool *writable,
+ kvm_pfn_t *p_pfn)
+{
+ kvm_pfn_t pfn;
+ pte_t *ptep;
+ spinlock_t *ptl;
+ int r;
+
+ r = follow_pte(vma->vm_mm, addr, &ptep, &ptl);
+ if (r) {
+ /*
+ * get_user_pages fails for VM_IO and VM_PFNMAP vmas and does
+ * not call the fault handler, so do it here.
+ */
+ bool unlocked = false;
+ r = fixup_user_fault(current->mm, addr,
+ (write_fault ? FAULT_FLAG_WRITE : 0),
+ &unlocked);
+ if (unlocked)
+ return -EAGAIN;
+ if (r)
+ return r;
+
+ r = follow_pte(vma->vm_mm, addr, &ptep, &ptl);
+ if (r)
+ return r;
+ }
+
+ if (write_fault && !pte_write(*ptep)) {
+ pfn = KVM_PFN_ERR_RO_FAULT;
+ goto out;
+ }
+
+ if (writable)
+ *writable = pte_write(*ptep);
+ pfn = pte_pfn(*ptep);
+
+ /*
+ * Get a reference here because callers of *hva_to_pfn* and
+ * *gfn_to_pfn* ultimately call kvm_release_pfn_clean on the
+ * returned pfn. This is only needed if the VMA has VM_MIXEDMAP
+ * set, but the kvm_get_pfn/kvm_release_pfn_clean pair will
+ * simply do nothing for reserved pfns.
+ *
+ * Whoever called remap_pfn_range is also going to call e.g.
+ * unmap_mapping_range before the underlying pages are freed,
+ * causing a call to our MMU notifier.
+ *
+ * Certain IO or PFNMAP mappings can be backed with valid
+ * struct pages, but be allocated without refcounting e.g.,
+ * tail pages of non-compound higher order allocations, which
+ * would then underflow the refcount when the caller does the
+ * required put_page. Don't allow those pages here.
+ */
+ if (!kvm_try_get_pfn(pfn))
+ r = -EFAULT;
+
+out:
+ pte_unmap_unlock(ptep, ptl);
+ *p_pfn = pfn;
+
+ return r;
+}
+
+/*
+ * Pin guest page in memory and return its pfn.
+ * @addr: host virtual address which maps memory to the guest
+ * @atomic: whether this function can sleep
+ * @async: whether this function need to wait IO complete if the
+ * host page is not in the memory
+ * @write_fault: whether we should get a writable host page
+ * @writable: whether it allows to map a writable host page for !@write_fault
+ *
+ * The function will map a writable host page for these two cases:
+ * 1): @write_fault = true
+ * 2): @write_fault = false && @writable, @writable will tell the caller
+ * whether the mapping is writable.
+ */
+static kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
+ bool write_fault, bool *writable)
+{
+ struct vm_area_struct *vma;
+ kvm_pfn_t pfn = 0;
+ int npages, r;
+
+ /* we can do it either atomically or asynchronously, not both */
+ BUG_ON(atomic && async);
+
+ if (hva_to_pfn_fast(addr, write_fault, writable, &pfn))
+ return pfn;
+
+ if (atomic)
+ return KVM_PFN_ERR_FAULT;
+
+ npages = hva_to_pfn_slow(addr, async, write_fault, writable, &pfn);
+ if (npages == 1)
+ return pfn;
+
+ mmap_read_lock(current->mm);
+ if (npages == -EHWPOISON ||
+ (!async && check_user_page_hwpoison(addr))) {
+ pfn = KVM_PFN_ERR_HWPOISON;
+ goto exit;
+ }
+
+retry:
+ vma = find_vma_intersection(current->mm, addr, addr + 1);
+
+ if (vma == NULL)
+ pfn = KVM_PFN_ERR_FAULT;
+ else if (vma->vm_flags & (VM_IO | VM_PFNMAP)) {
+ r = hva_to_pfn_remapped(vma, addr, async, write_fault, writable, &pfn);
+ if (r == -EAGAIN)
+ goto retry;
+ if (r < 0)
+ pfn = KVM_PFN_ERR_FAULT;
+ } else {
+ if (async && vma_is_valid(vma, write_fault))
+ *async = true;
+ pfn = KVM_PFN_ERR_FAULT;
+ }
+exit:
+ mmap_read_unlock(current->mm);
+ return pfn;
+}
+
+kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn,
+ bool atomic, bool *async, bool write_fault,
+ bool *writable)
+{
+ unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault);
+
+ if (addr == KVM_HVA_ERR_RO_BAD) {
+ if (writable)
+ *writable = false;
+ return KVM_PFN_ERR_RO_FAULT;
+ }
+
+ if (kvm_is_error_hva(addr)) {
+ if (writable)
+ *writable = false;
+ return KVM_PFN_NOSLOT;
+ }
+
+ /* Do not map writable pfn in the readonly memslot. */
+ if (writable && memslot_is_readonly(slot)) {
+ *writable = false;
+ writable = NULL;
+ }
+
+ return hva_to_pfn(addr, atomic, async, write_fault,
+ writable);
+}
+EXPORT_SYMBOL_GPL(__gfn_to_pfn_memslot);
+
+kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
+ bool *writable)
+{
+ return __gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn, false, NULL,
+ write_fault, writable);
+}
+EXPORT_SYMBOL_GPL(gfn_to_pfn_prot);
+
+kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn)
+{
+ return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL);
+}
+EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot);
+
+kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn)
+{
+ return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL);
+}
+EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic);
+
+kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+ return gfn_to_pfn_memslot_atomic(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_pfn_atomic);
+
+kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn)
+{
+ return gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn);
+}
+EXPORT_SYMBOL_GPL(gfn_to_pfn);
+
+kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+ return gfn_to_pfn_memslot(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_pfn);
+
+int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn,
+ struct page **pages, int nr_pages)
+{
+ unsigned long addr;
+ gfn_t entry = 0;
+
+ addr = gfn_to_hva_many(slot, gfn, &entry);
+ if (kvm_is_error_hva(addr))
+ return -1;
+
+ if (entry < nr_pages)
+ return 0;
+
+ return get_user_pages_fast_only(addr, nr_pages, FOLL_WRITE, pages);
+}
+EXPORT_SYMBOL_GPL(gfn_to_page_many_atomic);
+
+static struct page *kvm_pfn_to_page(kvm_pfn_t pfn)
+{
+ if (is_error_noslot_pfn(pfn))
+ return KVM_ERR_PTR_BAD_PAGE;
+
+ if (kvm_is_reserved_pfn(pfn)) {
+ WARN_ON(1);
+ return KVM_ERR_PTR_BAD_PAGE;
+ }
+
+ return pfn_to_page(pfn);
+}
+
+struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
+{
+ kvm_pfn_t pfn;
+
+ pfn = gfn_to_pfn(kvm, gfn);
+
+ return kvm_pfn_to_page(pfn);
+}
+EXPORT_SYMBOL_GPL(gfn_to_page);
+
+void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache)
+{
+ if (pfn == 0)
+ return;
+
+ if (cache)
+ cache->pfn = cache->gfn = 0;
+
+ if (dirty)
+ kvm_release_pfn_dirty(pfn);
+ else
+ kvm_release_pfn_clean(pfn);
+}
+
+static void kvm_cache_gfn_to_pfn(struct kvm_memory_slot *slot, gfn_t gfn,
+ struct gfn_to_pfn_cache *cache, u64 gen)
+{
+ kvm_release_pfn(cache->pfn, cache->dirty, cache);
+
+ cache->pfn = gfn_to_pfn_memslot(slot, gfn);
+ cache->gfn = gfn;
+ cache->dirty = false;
+ cache->generation = gen;
+}
+
+static int __kvm_map_gfn(struct kvm_memslots *slots, gfn_t gfn,
+ struct kvm_host_map *map,
+ struct gfn_to_pfn_cache *cache,
+ bool atomic)
+{
+ kvm_pfn_t pfn;
+ void *hva = NULL;
+ struct page *page = KVM_UNMAPPED_PAGE;
+ struct kvm_memory_slot *slot = __gfn_to_memslot(slots, gfn);
+ u64 gen = slots->generation;
+
+ if (!map)
+ return -EINVAL;
+
+ if (cache) {
+ if (!cache->pfn || cache->gfn != gfn ||
+ cache->generation != gen) {
+ if (atomic)
+ return -EAGAIN;
+ kvm_cache_gfn_to_pfn(slot, gfn, cache, gen);
+ }
+ pfn = cache->pfn;
+ } else {
+ if (atomic)
+ return -EAGAIN;
+ pfn = gfn_to_pfn_memslot(slot, gfn);
+ }
+ if (is_error_noslot_pfn(pfn))
+ return -EINVAL;
+
+ if (pfn_valid(pfn)) {
+ page = pfn_to_page(pfn);
+ if (atomic)
+ hva = kmap_atomic(page);
+ else
+ hva = kmap(page);
+#ifdef CONFIG_HAS_IOMEM
+ } else if (!atomic) {
+ hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB);
+ } else {
+ return -EINVAL;
+#endif
+ }
+
+ if (!hva)
+ return -EFAULT;
+
+ map->page = page;
+ map->hva = hva;
+ map->pfn = pfn;
+ map->gfn = gfn;
+
+ return 0;
+}
+
+int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map,
+ struct gfn_to_pfn_cache *cache, bool atomic)
+{
+ return __kvm_map_gfn(kvm_memslots(vcpu->kvm), gfn, map,
+ cache, atomic);
+}
+EXPORT_SYMBOL_GPL(kvm_map_gfn);
+
+int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map)
+{
+ return __kvm_map_gfn(kvm_vcpu_memslots(vcpu), gfn, map,
+ NULL, false);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_map);
+
+static void __kvm_unmap_gfn(struct kvm_memory_slot *memslot,
+ struct kvm_host_map *map,
+ struct gfn_to_pfn_cache *cache,
+ bool dirty, bool atomic)
+{
+ if (!map)
+ return;
+
+ if (!map->hva)
+ return;
+
+ if (map->page != KVM_UNMAPPED_PAGE) {
+ if (atomic)
+ kunmap_atomic(map->hva);
+ else
+ kunmap(map->page);
+ }
+#ifdef CONFIG_HAS_IOMEM
+ else if (!atomic)
+ memunmap(map->hva);
+ else
+ WARN_ONCE(1, "Unexpected unmapping in atomic context");
+#endif
+
+ if (dirty)
+ mark_page_dirty_in_slot(memslot, map->gfn);
+
+ if (cache)
+ cache->dirty |= dirty;
+ else
+ kvm_release_pfn(map->pfn, dirty, NULL);
+
+ map->hva = NULL;
+ map->page = NULL;
+}
+
+int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map,
+ struct gfn_to_pfn_cache *cache, bool dirty, bool atomic)
+{
+ __kvm_unmap_gfn(gfn_to_memslot(vcpu->kvm, map->gfn), map,
+ cache, dirty, atomic);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_unmap_gfn);
+
+void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty)
+{
+ __kvm_unmap_gfn(kvm_vcpu_gfn_to_memslot(vcpu, map->gfn), map, NULL,
+ dirty, false);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_unmap);
+
+struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+ kvm_pfn_t pfn;
+
+ pfn = kvm_vcpu_gfn_to_pfn(vcpu, gfn);
+
+ return kvm_pfn_to_page(pfn);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_page);
+
+void kvm_release_page_clean(struct page *page)
+{
+ WARN_ON(is_error_page(page));
+
+ kvm_release_pfn_clean(page_to_pfn(page));
+}
+EXPORT_SYMBOL_GPL(kvm_release_page_clean);
+
+void kvm_release_pfn_clean(kvm_pfn_t pfn)
+{
+ if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn))
+ put_page(pfn_to_page(pfn));
+}
+EXPORT_SYMBOL_GPL(kvm_release_pfn_clean);
+
+void kvm_release_page_dirty(struct page *page)
+{
+ WARN_ON(is_error_page(page));
+
+ kvm_release_pfn_dirty(page_to_pfn(page));
+}
+EXPORT_SYMBOL_GPL(kvm_release_page_dirty);
+
+void kvm_release_pfn_dirty(kvm_pfn_t pfn)
+{
+ kvm_set_pfn_dirty(pfn);
+ kvm_release_pfn_clean(pfn);
+}
+EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty);
+
+static bool kvm_is_ad_tracked_pfn(kvm_pfn_t pfn)
+{
+ if (!pfn_valid(pfn))
+ return false;
+
+ /*
+ * Per page-flags.h, pages tagged PG_reserved "should in general not be
+ * touched (e.g. set dirty) except by its owner".
+ */
+ return !PageReserved(pfn_to_page(pfn));
+}
+
+void kvm_set_pfn_dirty(kvm_pfn_t pfn)
+{
+ if (kvm_is_ad_tracked_pfn(pfn))
+ SetPageDirty(pfn_to_page(pfn));
+}
+EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty);
+
+void kvm_set_pfn_accessed(kvm_pfn_t pfn)
+{
+ if (kvm_is_ad_tracked_pfn(pfn))
+ mark_page_accessed(pfn_to_page(pfn));
+}
+EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed);
+
+void kvm_get_pfn(kvm_pfn_t pfn)
+{
+ if (!kvm_is_reserved_pfn(pfn))
+ get_page(pfn_to_page(pfn));
+}
+EXPORT_SYMBOL_GPL(kvm_get_pfn);
+
+static int next_segment(unsigned long len, int offset)
+{
+ if (len > PAGE_SIZE - offset)
+ return PAGE_SIZE - offset;
+ else
+ return len;
+}
+
+static int __kvm_read_guest_page(struct kvm_memory_slot *slot, gfn_t gfn,
+ void *data, int offset, int len)
+{
+ int r;
+ unsigned long addr;
+
+ addr = gfn_to_hva_memslot_prot(slot, gfn, NULL);
+ if (kvm_is_error_hva(addr))
+ return -EFAULT;
+ r = __copy_from_user(data, (void __user *)addr + offset, len);
+ if (r)
+ return -EFAULT;
+ return 0;
+}
+
+int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
+ int len)
+{
+ struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
+
+ return __kvm_read_guest_page(slot, gfn, data, offset, len);
+}
+EXPORT_SYMBOL_GPL(kvm_read_guest_page);
+
+int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data,
+ int offset, int len)
+{
+ struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
+
+ return __kvm_read_guest_page(slot, gfn, data, offset, len);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest_page);
+
+int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len)
+{
+ gfn_t gfn = gpa >> PAGE_SHIFT;
+ int seg;
+ int offset = offset_in_page(gpa);
+ int ret;
+
+ while ((seg = next_segment(len, offset)) != 0) {
+ ret = kvm_read_guest_page(kvm, gfn, data, offset, seg);
+ if (ret < 0)
+ return ret;
+ offset = 0;
+ len -= seg;
+ data += seg;
+ ++gfn;
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_read_guest);
+
+int kvm_vcpu_read_guest(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, unsigned long len)
+{
+ gfn_t gfn = gpa >> PAGE_SHIFT;
+ int seg;
+ int offset = offset_in_page(gpa);
+ int ret;
+
+ while ((seg = next_segment(len, offset)) != 0) {
+ ret = kvm_vcpu_read_guest_page(vcpu, gfn, data, offset, seg);
+ if (ret < 0)
+ return ret;
+ offset = 0;
+ len -= seg;
+ data += seg;
+ ++gfn;
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest);
+
+static int __kvm_read_guest_atomic(struct kvm_memory_slot *slot, gfn_t gfn,
+ void *data, int offset, unsigned long len)
+{
+ int r;
+ unsigned long addr;
+
+ addr = gfn_to_hva_memslot_prot(slot, gfn, NULL);
+ if (kvm_is_error_hva(addr))
+ return -EFAULT;
+ pagefault_disable();
+ r = __copy_from_user_inatomic(data, (void __user *)addr + offset, len);
+ pagefault_enable();
+ if (r)
+ return -EFAULT;
+ return 0;
+}
+
+int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa,
+ void *data, unsigned long len)
+{
+ gfn_t gfn = gpa >> PAGE_SHIFT;
+ struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
+ int offset = offset_in_page(gpa);
+
+ return __kvm_read_guest_atomic(slot, gfn, data, offset, len);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest_atomic);
+
+static int __kvm_write_guest_page(struct kvm_memory_slot *memslot, gfn_t gfn,
+ const void *data, int offset, int len)
+{
+ int r;
+ unsigned long addr;
+
+ addr = gfn_to_hva_memslot(memslot, gfn);
+ if (kvm_is_error_hva(addr))
+ return -EFAULT;
+ r = __copy_to_user((void __user *)addr + offset, data, len);
+ if (r)
+ return -EFAULT;
+ mark_page_dirty_in_slot(memslot, gfn);
+ return 0;
+}
+
+int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn,
+ const void *data, int offset, int len)
+{
+ struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
+
+ return __kvm_write_guest_page(slot, gfn, data, offset, len);
+}
+EXPORT_SYMBOL_GPL(kvm_write_guest_page);
+
+int kvm_vcpu_write_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn,
+ const void *data, int offset, int len)
+{
+ struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
+
+ return __kvm_write_guest_page(slot, gfn, data, offset, len);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_write_guest_page);
+
+int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data,
+ unsigned long len)
+{
+ gfn_t gfn = gpa >> PAGE_SHIFT;
+ int seg;
+ int offset = offset_in_page(gpa);
+ int ret;
+
+ while ((seg = next_segment(len, offset)) != 0) {
+ ret = kvm_write_guest_page(kvm, gfn, data, offset, seg);
+ if (ret < 0)
+ return ret;
+ offset = 0;
+ len -= seg;
+ data += seg;
+ ++gfn;
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_write_guest);
+
+int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data,
+ unsigned long len)
+{
+ gfn_t gfn = gpa >> PAGE_SHIFT;
+ int seg;
+ int offset = offset_in_page(gpa);
+ int ret;
+
+ while ((seg = next_segment(len, offset)) != 0) {
+ ret = kvm_vcpu_write_guest_page(vcpu, gfn, data, offset, seg);
+ if (ret < 0)
+ return ret;
+ offset = 0;
+ len -= seg;
+ data += seg;
+ ++gfn;
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_write_guest);
+
+static int __kvm_gfn_to_hva_cache_init(struct kvm_memslots *slots,
+ struct gfn_to_hva_cache *ghc,
+ gpa_t gpa, unsigned long len)
+{
+ int offset = offset_in_page(gpa);
+ gfn_t start_gfn = gpa >> PAGE_SHIFT;
+ gfn_t end_gfn = (gpa + len - 1) >> PAGE_SHIFT;
+ gfn_t nr_pages_needed = end_gfn - start_gfn + 1;
+ gfn_t nr_pages_avail;
+
+ /* Update ghc->generation before performing any error checks. */
+ ghc->generation = slots->generation;
+
+ if (start_gfn > end_gfn) {
+ ghc->hva = KVM_HVA_ERR_BAD;
+ return -EINVAL;
+ }
+
+ /*
+ * If the requested region crosses two memslots, we still
+ * verify that the entire region is valid here.
+ */
+ for ( ; start_gfn <= end_gfn; start_gfn += nr_pages_avail) {
+ ghc->memslot = __gfn_to_memslot(slots, start_gfn);
+ ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn,
+ &nr_pages_avail);
+ if (kvm_is_error_hva(ghc->hva))
+ return -EFAULT;
+ }
+
+ /* Use the slow path for cross page reads and writes. */
+ if (nr_pages_needed == 1)
+ ghc->hva += offset;
+ else
+ ghc->memslot = NULL;
+
+ ghc->gpa = gpa;
+ ghc->len = len;
+ return 0;
+}
+
+int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
+ gpa_t gpa, unsigned long len)
+{
+ struct kvm_memslots *slots = kvm_memslots(kvm);
+ return __kvm_gfn_to_hva_cache_init(slots, ghc, gpa, len);
+}
+EXPORT_SYMBOL_GPL(kvm_gfn_to_hva_cache_init);
+
+int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
+ void *data, unsigned int offset,
+ unsigned long len)
+{
+ struct kvm_memslots *slots = kvm_memslots(kvm);
+ int r;
+ gpa_t gpa = ghc->gpa + offset;
+
+ if (WARN_ON_ONCE(len + offset > ghc->len))
+ return -EINVAL;
+
+ if (slots->generation != ghc->generation) {
+ if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len))
+ return -EFAULT;
+ }
+
+ if (kvm_is_error_hva(ghc->hva))
+ return -EFAULT;
+
+ if (unlikely(!ghc->memslot))
+ return kvm_write_guest(kvm, gpa, data, len);
+
+ r = __copy_to_user((void __user *)ghc->hva + offset, data, len);
+ if (r)
+ return -EFAULT;
+ mark_page_dirty_in_slot(ghc->memslot, gpa >> PAGE_SHIFT);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_write_guest_offset_cached);
+
+int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
+ void *data, unsigned long len)
+{
+ return kvm_write_guest_offset_cached(kvm, ghc, data, 0, len);
+}
+EXPORT_SYMBOL_GPL(kvm_write_guest_cached);
+
+int kvm_read_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
+ void *data, unsigned int offset,
+ unsigned long len)
+{
+ struct kvm_memslots *slots = kvm_memslots(kvm);
+ int r;
+ gpa_t gpa = ghc->gpa + offset;
+
+ if (WARN_ON_ONCE(len + offset > ghc->len))
+ return -EINVAL;
+
+ if (slots->generation != ghc->generation) {
+ if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len))
+ return -EFAULT;
+ }
+
+ if (kvm_is_error_hva(ghc->hva))
+ return -EFAULT;
+
+ if (unlikely(!ghc->memslot))
+ return kvm_read_guest(kvm, gpa, data, len);
+
+ r = __copy_from_user(data, (void __user *)ghc->hva + offset, len);
+ if (r)
+ return -EFAULT;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_read_guest_offset_cached);
+
+int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
+ void *data, unsigned long len)
+{
+ return kvm_read_guest_offset_cached(kvm, ghc, data, 0, len);
+}
+EXPORT_SYMBOL_GPL(kvm_read_guest_cached);
+
+int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len)
+{
+ const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0)));
+
+ return kvm_write_guest_page(kvm, gfn, zero_page, offset, len);
+}
+EXPORT_SYMBOL_GPL(kvm_clear_guest_page);
+
+int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len)
+{
+ gfn_t gfn = gpa >> PAGE_SHIFT;
+ int seg;
+ int offset = offset_in_page(gpa);
+ int ret;
+
+ while ((seg = next_segment(len, offset)) != 0) {
+ ret = kvm_clear_guest_page(kvm, gfn, offset, seg);
+ if (ret < 0)
+ return ret;
+ offset = 0;
+ len -= seg;
+ ++gfn;
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_clear_guest);
+
+void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn)
+{
+ if (memslot && memslot->dirty_bitmap) {
+ unsigned long rel_gfn = gfn - memslot->base_gfn;
+
+ set_bit_le(rel_gfn, memslot->dirty_bitmap);
+ }
+}
+EXPORT_SYMBOL_GPL(mark_page_dirty_in_slot);
+
+void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
+{
+ struct kvm_memory_slot *memslot;
+
+ memslot = gfn_to_memslot(kvm, gfn);
+ mark_page_dirty_in_slot(memslot, gfn);
+}
+EXPORT_SYMBOL_GPL(mark_page_dirty);
+
+void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+ struct kvm_memory_slot *memslot;
+
+ memslot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
+ mark_page_dirty_in_slot(memslot, gfn);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_mark_page_dirty);
+
+void kvm_sigset_activate(struct kvm_vcpu *vcpu)
+{
+ if (!vcpu->sigset_active)
+ return;
+
+ /*
+ * This does a lockless modification of ->real_blocked, which is fine
+ * because, only current can change ->real_blocked and all readers of
+ * ->real_blocked don't care as long ->real_blocked is always a subset
+ * of ->blocked.
+ */
+ sigprocmask(SIG_SETMASK, &vcpu->sigset, &current->real_blocked);
+}
+
+void kvm_sigset_deactivate(struct kvm_vcpu *vcpu)
+{
+ if (!vcpu->sigset_active)
+ return;
+
+ sigprocmask(SIG_SETMASK, &current->real_blocked, NULL);
+ sigemptyset(&current->real_blocked);
+}
+
+static void grow_halt_poll_ns(struct kvm_vcpu *vcpu)
+{
+ unsigned int old, val, grow, grow_start;
+
+ old = val = vcpu->halt_poll_ns;
+ grow_start = READ_ONCE(halt_poll_ns_grow_start);
+ grow = READ_ONCE(halt_poll_ns_grow);
+ if (!grow)
+ goto out;
+
+ val *= grow;
+ if (val < grow_start)
+ val = grow_start;
+
+ if (val > vcpu->kvm->max_halt_poll_ns)
+ val = vcpu->kvm->max_halt_poll_ns;
+
+ vcpu->halt_poll_ns = val;
+out:
+ trace_kvm_halt_poll_ns_grow(vcpu->vcpu_id, val, old);
+}
+
+static void shrink_halt_poll_ns(struct kvm_vcpu *vcpu)
+{
+ unsigned int old, val, shrink, grow_start;
+
+ old = val = vcpu->halt_poll_ns;
+ shrink = READ_ONCE(halt_poll_ns_shrink);
+ grow_start = READ_ONCE(halt_poll_ns_grow_start);
+ if (shrink == 0)
+ val = 0;
+ else
+ val /= shrink;
+
+ if (val < grow_start)
+ val = 0;
+
+ vcpu->halt_poll_ns = val;
+ trace_kvm_halt_poll_ns_shrink(vcpu->vcpu_id, val, old);
+}
+
+static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu)
+{
+ int ret = -EINTR;
+ int idx = srcu_read_lock(&vcpu->kvm->srcu);
+
+ if (kvm_arch_vcpu_runnable(vcpu)) {
+ kvm_make_request(KVM_REQ_UNHALT, vcpu);
+ goto out;
+ }
+ if (kvm_cpu_has_pending_timer(vcpu))
+ goto out;
+ if (signal_pending(current))
+ goto out;
+
+ ret = 0;
+out:
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
+ return ret;
+}
+
+static inline void
+update_halt_poll_stats(struct kvm_vcpu *vcpu, u64 poll_ns, bool waited)
+{
+ if (waited)
+ vcpu->stat.halt_poll_fail_ns += poll_ns;
+ else
+ vcpu->stat.halt_poll_success_ns += poll_ns;
+}
+
+/*
+ * The vCPU has executed a HLT instruction with in-kernel mode enabled.
+ */
+void kvm_vcpu_block(struct kvm_vcpu *vcpu)
+{
+ ktime_t start, cur, poll_end;
+ bool waited = false;
+ u64 block_ns;
+
+ kvm_arch_vcpu_blocking(vcpu);
+
+ start = cur = poll_end = ktime_get();
+ if (vcpu->halt_poll_ns && !kvm_arch_no_poll(vcpu)) {
+ ktime_t stop = ktime_add_ns(ktime_get(), vcpu->halt_poll_ns);
+
+ ++vcpu->stat.halt_attempted_poll;
+ do {
+ /*
+ * This sets KVM_REQ_UNHALT if an interrupt
+ * arrives.
+ */
+ if (kvm_vcpu_check_block(vcpu) < 0) {
+ ++vcpu->stat.halt_successful_poll;
+ if (!vcpu_valid_wakeup(vcpu))
+ ++vcpu->stat.halt_poll_invalid;
+ goto out;
+ }
+ poll_end = cur = ktime_get();
+ } while (single_task_running() && !need_resched() &&
+ ktime_before(cur, stop));
+ }
+
+ prepare_to_rcuwait(&vcpu->wait);
+ for (;;) {
+ set_current_state(TASK_INTERRUPTIBLE);
+
+ if (kvm_vcpu_check_block(vcpu) < 0)
+ break;
+
+ waited = true;
+ schedule();
+ }
+ finish_rcuwait(&vcpu->wait);
+ cur = ktime_get();
+out:
+ kvm_arch_vcpu_unblocking(vcpu);
+ block_ns = ktime_to_ns(cur) - ktime_to_ns(start);
+
+ update_halt_poll_stats(
+ vcpu, ktime_to_ns(ktime_sub(poll_end, start)), waited);
+
+ if (!kvm_arch_no_poll(vcpu)) {
+ if (!vcpu_valid_wakeup(vcpu)) {
+ shrink_halt_poll_ns(vcpu);
+ } else if (vcpu->kvm->max_halt_poll_ns) {
+ if (block_ns <= vcpu->halt_poll_ns)
+ ;
+ /* we had a long block, shrink polling */
+ else if (vcpu->halt_poll_ns &&
+ block_ns > vcpu->kvm->max_halt_poll_ns)
+ shrink_halt_poll_ns(vcpu);
+ /* we had a short halt and our poll time is too small */
+ else if (vcpu->halt_poll_ns < vcpu->kvm->max_halt_poll_ns &&
+ block_ns < vcpu->kvm->max_halt_poll_ns)
+ grow_halt_poll_ns(vcpu);
+ } else {
+ vcpu->halt_poll_ns = 0;
+ }
+ }
+
+ trace_kvm_vcpu_wakeup(block_ns, waited, vcpu_valid_wakeup(vcpu));
+ kvm_arch_vcpu_block_finish(vcpu);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_block);
+
+bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu)
+{
+ struct rcuwait *waitp;
+
+ waitp = kvm_arch_vcpu_get_wait(vcpu);
+ if (rcuwait_wake_up(waitp)) {
+ WRITE_ONCE(vcpu->ready, true);
+ ++vcpu->stat.halt_wakeup;
+ return true;
+ }
+
+ return false;
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_wake_up);
+
+#ifndef CONFIG_S390
+/*
+ * Kick a sleeping VCPU, or a guest VCPU in guest mode, into host kernel mode.
+ */
+void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
+{
+ int me, cpu;
+
+ if (kvm_vcpu_wake_up(vcpu))
+ return;
+
+ /*
+ * Note, the vCPU could get migrated to a different pCPU at any point
+ * after kvm_arch_vcpu_should_kick(), which could result in sending an
+ * IPI to the previous pCPU. But, that's ok because the purpose of the
+ * IPI is to force the vCPU to leave IN_GUEST_MODE, and migrating the
+ * vCPU also requires it to leave IN_GUEST_MODE.
+ */
+ me = get_cpu();
+ if (kvm_arch_vcpu_should_kick(vcpu)) {
+ cpu = READ_ONCE(vcpu->cpu);
+ if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu))
+ smp_send_reschedule(cpu);
+ }
+ put_cpu();
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_kick);
+#endif /* !CONFIG_S390 */
+
+int kvm_vcpu_yield_to(struct kvm_vcpu *target)
+{
+ struct pid *pid;
+ struct task_struct *task = NULL;
+ int ret = 0;
+
+ rcu_read_lock();
+ pid = rcu_dereference(target->pid);
+ if (pid)
+ task = get_pid_task(pid, PIDTYPE_PID);
+ rcu_read_unlock();
+ if (!task)
+ return ret;
+ ret = yield_to(task, 1);
+ put_task_struct(task);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to);
+
+/*
+ * Helper that checks whether a VCPU is eligible for directed yield.
+ * Most eligible candidate to yield is decided by following heuristics:
+ *
+ * (a) VCPU which has not done pl-exit or cpu relax intercepted recently
+ * (preempted lock holder), indicated by @in_spin_loop.
+ * Set at the beginning and cleared at the end of interception/PLE handler.
+ *
+ * (b) VCPU which has done pl-exit/ cpu relax intercepted but did not get
+ * chance last time (mostly it has become eligible now since we have probably
+ * yielded to lockholder in last iteration. This is done by toggling
+ * @dy_eligible each time a VCPU checked for eligibility.)
+ *
+ * Yielding to a recently pl-exited/cpu relax intercepted VCPU before yielding
+ * to preempted lock-holder could result in wrong VCPU selection and CPU
+ * burning. Giving priority for a potential lock-holder increases lock
+ * progress.
+ *
+ * Since algorithm is based on heuristics, accessing another VCPU data without
+ * locking does not harm. It may result in trying to yield to same VCPU, fail
+ * and continue with next VCPU and so on.
+ */
+static bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
+ bool eligible;
+
+ eligible = !vcpu->spin_loop.in_spin_loop ||
+ vcpu->spin_loop.dy_eligible;
+
+ if (vcpu->spin_loop.in_spin_loop)
+ kvm_vcpu_set_dy_eligible(vcpu, !vcpu->spin_loop.dy_eligible);
+
+ return eligible;
+#else
+ return true;
+#endif
+}
+
+/*
+ * Unlike kvm_arch_vcpu_runnable, this function is called outside
+ * a vcpu_load/vcpu_put pair. However, for most architectures
+ * kvm_arch_vcpu_runnable does not require vcpu_load.
+ */
+bool __weak kvm_arch_dy_runnable(struct kvm_vcpu *vcpu)
+{
+ return kvm_arch_vcpu_runnable(vcpu);
+}
+
+static bool vcpu_dy_runnable(struct kvm_vcpu *vcpu)
+{
+ if (kvm_arch_dy_runnable(vcpu))
+ return true;
+
+#ifdef CONFIG_KVM_ASYNC_PF
+ if (!list_empty_careful(&vcpu->async_pf.done))
+ return true;
+#endif
+
+ return false;
+}
+
+void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode)
+{
+ struct kvm *kvm = me->kvm;
+ struct kvm_vcpu *vcpu;
+ int last_boosted_vcpu = me->kvm->last_boosted_vcpu;
+ int yielded = 0;
+ int try = 3;
+ int pass;
+ int i;
+
+ kvm_vcpu_set_in_spin_loop(me, true);
+ /*
+ * We boost the priority of a VCPU that is runnable but not
+ * currently running, because it got preempted by something
+ * else and called schedule in __vcpu_run. Hopefully that
+ * VCPU is holding the lock that we need and will release it.
+ * We approximate round-robin by starting at the last boosted VCPU.
+ */
+ for (pass = 0; pass < 2 && !yielded && try; pass++) {
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (!pass && i <= last_boosted_vcpu) {
+ i = last_boosted_vcpu;
+ continue;
+ } else if (pass && i > last_boosted_vcpu)
+ break;
+ if (!READ_ONCE(vcpu->ready))
+ continue;
+ if (vcpu == me)
+ continue;
+ if (rcuwait_active(&vcpu->wait) &&
+ !vcpu_dy_runnable(vcpu))
+ continue;
+ if (READ_ONCE(vcpu->preempted) && yield_to_kernel_mode &&
+ !kvm_arch_vcpu_in_kernel(vcpu))
+ continue;
+ if (!kvm_vcpu_eligible_for_directed_yield(vcpu))
+ continue;
+
+ yielded = kvm_vcpu_yield_to(vcpu);
+ if (yielded > 0) {
+ kvm->last_boosted_vcpu = i;
+ break;
+ } else if (yielded < 0) {
+ try--;
+ if (!try)
+ break;
+ }
+ }
+ }
+ kvm_vcpu_set_in_spin_loop(me, false);
+
+ /* Ensure vcpu is not eligible during next spinloop */
+ kvm_vcpu_set_dy_eligible(me, false);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin);
+
+static vm_fault_t kvm_vcpu_fault(struct vm_fault *vmf)
+{
+ struct kvm_vcpu *vcpu = vmf->vma->vm_file->private_data;
+ struct page *page;
+
+ if (vmf->pgoff == 0)
+ page = virt_to_page(vcpu->run);
+#ifdef CONFIG_X86
+ else if (vmf->pgoff == KVM_PIO_PAGE_OFFSET)
+ page = virt_to_page(vcpu->arch.pio_data);
+#endif
+#ifdef CONFIG_KVM_MMIO
+ else if (vmf->pgoff == KVM_COALESCED_MMIO_PAGE_OFFSET)
+ page = virt_to_page(vcpu->kvm->coalesced_mmio_ring);
+#endif
+ else
+ return kvm_arch_vcpu_fault(vcpu, vmf);
+ get_page(page);
+ vmf->page = page;
+ return 0;
+}
+
+static const struct vm_operations_struct kvm_vcpu_vm_ops = {
+ .fault = kvm_vcpu_fault,
+};
+
+static int kvm_vcpu_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ vma->vm_ops = &kvm_vcpu_vm_ops;
+ return 0;
+}
+
+static int kvm_vcpu_release(struct inode *inode, struct file *filp)
+{
+ struct kvm_vcpu *vcpu = filp->private_data;
+
+ kvm_put_kvm(vcpu->kvm);
+ return 0;
+}
+
+static struct file_operations kvm_vcpu_fops = {
+ .release = kvm_vcpu_release,
+ .unlocked_ioctl = kvm_vcpu_ioctl,
+ .mmap = kvm_vcpu_mmap,
+ .llseek = noop_llseek,
+ KVM_COMPAT(kvm_vcpu_compat_ioctl),
+};
+
+/*
+ * Allocates an inode for the vcpu.
+ */
+static int create_vcpu_fd(struct kvm_vcpu *vcpu)
+{
+ char name[8 + 1 + ITOA_MAX_LEN + 1];
+
+ snprintf(name, sizeof(name), "kvm-vcpu:%d", vcpu->vcpu_id);
+ return anon_inode_getfd(name, &kvm_vcpu_fops, vcpu, O_RDWR | O_CLOEXEC);
+}
+
+static void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
+{
+#ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS
+ struct dentry *debugfs_dentry;
+ char dir_name[ITOA_MAX_LEN * 2];
+
+ if (!debugfs_initialized())
+ return;
+
+ snprintf(dir_name, sizeof(dir_name), "vcpu%d", vcpu->vcpu_id);
+ debugfs_dentry = debugfs_create_dir(dir_name,
+ vcpu->kvm->debugfs_dentry);
+
+ kvm_arch_create_vcpu_debugfs(vcpu, debugfs_dentry);
+#endif
+}
+
+/*
+ * Creates some virtual cpus. Good luck creating more than one.
+ */
+static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
+{
+ int r;
+ struct kvm_vcpu *vcpu;
+ struct page *page;
+
+ if (id >= KVM_MAX_VCPU_ID)
+ return -EINVAL;
+
+ mutex_lock(&kvm->lock);
+ if (kvm->created_vcpus == KVM_MAX_VCPUS) {
+ mutex_unlock(&kvm->lock);
+ return -EINVAL;
+ }
+
+ kvm->created_vcpus++;
+ mutex_unlock(&kvm->lock);
+
+ r = kvm_arch_vcpu_precreate(kvm, id);
+ if (r)
+ goto vcpu_decrement;
+
+ vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
+ if (!vcpu) {
+ r = -ENOMEM;
+ goto vcpu_decrement;
+ }
+
+ BUILD_BUG_ON(sizeof(struct kvm_run) > PAGE_SIZE);
+ page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+ if (!page) {
+ r = -ENOMEM;
+ goto vcpu_free;
+ }
+ vcpu->run = page_address(page);
+
+ kvm_vcpu_init(vcpu, kvm, id);
+
+ r = kvm_arch_vcpu_create(vcpu);
+ if (r)
+ goto vcpu_free_run_page;
+
+ mutex_lock(&kvm->lock);
+ if (kvm_get_vcpu_by_id(kvm, id)) {
+ r = -EEXIST;
+ goto unlock_vcpu_destroy;
+ }
+
+ vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus);
+ BUG_ON(kvm->vcpus[vcpu->vcpu_idx]);
+
+ /* Now it's all set up, let userspace reach it */
+ kvm_get_kvm(kvm);
+ r = create_vcpu_fd(vcpu);
+ if (r < 0) {
+ kvm_put_kvm_no_destroy(kvm);
+ goto unlock_vcpu_destroy;
+ }
+
+ kvm->vcpus[vcpu->vcpu_idx] = vcpu;
+
+ /*
+ * Pairs with smp_rmb() in kvm_get_vcpu. Write kvm->vcpus
+ * before kvm->online_vcpu's incremented value.
+ */
+ smp_wmb();
+ atomic_inc(&kvm->online_vcpus);
+
+ mutex_unlock(&kvm->lock);
+ kvm_arch_vcpu_postcreate(vcpu);
+ kvm_create_vcpu_debugfs(vcpu);
+ return r;
+
+unlock_vcpu_destroy:
+ mutex_unlock(&kvm->lock);
+ kvm_arch_vcpu_destroy(vcpu);
+vcpu_free_run_page:
+ free_page((unsigned long)vcpu->run);
+vcpu_free:
+ kmem_cache_free(kvm_vcpu_cache, vcpu);
+vcpu_decrement:
+ mutex_lock(&kvm->lock);
+ kvm->created_vcpus--;
+ mutex_unlock(&kvm->lock);
+ return r;
+}
+
+static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset)
+{
+ if (sigset) {
+ sigdelsetmask(sigset, sigmask(SIGKILL)|sigmask(SIGSTOP));
+ vcpu->sigset_active = 1;
+ vcpu->sigset = *sigset;
+ } else
+ vcpu->sigset_active = 0;
+ return 0;
+}
+
+static long kvm_vcpu_ioctl(struct file *filp,
+ unsigned int ioctl, unsigned long arg)
+{
+ struct kvm_vcpu *vcpu = filp->private_data;
+ void __user *argp = (void __user *)arg;
+ int r;
+ struct kvm_fpu *fpu = NULL;
+ struct kvm_sregs *kvm_sregs = NULL;
+
+ if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_bugged)
+ return -EIO;
+
+ if (unlikely(_IOC_TYPE(ioctl) != KVMIO))
+ return -EINVAL;
+
+ /*
+ * Some architectures have vcpu ioctls that are asynchronous to vcpu
+ * execution; mutex_lock() would break them.
+ */
+ r = kvm_arch_vcpu_async_ioctl(filp, ioctl, arg);
+ if (r != -ENOIOCTLCMD)
+ return r;
+
+ if (mutex_lock_killable(&vcpu->mutex))
+ return -EINTR;
+ switch (ioctl) {
+ case KVM_RUN: {
+ struct pid *oldpid;
+ r = -EINVAL;
+ if (arg)
+ goto out;
+ oldpid = rcu_access_pointer(vcpu->pid);
+ if (unlikely(oldpid != task_pid(current))) {
+ /* The thread running this VCPU changed. */
+ struct pid *newpid;
+
+ r = kvm_arch_vcpu_run_pid_change(vcpu);
+ if (r)
+ break;
+
+ newpid = get_task_pid(current, PIDTYPE_PID);
+ rcu_assign_pointer(vcpu->pid, newpid);
+ if (oldpid)
+ synchronize_rcu();
+ put_pid(oldpid);
+ }
+ r = kvm_arch_vcpu_ioctl_run(vcpu);
+ trace_kvm_userspace_exit(vcpu->run->exit_reason, r);
+ break;
+ }
+ case KVM_GET_REGS: {
+ struct kvm_regs *kvm_regs;
+
+ r = -ENOMEM;
+ kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL_ACCOUNT);
+ if (!kvm_regs)
+ goto out;
+ r = kvm_arch_vcpu_ioctl_get_regs(vcpu, kvm_regs);
+ if (r)
+ goto out_free1;
+ r = -EFAULT;
+ if (copy_to_user(argp, kvm_regs, sizeof(struct kvm_regs)))
+ goto out_free1;
+ r = 0;
+out_free1:
+ kfree(kvm_regs);
+ break;
+ }
+ case KVM_SET_REGS: {
+ struct kvm_regs *kvm_regs;
+
+ kvm_regs = memdup_user(argp, sizeof(*kvm_regs));
+ if (IS_ERR(kvm_regs)) {
+ r = PTR_ERR(kvm_regs);
+ goto out;
+ }
+ r = kvm_arch_vcpu_ioctl_set_regs(vcpu, kvm_regs);
+ kfree(kvm_regs);
+ break;
+ }
+ case KVM_GET_SREGS: {
+ kvm_sregs = kzalloc(sizeof(struct kvm_sregs),
+ GFP_KERNEL_ACCOUNT);
+ r = -ENOMEM;
+ if (!kvm_sregs)
+ goto out;
+ r = kvm_arch_vcpu_ioctl_get_sregs(vcpu, kvm_sregs);
+ if (r)
+ goto out;
+ r = -EFAULT;
+ if (copy_to_user(argp, kvm_sregs, sizeof(struct kvm_sregs)))
+ goto out;
+ r = 0;
+ break;
+ }
+ case KVM_SET_SREGS: {
+ kvm_sregs = memdup_user(argp, sizeof(*kvm_sregs));
+ if (IS_ERR(kvm_sregs)) {
+ r = PTR_ERR(kvm_sregs);
+ kvm_sregs = NULL;
+ goto out;
+ }
+ r = kvm_arch_vcpu_ioctl_set_sregs(vcpu, kvm_sregs);
+ break;
+ }
+ case KVM_GET_MP_STATE: {
+ struct kvm_mp_state mp_state;
+
+ r = kvm_arch_vcpu_ioctl_get_mpstate(vcpu, &mp_state);
+ if (r)
+ goto out;
+ r = -EFAULT;
+ if (copy_to_user(argp, &mp_state, sizeof(mp_state)))
+ goto out;
+ r = 0;
+ break;
+ }
+ case KVM_SET_MP_STATE: {
+ struct kvm_mp_state mp_state;
+
+ r = -EFAULT;
+ if (copy_from_user(&mp_state, argp, sizeof(mp_state)))
+ goto out;
+ r = kvm_arch_vcpu_ioctl_set_mpstate(vcpu, &mp_state);
+ break;
+ }
+ case KVM_TRANSLATE: {
+ struct kvm_translation tr;
+
+ r = -EFAULT;
+ if (copy_from_user(&tr, argp, sizeof(tr)))
+ goto out;
+ r = kvm_arch_vcpu_ioctl_translate(vcpu, &tr);
+ if (r)
+ goto out;
+ r = -EFAULT;
+ if (copy_to_user(argp, &tr, sizeof(tr)))
+ goto out;
+ r = 0;
+ break;
+ }
+ case KVM_SET_GUEST_DEBUG: {
+ struct kvm_guest_debug dbg;
+
+ r = -EFAULT;
+ if (copy_from_user(&dbg, argp, sizeof(dbg)))
+ goto out;
+ r = kvm_arch_vcpu_ioctl_set_guest_debug(vcpu, &dbg);
+ break;
+ }
+ case KVM_SET_SIGNAL_MASK: {
+ struct kvm_signal_mask __user *sigmask_arg = argp;
+ struct kvm_signal_mask kvm_sigmask;
+ sigset_t sigset, *p;
+
+ p = NULL;
+ if (argp) {
+ r = -EFAULT;
+ if (copy_from_user(&kvm_sigmask, argp,
+ sizeof(kvm_sigmask)))
+ goto out;
+ r = -EINVAL;
+ if (kvm_sigmask.len != sizeof(sigset))
+ goto out;
+ r = -EFAULT;
+ if (copy_from_user(&sigset, sigmask_arg->sigset,
+ sizeof(sigset)))
+ goto out;
+ p = &sigset;
+ }
+ r = kvm_vcpu_ioctl_set_sigmask(vcpu, p);
+ break;
+ }
+ case KVM_GET_FPU: {
+ fpu = kzalloc(sizeof(struct kvm_fpu), GFP_KERNEL_ACCOUNT);
+ r = -ENOMEM;
+ if (!fpu)
+ goto out;
+ r = kvm_arch_vcpu_ioctl_get_fpu(vcpu, fpu);
+ if (r)
+ goto out;
+ r = -EFAULT;
+ if (copy_to_user(argp, fpu, sizeof(struct kvm_fpu)))
+ goto out;
+ r = 0;
+ break;
+ }
+ case KVM_SET_FPU: {
+ fpu = memdup_user(argp, sizeof(*fpu));
+ if (IS_ERR(fpu)) {
+ r = PTR_ERR(fpu);
+ fpu = NULL;
+ goto out;
+ }
+ r = kvm_arch_vcpu_ioctl_set_fpu(vcpu, fpu);
+ break;
+ }
+ default:
+ r = kvm_arch_vcpu_ioctl(filp, ioctl, arg);
+ }
+out:
+ mutex_unlock(&vcpu->mutex);
+ kfree(fpu);
+ kfree(kvm_sregs);
+ return r;
+}
+
+#ifdef CONFIG_KVM_COMPAT
+static long kvm_vcpu_compat_ioctl(struct file *filp,
+ unsigned int ioctl, unsigned long arg)
+{
+ struct kvm_vcpu *vcpu = filp->private_data;
+ void __user *argp = compat_ptr(arg);
+ int r;
+
+ if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_bugged)
+ return -EIO;
+
+ switch (ioctl) {
+ case KVM_SET_SIGNAL_MASK: {
+ struct kvm_signal_mask __user *sigmask_arg = argp;
+ struct kvm_signal_mask kvm_sigmask;
+ sigset_t sigset;
+
+ if (argp) {
+ r = -EFAULT;
+ if (copy_from_user(&kvm_sigmask, argp,
+ sizeof(kvm_sigmask)))
+ goto out;
+ r = -EINVAL;
+ if (kvm_sigmask.len != sizeof(compat_sigset_t))
+ goto out;
+ r = -EFAULT;
+ if (get_compat_sigset(&sigset,
+ (compat_sigset_t __user *)sigmask_arg->sigset))
+ goto out;
+ r = kvm_vcpu_ioctl_set_sigmask(vcpu, &sigset);
+ } else
+ r = kvm_vcpu_ioctl_set_sigmask(vcpu, NULL);
+ break;
+ }
+ default:
+ r = kvm_vcpu_ioctl(filp, ioctl, arg);
+ }
+
+out:
+ return r;
+}
+#endif
+
+static int kvm_device_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+ struct kvm_device *dev = filp->private_data;
+
+ if (dev->ops->mmap)
+ return dev->ops->mmap(dev, vma);
+
+ return -ENODEV;
+}
+
+static int kvm_device_ioctl_attr(struct kvm_device *dev,
+ int (*accessor)(struct kvm_device *dev,
+ struct kvm_device_attr *attr),
+ unsigned long arg)
+{
+ struct kvm_device_attr attr;
+
+ if (!accessor)
+ return -EPERM;
+
+ if (copy_from_user(&attr, (void __user *)arg, sizeof(attr)))
+ return -EFAULT;
+
+ return accessor(dev, &attr);
+}
+
+static long kvm_device_ioctl(struct file *filp, unsigned int ioctl,
+ unsigned long arg)
+{
+ struct kvm_device *dev = filp->private_data;
+
+ if (dev->kvm->mm != current->mm || dev->kvm->vm_bugged)
+ return -EIO;
+
+ switch (ioctl) {
+ case KVM_SET_DEVICE_ATTR:
+ return kvm_device_ioctl_attr(dev, dev->ops->set_attr, arg);
+ case KVM_GET_DEVICE_ATTR:
+ return kvm_device_ioctl_attr(dev, dev->ops->get_attr, arg);
+ case KVM_HAS_DEVICE_ATTR:
+ return kvm_device_ioctl_attr(dev, dev->ops->has_attr, arg);
+ default:
+ if (dev->ops->ioctl)
+ return dev->ops->ioctl(dev, ioctl, arg);
+
+ return -ENOTTY;
+ }
+}
+
+static int kvm_device_release(struct inode *inode, struct file *filp)
+{
+ struct kvm_device *dev = filp->private_data;
+ struct kvm *kvm = dev->kvm;
+
+ if (dev->ops->release) {
+ mutex_lock(&kvm->lock);
+ list_del(&dev->vm_node);
+ dev->ops->release(dev);
+ mutex_unlock(&kvm->lock);
+ }
+
+ kvm_put_kvm(kvm);
+ return 0;
+}
+
+static const struct file_operations kvm_device_fops = {
+ .unlocked_ioctl = kvm_device_ioctl,
+ .release = kvm_device_release,
+ KVM_COMPAT(kvm_device_ioctl),
+ .mmap = kvm_device_mmap,
+};
+
+struct kvm_device *kvm_device_from_filp(struct file *filp)
+{
+ if (filp->f_op != &kvm_device_fops)
+ return NULL;
+
+ return filp->private_data;
+}
+
+static const struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = {
+#ifdef CONFIG_KVM_MPIC
+ [KVM_DEV_TYPE_FSL_MPIC_20] = &kvm_mpic_ops,
+ [KVM_DEV_TYPE_FSL_MPIC_42] = &kvm_mpic_ops,
+#endif
+};
+
+int kvm_register_device_ops(const struct kvm_device_ops *ops, u32 type)
+{
+ if (type >= ARRAY_SIZE(kvm_device_ops_table))
+ return -ENOSPC;
+
+ if (kvm_device_ops_table[type] != NULL)
+ return -EEXIST;
+
+ kvm_device_ops_table[type] = ops;
+ return 0;
+}
+
+void kvm_unregister_device_ops(u32 type)
+{
+ if (kvm_device_ops_table[type] != NULL)
+ kvm_device_ops_table[type] = NULL;
+}
+
+static int kvm_ioctl_create_device(struct kvm *kvm,
+ struct kvm_create_device *cd)
+{
+ const struct kvm_device_ops *ops = NULL;
+ struct kvm_device *dev;
+ bool test = cd->flags & KVM_CREATE_DEVICE_TEST;
+ int type;
+ int ret;
+
+ if (cd->type >= ARRAY_SIZE(kvm_device_ops_table))
+ return -ENODEV;
+
+ type = array_index_nospec(cd->type, ARRAY_SIZE(kvm_device_ops_table));
+ ops = kvm_device_ops_table[type];
+ if (ops == NULL)
+ return -ENODEV;
+
+ if (test)
+ return 0;
+
+ dev = kzalloc(sizeof(*dev), GFP_KERNEL_ACCOUNT);
+ if (!dev)
+ return -ENOMEM;
+
+ dev->ops = ops;
+ dev->kvm = kvm;
+
+ mutex_lock(&kvm->lock);
+ ret = ops->create(dev, type);
+ if (ret < 0) {
+ mutex_unlock(&kvm->lock);
+ kfree(dev);
+ return ret;
+ }
+ list_add(&dev->vm_node, &kvm->devices);
+ mutex_unlock(&kvm->lock);
+
+ if (ops->init)
+ ops->init(dev);
+
+ kvm_get_kvm(kvm);
+ ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC);
+ if (ret < 0) {
+ kvm_put_kvm_no_destroy(kvm);
+ mutex_lock(&kvm->lock);
+ list_del(&dev->vm_node);
+ if (ops->release)
+ ops->release(dev);
+ mutex_unlock(&kvm->lock);
+ if (ops->destroy)
+ ops->destroy(dev);
+ return ret;
+ }
+
+ cd->fd = ret;
+ return 0;
+}
+
+static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
+{
+ switch (arg) {
+ case KVM_CAP_USER_MEMORY:
+ case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
+ case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS:
+ case KVM_CAP_INTERNAL_ERROR_DATA:
+#ifdef CONFIG_HAVE_KVM_MSI
+ case KVM_CAP_SIGNAL_MSI:
+#endif
+#ifdef CONFIG_HAVE_KVM_IRQFD
+ case KVM_CAP_IRQFD:
+ case KVM_CAP_IRQFD_RESAMPLE:
+#endif
+ case KVM_CAP_IOEVENTFD_ANY_LENGTH:
+ case KVM_CAP_CHECK_EXTENSION_VM:
+ case KVM_CAP_ENABLE_CAP_VM:
+ case KVM_CAP_HALT_POLL:
+ return 1;
+#ifdef CONFIG_KVM_MMIO
+ case KVM_CAP_COALESCED_MMIO:
+ return KVM_COALESCED_MMIO_PAGE_OFFSET;
+ case KVM_CAP_COALESCED_PIO:
+ return 1;
+#endif
+#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
+ case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2:
+ return KVM_DIRTY_LOG_MANUAL_CAPS;
+#endif
+#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
+ case KVM_CAP_IRQ_ROUTING:
+ return KVM_MAX_IRQ_ROUTES;
+#endif
+#if KVM_ADDRESS_SPACE_NUM > 1
+ case KVM_CAP_MULTI_ADDRESS_SPACE:
+ return KVM_ADDRESS_SPACE_NUM;
+#endif
+ case KVM_CAP_NR_MEMSLOTS:
+ return KVM_USER_MEM_SLOTS;
+ default:
+ break;
+ }
+ return kvm_vm_ioctl_check_extension(kvm, arg);
+}
+
+int __attribute__((weak)) kvm_vm_ioctl_enable_cap(struct kvm *kvm,
+ struct kvm_enable_cap *cap)
+{
+ return -EINVAL;
+}
+
+static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm,
+ struct kvm_enable_cap *cap)
+{
+ switch (cap->cap) {
+#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
+ case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2: {
+ u64 allowed_options = KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE;
+
+ if (cap->args[0] & KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE)
+ allowed_options = KVM_DIRTY_LOG_MANUAL_CAPS;
+
+ if (cap->flags || (cap->args[0] & ~allowed_options))
+ return -EINVAL;
+ kvm->manual_dirty_log_protect = cap->args[0];
+ return 0;
+ }
+#endif
+ case KVM_CAP_HALT_POLL: {
+ if (cap->flags || cap->args[0] != (unsigned int)cap->args[0])
+ return -EINVAL;
+
+ kvm->max_halt_poll_ns = cap->args[0];
+ return 0;
+ }
+ default:
+ return kvm_vm_ioctl_enable_cap(kvm, cap);
+ }
+}
+
+static long kvm_vm_ioctl(struct file *filp,
+ unsigned int ioctl, unsigned long arg)
+{
+ struct kvm *kvm = filp->private_data;
+ void __user *argp = (void __user *)arg;
+ int r;
+
+ if (kvm->mm != current->mm || kvm->vm_bugged)
+ return -EIO;
+ switch (ioctl) {
+ case KVM_CREATE_VCPU:
+ r = kvm_vm_ioctl_create_vcpu(kvm, arg);
+ break;
+ case KVM_ENABLE_CAP: {
+ struct kvm_enable_cap cap;
+
+ r = -EFAULT;
+ if (copy_from_user(&cap, argp, sizeof(cap)))
+ goto out;
+ r = kvm_vm_ioctl_enable_cap_generic(kvm, &cap);
+ break;
+ }
+ case KVM_SET_USER_MEMORY_REGION: {
+ struct kvm_userspace_memory_region kvm_userspace_mem;
+
+ r = -EFAULT;
+ if (copy_from_user(&kvm_userspace_mem, argp,
+ sizeof(kvm_userspace_mem)))
+ goto out;
+
+ r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem);
+ break;
+ }
+ case KVM_GET_DIRTY_LOG: {
+ struct kvm_dirty_log log;
+
+ r = -EFAULT;
+ if (copy_from_user(&log, argp, sizeof(log)))
+ goto out;
+ r = kvm_vm_ioctl_get_dirty_log(kvm, &log);
+ break;
+ }
+#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
+ case KVM_CLEAR_DIRTY_LOG: {
+ struct kvm_clear_dirty_log log;
+
+ r = -EFAULT;
+ if (copy_from_user(&log, argp, sizeof(log)))
+ goto out;
+ r = kvm_vm_ioctl_clear_dirty_log(kvm, &log);
+ break;
+ }
+#endif
+#ifdef CONFIG_KVM_MMIO
+ case KVM_REGISTER_COALESCED_MMIO: {
+ struct kvm_coalesced_mmio_zone zone;
+
+ r = -EFAULT;
+ if (copy_from_user(&zone, argp, sizeof(zone)))
+ goto out;
+ r = kvm_vm_ioctl_register_coalesced_mmio(kvm, &zone);
+ break;
+ }
+ case KVM_UNREGISTER_COALESCED_MMIO: {
+ struct kvm_coalesced_mmio_zone zone;
+
+ r = -EFAULT;
+ if (copy_from_user(&zone, argp, sizeof(zone)))
+ goto out;
+ r = kvm_vm_ioctl_unregister_coalesced_mmio(kvm, &zone);
+ break;
+ }
+#endif
+ case KVM_IRQFD: {
+ struct kvm_irqfd data;
+
+ r = -EFAULT;
+ if (copy_from_user(&data, argp, sizeof(data)))
+ goto out;
+ r = kvm_irqfd(kvm, &data);
+ break;
+ }
+ case KVM_IOEVENTFD: {
+ struct kvm_ioeventfd data;
+
+ r = -EFAULT;
+ if (copy_from_user(&data, argp, sizeof(data)))
+ goto out;
+ r = kvm_ioeventfd(kvm, &data);
+ break;
+ }
+#ifdef CONFIG_HAVE_KVM_MSI
+ case KVM_SIGNAL_MSI: {
+ struct kvm_msi msi;
+
+ r = -EFAULT;
+ if (copy_from_user(&msi, argp, sizeof(msi)))
+ goto out;
+ r = kvm_send_userspace_msi(kvm, &msi);
+ break;
+ }
+#endif
+#ifdef __KVM_HAVE_IRQ_LINE
+ case KVM_IRQ_LINE_STATUS:
+ case KVM_IRQ_LINE: {
+ struct kvm_irq_level irq_event;
+
+ r = -EFAULT;
+ if (copy_from_user(&irq_event, argp, sizeof(irq_event)))
+ goto out;
+
+ r = kvm_vm_ioctl_irq_line(kvm, &irq_event,
+ ioctl == KVM_IRQ_LINE_STATUS);
+ if (r)
+ goto out;
+
+ r = -EFAULT;
+ if (ioctl == KVM_IRQ_LINE_STATUS) {
+ if (copy_to_user(argp, &irq_event, sizeof(irq_event)))
+ goto out;
+ }
+
+ r = 0;
+ break;
+ }
+#endif
+#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
+ case KVM_SET_GSI_ROUTING: {
+ struct kvm_irq_routing routing;
+ struct kvm_irq_routing __user *urouting;
+ struct kvm_irq_routing_entry *entries = NULL;
+
+ r = -EFAULT;
+ if (copy_from_user(&routing, argp, sizeof(routing)))
+ goto out;
+ r = -EINVAL;
+ if (!kvm_arch_can_set_irq_routing(kvm))
+ goto out;
+ if (routing.nr > KVM_MAX_IRQ_ROUTES)
+ goto out;
+ if (routing.flags)
+ goto out;
+ if (routing.nr) {
+ urouting = argp;
+ entries = vmemdup_user(urouting->entries,
+ array_size(sizeof(*entries),
+ routing.nr));
+ if (IS_ERR(entries)) {
+ r = PTR_ERR(entries);
+ goto out;
+ }
+ }
+ r = kvm_set_irq_routing(kvm, entries, routing.nr,
+ routing.flags);
+ kvfree(entries);
+ break;
+ }
+#endif /* CONFIG_HAVE_KVM_IRQ_ROUTING */
+ case KVM_CREATE_DEVICE: {
+ struct kvm_create_device cd;
+
+ r = -EFAULT;
+ if (copy_from_user(&cd, argp, sizeof(cd)))
+ goto out;
+
+ r = kvm_ioctl_create_device(kvm, &cd);
+ if (r)
+ goto out;
+
+ r = -EFAULT;
+ if (copy_to_user(argp, &cd, sizeof(cd)))
+ goto out;
+
+ r = 0;
+ break;
+ }
+ case KVM_CHECK_EXTENSION:
+ r = kvm_vm_ioctl_check_extension_generic(kvm, arg);
+ break;
+ default:
+ r = kvm_arch_vm_ioctl(filp, ioctl, arg);
+ }
+out:
+ return r;
+}
+
+#ifdef CONFIG_KVM_COMPAT
+struct compat_kvm_dirty_log {
+ __u32 slot;
+ __u32 padding1;
+ union {
+ compat_uptr_t dirty_bitmap; /* one bit per page */
+ __u64 padding2;
+ };
+};
+
+struct compat_kvm_clear_dirty_log {
+ __u32 slot;
+ __u32 num_pages;
+ __u64 first_page;
+ union {
+ compat_uptr_t dirty_bitmap; /* one bit per page */
+ __u64 padding2;
+ };
+};
+
+long __weak kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl,
+ unsigned long arg)
+{
+ return -ENOTTY;
+}
+
+static long kvm_vm_compat_ioctl(struct file *filp,
+ unsigned int ioctl, unsigned long arg)
+{
+ struct kvm *kvm = filp->private_data;
+ int r;
+
+ if (kvm->mm != current->mm || kvm->vm_bugged)
+ return -EIO;
+
+ r = kvm_arch_vm_compat_ioctl(filp, ioctl, arg);
+ if (r != -ENOTTY)
+ return r;
+
+ switch (ioctl) {
+#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
+ case KVM_CLEAR_DIRTY_LOG: {
+ struct compat_kvm_clear_dirty_log compat_log;
+ struct kvm_clear_dirty_log log;
+
+ if (copy_from_user(&compat_log, (void __user *)arg,
+ sizeof(compat_log)))
+ return -EFAULT;
+ log.slot = compat_log.slot;
+ log.num_pages = compat_log.num_pages;
+ log.first_page = compat_log.first_page;
+ log.padding2 = compat_log.padding2;
+ log.dirty_bitmap = compat_ptr(compat_log.dirty_bitmap);
+
+ r = kvm_vm_ioctl_clear_dirty_log(kvm, &log);
+ break;
+ }
+#endif
+ case KVM_GET_DIRTY_LOG: {
+ struct compat_kvm_dirty_log compat_log;
+ struct kvm_dirty_log log;
+
+ if (copy_from_user(&compat_log, (void __user *)arg,
+ sizeof(compat_log)))
+ return -EFAULT;
+ log.slot = compat_log.slot;
+ log.padding1 = compat_log.padding1;
+ log.padding2 = compat_log.padding2;
+ log.dirty_bitmap = compat_ptr(compat_log.dirty_bitmap);
+
+ r = kvm_vm_ioctl_get_dirty_log(kvm, &log);
+ break;
+ }
+ default:
+ r = kvm_vm_ioctl(filp, ioctl, arg);
+ }
+ return r;
+}
+#endif
+
+static struct file_operations kvm_vm_fops = {
+ .release = kvm_vm_release,
+ .unlocked_ioctl = kvm_vm_ioctl,
+ .llseek = noop_llseek,
+ KVM_COMPAT(kvm_vm_compat_ioctl),
+};
+
+static int kvm_dev_ioctl_create_vm(unsigned long type)
+{
+ int r;
+ struct kvm *kvm;
+ struct file *file;
+
+ kvm = kvm_create_vm(type);
+ if (IS_ERR(kvm))
+ return PTR_ERR(kvm);
+#ifdef CONFIG_KVM_MMIO
+ r = kvm_coalesced_mmio_init(kvm);
+ if (r < 0)
+ goto put_kvm;
+#endif
+ r = get_unused_fd_flags(O_CLOEXEC);
+ if (r < 0)
+ goto put_kvm;
+
+ file = anon_inode_getfile("kvm-vm", &kvm_vm_fops, kvm, O_RDWR);
+ if (IS_ERR(file)) {
+ put_unused_fd(r);
+ r = PTR_ERR(file);
+ goto put_kvm;
+ }
+
+ /*
+ * Don't call kvm_put_kvm anymore at this point; file->f_op is
+ * already set, with ->release() being kvm_vm_release(). In error
+ * cases it will be called by the final fput(file) and will take
+ * care of doing kvm_put_kvm(kvm).
+ */
+ if (kvm_create_vm_debugfs(kvm, r) < 0) {
+ put_unused_fd(r);
+ fput(file);
+ return -ENOMEM;
+ }
+ kvm_uevent_notify_change(KVM_EVENT_CREATE_VM, kvm);
+
+ fd_install(r, file);
+ return r;
+
+put_kvm:
+ kvm_put_kvm(kvm);
+ return r;
+}
+
+static long kvm_dev_ioctl(struct file *filp,
+ unsigned int ioctl, unsigned long arg)
+{
+ long r = -EINVAL;
+
+ switch (ioctl) {
+ case KVM_GET_API_VERSION:
+ if (arg)
+ goto out;
+ r = KVM_API_VERSION;
+ break;
+ case KVM_CREATE_VM:
+ r = kvm_dev_ioctl_create_vm(arg);
+ break;
+ case KVM_CHECK_EXTENSION:
+ r = kvm_vm_ioctl_check_extension_generic(NULL, arg);
+ break;
+ case KVM_GET_VCPU_MMAP_SIZE:
+ if (arg)
+ goto out;
+ r = PAGE_SIZE; /* struct kvm_run */
+#ifdef CONFIG_X86
+ r += PAGE_SIZE; /* pio data page */
+#endif
+#ifdef CONFIG_KVM_MMIO
+ r += PAGE_SIZE; /* coalesced mmio ring page */
+#endif
+ break;
+ case KVM_TRACE_ENABLE:
+ case KVM_TRACE_PAUSE:
+ case KVM_TRACE_DISABLE:
+ r = -EOPNOTSUPP;
+ break;
+ default:
+ return kvm_arch_dev_ioctl(filp, ioctl, arg);
+ }
+out:
+ return r;
+}
+
+static struct file_operations kvm_chardev_ops = {
+ .unlocked_ioctl = kvm_dev_ioctl,
+ .llseek = noop_llseek,
+ KVM_COMPAT(kvm_dev_ioctl),
+};
+
+static struct miscdevice kvm_dev = {
+ KVM_MINOR,
+ "kvm",
+ &kvm_chardev_ops,
+};
+
+static void hardware_enable_nolock(void *junk)
+{
+ int cpu = raw_smp_processor_id();
+ int r;
+
+ if (cpumask_test_cpu(cpu, cpus_hardware_enabled))
+ return;
+
+ cpumask_set_cpu(cpu, cpus_hardware_enabled);
+
+ r = kvm_arch_hardware_enable();
+
+ if (r) {
+ cpumask_clear_cpu(cpu, cpus_hardware_enabled);
+ atomic_inc(&hardware_enable_failed);
+ pr_info("kvm: enabling virtualization on CPU%d failed\n", cpu);
+ }
+}
+
+static int kvm_starting_cpu(unsigned int cpu)
+{
+ raw_spin_lock(&kvm_count_lock);
+ if (kvm_usage_count)
+ hardware_enable_nolock(NULL);
+ raw_spin_unlock(&kvm_count_lock);
+ return 0;
+}
+
+static void hardware_disable_nolock(void *junk)
+{
+ int cpu = raw_smp_processor_id();
+
+ if (!cpumask_test_cpu(cpu, cpus_hardware_enabled))
+ return;
+ cpumask_clear_cpu(cpu, cpus_hardware_enabled);
+ kvm_arch_hardware_disable();
+}
+
+static int kvm_dying_cpu(unsigned int cpu)
+{
+ raw_spin_lock(&kvm_count_lock);
+ if (kvm_usage_count)
+ hardware_disable_nolock(NULL);
+ raw_spin_unlock(&kvm_count_lock);
+ return 0;
+}
+
+static void hardware_disable_all_nolock(void)
+{
+ BUG_ON(!kvm_usage_count);
+
+ kvm_usage_count--;
+ if (!kvm_usage_count)
+ on_each_cpu(hardware_disable_nolock, NULL, 1);
+}
+
+static void hardware_disable_all(void)
+{
+ raw_spin_lock(&kvm_count_lock);
+ hardware_disable_all_nolock();
+ raw_spin_unlock(&kvm_count_lock);
+}
+
+static int hardware_enable_all(void)
+{
+ int r = 0;
+
+ raw_spin_lock(&kvm_count_lock);
+
+ kvm_usage_count++;
+ if (kvm_usage_count == 1) {
+ atomic_set(&hardware_enable_failed, 0);
+ on_each_cpu(hardware_enable_nolock, NULL, 1);
+
+ if (atomic_read(&hardware_enable_failed)) {
+ hardware_disable_all_nolock();
+ r = -EBUSY;
+ }
+ }
+
+ raw_spin_unlock(&kvm_count_lock);
+
+ return r;
+}
+
+static int kvm_reboot(struct notifier_block *notifier, unsigned long val,
+ void *v)
+{
+ /*
+ * Some (well, at least mine) BIOSes hang on reboot if
+ * in vmx root mode.
+ *
+ * And Intel TXT required VMX off for all cpu when system shutdown.
+ */
+ pr_info("kvm: exiting hardware virtualization\n");
+ kvm_rebooting = true;
+ on_each_cpu(hardware_disable_nolock, NULL, 1);
+ return NOTIFY_OK;
+}
+
+static struct notifier_block kvm_reboot_notifier = {
+ .notifier_call = kvm_reboot,
+ .priority = 0,
+};
+
+static void kvm_io_bus_destroy(struct kvm_io_bus *bus)
+{
+ int i;
+
+ for (i = 0; i < bus->dev_count; i++) {
+ struct kvm_io_device *pos = bus->range[i].dev;
+
+ kvm_iodevice_destructor(pos);
+ }
+ kfree(bus);
+}
+
+static inline int kvm_io_bus_cmp(const struct kvm_io_range *r1,
+ const struct kvm_io_range *r2)
+{
+ gpa_t addr1 = r1->addr;
+ gpa_t addr2 = r2->addr;
+
+ if (addr1 < addr2)
+ return -1;
+
+ /* If r2->len == 0, match the exact address. If r2->len != 0,
+ * accept any overlapping write. Any order is acceptable for
+ * overlapping ranges, because kvm_io_bus_get_first_dev ensures
+ * we process all of them.
+ */
+ if (r2->len) {
+ addr1 += r1->len;
+ addr2 += r2->len;
+ }
+
+ if (addr1 > addr2)
+ return 1;
+
+ return 0;
+}
+
+static int kvm_io_bus_sort_cmp(const void *p1, const void *p2)
+{
+ return kvm_io_bus_cmp(p1, p2);
+}
+
+static int kvm_io_bus_get_first_dev(struct kvm_io_bus *bus,
+ gpa_t addr, int len)
+{
+ struct kvm_io_range *range, key;
+ int off;
+
+ key = (struct kvm_io_range) {
+ .addr = addr,
+ .len = len,
+ };
+
+ range = bsearch(&key, bus->range, bus->dev_count,
+ sizeof(struct kvm_io_range), kvm_io_bus_sort_cmp);
+ if (range == NULL)
+ return -ENOENT;
+
+ off = range - bus->range;
+
+ while (off > 0 && kvm_io_bus_cmp(&key, &bus->range[off-1]) == 0)
+ off--;
+
+ return off;
+}
+
+static int __kvm_io_bus_write(struct kvm_vcpu *vcpu, struct kvm_io_bus *bus,
+ struct kvm_io_range *range, const void *val)
+{
+ int idx;
+
+ idx = kvm_io_bus_get_first_dev(bus, range->addr, range->len);
+ if (idx < 0)
+ return -EOPNOTSUPP;
+
+ while (idx < bus->dev_count &&
+ kvm_io_bus_cmp(range, &bus->range[idx]) == 0) {
+ if (!kvm_iodevice_write(vcpu, bus->range[idx].dev, range->addr,
+ range->len, val))
+ return idx;
+ idx++;
+ }
+
+ return -EOPNOTSUPP;
+}
+
+/* kvm_io_bus_write - called under kvm->slots_lock */
+int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
+ int len, const void *val)
+{
+ struct kvm_io_bus *bus;
+ struct kvm_io_range range;
+ int r;
+
+ range = (struct kvm_io_range) {
+ .addr = addr,
+ .len = len,
+ };
+
+ bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu);
+ if (!bus)
+ return -ENOMEM;
+ r = __kvm_io_bus_write(vcpu, bus, &range, val);
+ return r < 0 ? r : 0;
+}
+EXPORT_SYMBOL_GPL(kvm_io_bus_write);
+
+/* kvm_io_bus_write_cookie - called under kvm->slots_lock */
+int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx,
+ gpa_t addr, int len, const void *val, long cookie)
+{
+ struct kvm_io_bus *bus;
+ struct kvm_io_range range;
+
+ range = (struct kvm_io_range) {
+ .addr = addr,
+ .len = len,
+ };
+
+ bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu);
+ if (!bus)
+ return -ENOMEM;
+
+ /* First try the device referenced by cookie. */
+ if ((cookie >= 0) && (cookie < bus->dev_count) &&
+ (kvm_io_bus_cmp(&range, &bus->range[cookie]) == 0))
+ if (!kvm_iodevice_write(vcpu, bus->range[cookie].dev, addr, len,
+ val))
+ return cookie;
+
+ /*
+ * cookie contained garbage; fall back to search and return the
+ * correct cookie value.
+ */
+ return __kvm_io_bus_write(vcpu, bus, &range, val);
+}
+
+static int __kvm_io_bus_read(struct kvm_vcpu *vcpu, struct kvm_io_bus *bus,
+ struct kvm_io_range *range, void *val)
+{
+ int idx;
+
+ idx = kvm_io_bus_get_first_dev(bus, range->addr, range->len);
+ if (idx < 0)
+ return -EOPNOTSUPP;
+
+ while (idx < bus->dev_count &&
+ kvm_io_bus_cmp(range, &bus->range[idx]) == 0) {
+ if (!kvm_iodevice_read(vcpu, bus->range[idx].dev, range->addr,
+ range->len, val))
+ return idx;
+ idx++;
+ }
+
+ return -EOPNOTSUPP;
+}
+
+/* kvm_io_bus_read - called under kvm->slots_lock */
+int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
+ int len, void *val)
+{
+ struct kvm_io_bus *bus;
+ struct kvm_io_range range;
+ int r;
+
+ range = (struct kvm_io_range) {
+ .addr = addr,
+ .len = len,
+ };
+
+ bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu);
+ if (!bus)
+ return -ENOMEM;
+ r = __kvm_io_bus_read(vcpu, bus, &range, val);
+ return r < 0 ? r : 0;
+}
+
+/* Caller must hold slots_lock. */
+int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
+ int len, struct kvm_io_device *dev)
+{
+ int i;
+ struct kvm_io_bus *new_bus, *bus;
+ struct kvm_io_range range;
+
+ bus = kvm_get_bus(kvm, bus_idx);
+ if (!bus)
+ return -ENOMEM;
+
+ /* exclude ioeventfd which is limited by maximum fd */
+ if (bus->dev_count - bus->ioeventfd_count > NR_IOBUS_DEVS - 1)
+ return -ENOSPC;
+
+ new_bus = kmalloc(struct_size(bus, range, bus->dev_count + 1),
+ GFP_KERNEL_ACCOUNT);
+ if (!new_bus)
+ return -ENOMEM;
+
+ range = (struct kvm_io_range) {
+ .addr = addr,
+ .len = len,
+ .dev = dev,
+ };
+
+ for (i = 0; i < bus->dev_count; i++)
+ if (kvm_io_bus_cmp(&bus->range[i], &range) > 0)
+ break;
+
+ memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range));
+ new_bus->dev_count++;
+ new_bus->range[i] = range;
+ memcpy(new_bus->range + i + 1, bus->range + i,
+ (bus->dev_count - i) * sizeof(struct kvm_io_range));
+ rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
+ synchronize_srcu_expedited(&kvm->srcu);
+ kfree(bus);
+
+ return 0;
+}
+
+/* Caller must hold slots_lock. */
+int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
+ struct kvm_io_device *dev)
+{
+ int i, j;
+ struct kvm_io_bus *new_bus, *bus;
+
+ bus = kvm_get_bus(kvm, bus_idx);
+ if (!bus)
+ return 0;
+
+ for (i = 0; i < bus->dev_count; i++)
+ if (bus->range[i].dev == dev) {
+ break;
+ }
+
+ if (i == bus->dev_count)
+ return 0;
+
+ new_bus = kmalloc(struct_size(bus, range, bus->dev_count - 1),
+ GFP_KERNEL_ACCOUNT);
+ if (new_bus) {
+ memcpy(new_bus, bus, struct_size(bus, range, i));
+ new_bus->dev_count--;
+ memcpy(new_bus->range + i, bus->range + i + 1,
+ flex_array_size(new_bus, range, new_bus->dev_count - i));
+ }
+
+ rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
+ synchronize_srcu_expedited(&kvm->srcu);
+
+ /* Destroy the old bus _after_ installing the (null) bus. */
+ if (!new_bus) {
+ pr_err("kvm: failed to shrink bus, removing it completely\n");
+ for (j = 0; j < bus->dev_count; j++) {
+ if (j == i)
+ continue;
+ kvm_iodevice_destructor(bus->range[j].dev);
+ }
+ }
+
+ kfree(bus);
+ return new_bus ? 0 : -ENOMEM;
+}
+
+struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,
+ gpa_t addr)
+{
+ struct kvm_io_bus *bus;
+ int dev_idx, srcu_idx;
+ struct kvm_io_device *iodev = NULL;
+
+ srcu_idx = srcu_read_lock(&kvm->srcu);
+
+ bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
+ if (!bus)
+ goto out_unlock;
+
+ dev_idx = kvm_io_bus_get_first_dev(bus, addr, 1);
+ if (dev_idx < 0)
+ goto out_unlock;
+
+ iodev = bus->range[dev_idx].dev;
+
+out_unlock:
+ srcu_read_unlock(&kvm->srcu, srcu_idx);
+
+ return iodev;
+}
+EXPORT_SYMBOL_GPL(kvm_io_bus_get_dev);
+
+static int kvm_debugfs_open(struct inode *inode, struct file *file,
+ int (*get)(void *, u64 *), int (*set)(void *, u64),
+ const char *fmt)
+{
+ struct kvm_stat_data *stat_data = (struct kvm_stat_data *)
+ inode->i_private;
+
+ /* The debugfs files are a reference to the kvm struct which
+ * is still valid when kvm_destroy_vm is called.
+ * To avoid the race between open and the removal of the debugfs
+ * directory we test against the users count.
+ */
+ if (!refcount_inc_not_zero(&stat_data->kvm->users_count))
+ return -ENOENT;
+
+ if (simple_attr_open(inode, file, get,
+ KVM_DBGFS_GET_MODE(stat_data->dbgfs_item) & 0222
+ ? set : NULL,
+ fmt)) {
+ kvm_put_kvm(stat_data->kvm);
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static int kvm_debugfs_release(struct inode *inode, struct file *file)
+{
+ struct kvm_stat_data *stat_data = (struct kvm_stat_data *)
+ inode->i_private;
+
+ simple_attr_release(inode, file);
+ kvm_put_kvm(stat_data->kvm);
+
+ return 0;
+}
+
+static int kvm_get_stat_per_vm(struct kvm *kvm, size_t offset, u64 *val)
+{
+ *val = *(ulong *)((void *)kvm + offset);
+
+ return 0;
+}
+
+static int kvm_clear_stat_per_vm(struct kvm *kvm, size_t offset)
+{
+ *(ulong *)((void *)kvm + offset) = 0;
+
+ return 0;
+}
+
+static int kvm_get_stat_per_vcpu(struct kvm *kvm, size_t offset, u64 *val)
+{
+ int i;
+ struct kvm_vcpu *vcpu;
+
+ *val = 0;
+
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ *val += *(u64 *)((void *)vcpu + offset);
+
+ return 0;
+}
+
+static int kvm_clear_stat_per_vcpu(struct kvm *kvm, size_t offset)
+{
+ int i;
+ struct kvm_vcpu *vcpu;
+
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ *(u64 *)((void *)vcpu + offset) = 0;
+
+ return 0;
+}
+
+static int kvm_stat_data_get(void *data, u64 *val)
+{
+ int r = -EFAULT;
+ struct kvm_stat_data *stat_data = (struct kvm_stat_data *)data;
+
+ switch (stat_data->dbgfs_item->kind) {
+ case KVM_STAT_VM:
+ r = kvm_get_stat_per_vm(stat_data->kvm,
+ stat_data->dbgfs_item->offset, val);
+ break;
+ case KVM_STAT_VCPU:
+ r = kvm_get_stat_per_vcpu(stat_data->kvm,
+ stat_data->dbgfs_item->offset, val);
+ break;
+ }
+
+ return r;
+}
+
+static int kvm_stat_data_clear(void *data, u64 val)
+{
+ int r = -EFAULT;
+ struct kvm_stat_data *stat_data = (struct kvm_stat_data *)data;
+
+ if (val)
+ return -EINVAL;
+
+ switch (stat_data->dbgfs_item->kind) {
+ case KVM_STAT_VM:
+ r = kvm_clear_stat_per_vm(stat_data->kvm,
+ stat_data->dbgfs_item->offset);
+ break;
+ case KVM_STAT_VCPU:
+ r = kvm_clear_stat_per_vcpu(stat_data->kvm,
+ stat_data->dbgfs_item->offset);
+ break;
+ }
+
+ return r;
+}
+
+static int kvm_stat_data_open(struct inode *inode, struct file *file)
+{
+ __simple_attr_check_format("%llu\n", 0ull);
+ return kvm_debugfs_open(inode, file, kvm_stat_data_get,
+ kvm_stat_data_clear, "%llu\n");
+}
+
+static const struct file_operations stat_fops_per_vm = {
+ .owner = THIS_MODULE,
+ .open = kvm_stat_data_open,
+ .release = kvm_debugfs_release,
+ .read = simple_attr_read,
+ .write = simple_attr_write,
+ .llseek = no_llseek,
+};
+
+static int vm_stat_get(void *_offset, u64 *val)
+{
+ unsigned offset = (long)_offset;
+ struct kvm *kvm;
+ u64 tmp_val;
+
+ *val = 0;
+ mutex_lock(&kvm_lock);
+ list_for_each_entry(kvm, &vm_list, vm_list) {
+ kvm_get_stat_per_vm(kvm, offset, &tmp_val);
+ *val += tmp_val;
+ }
+ mutex_unlock(&kvm_lock);
+ return 0;
+}
+
+static int vm_stat_clear(void *_offset, u64 val)
+{
+ unsigned offset = (long)_offset;
+ struct kvm *kvm;
+
+ if (val)
+ return -EINVAL;
+
+ mutex_lock(&kvm_lock);
+ list_for_each_entry(kvm, &vm_list, vm_list) {
+ kvm_clear_stat_per_vm(kvm, offset);
+ }
+ mutex_unlock(&kvm_lock);
+
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(vm_stat_fops, vm_stat_get, vm_stat_clear, "%llu\n");
+
+static int vcpu_stat_get(void *_offset, u64 *val)
+{
+ unsigned offset = (long)_offset;
+ struct kvm *kvm;
+ u64 tmp_val;
+
+ *val = 0;
+ mutex_lock(&kvm_lock);
+ list_for_each_entry(kvm, &vm_list, vm_list) {
+ kvm_get_stat_per_vcpu(kvm, offset, &tmp_val);
+ *val += tmp_val;
+ }
+ mutex_unlock(&kvm_lock);
+ return 0;
+}
+
+static int vcpu_stat_clear(void *_offset, u64 val)
+{
+ unsigned offset = (long)_offset;
+ struct kvm *kvm;
+
+ if (val)
+ return -EINVAL;
+
+ mutex_lock(&kvm_lock);
+ list_for_each_entry(kvm, &vm_list, vm_list) {
+ kvm_clear_stat_per_vcpu(kvm, offset);
+ }
+ mutex_unlock(&kvm_lock);
+
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_fops, vcpu_stat_get, vcpu_stat_clear,
+ "%llu\n");
+
+static const struct file_operations *stat_fops[] = {
+ [KVM_STAT_VCPU] = &vcpu_stat_fops,
+ [KVM_STAT_VM] = &vm_stat_fops,
+};
+
+static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm)
+{
+ struct kobj_uevent_env *env;
+ unsigned long long created, active;
+
+ if (!kvm_dev.this_device || !kvm)
+ return;
+
+ mutex_lock(&kvm_lock);
+ if (type == KVM_EVENT_CREATE_VM) {
+ kvm_createvm_count++;
+ kvm_active_vms++;
+ } else if (type == KVM_EVENT_DESTROY_VM) {
+ kvm_active_vms--;
+ }
+ created = kvm_createvm_count;
+ active = kvm_active_vms;
+ mutex_unlock(&kvm_lock);
+
+ env = kzalloc(sizeof(*env), GFP_KERNEL_ACCOUNT);
+ if (!env)
+ return;
+
+ add_uevent_var(env, "CREATED=%llu", created);
+ add_uevent_var(env, "COUNT=%llu", active);
+
+ if (type == KVM_EVENT_CREATE_VM) {
+ add_uevent_var(env, "EVENT=create");
+ kvm->userspace_pid = task_pid_nr(current);
+ } else if (type == KVM_EVENT_DESTROY_VM) {
+ add_uevent_var(env, "EVENT=destroy");
+ }
+ add_uevent_var(env, "PID=%d", kvm->userspace_pid);
+
+ if (kvm->debugfs_dentry) {
+ char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL_ACCOUNT);
+
+ if (p) {
+ tmp = dentry_path_raw(kvm->debugfs_dentry, p, PATH_MAX);
+ if (!IS_ERR(tmp))
+ add_uevent_var(env, "STATS_PATH=%s", tmp);
+ kfree(p);
+ }
+ }
+ /* no need for checks, since we are adding at most only 5 keys */
+ env->envp[env->envp_idx++] = NULL;
+ kobject_uevent_env(&kvm_dev.this_device->kobj, KOBJ_CHANGE, env->envp);
+ kfree(env);
+}
+
+static void kvm_init_debug(void)
+{
+ struct kvm_stats_debugfs_item *p;
+
+ kvm_debugfs_dir = debugfs_create_dir("kvm", NULL);
+
+ kvm_debugfs_num_entries = 0;
+ for (p = debugfs_entries; p->name; ++p, kvm_debugfs_num_entries++) {
+ debugfs_create_file(p->name, KVM_DBGFS_GET_MODE(p),
+ kvm_debugfs_dir, (void *)(long)p->offset,
+ stat_fops[p->kind]);
+ }
+}
+
+static int kvm_suspend(void)
+{
+ if (kvm_usage_count)
+ hardware_disable_nolock(NULL);
+ return 0;
+}
+
+static void kvm_resume(void)
+{
+ if (kvm_usage_count) {
+#ifdef CONFIG_LOCKDEP
+ WARN_ON(lockdep_is_held(&kvm_count_lock));
+#endif
+ hardware_enable_nolock(NULL);
+ }
+}
+
+static struct syscore_ops kvm_syscore_ops = {
+ .suspend = kvm_suspend,
+ .resume = kvm_resume,
+};
+
+static inline
+struct kvm_vcpu *preempt_notifier_to_vcpu(struct preempt_notifier *pn)
+{
+ return container_of(pn, struct kvm_vcpu, preempt_notifier);
+}
+
+static void kvm_sched_in(struct preempt_notifier *pn, int cpu)
+{
+ struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);
+
+ WRITE_ONCE(vcpu->preempted, false);
+ WRITE_ONCE(vcpu->ready, false);
+
+ __this_cpu_write(kvm_running_vcpu, vcpu);
+ kvm_arch_sched_in(vcpu, cpu);
+ kvm_arch_vcpu_load(vcpu, cpu);
+}
+
+static void kvm_sched_out(struct preempt_notifier *pn,
+ struct task_struct *next)
+{
+ struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);
+
+ if (current->state == TASK_RUNNING) {
+ WRITE_ONCE(vcpu->preempted, true);
+ WRITE_ONCE(vcpu->ready, true);
+ }
+ kvm_arch_vcpu_put(vcpu);
+ __this_cpu_write(kvm_running_vcpu, NULL);
+}
+
+/**
+ * kvm_get_running_vcpu - get the vcpu running on the current CPU.
+ *
+ * We can disable preemption locally around accessing the per-CPU variable,
+ * and use the resolved vcpu pointer after enabling preemption again,
+ * because even if the current thread is migrated to another CPU, reading
+ * the per-CPU value later will give us the same value as we update the
+ * per-CPU variable in the preempt notifier handlers.
+ */
+struct kvm_vcpu *kvm_get_running_vcpu(void)
+{
+ struct kvm_vcpu *vcpu;
+
+ preempt_disable();
+ vcpu = __this_cpu_read(kvm_running_vcpu);
+ preempt_enable();
+
+ return vcpu;
+}
+EXPORT_SYMBOL_GPL(kvm_get_running_vcpu);
+
+/**
+ * kvm_get_running_vcpus - get the per-CPU array of currently running vcpus.
+ */
+struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void)
+{
+ return &kvm_running_vcpu;
+}
+
+struct kvm_cpu_compat_check {
+ void *opaque;
+ int *ret;
+};
+
+static void check_processor_compat(void *data)
+{
+ struct kvm_cpu_compat_check *c = data;
+
+ *c->ret = kvm_arch_check_processor_compat(c->opaque);
+}
+
+int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
+ struct module *module)
+{
+ struct kvm_cpu_compat_check c;
+ int r;
+ int cpu;
+
+ r = kvm_arch_init(opaque);
+ if (r)
+ goto out_fail;
+
+ /*
+ * 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;
+ goto out_free_0;
+ }
+
+ r = kvm_arch_hardware_setup(opaque);
+ if (r < 0)
+ goto out_free_1;
+
+ c.ret = &r;
+ c.opaque = opaque;
+ for_each_online_cpu(cpu) {
+ smp_call_function_single(cpu, check_processor_compat, &c, 1);
+ if (r < 0)
+ goto out_free_2;
+ }
+
+ r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_STARTING, "kvm/cpu:starting",
+ kvm_starting_cpu, kvm_dying_cpu);
+ if (r)
+ goto out_free_2;
+ register_reboot_notifier(&kvm_reboot_notifier);
+
+ /* A kmem cache lets us meet the alignment requirements of fx_save. */
+ if (!vcpu_align)
+ vcpu_align = __alignof__(struct kvm_vcpu);
+ kvm_vcpu_cache =
+ kmem_cache_create_usercopy("kvm_vcpu", vcpu_size, vcpu_align,
+ SLAB_ACCOUNT,
+ offsetof(struct kvm_vcpu, arch),
+ sizeof_field(struct kvm_vcpu, arch),
+ NULL);
+ if (!kvm_vcpu_cache) {
+ r = -ENOMEM;
+ goto out_free_3;
+ }
+
+ for_each_possible_cpu(cpu) {
+ if (!alloc_cpumask_var_node(&per_cpu(cpu_kick_mask, cpu),
+ GFP_KERNEL, cpu_to_node(cpu))) {
+ r = -ENOMEM;
+ goto out_free_4;
+ }
+ }
+
+ r = kvm_async_pf_init();
+ if (r)
+ goto out_free_4;
+
+ kvm_chardev_ops.owner = module;
+ kvm_vm_fops.owner = module;
+ kvm_vcpu_fops.owner = module;
+
+ register_syscore_ops(&kvm_syscore_ops);
+
+ kvm_preempt_ops.sched_in = kvm_sched_in;
+ kvm_preempt_ops.sched_out = kvm_sched_out;
+
+ kvm_init_debug();
+
+ r = kvm_vfio_ops_init();
+ if (WARN_ON_ONCE(r))
+ goto err_vfio;
+
+ /*
+ * Registration _must_ be the very last thing done, as this exposes
+ * /dev/kvm to userspace, i.e. all infrastructure must be setup!
+ */
+ r = misc_register(&kvm_dev);
+ if (r) {
+ pr_err("kvm: misc device register failed\n");
+ goto err_register;
+ }
+
+ return 0;
+
+err_register:
+ kvm_vfio_ops_exit();
+err_vfio:
+ kvm_async_pf_deinit();
+out_free_4:
+ for_each_possible_cpu(cpu)
+ free_cpumask_var(per_cpu(cpu_kick_mask, cpu));
+ kmem_cache_destroy(kvm_vcpu_cache);
+out_free_3:
+ unregister_reboot_notifier(&kvm_reboot_notifier);
+ cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING);
+out_free_2:
+ kvm_arch_hardware_unsetup();
+out_free_1:
+ free_cpumask_var(cpus_hardware_enabled);
+out_free_0:
+ kvm_irqfd_exit();
+out_irqfd:
+ kvm_arch_exit();
+out_fail:
+ return r;
+}
+EXPORT_SYMBOL_GPL(kvm_init);
+
+void kvm_exit(void)
+{
+ int cpu;
+
+ /*
+ * Note, unregistering /dev/kvm doesn't strictly need to come first,
+ * fops_get(), a.k.a. try_module_get(), prevents acquiring references
+ * to KVM while the module is being stopped.
+ */
+ misc_deregister(&kvm_dev);
+
+ debugfs_remove_recursive(kvm_debugfs_dir);
+ for_each_possible_cpu(cpu)
+ free_cpumask_var(per_cpu(cpu_kick_mask, cpu));
+ kmem_cache_destroy(kvm_vcpu_cache);
+ kvm_async_pf_deinit();
+ unregister_syscore_ops(&kvm_syscore_ops);
+ unregister_reboot_notifier(&kvm_reboot_notifier);
+ cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING);
+ on_each_cpu(hardware_disable_nolock, NULL, 1);
+ kvm_arch_hardware_unsetup();
+ kvm_arch_exit();
+ kvm_irqfd_exit();
+ free_cpumask_var(cpus_hardware_enabled);
+ kvm_vfio_ops_exit();
+}
+EXPORT_SYMBOL_GPL(kvm_exit);
+
+struct kvm_vm_worker_thread_context {
+ struct kvm *kvm;
+ struct task_struct *parent;
+ struct completion init_done;
+ kvm_vm_thread_fn_t thread_fn;
+ uintptr_t data;
+ int err;
+};
+
+static int kvm_vm_worker_thread(void *context)
+{
+ /*
+ * The init_context is allocated on the stack of the parent thread, so
+ * we have to locally copy anything that is needed beyond initialization
+ */
+ struct kvm_vm_worker_thread_context *init_context = context;
+ struct kvm *kvm = init_context->kvm;
+ kvm_vm_thread_fn_t thread_fn = init_context->thread_fn;
+ uintptr_t data = init_context->data;
+ int err;
+
+ err = kthread_park(current);
+ /* kthread_park(current) is never supposed to return an error */
+ WARN_ON(err != 0);
+ if (err)
+ goto init_complete;
+
+ err = cgroup_attach_task_all(init_context->parent, current);
+ if (err) {
+ kvm_err("%s: cgroup_attach_task_all failed with err %d\n",
+ __func__, err);
+ goto init_complete;
+ }
+
+ set_user_nice(current, task_nice(init_context->parent));
+
+init_complete:
+ init_context->err = err;
+ complete(&init_context->init_done);
+ init_context = NULL;
+
+ if (err)
+ return err;
+
+ /* Wait to be woken up by the spawner before proceeding. */
+ kthread_parkme();
+
+ if (!kthread_should_stop())
+ err = thread_fn(kvm, data);
+
+ return err;
+}
+
+int kvm_vm_create_worker_thread(struct kvm *kvm, kvm_vm_thread_fn_t thread_fn,
+ uintptr_t data, const char *name,
+ struct task_struct **thread_ptr)
+{
+ struct kvm_vm_worker_thread_context init_context = {};
+ struct task_struct *thread;
+
+ *thread_ptr = NULL;
+ init_context.kvm = kvm;
+ init_context.parent = current;
+ init_context.thread_fn = thread_fn;
+ init_context.data = data;
+ init_completion(&init_context.init_done);
+
+ thread = kthread_run(kvm_vm_worker_thread, &init_context,
+ "%s-%d", name, task_pid_nr(current));
+ if (IS_ERR(thread))
+ return PTR_ERR(thread);
+
+ /* kthread_run is never supposed to return NULL */
+ WARN_ON(thread == NULL);
+
+ wait_for_completion(&init_context.init_done);
+
+ if (!init_context.err)
+ *thread_ptr = thread;
+
+ return init_context.err;
+}
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
new file mode 100644
index 000000000..8fcbc5022
--- /dev/null
+++ b/virt/kvm/vfio.c
@@ -0,0 +1,425 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * VFIO-KVM bridge pseudo device
+ *
+ * Copyright (C) 2013 Red Hat, Inc. All rights reserved.
+ * Author: Alex Williamson <alex.williamson@redhat.com>
+ */
+
+#include <linux/errno.h>
+#include <linux/file.h>
+#include <linux/kvm_host.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/vfio.h>
+#include "vfio.h"
+
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+#include <asm/kvm_ppc.h>
+#endif
+
+struct kvm_vfio_group {
+ struct list_head node;
+ struct vfio_group *vfio_group;
+};
+
+struct kvm_vfio {
+ struct list_head group_list;
+ struct mutex lock;
+ bool noncoherent;
+};
+
+static struct vfio_group *kvm_vfio_group_get_external_user(struct file *filep)
+{
+ struct vfio_group *vfio_group;
+ struct vfio_group *(*fn)(struct file *);
+
+ fn = symbol_get(vfio_group_get_external_user);
+ if (!fn)
+ return ERR_PTR(-EINVAL);
+
+ vfio_group = fn(filep);
+
+ symbol_put(vfio_group_get_external_user);
+
+ return vfio_group;
+}
+
+static bool kvm_vfio_external_group_match_file(struct vfio_group *group,
+ struct file *filep)
+{
+ bool ret, (*fn)(struct vfio_group *, struct file *);
+
+ fn = symbol_get(vfio_external_group_match_file);
+ if (!fn)
+ return false;
+
+ ret = fn(group, filep);
+
+ symbol_put(vfio_external_group_match_file);
+
+ return ret;
+}
+
+static void kvm_vfio_group_put_external_user(struct vfio_group *vfio_group)
+{
+ void (*fn)(struct vfio_group *);
+
+ fn = symbol_get(vfio_group_put_external_user);
+ if (!fn)
+ return;
+
+ fn(vfio_group);
+
+ symbol_put(vfio_group_put_external_user);
+}
+
+static void kvm_vfio_group_set_kvm(struct vfio_group *group, struct kvm *kvm)
+{
+ void (*fn)(struct vfio_group *, struct kvm *);
+
+ fn = symbol_get(vfio_group_set_kvm);
+ if (!fn)
+ return;
+
+ fn(group, kvm);
+
+ symbol_put(vfio_group_set_kvm);
+}
+
+static bool kvm_vfio_group_is_coherent(struct vfio_group *vfio_group)
+{
+ long (*fn)(struct vfio_group *, unsigned long);
+ long ret;
+
+ fn = symbol_get(vfio_external_check_extension);
+ if (!fn)
+ return false;
+
+ ret = fn(vfio_group, VFIO_DMA_CC_IOMMU);
+
+ symbol_put(vfio_external_check_extension);
+
+ return ret > 0;
+}
+
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+static int kvm_vfio_external_user_iommu_id(struct vfio_group *vfio_group)
+{
+ int (*fn)(struct vfio_group *);
+ int ret = -EINVAL;
+
+ fn = symbol_get(vfio_external_user_iommu_id);
+ if (!fn)
+ return ret;
+
+ ret = fn(vfio_group);
+
+ symbol_put(vfio_external_user_iommu_id);
+
+ return ret;
+}
+
+static struct iommu_group *kvm_vfio_group_get_iommu_group(
+ struct vfio_group *group)
+{
+ int group_id = kvm_vfio_external_user_iommu_id(group);
+
+ if (group_id < 0)
+ return NULL;
+
+ return iommu_group_get_by_id(group_id);
+}
+
+static void kvm_spapr_tce_release_vfio_group(struct kvm *kvm,
+ struct vfio_group *vfio_group)
+{
+ struct iommu_group *grp = kvm_vfio_group_get_iommu_group(vfio_group);
+
+ if (WARN_ON_ONCE(!grp))
+ return;
+
+ kvm_spapr_tce_release_iommu_group(kvm, grp);
+ iommu_group_put(grp);
+}
+#endif
+
+/*
+ * Groups can use the same or different IOMMU domains. If the same then
+ * adding a new group may change the coherency of groups we've previously
+ * been told about. We don't want to care about any of that so we retest
+ * each group and bail as soon as we find one that's noncoherent. This
+ * means we only ever [un]register_noncoherent_dma once for the whole device.
+ */
+static void kvm_vfio_update_coherency(struct kvm_device *dev)
+{
+ struct kvm_vfio *kv = dev->private;
+ bool noncoherent = false;
+ struct kvm_vfio_group *kvg;
+
+ mutex_lock(&kv->lock);
+
+ list_for_each_entry(kvg, &kv->group_list, node) {
+ if (!kvm_vfio_group_is_coherent(kvg->vfio_group)) {
+ noncoherent = true;
+ break;
+ }
+ }
+
+ if (noncoherent != kv->noncoherent) {
+ kv->noncoherent = noncoherent;
+
+ if (kv->noncoherent)
+ kvm_arch_register_noncoherent_dma(dev->kvm);
+ else
+ kvm_arch_unregister_noncoherent_dma(dev->kvm);
+ }
+
+ mutex_unlock(&kv->lock);
+}
+
+static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
+{
+ struct kvm_vfio *kv = dev->private;
+ struct vfio_group *vfio_group;
+ struct kvm_vfio_group *kvg;
+ int32_t __user *argp = (int32_t __user *)(unsigned long)arg;
+ struct fd f;
+ int32_t fd;
+ int ret;
+
+ switch (attr) {
+ case KVM_DEV_VFIO_GROUP_ADD:
+ if (get_user(fd, argp))
+ return -EFAULT;
+
+ f = fdget(fd);
+ if (!f.file)
+ return -EBADF;
+
+ vfio_group = kvm_vfio_group_get_external_user(f.file);
+ fdput(f);
+
+ if (IS_ERR(vfio_group))
+ return PTR_ERR(vfio_group);
+
+ mutex_lock(&kv->lock);
+
+ list_for_each_entry(kvg, &kv->group_list, node) {
+ if (kvg->vfio_group == vfio_group) {
+ mutex_unlock(&kv->lock);
+ kvm_vfio_group_put_external_user(vfio_group);
+ return -EEXIST;
+ }
+ }
+
+ kvg = kzalloc(sizeof(*kvg), GFP_KERNEL_ACCOUNT);
+ if (!kvg) {
+ mutex_unlock(&kv->lock);
+ kvm_vfio_group_put_external_user(vfio_group);
+ return -ENOMEM;
+ }
+
+ list_add_tail(&kvg->node, &kv->group_list);
+ kvg->vfio_group = vfio_group;
+
+ kvm_arch_start_assignment(dev->kvm);
+
+ mutex_unlock(&kv->lock);
+
+ kvm_vfio_group_set_kvm(vfio_group, dev->kvm);
+
+ kvm_vfio_update_coherency(dev);
+
+ return 0;
+
+ case KVM_DEV_VFIO_GROUP_DEL:
+ if (get_user(fd, argp))
+ return -EFAULT;
+
+ f = fdget(fd);
+ if (!f.file)
+ return -EBADF;
+
+ ret = -ENOENT;
+
+ mutex_lock(&kv->lock);
+
+ list_for_each_entry(kvg, &kv->group_list, node) {
+ if (!kvm_vfio_external_group_match_file(kvg->vfio_group,
+ f.file))
+ continue;
+
+ list_del(&kvg->node);
+ kvm_arch_end_assignment(dev->kvm);
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+ kvm_spapr_tce_release_vfio_group(dev->kvm,
+ kvg->vfio_group);
+#endif
+ kvm_vfio_group_set_kvm(kvg->vfio_group, NULL);
+ kvm_vfio_group_put_external_user(kvg->vfio_group);
+ kfree(kvg);
+ ret = 0;
+ break;
+ }
+
+ mutex_unlock(&kv->lock);
+
+ fdput(f);
+
+ kvm_vfio_update_coherency(dev);
+
+ return ret;
+
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+ case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: {
+ struct kvm_vfio_spapr_tce param;
+ struct kvm_vfio *kv = dev->private;
+ struct vfio_group *vfio_group;
+ struct kvm_vfio_group *kvg;
+ struct fd f;
+ struct iommu_group *grp;
+
+ if (copy_from_user(&param, (void __user *)arg,
+ sizeof(struct kvm_vfio_spapr_tce)))
+ return -EFAULT;
+
+ f = fdget(param.groupfd);
+ if (!f.file)
+ return -EBADF;
+
+ vfio_group = kvm_vfio_group_get_external_user(f.file);
+ fdput(f);
+
+ if (IS_ERR(vfio_group))
+ return PTR_ERR(vfio_group);
+
+ grp = kvm_vfio_group_get_iommu_group(vfio_group);
+ if (WARN_ON_ONCE(!grp)) {
+ kvm_vfio_group_put_external_user(vfio_group);
+ return -EIO;
+ }
+
+ ret = -ENOENT;
+
+ mutex_lock(&kv->lock);
+
+ list_for_each_entry(kvg, &kv->group_list, node) {
+ if (kvg->vfio_group != vfio_group)
+ continue;
+
+ ret = kvm_spapr_tce_attach_iommu_group(dev->kvm,
+ param.tablefd, grp);
+ break;
+ }
+
+ mutex_unlock(&kv->lock);
+
+ iommu_group_put(grp);
+ kvm_vfio_group_put_external_user(vfio_group);
+
+ return ret;
+ }
+#endif /* CONFIG_SPAPR_TCE_IOMMU */
+ }
+
+ return -ENXIO;
+}
+
+static int kvm_vfio_set_attr(struct kvm_device *dev,
+ struct kvm_device_attr *attr)
+{
+ switch (attr->group) {
+ case KVM_DEV_VFIO_GROUP:
+ return kvm_vfio_set_group(dev, attr->attr, attr->addr);
+ }
+
+ return -ENXIO;
+}
+
+static int kvm_vfio_has_attr(struct kvm_device *dev,
+ struct kvm_device_attr *attr)
+{
+ switch (attr->group) {
+ case KVM_DEV_VFIO_GROUP:
+ switch (attr->attr) {
+ case KVM_DEV_VFIO_GROUP_ADD:
+ case KVM_DEV_VFIO_GROUP_DEL:
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+ case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE:
+#endif
+ return 0;
+ }
+
+ break;
+ }
+
+ return -ENXIO;
+}
+
+static void kvm_vfio_destroy(struct kvm_device *dev)
+{
+ struct kvm_vfio *kv = dev->private;
+ struct kvm_vfio_group *kvg, *tmp;
+
+ list_for_each_entry_safe(kvg, tmp, &kv->group_list, node) {
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+ kvm_spapr_tce_release_vfio_group(dev->kvm, kvg->vfio_group);
+#endif
+ kvm_vfio_group_set_kvm(kvg->vfio_group, NULL);
+ kvm_vfio_group_put_external_user(kvg->vfio_group);
+ list_del(&kvg->node);
+ kfree(kvg);
+ kvm_arch_end_assignment(dev->kvm);
+ }
+
+ kvm_vfio_update_coherency(dev);
+
+ kfree(kv);
+ kfree(dev); /* alloc by kvm_ioctl_create_device, free by .destroy */
+}
+
+static int kvm_vfio_create(struct kvm_device *dev, u32 type);
+
+static struct kvm_device_ops kvm_vfio_ops = {
+ .name = "kvm-vfio",
+ .create = kvm_vfio_create,
+ .destroy = kvm_vfio_destroy,
+ .set_attr = kvm_vfio_set_attr,
+ .has_attr = kvm_vfio_has_attr,
+};
+
+static int kvm_vfio_create(struct kvm_device *dev, u32 type)
+{
+ struct kvm_device *tmp;
+ struct kvm_vfio *kv;
+
+ /* Only one VFIO "device" per VM */
+ list_for_each_entry(tmp, &dev->kvm->devices, vm_node)
+ if (tmp->ops == &kvm_vfio_ops)
+ return -EBUSY;
+
+ kv = kzalloc(sizeof(*kv), GFP_KERNEL_ACCOUNT);
+ if (!kv)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&kv->group_list);
+ mutex_init(&kv->lock);
+
+ dev->private = kv;
+
+ return 0;
+}
+
+int kvm_vfio_ops_init(void)
+{
+ return kvm_register_device_ops(&kvm_vfio_ops, KVM_DEV_TYPE_VFIO);
+}
+
+void kvm_vfio_ops_exit(void)
+{
+ kvm_unregister_device_ops(KVM_DEV_TYPE_VFIO);
+}
diff --git a/virt/kvm/vfio.h b/virt/kvm/vfio.h
new file mode 100644
index 000000000..e130a4a03
--- /dev/null
+++ b/virt/kvm/vfio.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __KVM_VFIO_H
+#define __KVM_VFIO_H
+
+#ifdef CONFIG_KVM_VFIO
+int kvm_vfio_ops_init(void);
+void kvm_vfio_ops_exit(void);
+#else
+static inline int kvm_vfio_ops_init(void)
+{
+ return 0;
+}
+static inline void kvm_vfio_ops_exit(void)
+{
+}
+#endif
+
+#endif
diff --git a/virt/lib/Kconfig b/virt/lib/Kconfig
new file mode 100644
index 000000000..2d9523b71
--- /dev/null
+++ b/virt/lib/Kconfig
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config IRQ_BYPASS_MANAGER
+ tristate
diff --git a/virt/lib/Makefile b/virt/lib/Makefile
new file mode 100644
index 000000000..bd7f9a78b
--- /dev/null
+++ b/virt/lib/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_IRQ_BYPASS_MANAGER) += irqbypass.o
diff --git a/virt/lib/irqbypass.c b/virt/lib/irqbypass.c
new file mode 100644
index 000000000..28fda42e4
--- /dev/null
+++ b/virt/lib/irqbypass.c
@@ -0,0 +1,266 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * IRQ offload/bypass manager
+ *
+ * Copyright (C) 2015 Red Hat, Inc.
+ * Copyright (c) 2015 Linaro Ltd.
+ *
+ * Various virtualization hardware acceleration techniques allow bypassing or
+ * offloading interrupts received from devices around the host kernel. Posted
+ * Interrupts on Intel VT-d systems can allow interrupts to be received
+ * directly by a virtual machine. ARM IRQ Forwarding allows forwarded physical
+ * interrupts to be directly deactivated by the guest. This manager allows
+ * interrupt producers and consumers to find each other to enable this sort of
+ * bypass.
+ */
+
+#include <linux/irqbypass.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("IRQ bypass manager utility module");
+
+static LIST_HEAD(producers);
+static LIST_HEAD(consumers);
+static DEFINE_MUTEX(lock);
+
+/* @lock must be held when calling connect */
+static int __connect(struct irq_bypass_producer *prod,
+ struct irq_bypass_consumer *cons)
+{
+ int ret = 0;
+
+ if (prod->stop)
+ prod->stop(prod);
+ if (cons->stop)
+ cons->stop(cons);
+
+ if (prod->add_consumer)
+ ret = prod->add_consumer(prod, cons);
+
+ if (!ret) {
+ ret = cons->add_producer(cons, prod);
+ if (ret && prod->del_consumer)
+ prod->del_consumer(prod, cons);
+ }
+
+ if (cons->start)
+ cons->start(cons);
+ if (prod->start)
+ prod->start(prod);
+
+ return ret;
+}
+
+/* @lock must be held when calling disconnect */
+static void __disconnect(struct irq_bypass_producer *prod,
+ struct irq_bypass_consumer *cons)
+{
+ if (prod->stop)
+ prod->stop(prod);
+ if (cons->stop)
+ cons->stop(cons);
+
+ cons->del_producer(cons, prod);
+
+ if (prod->del_consumer)
+ prod->del_consumer(prod, cons);
+
+ if (cons->start)
+ cons->start(cons);
+ if (prod->start)
+ prod->start(prod);
+}
+
+/**
+ * irq_bypass_register_producer - register IRQ bypass producer
+ * @producer: pointer to producer structure
+ *
+ * Add the provided IRQ producer to the list of producers and connect
+ * with any matching token found on the IRQ consumers list.
+ */
+int irq_bypass_register_producer(struct irq_bypass_producer *producer)
+{
+ struct irq_bypass_producer *tmp;
+ struct irq_bypass_consumer *consumer;
+ int ret;
+
+ if (!producer->token)
+ return -EINVAL;
+
+ might_sleep();
+
+ if (!try_module_get(THIS_MODULE))
+ return -ENODEV;
+
+ mutex_lock(&lock);
+
+ list_for_each_entry(tmp, &producers, node) {
+ if (tmp->token == producer->token) {
+ ret = -EBUSY;
+ goto out_err;
+ }
+ }
+
+ list_for_each_entry(consumer, &consumers, node) {
+ if (consumer->token == producer->token) {
+ ret = __connect(producer, consumer);
+ if (ret)
+ goto out_err;
+ break;
+ }
+ }
+
+ list_add(&producer->node, &producers);
+
+ mutex_unlock(&lock);
+
+ return 0;
+out_err:
+ mutex_unlock(&lock);
+ module_put(THIS_MODULE);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(irq_bypass_register_producer);
+
+/**
+ * irq_bypass_unregister_producer - unregister IRQ bypass producer
+ * @producer: pointer to producer structure
+ *
+ * Remove a previously registered IRQ producer from the list of producers
+ * and disconnect it from any connected IRQ consumer.
+ */
+void irq_bypass_unregister_producer(struct irq_bypass_producer *producer)
+{
+ struct irq_bypass_producer *tmp;
+ struct irq_bypass_consumer *consumer;
+
+ if (!producer->token)
+ return;
+
+ might_sleep();
+
+ if (!try_module_get(THIS_MODULE))
+ return; /* nothing in the list anyway */
+
+ mutex_lock(&lock);
+
+ list_for_each_entry(tmp, &producers, node) {
+ if (tmp->token != producer->token)
+ continue;
+
+ list_for_each_entry(consumer, &consumers, node) {
+ if (consumer->token == producer->token) {
+ __disconnect(producer, consumer);
+ break;
+ }
+ }
+
+ list_del(&producer->node);
+ module_put(THIS_MODULE);
+ break;
+ }
+
+ mutex_unlock(&lock);
+
+ module_put(THIS_MODULE);
+}
+EXPORT_SYMBOL_GPL(irq_bypass_unregister_producer);
+
+/**
+ * irq_bypass_register_consumer - register IRQ bypass consumer
+ * @consumer: pointer to consumer structure
+ *
+ * Add the provided IRQ consumer to the list of consumers and connect
+ * with any matching token found on the IRQ producer list.
+ */
+int irq_bypass_register_consumer(struct irq_bypass_consumer *consumer)
+{
+ struct irq_bypass_consumer *tmp;
+ struct irq_bypass_producer *producer;
+ int ret;
+
+ if (!consumer->token ||
+ !consumer->add_producer || !consumer->del_producer)
+ return -EINVAL;
+
+ might_sleep();
+
+ if (!try_module_get(THIS_MODULE))
+ return -ENODEV;
+
+ mutex_lock(&lock);
+
+ list_for_each_entry(tmp, &consumers, node) {
+ if (tmp->token == consumer->token || tmp == consumer) {
+ ret = -EBUSY;
+ goto out_err;
+ }
+ }
+
+ list_for_each_entry(producer, &producers, node) {
+ if (producer->token == consumer->token) {
+ ret = __connect(producer, consumer);
+ if (ret)
+ goto out_err;
+ break;
+ }
+ }
+
+ list_add(&consumer->node, &consumers);
+
+ mutex_unlock(&lock);
+
+ return 0;
+out_err:
+ mutex_unlock(&lock);
+ module_put(THIS_MODULE);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(irq_bypass_register_consumer);
+
+/**
+ * irq_bypass_unregister_consumer - unregister IRQ bypass consumer
+ * @consumer: pointer to consumer structure
+ *
+ * Remove a previously registered IRQ consumer from the list of consumers
+ * and disconnect it from any connected IRQ producer.
+ */
+void irq_bypass_unregister_consumer(struct irq_bypass_consumer *consumer)
+{
+ struct irq_bypass_consumer *tmp;
+ struct irq_bypass_producer *producer;
+
+ if (!consumer->token)
+ return;
+
+ might_sleep();
+
+ if (!try_module_get(THIS_MODULE))
+ return; /* nothing in the list anyway */
+
+ mutex_lock(&lock);
+
+ list_for_each_entry(tmp, &consumers, node) {
+ if (tmp != consumer)
+ continue;
+
+ list_for_each_entry(producer, &producers, node) {
+ if (producer->token == consumer->token) {
+ __disconnect(producer, consumer);
+ break;
+ }
+ }
+
+ list_del(&consumer->node);
+ module_put(THIS_MODULE);
+ break;
+ }
+
+ mutex_unlock(&lock);
+
+ module_put(THIS_MODULE);
+}
+EXPORT_SYMBOL_GPL(irq_bypass_unregister_consumer);