[PATCH 03/18] hugetlb_vmemmap: Leave pages partially HVOed upon restore failure

[James Houghton]

Right now it is assumed that the restore routine in vmemmap_remap_free()
will not fail; that is, if we fail to fully optimize a folio, it is
assumed that restoring the folio to its pre-HVO state is guaranteed to
succeed.

Although vmemmap restoration may never fail in practice, properly handle
such failure cases now. This will leave folios in a partially HVOed
state. In a follow-up patch, failure certainly becomes possible.

In the event we end up with partially-HVOed folios, make sure to:
  1. Leave the HVO page flag in place.
  2. Free any unused vmemmap pages.

Always pass the vmemmap_tail page to the restore routine to avoid
leaking the non-optimized vmemmap pages for a partially HVOed page.

Signed-off-by: James Houghton <jthoughton@xxxxxxxxxx>
---
 mm/hugetlb_vmemmap.c | 49 ++++++++++++++++++++++++++++++++++----------
 1 file changed, 38 insertions(+), 11 deletions(-)

diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 8d4e8ee51fdd..5fee01bf5b34 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -236,12 +236,15 @@ static void vmemmap_restore_pte(pte_t *pte, unsigned long addr,
 {
 	struct page *src = pte_page(ptep_get(pte)), *dst;
 
+	if (WARN_ON_ONCE(!walk->vmemmap_tail))
+		return;
+
 	/*
-	 * When rolling back vmemmap_remap_free(), keep the copied head page
+	 * When restoring a partially-HVOed page, keep the copied head page
 	 * mapping and restore only PTEs currently pointing at the shared tail
 	 * page.
 	 */
-	if (walk->vmemmap_tail && walk->vmemmap_tail != src)
+	if (walk->vmemmap_tail != src)
 		return;
 
 	VM_WARN_ON_ONCE(PageHead((const struct page *)addr));
@@ -277,6 +280,7 @@ static int vmemmap_remap_split(unsigned long start, unsigned long end)
 	return vmemmap_remap_range(start, end, &walk);
 }
 
+static const int VMEMMAP_REMAP_INCOMPLETE = 1;
 /**
  * vmemmap_remap_free - remap the vmemmap virtual address range [@start, @end)
  *			to use @vmemmap_head/tail, then free vmemmap which
@@ -291,7 +295,8 @@ static int vmemmap_remap_split(unsigned long start, unsigned long end)
  *		responsibility to free pages.
  * @flags:	modifications to vmemmap_remap_walk flags
  *
- * Return: %0 on success, negative error code otherwise.
+ * Return: %0 on success, VMEMMAP_REMAP_INCOMPLETE if the page is incompletely
+ *         optimized, negative error code otherwise.
  */
 static int vmemmap_remap_free(unsigned long start, unsigned long end,
 			      struct page *vmemmap_head,
@@ -326,7 +331,8 @@ static int vmemmap_remap_free(unsigned long start, unsigned long end,
 		.flags		= 0,
 	};
 
-	vmemmap_remap_range(start, end, &walk);
+	if (vmemmap_remap_range(start, end, &walk))
+		return VMEMMAP_REMAP_INCOMPLETE;
 
 	return ret;
 }
@@ -385,6 +391,8 @@ static struct page *vmemmap_get_tail(unsigned int order, struct zone *zone)
  * vmemmap_remap_alloc - remap the vmemmap virtual address range [@start, end)
  *			 to the page which is from the @vmemmap_pages
  *			 respectively.
+ * @h:		the hstate for the folio whose vmemmap is getting remapped
+ * @folio:	the folio whose vmemmap is getting remapped
  * @start:	start address of the vmemmap virtual address range that we want
  *		to remap.
  * @end:	end address of the vmemmap virtual address range that we want to
@@ -393,20 +401,35 @@ static struct page *vmemmap_get_tail(unsigned int order, struct zone *zone)
  *
  * Return: %0 on success, negative error code otherwise.
  */
-static int vmemmap_remap_alloc(unsigned long start, unsigned long end,
+static int vmemmap_remap_alloc(const struct hstate *h, struct folio *folio,
+			       unsigned long start, unsigned long end,
 			       unsigned long flags)
 {
 	LIST_HEAD(vmemmap_pages);
-	struct vmemmap_remap_walk walk = {
+	struct vmemmap_remap_walk walk;
+	struct page *vmemmap_tail;
+	int ret;
+
+	vmemmap_tail = vmemmap_get_tail(h->order, folio_zone(folio));
+	if (WARN_ON_ONCE(!vmemmap_tail))
+		return -ENOMEM;
+
+	if (alloc_vmemmap_page_list(start, end, &vmemmap_pages))
+		return -ENOMEM;
+
+	walk = (struct vmemmap_remap_walk) {
 		.remap_pte	= vmemmap_restore_pte,
+		.vmemmap_tail	= vmemmap_tail,
 		.vmemmap_pages	= &vmemmap_pages,
 		.flags		= flags,
 	};
 
-	if (alloc_vmemmap_page_list(start, end, &vmemmap_pages))
-		return -ENOMEM;
+	ret = vmemmap_remap_range(start, end, &walk);
 
-	return vmemmap_remap_range(start, end, &walk);
+	/* Not all pages may have been consumed */
+	free_vmemmap_page_list(&vmemmap_pages);
+
+	return ret;
 }
 
 static bool vmemmap_optimize_enabled = IS_ENABLED(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON);
@@ -439,7 +462,7 @@ static int __hugetlb_vmemmap_restore_folio(const struct hstate *h,
 	 * When a HugeTLB page is freed to the buddy allocator, previously
 	 * discarded vmemmap pages must be allocated and remapping.
 	 */
-	ret = vmemmap_remap_alloc(vmemmap_start, vmemmap_end, flags);
+	ret = vmemmap_remap_alloc(h, folio, vmemmap_start, vmemmap_end, flags);
 	if (!ret)
 		folio_clear_hugetlb_vmemmap_optimized(folio);
 
@@ -572,7 +595,11 @@ static int __hugetlb_vmemmap_optimize_folio(const struct hstate *h,
 				 vmemmap_head, vmemmap_tail,
 				 vmemmap_pages, flags);
 out:
-	if (ret)
+	/*
+	 * If ret == VMEMMAP_REMAP_INCOMPLETE, the folio might be partially
+	 * HVOed. Leave the HVO page folio flag in place.
+	 */
+	if (ret < 0)
 		folio_clear_hugetlb_vmemmap_optimized(folio);
 
 	return ret;
-- 
2.55.0.795.g602f6c329a-goog