Re: [PATCH v2 22/28] arch, mm: consolidate initialization of nodes, zones and memory map

Hi,

On 2026-01-02 08:59:58 +0200, Mike Rapoport wrote:
> From: "Mike Rapoport (Microsoft)" <[email protected]>
> 
> To initialize node, zone and memory map data structures every architecture
> calls free_area_init() during setup_arch() and passes it an array of zone
> limits.
> 
> Beside code duplication it creates "interesting" ordering cases between
> allocation and initialization of hugetlb and the memory map. Some
> architectures allocate hugetlb pages very early in setup_arch() in certain
> cases, some only create hugetlb CMA areas in setup_arch() and sometimes
> hugetlb allocations happen mm_core_init().
> 
> With arch_zone_limits_init() helper available now on all architectures it
> is no longer necessary to call free_area_init() from architecture setup
> code. Rather core MM initialization can call arch_zone_limits_init() in a
> single place.
> 
> This allows to unify ordering of hugetlb vs memory map allocation and
> initialization.
> 
> Remove the call to free_area_init() from architecture specific code and
> place it in a new mm_core_init_early() function that is called immediately
> after setup_arch().
> 
> After this refactoring it is possible to consolidate hugetlb allocations
> and eliminate differences in ordering of hugetlb and memory map
> initialization among different architectures.
> 
> As the first step of this consolidation move hugetlb_bootmem_alloc() to
> mm_core_early_init().
> 
> Signed-off-by: Mike Rapoport (Microsoft) <[email protected]>

This breaks boot on my Raspberry Pi 1. The reason seems to be the use of
page_folio() when initializing the dynamically allocated zero page in
arm, which doesn't work when free_area_init() hasn't been called yet.

The following oopses are generated:

 Booting Linux on physical CPU 0x0
 Linux version 6.19.0-rc3-03898-g7975b0084358 ([email protected]) (armv6j-unknown-linux-gnueabihf-gcc (Gentoo 15.2.1_p20251122 p3) 15.2.1 20251122, GNU ld (Gentoo 2.45.1 p1) 2.45.1) #451 Fri Jan  2 20:26:00 CET 2026
 CPU: ARMv6-compatible processor [410fb767] revision 7 (ARMv7), cr=00c5387d
 CPU: PIPT / VIPT nonaliasing data cache, VIPT nonaliasing instruction cache
 OF: fdt: Machine model: Raspberry Pi Model B Rev 2
 earlycon: pl11 at MMIO32 0x20201000 (options '')
 printk: legacy bootconsole [pl11] enabled
 Memory policy: Data cache writeback
 Reserved memory: created CMA memory pool at 0x19400000, size 64 MiB
 OF: reserved mem: initialized node linux,cma, compatible id shared-dma-pool
 OF: reserved mem: 0x19400000..0x1d3fffff (65536 KiB) map reusable linux,cma
 8<--- cut here ---
 Unable to handle kernel paging request at virtual address 003dfb44 when read
 [003dfb44] *pgd=00000000
 Internal error: Oops: 5 [#1] ARM
 CPU: 0 UID: 0 PID: 0 Comm: swapper Not tainted 6.19.0-rc3-03898-g7975b0084358 #451 NONE
 Hardware name: BCM2835
 PC is at paging_init (include/linux/page-flags.h:284 (discriminator 2) arch/arm/mm/mmu.c:1790 (discriminator 2))
 LR is at paging_init (arch/arm/mm/mmu.c:1789 (discriminator 1))
 pc :    lr :    psr: 600000d3
 sp : c0d01ef8  ip : defdb000  fp : 0000000b
 r10: 00200000  r9 : d9400000  r8 : ffe00000
 r7 : c0d09050  r6 : c0d0902c  r5 : c0d43d40  r4 : 0001efda
 r3 : c0dab20c  r2 : 00000000  r1 : 003dfb40  r0 : 00000000
 Flags: nZCv  IRQs off  FIQs off  Mode SVC_32  ISA ARM  Segment none
 Control: 00c5387d  Table: 00004008  DAC: 00000051
 Register r0 information: NULL pointer
 Register r1 information: non-paged memory
 Register r2 information: NULL pointer
 Register r3 information:
 8<--- cut here ---
 Unable to handle kernel paging request at virtual address 0001b564 when read
 [0001b564] *pgd=00000000
 Internal error: Oops: 5 [#2] ARM
 CPU: 0 UID: 0 PID: 0 Comm: swapper Not tainted 6.19.0-rc3-03898-g7975b0084358 #451 NONE
 Hardware name: BCM2835
 PC is at kmem_dump_obj (mm/slab.h:142 (discriminator 2) mm/slab.h:178 (discriminator 2) mm/slab_common.c:609 (discriminator 2))
 LR is at 0x1
 pc :    lr :    psr: 200001d3
 sp : c0d01cc8  ip : 00000000  fp : 0000000b
 r10: 00200000  r9 : c0dab1dc  r8 : 00000000
 r7 : 00000005  r6 : 00000dab  r5 : 0001b560  r4 : c0dab20c
 r3 : c0dc2058  r2 : 1f000000  r1 : 00c00000  r0 : 00000001
 Flags: nzCv  IRQs off  FIQs off  Mode SVC_32  ISA ARM  Segment none
 Control: 00c5387d  Table: 00004008  DAC: 00000051
 Register r0 information: non-paged memory
 Register r1 information: non-paged memory
 Register r2 information: non-paged memory
 Register r3 information:
 8<--- cut here ---

and the second one repeats for some time afterwards.

I experimented a little by allocating the zero page statically as many
other arches do which fixes the issue as it does not need to be
initialized at this point anymore, though I have no idea if that's
appropriate.

Regards,
Klara Modin

...

> diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
> index bdcc3639681f..a8f7b4084715 100644
> --- a/arch/arm/mm/init.c
> +++ b/arch/arm/mm/init.c
> @@ -118,15 +118,6 @@ void __init arch_zone_limits_init(unsigned long *max_zone_pfn)
>  #endif
>  }
>  
> -static void __init zone_sizes_init(unsigned long min, unsigned long max_low,
> -	unsigned long max_high)
> -{
> -	unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0 };
> -
> -	arch_zone_limits_init(max_zone_pfn);
> -	free_area_init(max_zone_pfn);
> -}
> -
>  #ifdef CONFIG_HAVE_ARCH_PFN_VALID
>  int pfn_valid(unsigned long pfn)
>  {
> @@ -222,13 +213,6 @@ void __init bootmem_init(void)
>  	 * done after the fixed reservations
>  	 */
>  	sparse_init();
> -
> -	/*
> -	 * Now free the memory - free_area_init needs
> -	 * the sparse mem_map arrays initialized by sparse_init()
> -	 * for memmap_init_zone(), otherwise all PFNs are invalid.
> -	 */
> -	zone_sizes_init(min_low_pfn, max_low_pfn, max_pfn);
>  }
>  
>  /*

...

> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 628c0e0ac313..64d6f9c15ef1 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -45,6 +45,7 @@ struct pt_regs;
>  struct folio_batch;
>  
>  void arch_mm_preinit(void);
> +void mm_core_init_early(void);
>  void mm_core_init(void);
>  void init_mm_internals(void);
>  
> @@ -3536,7 +3537,7 @@ static inline unsigned long get_num_physpages(void)
>  }
>  
>  /*
> - * Using memblock node mappings, an architecture may initialise its
> + * FIXME: Using memblock node mappings, an architecture may initialise its
>   * zones, allocate the backing mem_map and account for memory holes in an
>   * architecture independent manner.
>   *
> @@ -3551,7 +3552,6 @@ static inline unsigned long get_num_physpages(void)
>   *	memblock_add_node(base, size, nid, MEMBLOCK_NONE)
>   * free_area_init(max_zone_pfns);
>   */
> -void free_area_init(unsigned long *max_zone_pfn);
>  void arch_zone_limits_init(unsigned long *max_zone_pfn);
>  unsigned long node_map_pfn_alignment(void);
>  extern unsigned long absent_pages_in_range(unsigned long start_pfn,
> diff --git a/init/main.c b/init/main.c
> index b84818ad9685..445b5643ecec 100644
> --- a/init/main.c
> +++ b/init/main.c
> @@ -1025,6 +1025,7 @@ void start_kernel(void)
>  	page_address_init();
>  	pr_notice("%s", linux_banner);
>  	setup_arch(&command_line);
> +	mm_core_init_early();
>  	/* Static keys and static calls are needed by LSMs */
>  	jump_label_init();
>  	static_call_init();
> diff --git a/mm/mm_init.c b/mm/mm_init.c
> index fc2a6f1e518f..ffc4a0f1fee9 100644
> --- a/mm/mm_init.c
> +++ b/mm/mm_init.c
> @@ -1810,7 +1810,6 @@ static void __init set_high_memory(void)
>  
>  /**
>   * free_area_init - Initialise all pg_data_t and zone data
> - * @max_zone_pfn: an array of max PFNs for each zone
>   *
>   * This will call free_area_init_node() for each active node in the system.
>   * Using the page ranges provided by memblock_set_node(), the size of each
> @@ -1821,17 +1820,14 @@ static void __init set_high_memory(void)
>   * starts where the previous one ended. For example, ZONE_DMA32 starts
>   * at arch_max_dma_pfn.
>   */
> -void __init free_area_init(unsigned long *max_zone_pfn)
> +static void __init free_area_init(void)
>  {
> +	unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0 };
>  	unsigned long start_pfn, end_pfn;
>  	int i, nid, zone;
>  	bool descending;
>  
> -	/* Record where the zone boundaries are */
> -	memset(arch_zone_lowest_possible_pfn, 0,
> -				sizeof(arch_zone_lowest_possible_pfn));
> -	memset(arch_zone_highest_possible_pfn, 0,
> -				sizeof(arch_zone_highest_possible_pfn));
> +	arch_zone_limits_init(max_zone_pfn);
>  
>  	start_pfn = PHYS_PFN(memblock_start_of_DRAM());
>  	descending = arch_has_descending_max_zone_pfns();
> @@ -2681,13 +2677,19 @@ void __init __weak mem_init(void)
>  {
>  }
>  
> +void __init mm_core_init_early(void)
> +{
> +	hugetlb_bootmem_alloc();
> +
> +	free_area_init();
> +}
> +
>  /*
>   * Set up kernel memory allocators
>   */
>  void __init mm_core_init(void)
>  {
>  	arch_mm_preinit();
> -	hugetlb_bootmem_alloc();
>  
>  	/* Initializations relying on SMP setup */
>  	BUILD_BUG_ON(MAX_ZONELISTS > 2);
> -- 
> 2.51.0
>