[PATCH v2 09/11] hugetlb: batch PMD split for bulk vmemmap dedup

[Mike Kravetz]

From: Joao Martins <joao.m.martins@xxxxxxxxxx>

In an effort to minimize amount of TLB flushes, batch all PMD splits
belonging to a range of pages in order to perform only 1 (global) TLB
flush.

Rebased and updated by Mike Kravetz

Signed-off-by: Joao Martins <joao.m.martins@xxxxxxxxxx>
Signed-off-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
---
 mm/hugetlb_vmemmap.c | 72 +++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 68 insertions(+), 4 deletions(-)

diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index a715712df831..d956551699bc 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -37,7 +37,7 @@ struct vmemmap_remap_walk {
 	struct list_head	*vmemmap_pages;
 };
 
-static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start)
+static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start, bool flush)
 {
 	pmd_t __pmd;
 	int i;
@@ -80,7 +80,8 @@ static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start)
 		/* Make pte visible before pmd. See comment in pmd_install(). */
 		smp_wmb();
 		pmd_populate_kernel(&init_mm, pmd, pgtable);
-		flush_tlb_kernel_range(start, start + PMD_SIZE);
+		if (flush)
+			flush_tlb_kernel_range(start, start + PMD_SIZE);
 	} else {
 		pte_free_kernel(&init_mm, pgtable);
 	}
@@ -127,11 +128,20 @@ static int vmemmap_pmd_range(pud_t *pud, unsigned long addr,
 	do {
 		int ret;
 
-		ret = split_vmemmap_huge_pmd(pmd, addr & PMD_MASK);
+		ret = split_vmemmap_huge_pmd(pmd, addr & PMD_MASK,
+				walk->remap_pte != NULL);
 		if (ret)
 			return ret;
 
 		next = pmd_addr_end(addr, end);
+
+		/*
+		 * We are only splitting, not remapping the hugetlb vmemmap
+		 * pages.
+		 */
+		if (!walk->remap_pte)
+			continue;
+
 		vmemmap_pte_range(pmd, addr, next, walk);
 	} while (pmd++, addr = next, addr != end);
 
@@ -198,7 +208,8 @@ static int vmemmap_remap_range(unsigned long start, unsigned long end,
 			return ret;
 	} while (pgd++, addr = next, addr != end);
 
-	flush_tlb_kernel_range(start, end);
+	if (walk->remap_pte)
+		flush_tlb_kernel_range(start, end);
 
 	return 0;
 }
@@ -297,6 +308,35 @@ static void vmemmap_restore_pte(pte_t *pte, unsigned long addr,
 	set_pte_at(&init_mm, addr, pte, mk_pte(page, pgprot));
 }
 
+/**
+ * vmemmap_remap_split - split the vmemmap virtual address range [@start, @end)
+ *                      backing PMDs of the directmap into PTEs
+ * @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
+ *             remap.
+ * @reuse:     reuse address.
+ *
+ * Return: %0 on success, negative error code otherwise.
+ */
+static int vmemmap_remap_split(unsigned long start, unsigned long end,
+				unsigned long reuse)
+{
+	int ret;
+	struct vmemmap_remap_walk walk = {
+		.remap_pte	= NULL,
+	};
+
+	/* See the comment in the vmemmap_remap_free(). */
+	BUG_ON(start - reuse != PAGE_SIZE);
+
+	mmap_read_lock(&init_mm);
+	ret = vmemmap_remap_range(reuse, end, &walk);
+	mmap_read_unlock(&init_mm);
+
+	return ret;
+}
+
 /**
  * vmemmap_remap_free - remap the vmemmap virtual address range [@start, @end)
  *			to the page which @reuse is mapped to, then free vmemmap
@@ -602,11 +642,35 @@ void hugetlb_vmemmap_optimize(const struct hstate *h, struct page *head)
 	free_vmemmap_page_list(&vmemmap_pages);
 }
 
+static void hugetlb_vmemmap_split(const struct hstate *h, struct page *head)
+{
+	unsigned long vmemmap_start = (unsigned long)head, vmemmap_end;
+	unsigned long vmemmap_reuse;
+
+	if (!vmemmap_should_optimize(h, head))
+		return;
+
+	vmemmap_end     = vmemmap_start + hugetlb_vmemmap_size(h);
+	vmemmap_reuse   = vmemmap_start;
+	vmemmap_start   += HUGETLB_VMEMMAP_RESERVE_SIZE;
+
+	/*
+	 * Split PMDs on the vmemmap virtual address range [@vmemmap_start,
+	 * @vmemmap_end]
+	 */
+	vmemmap_remap_split(vmemmap_start, vmemmap_end, vmemmap_reuse);
+}
+
 void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_list)
 {
 	struct folio *folio;
 	LIST_HEAD(vmemmap_pages);
 
+	list_for_each_entry(folio, folio_list, lru)
+		hugetlb_vmemmap_split(h, &folio->page);
+
+	flush_tlb_all();
+
 	list_for_each_entry(folio, folio_list, lru)
 		__hugetlb_vmemmap_optimize(h, &folio->page, &vmemmap_pages);
 
-- 
2.41.0