Re: [PATCH v12 08/29] HMM: add device page fault support v6.

["Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>]

Jérôme Glisse <jglisse@redhat.com> writes:

> [ text/plain ]
> This patch add helper for device page fault. Thus helpers will fill
> the mirror page table using the CPU page table and synchronizing
> with any update to CPU page table.
>
> Changed since v1:
>   - Add comment about directory lock.
>
> Changed since v2:
>   - Check for mirror->hmm in hmm_mirror_fault()
>
> Changed since v3:
>   - Adapt to HMM page table changes.
>
> Changed since v4:
>   - Fix PROT_NONE, ie do not populate from protnone pte.
>   - Fix huge pmd handling (start address may != pmd start address)
>   - Fix missing entry case.
>
> Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
> Signed-off-by: Sherry Cheung <SCheung@nvidia.com>
> Signed-off-by: Subhash Gutti <sgutti@nvidia.com>
> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com>
> Signed-off-by: John Hubbard <jhubbard@nvidia.com>
> Signed-off-by: Jatin Kumar <jakumar@nvidia.com>
> ---


....
....

 +static int hmm_mirror_fault_hpmd(struct hmm_mirror *mirror,
> +				 struct hmm_event *event,
> +				 struct vm_area_struct *vma,
> +				 struct hmm_pt_iter *iter,
> +				 pmd_t *pmdp,
> +				 struct hmm_mirror_fault *mirror_fault,
> +				 unsigned long start,
> +				 unsigned long end)
> +{
> +	struct page *page;
> +	unsigned long addr, pfn;
> +	unsigned flags = FOLL_TOUCH;
> +	spinlock_t *ptl;
> +	int ret;
> +
> +	ptl = pmd_lock(mirror->hmm->mm, pmdp);
> +	if (unlikely(!pmd_trans_huge(*pmdp))) {
> +		spin_unlock(ptl);
> +		return -EAGAIN;
> +	}
> +	flags |= event->etype == HMM_DEVICE_WFAULT ? FOLL_WRITE : 0;
> +	page = follow_trans_huge_pmd(vma, start, pmdp, flags);
> +	pfn = page_to_pfn(page);
> +	spin_unlock(ptl);
> +
> +	/* Just fault in the whole PMD. */
> +	start &= PMD_MASK;
> +	end = start + PMD_SIZE - 1;
> +
> +	if (!pmd_write(*pmdp) && event->etype == HMM_DEVICE_WFAULT)
> +			return -ENOENT;
> +
> +	for (ret = 0, addr = start; !ret && addr < end;) {
> +		unsigned long i, next = end;
> +		dma_addr_t *hmm_pte;
> +
> +		hmm_pte = hmm_pt_iter_populate(iter, addr, &next);
> +		if (!hmm_pte)
> +			return -ENOMEM;
> +
> +		i = hmm_pt_index(&mirror->pt, addr, mirror->pt.llevel);
> +
> +		/*
> +		 * The directory lock protect against concurrent clearing of
> +		 * page table bit flags. Exceptions being the dirty bit and
> +		 * the device driver private flags.
> +		 */
> +		hmm_pt_iter_directory_lock(iter);
> +		do {
> +			if (!hmm_pte_test_valid_pfn(&hmm_pte[i])) {
> +				hmm_pte[i] = hmm_pte_from_pfn(pfn);
> +				hmm_pt_iter_directory_ref(iter);

I looked at that and it is actually 
static inline void hmm_pt_iter_directory_ref(struct hmm_pt_iter *iter)
{
	BUG_ON(!iter->ptd[iter->pt->llevel - 1]);
	hmm_pt_directory_ref(iter->pt, iter->ptd[iter->pt->llevel - 1]);
}

static inline void hmm_pt_directory_ref(struct hmm_pt *pt,
					struct page *ptd)
{
	if (!atomic_inc_not_zero(&ptd->_mapcount))
		/* Illegal this should not happen. */
		BUG();
}

what is the mapcount update about ?

> +			}
> +			BUG_ON(hmm_pte_pfn(hmm_pte[i]) != pfn);
> +			if (pmd_write(*pmdp))
> +				hmm_pte_set_write(&hmm_pte[i]);
> +		} while (addr += PAGE_SIZE, pfn++, i++, addr != next);
> +		hmm_pt_iter_directory_unlock(iter);
> +		mirror_fault->addr = addr;
> +	}
> +

So we don't have huge page mapping in hmm page table ? 


> +	return 0;
> +}
> +
> +static int hmm_pte_hole(unsigned long addr,
> +			unsigned long next,
> +			struct mm_walk *walk)
> +{
> +	return -ENOENT;
> +}
> +


-aneesh

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>