mm: cache struct page for empty_zero_page and return it from ZERO_PAGE()

For most architectures every invocation of ZERO_PAGE() does
virt_to_page(empty_zero_page).  But empty_zero_page is in BSS and it is
enough to get its struct page once at initialization time and then use it
whenever a zero page should be accessed.

Add yet another __zero_page variable that will be initialized as
virt_to_page(empty_zero_page) for most architectures in a weak
arch_setup_zero_pages() function.

For architectures that use colored zero pages (MIPS and s390) rename their
setup_zero_pages() to arch_setup_zero_pages() and make it global rather
than static.

For architectures that cannot use virt_to_page() for BSS (arm64 and
sparc64) add override of arch_setup_zero_pages().

Link: https://lkml.kernel.org/r/20260211103141.3215197-5-rppt@kernel.org
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Acked-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Andreas Larsson <andreas@gaisler.com>
Cc: "Borislav Petkov (AMD)" <bp@alien8.de>
Cc: Christophe Leroy (CS GROUP) <chleroy@kernel.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Dinh Nguyen <dinguyen@kernel.org>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Helge Deller <deller@gmx.de>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Magnus Lindholm <linmag7@gmail.com>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Richard Weinberger <richard@nod.at>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vineet Gupta <vgupta@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

arch/arm64/include/asm/pgtable.h

@@ -106,12 +106,6 @@ static inline void arch_leave_lazy_mmu_mode(void)
 #define flush_tlb_fix_spurious_fault_pmd(vma, address, pmdp)	\
 	local_flush_tlb_page_nonotify(vma, address)
 
-/*
- * ZERO_PAGE is a global shared page that is always zero: used
- * for zero-mapped memory areas etc..
- */
-#define ZERO_PAGE(vaddr)	phys_to_page(__pa_symbol(empty_zero_page))
-
 #define pte_ERROR(e)	\
 	pr_err("%s:%d: bad pte %016llx.\n", __FILE__, __LINE__, pte_val(e))
 

arch/arm64/mm/init.c

@@ -328,6 +328,11 @@ void __init bootmem_init(void)
 	memblock_dump_all();
 }
 
+void __init arch_setup_zero_pages(void)
+{
+	__zero_page = phys_to_page(__pa_symbol(empty_zero_page));
+}
+
 void __init arch_mm_preinit(void)
 {
 	unsigned int flags = SWIOTLB_VERBOSE;

arch/mips/mm/init.c

@@ -56,10 +56,7 @@ unsigned long empty_zero_page, zero_page_mask;
 EXPORT_SYMBOL_GPL(empty_zero_page);
 EXPORT_SYMBOL(zero_page_mask);
 
-/*
- * Not static inline because used by IP27 special magic initialization code
- */
-static void __init setup_zero_pages(void)
+void __init arch_setup_zero_pages(void)
 {
 	unsigned int order;
 
@@ -450,7 +447,6 @@ void __init arch_mm_preinit(void)
 	BUILD_BUG_ON(IS_ENABLED(CONFIG_32BIT) && (PFN_PTE_SHIFT > PAGE_SHIFT));
 
 	maar_init();
-	setup_zero_pages();	/* Setup zeroed pages.  */
 	highmem_init();
 
 #ifdef CONFIG_64BIT
@@ -461,11 +457,6 @@ void __init arch_mm_preinit(void)
 				0x80000000 - 4, KCORE_TEXT);
 #endif
 }
-#else  /* CONFIG_NUMA */
-void __init arch_mm_preinit(void)
-{
-	setup_zero_pages();	/* This comes from node 0 */
-}
 #endif /* !CONFIG_NUMA */
 
 void free_init_pages(const char *what, unsigned long begin, unsigned long end)

arch/s390/mm/init.c

@@ -69,7 +69,7 @@ unsigned long empty_zero_page, zero_page_mask;
 EXPORT_SYMBOL(empty_zero_page);
 EXPORT_SYMBOL(zero_page_mask);
 
-static void __init setup_zero_pages(void)
+void __init arch_setup_zero_pages(void)
 {
 	unsigned long total_pages = memblock_estimated_nr_free_pages();
 	unsigned int order;
@@ -159,8 +159,6 @@ void __init arch_mm_preinit(void)
 	cpumask_set_cpu(0, mm_cpumask(&init_mm));
 
 	pv_init();
-
-	setup_zero_pages();	/* Setup zeroed pages. */
 }
 
 unsigned long memory_block_size_bytes(void)

arch/sparc/include/asm/pgtable_64.h

@@ -210,9 +210,6 @@ extern unsigned long _PAGE_CACHE;
 extern unsigned long pg_iobits;
 extern unsigned long _PAGE_ALL_SZ_BITS;
 
-extern struct page *mem_map_zero;
-#define ZERO_PAGE(vaddr)	(mem_map_zero)
-
 /* PFNs are real physical page numbers.  However, mem_map only begins to record
  * per-page information starting at pfn_base.  This is to handle systems where
  * the first physical page in the machine is at some huge physical address,

arch/sparc/mm/init_64.c

@@ -177,9 +177,6 @@ extern unsigned long sparc_ramdisk_image64;
 extern unsigned int sparc_ramdisk_image;
 extern unsigned int sparc_ramdisk_size;
 
-struct page *mem_map_zero __read_mostly;
-EXPORT_SYMBOL(mem_map_zero);
-
 unsigned int sparc64_highest_unlocked_tlb_ent __read_mostly;
 
 unsigned long sparc64_kern_pri_context __read_mostly;
@@ -2490,11 +2487,17 @@ static void __init register_page_bootmem_info(void)
 			register_page_bootmem_info_node(NODE_DATA(i));
 #endif
 }
-void __init mem_init(void)
+
+void __init arch_setup_zero_pages(void)
 {
 	phys_addr_t zero_page_pa = kern_base +
 		((unsigned long)&empty_zero_page[0] - KERNBASE);
 
+	__zero_page = phys_to_page(zero_page_pa);
+}
+
+void __init mem_init(void)
+{
 	/*
 	 * Must be done after boot memory is put on freelist, because here we
 	 * might set fields in deferred struct pages that have not yet been
@@ -2503,12 +2506,6 @@ void __init mem_init(void)
 	 */
 	register_page_bootmem_info();
 
-	/*
-	 * Set up the zero page, mark it reserved, so that page count
-	 * is not manipulated when freeing the page from user ptes.
-	 */
-	mem_map_zero = pfn_to_page(PHYS_PFN(zero_page_pa));
-
 	if (tlb_type == cheetah || tlb_type == cheetah_plus)
 		cheetah_ecache_flush_init();
 }

include/linux/pgtable.h

@@ -1929,6 +1929,8 @@ static inline void pfnmap_setup_cachemode_pfn(unsigned long pfn, pgprot_t *prot)
  * For architectures that don't __HAVE_COLOR_ZERO_PAGE the zero page lives in
  * empty_zero_page in BSS.
  */
+void arch_setup_zero_pages(void);
+
 #ifdef __HAVE_COLOR_ZERO_PAGE
 static inline int is_zero_pfn(unsigned long pfn)
 {
@@ -1956,10 +1958,13 @@ static inline unsigned long zero_pfn(unsigned long addr)
 }
 
 extern uint8_t empty_zero_page[PAGE_SIZE];
+extern struct page *__zero_page;
 
-#ifndef ZERO_PAGE
-#define ZERO_PAGE(vaddr) ((void)(vaddr),virt_to_page(empty_zero_page))
-#endif
+static inline struct page *_zero_page(unsigned long addr)
+{
+	return __zero_page;
+}
+#define ZERO_PAGE(vaddr) _zero_page(vaddr)
 
 #endif /* __HAVE_COLOR_ZERO_PAGE */
 

mm/mm_init.c

@@ -59,7 +59,10 @@ EXPORT_SYMBOL(zero_page_pfn);
 #ifndef __HAVE_COLOR_ZERO_PAGE
 uint8_t empty_zero_page[PAGE_SIZE] __page_aligned_bss;
 EXPORT_SYMBOL(empty_zero_page);
-#endif
+
+struct page *__zero_page __ro_after_init;
+EXPORT_SYMBOL(__zero_page);
+#endif /* __HAVE_COLOR_ZERO_PAGE */
 
 #ifdef CONFIG_DEBUG_MEMORY_INIT
 int __meminitdata mminit_loglevel;
@@ -2680,12 +2683,21 @@ static void __init mem_init_print_info(void)
 		);
 }
 
-static int __init init_zero_page_pfn(void)
+#ifndef __HAVE_COLOR_ZERO_PAGE
+/*
+ * architectures that __HAVE_COLOR_ZERO_PAGE must define this function
+ */
+void __init __weak arch_setup_zero_pages(void)
 {
-	zero_page_pfn = page_to_pfn(ZERO_PAGE(0));
-	return 0;
+	__zero_page = virt_to_page(empty_zero_page);
+}
+#endif
+
+static void __init init_zero_page_pfn(void)
+{
+	arch_setup_zero_pages();
+	zero_page_pfn = page_to_pfn(ZERO_PAGE(0));
 }
-early_initcall(init_zero_page_pfn);
 
 void __init __weak arch_mm_preinit(void)
 {
@@ -2709,6 +2721,7 @@ void __init mm_core_init_early(void)
 void __init mm_core_init(void)
 {
 	arch_mm_preinit();
+	init_zero_page_pfn();
 
 	/* Initializations relying on SMP setup */
 	BUILD_BUG_ON(MAX_ZONELISTS > 2);