summaryrefslogtreecommitdiffstats
path: root/virt/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'virt/kvm')
-rw-r--r--virt/kvm/Kconfig88
-rw-r--r--virt/kvm/Makefile.kvm14
-rw-r--r--virt/kvm/async_pf.c228
-rw-r--r--virt/kvm/async_pf.h24
-rw-r--r--virt/kvm/binary_stats.c144
-rw-r--r--virt/kvm/coalesced_mmio.c211
-rw-r--r--virt/kvm/coalesced_mmio.h39
-rw-r--r--virt/kvm/dirty_ring.c180
-rw-r--r--virt/kvm/eventfd.c983
-rw-r--r--virt/kvm/irqchip.c240
-rw-r--r--virt/kvm/kvm_main.c6160
-rw-r--r--virt/kvm/kvm_mm.h44
-rw-r--r--virt/kvm/pfncache.c422
-rw-r--r--virt/kvm/vfio.c402
-rw-r--r--virt/kvm/vfio.h18
15 files changed, 9197 insertions, 0 deletions
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
new file mode 100644
index 000000000..800f9470e
--- /dev/null
+++ b/virt/kvm/Kconfig
@@ -0,0 +1,88 @@
+# SPDX-License-Identifier: GPL-2.0
+# KVM common configuration items and defaults
+
+config HAVE_KVM
+ bool
+
+config HAVE_KVM_PFNCACHE
+ bool
+
+config HAVE_KVM_IRQCHIP
+ bool
+
+config HAVE_KVM_IRQFD
+ bool
+
+config HAVE_KVM_IRQ_ROUTING
+ bool
+
+config HAVE_KVM_DIRTY_RING
+ bool
+
+# Only strongly ordered architectures can select this, as it doesn't
+# put any explicit constraint on userspace ordering. They can also
+# select the _ACQ_REL version.
+config HAVE_KVM_DIRTY_RING_TSO
+ bool
+ select HAVE_KVM_DIRTY_RING
+ depends on X86
+
+# Weakly ordered architectures can only select this, advertising
+# to userspace the additional ordering requirements.
+config HAVE_KVM_DIRTY_RING_ACQ_REL
+ bool
+ select HAVE_KVM_DIRTY_RING
+
+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 || RISCV)
+
+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
+
+config HAVE_KVM_PM_NOTIFIER
+ bool
diff --git a/virt/kvm/Makefile.kvm b/virt/kvm/Makefile.kvm
new file mode 100644
index 000000000..2c27d5d0c
--- /dev/null
+++ b/virt/kvm/Makefile.kvm
@@ -0,0 +1,14 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for Kernel-based Virtual Machine module
+#
+
+KVM ?= ../../../virt/kvm
+
+kvm-y := $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/binary_stats.o
+kvm-$(CONFIG_KVM_VFIO) += $(KVM)/vfio.o
+kvm-$(CONFIG_KVM_MMIO) += $(KVM)/coalesced_mmio.o
+kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o
+kvm-$(CONFIG_HAVE_KVM_IRQ_ROUTING) += $(KVM)/irqchip.o
+kvm-$(CONFIG_HAVE_KVM_DIRTY_RING) += $(KVM)/dirty_ring.o
+kvm-$(CONFIG_HAVE_KVM_PFNCACHE) += $(KVM)/pfncache.o
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
new file mode 100644
index 000000000..9bfe1d6f6
--- /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);
+
+ __kvm_vcpu_wake_up(vcpu);
+
+ 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/binary_stats.c b/virt/kvm/binary_stats.c
new file mode 100644
index 000000000..eefca6c69
--- /dev/null
+++ b/virt/kvm/binary_stats.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * KVM binary statistics interface implementation
+ *
+ * Copyright 2021 Google LLC
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/kvm.h>
+#include <linux/errno.h>
+#include <linux/uaccess.h>
+
+/**
+ * kvm_stats_read() - Common function to read from the binary statistics
+ * file descriptor.
+ *
+ * @id: identification string of the stats
+ * @header: stats header for a vm or a vcpu
+ * @desc: start address of an array of stats descriptors for a vm or a vcpu
+ * @stats: start address of stats data block for a vm or a vcpu
+ * @size_stats: the size of stats data block pointed by @stats
+ * @user_buffer: start address of userspace buffer
+ * @size: requested read size from userspace
+ * @offset: the start position from which the content will be read for the
+ * corresponding vm or vcp file descriptor
+ *
+ * The file content of a vm/vcpu file descriptor is now defined as below:
+ * +-------------+
+ * | Header |
+ * +-------------+
+ * | id string |
+ * +-------------+
+ * | Descriptors |
+ * +-------------+
+ * | Stats Data |
+ * +-------------+
+ * Although this function allows userspace to read any amount of data (as long
+ * as in the limit) from any position, the typical usage would follow below
+ * steps:
+ * 1. Read header from offset 0. Get the offset of descriptors and stats data
+ * and some other necessary information. This is a one-time work for the
+ * lifecycle of the corresponding vm/vcpu stats fd.
+ * 2. Read id string from its offset. This is a one-time work for the lifecycle
+ * of the corresponding vm/vcpu stats fd.
+ * 3. Read descriptors from its offset and discover all the stats by parsing
+ * descriptors. This is a one-time work for the lifecycle of the
+ * corresponding vm/vcpu stats fd.
+ * 4. Periodically read stats data from its offset using pread.
+ *
+ * Return: the number of bytes that has been successfully read
+ */
+ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header,
+ const struct _kvm_stats_desc *desc,
+ void *stats, size_t size_stats,
+ char __user *user_buffer, size_t size, loff_t *offset)
+{
+ ssize_t len;
+ ssize_t copylen;
+ ssize_t remain = size;
+ size_t size_desc;
+ size_t size_header;
+ void *src;
+ loff_t pos = *offset;
+ char __user *dest = user_buffer;
+
+ size_header = sizeof(*header);
+ size_desc = header->num_desc * sizeof(*desc);
+
+ len = KVM_STATS_NAME_SIZE + size_header + size_desc + size_stats - pos;
+ len = min(len, remain);
+ if (len <= 0)
+ return 0;
+ remain = len;
+
+ /*
+ * Copy kvm stats header.
+ * The header is the first block of content userspace usually read out.
+ * The pos is 0 and the copylen and remain would be the size of header.
+ * The copy of the header would be skipped if offset is larger than the
+ * size of header. That usually happens when userspace reads stats
+ * descriptors and stats data.
+ */
+ copylen = size_header - pos;
+ copylen = min(copylen, remain);
+ if (copylen > 0) {
+ src = (void *)header + pos;
+ if (copy_to_user(dest, src, copylen))
+ return -EFAULT;
+ remain -= copylen;
+ pos += copylen;
+ dest += copylen;
+ }
+
+ /*
+ * Copy kvm stats header id string.
+ * The id string is unique for every vm/vcpu, which is stored in kvm
+ * and kvm_vcpu structure.
+ * The id string is part of the stat header from the perspective of
+ * userspace, it is usually read out together with previous constant
+ * header part and could be skipped for later descriptors and stats
+ * data readings.
+ */
+ copylen = header->id_offset + KVM_STATS_NAME_SIZE - pos;
+ copylen = min(copylen, remain);
+ if (copylen > 0) {
+ src = id + pos - header->id_offset;
+ if (copy_to_user(dest, src, copylen))
+ return -EFAULT;
+ remain -= copylen;
+ pos += copylen;
+ dest += copylen;
+ }
+
+ /*
+ * Copy kvm stats descriptors.
+ * The descriptors copy would be skipped in the typical case that
+ * userspace periodically read stats data, since the pos would be
+ * greater than the end address of descriptors
+ * (header->header.desc_offset + size_desc) causing copylen <= 0.
+ */
+ copylen = header->desc_offset + size_desc - pos;
+ copylen = min(copylen, remain);
+ if (copylen > 0) {
+ src = (void *)desc + pos - header->desc_offset;
+ if (copy_to_user(dest, src, copylen))
+ return -EFAULT;
+ remain -= copylen;
+ pos += copylen;
+ dest += copylen;
+ }
+
+ /* Copy kvm stats values */
+ copylen = header->data_offset + size_stats - pos;
+ copylen = min(copylen, remain);
+ if (copylen > 0) {
+ src = stats + pos - header->data_offset;
+ if (copy_to_user(dest, src, copylen))
+ return -EFAULT;
+ pos += copylen;
+ }
+
+ *offset = pos;
+ return len;
+}
diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c
new file mode 100644
index 000000000..5ef88f5a0
--- /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_ACCOUNT | __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/dirty_ring.c b/virt/kvm/dirty_ring.c
new file mode 100644
index 000000000..d6fabf238
--- /dev/null
+++ b/virt/kvm/dirty_ring.c
@@ -0,0 +1,180 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * KVM dirty ring implementation
+ *
+ * Copyright 2019 Red Hat, Inc.
+ */
+#include <linux/kvm_host.h>
+#include <linux/kvm.h>
+#include <linux/vmalloc.h>
+#include <linux/kvm_dirty_ring.h>
+#include <trace/events/kvm.h>
+#include "kvm_mm.h"
+
+int __weak kvm_cpu_dirty_log_size(void)
+{
+ return 0;
+}
+
+u32 kvm_dirty_ring_get_rsvd_entries(void)
+{
+ return KVM_DIRTY_RING_RSVD_ENTRIES + kvm_cpu_dirty_log_size();
+}
+
+static u32 kvm_dirty_ring_used(struct kvm_dirty_ring *ring)
+{
+ return READ_ONCE(ring->dirty_index) - READ_ONCE(ring->reset_index);
+}
+
+bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring)
+{
+ return kvm_dirty_ring_used(ring) >= ring->soft_limit;
+}
+
+static bool kvm_dirty_ring_full(struct kvm_dirty_ring *ring)
+{
+ return kvm_dirty_ring_used(ring) >= ring->size;
+}
+
+static void kvm_reset_dirty_gfn(struct kvm *kvm, u32 slot, u64 offset, u64 mask)
+{
+ struct kvm_memory_slot *memslot;
+ int as_id, id;
+
+ as_id = slot >> 16;
+ id = (u16)slot;
+
+ if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
+ return;
+
+ memslot = id_to_memslot(__kvm_memslots(kvm, as_id), id);
+
+ if (!memslot || (offset + __fls(mask)) >= memslot->npages)
+ return;
+
+ KVM_MMU_LOCK(kvm);
+ kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, offset, mask);
+ KVM_MMU_UNLOCK(kvm);
+}
+
+int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size)
+{
+ ring->dirty_gfns = vzalloc(size);
+ if (!ring->dirty_gfns)
+ return -ENOMEM;
+
+ ring->size = size / sizeof(struct kvm_dirty_gfn);
+ ring->soft_limit = ring->size - kvm_dirty_ring_get_rsvd_entries();
+ ring->dirty_index = 0;
+ ring->reset_index = 0;
+ ring->index = index;
+
+ return 0;
+}
+
+static inline void kvm_dirty_gfn_set_invalid(struct kvm_dirty_gfn *gfn)
+{
+ smp_store_release(&gfn->flags, 0);
+}
+
+static inline void kvm_dirty_gfn_set_dirtied(struct kvm_dirty_gfn *gfn)
+{
+ gfn->flags = KVM_DIRTY_GFN_F_DIRTY;
+}
+
+static inline bool kvm_dirty_gfn_harvested(struct kvm_dirty_gfn *gfn)
+{
+ return smp_load_acquire(&gfn->flags) & KVM_DIRTY_GFN_F_RESET;
+}
+
+int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring)
+{
+ u32 cur_slot, next_slot;
+ u64 cur_offset, next_offset;
+ unsigned long mask;
+ int count = 0;
+ struct kvm_dirty_gfn *entry;
+ bool first_round = true;
+
+ /* This is only needed to make compilers happy */
+ cur_slot = cur_offset = mask = 0;
+
+ while (true) {
+ entry = &ring->dirty_gfns[ring->reset_index & (ring->size - 1)];
+
+ if (!kvm_dirty_gfn_harvested(entry))
+ break;
+
+ next_slot = READ_ONCE(entry->slot);
+ next_offset = READ_ONCE(entry->offset);
+
+ /* Update the flags to reflect that this GFN is reset */
+ kvm_dirty_gfn_set_invalid(entry);
+
+ ring->reset_index++;
+ count++;
+ /*
+ * Try to coalesce the reset operations when the guest is
+ * scanning pages in the same slot.
+ */
+ if (!first_round && next_slot == cur_slot) {
+ s64 delta = next_offset - cur_offset;
+
+ if (delta >= 0 && delta < BITS_PER_LONG) {
+ mask |= 1ull << delta;
+ continue;
+ }
+
+ /* Backwards visit, careful about overflows! */
+ if (delta > -BITS_PER_LONG && delta < 0 &&
+ (mask << -delta >> -delta) == mask) {
+ cur_offset = next_offset;
+ mask = (mask << -delta) | 1;
+ continue;
+ }
+ }
+ kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask);
+ cur_slot = next_slot;
+ cur_offset = next_offset;
+ mask = 1;
+ first_round = false;
+ }
+
+ kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask);
+
+ trace_kvm_dirty_ring_reset(ring);
+
+ return count;
+}
+
+void kvm_dirty_ring_push(struct kvm_dirty_ring *ring, u32 slot, u64 offset)
+{
+ struct kvm_dirty_gfn *entry;
+
+ /* It should never get full */
+ WARN_ON_ONCE(kvm_dirty_ring_full(ring));
+
+ entry = &ring->dirty_gfns[ring->dirty_index & (ring->size - 1)];
+
+ entry->slot = slot;
+ entry->offset = offset;
+ /*
+ * Make sure the data is filled in before we publish this to
+ * the userspace program. There's no paired kernel-side reader.
+ */
+ smp_wmb();
+ kvm_dirty_gfn_set_dirtied(entry);
+ ring->dirty_index++;
+ trace_kvm_dirty_ring_push(ring, slot, offset);
+}
+
+struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset)
+{
+ return vmalloc_to_page((void *)ring->dirty_gfns + offset * PAGE_SIZE);
+}
+
+void kvm_dirty_ring_free(struct kvm_dirty_ring *ring)
+{
+ vfree(ring->dirty_gfns);
+ ring->dirty_gfns = NULL;
+}
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
new file mode 100644
index 000000000..2a3ed401c
--- /dev/null
+++ b/virt/kvm/eventfd.c
@@ -0,0 +1,983 @@
+// 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_srcu(irqfd, &resampler->list, resampler_link,
+ srcu_read_lock_held(&kvm->irq_srcu))
+ 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;
+ int ret = 0;
+
+ if (flags & EPOLLIN) {
+ u64 cnt;
+ eventfd_ctx_do_read(irqfd->eventfd, &cnt);
+
+ 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);
+ ret = 1;
+ }
+
+ 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 ret;
+}
+
+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_priority(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;
+}
+
+bool __attribute__((weak)) kvm_arch_irqfd_route_changed(
+ struct kvm_kernel_irq_routing_entry *old,
+ struct kvm_kernel_irq_routing_entry *new)
+{
+ return true;
+}
+#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) {
+#ifdef CONFIG_HAVE_KVM_IRQ_BYPASS
+ /* Under irqfds.lock, so can read irq_entry safely */
+ struct kvm_kernel_irq_routing_entry old = irqfd->irq_entry;
+#endif
+
+ irqfd_update(kvm, irqfd);
+
+#ifdef CONFIG_HAVE_KVM_IRQ_BYPASS
+ if (irqfd->producer &&
+ kvm_arch_irqfd_route_changed(&old, &irqfd->irq_entry)) {
+ 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..8123f4d15
--- /dev/null
+++ b/virt/kvm/kvm_main.c
@@ -0,0 +1,6160 @@
+// 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 <linux/suspend.h>
+
+#include <asm/processor.h>
+#include <asm/ioctl.h>
+#include <linux/uaccess.h>
+
+#include "coalesced_mmio.h"
+#include "async_pf.h"
+#include "kvm_mm.h"
+#include "vfio.h"
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/kvm.h>
+
+#include <linux/kvm_dirty_ring.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 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_page(struct page *page)
+{
+ /*
+ * 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 (WARN_ON_ONCE(!page_count(page)))
+ return false;
+
+ return is_zone_device_page(page);
+}
+
+/*
+ * Returns a 'struct page' if the pfn is "valid" and backed by a refcounted
+ * page, NULL otherwise. Note, the list of refcounted PG_reserved page types
+ * is likely incomplete, it has been compiled purely through people wanting to
+ * back guest with a certain type of memory and encountering issues.
+ */
+struct page *kvm_pfn_to_refcounted_page(kvm_pfn_t pfn)
+{
+ struct page *page;
+
+ if (!pfn_valid(pfn))
+ return NULL;
+
+ page = pfn_to_page(pfn);
+ if (!PageReserved(page))
+ return page;
+
+ /* The ZERO_PAGE(s) is marked PG_reserved, but is refcounted. */
+ if (is_zero_pfn(pfn))
+ return page;
+
+ /*
+ * ZONE_DEVICE pages currently set PG_reserved, but from a refcounting
+ * perspective they are "normal" pages, albeit with slightly different
+ * usage rules.
+ */
+ if (kvm_is_zone_device_page(page))
+ return page;
+
+ return NULL;
+}
+
+/*
+ * 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_kick(void *_completed)
+{
+}
+
+static inline bool kvm_kick_many_cpus(struct cpumask *cpus, bool wait)
+{
+ if (cpumask_empty(cpus))
+ return false;
+
+ smp_call_function_many(cpus, ack_kick, NULL, wait);
+ return true;
+}
+
+static void kvm_make_vcpu_request(struct kvm_vcpu *vcpu, unsigned int req,
+ struct cpumask *tmp, int current_cpu)
+{
+ int cpu;
+
+ if (likely(!(req & KVM_REQUEST_NO_ACTION)))
+ __kvm_make_request(req, vcpu);
+
+ if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu))
+ 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,
+ unsigned long *vcpu_bitmap)
+{
+ struct kvm_vcpu *vcpu;
+ struct cpumask *cpus;
+ int i, me;
+ bool called;
+
+ me = get_cpu();
+
+ cpus = this_cpu_cpumask_var_ptr(cpu_kick_mask);
+ cpumask_clear(cpus);
+
+ for_each_set_bit(i, vcpu_bitmap, KVM_MAX_VCPUS) {
+ vcpu = kvm_get_vcpu(kvm, i);
+ if (!vcpu)
+ continue;
+ kvm_make_vcpu_request(vcpu, req, cpus, me);
+ }
+
+ called = kvm_kick_many_cpus(cpus, !!(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;
+ unsigned long i;
+ bool called;
+ int 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(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);
+}
+EXPORT_SYMBOL_GPL(kvm_make_all_cpus_request);
+
+#ifndef CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL
+void kvm_flush_remote_tlbs(struct kvm *kvm)
+{
+ ++kvm->stat.generic.remote_tlb_flush_requests;
+
+ /*
+ * 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.generic.remote_tlb_flush;
+}
+EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs);
+#endif
+
+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 capacity, int min)
+{
+ gfp_t gfp = mc->gfp_custom ? mc->gfp_custom : GFP_KERNEL_ACCOUNT;
+ void *obj;
+
+ if (mc->nobjs >= min)
+ return 0;
+
+ if (unlikely(!mc->objects)) {
+ if (WARN_ON_ONCE(!capacity))
+ return -EIO;
+
+ mc->objects = kvmalloc_array(sizeof(void *), capacity, gfp);
+ if (!mc->objects)
+ return -ENOMEM;
+
+ mc->capacity = capacity;
+ }
+
+ /* It is illegal to request a different capacity across topups. */
+ if (WARN_ON_ONCE(mc->capacity != capacity))
+ return -EIO;
+
+ while (mc->nobjs < mc->capacity) {
+ obj = mmu_memory_cache_alloc_obj(mc, gfp);
+ if (!obj)
+ return mc->nobjs >= min ? 0 : -ENOMEM;
+ mc->objects[mc->nobjs++] = obj;
+ }
+ return 0;
+}
+
+int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min)
+{
+ return __kvm_mmu_topup_memory_cache(mc, KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE, min);
+}
+
+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]);
+ }
+
+ kvfree(mc->objects);
+
+ mc->objects = NULL;
+ mc->capacity = 0;
+}
+
+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;
+#ifndef __KVM_HAVE_ARCH_WQP
+ rcuwait_init(&vcpu->wait);
+#endif
+ kvm_async_pf_vcpu_init(vcpu);
+
+ 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);
+ vcpu->last_used_slot = NULL;
+
+ /* Fill the stats id string for the vcpu */
+ snprintf(vcpu->stats_id, sizeof(vcpu->stats_id), "kvm-%d/vcpu-%d",
+ task_pid_nr(current), id);
+}
+
+static void kvm_vcpu_destroy(struct kvm_vcpu *vcpu)
+{
+ kvm_arch_vcpu_destroy(vcpu);
+ kvm_dirty_ring_free(&vcpu->dirty_ring);
+
+ /*
+ * 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);
+}
+
+void kvm_destroy_vcpus(struct kvm *kvm)
+{
+ unsigned long i;
+ struct kvm_vcpu *vcpu;
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ kvm_vcpu_destroy(vcpu);
+ xa_erase(&kvm->vcpu_array, i);
+ }
+
+ atomic_set(&kvm->online_vcpus, 0);
+}
+EXPORT_SYMBOL_GPL(kvm_destroy_vcpus);
+
+#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);
+}
+
+typedef bool (*hva_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range);
+
+typedef void (*on_lock_fn_t)(struct kvm *kvm, unsigned long start,
+ unsigned long end);
+
+typedef void (*on_unlock_fn_t)(struct kvm *kvm);
+
+struct kvm_hva_range {
+ unsigned long start;
+ unsigned long end;
+ pte_t pte;
+ hva_handler_t handler;
+ on_lock_fn_t on_lock;
+ on_unlock_fn_t on_unlock;
+ bool flush_on_ret;
+ bool may_block;
+};
+
+/*
+ * Use a dedicated stub instead of NULL to indicate that there is no callback
+ * function/handler. The compiler technically can't guarantee that a real
+ * function will have a non-zero address, and so it will generate code to
+ * check for !NULL, whereas comparing against a stub will be elided at compile
+ * time (unless the compiler is getting long in the tooth, e.g. gcc 4.9).
+ */
+static void kvm_null_fn(void)
+{
+
+}
+#define IS_KVM_NULL_FN(fn) ((fn) == (void *)kvm_null_fn)
+
+/* Iterate over each memslot intersecting [start, last] (inclusive) range */
+#define kvm_for_each_memslot_in_hva_range(node, slots, start, last) \
+ for (node = interval_tree_iter_first(&slots->hva_tree, start, last); \
+ node; \
+ node = interval_tree_iter_next(node, start, last)) \
+
+static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
+ const struct kvm_hva_range *range)
+{
+ bool ret = false, locked = false;
+ struct kvm_gfn_range gfn_range;
+ struct kvm_memory_slot *slot;
+ struct kvm_memslots *slots;
+ int i, idx;
+
+ if (WARN_ON_ONCE(range->end <= range->start))
+ return 0;
+
+ /* A null handler is allowed if and only if on_lock() is provided. */
+ if (WARN_ON_ONCE(IS_KVM_NULL_FN(range->on_lock) &&
+ IS_KVM_NULL_FN(range->handler)))
+ return 0;
+
+ idx = srcu_read_lock(&kvm->srcu);
+
+ for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+ struct interval_tree_node *node;
+
+ slots = __kvm_memslots(kvm, i);
+ kvm_for_each_memslot_in_hva_range(node, slots,
+ range->start, range->end - 1) {
+ unsigned long hva_start, hva_end;
+
+ slot = container_of(node, struct kvm_memory_slot, hva_node[slots->node_idx]);
+ hva_start = max(range->start, slot->userspace_addr);
+ hva_end = min(range->end, slot->userspace_addr +
+ (slot->npages << PAGE_SHIFT));
+
+ /*
+ * To optimize for the likely case where the address
+ * range is covered by zero or one memslots, don't
+ * bother making these conditional (to avoid writes on
+ * the second or later invocation of the handler).
+ */
+ gfn_range.pte = range->pte;
+ gfn_range.may_block = range->may_block;
+
+ /*
+ * {gfn(page) | page intersects with [hva_start, hva_end)} =
+ * {gfn_start, gfn_start+1, ..., gfn_end-1}.
+ */
+ gfn_range.start = hva_to_gfn_memslot(hva_start, slot);
+ gfn_range.end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, slot);
+ gfn_range.slot = slot;
+
+ if (!locked) {
+ locked = true;
+ KVM_MMU_LOCK(kvm);
+ if (!IS_KVM_NULL_FN(range->on_lock))
+ range->on_lock(kvm, range->start, range->end);
+ if (IS_KVM_NULL_FN(range->handler))
+ break;
+ }
+ ret |= range->handler(kvm, &gfn_range);
+ }
+ }
+
+ if (range->flush_on_ret && ret)
+ kvm_flush_remote_tlbs(kvm);
+
+ if (locked) {
+ KVM_MMU_UNLOCK(kvm);
+ if (!IS_KVM_NULL_FN(range->on_unlock))
+ range->on_unlock(kvm);
+ }
+
+ srcu_read_unlock(&kvm->srcu, idx);
+
+ /* The notifiers are averse to booleans. :-( */
+ return (int)ret;
+}
+
+static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn,
+ unsigned long start,
+ unsigned long end,
+ pte_t pte,
+ hva_handler_t handler)
+{
+ struct kvm *kvm = mmu_notifier_to_kvm(mn);
+ const struct kvm_hva_range range = {
+ .start = start,
+ .end = end,
+ .pte = pte,
+ .handler = handler,
+ .on_lock = (void *)kvm_null_fn,
+ .on_unlock = (void *)kvm_null_fn,
+ .flush_on_ret = true,
+ .may_block = false,
+ };
+
+ return __kvm_handle_hva_range(kvm, &range);
+}
+
+static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn,
+ unsigned long start,
+ unsigned long end,
+ hva_handler_t handler)
+{
+ struct kvm *kvm = mmu_notifier_to_kvm(mn);
+ const struct kvm_hva_range range = {
+ .start = start,
+ .end = end,
+ .pte = __pte(0),
+ .handler = handler,
+ .on_lock = (void *)kvm_null_fn,
+ .on_unlock = (void *)kvm_null_fn,
+ .flush_on_ret = false,
+ .may_block = false,
+ };
+
+ return __kvm_handle_hva_range(kvm, &range);
+}
+
+static bool kvm_change_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
+{
+ /*
+ * Skipping invalid memslots is correct if and only change_pte() is
+ * surrounded by invalidate_range_{start,end}(), which is currently
+ * guaranteed by the primary MMU. If that ever changes, KVM needs to
+ * unmap the memslot instead of skipping the memslot to ensure that KVM
+ * doesn't hold references to the old PFN.
+ */
+ WARN_ON_ONCE(!READ_ONCE(kvm->mn_active_invalidate_count));
+
+ if (range->slot->flags & KVM_MEMSLOT_INVALID)
+ return false;
+
+ return kvm_set_spte_gfn(kvm, range);
+}
+
+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);
+
+ trace_kvm_set_spte_hva(address);
+
+ /*
+ * .change_pte() must be surrounded by .invalidate_range_{start,end}().
+ * If mmu_invalidate_in_progress is zero, then no in-progress
+ * invalidations, including this one, found a relevant memslot at
+ * start(); rechecking memslots here is unnecessary. Note, a false
+ * positive (count elevated by a different invalidation) is sub-optimal
+ * but functionally ok.
+ */
+ WARN_ON_ONCE(!READ_ONCE(kvm->mn_active_invalidate_count));
+ if (!READ_ONCE(kvm->mmu_invalidate_in_progress))
+ return;
+
+ kvm_handle_hva_range(mn, address, address + 1, pte, kvm_change_spte_gfn);
+}
+
+void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
+ unsigned long end)
+{
+ /*
+ * 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_invalidate_in_progress++;
+ if (likely(kvm->mmu_invalidate_in_progress == 1)) {
+ kvm->mmu_invalidate_range_start = start;
+ kvm->mmu_invalidate_range_end = end;
+ } else {
+ /*
+ * Fully tracking multiple concurrent ranges has diminishing
+ * returns. Keep things simple and just find the minimal range
+ * which includes the current and new ranges. As there won't be
+ * enough information to subtract a range after its invalidate
+ * completes, any ranges invalidated concurrently will
+ * accumulate and persist until all outstanding invalidates
+ * complete.
+ */
+ kvm->mmu_invalidate_range_start =
+ min(kvm->mmu_invalidate_range_start, start);
+ kvm->mmu_invalidate_range_end =
+ max(kvm->mmu_invalidate_range_end, end);
+ }
+}
+
+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);
+ const struct kvm_hva_range hva_range = {
+ .start = range->start,
+ .end = range->end,
+ .pte = __pte(0),
+ .handler = kvm_unmap_gfn_range,
+ .on_lock = kvm_mmu_invalidate_begin,
+ .on_unlock = kvm_arch_guest_memory_reclaimed,
+ .flush_on_ret = true,
+ .may_block = mmu_notifier_range_blockable(range),
+ };
+
+ trace_kvm_unmap_hva_range(range->start, range->end);
+
+ /*
+ * Prevent memslot modification between range_start() and range_end()
+ * so that conditionally locking provides the same result in both
+ * functions. Without that guarantee, the mmu_invalidate_in_progress
+ * adjustments will be imbalanced.
+ *
+ * Pairs with the decrement in range_end().
+ */
+ spin_lock(&kvm->mn_invalidate_lock);
+ kvm->mn_active_invalidate_count++;
+ spin_unlock(&kvm->mn_invalidate_lock);
+
+ /*
+ * Invalidate pfn caches _before_ invalidating the secondary MMUs, i.e.
+ * before acquiring mmu_lock, to avoid holding mmu_lock while acquiring
+ * each cache's lock. There are relatively few caches in existence at
+ * any given time, and the caches themselves can check for hva overlap,
+ * i.e. don't need to rely on memslot overlap checks for performance.
+ * Because this runs without holding mmu_lock, the pfn caches must use
+ * mn_active_invalidate_count (see above) instead of
+ * mmu_invalidate_in_progress.
+ */
+ gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end,
+ hva_range.may_block);
+
+ __kvm_handle_hva_range(kvm, &hva_range);
+
+ return 0;
+}
+
+void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start,
+ unsigned long end)
+{
+ /*
+ * 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_invalidate_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_invalidate_retry().
+ */
+ kvm->mmu_invalidate_in_progress--;
+}
+
+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);
+ const struct kvm_hva_range hva_range = {
+ .start = range->start,
+ .end = range->end,
+ .pte = __pte(0),
+ .handler = (void *)kvm_null_fn,
+ .on_lock = kvm_mmu_invalidate_end,
+ .on_unlock = (void *)kvm_null_fn,
+ .flush_on_ret = false,
+ .may_block = mmu_notifier_range_blockable(range),
+ };
+ bool wake;
+
+ __kvm_handle_hva_range(kvm, &hva_range);
+
+ /* Pairs with the increment in range_start(). */
+ spin_lock(&kvm->mn_invalidate_lock);
+ wake = (--kvm->mn_active_invalidate_count == 0);
+ spin_unlock(&kvm->mn_invalidate_lock);
+
+ /*
+ * There can only be one waiter, since the wait happens under
+ * slots_lock.
+ */
+ if (wake)
+ rcuwait_wake_up(&kvm->mn_memslots_update_rcuwait);
+
+ BUG_ON(kvm->mmu_invalidate_in_progress < 0);
+}
+
+static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
+ struct mm_struct *mm,
+ unsigned long start,
+ unsigned long end)
+{
+ trace_kvm_age_hva(start, end);
+
+ return kvm_handle_hva_range(mn, start, end, __pte(0), kvm_age_gfn);
+}
+
+static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn,
+ struct mm_struct *mm,
+ unsigned long start,
+ unsigned long end)
+{
+ trace_kvm_age_hva(start, end);
+
+ /*
+ * 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.
+ */
+ return kvm_handle_hva_range_no_flush(mn, start, end, kvm_age_gfn);
+}
+
+static int kvm_mmu_notifier_test_young(struct mmu_notifier *mn,
+ struct mm_struct *mm,
+ unsigned long address)
+{
+ trace_kvm_test_age_hva(address);
+
+ return kvm_handle_hva_range_no_flush(mn, address, address + 1,
+ kvm_test_age_gfn);
+}
+
+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 */
+
+#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
+static int kvm_pm_notifier_call(struct notifier_block *bl,
+ unsigned long state,
+ void *unused)
+{
+ struct kvm *kvm = container_of(bl, struct kvm, pm_notifier);
+
+ return kvm_arch_pm_notifier(kvm, state);
+}
+
+static void kvm_init_pm_notifier(struct kvm *kvm)
+{
+ kvm->pm_notifier.notifier_call = kvm_pm_notifier_call;
+ /* Suspend KVM before we suspend ftrace, RCU, etc. */
+ kvm->pm_notifier.priority = INT_MAX;
+ register_pm_notifier(&kvm->pm_notifier);
+}
+
+static void kvm_destroy_pm_notifier(struct kvm *kvm)
+{
+ unregister_pm_notifier(&kvm->pm_notifier);
+}
+#else /* !CONFIG_HAVE_KVM_PM_NOTIFIER */
+static void kvm_init_pm_notifier(struct kvm *kvm)
+{
+}
+
+static void kvm_destroy_pm_notifier(struct kvm *kvm)
+{
+}
+#endif /* CONFIG_HAVE_KVM_PM_NOTIFIER */
+
+static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)
+{
+ if (!memslot->dirty_bitmap)
+ return;
+
+ kvfree(memslot->dirty_bitmap);
+ memslot->dirty_bitmap = NULL;
+}
+
+/* This does not remove the slot from struct kvm_memslots data structures */
+static void kvm_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot)
+{
+ kvm_destroy_dirty_bitmap(slot);
+
+ kvm_arch_free_memslot(kvm, slot);
+
+ kfree(slot);
+}
+
+static void kvm_free_memslots(struct kvm *kvm, struct kvm_memslots *slots)
+{
+ struct hlist_node *idnode;
+ struct kvm_memory_slot *memslot;
+ int bkt;
+
+ /*
+ * The same memslot objects live in both active and inactive sets,
+ * arbitrarily free using index '1' so the second invocation of this
+ * function isn't operating over a structure with dangling pointers
+ * (even though this function isn't actually touching them).
+ */
+ if (!slots->node_idx)
+ return;
+
+ hash_for_each_safe(slots->id_hash, bkt, idnode, memslot, id_node[1])
+ kvm_free_memslot(kvm, memslot);
+}
+
+static umode_t kvm_stats_debugfs_mode(const struct _kvm_stats_desc *pdesc)
+{
+ switch (pdesc->desc.flags & KVM_STATS_TYPE_MASK) {
+ case KVM_STATS_TYPE_INSTANT:
+ return 0444;
+ case KVM_STATS_TYPE_CUMULATIVE:
+ case KVM_STATS_TYPE_PEAK:
+ default:
+ return 0644;
+ }
+}
+
+
+static void kvm_destroy_vm_debugfs(struct kvm *kvm)
+{
+ int i;
+ int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc +
+ kvm_vcpu_stats_header.num_desc;
+
+ if (IS_ERR(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, const char *fdname)
+{
+ static DEFINE_MUTEX(kvm_debugfs_lock);
+ struct dentry *dent;
+ char dir_name[ITOA_MAX_LEN * 2];
+ struct kvm_stat_data *stat_data;
+ const struct _kvm_stats_desc *pdesc;
+ int i, ret = -ENOMEM;
+ int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc +
+ kvm_vcpu_stats_header.num_desc;
+
+ if (!debugfs_initialized())
+ return 0;
+
+ snprintf(dir_name, sizeof(dir_name), "%d-%s", task_pid_nr(current), fdname);
+ 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)
+ goto out_err;
+
+ for (i = 0; i < kvm_vm_stats_header.num_desc; ++i) {
+ pdesc = &kvm_vm_stats_desc[i];
+ stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT);
+ if (!stat_data)
+ goto out_err;
+
+ stat_data->kvm = kvm;
+ stat_data->desc = pdesc;
+ stat_data->kind = KVM_STAT_VM;
+ kvm->debugfs_stat_data[i] = stat_data;
+ debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc),
+ kvm->debugfs_dentry, stat_data,
+ &stat_fops_per_vm);
+ }
+
+ for (i = 0; i < kvm_vcpu_stats_header.num_desc; ++i) {
+ pdesc = &kvm_vcpu_stats_desc[i];
+ stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT);
+ if (!stat_data)
+ goto out_err;
+
+ stat_data->kvm = kvm;
+ stat_data->desc = pdesc;
+ stat_data->kind = KVM_STAT_VCPU;
+ kvm->debugfs_stat_data[i + kvm_vm_stats_header.num_desc] = stat_data;
+ debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc),
+ kvm->debugfs_dentry, stat_data,
+ &stat_fops_per_vm);
+ }
+
+ ret = kvm_arch_create_vm_debugfs(kvm);
+ if (ret)
+ goto out_err;
+
+ return 0;
+out_err:
+ kvm_destroy_vm_debugfs(kvm);
+ return ret;
+}
+
+/*
+ * 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)
+{
+}
+
+/*
+ * Called after per-vm debugfs created. When called kvm->debugfs_dentry should
+ * be setup already, so we can create arch-specific debugfs entries under it.
+ * Cleanup should be automatic done in kvm_destroy_vm_debugfs() recursively, so
+ * a per-arch destroy interface is not needed.
+ */
+int __weak kvm_arch_create_vm_debugfs(struct kvm *kvm)
+{
+ return 0;
+}
+
+static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
+{
+ struct kvm *kvm = kvm_arch_alloc_vm();
+ struct kvm_memslots *slots;
+ int r = -ENOMEM;
+ int i, j;
+
+ if (!kvm)
+ return ERR_PTR(-ENOMEM);
+
+ /* KVM is pinned via open("/dev/kvm"), the fd passed to this ioctl(). */
+ __module_get(kvm_chardev_ops.owner);
+
+ KVM_MMU_LOCK_INIT(kvm);
+ 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);
+ mutex_init(&kvm->slots_arch_lock);
+ spin_lock_init(&kvm->mn_invalidate_lock);
+ rcuwait_init(&kvm->mn_memslots_update_rcuwait);
+ xa_init(&kvm->vcpu_array);
+
+ INIT_LIST_HEAD(&kvm->gpc_list);
+ spin_lock_init(&kvm->gpc_lock);
+
+ INIT_LIST_HEAD(&kvm->devices);
+ kvm->max_vcpus = KVM_MAX_VCPUS;
+
+ BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX);
+
+ /*
+ * Force subsequent debugfs file creations to fail if the VM directory
+ * is not created (by kvm_create_vm_debugfs()).
+ */
+ kvm->debugfs_dentry = ERR_PTR(-ENOENT);
+
+ snprintf(kvm->stats_id, sizeof(kvm->stats_id), "kvm-%d",
+ task_pid_nr(current));
+
+ 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++) {
+ for (j = 0; j < 2; j++) {
+ slots = &kvm->__memslots[i][j];
+
+ atomic_long_set(&slots->last_used_slot, (unsigned long)NULL);
+ slots->hva_tree = RB_ROOT_CACHED;
+ slots->gfn_tree = RB_ROOT;
+ hash_init(slots->id_hash);
+ slots->node_idx = j;
+
+ /* Generations must be different for each address space. */
+ slots->generation = i;
+ }
+
+ rcu_assign_pointer(kvm->memslots[i], &kvm->__memslots[i][0]);
+ }
+
+ 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;
+ }
+
+ 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_coalesced_mmio_init(kvm);
+ if (r < 0)
+ goto out_no_coalesced_mmio;
+
+ r = kvm_create_vm_debugfs(kvm, fdname);
+ if (r)
+ goto out_err_no_debugfs;
+
+ 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();
+ kvm_init_pm_notifier(kvm);
+
+ return kvm;
+
+out_err:
+ kvm_destroy_vm_debugfs(kvm);
+out_err_no_debugfs:
+ kvm_coalesced_mmio_free(kvm);
+out_no_coalesced_mmio:
+#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));
+ 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);
+ module_put(kvm_chardev_ops.owner);
+ 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_destroy_pm_notifier(kvm);
+ 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);
+ /*
+ * At this point, pending calls to invalidate_range_start()
+ * have completed but no more MMU notifiers will run, so
+ * mn_active_invalidate_count may remain unbalanced.
+ * No threads can be waiting in install_new_memslots as the
+ * last reference on KVM has been dropped, but freeing
+ * memslots would deadlock without this manual intervention.
+ */
+ WARN_ON(rcuwait_active(&kvm->mn_memslots_update_rcuwait));
+ kvm->mn_active_invalidate_count = 0;
+#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[i][0]);
+ kvm_free_memslots(kvm, &kvm->__memslots[i][1]);
+ }
+ 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);
+
+/*
+ * Make sure the vm is not during destruction, which is a safe version of
+ * kvm_get_kvm(). Return true if kvm referenced successfully, false otherwise.
+ */
+bool kvm_get_kvm_safe(struct kvm *kvm)
+{
+ return refcount_inc_not_zero(&kvm->users_count);
+}
+EXPORT_SYMBOL_GPL(kvm_get_kvm_safe);
+
+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 = kvm_dirty_bitmap_bytes(memslot);
+
+ memslot->dirty_bitmap = __vcalloc(2, dirty_bytes, GFP_KERNEL_ACCOUNT);
+ if (!memslot->dirty_bitmap)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static struct kvm_memslots *kvm_get_inactive_memslots(struct kvm *kvm, int as_id)
+{
+ struct kvm_memslots *active = __kvm_memslots(kvm, as_id);
+ int node_idx_inactive = active->node_idx ^ 1;
+
+ return &kvm->__memslots[as_id][node_idx_inactive];
+}
+
+/*
+ * Helper to get the address space ID when one of memslot pointers may be NULL.
+ * This also serves as a sanity that at least one of the pointers is non-NULL,
+ * and that their address space IDs don't diverge.
+ */
+static int kvm_memslots_get_as_id(struct kvm_memory_slot *a,
+ struct kvm_memory_slot *b)
+{
+ if (WARN_ON_ONCE(!a && !b))
+ return 0;
+
+ if (!a)
+ return b->as_id;
+ if (!b)
+ return a->as_id;
+
+ WARN_ON_ONCE(a->as_id != b->as_id);
+ return a->as_id;
+}
+
+static void kvm_insert_gfn_node(struct kvm_memslots *slots,
+ struct kvm_memory_slot *slot)
+{
+ struct rb_root *gfn_tree = &slots->gfn_tree;
+ struct rb_node **node, *parent;
+ int idx = slots->node_idx;
+
+ parent = NULL;
+ for (node = &gfn_tree->rb_node; *node; ) {
+ struct kvm_memory_slot *tmp;
+
+ tmp = container_of(*node, struct kvm_memory_slot, gfn_node[idx]);
+ parent = *node;
+ if (slot->base_gfn < tmp->base_gfn)
+ node = &(*node)->rb_left;
+ else if (slot->base_gfn > tmp->base_gfn)
+ node = &(*node)->rb_right;
+ else
+ BUG();
+ }
+
+ rb_link_node(&slot->gfn_node[idx], parent, node);
+ rb_insert_color(&slot->gfn_node[idx], gfn_tree);
+}
+
+static void kvm_erase_gfn_node(struct kvm_memslots *slots,
+ struct kvm_memory_slot *slot)
+{
+ rb_erase(&slot->gfn_node[slots->node_idx], &slots->gfn_tree);
+}
+
+static void kvm_replace_gfn_node(struct kvm_memslots *slots,
+ struct kvm_memory_slot *old,
+ struct kvm_memory_slot *new)
+{
+ int idx = slots->node_idx;
+
+ WARN_ON_ONCE(old->base_gfn != new->base_gfn);
+
+ rb_replace_node(&old->gfn_node[idx], &new->gfn_node[idx],
+ &slots->gfn_tree);
+}
+
+/*
+ * Replace @old with @new in the inactive memslots.
+ *
+ * With NULL @old this simply adds @new.
+ * With NULL @new this simply removes @old.
+ *
+ * If @new is non-NULL its hva_node[slots_idx] range has to be set
+ * appropriately.
+ */
+static void kvm_replace_memslot(struct kvm *kvm,
+ struct kvm_memory_slot *old,
+ struct kvm_memory_slot *new)
+{
+ int as_id = kvm_memslots_get_as_id(old, new);
+ struct kvm_memslots *slots = kvm_get_inactive_memslots(kvm, as_id);
+ int idx = slots->node_idx;
+
+ if (old) {
+ hash_del(&old->id_node[idx]);
+ interval_tree_remove(&old->hva_node[idx], &slots->hva_tree);
+
+ if ((long)old == atomic_long_read(&slots->last_used_slot))
+ atomic_long_set(&slots->last_used_slot, (long)new);
+
+ if (!new) {
+ kvm_erase_gfn_node(slots, old);
+ return;
+ }
+ }
+
+ /*
+ * Initialize @new's hva range. Do this even when replacing an @old
+ * slot, kvm_copy_memslot() deliberately does not touch node data.
+ */
+ new->hva_node[idx].start = new->userspace_addr;
+ new->hva_node[idx].last = new->userspace_addr +
+ (new->npages << PAGE_SHIFT) - 1;
+
+ /*
+ * (Re)Add the new memslot. There is no O(1) interval_tree_replace(),
+ * hva_node needs to be swapped with remove+insert even though hva can't
+ * change when replacing an existing slot.
+ */
+ hash_add(slots->id_hash, &new->id_node[idx], new->id);
+ interval_tree_insert(&new->hva_node[idx], &slots->hva_tree);
+
+ /*
+ * If the memslot gfn is unchanged, rb_replace_node() can be used to
+ * switch the node in the gfn tree instead of removing the old and
+ * inserting the new as two separate operations. Replacement is a
+ * single O(1) operation versus two O(log(n)) operations for
+ * remove+insert.
+ */
+ if (old && old->base_gfn == new->base_gfn) {
+ kvm_replace_gfn_node(slots, old, new);
+ } else {
+ if (old)
+ kvm_erase_gfn_node(slots, old);
+ kvm_insert_gfn_node(slots, new);
+ }
+}
+
+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 void kvm_swap_active_memslots(struct kvm *kvm, int as_id)
+{
+ struct kvm_memslots *slots = kvm_get_inactive_memslots(kvm, as_id);
+
+ /* Grab the generation from the activate memslots. */
+ u64 gen = __kvm_memslots(kvm, as_id)->generation;
+
+ WARN_ON(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS);
+ slots->generation = gen | KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS;
+
+ /*
+ * Do not store the new memslots while there are invalidations in
+ * progress, otherwise the locking in invalidate_range_start and
+ * invalidate_range_end will be unbalanced.
+ */
+ spin_lock(&kvm->mn_invalidate_lock);
+ prepare_to_rcuwait(&kvm->mn_memslots_update_rcuwait);
+ while (kvm->mn_active_invalidate_count) {
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ spin_unlock(&kvm->mn_invalidate_lock);
+ schedule();
+ spin_lock(&kvm->mn_invalidate_lock);
+ }
+ finish_rcuwait(&kvm->mn_memslots_update_rcuwait);
+ rcu_assign_pointer(kvm->memslots[as_id], slots);
+ spin_unlock(&kvm->mn_invalidate_lock);
+
+ /*
+ * Acquired in kvm_set_memslot. Must be released before synchronize
+ * SRCU below in order to avoid deadlock with another thread
+ * acquiring the slots_arch_lock in an srcu critical section.
+ */
+ mutex_unlock(&kvm->slots_arch_lock);
+
+ 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;
+}
+
+static int kvm_prepare_memory_region(struct kvm *kvm,
+ const struct kvm_memory_slot *old,
+ struct kvm_memory_slot *new,
+ enum kvm_mr_change change)
+{
+ int r;
+
+ /*
+ * If dirty logging is disabled, nullify the bitmap; the old bitmap
+ * will be freed on "commit". If logging is enabled in both old and
+ * new, reuse the existing bitmap. If logging is enabled only in the
+ * new and KVM isn't using a ring buffer, allocate and initialize a
+ * new bitmap.
+ */
+ if (change != KVM_MR_DELETE) {
+ if (!(new->flags & KVM_MEM_LOG_DIRTY_PAGES))
+ new->dirty_bitmap = NULL;
+ else if (old && old->dirty_bitmap)
+ new->dirty_bitmap = old->dirty_bitmap;
+ else if (!kvm->dirty_ring_size) {
+ 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_arch_prepare_memory_region(kvm, old, new, change);
+
+ /* Free the bitmap on failure if it was allocated above. */
+ if (r && new && new->dirty_bitmap && (!old || !old->dirty_bitmap))
+ kvm_destroy_dirty_bitmap(new);
+
+ return r;
+}
+
+static void kvm_commit_memory_region(struct kvm *kvm,
+ struct kvm_memory_slot *old,
+ const struct kvm_memory_slot *new,
+ enum kvm_mr_change change)
+{
+ /*
+ * Update the total number of memslot pages before calling the arch
+ * hook so that architectures can consume the result directly.
+ */
+ if (change == KVM_MR_DELETE)
+ kvm->nr_memslot_pages -= old->npages;
+ else if (change == KVM_MR_CREATE)
+ kvm->nr_memslot_pages += new->npages;
+
+ kvm_arch_commit_memory_region(kvm, old, new, change);
+
+ switch (change) {
+ case KVM_MR_CREATE:
+ /* Nothing more to do. */
+ break;
+ case KVM_MR_DELETE:
+ /* Free the old memslot and all its metadata. */
+ kvm_free_memslot(kvm, old);
+ break;
+ case KVM_MR_MOVE:
+ case KVM_MR_FLAGS_ONLY:
+ /*
+ * Free the dirty bitmap as needed; the below check encompasses
+ * both the flags and whether a ring buffer is being used)
+ */
+ if (old->dirty_bitmap && !new->dirty_bitmap)
+ kvm_destroy_dirty_bitmap(old);
+
+ /*
+ * The final quirk. Free the detached, old slot, but only its
+ * memory, not any metadata. Metadata, including arch specific
+ * data, may be reused by @new.
+ */
+ kfree(old);
+ break;
+ default:
+ BUG();
+ }
+}
+
+/*
+ * Activate @new, which must be installed in the inactive slots by the caller,
+ * by swapping the active slots and then propagating @new to @old once @old is
+ * unreachable and can be safely modified.
+ *
+ * With NULL @old this simply adds @new to @active (while swapping the sets).
+ * With NULL @new this simply removes @old from @active and frees it
+ * (while also swapping the sets).
+ */
+static void kvm_activate_memslot(struct kvm *kvm,
+ struct kvm_memory_slot *old,
+ struct kvm_memory_slot *new)
+{
+ int as_id = kvm_memslots_get_as_id(old, new);
+
+ kvm_swap_active_memslots(kvm, as_id);
+
+ /* Propagate the new memslot to the now inactive memslots. */
+ kvm_replace_memslot(kvm, old, new);
+}
+
+static void kvm_copy_memslot(struct kvm_memory_slot *dest,
+ const struct kvm_memory_slot *src)
+{
+ dest->base_gfn = src->base_gfn;
+ dest->npages = src->npages;
+ dest->dirty_bitmap = src->dirty_bitmap;
+ dest->arch = src->arch;
+ dest->userspace_addr = src->userspace_addr;
+ dest->flags = src->flags;
+ dest->id = src->id;
+ dest->as_id = src->as_id;
+}
+
+static void kvm_invalidate_memslot(struct kvm *kvm,
+ struct kvm_memory_slot *old,
+ struct kvm_memory_slot *invalid_slot)
+{
+ /*
+ * Mark the current slot INVALID. As with all memslot modifications,
+ * this must be done on an unreachable slot to avoid modifying the
+ * current slot in the active tree.
+ */
+ kvm_copy_memslot(invalid_slot, old);
+ invalid_slot->flags |= KVM_MEMSLOT_INVALID;
+ kvm_replace_memslot(kvm, old, invalid_slot);
+
+ /*
+ * Activate the slot that is now marked INVALID, but don't propagate
+ * the slot to the now inactive slots. The slot is either going to be
+ * deleted or recreated as a new slot.
+ */
+ kvm_swap_active_memslots(kvm, old->as_id);
+
+ /*
+ * 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, old);
+ kvm_arch_guest_memory_reclaimed(kvm);
+
+ /* Was released by kvm_swap_active_memslots, reacquire. */
+ mutex_lock(&kvm->slots_arch_lock);
+
+ /*
+ * Copy the arch-specific field of the newly-installed slot back to the
+ * old slot as the arch data could have changed between releasing
+ * slots_arch_lock in install_new_memslots() and re-acquiring the lock
+ * above. Writers are required to retrieve memslots *after* acquiring
+ * slots_arch_lock, thus the active slot's data is guaranteed to be fresh.
+ */
+ old->arch = invalid_slot->arch;
+}
+
+static void kvm_create_memslot(struct kvm *kvm,
+ struct kvm_memory_slot *new)
+{
+ /* Add the new memslot to the inactive set and activate. */
+ kvm_replace_memslot(kvm, NULL, new);
+ kvm_activate_memslot(kvm, NULL, new);
+}
+
+static void kvm_delete_memslot(struct kvm *kvm,
+ struct kvm_memory_slot *old,
+ struct kvm_memory_slot *invalid_slot)
+{
+ /*
+ * Remove the old memslot (in the inactive memslots) by passing NULL as
+ * the "new" slot, and for the invalid version in the active slots.
+ */
+ kvm_replace_memslot(kvm, old, NULL);
+ kvm_activate_memslot(kvm, invalid_slot, NULL);
+}
+
+static void kvm_move_memslot(struct kvm *kvm,
+ struct kvm_memory_slot *old,
+ struct kvm_memory_slot *new,
+ struct kvm_memory_slot *invalid_slot)
+{
+ /*
+ * Replace the old memslot in the inactive slots, and then swap slots
+ * and replace the current INVALID with the new as well.
+ */
+ kvm_replace_memslot(kvm, old, new);
+ kvm_activate_memslot(kvm, invalid_slot, new);
+}
+
+static void kvm_update_flags_memslot(struct kvm *kvm,
+ struct kvm_memory_slot *old,
+ struct kvm_memory_slot *new)
+{
+ /*
+ * Similar to the MOVE case, but the slot doesn't need to be zapped as
+ * an intermediate step. Instead, the old memslot is simply replaced
+ * with a new, updated copy in both memslot sets.
+ */
+ kvm_replace_memslot(kvm, old, new);
+ kvm_activate_memslot(kvm, old, new);
+}
+
+static int kvm_set_memslot(struct kvm *kvm,
+ struct kvm_memory_slot *old,
+ struct kvm_memory_slot *new,
+ enum kvm_mr_change change)
+{
+ struct kvm_memory_slot *invalid_slot;
+ int r;
+
+ /*
+ * Released in kvm_swap_active_memslots.
+ *
+ * Must be held from before the current memslots are copied until
+ * after the new memslots are installed with rcu_assign_pointer,
+ * then released before the synchronize srcu in kvm_swap_active_memslots.
+ *
+ * When modifying memslots outside of the slots_lock, must be held
+ * before reading the pointer to the current memslots until after all
+ * changes to those memslots are complete.
+ *
+ * These rules ensure that installing new memslots does not lose
+ * changes made to the previous memslots.
+ */
+ mutex_lock(&kvm->slots_arch_lock);
+
+ /*
+ * Invalidate the old slot if it's being deleted or moved. This is
+ * done prior to actually deleting/moving the memslot to allow vCPUs to
+ * continue running by ensuring there are no mappings or shadow pages
+ * for the memslot when it is deleted/moved. Without pre-invalidation
+ * (and without a lock), a window would exist between effecting the
+ * delete/move and committing the changes in arch code where KVM or a
+ * guest could access a non-existent memslot.
+ *
+ * Modifications are done on a temporary, unreachable slot. The old
+ * slot needs to be preserved in case a later step fails and the
+ * invalidation needs to be reverted.
+ */
+ if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) {
+ invalid_slot = kzalloc(sizeof(*invalid_slot), GFP_KERNEL_ACCOUNT);
+ if (!invalid_slot) {
+ mutex_unlock(&kvm->slots_arch_lock);
+ return -ENOMEM;
+ }
+ kvm_invalidate_memslot(kvm, old, invalid_slot);
+ }
+
+ r = kvm_prepare_memory_region(kvm, old, new, change);
+ if (r) {
+ /*
+ * For DELETE/MOVE, revert the above INVALID change. No
+ * modifications required since the original slot was preserved
+ * in the inactive slots. Changing the active memslots also
+ * release slots_arch_lock.
+ */
+ if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) {
+ kvm_activate_memslot(kvm, invalid_slot, old);
+ kfree(invalid_slot);
+ } else {
+ mutex_unlock(&kvm->slots_arch_lock);
+ }
+ return r;
+ }
+
+ /*
+ * For DELETE and MOVE, the working slot is now active as the INVALID
+ * version of the old slot. MOVE is particularly special as it reuses
+ * the old slot and returns a copy of the old slot (in working_slot).
+ * For CREATE, there is no old slot. For DELETE and FLAGS_ONLY, the
+ * old slot is detached but otherwise preserved.
+ */
+ if (change == KVM_MR_CREATE)
+ kvm_create_memslot(kvm, new);
+ else if (change == KVM_MR_DELETE)
+ kvm_delete_memslot(kvm, old, invalid_slot);
+ else if (change == KVM_MR_MOVE)
+ kvm_move_memslot(kvm, old, new, invalid_slot);
+ else if (change == KVM_MR_FLAGS_ONLY)
+ kvm_update_flags_memslot(kvm, old, new);
+ else
+ BUG();
+
+ /* Free the temporary INVALID slot used for DELETE and MOVE. */
+ if (change == KVM_MR_DELETE || change == KVM_MR_MOVE)
+ kfree(invalid_slot);
+
+ /*
+ * No need to refresh new->arch, changes after dropping slots_arch_lock
+ * will directly hit the final, active memslot. Architectures are
+ * responsible for knowing that new->arch may be stale.
+ */
+ kvm_commit_memory_region(kvm, old, new, change);
+
+ return 0;
+}
+
+static bool kvm_check_memslot_overlap(struct kvm_memslots *slots, int id,
+ gfn_t start, gfn_t end)
+{
+ struct kvm_memslot_iter iter;
+
+ kvm_for_each_memslot_in_gfn_range(&iter, slots, start, end) {
+ if (iter.slot->id != id)
+ return true;
+ }
+
+ return false;
+}
+
+/*
+ * 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_memslots *slots;
+ enum kvm_mr_change change;
+ unsigned long npages;
+ gfn_t base_gfn;
+ 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;
+ if ((mem->memory_size >> PAGE_SHIFT) > KVM_MEM_MAX_NR_PAGES)
+ return -EINVAL;
+
+ slots = __kvm_memslots(kvm, as_id);
+
+ /*
+ * Note, the old memslot (and the pointer itself!) may be invalidated
+ * and/or destroyed by kvm_set_memslot().
+ */
+ old = id_to_memslot(slots, id);
+
+ if (!mem->memory_size) {
+ if (!old || !old->npages)
+ return -EINVAL;
+
+ if (WARN_ON_ONCE(kvm->nr_memslot_pages < old->npages))
+ return -EIO;
+
+ return kvm_set_memslot(kvm, old, NULL, KVM_MR_DELETE);
+ }
+
+ base_gfn = (mem->guest_phys_addr >> PAGE_SHIFT);
+ npages = (mem->memory_size >> PAGE_SHIFT);
+
+ if (!old || !old->npages) {
+ change = KVM_MR_CREATE;
+
+ /*
+ * To simplify KVM internals, the total number of pages across
+ * all memslots must fit in an unsigned long.
+ */
+ if ((kvm->nr_memslot_pages + npages) < kvm->nr_memslot_pages)
+ return -EINVAL;
+ } else { /* Modify an existing slot. */
+ if ((mem->userspace_addr != old->userspace_addr) ||
+ (npages != old->npages) ||
+ ((mem->flags ^ old->flags) & KVM_MEM_READONLY))
+ return -EINVAL;
+
+ if (base_gfn != old->base_gfn)
+ change = KVM_MR_MOVE;
+ else if (mem->flags != old->flags)
+ change = KVM_MR_FLAGS_ONLY;
+ else /* Nothing to change. */
+ return 0;
+ }
+
+ if ((change == KVM_MR_CREATE || change == KVM_MR_MOVE) &&
+ kvm_check_memslot_overlap(slots, id, base_gfn, base_gfn + npages))
+ return -EEXIST;
+
+ /* Allocate a slot that will persist in the memslot. */
+ new = kzalloc(sizeof(*new), GFP_KERNEL_ACCOUNT);
+ if (!new)
+ return -ENOMEM;
+
+ new->as_id = as_id;
+ new->id = id;
+ new->base_gfn = base_gfn;
+ new->npages = npages;
+ new->flags = mem->flags;
+ new->userspace_addr = mem->userspace_addr;
+
+ r = kvm_set_memslot(kvm, old, new, change);
+ if (r)
+ kfree(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;
+
+ /* Dirty ring tracking is exclusive to dirty log tracking */
+ if (kvm->dirty_ring_size)
+ return -ENXIO;
+
+ *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;
+
+ /* Dirty ring tracking is exclusive to dirty log tracking */
+ if (kvm->dirty_ring_size)
+ return -ENXIO;
+
+ 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);
+
+ KVM_MMU_LOCK(kvm);
+ 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);
+ }
+ KVM_MMU_UNLOCK(kvm);
+ }
+
+ 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;
+
+ /* Dirty ring tracking is exclusive to dirty log tracking */
+ if (kvm->dirty_ring_size)
+ return -ENXIO;
+
+ 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;
+
+ KVM_MMU_LOCK(kvm);
+ 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);
+ }
+ }
+ KVM_MMU_UNLOCK(kvm);
+
+ 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)
+{
+ struct kvm_memslots *slots = kvm_vcpu_memslots(vcpu);
+ u64 gen = slots->generation;
+ struct kvm_memory_slot *slot;
+
+ /*
+ * This also protects against using a memslot from a different address space,
+ * since different address spaces have different generation numbers.
+ */
+ if (unlikely(gen != vcpu->last_used_slot_gen)) {
+ vcpu->last_used_slot = NULL;
+ vcpu->last_used_slot_gen = gen;
+ }
+
+ slot = try_get_memslot(vcpu->last_used_slot, gfn);
+ if (slot)
+ return slot;
+
+ /*
+ * Fall back to searching all memslots. We purposely use
+ * search_memslots() instead of __gfn_to_memslot() to avoid
+ * thrashing the VM-wide last_used_slot in kvm_memslots.
+ */
+ slot = search_memslots(slots, gfn, false);
+ if (slot) {
+ vcpu->last_used_slot = slot;
+ return slot;
+ }
+
+ return NULL;
+}
+
+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(const struct kvm_memory_slot *slot)
+{
+ return slot->flags & KVM_MEM_READONLY;
+}
+
+static unsigned long __gfn_to_hva_many(const 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;
+
+ 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)
+{
+ struct page *page = kvm_pfn_to_refcounted_page(pfn);
+
+ if (!page)
+ return 1;
+
+ return get_page_unless_zero(page);
+}
+
+static int hva_to_pfn_remapped(struct vm_area_struct *vma,
+ unsigned long addr, 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_try_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.
+ */
+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;
+ 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 = vma_lookup(current->mm, addr);
+
+ if (vma == NULL)
+ pfn = KVM_PFN_ERR_FAULT;
+ else if (vma->vm_flags & (VM_IO | VM_PFNMAP)) {
+ r = hva_to_pfn_remapped(vma, addr, 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(const struct kvm_memory_slot *slot, gfn_t gfn,
+ bool atomic, bool *async, bool write_fault,
+ bool *writable, hva_t *hva)
+{
+ unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault);
+
+ if (hva)
+ *hva = addr;
+
+ 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, NULL);
+}
+EXPORT_SYMBOL_GPL(gfn_to_pfn_prot);
+
+kvm_pfn_t gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn)
+{
+ return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL, NULL);
+}
+EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot);
+
+kvm_pfn_t gfn_to_pfn_memslot_atomic(const struct kvm_memory_slot *slot, gfn_t gfn)
+{
+ return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL, 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);
+
+/*
+ * Do not use this helper unless you are absolutely certain the gfn _must_ be
+ * backed by 'struct page'. A valid example is if the backing memslot is
+ * controlled by KVM. Note, if the returned page is valid, it's refcount has
+ * been elevated by gfn_to_pfn().
+ */
+struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
+{
+ struct page *page;
+ kvm_pfn_t pfn;
+
+ pfn = gfn_to_pfn(kvm, gfn);
+
+ if (is_error_noslot_pfn(pfn))
+ return KVM_ERR_PTR_BAD_PAGE;
+
+ page = kvm_pfn_to_refcounted_page(pfn);
+ if (!page)
+ return KVM_ERR_PTR_BAD_PAGE;
+
+ return page;
+}
+EXPORT_SYMBOL_GPL(gfn_to_page);
+
+void kvm_release_pfn(kvm_pfn_t pfn, bool dirty)
+{
+ if (dirty)
+ kvm_release_pfn_dirty(pfn);
+ else
+ kvm_release_pfn_clean(pfn);
+}
+
+int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map)
+{
+ kvm_pfn_t pfn;
+ void *hva = NULL;
+ struct page *page = KVM_UNMAPPED_PAGE;
+
+ if (!map)
+ return -EINVAL;
+
+ pfn = gfn_to_pfn(vcpu->kvm, gfn);
+ if (is_error_noslot_pfn(pfn))
+ return -EINVAL;
+
+ if (pfn_valid(pfn)) {
+ page = pfn_to_page(pfn);
+ hva = kmap(page);
+#ifdef CONFIG_HAS_IOMEM
+ } else {
+ hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB);
+#endif
+ }
+
+ if (!hva)
+ return -EFAULT;
+
+ map->page = page;
+ map->hva = hva;
+ map->pfn = pfn;
+ map->gfn = gfn;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_map);
+
+void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty)
+{
+ if (!map)
+ return;
+
+ if (!map->hva)
+ return;
+
+ if (map->page != KVM_UNMAPPED_PAGE)
+ kunmap(map->page);
+#ifdef CONFIG_HAS_IOMEM
+ else
+ memunmap(map->hva);
+#endif
+
+ if (dirty)
+ kvm_vcpu_mark_page_dirty(vcpu, map->gfn);
+
+ kvm_release_pfn(map->pfn, dirty);
+
+ map->hva = NULL;
+ map->page = NULL;
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_unmap);
+
+static bool kvm_is_ad_tracked_page(struct page *page)
+{
+ /*
+ * Per page-flags.h, pages tagged PG_reserved "should in general not be
+ * touched (e.g. set dirty) except by its owner".
+ */
+ return !PageReserved(page);
+}
+
+static void kvm_set_page_dirty(struct page *page)
+{
+ if (kvm_is_ad_tracked_page(page))
+ SetPageDirty(page);
+}
+
+static void kvm_set_page_accessed(struct page *page)
+{
+ if (kvm_is_ad_tracked_page(page))
+ mark_page_accessed(page);
+}
+
+void kvm_release_page_clean(struct page *page)
+{
+ WARN_ON(is_error_page(page));
+
+ kvm_set_page_accessed(page);
+ put_page(page);
+}
+EXPORT_SYMBOL_GPL(kvm_release_page_clean);
+
+void kvm_release_pfn_clean(kvm_pfn_t pfn)
+{
+ struct page *page;
+
+ if (is_error_noslot_pfn(pfn))
+ return;
+
+ page = kvm_pfn_to_refcounted_page(pfn);
+ if (!page)
+ return;
+
+ kvm_release_page_clean(page);
+}
+EXPORT_SYMBOL_GPL(kvm_release_pfn_clean);
+
+void kvm_release_page_dirty(struct page *page)
+{
+ WARN_ON(is_error_page(page));
+
+ kvm_set_page_dirty(page);
+ kvm_release_page_clean(page);
+}
+EXPORT_SYMBOL_GPL(kvm_release_page_dirty);
+
+void kvm_release_pfn_dirty(kvm_pfn_t pfn)
+{
+ struct page *page;
+
+ if (is_error_noslot_pfn(pfn))
+ return;
+
+ page = kvm_pfn_to_refcounted_page(pfn);
+ if (!page)
+ return;
+
+ kvm_release_page_dirty(page);
+}
+EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty);
+
+/*
+ * Note, checking for an error/noslot pfn is the caller's responsibility when
+ * directly marking a page dirty/accessed. Unlike the "release" helpers, the
+ * "set" helpers are not to be used when the pfn might point at garbage.
+ */
+void kvm_set_pfn_dirty(kvm_pfn_t pfn)
+{
+ if (WARN_ON(is_error_noslot_pfn(pfn)))
+ return;
+
+ if (pfn_valid(pfn))
+ kvm_set_page_dirty(pfn_to_page(pfn));
+}
+EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty);
+
+void kvm_set_pfn_accessed(kvm_pfn_t pfn)
+{
+ if (WARN_ON(is_error_noslot_pfn(pfn)))
+ return;
+
+ if (pfn_valid(pfn))
+ kvm_set_page_accessed(pfn_to_page(pfn));
+}
+EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed);
+
+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 *kvm,
+ 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(kvm, 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(kvm, 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(vcpu->kvm, 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(kvm, 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(struct kvm *kvm, gpa_t gpa, unsigned long len)
+{
+ const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0)));
+ 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, zero_page, offset, len);
+ 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 *kvm,
+ const struct kvm_memory_slot *memslot,
+ gfn_t gfn)
+{
+ struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
+
+#ifdef CONFIG_HAVE_KVM_DIRTY_RING
+ if (WARN_ON_ONCE(!vcpu) || WARN_ON_ONCE(vcpu->kvm != kvm))
+ return;
+#endif
+
+ if (memslot && kvm_slot_dirty_track_enabled(memslot)) {
+ unsigned long rel_gfn = gfn - memslot->base_gfn;
+ u32 slot = (memslot->as_id << 16) | memslot->id;
+
+ if (kvm->dirty_ring_size)
+ kvm_dirty_ring_push(&vcpu->dirty_ring,
+ slot, rel_gfn);
+ else
+ 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(kvm, 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(vcpu->kvm, 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;
+
+ 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))
+ goto out;
+ if (kvm_cpu_has_pending_timer(vcpu))
+ goto out;
+ if (signal_pending(current))
+ goto out;
+ if (kvm_check_request(KVM_REQ_UNBLOCK, vcpu))
+ goto out;
+
+ ret = 0;
+out:
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
+ return ret;
+}
+
+/*
+ * Block the vCPU until the vCPU is runnable, an event arrives, or a signal is
+ * pending. This is mostly used when halting a vCPU, but may also be used
+ * directly for other vCPU non-runnable states, e.g. x86's Wait-For-SIPI.
+ */
+bool kvm_vcpu_block(struct kvm_vcpu *vcpu)
+{
+ struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu);
+ bool waited = false;
+
+ vcpu->stat.generic.blocking = 1;
+
+ preempt_disable();
+ kvm_arch_vcpu_blocking(vcpu);
+ prepare_to_rcuwait(wait);
+ preempt_enable();
+
+ for (;;) {
+ set_current_state(TASK_INTERRUPTIBLE);
+
+ if (kvm_vcpu_check_block(vcpu) < 0)
+ break;
+
+ waited = true;
+ schedule();
+ }
+
+ preempt_disable();
+ finish_rcuwait(wait);
+ kvm_arch_vcpu_unblocking(vcpu);
+ preempt_enable();
+
+ vcpu->stat.generic.blocking = 0;
+
+ return waited;
+}
+
+static inline void update_halt_poll_stats(struct kvm_vcpu *vcpu, ktime_t start,
+ ktime_t end, bool success)
+{
+ struct kvm_vcpu_stat_generic *stats = &vcpu->stat.generic;
+ u64 poll_ns = ktime_to_ns(ktime_sub(end, start));
+
+ ++vcpu->stat.generic.halt_attempted_poll;
+
+ if (success) {
+ ++vcpu->stat.generic.halt_successful_poll;
+
+ if (!vcpu_valid_wakeup(vcpu))
+ ++vcpu->stat.generic.halt_poll_invalid;
+
+ stats->halt_poll_success_ns += poll_ns;
+ KVM_STATS_LOG_HIST_UPDATE(stats->halt_poll_success_hist, poll_ns);
+ } else {
+ stats->halt_poll_fail_ns += poll_ns;
+ KVM_STATS_LOG_HIST_UPDATE(stats->halt_poll_fail_hist, poll_ns);
+ }
+}
+
+static unsigned int kvm_vcpu_max_halt_poll_ns(struct kvm_vcpu *vcpu)
+{
+ struct kvm *kvm = vcpu->kvm;
+
+ if (kvm->override_halt_poll_ns) {
+ /*
+ * Ensure kvm->max_halt_poll_ns is not read before
+ * kvm->override_halt_poll_ns.
+ *
+ * Pairs with the smp_wmb() when enabling KVM_CAP_HALT_POLL.
+ */
+ smp_rmb();
+ return READ_ONCE(kvm->max_halt_poll_ns);
+ }
+
+ return READ_ONCE(halt_poll_ns);
+}
+
+/*
+ * Emulate a vCPU halt condition, e.g. HLT on x86, WFI on arm, etc... If halt
+ * polling is enabled, busy wait for a short time before blocking to avoid the
+ * expensive block+unblock sequence if a wake event arrives soon after the vCPU
+ * is halted.
+ */
+void kvm_vcpu_halt(struct kvm_vcpu *vcpu)
+{
+ unsigned int max_halt_poll_ns = kvm_vcpu_max_halt_poll_ns(vcpu);
+ bool halt_poll_allowed = !kvm_arch_no_poll(vcpu);
+ ktime_t start, cur, poll_end;
+ bool waited = false;
+ bool do_halt_poll;
+ u64 halt_ns;
+
+ if (vcpu->halt_poll_ns > max_halt_poll_ns)
+ vcpu->halt_poll_ns = max_halt_poll_ns;
+
+ do_halt_poll = halt_poll_allowed && vcpu->halt_poll_ns;
+
+ start = cur = poll_end = ktime_get();
+ if (do_halt_poll) {
+ ktime_t stop = ktime_add_ns(start, vcpu->halt_poll_ns);
+
+ do {
+ /*
+ * This sets KVM_REQ_UNHALT if an interrupt
+ * arrives.
+ */
+ if (kvm_vcpu_check_block(vcpu) < 0)
+ goto out;
+ cpu_relax();
+ poll_end = cur = ktime_get();
+ } while (kvm_vcpu_can_poll(cur, stop));
+ }
+
+ waited = kvm_vcpu_block(vcpu);
+
+ cur = ktime_get();
+ if (waited) {
+ vcpu->stat.generic.halt_wait_ns +=
+ ktime_to_ns(cur) - ktime_to_ns(poll_end);
+ KVM_STATS_LOG_HIST_UPDATE(vcpu->stat.generic.halt_wait_hist,
+ ktime_to_ns(cur) - ktime_to_ns(poll_end));
+ }
+out:
+ /* The total time the vCPU was "halted", including polling time. */
+ halt_ns = ktime_to_ns(cur) - ktime_to_ns(start);
+
+ /*
+ * Note, halt-polling is considered successful so long as the vCPU was
+ * never actually scheduled out, i.e. even if the wake event arrived
+ * after of the halt-polling loop itself, but before the full wait.
+ */
+ if (do_halt_poll)
+ update_halt_poll_stats(vcpu, start, poll_end, !waited);
+
+ if (halt_poll_allowed) {
+ /* Recompute the max halt poll time in case it changed. */
+ max_halt_poll_ns = kvm_vcpu_max_halt_poll_ns(vcpu);
+
+ if (!vcpu_valid_wakeup(vcpu)) {
+ shrink_halt_poll_ns(vcpu);
+ } else if (max_halt_poll_ns) {
+ if (halt_ns <= vcpu->halt_poll_ns)
+ ;
+ /* we had a long block, shrink polling */
+ else if (vcpu->halt_poll_ns &&
+ halt_ns > 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 < max_halt_poll_ns &&
+ halt_ns < max_halt_poll_ns)
+ grow_halt_poll_ns(vcpu);
+ } else {
+ vcpu->halt_poll_ns = 0;
+ }
+ }
+
+ trace_kvm_vcpu_wakeup(halt_ns, waited, vcpu_valid_wakeup(vcpu));
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_halt);
+
+bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu)
+{
+ if (__kvm_vcpu_wake_up(vcpu)) {
+ WRITE_ONCE(vcpu->ready, true);
+ ++vcpu->stat.generic.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;
+
+ me = get_cpu();
+ /*
+ * The only state change done outside the vcpu mutex is IN_GUEST_MODE
+ * to EXITING_GUEST_MODE. Therefore the moderately expensive "should
+ * kick" check does not need atomic operations if kvm_vcpu_kick is used
+ * within the vCPU thread itself.
+ */
+ if (vcpu == __this_cpu_read(kvm_running_vcpu)) {
+ if (vcpu->mode == IN_GUEST_MODE)
+ WRITE_ONCE(vcpu->mode, EXITING_GUEST_MODE);
+ goto out;
+ }
+
+ /*
+ * 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.
+ */
+ 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);
+ }
+out:
+ 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;
+}
+
+bool __weak kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu)
+{
+ 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;
+ unsigned long i;
+ int yielded = 0;
+ int try = 3;
+ int pass;
+
+ 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 (kvm_vcpu_is_blocking(vcpu) && !vcpu_dy_runnable(vcpu))
+ continue;
+ if (READ_ONCE(vcpu->preempted) && yield_to_kernel_mode &&
+ !kvm_arch_dy_has_pending_interrupt(vcpu) &&
+ !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 bool kvm_page_in_dirty_ring(struct kvm *kvm, unsigned long pgoff)
+{
+#ifdef CONFIG_HAVE_KVM_DIRTY_RING
+ return (pgoff >= KVM_DIRTY_LOG_PAGE_OFFSET) &&
+ (pgoff < KVM_DIRTY_LOG_PAGE_OFFSET +
+ kvm->dirty_ring_size / PAGE_SIZE);
+#else
+ return false;
+#endif
+}
+
+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 if (kvm_page_in_dirty_ring(vcpu->kvm, vmf->pgoff))
+ page = kvm_dirty_ring_get_page(
+ &vcpu->dirty_ring,
+ vmf->pgoff - KVM_DIRTY_LOG_PAGE_OFFSET);
+ 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)
+{
+ struct kvm_vcpu *vcpu = file->private_data;
+ unsigned long pages = vma_pages(vma);
+
+ if ((kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff) ||
+ kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff + pages - 1)) &&
+ ((vma->vm_flags & VM_EXEC) || !(vma->vm_flags & VM_SHARED)))
+ return -EINVAL;
+
+ 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 const 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);
+}
+
+#ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS
+static int vcpu_get_pid(void *data, u64 *val)
+{
+ struct kvm_vcpu *vcpu = (struct kvm_vcpu *) data;
+ *val = pid_nr(rcu_access_pointer(vcpu->pid));
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(vcpu_get_pid_fops, vcpu_get_pid, NULL, "%llu\n");
+
+static void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
+{
+ 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);
+ debugfs_create_file("pid", 0444, debugfs_dentry, vcpu,
+ &vcpu_get_pid_fops);
+
+ 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_IDS)
+ return -EINVAL;
+
+ mutex_lock(&kvm->lock);
+ if (kvm->created_vcpus >= kvm->max_vcpus) {
+ mutex_unlock(&kvm->lock);
+ return -EINVAL;
+ }
+
+ r = kvm_arch_vcpu_precreate(kvm, id);
+ if (r) {
+ mutex_unlock(&kvm->lock);
+ return r;
+ }
+
+ kvm->created_vcpus++;
+ mutex_unlock(&kvm->lock);
+
+ vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT);
+ if (!vcpu) {
+ r = -ENOMEM;
+ goto vcpu_decrement;
+ }
+
+ BUILD_BUG_ON(sizeof(struct kvm_run) > PAGE_SIZE);
+ page = alloc_page(GFP_KERNEL_ACCOUNT | __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;
+
+ if (kvm->dirty_ring_size) {
+ r = kvm_dirty_ring_alloc(&vcpu->dirty_ring,
+ id, kvm->dirty_ring_size);
+ if (r)
+ goto arch_vcpu_destroy;
+ }
+
+ 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);
+ r = xa_reserve(&kvm->vcpu_array, vcpu->vcpu_idx, GFP_KERNEL_ACCOUNT);
+ if (r)
+ goto unlock_vcpu_destroy;
+
+ /* Now it's all set up, let userspace reach it */
+ kvm_get_kvm(kvm);
+ r = create_vcpu_fd(vcpu);
+ if (r < 0)
+ goto kvm_put_xa_release;
+
+ if (KVM_BUG_ON(!!xa_store(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, 0), kvm)) {
+ r = -EINVAL;
+ goto kvm_put_xa_release;
+ }
+
+ /*
+ * Pairs with smp_rmb() in kvm_get_vcpu. Store the vcpu
+ * pointer 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;
+
+kvm_put_xa_release:
+ kvm_put_kvm_no_destroy(kvm);
+ xa_release(&kvm->vcpu_array, vcpu->vcpu_idx);
+unlock_vcpu_destroy:
+ mutex_unlock(&kvm->lock);
+ kvm_dirty_ring_free(&vcpu->dirty_ring);
+arch_vcpu_destroy:
+ 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 ssize_t kvm_vcpu_stats_read(struct file *file, char __user *user_buffer,
+ size_t size, loff_t *offset)
+{
+ struct kvm_vcpu *vcpu = file->private_data;
+
+ return kvm_stats_read(vcpu->stats_id, &kvm_vcpu_stats_header,
+ &kvm_vcpu_stats_desc[0], &vcpu->stat,
+ sizeof(vcpu->stat), user_buffer, size, offset);
+}
+
+static int kvm_vcpu_stats_release(struct inode *inode, struct file *file)
+{
+ struct kvm_vcpu *vcpu = file->private_data;
+
+ kvm_put_kvm(vcpu->kvm);
+ return 0;
+}
+
+static const struct file_operations kvm_vcpu_stats_fops = {
+ .read = kvm_vcpu_stats_read,
+ .release = kvm_vcpu_stats_release,
+ .llseek = noop_llseek,
+};
+
+static int kvm_vcpu_ioctl_get_stats_fd(struct kvm_vcpu *vcpu)
+{
+ int fd;
+ struct file *file;
+ char name[15 + ITOA_MAX_LEN + 1];
+
+ snprintf(name, sizeof(name), "kvm-vcpu-stats:%d", vcpu->vcpu_id);
+
+ fd = get_unused_fd_flags(O_CLOEXEC);
+ if (fd < 0)
+ return fd;
+
+ file = anon_inode_getfile(name, &kvm_vcpu_stats_fops, vcpu, O_RDONLY);
+ if (IS_ERR(file)) {
+ put_unused_fd(fd);
+ return PTR_ERR(file);
+ }
+
+ kvm_get_kvm(vcpu->kvm);
+
+ file->f_mode |= FMODE_PREAD;
+ fd_install(fd, file);
+
+ return fd;
+}
+
+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_dead)
+ 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;
+ }
+ case KVM_GET_STATS_FD: {
+ r = kvm_vcpu_ioctl_get_stats_fd(vcpu);
+ 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_dead)
+ 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_dead)
+ 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;
+ 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;
+ case KVM_CAP_DIRTY_LOG_RING:
+#ifdef CONFIG_HAVE_KVM_DIRTY_RING_TSO
+ return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn);
+#else
+ return 0;
+#endif
+ case KVM_CAP_DIRTY_LOG_RING_ACQ_REL:
+#ifdef CONFIG_HAVE_KVM_DIRTY_RING_ACQ_REL
+ return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn);
+#else
+ return 0;
+#endif
+ case KVM_CAP_BINARY_STATS_FD:
+ case KVM_CAP_SYSTEM_EVENT_DATA:
+ return 1;
+ default:
+ break;
+ }
+ return kvm_vm_ioctl_check_extension(kvm, arg);
+}
+
+static int kvm_vm_ioctl_enable_dirty_log_ring(struct kvm *kvm, u32 size)
+{
+ int r;
+
+ if (!KVM_DIRTY_LOG_PAGE_OFFSET)
+ return -EINVAL;
+
+ /* the size should be power of 2 */
+ if (!size || (size & (size - 1)))
+ return -EINVAL;
+
+ /* Should be bigger to keep the reserved entries, or a page */
+ if (size < kvm_dirty_ring_get_rsvd_entries() *
+ sizeof(struct kvm_dirty_gfn) || size < PAGE_SIZE)
+ return -EINVAL;
+
+ if (size > KVM_DIRTY_RING_MAX_ENTRIES *
+ sizeof(struct kvm_dirty_gfn))
+ return -E2BIG;
+
+ /* We only allow it to set once */
+ if (kvm->dirty_ring_size)
+ return -EINVAL;
+
+ mutex_lock(&kvm->lock);
+
+ if (kvm->created_vcpus) {
+ /* We don't allow to change this value after vcpu created */
+ r = -EINVAL;
+ } else {
+ kvm->dirty_ring_size = size;
+ r = 0;
+ }
+
+ mutex_unlock(&kvm->lock);
+ return r;
+}
+
+static int kvm_vm_ioctl_reset_dirty_pages(struct kvm *kvm)
+{
+ unsigned long i;
+ struct kvm_vcpu *vcpu;
+ int cleared = 0;
+
+ if (!kvm->dirty_ring_size)
+ return -EINVAL;
+
+ mutex_lock(&kvm->slots_lock);
+
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ cleared += kvm_dirty_ring_reset(vcpu->kvm, &vcpu->dirty_ring);
+
+ mutex_unlock(&kvm->slots_lock);
+
+ if (cleared)
+ kvm_flush_remote_tlbs(kvm);
+
+ return cleared;
+}
+
+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];
+
+ /*
+ * Ensure kvm->override_halt_poll_ns does not become visible
+ * before kvm->max_halt_poll_ns.
+ *
+ * Pairs with the smp_rmb() in kvm_vcpu_max_halt_poll_ns().
+ */
+ smp_wmb();
+ kvm->override_halt_poll_ns = true;
+
+ return 0;
+ }
+ case KVM_CAP_DIRTY_LOG_RING:
+ case KVM_CAP_DIRTY_LOG_RING_ACQ_REL:
+ if (!kvm_vm_ioctl_check_extension_generic(kvm, cap->cap))
+ return -EINVAL;
+
+ return kvm_vm_ioctl_enable_dirty_log_ring(kvm, cap->args[0]);
+ default:
+ return kvm_vm_ioctl_enable_cap(kvm, cap);
+ }
+}
+
+static ssize_t kvm_vm_stats_read(struct file *file, char __user *user_buffer,
+ size_t size, loff_t *offset)
+{
+ struct kvm *kvm = file->private_data;
+
+ return kvm_stats_read(kvm->stats_id, &kvm_vm_stats_header,
+ &kvm_vm_stats_desc[0], &kvm->stat,
+ sizeof(kvm->stat), user_buffer, size, offset);
+}
+
+static int kvm_vm_stats_release(struct inode *inode, struct file *file)
+{
+ struct kvm *kvm = file->private_data;
+
+ kvm_put_kvm(kvm);
+ return 0;
+}
+
+static const struct file_operations kvm_vm_stats_fops = {
+ .read = kvm_vm_stats_read,
+ .release = kvm_vm_stats_release,
+ .llseek = noop_llseek,
+};
+
+static int kvm_vm_ioctl_get_stats_fd(struct kvm *kvm)
+{
+ int fd;
+ struct file *file;
+
+ fd = get_unused_fd_flags(O_CLOEXEC);
+ if (fd < 0)
+ return fd;
+
+ file = anon_inode_getfile("kvm-vm-stats",
+ &kvm_vm_stats_fops, kvm, O_RDONLY);
+ if (IS_ERR(file)) {
+ put_unused_fd(fd);
+ return PTR_ERR(file);
+ }
+
+ kvm_get_kvm(kvm);
+
+ file->f_mode |= FMODE_PREAD;
+ fd_install(fd, file);
+
+ return fd;
+}
+
+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_dead)
+ 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;
+ case KVM_RESET_DIRTY_RINGS:
+ r = kvm_vm_ioctl_reset_dirty_pages(kvm);
+ break;
+ case KVM_GET_STATS_FD:
+ r = kvm_vm_ioctl_get_stats_fd(kvm);
+ 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_dead)
+ 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 const struct file_operations kvm_vm_fops = {
+ .release = kvm_vm_release,
+ .unlocked_ioctl = kvm_vm_ioctl,
+ .llseek = noop_llseek,
+ KVM_COMPAT(kvm_vm_compat_ioctl),
+};
+
+bool file_is_kvm(struct file *file)
+{
+ return file && file->f_op == &kvm_vm_fops;
+}
+EXPORT_SYMBOL_GPL(file_is_kvm);
+
+static int kvm_dev_ioctl_create_vm(unsigned long type)
+{
+ char fdname[ITOA_MAX_LEN + 1];
+ int r, fd;
+ struct kvm *kvm;
+ struct file *file;
+
+ fd = get_unused_fd_flags(O_CLOEXEC);
+ if (fd < 0)
+ return fd;
+
+ snprintf(fdname, sizeof(fdname), "%d", fd);
+
+ kvm = kvm_create_vm(type, fdname);
+ if (IS_ERR(kvm)) {
+ r = PTR_ERR(kvm);
+ goto put_fd;
+ }
+
+ file = anon_inode_getfile("kvm-vm", &kvm_vm_fops, kvm, O_RDWR);
+ if (IS_ERR(file)) {
+ 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).
+ */
+ kvm_uevent_notify_change(KVM_EVENT_CREATE_VM, kvm);
+
+ fd_install(fd, file);
+ return fd;
+
+put_kvm:
+ kvm_put_kvm(kvm);
+put_fd:
+ put_unused_fd(fd);
+ 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;
+}
+
+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;
+
+ lockdep_assert_held(&kvm->slots_lock);
+
+ 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)
+{
+ int ret;
+ 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. kvm_get_kvm_safe
+ * avoids the race between open and the removal of the debugfs directory.
+ */
+ if (!kvm_get_kvm_safe(stat_data->kvm))
+ return -ENOENT;
+
+ ret = simple_attr_open(inode, file, get,
+ kvm_stats_debugfs_mode(stat_data->desc) & 0222
+ ? set : NULL, fmt);
+ if (ret)
+ kvm_put_kvm(stat_data->kvm);
+
+ return ret;
+}
+
+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 = *(u64 *)((void *)(&kvm->stat) + offset);
+
+ return 0;
+}
+
+static int kvm_clear_stat_per_vm(struct kvm *kvm, size_t offset)
+{
+ *(u64 *)((void *)(&kvm->stat) + offset) = 0;
+
+ return 0;
+}
+
+static int kvm_get_stat_per_vcpu(struct kvm *kvm, size_t offset, u64 *val)
+{
+ unsigned long i;
+ struct kvm_vcpu *vcpu;
+
+ *val = 0;
+
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ *val += *(u64 *)((void *)(&vcpu->stat) + offset);
+
+ return 0;
+}
+
+static int kvm_clear_stat_per_vcpu(struct kvm *kvm, size_t offset)
+{
+ unsigned long i;
+ struct kvm_vcpu *vcpu;
+
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ *(u64 *)((void *)(&vcpu->stat) + 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->kind) {
+ case KVM_STAT_VM:
+ r = kvm_get_stat_per_vm(stat_data->kvm,
+ stat_data->desc->desc.offset, val);
+ break;
+ case KVM_STAT_VCPU:
+ r = kvm_get_stat_per_vcpu(stat_data->kvm,
+ stat_data->desc->desc.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->kind) {
+ case KVM_STAT_VM:
+ r = kvm_clear_stat_per_vm(stat_data->kvm,
+ stat_data->desc->desc.offset);
+ break;
+ case KVM_STAT_VCPU:
+ r = kvm_clear_stat_per_vcpu(stat_data->kvm,
+ stat_data->desc->desc.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");
+DEFINE_SIMPLE_ATTRIBUTE(vm_stat_readonly_fops, vm_stat_get, NULL, "%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");
+DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_readonly_fops, vcpu_stat_get, NULL, "%llu\n");
+
+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 (!IS_ERR(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)
+{
+ const struct file_operations *fops;
+ const struct _kvm_stats_desc *pdesc;
+ int i;
+
+ kvm_debugfs_dir = debugfs_create_dir("kvm", NULL);
+
+ for (i = 0; i < kvm_vm_stats_header.num_desc; ++i) {
+ pdesc = &kvm_vm_stats_desc[i];
+ if (kvm_stats_debugfs_mode(pdesc) & 0222)
+ fops = &vm_stat_fops;
+ else
+ fops = &vm_stat_readonly_fops;
+ debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc),
+ kvm_debugfs_dir,
+ (void *)(long)pdesc->desc.offset, fops);
+ }
+
+ for (i = 0; i < kvm_vcpu_stats_header.num_desc; ++i) {
+ pdesc = &kvm_vcpu_stats_desc[i];
+ if (kvm_stats_debugfs_mode(pdesc) & 0222)
+ fops = &vcpu_stat_fops;
+ else
+ fops = &vcpu_stat_readonly_fops;
+ debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc),
+ kvm_debugfs_dir,
+ (void *)(long)pdesc->desc.offset, fops);
+ }
+}
+
+static int kvm_suspend(void)
+{
+ if (kvm_usage_count)
+ hardware_disable_nolock(NULL);
+ return 0;
+}
+
+static void kvm_resume(void)
+{
+ if (kvm_usage_count) {
+ lockdep_assert_not_held(&kvm_count_lock);
+ 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->on_rq) {
+ 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;
+}
+
+#ifdef CONFIG_GUEST_PERF_EVENTS
+static unsigned int kvm_guest_state(void)
+{
+ struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
+ unsigned int state;
+
+ if (!kvm_arch_pmi_in_guest(vcpu))
+ return 0;
+
+ state = PERF_GUEST_ACTIVE;
+ if (!kvm_arch_vcpu_in_kernel(vcpu))
+ state |= PERF_GUEST_USER;
+
+ return state;
+}
+
+static unsigned long kvm_guest_get_ip(void)
+{
+ struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
+
+ /* Retrieving the IP must be guarded by a call to kvm_guest_state(). */
+ if (WARN_ON_ONCE(!kvm_arch_pmi_in_guest(vcpu)))
+ return 0;
+
+ return kvm_arch_vcpu_get_ip(vcpu);
+}
+
+static struct perf_guest_info_callbacks kvm_guest_cbs = {
+ .state = kvm_guest_state,
+ .get_ip = kvm_guest_get_ip,
+ .handle_intel_pt_intr = NULL,
+};
+
+void kvm_register_perf_callbacks(unsigned int (*pt_intr_handler)(void))
+{
+ kvm_guest_cbs.handle_intel_pt_intr = pt_intr_handler;
+ perf_register_guest_info_callbacks(&kvm_guest_cbs);
+}
+void kvm_unregister_perf_callbacks(void)
+{
+ perf_unregister_guest_info_callbacks(&kvm_guest_cbs);
+}
+#endif
+
+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),
+ offsetofend(struct kvm_vcpu, stats_id)
+ - offsetof(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;
+
+ 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 task_struct *parent;
+ 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)
+ goto out;
+
+ /* Wait to be woken up by the spawner before proceeding. */
+ kthread_parkme();
+
+ if (!kthread_should_stop())
+ err = thread_fn(kvm, data);
+
+out:
+ /*
+ * Move kthread back to its original cgroup to prevent it lingering in
+ * the cgroup of the VM process, after the latter finishes its
+ * execution.
+ *
+ * kthread_stop() waits on the 'exited' completion condition which is
+ * set in exit_mm(), via mm_release(), in do_exit(). However, the
+ * kthread is removed from the cgroup in the cgroup_exit() which is
+ * called after the exit_mm(). This causes the kthread_stop() to return
+ * before the kthread actually quits the cgroup.
+ */
+ rcu_read_lock();
+ parent = rcu_dereference(current->real_parent);
+ get_task_struct(parent);
+ rcu_read_unlock();
+ cgroup_attach_task_all(parent, current);
+ put_task_struct(parent);
+
+ 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/kvm_mm.h b/virt/kvm/kvm_mm.h
new file mode 100644
index 000000000..41da467d9
--- /dev/null
+++ b/virt/kvm/kvm_mm.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __KVM_MM_H__
+#define __KVM_MM_H__ 1
+
+/*
+ * Architectures can choose whether to use an rwlock or spinlock
+ * for the mmu_lock. These macros, for use in common code
+ * only, avoids using #ifdefs in places that must deal with
+ * multiple architectures.
+ */
+
+#ifdef KVM_HAVE_MMU_RWLOCK
+#define KVM_MMU_LOCK_INIT(kvm) rwlock_init(&(kvm)->mmu_lock)
+#define KVM_MMU_LOCK(kvm) write_lock(&(kvm)->mmu_lock)
+#define KVM_MMU_UNLOCK(kvm) write_unlock(&(kvm)->mmu_lock)
+#define KVM_MMU_READ_LOCK(kvm) read_lock(&(kvm)->mmu_lock)
+#define KVM_MMU_READ_UNLOCK(kvm) read_unlock(&(kvm)->mmu_lock)
+#else
+#define KVM_MMU_LOCK_INIT(kvm) spin_lock_init(&(kvm)->mmu_lock)
+#define KVM_MMU_LOCK(kvm) spin_lock(&(kvm)->mmu_lock)
+#define KVM_MMU_UNLOCK(kvm) spin_unlock(&(kvm)->mmu_lock)
+#define KVM_MMU_READ_LOCK(kvm) spin_lock(&(kvm)->mmu_lock)
+#define KVM_MMU_READ_UNLOCK(kvm) spin_unlock(&(kvm)->mmu_lock)
+#endif /* KVM_HAVE_MMU_RWLOCK */
+
+kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
+ bool write_fault, bool *writable);
+
+#ifdef CONFIG_HAVE_KVM_PFNCACHE
+void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm,
+ unsigned long start,
+ unsigned long end,
+ bool may_block);
+#else
+static inline void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm,
+ unsigned long start,
+ unsigned long end,
+ bool may_block)
+{
+}
+#endif /* HAVE_KVM_PFNCACHE */
+
+#endif /* __KVM_MM_H__ */
diff --git a/virt/kvm/pfncache.c b/virt/kvm/pfncache.c
new file mode 100644
index 000000000..7c248193c
--- /dev/null
+++ b/virt/kvm/pfncache.c
@@ -0,0 +1,422 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Kernel-based Virtual Machine driver for Linux
+ *
+ * This module enables kernel and guest-mode vCPU access to guest physical
+ * memory with suitable invalidation mechanisms.
+ *
+ * Copyright © 2021 Amazon.com, Inc. or its affiliates.
+ *
+ * Authors:
+ * David Woodhouse <dwmw2@infradead.org>
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/kvm.h>
+#include <linux/highmem.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+
+#include "kvm_mm.h"
+
+/*
+ * MMU notifier 'invalidate_range_start' hook.
+ */
+void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, unsigned long start,
+ unsigned long end, bool may_block)
+{
+ DECLARE_BITMAP(vcpu_bitmap, KVM_MAX_VCPUS);
+ struct gfn_to_pfn_cache *gpc;
+ bool evict_vcpus = false;
+
+ spin_lock(&kvm->gpc_lock);
+ list_for_each_entry(gpc, &kvm->gpc_list, list) {
+ write_lock_irq(&gpc->lock);
+
+ /* Only a single page so no need to care about length */
+ if (gpc->valid && !is_error_noslot_pfn(gpc->pfn) &&
+ gpc->uhva >= start && gpc->uhva < end) {
+ gpc->valid = false;
+
+ /*
+ * If a guest vCPU could be using the physical address,
+ * it needs to be forced out of guest mode.
+ */
+ if (gpc->usage & KVM_GUEST_USES_PFN) {
+ if (!evict_vcpus) {
+ evict_vcpus = true;
+ bitmap_zero(vcpu_bitmap, KVM_MAX_VCPUS);
+ }
+ __set_bit(gpc->vcpu->vcpu_idx, vcpu_bitmap);
+ }
+ }
+ write_unlock_irq(&gpc->lock);
+ }
+ spin_unlock(&kvm->gpc_lock);
+
+ if (evict_vcpus) {
+ /*
+ * KVM needs to ensure the vCPU is fully out of guest context
+ * before allowing the invalidation to continue.
+ */
+ unsigned int req = KVM_REQ_OUTSIDE_GUEST_MODE;
+ bool called;
+
+ /*
+ * If the OOM reaper is active, then all vCPUs should have
+ * been stopped already, so perform the request without
+ * KVM_REQUEST_WAIT and be sad if any needed to be IPI'd.
+ */
+ if (!may_block)
+ req &= ~KVM_REQUEST_WAIT;
+
+ called = kvm_make_vcpus_request_mask(kvm, req, vcpu_bitmap);
+
+ WARN_ON_ONCE(called && !may_block);
+ }
+}
+
+bool kvm_gfn_to_pfn_cache_check(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
+ gpa_t gpa, unsigned long len)
+{
+ struct kvm_memslots *slots = kvm_memslots(kvm);
+
+ if (!gpc->active)
+ return false;
+
+ if ((gpa & ~PAGE_MASK) + len > PAGE_SIZE)
+ return false;
+
+ if (gpc->gpa != gpa || gpc->generation != slots->generation ||
+ kvm_is_error_hva(gpc->uhva))
+ return false;
+
+ if (!gpc->valid)
+ return false;
+
+ return true;
+}
+EXPORT_SYMBOL_GPL(kvm_gfn_to_pfn_cache_check);
+
+static void gpc_unmap_khva(struct kvm *kvm, kvm_pfn_t pfn, void *khva)
+{
+ /* Unmap the old pfn/page if it was mapped before. */
+ if (!is_error_noslot_pfn(pfn) && khva) {
+ if (pfn_valid(pfn))
+ kunmap(pfn_to_page(pfn));
+#ifdef CONFIG_HAS_IOMEM
+ else
+ memunmap(khva);
+#endif
+ }
+}
+
+static inline bool mmu_notifier_retry_cache(struct kvm *kvm, unsigned long mmu_seq)
+{
+ /*
+ * mn_active_invalidate_count acts for all intents and purposes
+ * like mmu_invalidate_in_progress here; but the latter cannot
+ * be used here because the invalidation of caches in the
+ * mmu_notifier event occurs _before_ mmu_invalidate_in_progress
+ * is elevated.
+ *
+ * Note, it does not matter that mn_active_invalidate_count
+ * is not protected by gpc->lock. It is guaranteed to
+ * be elevated before the mmu_notifier acquires gpc->lock, and
+ * isn't dropped until after mmu_invalidate_seq is updated.
+ */
+ if (kvm->mn_active_invalidate_count)
+ return true;
+
+ /*
+ * Ensure mn_active_invalidate_count is read before
+ * mmu_invalidate_seq. This pairs with the smp_wmb() in
+ * mmu_notifier_invalidate_range_end() to guarantee either the
+ * old (non-zero) value of mn_active_invalidate_count or the
+ * new (incremented) value of mmu_invalidate_seq is observed.
+ */
+ smp_rmb();
+ return kvm->mmu_invalidate_seq != mmu_seq;
+}
+
+static kvm_pfn_t hva_to_pfn_retry(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
+{
+ /* Note, the new page offset may be different than the old! */
+ void *old_khva = gpc->khva - offset_in_page(gpc->khva);
+ kvm_pfn_t new_pfn = KVM_PFN_ERR_FAULT;
+ void *new_khva = NULL;
+ unsigned long mmu_seq;
+
+ lockdep_assert_held(&gpc->refresh_lock);
+
+ lockdep_assert_held_write(&gpc->lock);
+
+ /*
+ * Invalidate the cache prior to dropping gpc->lock, the gpa=>uhva
+ * assets have already been updated and so a concurrent check() from a
+ * different task may not fail the gpa/uhva/generation checks.
+ */
+ gpc->valid = false;
+
+ do {
+ mmu_seq = kvm->mmu_invalidate_seq;
+ smp_rmb();
+
+ write_unlock_irq(&gpc->lock);
+
+ /*
+ * If the previous iteration "failed" due to an mmu_notifier
+ * event, release the pfn and unmap the kernel virtual address
+ * from the previous attempt. Unmapping might sleep, so this
+ * needs to be done after dropping the lock. Opportunistically
+ * check for resched while the lock isn't held.
+ */
+ if (new_pfn != KVM_PFN_ERR_FAULT) {
+ /*
+ * Keep the mapping if the previous iteration reused
+ * the existing mapping and didn't create a new one.
+ */
+ if (new_khva != old_khva)
+ gpc_unmap_khva(kvm, new_pfn, new_khva);
+
+ kvm_release_pfn_clean(new_pfn);
+
+ cond_resched();
+ }
+
+ /* We always request a writeable mapping */
+ new_pfn = hva_to_pfn(gpc->uhva, false, NULL, true, NULL);
+ if (is_error_noslot_pfn(new_pfn))
+ goto out_error;
+
+ /*
+ * Obtain a new kernel mapping if KVM itself will access the
+ * pfn. Note, kmap() and memremap() can both sleep, so this
+ * too must be done outside of gpc->lock!
+ */
+ if (gpc->usage & KVM_HOST_USES_PFN) {
+ if (new_pfn == gpc->pfn) {
+ new_khva = old_khva;
+ } else if (pfn_valid(new_pfn)) {
+ new_khva = kmap(pfn_to_page(new_pfn));
+#ifdef CONFIG_HAS_IOMEM
+ } else {
+ new_khva = memremap(pfn_to_hpa(new_pfn), PAGE_SIZE, MEMREMAP_WB);
+#endif
+ }
+ if (!new_khva) {
+ kvm_release_pfn_clean(new_pfn);
+ goto out_error;
+ }
+ }
+
+ write_lock_irq(&gpc->lock);
+
+ /*
+ * Other tasks must wait for _this_ refresh to complete before
+ * attempting to refresh.
+ */
+ WARN_ON_ONCE(gpc->valid);
+ } while (mmu_notifier_retry_cache(kvm, mmu_seq));
+
+ gpc->valid = true;
+ gpc->pfn = new_pfn;
+ gpc->khva = new_khva + (gpc->gpa & ~PAGE_MASK);
+
+ /*
+ * Put the reference to the _new_ pfn. The pfn is now tracked by the
+ * cache and can be safely migrated, swapped, etc... as the cache will
+ * invalidate any mappings in response to relevant mmu_notifier events.
+ */
+ kvm_release_pfn_clean(new_pfn);
+
+ return 0;
+
+out_error:
+ write_lock_irq(&gpc->lock);
+
+ return -EFAULT;
+}
+
+int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
+ gpa_t gpa, unsigned long len)
+{
+ struct kvm_memslots *slots = kvm_memslots(kvm);
+ unsigned long page_offset = gpa & ~PAGE_MASK;
+ bool unmap_old = false;
+ unsigned long old_uhva;
+ kvm_pfn_t old_pfn;
+ void *old_khva;
+ int ret;
+
+ /*
+ * If must fit within a single page. The 'len' argument is
+ * only to enforce that.
+ */
+ if (page_offset + len > PAGE_SIZE)
+ return -EINVAL;
+
+ /*
+ * If another task is refreshing the cache, wait for it to complete.
+ * There is no guarantee that concurrent refreshes will see the same
+ * gpa, memslots generation, etc..., so they must be fully serialized.
+ */
+ mutex_lock(&gpc->refresh_lock);
+
+ write_lock_irq(&gpc->lock);
+
+ if (!gpc->active) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
+
+ old_pfn = gpc->pfn;
+ old_khva = gpc->khva - offset_in_page(gpc->khva);
+ old_uhva = gpc->uhva;
+
+ /* If the userspace HVA is invalid, refresh that first */
+ if (gpc->gpa != gpa || gpc->generation != slots->generation ||
+ kvm_is_error_hva(gpc->uhva)) {
+ gfn_t gfn = gpa_to_gfn(gpa);
+
+ gpc->gpa = gpa;
+ gpc->generation = slots->generation;
+ gpc->memslot = __gfn_to_memslot(slots, gfn);
+ gpc->uhva = gfn_to_hva_memslot(gpc->memslot, gfn);
+
+ if (kvm_is_error_hva(gpc->uhva)) {
+ ret = -EFAULT;
+ goto out;
+ }
+ }
+
+ /*
+ * If the userspace HVA changed or the PFN was already invalid,
+ * drop the lock and do the HVA to PFN lookup again.
+ */
+ if (!gpc->valid || old_uhva != gpc->uhva) {
+ ret = hva_to_pfn_retry(kvm, gpc);
+ } else {
+ /*
+ * If the HVA→PFN mapping was already valid, don't unmap it.
+ * But do update gpc->khva because the offset within the page
+ * may have changed.
+ */
+ gpc->khva = old_khva + page_offset;
+ old_pfn = KVM_PFN_ERR_FAULT;
+ old_khva = NULL;
+ ret = 0;
+ }
+
+ out:
+ /*
+ * Invalidate the cache and purge the pfn/khva if the refresh failed.
+ * Some/all of the uhva, gpa, and memslot generation info may still be
+ * valid, leave it as is.
+ */
+ if (ret) {
+ gpc->valid = false;
+ gpc->pfn = KVM_PFN_ERR_FAULT;
+ gpc->khva = NULL;
+ }
+
+ /* Detect a pfn change before dropping the lock! */
+ unmap_old = (old_pfn != gpc->pfn);
+
+out_unlock:
+ write_unlock_irq(&gpc->lock);
+
+ mutex_unlock(&gpc->refresh_lock);
+
+ if (unmap_old)
+ gpc_unmap_khva(kvm, old_pfn, old_khva);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(kvm_gfn_to_pfn_cache_refresh);
+
+void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
+{
+ void *old_khva;
+ kvm_pfn_t old_pfn;
+
+ mutex_lock(&gpc->refresh_lock);
+ write_lock_irq(&gpc->lock);
+
+ gpc->valid = false;
+
+ old_khva = gpc->khva - offset_in_page(gpc->khva);
+ old_pfn = gpc->pfn;
+
+ /*
+ * We can leave the GPA → uHVA map cache intact but the PFN
+ * lookup will need to be redone even for the same page.
+ */
+ gpc->khva = NULL;
+ gpc->pfn = KVM_PFN_ERR_FAULT;
+
+ write_unlock_irq(&gpc->lock);
+ mutex_unlock(&gpc->refresh_lock);
+
+ gpc_unmap_khva(kvm, old_pfn, old_khva);
+}
+EXPORT_SYMBOL_GPL(kvm_gfn_to_pfn_cache_unmap);
+
+void kvm_gpc_init(struct gfn_to_pfn_cache *gpc)
+{
+ rwlock_init(&gpc->lock);
+ mutex_init(&gpc->refresh_lock);
+}
+EXPORT_SYMBOL_GPL(kvm_gpc_init);
+
+int kvm_gpc_activate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
+ struct kvm_vcpu *vcpu, enum pfn_cache_usage usage,
+ gpa_t gpa, unsigned long len)
+{
+ WARN_ON_ONCE(!usage || (usage & KVM_GUEST_AND_HOST_USE_PFN) != usage);
+
+ if (!gpc->active) {
+ gpc->khva = NULL;
+ gpc->pfn = KVM_PFN_ERR_FAULT;
+ gpc->uhva = KVM_HVA_ERR_BAD;
+ gpc->vcpu = vcpu;
+ gpc->usage = usage;
+ gpc->valid = false;
+
+ spin_lock(&kvm->gpc_lock);
+ list_add(&gpc->list, &kvm->gpc_list);
+ spin_unlock(&kvm->gpc_lock);
+
+ /*
+ * Activate the cache after adding it to the list, a concurrent
+ * refresh must not establish a mapping until the cache is
+ * reachable by mmu_notifier events.
+ */
+ write_lock_irq(&gpc->lock);
+ gpc->active = true;
+ write_unlock_irq(&gpc->lock);
+ }
+ return kvm_gfn_to_pfn_cache_refresh(kvm, gpc, gpa, len);
+}
+EXPORT_SYMBOL_GPL(kvm_gpc_activate);
+
+void kvm_gpc_deactivate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
+{
+ if (gpc->active) {
+ /*
+ * Deactivate the cache before removing it from the list, KVM
+ * must stall mmu_notifier events until all users go away, i.e.
+ * until gpc->lock is dropped and refresh is guaranteed to fail.
+ */
+ write_lock_irq(&gpc->lock);
+ gpc->active = false;
+ write_unlock_irq(&gpc->lock);
+
+ spin_lock(&kvm->gpc_lock);
+ list_del(&gpc->list);
+ spin_unlock(&kvm->gpc_lock);
+
+ kvm_gfn_to_pfn_cache_unmap(kvm, gpc);
+ }
+}
+EXPORT_SYMBOL_GPL(kvm_gpc_deactivate);
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
new file mode 100644
index 000000000..365d30779
--- /dev/null
+++ b/virt/kvm/vfio.c
@@ -0,0 +1,402 @@
+// 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_file {
+ struct list_head node;
+ struct file *file;
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+ struct iommu_group *iommu_group;
+#endif
+};
+
+struct kvm_vfio {
+ struct list_head file_list;
+ struct mutex lock;
+ bool noncoherent;
+};
+
+static void kvm_vfio_file_set_kvm(struct file *file, struct kvm *kvm)
+{
+ void (*fn)(struct file *file, struct kvm *kvm);
+
+ fn = symbol_get(vfio_file_set_kvm);
+ if (!fn)
+ return;
+
+ fn(file, kvm);
+
+ symbol_put(vfio_file_set_kvm);
+}
+
+static bool kvm_vfio_file_enforced_coherent(struct file *file)
+{
+ bool (*fn)(struct file *file);
+ bool ret;
+
+ fn = symbol_get(vfio_file_enforced_coherent);
+ if (!fn)
+ return false;
+
+ ret = fn(file);
+
+ symbol_put(vfio_file_enforced_coherent);
+
+ return ret;
+}
+
+static bool kvm_vfio_file_is_group(struct file *file)
+{
+ bool (*fn)(struct file *file);
+ bool ret;
+
+ fn = symbol_get(vfio_file_is_group);
+ if (!fn)
+ return false;
+
+ ret = fn(file);
+
+ symbol_put(vfio_file_is_group);
+
+ return ret;
+}
+
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+static struct iommu_group *kvm_vfio_file_iommu_group(struct file *file)
+{
+ struct iommu_group *(*fn)(struct file *file);
+ struct iommu_group *ret;
+
+ fn = symbol_get(vfio_file_iommu_group);
+ if (!fn)
+ return NULL;
+
+ ret = fn(file);
+
+ symbol_put(vfio_file_iommu_group);
+
+ return ret;
+}
+
+static void kvm_spapr_tce_release_vfio_group(struct kvm *kvm,
+ struct kvm_vfio_file *kvf)
+{
+ if (WARN_ON_ONCE(!kvf->iommu_group))
+ return;
+
+ kvm_spapr_tce_release_iommu_group(kvm, kvf->iommu_group);
+ iommu_group_put(kvf->iommu_group);
+ kvf->iommu_group = NULL;
+}
+#endif
+
+/*
+ * Groups/devices can use the same or different IOMMU domains. If the same
+ * then adding a new group/device may change the coherency of groups/devices
+ * we've previously been told about. We don't want to care about any of
+ * that so we retest each group/device 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_file *kvf;
+
+ mutex_lock(&kv->lock);
+
+ list_for_each_entry(kvf, &kv->file_list, node) {
+ if (!kvm_vfio_file_enforced_coherent(kvf->file)) {
+ 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_file_add(struct kvm_device *dev, unsigned int fd)
+{
+ struct kvm_vfio *kv = dev->private;
+ struct kvm_vfio_file *kvf;
+ struct file *filp;
+ int ret;
+
+ filp = fget(fd);
+ if (!filp)
+ return -EBADF;
+
+ /* Ensure the FD is a vfio group FD.*/
+ if (!kvm_vfio_file_is_group(filp)) {
+ ret = -EINVAL;
+ goto err_fput;
+ }
+
+ mutex_lock(&kv->lock);
+
+ list_for_each_entry(kvf, &kv->file_list, node) {
+ if (kvf->file == filp) {
+ ret = -EEXIST;
+ goto err_unlock;
+ }
+ }
+
+ kvf = kzalloc(sizeof(*kvf), GFP_KERNEL_ACCOUNT);
+ if (!kvf) {
+ ret = -ENOMEM;
+ goto err_unlock;
+ }
+
+ kvf->file = filp;
+ list_add_tail(&kvf->node, &kv->file_list);
+
+ kvm_arch_start_assignment(dev->kvm);
+ kvm_vfio_file_set_kvm(kvf->file, dev->kvm);
+
+ mutex_unlock(&kv->lock);
+
+ kvm_vfio_update_coherency(dev);
+
+ return 0;
+err_unlock:
+ mutex_unlock(&kv->lock);
+err_fput:
+ fput(filp);
+ return ret;
+}
+
+static int kvm_vfio_file_del(struct kvm_device *dev, unsigned int fd)
+{
+ struct kvm_vfio *kv = dev->private;
+ struct kvm_vfio_file *kvf;
+ struct fd f;
+ int ret;
+
+ f = fdget(fd);
+ if (!f.file)
+ return -EBADF;
+
+ ret = -ENOENT;
+
+ mutex_lock(&kv->lock);
+
+ list_for_each_entry(kvf, &kv->file_list, node) {
+ if (kvf->file != f.file)
+ continue;
+
+ list_del(&kvf->node);
+ kvm_arch_end_assignment(dev->kvm);
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+ kvm_spapr_tce_release_vfio_group(dev->kvm, kvf);
+#endif
+ kvm_vfio_file_set_kvm(kvf->file, NULL);
+ fput(kvf->file);
+ kfree(kvf);
+ ret = 0;
+ break;
+ }
+
+ mutex_unlock(&kv->lock);
+
+ fdput(f);
+
+ kvm_vfio_update_coherency(dev);
+
+ return ret;
+}
+
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+static int kvm_vfio_file_set_spapr_tce(struct kvm_device *dev,
+ void __user *arg)
+{
+ struct kvm_vfio_spapr_tce param;
+ struct kvm_vfio *kv = dev->private;
+ struct kvm_vfio_file *kvf;
+ struct fd f;
+ int ret;
+
+ if (copy_from_user(&param, arg, sizeof(struct kvm_vfio_spapr_tce)))
+ return -EFAULT;
+
+ f = fdget(param.groupfd);
+ if (!f.file)
+ return -EBADF;
+
+ ret = -ENOENT;
+
+ mutex_lock(&kv->lock);
+
+ list_for_each_entry(kvf, &kv->file_list, node) {
+ if (kvf->file != f.file)
+ continue;
+
+ if (!kvf->iommu_group) {
+ kvf->iommu_group = kvm_vfio_file_iommu_group(kvf->file);
+ if (WARN_ON_ONCE(!kvf->iommu_group)) {
+ ret = -EIO;
+ goto err_fdput;
+ }
+ }
+
+ ret = kvm_spapr_tce_attach_iommu_group(dev->kvm, param.tablefd,
+ kvf->iommu_group);
+ break;
+ }
+
+err_fdput:
+ mutex_unlock(&kv->lock);
+ fdput(f);
+ return ret;
+}
+#endif
+
+static int kvm_vfio_set_file(struct kvm_device *dev, long attr,
+ void __user *arg)
+{
+ int32_t __user *argp = arg;
+ int32_t fd;
+
+ switch (attr) {
+ case KVM_DEV_VFIO_GROUP_ADD:
+ if (get_user(fd, argp))
+ return -EFAULT;
+ return kvm_vfio_file_add(dev, fd);
+
+ case KVM_DEV_VFIO_GROUP_DEL:
+ if (get_user(fd, argp))
+ return -EFAULT;
+ return kvm_vfio_file_del(dev, fd);
+
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+ case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE:
+ return kvm_vfio_file_set_spapr_tce(dev, arg);
+#endif
+ }
+
+ 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_file(dev, attr->attr,
+ u64_to_user_ptr(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_release(struct kvm_device *dev)
+{
+ struct kvm_vfio *kv = dev->private;
+ struct kvm_vfio_file *kvf, *tmp;
+
+ list_for_each_entry_safe(kvf, tmp, &kv->file_list, node) {
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+ kvm_spapr_tce_release_vfio_group(dev->kvm, kvf);
+#endif
+ kvm_vfio_file_set_kvm(kvf->file, NULL);
+ fput(kvf->file);
+ list_del(&kvf->node);
+ kfree(kvf);
+ kvm_arch_end_assignment(dev->kvm);
+ }
+
+ kvm_vfio_update_coherency(dev);
+
+ kfree(kv);
+ kfree(dev); /* alloc by kvm_ioctl_create_device, free by .release */
+}
+
+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,
+ .release = kvm_vfio_release,
+ .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->file_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