Re: [PATCH v4 RESEND 1/2] thp, dax: add thp_get_unmapped_area for pmd mappings

[Dan Williams]

On Mon, Aug 29, 2016 at 1:44 PM, Kani, Toshimitsu <toshi.kani@xxxxxxx> wrote:
> On Mon, 2016-08-29 at 12:34 -0700, Dan Williams wrote:
>> On Mon, Aug 29, 2016 at 12:11 PM, Toshi Kani <toshi.kani@xxxxxxx>
>> wrote:
>> >
>> > When CONFIG_FS_DAX_PMD is set, DAX supports mmap() using pmd page
>> > size.  This feature relies on both mmap virtual address and FS
>> > block (i.e. physical address) to be aligned by the pmd page size.
>> > Users can use mkfs options to specify FS to align block
>> > allocations. However, aligning mmap address requires code changes
>> > to existing applications for providing a pmd-aligned address to
>> > mmap().
>> >
>> > For instance, fio with "ioengine=mmap" performs I/Os with mmap()
>> > [1]. It calls mmap() with a NULL address, which needs to be changed
>> > to provide a pmd-aligned address for testing with DAX pmd mappings.
>> > Changing all applications that call mmap() with NULL is
>> > undesirable.
>> >
>> > Add thp_get_unmapped_area(), which can be called by filesystem's
>> > get_unmapped_area to align an mmap address by the pmd size for
>> > a DAX file.  It calls the default handler, mm->get_unmapped_area(),
>> > to find a range and then aligns it for a DAX file.
>> >
>> > The patch is based on Matthew Wilcox's change that allows adding
>> > support of the pud page size easily.
>  :
>>
>> Reviewed-by: Dan Williams <dan.j.williams@xxxxxxxxx>
>
> Great!
>
>> ...with one minor nit:
>>
>>
>> >
>> >  include/linux/huge_mm.h |    7 +++++++
>> >  mm/huge_memory.c        |   43
>> > +++++++++++++++++++++++++++++++++++++++++++
>> >  2 files changed, 50 insertions(+)
>> >
>> > diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
>> > index 6f14de4..4fca526 100644
>> > --- a/include/linux/huge_mm.h
>> > +++ b/include/linux/huge_mm.h
>> > @@ -87,6 +87,10 @@ extern bool is_vma_temporary_stack(struct
>> > vm_area_struct *vma);
>> >
>> >  extern unsigned long transparent_hugepage_flags;
>> >
>> > +extern unsigned long thp_get_unmapped_area(struct file *filp,
>> > +               unsigned long addr, unsigned long len, unsigned
>> > long pgoff,
>> > +               unsigned long flags);
>> > +
>> >  extern void prep_transhuge_page(struct page *page);
>> >  extern void free_transhuge_page(struct page *page);
>> >
>> > @@ -169,6 +173,9 @@ void put_huge_zero_page(void);
>> >  static inline void prep_transhuge_page(struct page *page) {}
>> >
>> >  #define transparent_hugepage_flags 0UL
>> > +
>> > +#define thp_get_unmapped_area  NULL
>>
>> Lets make this:
>>
>> static inline unsigned long thp_get_unmapped_area(struct file *filp,
>>                unsigned long addr, unsigned long len, unsigned long
>> pgoff,
>>                unsigned long flags)
>> {
>>     return 0;
>> }
>>
>> ...to get some type checking in the CONFIG_TRANSPARENT_HUGEPAGE=n
>> case.
>>
>
> Per get_unmapped_area() in mm/mmap.c, I think we need to set it to NULL
> when we do not override current->mm->get_unmapped_area.

Ah, ok.