From c1a6c536fb088c01d6bdce77731d89ad5e1734c6 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Date: Tue, 25 Jul 2023 00:37:49 +0530
Subject: [PATCH] mm/vmemmap: improve vmemmap_can_optimize and allow
 architectures to override

dax vmemmap optimization requires a minimum of 2 PAGE_SIZE area within
vmemmap such that tail page mapping can point to the second PAGE_SIZE
area.  Enforce that in vmemmap_can_optimize() function.

Architectures like powerpc also want to enable vmemmap optimization
conditionally (only with radix MMU translation).  Hence allow architecture
override.

Link: https://lkml.kernel.org/r/20230724190759.483013-4-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm.h | 27 +++++++++++++++++++++++----
 mm/mm_init.c       |  2 +-
 2 files changed, 24 insertions(+), 5 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 21299a0cfbca..d4ce73c20dcc 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3632,13 +3632,32 @@ void vmemmap_free(unsigned long start, unsigned long end,
 		struct vmem_altmap *altmap);
 #endif
 
+#define VMEMMAP_RESERVE_NR	2
 #ifdef CONFIG_ARCH_WANT_OPTIMIZE_VMEMMAP
-static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap,
-					   struct dev_pagemap *pgmap)
+static inline bool __vmemmap_can_optimize(struct vmem_altmap *altmap,
+					  struct dev_pagemap *pgmap)
 {
-	return is_power_of_2(sizeof(struct page)) &&
-		pgmap && (pgmap_vmemmap_nr(pgmap) > 1) && !altmap;
+	unsigned long nr_pages;
+	unsigned long nr_vmemmap_pages;
+
+	if (!pgmap || !is_power_of_2(sizeof(struct page)))
+		return false;
+
+	nr_pages = pgmap_vmemmap_nr(pgmap);
+	nr_vmemmap_pages = ((nr_pages * sizeof(struct page)) >> PAGE_SHIFT);
+	/*
+	 * For vmemmap optimization with DAX we need minimum 2 vmemmap
+	 * pages. See layout diagram in Documentation/mm/vmemmap_dedup.rst
+	 */
+	return !altmap && (nr_vmemmap_pages > VMEMMAP_RESERVE_NR);
 }
+/*
+ * If we don't have an architecture override, use the generic rule
+ */
+#ifndef vmemmap_can_optimize
+#define vmemmap_can_optimize __vmemmap_can_optimize
+#endif
+
 #else
 static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap,
 					   struct dev_pagemap *pgmap)
diff --git a/mm/mm_init.c b/mm/mm_init.c
index acb0ac194672..641c56fd08a2 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -1020,7 +1020,7 @@ static inline unsigned long compound_nr_pages(struct vmem_altmap *altmap,
 	if (!vmemmap_can_optimize(altmap, pgmap))
 		return pgmap_vmemmap_nr(pgmap);
 
-	return 2 * (PAGE_SIZE / sizeof(struct page));
+	return VMEMMAP_RESERVE_NR * (PAGE_SIZE / sizeof(struct page));
 }
 
 static void __ref memmap_init_compound(struct page *head,