On Tue, May 14, 2013 at 10:57:29AM +0900, HATAYAMA Daisuke wrote:
> We want to allocate ELF note segment buffer on the 2nd kernel in
> vmalloc space and remap it to user-space in order to reduce the risk
> that memory allocation fails on system with huge number of CPUs and so
> with huge ELF note segment that exceeds 11-order block size.
> 
> Although there's already remap_vmalloc_range for the purpose of
> remapping vmalloc memory to user-space, we need to specify user-space
> range via vma. Mmap on /proc/vmcore needs to remap range across
> multiple objects, so the interface that requires vma to cover full
> range is problematic.
> 
> This patch introduces remap_vmalloc_range_partial that receives
> user-space range as a pair of base address and size and can be used
> for mmap on /proc/vmcore case.
> 
> remap_vmalloc_range is rewritten using remap_vmalloc_range_partial.
> 
> Signed-off-by: HATAYAMA Daisuke <[email protected]>

This also needs ACK of VM folks. CCing some of them.

Thanks
Vivek

> ---
> 
>  include/linux/vmalloc.h |    4 +++
>  mm/vmalloc.c            |   63 
> +++++++++++++++++++++++++++++++++--------------
>  2 files changed, 48 insertions(+), 19 deletions(-)
> 
> diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
> index 7d5773a..dd0a2c8 100644
> --- a/include/linux/vmalloc.h
> +++ b/include/linux/vmalloc.h
> @@ -82,6 +82,10 @@ extern void *vmap(struct page **pages, unsigned int count,
>                       unsigned long flags, pgprot_t prot);
>  extern void vunmap(const void *addr);
>  
> +extern int remap_vmalloc_range_partial(struct vm_area_struct *vma,
> +                                    unsigned long uaddr, void *kaddr,
> +                                    unsigned long size);
> +

>  extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
>                                                       unsigned long pgoff);
>  void vmalloc_sync_all(void);
> diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> index 3875fa2..d9a9f4f6 100644
> --- a/mm/vmalloc.c
> +++ b/mm/vmalloc.c
> @@ -2148,42 +2148,44 @@ finished:
>  }
>  
>  /**
> - *   remap_vmalloc_range  -  map vmalloc pages to userspace
> - *   @vma:           vma to cover (map full range of vma)
> - *   @addr:          vmalloc memory
> - *   @pgoff:         number of pages into addr before first page to map
> + *   remap_vmalloc_range_partial  -  map vmalloc pages to userspace
> + *   @vma:           vma to cover
> + *   @uaddr:         target user address to start at
> + *   @kaddr:         virtual address of vmalloc kernel memory
> + *   @size:          size of map area
>   *
>   *   Returns:        0 for success, -Exxx on failure
>   *
> - *   This function checks that addr is a valid vmalloc'ed area, and
> - *   that it is big enough to cover the vma. Will return failure if
> - *   that criteria isn't met.
> + *   This function checks that @kaddr is a valid vmalloc'ed area,
> + *   and that it is big enough to cover the range starting at
> + *   @uaddr in @vma. Will return failure if that criteria isn't
> + *   met.
>   *
>   *   Similar to remap_pfn_range() (see mm/memory.c)
>   */
> -int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
> -                                             unsigned long pgoff)
> +int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long 
> uaddr,
> +                             void *kaddr, unsigned long size)
>  {
>       struct vm_struct *area;
> -     unsigned long uaddr = vma->vm_start;
> -     unsigned long usize = vma->vm_end - vma->vm_start;
>  
> -     if ((PAGE_SIZE-1) & (unsigned long)addr)
> +     size = PAGE_ALIGN(size);
> +
> +     if (((PAGE_SIZE-1) & (unsigned long)uaddr) ||
> +         ((PAGE_SIZE-1) & (unsigned long)kaddr))
>               return -EINVAL;
>  
> -     area = find_vm_area(addr);
> +     area = find_vm_area(kaddr);
>       if (!area)
>               return -EINVAL;
>  
>       if (!(area->flags & VM_USERMAP))
>               return -EINVAL;
>  
> -     if (usize + (pgoff << PAGE_SHIFT) > area->size - PAGE_SIZE)
> +     if (kaddr + size > area->addr + area->size)
>               return -EINVAL;
>  
> -     addr += pgoff << PAGE_SHIFT;
>       do {
> -             struct page *page = vmalloc_to_page(addr);
> +             struct page *page = vmalloc_to_page(kaddr);
>               int ret;
>  
>               ret = vm_insert_page(vma, uaddr, page);
> @@ -2191,14 +2193,37 @@ int remap_vmalloc_range(struct vm_area_struct *vma, 
> void *addr,
>                       return ret;
>  
>               uaddr += PAGE_SIZE;
> -             addr += PAGE_SIZE;
> -             usize -= PAGE_SIZE;
> -     } while (usize > 0);
> +             kaddr += PAGE_SIZE;
> +             size -= PAGE_SIZE;
> +     } while (size > 0);
>  
>       vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
>  
>       return 0;
>  }
> +EXPORT_SYMBOL(remap_vmalloc_range_partial);
> +
> +/**
> + *   remap_vmalloc_range  -  map vmalloc pages to userspace
> + *   @vma:           vma to cover (map full range of vma)
> + *   @addr:          vmalloc memory
> + *   @pgoff:         number of pages into addr before first page to map
> + *
> + *   Returns:        0 for success, -Exxx on failure
> + *
> + *   This function checks that addr is a valid vmalloc'ed area, and
> + *   that it is big enough to cover the vma. Will return failure if
> + *   that criteria isn't met.
> + *
> + *   Similar to remap_pfn_range() (see mm/memory.c)
> + */
> +int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
> +                                             unsigned long pgoff)
> +{
> +     return remap_vmalloc_range_partial(vma, vma->vm_start,
> +                                        addr + (pgoff << PAGE_SHIFT),
> +                                        vma->vm_end - vma->vm_start);
> +}
>  EXPORT_SYMBOL(remap_vmalloc_range);
>  
>  /*
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Reply via email to