Re: [PATCH v2 09/11] mm/hmm: allow to mirror vma of a file on a DAX backed filesystem v2

[Jerome Glisse <jglisse@redhat.com>]

On Thu, Mar 28, 2019 at 11:04:26AM -0700, Ira Weiny wrote:
> On Mon, Mar 25, 2019 at 10:40:09AM -0400, Jerome Glisse wrote:
> > From: Jérôme Glisse <jglisse@redhat.com>
> > 
> > HMM mirror is a device driver helpers to mirror range of virtual address.
> > It means that the process jobs running on the device can access the same
> > virtual address as the CPU threads of that process. This patch adds support
> > for mirroring mapping of file that are on a DAX block device (ie range of
> > virtual address that is an mmap of a file in a filesystem on a DAX block
> > device). There is no reason to not support such case when mirroring virtual
> > address on a device.
> > 
> > Note that unlike GUP code we do not take page reference hence when we
> > back-off we have nothing to undo.
> > 
> > Changes since v1:
> >     - improved commit message
> >     - squashed: Arnd Bergmann: fix unused variable warning in hmm_vma_walk_pud
> > 
> > Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
> > Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
> > Cc: Andrew Morton <akpm@linux-foundation.org>
> > Cc: Dan Williams <dan.j.williams@intel.com>
> > Cc: John Hubbard <jhubbard@nvidia.com>
> > Cc: Arnd Bergmann <arnd@arndb.de>
> > ---
> >  mm/hmm.c | 132 ++++++++++++++++++++++++++++++++++++++++++++++---------
> >  1 file changed, 111 insertions(+), 21 deletions(-)
> > 
> > diff --git a/mm/hmm.c b/mm/hmm.c
> > index 64a33770813b..ce33151c6832 100644
> > --- a/mm/hmm.c
> > +++ b/mm/hmm.c
> > @@ -325,6 +325,7 @@ EXPORT_SYMBOL(hmm_mirror_unregister);
> >  
> >  struct hmm_vma_walk {
> >  	struct hmm_range	*range;
> > +	struct dev_pagemap	*pgmap;
> >  	unsigned long		last;
> >  	bool			fault;
> >  	bool			block;
> > @@ -499,6 +500,15 @@ static inline uint64_t pmd_to_hmm_pfn_flags(struct hmm_range *range, pmd_t pmd)
> >  				range->flags[HMM_PFN_VALID];
> >  }
> >  
> > +static inline uint64_t pud_to_hmm_pfn_flags(struct hmm_range *range, pud_t pud)
> > +{
> > +	if (!pud_present(pud))
> > +		return 0;
> > +	return pud_write(pud) ? range->flags[HMM_PFN_VALID] |
> > +				range->flags[HMM_PFN_WRITE] :
> > +				range->flags[HMM_PFN_VALID];
> > +}
> > +
> >  static int hmm_vma_handle_pmd(struct mm_walk *walk,
> >  			      unsigned long addr,
> >  			      unsigned long end,
> > @@ -520,8 +530,19 @@ static int hmm_vma_handle_pmd(struct mm_walk *walk,
> >  		return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk);
> >  
> >  	pfn = pmd_pfn(pmd) + pte_index(addr);
> > -	for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++)
> > +	for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++) {
> > +		if (pmd_devmap(pmd)) {
> > +			hmm_vma_walk->pgmap = get_dev_pagemap(pfn,
> > +					      hmm_vma_walk->pgmap);
> > +			if (unlikely(!hmm_vma_walk->pgmap))
> > +				return -EBUSY;
> > +		}
> >  		pfns[i] = hmm_pfn_from_pfn(range, pfn) | cpu_flags;
> > +	}
> > +	if (hmm_vma_walk->pgmap) {
> > +		put_dev_pagemap(hmm_vma_walk->pgmap);
> > +		hmm_vma_walk->pgmap = NULL;
> > +	}
> >  	hmm_vma_walk->last = end;
> >  	return 0;
> >  }
> > @@ -608,10 +629,24 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
> >  	if (fault || write_fault)
> >  		goto fault;
> >  
> > +	if (pte_devmap(pte)) {
> > +		hmm_vma_walk->pgmap = get_dev_pagemap(pte_pfn(pte),
> > +					      hmm_vma_walk->pgmap);
> > +		if (unlikely(!hmm_vma_walk->pgmap))
> > +			return -EBUSY;
> > +	} else if (IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) && pte_special(pte)) {
> > +		*pfn = range->values[HMM_PFN_SPECIAL];
> > +		return -EFAULT;
> > +	}
> > +
> >  	*pfn = hmm_pfn_from_pfn(range, pte_pfn(pte)) | cpu_flags;
> 
> 	<tag>
> 
> >  	return 0;
> >  
> >  fault:
> > +	if (hmm_vma_walk->pgmap) {
> > +		put_dev_pagemap(hmm_vma_walk->pgmap);
> > +		hmm_vma_walk->pgmap = NULL;
> > +	}
> >  	pte_unmap(ptep);
> >  	/* Fault any virtual address we were asked to fault */
> >  	return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk);
> > @@ -699,12 +734,83 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp,
> >  			return r;
> >  		}
> >  	}
> > +	if (hmm_vma_walk->pgmap) {
> > +		put_dev_pagemap(hmm_vma_walk->pgmap);
> > +		hmm_vma_walk->pgmap = NULL;
> > +	}
> 
> 
> Why is this here and not in hmm_vma_handle_pte()?  Unless I'm just getting
> tired this is the corresponding put when hmm_vma_handle_pte() returns 0 above
> at <tag> above.

This is because get_dev_pagemap() optimize away the reference getting
if we already hold a reference on the correct dev_pagemap. So if we
were releasing the reference within hmm_vma_handle_pte() then we would
loose the get_dev_pagemap() optimization.

Cheers,
Jérôme