[PATCH 21/49] mm/sparse: drop power-of-2 size requirement for struct mem_section

[Muchun Song]

Since sparsemem-extreme was introduced, struct mem_section has been
forced to a power-of-2 size so that the section-to-root lookup could
use a cheap bit-mask instead of an expensive divide:

    section = &mem_section[root][nr & SECTION_ROOT_MASK];

This is enforced at compile time with

    BUILD_BUG_ON(!is_power_of_2(sizeof(struct mem_section)));

and forces us to add padding that grows and shrinks with every config
combination, wasting memory just to keep the structure aligned to the
next power of two.  With CONFIG_PAGE_EXTENSION enabled the padding
alone can reach 42 struct mem_section instances per section-root page.

Drop the requirement and switch to a plain modulo:

    section = &mem_section[root][nr % SECTIONS_PER_ROOT];

Modern compilers turn the divide into a multiply-by-reciprocal approach,
so the runtime impact is negligible.  In return we get:

1. Immediate memory savings when CONFIG_PAGE_EXTENSION is enabled.
2. Freedom to extend struct mem_section in the future without having
   to fiddle with artificial padding or the power-of-2 rule.

Signed-off-by: Muchun Song <songmuchun at bytedance.com>
---
 include/linux/mmzone.h  | 8 +-------
 mm/sparse.c             | 2 --
 scripts/gdb/linux/mm.py | 6 ++----
 3 files changed, 3 insertions(+), 13 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 378feaf4e4ed..3e3755666846 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -2013,12 +2013,7 @@ struct mem_section {
 	 * section. (see page_ext.h about this.)
 	 */
 	struct page_ext *page_ext;
-	unsigned long pad;
 #endif
-	/*
-	 * WARNING: mem_section must be a power-of-2 in size for the
-	 * calculation and use of SECTION_ROOT_MASK to make sense.
-	 */
 };
 
 #ifdef CONFIG_SPARSEMEM_EXTREME
@@ -2029,7 +2024,6 @@ struct mem_section {
 
 #define SECTION_NR_TO_ROOT(sec)	((sec) / SECTIONS_PER_ROOT)
 #define NR_SECTION_ROOTS	DIV_ROUND_UP(NR_MEM_SECTIONS, SECTIONS_PER_ROOT)
-#define SECTION_ROOT_MASK	(SECTIONS_PER_ROOT - 1)
 
 #ifdef CONFIG_SPARSEMEM_EXTREME
 extern struct mem_section **mem_section;
@@ -2053,7 +2047,7 @@ static inline struct mem_section *__nr_to_section(unsigned long nr)
 	if (!mem_section || !mem_section[root])
 		return NULL;
 #endif
-	return &mem_section[root][nr & SECTION_ROOT_MASK];
+	return &mem_section[root][nr % SECTIONS_PER_ROOT];
 }
 extern size_t mem_section_usage_size(void);
 
diff --git a/mm/sparse.c b/mm/sparse.c
index 5fe0a7e66775..cfe4ffd89baf 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -394,8 +394,6 @@ void __init sparse_init(void)
 	unsigned long pnum_end, pnum_begin, map_count = 1;
 	int nid_begin;
 
-	/* see include/linux/mmzone.h 'struct mem_section' definition */
-	BUILD_BUG_ON(!is_power_of_2(sizeof(struct mem_section)));
 	memblocks_present();
 
 	if (compound_info_has_mask()) {
diff --git a/scripts/gdb/linux/mm.py b/scripts/gdb/linux/mm.py
index d78908f6664d..0c9eeed92064 100644
--- a/scripts/gdb/linux/mm.py
+++ b/scripts/gdb/linux/mm.py
@@ -70,7 +70,6 @@ class x86_page_ops():
             self.SECTIONS_PER_ROOT = 1
 
         self.NR_SECTION_ROOTS = DIV_ROUND_UP(self.NR_MEM_SECTIONS, self.SECTIONS_PER_ROOT)
-        self.SECTION_ROOT_MASK = self.SECTIONS_PER_ROOT - 1
 
         try:
             self.SECTION_HAS_MEM_MAP = 1 << int(gdb.parse_and_eval('SECTION_HAS_MEM_MAP_BIT'))
@@ -100,7 +99,7 @@ class x86_page_ops():
     def __nr_to_section(self, nr):
         root = self.SECTION_NR_TO_ROOT(nr)
         mem_section = gdb.parse_and_eval("mem_section")
-        return mem_section[root][nr & self.SECTION_ROOT_MASK]
+        return mem_section[root][nr % self.SECTIONS_PER_ROOT]
 
     def pfn_to_section_nr(self, pfn):
         return pfn >> self.PFN_SECTION_SHIFT
@@ -249,7 +248,6 @@ class aarch64_page_ops():
             self.SECTIONS_PER_ROOT = 1
 
         self.NR_SECTION_ROOTS = DIV_ROUND_UP(self.NR_MEM_SECTIONS, self.SECTIONS_PER_ROOT)
-        self.SECTION_ROOT_MASK = self.SECTIONS_PER_ROOT - 1
         self.SUBSECTION_SHIFT = 21
         self.SEBSECTION_SIZE = 1 << self.SUBSECTION_SHIFT
         self.PFN_SUBSECTION_SHIFT = self.SUBSECTION_SHIFT - self.PAGE_SHIFT
@@ -304,7 +302,7 @@ class aarch64_page_ops():
     def __nr_to_section(self, nr):
         root = self.SECTION_NR_TO_ROOT(nr)
         mem_section = gdb.parse_and_eval("mem_section")
-        return mem_section[root][nr & self.SECTION_ROOT_MASK]
+        return mem_section[root][nr % self.SECTIONS_PER_ROOT]
 
     def pfn_to_section_nr(self, pfn):
         return pfn >> self.PFN_SECTION_SHIFT
-- 
2.20.1