hugetlb: batch PMD split for bulk vmemmap dedup

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.

Add a flags field to the walker and pass whether it's a bulk allocation or
just a single page to decide to remap.  First value
(VMEMMAP_SPLIT_NO_TLB_FLUSH) designates the request to not do the TLB
flush when we split the PMD.

Rebased and updated by Mike Kravetz

Link: https://lkml.kernel.org/r/20231019023113.345257-7-mike.kravetz@oracle.com
Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Barry Song <21cnbao@gmail.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: James Houghton <jthoughton@google.com>
Cc: Konrad Dybcio <konradybcio@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Naoya Horiguchi <naoya.horiguchi@linux.dev>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Usama Arif <usama.arif@bytedance.com>
Cc: Xiongchun Duan <duanxiongchun@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

mm/hugetlb_vmemmap.c

@@ -27,6 +27,8 @@
  * @reuse_addr:		the virtual address of the @reuse_page page.
  * @vmemmap_pages:	the list head of the vmemmap pages that can be freed
  *			or is mapped from.
+ * @flags:		used to modify behavior in vmemmap page table walking
+ *			operations.
  */
 struct vmemmap_remap_walk {
 	void			(*remap_pte)(pte_t *pte, unsigned long addr,
@@ -35,9 +37,13 @@ struct vmemmap_remap_walk {
 	struct page		*reuse_page;
 	unsigned long		reuse_addr;
 	struct list_head	*vmemmap_pages;
+
+/* Skip the TLB flush when we split the PMD */
+#define VMEMMAP_SPLIT_NO_TLB_FLUSH	BIT(0)
+	unsigned long		flags;
 };
 
-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 +86,8 @@ 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 +134,20 @@ 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->flags & VMEMMAP_SPLIT_NO_TLB_FLUSH));
 		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 +214,8 @@ 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 +314,36 @@ 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,
+		.flags		= VMEMMAP_SPLIT_NO_TLB_FLUSH,
+	};
+
+	/* 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
@@ -320,6 +367,7 @@ static int vmemmap_remap_free(unsigned long start, unsigned long end,
 		.remap_pte	= vmemmap_remap_pte,
 		.reuse_addr	= reuse,
 		.vmemmap_pages	= vmemmap_pages,
+		.flags		= 0,
 	};
 	int nid = page_to_nid((struct page *)reuse);
 	gfp_t gfp_mask = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
@@ -368,6 +416,7 @@ static int vmemmap_remap_free(unsigned long start, unsigned long end,
 			.remap_pte	= vmemmap_restore_pte,
 			.reuse_addr	= reuse,
 			.vmemmap_pages	= vmemmap_pages,
+			.flags		= 0,
 		};
 
 		vmemmap_remap_range(reuse, end, &walk);
@@ -419,6 +468,7 @@ static int vmemmap_remap_alloc(unsigned long start, unsigned long end,
 		.remap_pte	= vmemmap_restore_pte,
 		.reuse_addr	= reuse,
 		.vmemmap_pages	= &vmemmap_pages,
+		.flags		= 0,
 	};
 
 	/* See the comment in the vmemmap_remap_free(). */
@@ -628,11 +678,45 @@ void hugetlb_vmemmap_optimize(const struct hstate *h, struct page *head)
 	free_vmemmap_page_list(&vmemmap_pages);
 }
 
+static int 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 0;
+
+	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]
+	 */
+	return 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) {
+		int ret = hugetlb_vmemmap_split(h, &folio->page);
+
+		/*
+		 * Spliting the PMD requires allocating a page, thus lets fail
+		 * early once we encounter the first OOM. No point in retrying
+		 * as it can be dynamically done on remap with the memory
+		 * we get back from the vmemmap deduplication.
+		 */
+		if (ret == -ENOMEM)
+			break;
+	}
+
+	flush_tlb_all();
+
 	list_for_each_entry(folio, folio_list, lru) {
 		int ret = __hugetlb_vmemmap_optimize(h, &folio->page,
 								&vmemmap_pages);