Re: [PATCH v3 19/20] xen/privcmd: Add support for Linux 64KB page granularity

[Stefano Stabellini]

On Fri, 7 Aug 2015, Julien Grall wrote:
> The hypercall interface (as well as the toolstack) is always using 4KB
> page granularity. When the toolstack is asking for mapping a series of
> guest PFN in a batch, it expects to have the page map contiguously in
> its virtual memory.
> 
> When Linux is using 64KB page granularity, the privcmd driver will have
> to map multiple Xen PFN in a single Linux page.
> 
> Note that this solution works on page granularity which is a multiple of
> 4KB.
> 
> Signed-off-by: Julien Grall <julien.grall@xxxxxxxxxx>
> 
> ---
> Cc: Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx>
> Cc: Boris Ostrovsky <boris.ostrovsky@xxxxxxxxxx>
> Cc: David Vrabel <david.vrabel@xxxxxxxxxx>
> 
>     I kept the hypercall arguments in remap_data to avoid allocating them on
>     the stack every time that remap_pte_fn is called.
>     I will keep like that unless someone is strongly disagree.
> 
>     Changes in v3:
>         - The function to split a Linux page in mutiple Xen page has
>         been moved internally. It was the only use (not used anymore in
>         the balloon) and it's not quite clear what should be the common
>         interface. Differ the question until someone need to use it.
>         - s/nr_pfn/numgfns/ to make clear that we are dealing with GFN
>         - Use DIV_ROUND_UP rather round_up and fix the usage in
>         xen_xlate_unmap_gfn_range
> 
>     Changes in v2:
>         - Use xen_apply_to_page
> ---
>  drivers/xen/privcmd.c   |   8 ++--
>  drivers/xen/xlate_mmu.c | 124 ++++++++++++++++++++++++++++++++----------------
>  2 files changed, 89 insertions(+), 43 deletions(-)
> 
> diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
> index c6deb87..c8798ee 100644
> --- a/drivers/xen/privcmd.c
> +++ b/drivers/xen/privcmd.c
> @@ -446,7 +446,7 @@ static long privcmd_ioctl_mmap_batch(void __user *udata, int version)
>  		return -EINVAL;
>  	}
>  
> -	nr_pages = m.num;
> +	nr_pages = DIV_ROUND_UP(m.num, XEN_PFN_PER_PAGE);
>  	if ((m.num <= 0) || (nr_pages > (LONG_MAX >> PAGE_SHIFT)))
>  		return -EINVAL;
>  
> @@ -494,7 +494,7 @@ static long privcmd_ioctl_mmap_batch(void __user *udata, int version)
>  			goto out_unlock;
>  		}
>  		if (xen_feature(XENFEAT_auto_translated_physmap)) {
> -			ret = alloc_empty_pages(vma, m.num);
> +			ret = alloc_empty_pages(vma, nr_pages);
>  			if (ret < 0)
>  				goto out_unlock;
>  		} else
> @@ -518,6 +518,7 @@ static long privcmd_ioctl_mmap_batch(void __user *udata, int version)
>  	state.global_error  = 0;
>  	state.version       = version;
>  
> +	BUILD_BUG_ON(((PAGE_SIZE / sizeof(xen_pfn_t)) % XEN_PFN_PER_PAGE) != 0);
>  	/* mmap_batch_fn guarantees ret == 0 */
>  	BUG_ON(traverse_pages_block(m.num, sizeof(xen_pfn_t),
>  				    &pagelist, mmap_batch_fn, &state));
> @@ -582,12 +583,13 @@ static void privcmd_close(struct vm_area_struct *vma)
>  {
>  	struct page **pages = vma->vm_private_data;
>  	int numpgs = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
> +	int numgfns = (vma->vm_end - vma->vm_start) >> XEN_PAGE_SHIFT;
>  	int rc;
>  
>  	if (!xen_feature(XENFEAT_auto_translated_physmap) || !numpgs || !pages)
>  		return;
>  
> -	rc = xen_unmap_domain_gfn_range(vma, numpgs, pages);
> +	rc = xen_unmap_domain_gfn_range(vma, numgfns, pages);
>  	if (rc == 0)
>  		free_xenballooned_pages(numpgs, pages);
>  	else
> diff --git a/drivers/xen/xlate_mmu.c b/drivers/xen/xlate_mmu.c
> index cff2387..a1d3904 100644
> --- a/drivers/xen/xlate_mmu.c
> +++ b/drivers/xen/xlate_mmu.c
> @@ -38,31 +38,28 @@
>  #include <xen/interface/xen.h>
>  #include <xen/interface/memory.h>
>  
> -/* map fgfn of domid to lpfn in the current domain */
> -static int map_foreign_page(unsigned long lpfn, unsigned long fgfn,
> -			    unsigned int domid)
> -{
> -	int rc;
> -	struct xen_add_to_physmap_range xatp = {
> -		.domid = DOMID_SELF,
> -		.foreign_domid = domid,
> -		.size = 1,
> -		.space = XENMAPSPACE_gmfn_foreign,
> -	};
> -	xen_ulong_t idx = fgfn;
> -	xen_pfn_t gpfn = lpfn;
> -	int err = 0;
> +typedef void (*xen_gfn_fn_t)(unsigned long gfn, void *data);
>  
> -	set_xen_guest_handle(xatp.idxs, &idx);
> -	set_xen_guest_handle(xatp.gpfns, &gpfn);
> -	set_xen_guest_handle(xatp.errs, &err);
> +/* Break down the pages in 4KB chunk and call fn for each gfn */
> +static void xen_for_each_gfn(struct page **pages, unsigned nr_gfn,
> +			     xen_gfn_fn_t fn, void *data)
> +{
> +	unsigned long xen_pfn = 0;
> +	struct page *page;
> +	int i;
>  
> -	rc = HYPERVISOR_memory_op(XENMEM_add_to_physmap_range, &xatp);
> -	return rc < 0 ? rc : err;
> +	for (i = 0; i < nr_gfn; i++) {
> +		if ((i % XEN_PFN_PER_PAGE) == 0) {
> +			page = pages[i / XEN_PFN_PER_PAGE];

If this function is going to be called very frequently you might want to
consider using a shift instead.

    page = pages[i >> 4];

With an appropriate macro of course.


> +			xen_pfn = xen_page_to_pfn(page);
> +		}
> +		fn(pfn_to_gfn(xen_pfn++), data);

What is the purpose of incrementing xen_pfn here?


> +	}
>  }
>  
>  struct remap_data {
>  	xen_pfn_t *fgfn; /* foreign domain's gfn */
> +	int nr_fgfn; /* Number of foreign gfn left to map */
>  	pgprot_t prot;
>  	domid_t  domid;
>  	struct vm_area_struct *vma;
> @@ -71,24 +68,71 @@ struct remap_data {
>  	struct xen_remap_gfn_info *info;
>  	int *err_ptr;
>  	int mapped;
> +
> +	/* Hypercall parameters */
> +	int h_errs[XEN_PFN_PER_PAGE];
> +	xen_ulong_t h_idxs[XEN_PFN_PER_PAGE];
> +	xen_pfn_t h_gpfns[XEN_PFN_PER_PAGE];
> +
> +	int h_iter;	/* Iterator */
>  };
>  
> +static void setup_hparams(unsigned long gfn, void *data)
> +{
> +	struct remap_data *info = data;
> +
> +	info->h_idxs[info->h_iter] = *info->fgfn;
> +	info->h_gpfns[info->h_iter] = gfn;
> +	info->h_errs[info->h_iter] = 0;
> +
> +	info->h_iter++;
> +	info->fgfn++;
> +}
> +
>  static int remap_pte_fn(pte_t *ptep, pgtable_t token, unsigned long addr,
>  			void *data)
>  {
>  	struct remap_data *info = data;
>  	struct page *page = info->pages[info->index++];
> -	unsigned long pfn = page_to_pfn(page);
> -	pte_t pte = pte_mkspecial(pfn_pte(pfn, info->prot));
> -	int rc;
> +	pte_t pte = pte_mkspecial(pfn_pte(page_to_pfn(page), info->prot));
> +	int rc, nr_gfn;
> +	uint32_t i;
> +	struct xen_add_to_physmap_range xatp = {
> +		.domid = DOMID_SELF,
> +		.foreign_domid = info->domid,
> +		.space = XENMAPSPACE_gmfn_foreign,
> +	};
>  
> -	rc = map_foreign_page(pfn, *info->fgfn, info->domid);
> -	*info->err_ptr++ = rc;
> -	if (!rc) {
> -		set_pte_at(info->vma->vm_mm, addr, ptep, pte);
> -		info->mapped++;
> +	nr_gfn = min_t(typeof(info->nr_fgfn), XEN_PFN_PER_PAGE, info->nr_fgfn);
> +	info->nr_fgfn -= nr_gfn;
> +
> +	info->h_iter = 0;
> +	xen_for_each_gfn(&page, nr_gfn, setup_hparams, info);
> +	BUG_ON(info->h_iter != nr_gfn);
> +
> +	set_xen_guest_handle(xatp.idxs, info->h_idxs);
> +	set_xen_guest_handle(xatp.gpfns, info->h_gpfns);
> +	set_xen_guest_handle(xatp.errs, info->h_errs);
> +	xatp.size = nr_gfn;
> +
> +	rc = HYPERVISOR_memory_op(XENMEM_add_to_physmap_range, &xatp);
> +
> +	/* info->err_ptr expect to have one error status per Xen PFN */
> +	for (i = 0; i < nr_gfn; i++) {
> +		int err = (rc < 0) ? rc : info->h_errs[i];
> +
> +		*(info->err_ptr++) = err;
> +		if (!err)
> +			info->mapped++;
>  	}
> -	info->fgfn++;
> +
> +	/*
> +	 * Note: The hypercall will return 0 in most of the case if even if
> +	 * all the fgmfn are not mapped. We still have to update the pte
> +	 * as the userspace may decide to continue.
> +	 */
> +	if (!rc)
> +		set_pte_at(info->vma->vm_mm, addr, ptep, pte);
>  
>  	return 0;
>  }
> @@ -102,13 +146,14 @@ int xen_xlate_remap_gfn_array(struct vm_area_struct *vma,
>  {
>  	int err;
>  	struct remap_data data;
> -	unsigned long range = nr << PAGE_SHIFT;
> +	unsigned long range = DIV_ROUND_UP(nr, XEN_PFN_PER_PAGE) << PAGE_SHIFT;
>  
>  	/* Kept here for the purpose of making sure code doesn't break
>  	   x86 PVOPS */
>  	BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_IO)) == (VM_PFNMAP | VM_IO)));
>  
>  	data.fgfn = gfn;
> +	data.nr_fgfn = nr;
>  	data.prot  = prot;
>  	data.domid = domid;
>  	data.vma   = vma;
> @@ -123,21 +168,20 @@ int xen_xlate_remap_gfn_array(struct vm_area_struct *vma,
>  }
>  EXPORT_SYMBOL_GPL(xen_xlate_remap_gfn_array);
>  
> -int xen_xlate_unmap_gfn_range(struct vm_area_struct *vma,
> -			      int nr, struct page **pages)
> +static void unmap_gfn(unsigned long gfn, void *data)
>  {
> -	int i;
> +	struct xen_remove_from_physmap xrp;
>  
> -	for (i = 0; i < nr; i++) {
> -		struct xen_remove_from_physmap xrp;
> -		unsigned long pfn;
> +	xrp.domid = DOMID_SELF;
> +	xrp.gpfn = gfn;
> +	(void)HYPERVISOR_memory_op(XENMEM_remove_from_physmap, &xrp);
> +}
>  
> -		pfn = page_to_pfn(pages[i]);
> +int xen_xlate_unmap_gfn_range(struct vm_area_struct *vma,
> +			      int nr, struct page **pages)
> +{
> +	xen_for_each_gfn(pages, nr, unmap_gfn, NULL);
>  
> -		xrp.domid = DOMID_SELF;
> -		xrp.gpfn = pfn;
> -		(void)HYPERVISOR_memory_op(XENMEM_remove_from_physmap, &xrp);
> -	}
>  	return 0;
>  }
>  EXPORT_SYMBOL_GPL(xen_xlate_unmap_gfn_range);
> -- 
> 2.1.4
> 
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/