diff mbox series

[RFC,v11,13/29] KVM: Add transparent hugepage support for dedicated guest memory

Message ID 20230718234512.1690985-14-seanjc@google.com (mailing list archive)
State Handled Elsewhere
Delegated to: Paul Moore
Headers show
Series KVM: guest_memfd() and per-page attributes | expand

Commit Message

Sean Christopherson July 18, 2023, 11:44 p.m. UTC 
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 include/uapi/linux/kvm.h |  2 ++
 virt/kvm/guest_mem.c     | 52 ++++++++++++++++++++++++++++++++++++----
 2 files changed, 50 insertions(+), 4 deletions(-)

Comments

Paolo Bonzini July 21, 2023, 3:07 p.m. UTC | #1 
On 7/19/23 01:44, Sean Christopherson wrote:
>   
> @@ -413,6 +454,9 @@ 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;
> +

I think it should be always allowed.  The outcome would just be "never 
have a hugepage" if thp is not enabled in the kernel.

Paolo
Sean Christopherson July 21, 2023, 5:13 p.m. UTC | #2 
On Fri, Jul 21, 2023, Paolo Bonzini wrote:
> On 7/19/23 01:44, Sean Christopherson wrote:
> > @@ -413,6 +454,9 @@ 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;
> > +
> 
> I think it should be always allowed.  The outcome would just be "never have
> a hugepage" if thp is not enabled in the kernel.

I don't have a strong preference.  My thinking was that userspace would probably
rather have an explicit error, as opposed to silently running with a misconfigured
setup.
Paolo Bonzini Sept. 6, 2023, 10:10 p.m. UTC | #3 
On Fri, Jul 21, 2023 at 7:13 PM Sean Christopherson <seanjc@google.com> wrote:
> On Fri, Jul 21, 2023, Paolo Bonzini wrote:
> > On 7/19/23 01:44, Sean Christopherson wrote:
> > > @@ -413,6 +454,9 @@ 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;
> > > +
> >
> > I think it should be always allowed.  The outcome would just be "never have
> > a hugepage" if thp is not enabled in the kernel.
>
> I don't have a strong preference.  My thinking was that userspace would probably
> rather have an explicit error, as opposed to silently running with a misconfigured
> setup.

Considering that is how madvise(MADV_HUGEPAGE) behaves, your patch is
good. I disagree but consistency is better.

Paolo
diff mbox series

Patch

diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 9b344fc98598..17b12ee8b70e 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -2290,6 +2290,8 @@  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 1b705fd63fa8..384671a55b41 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 (!(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 (!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
@@ -332,7 +365,8 @@  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));
@@ -355,6 +389,7 @@  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_unevictable(inode->i_mapping);
 	mapping_set_unmovable(inode->i_mapping);
 
@@ -404,6 +439,12 @@  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;
 }
 
@@ -413,6 +454,9 @@  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;