arch, mm: introduce arch_mm_preinit

Currently, implementation of mem_init() in every architecture consists of
one or more of the following:

* initializations that must run before page allocator is active, for
  instance swiotlb_init()
* a call to memblock_free_all() to release all the memory to the buddy
  allocator
* initializations that must run after page allocator is ready and there is
  no arch-specific hook other than mem_init() for that, like for example
  register_page_bootmem_info() in x86 and sparc64 or simple setting of
  mem_init_done = 1 in several architectures
* a bunch of semi-related stuff that apparently had no better place to
  live, for example a ton of BUILD_BUG_ON()s in parisc.

Introduce arch_mm_preinit() that will be the first thing called from
mm_core_init(). On architectures that have initializations that must happen
before the page allocator is ready, move those into arch_mm_preinit() along
with the code that does not depend on ordering with page allocator setup.

On several architectures this results in reduction of mem_init() to a
single call to memblock_free_all() that allows its consolidation next.

Link: https://lkml.kernel.org/r/20250313135003.836600-13-rppt@kernel.org
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>	[x86]
Tested-by: Mark Brown <broonie@kernel.org>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Andreas Larsson <andreas@gaisler.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Borislav Betkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Dinh Nguyen <dinguyen@kernel.org>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Guo Ren (csky) <guoren@kernel.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Helge Deller <deller@gmx.de>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Richard Weinberger <richard@nod.at>
Cc: Russel King <linux@armlinux.org.uk>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleinxer <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vineet Gupta <vgupta@kernel.org>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

arch/arc/mm/init.c

@@ -157,11 +157,16 @@ void __init setup_arch_memory(void)
 	free_area_init(max_zone_pfn);
 }
 
-static void __init highmem_init(void)
+void __init arch_mm_preinit(void)
 {
 #ifdef CONFIG_HIGHMEM
 	memblock_phys_free(high_mem_start, high_mem_sz);
 #endif
+
+	BUILD_BUG_ON((PTRS_PER_PGD * sizeof(pgd_t)) > PAGE_SIZE);
+	BUILD_BUG_ON((PTRS_PER_PUD * sizeof(pud_t)) > PAGE_SIZE);
+	BUILD_BUG_ON((PTRS_PER_PMD * sizeof(pmd_t)) > PAGE_SIZE);
+	BUILD_BUG_ON((PTRS_PER_PTE * sizeof(pte_t)) > PAGE_SIZE);
 }
 
 /*
@@ -172,13 +177,7 @@ static void __init highmem_init(void)
  */
 void __init mem_init(void)
 {
-	highmem_init();
 	memblock_free_all();
-
-	BUILD_BUG_ON((PTRS_PER_PGD * sizeof(pgd_t)) > PAGE_SIZE);
-	BUILD_BUG_ON((PTRS_PER_PUD * sizeof(pud_t)) > PAGE_SIZE);
-	BUILD_BUG_ON((PTRS_PER_PMD * sizeof(pmd_t)) > PAGE_SIZE);
-	BUILD_BUG_ON((PTRS_PER_PTE * sizeof(pte_t)) > PAGE_SIZE);
 }
 
 #ifdef CONFIG_HIGHMEM

arch/arm/mm/init.c

@@ -237,12 +237,7 @@ static inline void poison_init_mem(void *s, size_t count)
 		*p++ = 0xe7fddef0;
 }
 
-/*
- * mem_init() marks the free areas in the mem_map and tells us how much
- * memory is free.  This is done after various parts of the system have
- * claimed their memory after the kernel image.
- */
-void __init mem_init(void)
+void __init arch_mm_preinit(void)
 {
 #ifdef CONFIG_ARM_LPAE
 	swiotlb_init(max_pfn > arm_dma_pfn_limit, SWIOTLB_VERBOSE);
@@ -253,9 +248,6 @@ void __init mem_init(void)
 	memblock_phys_free(PHYS_OFFSET, __pa(swapper_pg_dir) - PHYS_OFFSET);
 #endif
 
-	/* this will put all unused low memory onto the freelists */
-	memblock_free_all();
-
 	/*
 	 * Check boundaries twice: Some fundamental inconsistencies can
 	 * be detected at build time already.
@@ -271,6 +263,17 @@ void __init mem_init(void)
 #endif
 }
 
+/*
+ * mem_init() marks the free areas in the mem_map and tells us how much
+ * memory is free.  This is done after various parts of the system have
+ * claimed their memory after the kernel image.
+ */
+void __init mem_init(void)
+{
+	/* this will put all unused low memory onto the freelists */
+	memblock_free_all();
+}
+
 #ifdef CONFIG_STRICT_KERNEL_RWX
 struct section_perm {
 	const char *name;

arch/arm64/mm/init.c

@@ -357,12 +357,7 @@ void __init bootmem_init(void)
 	memblock_dump_all();
 }
 
-/*
- * mem_init() marks the free areas in the mem_map and tells us how much memory
- * is free.  This is done after various parts of the system have claimed their
- * memory after the kernel image.
- */
-void __init mem_init(void)
+void __init arch_mm_preinit(void)
 {
 	unsigned int flags = SWIOTLB_VERBOSE;
 	bool swiotlb = max_pfn > PFN_DOWN(arm64_dma_phys_limit);
@@ -386,9 +381,6 @@ void __init mem_init(void)
 	swiotlb_init(swiotlb, flags);
 	swiotlb_update_mem_attributes();
 
-	/* this will put all unused low memory onto the freelists */
-	memblock_free_all();
-
 	/*
 	 * Check boundaries twice: Some fundamental inconsistencies can be
 	 * detected at build time already.
@@ -414,6 +406,17 @@ void __init mem_init(void)
 	}
 }
 
+/*
+ * mem_init() marks the free areas in the mem_map and tells us how much memory
+ * is free.  This is done after various parts of the system have claimed their
+ * memory after the kernel image.
+ */
+void __init mem_init(void)
+{
+	/* this will put all unused low memory onto the freelists */
+	memblock_free_all();
+}
+
 void free_initmem(void)
 {
 	void *lm_init_begin = lm_alias(__init_begin);

arch/mips/mm/init.c

@@ -425,7 +425,7 @@ void __init paging_init(void)
 static struct kcore_list kcore_kseg0;
 #endif
 
-void __init mem_init(void)
+void __init arch_mm_preinit(void)
 {
 	/*
 	 * When PFN_PTE_SHIFT is greater than PAGE_SHIFT we won't have enough PTE
@@ -435,7 +435,6 @@ void __init mem_init(void)
 
 	maar_init();
 	setup_zero_pages();	/* Setup zeroed pages.  */
-	memblock_free_all();
 
 #ifdef CONFIG_64BIT
 	if ((unsigned long) &_text > (unsigned long) CKSEG0)
@@ -446,13 +445,17 @@ void __init mem_init(void)
 #endif
 }
 #else  /* CONFIG_NUMA */
-void __init mem_init(void)
+void __init arch_mm_preinit(void)
 {
 	setup_zero_pages();	/* This comes from node 0 */
-	memblock_free_all();
 }
 #endif /* !CONFIG_NUMA */
 
+void __init mem_init(void)
+{
+	memblock_free_all();
+}
+
 void free_init_pages(const char *what, unsigned long begin, unsigned long end)
 {
 	unsigned long pfn;

arch/powerpc/mm/mem.c

@@ -273,7 +273,7 @@ void __init paging_init(void)
 	mark_nonram_nosave();
 }
 
-void __init mem_init(void)
+void __init arch_mm_preinit(void)
 {
 	/*
 	 * book3s is limited to 16 page sizes due to encoding this in
@@ -295,8 +295,6 @@ void __init mem_init(void)
 
 	kasan_late_init();
 
-	memblock_free_all();
-
 #if defined(CONFIG_PPC_E500) && !defined(CONFIG_SMP)
 	/*
 	 * If smp is enabled, next_tlbcam_idx is initialized in the cpu up
@@ -329,6 +327,11 @@ void __init mem_init(void)
 #endif /* CONFIG_PPC32 */
 }
 
+void __init mem_init(void)
+{
+	memblock_free_all();
+}
+
 void free_initmem(void)
 {
 	ppc_md.progress = ppc_printk_progress;

arch/riscv/mm/init.c

@@ -171,7 +171,7 @@ static void __init print_vm_layout(void)
 static void print_vm_layout(void) { }
 #endif /* CONFIG_DEBUG_VM */
 
-void __init mem_init(void)
+void __init arch_mm_preinit(void)
 {
 	bool swiotlb = max_pfn > PFN_DOWN(dma32_phys_limit);
 #ifdef CONFIG_FLATMEM
@@ -192,11 +192,15 @@ void __init mem_init(void)
 	}
 
 	swiotlb_init(swiotlb, SWIOTLB_VERBOSE);
-	memblock_free_all();
 
 	print_vm_layout();
 }
 
+void __init mem_init(void)
+{
+	memblock_free_all();
+}
+
 /* Limit the memory size via mem. */
 static phys_addr_t memory_limit;
 #ifdef CONFIG_XIP_KERNEL

arch/s390/mm/init.c

@@ -154,7 +154,7 @@ static void pv_init(void)
 	swiotlb_update_mem_attributes();
 }
 
-void __init mem_init(void)
+void __init arch_mm_preinit(void)
 {
 	cpumask_set_cpu(0, &init_mm.context.cpu_attach_mask);
 	cpumask_set_cpu(0, mm_cpumask(&init_mm));
@@ -163,7 +163,10 @@ void __init mem_init(void)
 	kfence_split_mapping();
 
 	setup_zero_pages();	/* Setup zeroed pages. */
+}
 
+void __init mem_init(void)
+{
 	/* this will put all low memory onto the freelists */
 	memblock_free_all();
 }

arch/sparc/mm/init_32.c

@@ -232,7 +232,7 @@ static void __init taint_real_pages(void)
 	}
 }
 
-void __init mem_init(void)
+void __init arch_mm_preinit(void)
 {
 	int i;
 
@@ -262,7 +262,10 @@ void __init mem_init(void)
 	memset(sparc_valid_addr_bitmap, 0, i << 2);
 
 	taint_real_pages();
+}
 
+void __init mem_init(void)
+{
 	memblock_free_all();
 }
 

arch/um/kernel/mem.c

@@ -54,7 +54,7 @@ int kmalloc_ok = 0;
 /* Used during early boot */
 static unsigned long brk_end;
 
-void __init mem_init(void)
+void __init arch_mm_preinit(void)
 {
 	/* clear the zero-page */
 	memset(empty_zero_page, 0, PAGE_SIZE);
@@ -66,10 +66,13 @@ void __init mem_init(void)
 	map_memory(brk_end, __pa(brk_end), uml_reserved - brk_end, 1, 1, 0);
 	memblock_free((void *)brk_end, uml_reserved - brk_end);
 	uml_reserved = brk_end;
+	max_pfn = max_low_pfn;
+}
 
+void __init mem_init(void)
+{
 	/* this will put all low memory onto the freelists */
 	memblock_free_all();
-	max_pfn = max_low_pfn;
 	kmalloc_ok = 1;
 }
 

arch/x86/mm/init_32.c

@@ -691,13 +691,17 @@ static void __init test_wp_bit(void)
 	panic("Linux doesn't support CPUs with broken WP.");
 }
 
-void __init mem_init(void)
+void __init arch_mm_preinit(void)
 {
 	pci_iommu_alloc();
 
 #ifdef CONFIG_FLATMEM
 	BUG_ON(!mem_map);
 #endif
+}
+
+void __init mem_init(void)
+{
 	/* this will put all low memory onto the freelists */
 	memblock_free_all();
 

arch/x86/mm/init_64.c

@@ -1348,10 +1348,13 @@ failed:
 	panic("Failed to pre-allocate %s pages for vmalloc area\n", lvl);
 }
 
-void __init mem_init(void)
+void __init arch_mm_preinit(void)
 {
 	pci_iommu_alloc();
+}
 
+void __init mem_init(void)
+{
 	/* clear_bss() already clear the empty_zero_page */
 
 	/* this will put all memory onto the freelists */

include/linux/mm.h

@@ -43,6 +43,7 @@ struct folio_batch;
 
 extern int sysctl_page_lock_unfairness;
 
+void arch_mm_preinit(void);
 void mm_core_init(void);
 void init_mm_internals(void);
 

mm/mm_init.c

@@ -2734,11 +2734,16 @@ static void __init mem_init_print_info(void)
 		);
 }
 
+void __init __weak arch_mm_preinit(void)
+{
+}
+
 /*
  * Set up kernel memory allocators
  */
 void __init mm_core_init(void)
 {
+	arch_mm_preinit();
 	hugetlb_bootmem_alloc();
 
 	/* Initializations relying on SMP setup */