[PATCHv5 13/17] hugetlb: Remove VMEMMAP_SYNCHRONIZE_RCU

[Kiryl Shutsemau]

The VMEMMAP_SYNCHRONIZE_RCU flag triggered synchronize_rcu() calls to
prevent a race between HVO remapping and page_ref_add_unless(). The
race could occur when a speculative PFN walker tried to modify the
refcount on a struct page that was in the process of being remapped
to a fake head.

With fake heads eliminated, page_ref_add_unless() no longer needs RCU
protection.

Remove the flag and synchronize_rcu() calls.

Signed-off-by: Kiryl Shutsemau <kas at kernel.org>
Reviewed-by: Muchun Song <muchun.song at linux.dev>
---
 mm/hugetlb_vmemmap.c | 20 ++++----------------
 1 file changed, 4 insertions(+), 16 deletions(-)

diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index f5f42b92dd7d..fd74a164c494 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -47,8 +47,6 @@ struct vmemmap_remap_walk {
 #define VMEMMAP_SPLIT_NO_TLB_FLUSH	BIT(0)
 /* Skip the TLB flush when we remap the PTE */
 #define VMEMMAP_REMAP_NO_TLB_FLUSH	BIT(1)
-/* synchronize_rcu() to avoid writes from page_ref_add_unless() */
-#define VMEMMAP_SYNCHRONIZE_RCU		BIT(2)
 	unsigned long		flags;
 };
 
@@ -409,9 +407,6 @@ static int __hugetlb_vmemmap_restore_folio(const struct hstate *h,
 	if (!folio_test_hugetlb_vmemmap_optimized(folio))
 		return 0;
 
-	if (flags & VMEMMAP_SYNCHRONIZE_RCU)
-		synchronize_rcu();
-
 	vmemmap_start	= (unsigned long)&folio->page;
 	vmemmap_end	= vmemmap_start + hugetlb_vmemmap_size(h);
 
@@ -444,7 +439,7 @@ static int __hugetlb_vmemmap_restore_folio(const struct hstate *h,
  */
 int hugetlb_vmemmap_restore_folio(const struct hstate *h, struct folio *folio)
 {
-	return __hugetlb_vmemmap_restore_folio(h, folio, VMEMMAP_SYNCHRONIZE_RCU);
+	return __hugetlb_vmemmap_restore_folio(h, folio, 0);
 }
 
 /**
@@ -467,14 +462,11 @@ long hugetlb_vmemmap_restore_folios(const struct hstate *h,
 	struct folio *folio, *t_folio;
 	long restored = 0;
 	long ret = 0;
-	unsigned long flags = VMEMMAP_REMAP_NO_TLB_FLUSH | VMEMMAP_SYNCHRONIZE_RCU;
+	unsigned long flags = VMEMMAP_REMAP_NO_TLB_FLUSH;
 
 	list_for_each_entry_safe(folio, t_folio, folio_list, lru) {
 		if (folio_test_hugetlb_vmemmap_optimized(folio)) {
 			ret = __hugetlb_vmemmap_restore_folio(h, folio, flags);
-			/* only need to synchronize_rcu() once for each batch */
-			flags &= ~VMEMMAP_SYNCHRONIZE_RCU;
-
 			if (ret)
 				break;
 			restored++;
@@ -556,8 +548,6 @@ static int __hugetlb_vmemmap_optimize_folio(const struct hstate *h,
 
 	static_branch_inc(&hugetlb_optimize_vmemmap_key);
 
-	if (flags & VMEMMAP_SYNCHRONIZE_RCU)
-		synchronize_rcu();
 	/*
 	 * Very Subtle
 	 * If VMEMMAP_REMAP_NO_TLB_FLUSH is set, TLB flushing is not performed
@@ -615,7 +605,7 @@ void hugetlb_vmemmap_optimize_folio(const struct hstate *h, struct folio *folio)
 {
 	LIST_HEAD(vmemmap_pages);
 
-	__hugetlb_vmemmap_optimize_folio(h, folio, &vmemmap_pages, VMEMMAP_SYNCHRONIZE_RCU);
+	__hugetlb_vmemmap_optimize_folio(h, folio, &vmemmap_pages, 0);
 	free_vmemmap_page_list(&vmemmap_pages);
 }
 
@@ -643,7 +633,7 @@ static void __hugetlb_vmemmap_optimize_folios(struct hstate *h,
 	struct folio *folio;
 	int nr_to_optimize;
 	LIST_HEAD(vmemmap_pages);
-	unsigned long flags = VMEMMAP_REMAP_NO_TLB_FLUSH | VMEMMAP_SYNCHRONIZE_RCU;
+	unsigned long flags = VMEMMAP_REMAP_NO_TLB_FLUSH;
 
 	nr_to_optimize = 0;
 	list_for_each_entry(folio, folio_list, lru) {
@@ -696,8 +686,6 @@ static void __hugetlb_vmemmap_optimize_folios(struct hstate *h,
 		int ret;
 
 		ret = __hugetlb_vmemmap_optimize_folio(h, folio, &vmemmap_pages, flags);
-		/* only need to synchronize_rcu() once for each batch */
-		flags &= ~VMEMMAP_SYNCHRONIZE_RCU;
 
 		/*
 		 * Pages to be freed may have been accumulated.  If we
-- 
2.51.2