Re: [PATCH v9 1/8] mm: introduce FOLL_PCI_P2PDMA to gate getting PCI P2PDMA pages

[John Hubbard]

On 8/25/22 08:24, Logan Gunthorpe wrote:
> GUP Callers that expect PCI P2PDMA pages can now set FOLL_PCI_P2PDMA to
> allow obtaining P2PDMA pages. If GUP is called without the flag and a
> P2PDMA page is found, it will return an error.
> 
> FOLL_PCI_P2PDMA cannot be set if FOLL_LONGTERM is set.
> 
> Signed-off-by: Logan Gunthorpe <logang@xxxxxxxxxxxx>
> Reviewed-by: Christoph Hellwig <hch@xxxxxx>
> ---
>  include/linux/mm.h |  1 +
>  mm/gup.c           | 22 +++++++++++++++++++++-
>  2 files changed, 22 insertions(+), 1 deletion(-)
> 

Looks good. And I see that Dan Williams' upcoming "Fix the DAX-gup
mistake" series will remove the need for most (all?) of the
undo_dev_pagemap() calls that you have to make here, so the end result
will be even simpler.


Reviewed-by: John Hubbard <jhubbard@xxxxxxxxxx>

thanks,

-- 
John Hubbard
NVIDIA

> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 3bedc449c14d..37a3e91e6e77 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -2891,6 +2891,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
>  #define FOLL_SPLIT_PMD	0x20000	/* split huge pmd before returning */
>  #define FOLL_PIN	0x40000	/* pages must be released via unpin_user_page */
>  #define FOLL_FAST_ONLY	0x80000	/* gup_fast: prevent fall-back to slow gup */
> +#define FOLL_PCI_P2PDMA	0x100000 /* allow returning PCI P2PDMA pages */
>  
>  /*
>   * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each
> diff --git a/mm/gup.c b/mm/gup.c
> index 732825157430..79aea452619e 100644
> --- a/mm/gup.c
> +++ b/mm/gup.c
> @@ -566,6 +566,12 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
>  		goto out;
>  	}
>  
> +	if (unlikely(!(flags & FOLL_PCI_P2PDMA) &&
> +		     is_pci_p2pdma_page(page))) {
> +		page = ERR_PTR(-EREMOTEIO);
> +		goto out;
> +	}
> +
>  	VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) &&
>  		       !PageAnonExclusive(page), page);
>  
> @@ -1015,6 +1021,9 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
>  	if ((gup_flags & FOLL_LONGTERM) && vma_is_fsdax(vma))
>  		return -EOPNOTSUPP;
>  
> +	if ((gup_flags & FOLL_LONGTERM) && (gup_flags & FOLL_PCI_P2PDMA))
> +		return -EOPNOTSUPP;
> +
>  	if (vma_is_secretmem(vma))
>  		return -EFAULT;
>  
> @@ -2359,6 +2368,10 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
>  		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
>  		page = pte_page(pte);
>  
> +		if (unlikely(!(flags & FOLL_PCI_P2PDMA) &&
> +			     is_pci_p2pdma_page(page)))
> +			goto pte_unmap;
> +
>  		folio = try_grab_folio(page, 1, flags);
>  		if (!folio)
>  			goto pte_unmap;
> @@ -2438,6 +2451,12 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr,
>  			undo_dev_pagemap(nr, nr_start, flags, pages);
>  			break;
>  		}
> +
> +		if (!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page)) {
> +			undo_dev_pagemap(nr, nr_start, flags, pages);
> +			break;
> +		}
> +
>  		SetPageReferenced(page);
>  		pages[*nr] = page;
>  		if (unlikely(!try_grab_page(page, flags))) {
> @@ -2926,7 +2945,8 @@ static int internal_get_user_pages_fast(unsigned long start,
>  
>  	if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM |
>  				       FOLL_FORCE | FOLL_PIN | FOLL_GET |
> -				       FOLL_FAST_ONLY | FOLL_NOFAULT)))
> +				       FOLL_FAST_ONLY | FOLL_NOFAULT |
> +				       FOLL_PCI_P2PDMA)))
>  		return -EINVAL;
>  
>  	if (gup_flags & FOLL_PIN)