[PATCH v4 12/20] xen/balloon: Don't rely on the page granularity is the same for Xen and Linux

[Stefano Stabellini]

On Mon, 7 Sep 2015, Julien Grall wrote:
> For ARM64 guests, Linux is able to support either 64K or 4K page
> granularity. Although, the hypercall interface is always based on 4K
> page granularity.
> 
> With 64K page granularity, a single page will be spread over multiple
> Xen frame.
> 
> To avoid splitting the page into 4K frame, take advantage of the
> extent_order field to directly allocate/free chunk of the Linux page
> size.
> 
> Note that PVMMU is only used for PV guest (which is x86) and the page
> granularity is always 4KB. Some BUILD_BUG_ON has been added to ensure
> that because the code has not been modified.
> 
> Signed-off-by: Julien Grall <julien.grall at citrix.com>

Reviewed-by: Stefano Stabellini <stefano.stabellini at eu.citrix.com>


> ---
> Cc: Konrad Rzeszutek Wilk <konrad.wilk at oracle.com>
> Cc: Boris Ostrovsky <boris.ostrovsky at oracle.com>
> Cc: David Vrabel <david.vrabel at citrix.com>
> Cc: Wei Liu <wei.liu2 at citrix.com>
> 
> Note that two BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE) in code built
> for the PV MMU code is kept in order to have at least one even if we
> ever decide to drop of code section.
> 
>     Changes in v4:
>         - s/xen_page_to_pfn/page_to_xen_pfn/ based on the new naming
>         - Use the field lru in the page to get a list of pages when
>         decreasing the memory reservation. It avoids to use a static
>         array to store the pages (see v3).
>         - Update comment for EXTENT_ORDER.
> 
>     Changes in v3:
>         - Fix errors reported by checkpatch.pl
>         - s/mfn/gfn/ based on the new naming
>         - Rather than splitting the page into 4KB chunk, use the
>         extent_order field to allocate directly a Linux page size. This
>         is avoid lots of code for no benefits.
> 
>     Changes in v2:
>         - Use xen_apply_to_page to split a page in 4K chunk
>         - It's not necessary to have a smaller frame list. Re-use
>         PAGE_SIZE
>         - Convert reserve_additional_memory to use XEN_... macro
> ---
>  drivers/xen/balloon.c | 59 ++++++++++++++++++++++++++++++++++++++-------------
>  1 file changed, 44 insertions(+), 15 deletions(-)
> 
> diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
> index c79329f..3babf13 100644
> --- a/drivers/xen/balloon.c
> +++ b/drivers/xen/balloon.c
> @@ -70,6 +70,11 @@
>  #include <xen/features.h>
>  #include <xen/page.h>
>  
> +/* Use one extent per PAGE_SIZE to avoid to break down the page into
> + * multiple frame.
> + */
> +#define EXTENT_ORDER (fls(XEN_PFN_PER_PAGE) - 1)
> +
>  /*
>   * balloon_process() state:
>   *
> @@ -230,6 +235,11 @@ static enum bp_state reserve_additional_memory(long credit)
>  	nid = memory_add_physaddr_to_nid(hotplug_start_paddr);
>  
>  #ifdef CONFIG_XEN_HAVE_PVMMU
> +	/* We don't support PV MMU when Linux and Xen is using
> +	 * different page granularity.
> +	 */
> +	BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE);
> +
>          /*
>           * add_memory() will build page tables for the new memory so
>           * the p2m must contain invalid entries so the correct
> @@ -326,11 +336,11 @@ static enum bp_state reserve_additional_memory(long credit)
>  static enum bp_state increase_reservation(unsigned long nr_pages)
>  {
>  	int rc;
> -	unsigned long  pfn, i;
> +	unsigned long i;
>  	struct page   *page;
>  	struct xen_memory_reservation reservation = {
>  		.address_bits = 0,
> -		.extent_order = 0,
> +		.extent_order = EXTENT_ORDER,
>  		.domid        = DOMID_SELF
>  	};
>  
> @@ -352,7 +362,11 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
>  			nr_pages = i;
>  			break;
>  		}
> -		frame_list[i] = page_to_pfn(page);
> +
> +		/* XENMEM_populate_physmap requires a PFN based on Xen
> +		 * granularity.
> +		 */
> +		frame_list[i] = page_to_xen_pfn(page);
>  		page = balloon_next_page(page);
>  	}
>  
> @@ -366,10 +380,15 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
>  		page = balloon_retrieve(false);
>  		BUG_ON(page == NULL);
>  
> -		pfn = page_to_pfn(page);
> -
>  #ifdef CONFIG_XEN_HAVE_PVMMU
> +		/* We don't support PV MMU when Linux and Xen is using
> +		 * different page granularity.
> +		 */
> +		BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE);
> +
>  		if (!xen_feature(XENFEAT_auto_translated_physmap)) {
> +			unsigned long pfn = page_to_pfn(page);
> +
>  			set_phys_to_machine(pfn, frame_list[i]);
>  
>  			/* Link back into the page tables if not highmem. */
> @@ -396,14 +415,15 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
>  static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
>  {
>  	enum bp_state state = BP_DONE;
> -	unsigned long  pfn, i;
> -	struct page   *page;
> +	unsigned long i;
> +	struct page *page, *tmp;
>  	int ret;
>  	struct xen_memory_reservation reservation = {
>  		.address_bits = 0,
> -		.extent_order = 0,
> +		.extent_order = EXTENT_ORDER,
>  		.domid        = DOMID_SELF
>  	};
> +	LIST_HEAD(pages);
>  
>  #ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
>  	if (balloon_stats.hotplug_pages) {
> @@ -425,8 +445,7 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
>  			break;
>  		}
>  		scrub_page(page);
> -
> -		frame_list[i] = page_to_pfn(page);
> +		list_add(&page->lru, &pages);
>  	}
>  
>  	/*
> @@ -438,14 +457,23 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
>  	 */
>  	kmap_flush_unused();
>  
> -	/* Update direct mapping, invalidate P2M, and add to balloon. */
> -	for (i = 0; i < nr_pages; i++) {
> -		pfn = frame_list[i];
> -		frame_list[i] = pfn_to_gfn(pfn);
> -		page = pfn_to_page(pfn);
> +	/*
> +	 * Setup the frame, update direct mapping, invalidate P2M,
> +	 * and add to balloon.
> +	 */
> +	list_for_each_entry_safe(page, tmp, &pages, lru) {
> +		/* XENMEM_decrease_reservation requires a GFN */
> +		frame_list[i] = xen_page_to_gfn(page);
>  
>  #ifdef CONFIG_XEN_HAVE_PVMMU
> +		/* We don't support PV MMU when Linux and Xen is using
> +		 * different page granularity.
> +		 */
> +		BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE);
> +
>  		if (!xen_feature(XENFEAT_auto_translated_physmap)) {
> +			unsigned long pfn = page_to_pfn(page);
> +
>  			if (!PageHighMem(page)) {
>  				ret = HYPERVISOR_update_va_mapping(
>  						(unsigned long)__va(pfn << PAGE_SHIFT),
> @@ -455,6 +483,7 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
>  			__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
>  		}
>  #endif
> +		list_del(&page->lru);
>  
>  		balloon_append(page);
>  	}
> -- 
> 2.1.4
>