Add support for mmap() and fault() for guest_memfd backed memory
in the host for VMs that support in-place conversion between
shared and private. To that end, this patch adds the ability to
check whether the VM type supports in-place conversion, and only
allows mapping its memory if that's the case.
Also add the KVM capability KVM_CAP_GMEM_SHARED_MEM, which
indicates that the VM supports shared memory in guest_memfd, or
that the host can create VMs that support shared memory.
Supporting shared memory implies that memory can be mapped when
shared with the host.
This is controlled by the KVM_GMEM_SHARED_MEM configuration
option.
Signed-off-by: Fuad Tabba <tabba@xxxxxxxxxx>
---
include/linux/kvm_host.h | 11 ++++
include/uapi/linux/kvm.h | 1 +
virt/kvm/guest_memfd.c | 105 +++++++++++++++++++++++++++++++++++++++
virt/kvm/kvm_main.c | 4 ++
4 files changed, 121 insertions(+)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 7788e3625f6d..2d025b8ee20e 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -728,6 +728,17 @@ static inline bool kvm_arch_has_private_mem(struct kvm *kvm)
}
#endif
+/*
+ * Arch code must define kvm_arch_gmem_supports_shared_mem if support for
+ * private memory is enabled and it supports in-place shared/private conversion.
+ */
+#if !defined(kvm_arch_gmem_supports_shared_mem) && !IS_ENABLED(CONFIG_KVM_PRIVATE_MEM)
+static inline bool kvm_arch_gmem_supports_shared_mem(struct kvm *kvm)
+{
+ return false;
+}
+#endif
+
#ifndef kvm_arch_has_readonly_mem
static inline bool kvm_arch_has_readonly_mem(struct kvm *kvm)
{
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 45e6d8fca9b9..117937a895da 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -929,6 +929,7 @@ struct kvm_enable_cap {
#define KVM_CAP_PRE_FAULT_MEMORY 236
#define KVM_CAP_X86_APIC_BUS_CYCLES_NS 237
#define KVM_CAP_X86_GUEST_MODE 238
+#define KVM_CAP_GMEM_SHARED_MEM 239
struct kvm_irq_routing_irqchip {
__u32 irqchip;
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index b2aa6bf24d3a..4291956b51ae 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -312,7 +312,112 @@ static pgoff_t kvm_gmem_get_index(struct kvm_memory_slot *slot, gfn_t gfn)
return gfn - slot->base_gfn + slot->gmem.pgoff;
}
+#ifdef CONFIG_KVM_GMEM_SHARED_MEM
+static bool kvm_gmem_offset_is_shared(struct file *file, pgoff_t index)
+{
+ struct kvm_gmem *gmem = file->private_data;
+
+ /* For now, VMs that support shared memory share all their memory. */
+ return kvm_arch_gmem_supports_shared_mem(gmem->kvm);
+}
+
+static vm_fault_t kvm_gmem_fault(struct vm_fault *vmf)
+{
+ struct inode *inode = file_inode(vmf->vma->vm_file);
+ struct folio *folio;
+ vm_fault_t ret = VM_FAULT_LOCKED;
+
+ filemap_invalidate_lock_shared(inode->i_mapping);
+
+ folio = kvm_gmem_get_folio(inode, vmf->pgoff);
+ if (IS_ERR(folio)) {
+ switch (PTR_ERR(folio)) {
+ case -EAGAIN:
+ ret = VM_FAULT_RETRY;
+ break;
+ case -ENOMEM:
+ ret = VM_FAULT_OOM;
+ break;
+ default:
+ ret = VM_FAULT_SIGBUS;
+ break;
+ }
+ goto out_filemap;
+ }
+
+ if (folio_test_hwpoison(folio)) {
+ ret = VM_FAULT_HWPOISON;
+ goto out_folio;
+ }
+
+ /* Must be called with folio lock held, i.e., after kvm_gmem_get_folio() */
+ if (!kvm_gmem_offset_is_shared(vmf->vma->vm_file, vmf->pgoff)) {
+ ret = VM_FAULT_SIGBUS;
+ goto out_folio;
+ }
+
+ /*
+ * Only private folios are marked as "guestmem" so far, and we never
+ * expect private folios at this point.
+ */
+ if (WARN_ON_ONCE(folio_test_guestmem(folio))) {
+ ret = VM_FAULT_SIGBUS;
+ goto out_folio;
+ }
+
+ /* No support for huge pages. */
+ if (WARN_ON_ONCE(folio_test_large(folio))) {
+ ret = VM_FAULT_SIGBUS;
+ goto out_folio;
+ }
+
+ if (!folio_test_uptodate(folio)) {
+ clear_highpage(folio_page(folio, 0));
+ kvm_gmem_mark_prepared(folio);
+ }
+
+ vmf->page = folio_file_page(folio, vmf->pgoff);
+
+out_folio:
+ if (ret != VM_FAULT_LOCKED) {
+ folio_unlock(folio);
+ folio_put(folio);
+ }
+
+out_filemap:
+ filemap_invalidate_unlock_shared(inode->i_mapping);
+
+ return ret;
+}
+
+static const struct vm_operations_struct kvm_gmem_vm_ops = {
+ .fault = kvm_gmem_fault,
+};
+
+static int kvm_gmem_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ struct kvm_gmem *gmem = file->private_data;
+
+ if (!kvm_arch_gmem_supports_shared_mem(gmem->kvm))
+ return -ENODEV;
+
+ if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) !=
+ (VM_SHARED | VM_MAYSHARE)) {
+ return -EINVAL;
+ }
+
+ file_accessed(file);
+ vm_flags_set(vma, VM_DONTDUMP);
+ vma->vm_ops = &kvm_gmem_vm_ops;
+
+ return 0;
+}
+#else
+#define kvm_gmem_mmap NULL
+#endif /* CONFIG_KVM_GMEM_SHARED_MEM */
+
static struct file_operations kvm_gmem_fops = {
+ .mmap = kvm_gmem_mmap,
.open = generic_file_open,
.release = kvm_gmem_release,
.fallocate = kvm_gmem_fallocate,
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index ba0327e2d0d3..38f0f402ea46 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -4830,6 +4830,10 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
#ifdef CONFIG_KVM_PRIVATE_MEM
case KVM_CAP_GUEST_MEMFD:
return !kvm || kvm_arch_has_private_mem(kvm);
+#endif
+#ifdef CONFIG_KVM_GMEM_SHARED_MEM
+ case KVM_CAP_GMEM_SHARED_MEM:
+ return !kvm || kvm_arch_gmem_supports_shared_mem(kvm);
#endif
default:
break;
--
2.48.1.711.g2feabab25a-goog
