mm/hugetlb: add pre-HVO framework

Define flags for pre-HVOed bootmem hugetlb pages, and act on them.

The most important flag is the HVO flag, signalling that a bootmem
allocated gigantic page has already been HVO-ed.  If this flag is seen by
the hugetlb bootmem gather code, the page is marked as HVO optimized.  The
HVO code will then not try to optimize it again.  Instead, it will just
map the tail page mirror pages read-only, completing the HVO steps.

No functional change, as nothing sets the flags yet.

Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Frank van der Linden <[email protected]>
Cc: Alexander Gordeev <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Arnd Bergmann <[email protected]>
Cc: Dan Carpenter <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: Heiko Carstens <[email protected]>
Cc: Joao Martins <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Madhavan Srinivasan <[email protected]>
Cc: Michael Ellerman <[email protected]>
Cc: Muchun Song <[email protected]>
Cc: Oscar Salvador <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Roman Gushchin (Cruise) <[email protected]>
Cc: Usama Arif <[email protected]>
Cc: Vasily Gorbik <[email protected]>
Cc: Yu Zhao <[email protected]>
Cc: Zi Yan <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

1 files changed, 48 insertions, 2 deletions

diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 5b484758f813..be6b33ecbc8e 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -649,14 +649,39 @@ static int hugetlb_vmemmap_split_folio(const struct hstate *h, struct folio *fol
 	return vmemmap_remap_split(vmemmap_start, vmemmap_end, vmemmap_reuse);
 }
 
-void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_list)
+static void __hugetlb_vmemmap_optimize_folios(struct hstate *h,
+					      struct list_head *folio_list,
+					      bool boot)
 {
 	struct folio *folio;
+	int nr_to_optimize;
 	LIST_HEAD(vmemmap_pages);
 	unsigned long flags = VMEMMAP_REMAP_NO_TLB_FLUSH | VMEMMAP_SYNCHRONIZE_RCU;
 
+	nr_to_optimize = 0;
 	list_for_each_entry(folio, folio_list, lru) {
-		int ret = hugetlb_vmemmap_split_folio(h, folio);
+		int ret;
+		unsigned long spfn, epfn;
+
+		if (boot && folio_test_hugetlb_vmemmap_optimized(folio)) {
+			/*
+			 * Already optimized by pre-HVO, just map the
+			 * mirrored tail page structs RO.
+			 */
+			spfn = (unsigned long)&folio->page;
+			epfn = spfn + pages_per_huge_page(h);
+			vmemmap_wrprotect_hvo(spfn, epfn, folio_nid(folio),
+					HUGETLB_VMEMMAP_RESERVE_SIZE);
+			register_page_bootmem_memmap(pfn_to_section_nr(spfn),
+					&folio->page,
+					HUGETLB_VMEMMAP_RESERVE_SIZE);
+			static_branch_inc(&hugetlb_optimize_vmemmap_key);
+			continue;
+		}
+
+		nr_to_optimize++;
+
+		ret = hugetlb_vmemmap_split_folio(h, folio);
 
 		/*
 		 * Spliting the PMD requires allocating a page, thus lets fail
@@ -668,6 +693,16 @@ void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_l
 			break;
 	}
 
+	if (!nr_to_optimize)
+		/*
+		 * All pre-HVO folios, nothing left to do. It's ok if
+		 * there is a mix of pre-HVO and not yet HVO-ed folios
+		 * here, as __hugetlb_vmemmap_optimize_folio() will
+		 * skip any folios that already have the optimized flag
+		 * set, see vmemmap_should_optimize_folio().
+		 */
+		goto out;
+
 	flush_tlb_all();
 
 	list_for_each_entry(folio, folio_list, lru) {
@@ -693,10 +728,21 @@ void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_l
 		}
 	}
 
+out:
 	flush_tlb_all();
 	free_vmemmap_page_list(&vmemmap_pages);
 }
 
+void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_list)
+{
+	__hugetlb_vmemmap_optimize_folios(h, folio_list, false);
+}
+
+void hugetlb_vmemmap_optimize_bootmem_folios(struct hstate *h, struct list_head *folio_list)
+{
+	__hugetlb_vmemmap_optimize_folios(h, folio_list, true);
+}
+
 static const struct ctl_table hugetlb_vmemmap_sysctls[] = {
 	{
 		.procname	= "hugetlb_optimize_vmemmap",