[RFC,v12,15/33] KVM: Add transparent hugepage support for dedicated guest memory

Commit Message

Sean Christopherson Sept. 14, 2023, 1:55 a.m. UTC

TODO: writeme

Signed-off-by: Sean Christopherson <[e-mail]>
---
 include/uapi/linux/kvm.h |  2 ++
 virt/kvm/guest_mem.c     | 54 ++++++++++++++++++++++++++++++++++++----
 2 files changed, 51 insertions(+), 5 deletions(-)

Patch

diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index b6f90a273e2e..2df18796fd8e 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -2314,6 +2314,8 @@  struct kvm_memory_attributes {
 
 #define KVM_CREATE_GUEST_MEMFD	_IOWR(KVMIO,  0xd4, struct kvm_create_guest_memfd)
 
+#define KVM_GUEST_MEMFD_ALLOW_HUGEPAGE		(1ULL << 0)
+
 struct kvm_create_guest_memfd {
 	__u64 size;
 	__u64 flags;
diff --git a/virt/kvm/guest_mem.c b/virt/kvm/guest_mem.c
index 0dd3f836cf9c..a819367434e9 100644
--- a/virt/kvm/guest_mem.c
+++ b/virt/kvm/guest_mem.c
@@ -17,15 +17,48 @@  struct kvm_gmem {
 	struct list_head entry;
 };
 
-static struct folio *kvm_gmem_get_folio(struct file *file, pgoff_t index)
+static struct folio *kvm_gmem_get_huge_folio(struct inode *inode, pgoff_t index)
 {
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	unsigned long huge_index = round_down(index, HPAGE_PMD_NR);
+	unsigned long flags = (unsigned long)inode->i_private;
+	struct address_space *mapping  = inode->i_mapping;
+	gfp_t gfp = mapping_gfp_mask(mapping);
 	struct folio *folio;
 
-	/* TODO: Support huge pages. */
-	folio = filemap_grab_folio(file->f_mapping, index);
-	if (IS_ERR_OR_NULL(folio))
+	if (!(flags & KVM_GUEST_MEMFD_ALLOW_HUGEPAGE))
 		return NULL;
 
+	if (filemap_range_has_page(mapping, huge_index << PAGE_SHIFT,
+				   (huge_index + HPAGE_PMD_NR - 1) << PAGE_SHIFT))
+		return NULL;
+
+	folio = filemap_alloc_folio(gfp, HPAGE_PMD_ORDER);
+	if (!folio)
+		return NULL;
+
+	if (filemap_add_folio(mapping, folio, huge_index, gfp)) {
+		folio_put(folio);
+		return NULL;
+	}
+
+	return folio;
+#else
+	return NULL;
+#endif
+}
+
+static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index)
+{
+	struct folio *folio;
+
+	folio = kvm_gmem_get_huge_folio(inode, index);
+	if (!folio) {
+		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
@@ -323,7 +356,8 @@  static const struct inode_operations kvm_gmem_iops = {
 	.setattr	= kvm_gmem_setattr,
 };
 
-static int __kvm_gmem_create(struct kvm *kvm, loff_t size, struct vfsmount *mnt)
+static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags,
+			     struct vfsmount *mnt)
 {
 	const char *anon_name = "[kvm-gmem]";
 	const struct qstr qname = QSTR_INIT(anon_name, strlen(anon_name));
@@ -346,6 +380,7 @@  static int __kvm_gmem_create(struct kvm *kvm, loff_t size, struct vfsmount *mnt)
 	inode->i_mode |= S_IFREG;
 	inode->i_size = size;
 	mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
+	mapping_set_large_folios(inode->i_mapping);
 	mapping_set_unmovable(inode->i_mapping);
 	/* Unmovable mappings are supposed to be marked unevictable as well. */
 	WARN_ON_ONCE(!mapping_unevictable(inode->i_mapping));
@@ -396,6 +431,12 @@  static bool kvm_gmem_is_valid_size(loff_t size, u64 flags)
 	if (size < 0 || !PAGE_ALIGNED(size))
 		return false;
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	if ((flags & KVM_GUEST_MEMFD_ALLOW_HUGEPAGE) &&
+	    !IS_ALIGNED(size, HPAGE_PMD_SIZE))
+		return false;
+#endif
+
 	return true;
 }
 
@@ -405,6 +446,9 @@  int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args)
 	u64 flags = args->flags;
 	u64 valid_flags = 0;
 
+	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		valid_flags |= KVM_GUEST_MEMFD_ALLOW_HUGEPAGE;
+
 	if (flags & ~valid_flags)
 		return -EINVAL;