[RFC PATCH 07/14] KVM: guest_memfd: Update exports when pages are allocated

[Fred Griffoul <griffoul@gmail.com>]

From: Fred Griffoul <fgriffo@amazon.co.uk>

An export maps only the pages that have memory when it looks them up,
and a device cannot fault in the others, so guest_memfd must call
update() when a page gets memory.

Lookups treat a folio that was never zeroed as a hole. Zero folios in
one helper, under the invalidate lock, from the host fault, KVM's
get_pfn() and fallocate(), which did not zero at all, and update the
exports for each folio zeroed. Mark zeroed folios dirty: lookups hold no
reference, and memory-failure handling evicts clean folios that nothing
references.

In PFN mode, update the block that get_pfn() reports when it fills a
hole, since the provider may back all of it.

Assisted-by: Claude:claude-opus-5-5
Signed-off-by: Fred Griffoul <fgriffo@amazon.co.uk>
---
 include/linux/guest_memfd.h | 26 ++++++------
 virt/kvm/guest_memfd.c      | 85 +++++++++++++++++++++++++++++++------
 2 files changed, 85 insertions(+), 26 deletions(-)

diff --git a/include/linux/guest_memfd.h b/include/linux/guest_memfd.h
index 937693ae9573..f8e89723dd68 100644
--- a/include/linux/guest_memfd.h
+++ b/include/linux/guest_memfd.h
@@ -90,13 +90,14 @@ static inline int kvm_gmem_revoke(struct inode *inode, pgoff_t start, size_t nr_
  * nor fault them.  It attaches to the file, looks up the frame behind each
  * shared page without taking a reference, and guest_memfd calls its update()
  * whenever what a lookup returns for a range may have changed: conversions,
- * punch holes, memory failure and a provider's kvm_gmem_revoke().  update()
- * makes the consumer's mappings of the range match what a lookup returns now:
- * a frame, or a hole for a private page or a page without a frame.  It may be
- * called for pages that did not change, and for ranges that do not follow the
- * blocks that lookups report: the consumer may then remap whole blocks, also
- * outside the range, e.g. to merge them into larger mappings.  A consumer that
- * can fault may instead only remove its mappings of the range.
+ * punch holes, memory failure, a provider's kvm_gmem_revoke(), fallocate() and
+ * pages getting their first frame.  update() makes the consumer's mappings of
+ * the range match what a lookup returns now: a frame, or a hole for a private
+ * page or a page without a frame.  It may be called for pages that did not
+ * change, and for ranges that do not follow the blocks that lookups report:
+ * the consumer may then remap whole blocks, also outside the range, e.g. to
+ * merge them into larger mappings.  A consumer that can fault may instead only
+ * remove its mappings of the range.
  *
  * Until update() returns, the frames it replaces stay valid, so a consumer
  * may switch each mapping to its new target in one step; once it returns,
@@ -105,11 +106,12 @@ static inline int kvm_gmem_revoke(struct inode *inode, pgoff_t start, size_t nr_
  * beforehand.
  *
  * guest_memfd calls update() with its invalidate lock held, exclusive when it
- * takes frames away or pages convert and shared on memory failure, possibly
- * with a folio of the file locked; so update() may only call
- * kvm_gmem_export_lookup_pfn().  Under the shared lock, updates may run at the
- * same time, also for overlapping ranges.  The consumer holds a lock across a
- * lookup and the mapping it installs, which update() also takes.  Lock order:
+ * takes frames away or pages convert, and shared when pages only gain frames
+ * and on memory failure, possibly with a folio of the file locked; so update()
+ * may only call kvm_gmem_export_lookup_pfn().  Under the shared lock, updates
+ * may run at the same time, also for overlapping ranges.  The consumer holds a
+ * lock across a lookup and the mapping it installs, which update() also takes.
+ * Lock order:
  *
  *   PFN mode provider lock (across kvm_gmem_revoke())
  *     guest_memfd invalidate lock
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index 1c5826c5384e..42bb5f263e23 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -286,7 +286,8 @@ static bool kvm_gmem_range_has_attributes(struct inode *inode,
  * There is no backing storage for the memory, so the folio will remain
  * up-to-date until it's removed.
  *
- * Ignore accessed, referenced, and dirty flags.  The memory is
+ * Ignore accessed and referenced flags; the dirty flag only keeps a zeroed
+ * folio in the page cache, see kvm_gmem_folio_zero().  The memory is
  * unevictable and there is no storage to write back to.
  */
 static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index)
@@ -430,7 +431,8 @@ static void kvm_gmem_invalidate_end(struct inode *inode, pgoff_t start,
 
 /*
  * What a lookup returns for [start, end) may have changed: exclusive lock when
- * frames were taken away or pages converted, at least shared on memory failure.
+ * frames were taken away or pages converted, at least shared when pages only
+ * gained frames and on memory failure.
  */
 static void kvm_gmem_update_exports(struct inode *inode, pgoff_t start,
 				    pgoff_t end)
@@ -590,6 +592,64 @@ int kvm_gmem_revoke(struct inode *inode, pgoff_t start, size_t nr_pages,
 }
 EXPORT_SYMBOL_GPL(kvm_gmem_revoke);
 
+/*
+ * Zero a folio on its first use.  Lookups find it from then on, with no
+ * reference held, so mark it dirty: memory-failure handling drops clean
+ * folios that nothing references from the page cache (mapping_evict_folio()).
+ * Called with the folio locked.  Returns true if the folio was zeroed.
+ */
+static bool kvm_gmem_folio_zero(struct folio *folio)
+{
+	if (folio_test_uptodate(folio))
+		return false;
+
+	folio_zero_range(folio, 0, folio_size(folio));
+	folio_mark_uptodate(folio);
+	folio_mark_dirty(folio);
+	return true;
+}
+
+/* Zero a folio on its first use, and tell the exports.  Under the lock. */
+static void kvm_gmem_folio_clear(struct inode *inode, struct folio *folio)
+{
+	if (kvm_gmem_folio_zero(folio))
+		kvm_gmem_update_exports(inode, folio->index, folio_next_index(folio));
+}
+
+/*
+ * get_pfn() in PFN mode, which may back a hole: then tell the exports about
+ * the whole block that get_pfn() reports, as the provider may have backed all
+ * of it.  Called with the invalidate lock held.
+ */
+static int kvm_gmem_pfn_get(struct inode *inode, pgoff_t index,
+			    kvm_pfn_t *pfn, int *max_order, u32 *attrs)
+{
+	pgoff_t npages = i_size_read(inode) >> PAGE_SHIFT;
+	struct gmem_inode *gi = GMEM_I(inode);
+	bool hole = false;
+	unsigned long raw;
+	pgoff_t first;
+	int order, r;
+	size_t nr;
+
+	if (!list_empty(&gi->exports))
+		hole = gi->provider_ops->lookup_pfn_range(gi->provider, index,
+							  &raw, &nr) == -ENOENT;
+
+	r = gmem_provider_get_pfn(gi, index, pfn, &order, attrs);
+	if (r)
+		return r;
+
+	if (hole) {
+		first = round_down(index, 1UL << order);
+		kvm_gmem_update_exports(inode, first,
+					min(first + (1UL << order), npages));
+	}
+	if (max_order)
+		*max_order = order;
+	return 0;
+}
+
 static long kvm_gmem_allocate(struct inode *inode, loff_t offset, loff_t len)
 {
 	struct address_space *mapping = inode->i_mapping;
@@ -619,7 +679,7 @@ static long kvm_gmem_allocate(struct inode *inode, loff_t offset, loff_t len)
 				break;
 			}
 
-			r = gmem_provider_get_pfn(gi, index, &pfn, &max_order, NULL);
+			r = kvm_gmem_pfn_get(inode, index, &pfn, &max_order, NULL);
 			if (r)
 				break;
 
@@ -647,6 +707,8 @@ static long kvm_gmem_allocate(struct inode *inode, loff_t offset, loff_t len)
 
 		index = folio_next_index(folio);
 
+		/* Zeroed now, so that a device can map it before first use. */
+		kvm_gmem_folio_clear(inode, folio);
 		folio_unlock(folio);
 		folio_put(folio);
 
@@ -819,7 +881,7 @@ static vm_fault_t kvm_gmem_pfn_fault(struct vm_fault *vmf)
 	u32 attrs;
 	int r;
 
-	r = gmem_provider_get_pfn(GMEM_I(inode), vmf->pgoff, &pfn, NULL, &attrs);
+	r = kvm_gmem_pfn_get(inode, vmf->pgoff, &pfn, NULL, &attrs);
 	if (r)
 		return vmf_error(r);
 
@@ -873,6 +935,8 @@ static vm_fault_t kvm_gmem_fault_user_mapping(struct vm_fault *vmf)
 		folio = kvm_gmem_get_folio(inode, vmf->pgoff);
 		if (IS_ERR(folio))
 			r = PTR_ERR(folio);
+		else if (!folio_test_large(folio))
+			kvm_gmem_folio_clear(inode, folio);
 	}
 	filemap_invalidate_unlock_shared(inode->i_mapping);
 
@@ -891,11 +955,6 @@ static vm_fault_t kvm_gmem_fault_user_mapping(struct vm_fault *vmf)
 		goto out_folio;
 	}
 
-	if (!folio_test_uptodate(folio)) {
-		clear_highpage(folio_page(folio, 0));
-		folio_mark_uptodate(folio);
-	}
-
 	vmf->page = folio_file_page(folio, vmf->pgoff);
 
 out_folio:
@@ -1887,7 +1946,8 @@ static struct folio *__kvm_gmem_get_pfn(struct file *file,
 	}
 
 	if (kvm_gmem_is_pfn_mode(gi)) {
-		r = gmem_provider_get_pfn(gi, index, pfn, max_order, attrs);
+		r = kvm_gmem_pfn_get(file_inode(file), index, pfn, max_order,
+				     attrs);
 		if (r)
 			return ERR_PTR(r);
 		return NULL;
@@ -1903,10 +1963,7 @@ static struct folio *__kvm_gmem_get_pfn(struct file *file,
 		return ERR_PTR(-EHWPOISON);
 	}
 
-	if (!folio_test_uptodate(folio)) {
-		clear_highpage(folio_page(folio, 0));
-		folio_mark_uptodate(folio);
-	}
+	kvm_gmem_folio_clear(file_inode(file), folio);
 
 	*pfn = folio_file_pfn(folio, index);
 	if (max_order)
-- 
2.47.3