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

arch/powerpc/mm/hugetlbpage.c

···
 	gpage_freearray[nr_gpages] = 0;
 	list_add(&m->list, &huge_boot_pages[0]);
 	m->hstate = hstate;
+	m->flags = 0;
 	return 1;
 }
 

include/linux/hugetlb.h

···
 struct huge_bootmem_page {
 	struct list_head list;
 	struct hstate *hstate;
+	unsigned long flags;
 };
+
+#define HUGE_BOOTMEM_HVO		0x0001
+#define HUGE_BOOTMEM_ZONES_VALID	0x0002
 
 int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list);
 int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn);

mm/hugetlb.c

···
 	INIT_LIST_HEAD(&m->list);
 	list_add(&m->list, &huge_boot_pages[node]);
 	m->hstate = h;
+	m->flags = 0;
 	return 1;
 }
 
···
 	struct folio *folio, *tmp_f;
 
 	/* Send list for bulk vmemmap optimization processing */
-	hugetlb_vmemmap_optimize_folios(h, folio_list);
+	hugetlb_vmemmap_optimize_bootmem_folios(h, folio_list);
 
 	list_for_each_entry_safe(folio, tmp_f, folio_list, lru) {
 		if (!folio_test_hugetlb_vmemmap_optimized(folio)) {
···
 {
 	unsigned long start_pfn;
 	bool valid;
+
+	if (m->flags & HUGE_BOOTMEM_ZONES_VALID) {
+		/*
+		 * Already validated, skip check.
+		 */
+		return true;
+	}
 
 	start_pfn = virt_to_phys(m) >> PAGE_SHIFT;
 
···
 		free_reserved_page(page);
 		page++;
 	}
+}
+
+static bool __init hugetlb_bootmem_page_prehvo(struct huge_bootmem_page *m)
+{
+	return (m->flags & HUGE_BOOTMEM_HVO);
 }
 
 /*
···
 		hugetlb_folio_init_vmemmap(folio, h,
 					   HUGETLB_VMEMMAP_RESERVE_PAGES);
 		init_new_hugetlb_folio(h, folio);
+
+		if (hugetlb_bootmem_page_prehvo(m))
+			/*
+			 * If pre-HVO was done, just set the
+			 * flag, the HVO code will then skip
+			 * this folio.
+			 */
+			folio_set_hugetlb_vmemmap_optimized(folio);
+
 		list_add(&folio->lru, &folio_list);
 
 		/*

mm/hugetlb_vmemmap.c

···
 	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
···
 		if (ret == -ENOMEM)
 			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();
 
···
 		}
 	}
 
+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[] = {

mm/hugetlb_vmemmap.h

···
 					struct list_head *non_hvo_folios);
 void hugetlb_vmemmap_optimize_folio(const struct hstate *h, struct folio *folio);
 void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_list);
+void hugetlb_vmemmap_optimize_bootmem_folios(struct hstate *h, struct list_head *folio_list);
+
 
 static inline unsigned int hugetlb_vmemmap_size(const struct hstate *h)
 {
···
 }
 
 static inline void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_list)
+{
+}
+
+static inline void hugetlb_vmemmap_optimize_bootmem_folios(struct hstate *h,
+						struct list_head *folio_list)
 {
 }