:Parameters: struct kvm_userspace_memory_region2 (in)
:Returns: 0 on success, -1 on error
+KVM_SET_USER_MEMORY_REGION2 is an extension to KVM_SET_USER_MEMORY_REGION that
+allows mapping guest_memfd memory into a guest. All fields shared with
+KVM_SET_USER_MEMORY_REGION identically. Userspace can set KVM_MEM_GUEST_MEMFD
+in flags to have KVM bind the memory region to a given guest_memfd range of
+[guest_memfd_offset, guest_memfd_offset + memory_size]. The target guest_memfd
+must point at a file created via KVM_CREATE_GUEST_MEMFD on the current VM, and
+the target range must not be bound to any other memory region. All standard
+bounds checks apply (use common sense).
+
::
struct kvm_userspace_memory_region2 {
__u64 guest_phys_addr;
__u64 memory_size; /* bytes */
__u64 userspace_addr; /* start of the userspace allocated memory */
- __u64 pad[16];
+ __u64 guest_memfd_offset;
+ __u32 guest_memfd;
+ __u32 pad1;
+ __u64 pad2[14];
};
-See KVM_SET_USER_MEMORY_REGION.
+A KVM_MEM_GUEST_MEMFD region _must_ have a valid guest_memfd (private memory) and
+userspace_addr (shared memory). However, "valid" for userspace_addr simply
+means that the address itself must be a legal userspace address. The backing
+mapping for userspace_addr is not required to be valid/populated at the time of
+KVM_SET_USER_MEMORY_REGION2, e.g. shared memory can be lazily mapped/allocated
+on-demand.
+
+When mapping a gfn into the guest, KVM selects shared vs. private, i.e consumes
+userspace_addr vs. guest_memfd, based on the gfn's KVM_MEMORY_ATTRIBUTE_PRIVATE
+state. At VM creation time, all memory is shared, i.e. the PRIVATE attribute
+is '0' for all gfns. Userspace can control whether memory is shared/private by
+toggling KVM_MEMORY_ATTRIBUTE_PRIVATE via KVM_SET_MEMORY_ATTRIBUTES as needed.
4.141 KVM_SET_MEMORY_ATTRIBUTES
-------------------------------
The "flags" field is reserved for future extensions and must be '0'.
+4.142 KVM_CREATE_GUEST_MEMFD
+----------------------------
+
+:Capability: KVM_CAP_GUEST_MEMFD
+:Architectures: none
+:Type: vm ioctl
+:Parameters: struct kvm_create_guest_memfd(in)
+:Returns: 0 on success, <0 on error
+
+KVM_CREATE_GUEST_MEMFD creates an anonymous file and returns a file descriptor
+that refers to it. guest_memfd files are roughly analogous to files created
+via memfd_create(), e.g. guest_memfd files live in RAM, have volatile storage,
+and are automatically released when the last reference is dropped. Unlike
+"regular" memfd_create() files, guest_memfd files are bound to their owning
+virtual machine (see below), cannot be mapped, read, or written by userspace,
+and cannot be resized (guest_memfd files do however support PUNCH_HOLE).
+
+::
+
+ struct kvm_create_guest_memfd {
+ __u64 size;
+ __u64 flags;
+ __u64 reserved[6];
+ };
+
+Conceptually, the inode backing a guest_memfd file represents physical memory,
+i.e. is coupled to the virtual machine as a thing, not to a "struct kvm". The
+file itself, which is bound to a "struct kvm", is that instance's view of the
+underlying memory, e.g. effectively provides the translation of guest addresses
+to host memory. This allows for use cases where multiple KVM structures are
+used to manage a single virtual machine, e.g. when performing intrahost
+migration of a virtual machine.
+
+KVM currently only supports mapping guest_memfd via KVM_SET_USER_MEMORY_REGION2,
+and more specifically via the guest_memfd and guest_memfd_offset fields in
+"struct kvm_userspace_memory_region2", where guest_memfd_offset is the offset
+into the guest_memfd instance. For a given guest_memfd file, there can be at
+most one mapping per page, i.e. binding multiple memory regions to a single
+guest_memfd range is not allowed (any number of memory regions can be bound to
+a single guest_memfd file, but the bound ranges must not overlap).
+
+See KVM_SET_USER_MEMORY_REGION2 for additional details.
+
5. The kvm_run structure
========================
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/backing-dev.h>
+#include <linux/falloc.h>
+#include <linux/kvm_host.h>
+#include <linux/pagemap.h>
+#include <linux/anon_inodes.h>
+
+#include "kvm_mm.h"
+
+struct kvm_gmem {
+ struct kvm *kvm;
+ struct xarray bindings;
+ struct list_head entry;
+};
+
+static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index)
+{
+ struct folio *folio;
+
+ /* TODO: Support huge pages. */
+ folio = filemap_grab_folio(inode->i_mapping, index);
+ if (IS_ERR_OR_NULL(folio))
+ return NULL;
+
+ /*
+ * Use the up-to-date flag to track whether or not the memory has been
+ * zeroed before being handed off to the guest. There is no backing
+ * storage for the memory, so the folio will remain up-to-date until
+ * it's removed.
+ *
+ * TODO: Skip clearing pages when trusted firmware will do it when
+ * assigning memory to the guest.
+ */
+ if (!folio_test_uptodate(folio)) {
+ unsigned long nr_pages = folio_nr_pages(folio);
+ unsigned long i;
+
+ for (i = 0; i < nr_pages; i++)
+ clear_highpage(folio_page(folio, i));
+
+ folio_mark_uptodate(folio);
+ }
+
+ /*
+ * Ignore accessed, referenced, and dirty flags. The memory is
+ * unevictable and there is no storage to write back to.
+ */
+ return folio;
+}
+
+static void kvm_gmem_invalidate_begin(struct kvm_gmem *gmem, pgoff_t start,
+ pgoff_t end)
+{
+ bool flush = false, found_memslot = false;
+ struct kvm_memory_slot *slot;
+ struct kvm *kvm = gmem->kvm;
+ unsigned long index;
+
+ xa_for_each_range(&gmem->bindings, index, slot, start, end - 1) {
+ pgoff_t pgoff = slot->gmem.pgoff;
+
+ struct kvm_gfn_range gfn_range = {
+ .start = slot->base_gfn + max(pgoff, start) - pgoff,
+ .end = slot->base_gfn + min(pgoff + slot->npages, end) - pgoff,
+ .slot = slot,
+ .may_block = true,
+ };
+
+ if (!found_memslot) {
+ found_memslot = true;
+
+ KVM_MMU_LOCK(kvm);
+ kvm_mmu_invalidate_begin(kvm);
+ }
+
+ flush |= kvm_mmu_unmap_gfn_range(kvm, &gfn_range);
+ }
+
+ if (flush)
+ kvm_flush_remote_tlbs(kvm);
+
+ if (found_memslot)
+ KVM_MMU_UNLOCK(kvm);
+}
+
+static void kvm_gmem_invalidate_end(struct kvm_gmem *gmem, pgoff_t start,
+ pgoff_t end)
+{
+ struct kvm *kvm = gmem->kvm;
+
+ if (xa_find(&gmem->bindings, &start, end - 1, XA_PRESENT)) {
+ KVM_MMU_LOCK(kvm);
+ kvm_mmu_invalidate_end(kvm);
+ KVM_MMU_UNLOCK(kvm);
+ }
+}
+
+static long kvm_gmem_punch_hole(struct inode *inode, loff_t offset, loff_t len)
+{
+ struct list_head *gmem_list = &inode->i_mapping->private_list;
+ pgoff_t start = offset >> PAGE_SHIFT;
+ pgoff_t end = (offset + len) >> PAGE_SHIFT;
+ struct kvm_gmem *gmem;
+
+ /*
+ * Bindings must be stable across invalidation to ensure the start+end
+ * are balanced.
+ */
+ filemap_invalidate_lock(inode->i_mapping);
+
+ list_for_each_entry(gmem, gmem_list, entry)
+ kvm_gmem_invalidate_begin(gmem, start, end);
+
+ truncate_inode_pages_range(inode->i_mapping, offset, offset + len - 1);
+
+ list_for_each_entry(gmem, gmem_list, entry)
+ kvm_gmem_invalidate_end(gmem, start, end);
+
+ filemap_invalidate_unlock(inode->i_mapping);
+
+ return 0;
+}
+
+static long kvm_gmem_allocate(struct inode *inode, loff_t offset, loff_t len)
+{
+ struct address_space *mapping = inode->i_mapping;
+ pgoff_t start, index, end;
+ int r;
+
+ /* Dedicated guest is immutable by default. */
+ if (offset + len > i_size_read(inode))
+ return -EINVAL;
+
+ filemap_invalidate_lock_shared(mapping);
+
+ start = offset >> PAGE_SHIFT;
+ end = (offset + len) >> PAGE_SHIFT;
+
+ r = 0;
+ for (index = start; index < end; ) {
+ struct folio *folio;
+
+ if (signal_pending(current)) {
+ r = -EINTR;
+ break;
+ }
+
+ folio = kvm_gmem_get_folio(inode, index);
+ if (!folio) {
+ r = -ENOMEM;
+ break;
+ }
+
+ index = folio_next_index(folio);
+
+ folio_unlock(folio);
+ folio_put(folio);
+
+ /* 64-bit only, wrapping the index should be impossible. */
+ if (WARN_ON_ONCE(!index))
+ break;
+
+ cond_resched();
+ }
+
+ filemap_invalidate_unlock_shared(mapping);
+
+ return r;
+}
+
+static long kvm_gmem_fallocate(struct file *file, int mode, loff_t offset,
+ loff_t len)
+{
+ int ret;
+
+ if (!(mode & FALLOC_FL_KEEP_SIZE))
+ return -EOPNOTSUPP;
+
+ if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+ return -EOPNOTSUPP;
+
+ if (!PAGE_ALIGNED(offset) || !PAGE_ALIGNED(len))
+ return -EINVAL;
+
+ if (mode & FALLOC_FL_PUNCH_HOLE)
+ ret = kvm_gmem_punch_hole(file_inode(file), offset, len);
+ else
+ ret = kvm_gmem_allocate(file_inode(file), offset, len);
+
+ if (!ret)
+ file_modified(file);
+ return ret;
+}
+
+static int kvm_gmem_release(struct inode *inode, struct file *file)
+{
+ struct kvm_gmem *gmem = file->private_data;
+ struct kvm_memory_slot *slot;
+ struct kvm *kvm = gmem->kvm;
+ unsigned long index;
+
+ /*
+ * Prevent concurrent attempts to *unbind* a memslot. This is the last
+ * reference to the file and thus no new bindings can be created, but
+ * dereferencing the slot for existing bindings needs to be protected
+ * against memslot updates, specifically so that unbind doesn't race
+ * and free the memslot (kvm_gmem_get_file() will return NULL).
+ */
+ mutex_lock(&kvm->slots_lock);
+
+ filemap_invalidate_lock(inode->i_mapping);
+
+ xa_for_each(&gmem->bindings, index, slot)
+ rcu_assign_pointer(slot->gmem.file, NULL);
+
+ synchronize_rcu();
+
+ /*
+ * All in-flight operations are gone and new bindings can be created.
+ * Zap all SPTEs pointed at by this file. Do not free the backing
+ * memory, as its lifetime is associated with the inode, not the file.
+ */
+ kvm_gmem_invalidate_begin(gmem, 0, -1ul);
+ kvm_gmem_invalidate_end(gmem, 0, -1ul);
+
+ list_del(&gmem->entry);
+
+ filemap_invalidate_unlock(inode->i_mapping);
+
+ mutex_unlock(&kvm->slots_lock);
+
+ xa_destroy(&gmem->bindings);
+ kfree(gmem);
+
+ kvm_put_kvm(kvm);
+
+ return 0;
+}
+
+static struct file *kvm_gmem_get_file(struct kvm_memory_slot *slot)
+{
+ struct file *file;
+
+ rcu_read_lock();
+
+ file = rcu_dereference(slot->gmem.file);
+ if (file && !get_file_rcu(file))
+ file = NULL;
+
+ rcu_read_unlock();
+
+ return file;
+}
+
+static struct file_operations kvm_gmem_fops = {
+ .open = generic_file_open,
+ .release = kvm_gmem_release,
+ .fallocate = kvm_gmem_fallocate,
+};
+
+void kvm_gmem_init(struct module *module)
+{
+ kvm_gmem_fops.owner = module;
+}
+
+static int kvm_gmem_migrate_folio(struct address_space *mapping,
+ struct folio *dst, struct folio *src,
+ enum migrate_mode mode)
+{
+ WARN_ON_ONCE(1);
+ return -EINVAL;
+}
+
+static int kvm_gmem_error_page(struct address_space *mapping, struct page *page)
+{
+ struct list_head *gmem_list = &mapping->private_list;
+ struct kvm_gmem *gmem;
+ pgoff_t start, end;
+
+ filemap_invalidate_lock_shared(mapping);
+
+ start = page->index;
+ end = start + thp_nr_pages(page);
+
+ list_for_each_entry(gmem, gmem_list, entry)
+ kvm_gmem_invalidate_begin(gmem, start, end);
+
+ /*
+ * Do not truncate the range, what action is taken in response to the
+ * error is userspace's decision (assuming the architecture supports
+ * gracefully handling memory errors). If/when the guest attempts to
+ * access a poisoned page, kvm_gmem_get_pfn() will return -EHWPOISON,
+ * at which point KVM can either terminate the VM or propagate the
+ * error to userspace.
+ */
+
+ list_for_each_entry(gmem, gmem_list, entry)
+ kvm_gmem_invalidate_end(gmem, start, end);
+
+ filemap_invalidate_unlock_shared(mapping);
+
+ return MF_DELAYED;
+}
+
+static const struct address_space_operations kvm_gmem_aops = {
+ .dirty_folio = noop_dirty_folio,
+#ifdef CONFIG_MIGRATION
+ .migrate_folio = kvm_gmem_migrate_folio,
+#endif
+ .error_remove_page = kvm_gmem_error_page,
+};
+
+static int kvm_gmem_getattr(struct mnt_idmap *idmap, const struct path *path,
+ struct kstat *stat, u32 request_mask,
+ unsigned int query_flags)
+{
+ struct inode *inode = path->dentry->d_inode;
+
+ generic_fillattr(idmap, request_mask, inode, stat);
+ return 0;
+}
+
+static int kvm_gmem_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+ struct iattr *attr)
+{
+ return -EINVAL;
+}
+static const struct inode_operations kvm_gmem_iops = {
+ .getattr = kvm_gmem_getattr,
+ .setattr = kvm_gmem_setattr,
+};
+
+static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags)
+{
+ const char *anon_name = "[kvm-gmem]";
+ struct kvm_gmem *gmem;
+ struct inode *inode;
+ struct file *file;
+ int fd, err;
+
+ fd = get_unused_fd_flags(0);
+ if (fd < 0)
+ return fd;
+
+ gmem = kzalloc(sizeof(*gmem), GFP_KERNEL);
+ if (!gmem) {
+ err = -ENOMEM;
+ goto err_fd;
+ }
+
+ file = anon_inode_create_getfile(anon_name, &kvm_gmem_fops, gmem,
+ O_RDWR, NULL);
+ if (IS_ERR(file)) {
+ err = PTR_ERR(file);
+ goto err_gmem;
+ }
+
+ file->f_flags |= O_LARGEFILE;
+
+ inode = file->f_inode;
+ WARN_ON(file->f_mapping != inode->i_mapping);
+
+ inode->i_private = (void *)(unsigned long)flags;
+ inode->i_op = &kvm_gmem_iops;
+ inode->i_mapping->a_ops = &kvm_gmem_aops;
+ inode->i_mode |= S_IFREG;
+ inode->i_size = size;
+ mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
+ mapping_set_unmovable(inode->i_mapping);
+ /* Unmovable mappings are supposed to be marked unevictable as well. */
+ WARN_ON_ONCE(!mapping_unevictable(inode->i_mapping));
+
+ kvm_get_kvm(kvm);
+ gmem->kvm = kvm;
+ xa_init(&gmem->bindings);
+ list_add(&gmem->entry, &inode->i_mapping->private_list);
+
+ fd_install(fd, file);
+ return fd;
+
+err_gmem:
+ kfree(gmem);
+err_fd:
+ put_unused_fd(fd);
+ return err;
+}
+
+int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args)
+{
+ loff_t size = args->size;
+ u64 flags = args->flags;
+ u64 valid_flags = 0;
+
+ if (flags & ~valid_flags)
+ return -EINVAL;
+
+ if (size <= 0 || !PAGE_ALIGNED(size))
+ return -EINVAL;
+
+ return __kvm_gmem_create(kvm, size, flags);
+}
+
+int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot,
+ unsigned int fd, loff_t offset)
+{
+ loff_t size = slot->npages << PAGE_SHIFT;
+ unsigned long start, end;
+ struct kvm_gmem *gmem;
+ struct inode *inode;
+ struct file *file;
+ int r = -EINVAL;
+
+ BUILD_BUG_ON(sizeof(gfn_t) != sizeof(slot->gmem.pgoff));
+
+ file = fget(fd);
+ if (!file)
+ return -EBADF;
+
+ if (file->f_op != &kvm_gmem_fops)
+ goto err;
+
+ gmem = file->private_data;
+ if (gmem->kvm != kvm)
+ goto err;
+
+ inode = file_inode(file);
+
+ if (offset < 0 || !PAGE_ALIGNED(offset) ||
+ offset + size > i_size_read(inode))
+ goto err;
+
+ filemap_invalidate_lock(inode->i_mapping);
+
+ start = offset >> PAGE_SHIFT;
+ end = start + slot->npages;
+
+ if (!xa_empty(&gmem->bindings) &&
+ xa_find(&gmem->bindings, &start, end - 1, XA_PRESENT)) {
+ filemap_invalidate_unlock(inode->i_mapping);
+ goto err;
+ }
+
+ /*
+ * No synchronize_rcu() needed, any in-flight readers are guaranteed to
+ * be see either a NULL file or this new file, no need for them to go
+ * away.
+ */
+ rcu_assign_pointer(slot->gmem.file, file);
+ slot->gmem.pgoff = start;
+
+ xa_store_range(&gmem->bindings, start, end - 1, slot, GFP_KERNEL);
+ filemap_invalidate_unlock(inode->i_mapping);
+
+ /*
+ * Drop the reference to the file, even on success. The file pins KVM,
+ * not the other way 'round. Active bindings are invalidated if the
+ * file is closed before memslots are destroyed.
+ */
+ r = 0;
+err:
+ fput(file);
+ return r;
+}
+
+void kvm_gmem_unbind(struct kvm_memory_slot *slot)
+{
+ unsigned long start = slot->gmem.pgoff;
+ unsigned long end = start + slot->npages;
+ struct kvm_gmem *gmem;
+ struct file *file;
+
+ /*
+ * Nothing to do if the underlying file was already closed (or is being
+ * closed right now), kvm_gmem_release() invalidates all bindings.
+ */
+ file = kvm_gmem_get_file(slot);
+ if (!file)
+ return;
+
+ gmem = file->private_data;
+
+ filemap_invalidate_lock(file->f_mapping);
+ xa_store_range(&gmem->bindings, start, end - 1, NULL, GFP_KERNEL);
+ rcu_assign_pointer(slot->gmem.file, NULL);
+ synchronize_rcu();
+ filemap_invalidate_unlock(file->f_mapping);
+
+ fput(file);
+}
+
+int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
+ gfn_t gfn, kvm_pfn_t *pfn, int *max_order)
+{
+ pgoff_t index = gfn - slot->base_gfn + slot->gmem.pgoff;
+ struct kvm_gmem *gmem;
+ struct folio *folio;
+ struct page *page;
+ struct file *file;
+ int r;
+
+ file = kvm_gmem_get_file(slot);
+ if (!file)
+ return -EFAULT;
+
+ gmem = file->private_data;
+
+ if (WARN_ON_ONCE(xa_load(&gmem->bindings, index) != slot)) {
+ r = -EIO;
+ goto out_fput;
+ }
+
+ folio = kvm_gmem_get_folio(file_inode(file), index);
+ if (!folio) {
+ r = -ENOMEM;
+ goto out_fput;
+ }
+
+ if (folio_test_hwpoison(folio)) {
+ r = -EHWPOISON;
+ goto out_unlock;
+ }
+
+ page = folio_file_page(folio, index);
+
+ *pfn = page_to_pfn(page);
+ if (max_order)
+ *max_order = 0;
+
+ r = 0;
+
+out_unlock:
+ folio_unlock(folio);
+out_fput:
+ fput(file);
+
+ return r;
+}
+EXPORT_SYMBOL_GPL(kvm_gmem_get_pfn);
}
}
-static bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
+bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
{
kvm_mmu_invalidate_range_add(kvm, range->start, range->end);
return kvm_unmap_gfn_range(kvm, range);
/* 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)
{
+ if (slot->flags & KVM_MEM_GUEST_MEMFD)
+ kvm_gmem_unbind(slot);
+
kvm_destroy_dirty_bitmap(slot);
kvm_arch_free_memslot(kvm, slot);
#define KVM_SET_USER_MEMORY_REGION_V1_FLAGS \
(KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_READONLY)
-static int check_memory_region_flags(const struct kvm_userspace_memory_region2 *mem)
+static int check_memory_region_flags(struct kvm *kvm,
+ const struct kvm_userspace_memory_region2 *mem)
{
u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
+ if (kvm_arch_has_private_mem(kvm))
+ valid_flags |= KVM_MEM_GUEST_MEMFD;
+
+ /* Dirty logging private memory is not currently supported. */
+ if (mem->flags & KVM_MEM_GUEST_MEMFD)
+ valid_flags &= ~KVM_MEM_LOG_DIRTY_PAGES;
+
#ifdef __KVM_HAVE_READONLY_MEM
valid_flags |= KVM_MEM_READONLY;
#endif
int as_id, id;
int r;
- r = check_memory_region_flags(mem);
+ r = check_memory_region_flags(kvm, mem);
if (r)
return r;
!access_ok((void __user *)(unsigned long)mem->userspace_addr,
mem->memory_size))
return -EINVAL;
+ if (mem->flags & KVM_MEM_GUEST_MEMFD &&
+ (mem->guest_memfd_offset & (PAGE_SIZE - 1) ||
+ mem->guest_memfd_offset + mem->memory_size < mem->guest_memfd_offset))
+ 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)
if ((kvm->nr_memslot_pages + npages) < kvm->nr_memslot_pages)
return -EINVAL;
} else { /* Modify an existing slot. */
+ /* Private memslots are immutable, they can only be deleted. */
+ if (mem->flags & KVM_MEM_GUEST_MEMFD)
+ return -EINVAL;
if ((mem->userspace_addr != old->userspace_addr) ||
(npages != old->npages) ||
((mem->flags ^ old->flags) & KVM_MEM_READONLY))
new->npages = npages;
new->flags = mem->flags;
new->userspace_addr = mem->userspace_addr;
+ if (mem->flags & KVM_MEM_GUEST_MEMFD) {
+ r = kvm_gmem_bind(kvm, new, mem->guest_memfd, mem->guest_memfd_offset);
+ if (r)
+ goto out;
+ }
r = kvm_set_memslot(kvm, old, new, change);
if (r)
- kfree(new);
+ goto out_unbind;
+
+ return 0;
+
+out_unbind:
+ if (mem->flags & KVM_MEM_GUEST_MEMFD)
+ kvm_gmem_unbind(new);
+out:
+ kfree(new);
return r;
}
EXPORT_SYMBOL_GPL(__kvm_set_memory_region);
static u64 kvm_supported_mem_attributes(struct kvm *kvm)
{
- if (!kvm)
+ if (!kvm || kvm_arch_has_private_mem(kvm))
return KVM_MEMORY_ATTRIBUTE_PRIVATE;
return 0;
#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
case KVM_CAP_MEMORY_ATTRIBUTES:
return kvm_supported_mem_attributes(kvm);
+#endif
+#ifdef CONFIG_KVM_PRIVATE_MEM
+ case KVM_CAP_GUEST_MEMFD:
+ return !kvm || kvm_arch_has_private_mem(kvm);
#endif
default:
break;
case KVM_GET_STATS_FD:
r = kvm_vm_ioctl_get_stats_fd(kvm);
break;
+#ifdef CONFIG_KVM_PRIVATE_MEM
+ case KVM_CREATE_GUEST_MEMFD: {
+ struct kvm_create_guest_memfd guest_memfd;
+
+ r = -EFAULT;
+ if (copy_from_user(&guest_memfd, argp, sizeof(guest_memfd)))
+ goto out;
+
+ r = kvm_gmem_create(kvm, &guest_memfd);
+ break;
+ }
+#endif
default:
r = kvm_arch_vm_ioctl(filp, ioctl, arg);
}
if (WARN_ON_ONCE(r))
goto err_vfio;
+ kvm_gmem_init(module);
+
/*
* Registration _must_ be the very last thing done, as this exposes
* /dev/kvm to userspace, i.e. all infrastructure must be setup!
projects / users / hch / dma-mapping.git / commitdiff