Re: [RFC PATCH 5/7] x86: Call preallocate_vmalloc_pages() later

[Anshuman Khandual <anshuman.khandual@arm.com>]

On 20/10/25 5:46 AM, Matthew Wilcox (Oracle) wrote:
> When separately allocating ptdesc from struct page, calling
> preallocate_vmalloc_pages() from mem_init() is too early as the slab
> allocator hasn't been set up yet.  Move preallocate_vmalloc_pages() to
> vmalloc_init() which is called after the slab allocator has been set up.
> 
> Honestly, this patch is a bit bobbins and I'm sure it'll be reworked
> before it goes upstream.
> 
> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
> ---
>  arch/x86/mm/init_64.c |  4 +---
>  include/linux/mm.h    | 33 +++++++++++++++++++++++++++++++--
>  mm/vmalloc.c          |  2 ++
>  3 files changed, 34 insertions(+), 5 deletions(-)
> 
> diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
> index 0e4270e20fad..5270fc24f6f6 100644
> --- a/arch/x86/mm/init_64.c
> +++ b/arch/x86/mm/init_64.c
> @@ -1322,7 +1322,7 @@ static void __init register_page_bootmem_info(void)
>   * Only the level which needs to be synchronized between all page-tables is
>   * allocated because the synchronization can be expensive.
>   */
> -static void __init preallocate_vmalloc_pages(void)
> +void __init preallocate_vmalloc_pages(void)
>  {
>  	unsigned long addr;
>  	const char *lvl;
> @@ -1390,8 +1390,6 @@ void __init mem_init(void)
>  	/* Register memory areas for /proc/kcore */
>  	if (get_gate_vma(&init_mm))
>  		kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, PAGE_SIZE, KCORE_USER);
> -
> -	preallocate_vmalloc_pages();
>  }
>  
>  int kernel_set_to_readonly;
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index edcb7d75542f..e60b181da3df 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -1160,6 +1160,12 @@ static inline int is_vmalloc_or_module_addr(const void *x)
>  }
>  #endif
>  
> +#ifdef CONFIG_X86
> +void __init preallocate_vmalloc_pages(void);
> +#else
> +static inline void preallocate_vmalloc_pages(void) { }
> +#endif
> +
>  /*
>   * How many times the entire folio is mapped as a single unit (eg by a
>   * PMD or PUD entry).  This is probably not what you want, except for
> @@ -2939,9 +2945,32 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a
>  }
>  #endif /* CONFIG_MMU */
>  
> +static inline struct page *ptdesc_page(const struct ptdesc *pt)
> +{
> +	return pt->pt_page;
> +}

pt_page has not been added as an element into ptdesc and hence
the build fails upto this patch.
> +
> +static inline struct ptdesc *page_ptdesc(const struct page *page)
> +{
> +	memdesc_t memdesc = READ_ONCE(page->memdesc);
> +
> +	if (memdesc_type(memdesc) != MEMDESC_TYPE_PAGE_TABLE) {
> +		printk(KERN_EMERG "memdesc %lx index %lx\n", memdesc.v, page->__folio_index);
> +		VM_BUG_ON_PAGE(1, page);
> +		return NULL;
> +	}
> +	return (void *)(memdesc.v - MEMDESC_TYPE_PAGE_TABLE);
> +}

Ditto - these elements have not been introduced.
> +
> +/**
> + * enum pt_flags = How the ptdesc flags bits are used.
> + * @PT_reserved: Used by PowerPC
> + *
> + * The pt flags are stored in a memdesc_flags_t.
> + * The high bits are used for information like zone/node/section.
> + */
>  enum pt_flags {
>  	PT_reserved = PG_reserved,
> -	/* High bits are used for zone/node/section */
>  };
>  
>  static inline struct ptdesc *virt_to_ptdesc(const void *x)
> @@ -2957,7 +2986,7 @@ static inline struct ptdesc *virt_to_ptdesc(const void *x)
>   */
>  static inline void *ptdesc_address(const struct ptdesc *pt)
>  {
> -	return folio_address(ptdesc_folio(pt));
> +	return page_address(pt->pt_page);
>  }
>  
>  static inline bool pagetable_is_reserved(struct ptdesc *pt)
> diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> index 798b2ed21e46..9b349051a83a 100644
> --- a/mm/vmalloc.c
> +++ b/mm/vmalloc.c
> @@ -5264,6 +5264,8 @@ void __init vmalloc_init(void)
>  	struct vm_struct *tmp;
>  	int i;
>  
> +	preallocate_vmalloc_pages();
> +
>  	/*
>  	 * Create the cache for vmap_area objects.
>  	 */