Re: [PATCH bpf 2/4] vmalloc: introduce HAVE_ARCH_HUGE_VMALLOC_FLAG

["Edgecombe, Rick P" <rick.p.edgecombe@intel.com>]

On Wed, 2022-03-30 at 15:56 -0700, Song Liu wrote:
> With HAVE_ARCH_HUGE_VMALLOC_FLAG, users of __vmalloc_node_range()
> could
> use VM_TRY_HUGE_VMAP to (try to) allocate PMD_SIZE pages for
> size >= PMD_SIZE cases. Similar to HAVE_ARCH_HUGE_VMALLOC, the use
> can
> disable huge page by specifying nohugeiomap in kernel command line.
> 
> The first user of VM_TRY_HUGE_VMAP will be bpf_prog_pack.
> 
> Signed-off-by: Song Liu <song@kernel.org>
> ---
>  arch/Kconfig            |  9 +++++++++
>  include/linux/vmalloc.h |  9 +++++++--
>  mm/vmalloc.c            | 28 +++++++++++++++++++---------
>  3 files changed, 35 insertions(+), 11 deletions(-)
> 
> diff --git a/arch/Kconfig b/arch/Kconfig
> index 33e06966f248..23b6e92aebaa 100644
> --- a/arch/Kconfig
> +++ b/arch/Kconfig
> @@ -864,6 +864,15 @@ config HAVE_ARCH_HUGE_VMALLOC
>  	depends on HAVE_ARCH_HUGE_VMAP
>  	bool
>  
> +#
> +# HAVE_ARCH_HUGE_VMALLOC_FLAG allows users of __vmalloc_node_range
> to allocate
> +# huge page without HAVE_ARCH_HUGE_VMALLOC. To allocate huge pages,
> the user
> +# need to call __vmalloc_node_range with VM_TRY_HUGE_VMAP.
> +#
> +config HAVE_ARCH_HUGE_VMALLOC_FLAG
> +	depends on HAVE_ARCH_HUGE_VMAP
> +	bool
> +
>  config ARCH_WANT_HUGE_PMD_SHARE
>  	bool
>  
> diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
> index 3b1df7da402d..a48d0690b66f 100644
> --- a/include/linux/vmalloc.h
> +++ b/include/linux/vmalloc.h
> @@ -35,6 +35,11 @@ struct notifier_block;		/* in
> notifier.h */
>  #define VM_DEFER_KMEMLEAK	0
>  #endif
>  
> +#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG
> +#define VM_TRY_HUGE_VMAP	0x00001000	/* Allow for huge
> pages on HAVE_ARCH_HUGE_VMALLOC_FLAG arch's */
> +#else
> +#define VM_TRY_HUGE_VMAP	0
> +#endif
>  /* bits [20..32] reserved for arch specific ioremap internals */
>  
>  /*
> @@ -51,7 +56,7 @@ struct vm_struct {
>  	unsigned long		size;
>  	unsigned long		flags;
>  	struct page		**pages;
> -#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
> +#if (defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC) ||
> defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG))
>  	unsigned int		page_order;
>  #endif
>  	unsigned int		nr_pages;
> @@ -225,7 +230,7 @@ static inline bool is_vm_area_hugepages(const
> void *addr)
>  	 * prevents that. This only indicates the size of the physical
> page
>  	 * allocated in the vmalloc layer.
>  	 */
> -#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
> +#if (defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC) ||
> defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG))

Since HAVE_ARCH_HUGE_VMALLOC_FLAG depends on HAVE_ARCH_HUGE_VMAP, I
don't think you need both here.

>  	return find_vm_area(addr)->page_order > 0;
>  #else
>  	return false;
> diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> index e163372d3967..179200bce285 100644
> --- a/mm/vmalloc.c
> +++ b/mm/vmalloc.c
> @@ -46,7 +46,7 @@
>  #include "internal.h"
>  #include "pgalloc-track.h"
>  
> -#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
> +#if (defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC) ||
> defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG))

Same as above.

>  static unsigned int __ro_after_init ioremap_max_page_shift =
> BITS_PER_LONG - 1;
>  
>  static int __init set_nohugeiomap(char *str)
> @@ -55,11 +55,11 @@ static int __init set_nohugeiomap(char *str)
>  	return 0;
>  }
>  early_param("nohugeiomap", set_nohugeiomap);
> -#else /* CONFIG_HAVE_ARCH_HUGE_VMAP */
> +#else /* CONFIG_HAVE_ARCH_HUGE_VMAP ||
> CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG */
>  static const unsigned int ioremap_max_page_shift = PAGE_SHIFT;
> -#endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP */
> +#endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP ||
> CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG*/

Same here, and for the rest below. I think having
HAVE_ARCH_HUGE_VMALLOC_FLAG depend on HAVE_ARCH_HUGE_VMAP like you did
is nice because you don't need to special logic for most of the huge
page parts. It should shrink this patch.

>  
> -#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
> +#if (defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC) || 
> defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG))
>  static bool __ro_after_init vmap_allow_huge = true;
>  
>  static int __init set_nohugevmalloc(char *str)
> @@ -582,8 +582,9 @@ int vmap_pages_range_noflush(unsigned long addr,
> unsigned long end,
>  
>  	WARN_ON(page_shift < PAGE_SHIFT);
>  
> -	if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMALLOC) ||
> -			page_shift == PAGE_SHIFT)
> +	if ((!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMALLOC) &&
> +	     !IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG)) ||
> +	    (page_shift == PAGE_SHIFT))
>  		return vmap_small_pages_range_noflush(addr, end, prot,
> pages);
>  
>  	for (i = 0; i < nr; i += 1U << (page_shift - PAGE_SHIFT)) {
> @@ -2252,7 +2253,7 @@ static struct vm_struct *vmlist __initdata;
>  
>  static inline unsigned int vm_area_page_order(struct vm_struct *vm)
>  {
> -#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
> +#if (defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC) ||
> defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG))
>  	return vm->page_order;
>  #else
>  	return 0;
> @@ -2261,7 +2262,7 @@ static inline unsigned int
> vm_area_page_order(struct vm_struct *vm)
>  
>  static inline void set_vm_area_page_order(struct vm_struct *vm,
> unsigned int order)
>  {
> -#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
> +#if (defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC) ||
> defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG))
>  	vm->page_order = order;
>  #else
>  	BUG_ON(order != 0);
> @@ -3056,6 +3057,15 @@ static void *__vmalloc_area_node(struct
> vm_struct *area, gfp_t gfp_mask,
>  	return NULL;
>  }
>  
> +static bool vmalloc_try_huge_page(unsigned long vm_flags)
> +{
> +	if (!vmap_allow_huge || (vm_flags & VM_NO_HUGE_VMAP))
> +		return false;
> +
> +	/* VM_TRY_HUGE_VMAP only works for
> CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG */
> +	return vm_flags & VM_TRY_HUGE_VMAP;
> +}
> +

It won't return true in the case of just CONFIG_HAVE_ARCH_HUGE_VMALLOC
and vmap_allow_huge. If you have CONFIG_HAVE_ARCH_HUGE_VMALLOC, but not
CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG like powerpc, it should still try
huge pages like before.

>  /**
>   * __vmalloc_node_range - allocate virtually contiguous memory
>   * @size:		  allocation size
> @@ -3106,7 +3116,7 @@ void *__vmalloc_node_range(unsigned long size,
> unsigned long align,
>  		return NULL;
>  	}
>  
> -	if (vmap_allow_huge && !(vm_flags & VM_NO_HUGE_VMAP)) {
> +	if (vmalloc_try_huge_page(vm_flags)) {
>  		unsigned long size_per_node;
>  
>  		/*