Re: [Xen-devel] [PATCH][2/4] Enable 1GB for Xen HVM host page

[Tim Deegan <Tim.Deegan@xxxxxxxxxx>]

At 17:18 +0000 on 22 Feb (1266859100), Wei Huang wrote:
> Change page allocation code in Xen tools. The allocation request now 
> starts with 1GB; if that fails, then falls back to 2MB and then 4KB.
> 
> Signed-off-by: Wei Huang <wei.huang2@xxxxxxx>
> Acked-by: Dongxiao Xu <dongxiao.xu@xxxxxxxxx>
> 

Content-Description: 2-xen-hap-fix-tools.patch
> # HG changeset patch
> # User huangwei@xxxxxxxxxxxxxxxx
> # Date 1266853449 21600
> # Node ID c9b45664b423e11003358944bb8e6e976e735301
> # Parent  1d166c5703256ab97225c6ae46ac87dd5bd07e89
> fix the tools to support 1GB. Create 1GB pages if possible; otherwise falls 
> back to 2MB then 4KB.
> 
> diff -r 1d166c570325 -r c9b45664b423 tools/libxc/xc_hvm_build.c
> --- a/tools/libxc/xc_hvm_build.c      Mon Feb 22 09:44:04 2010 -0600
> +++ b/tools/libxc/xc_hvm_build.c      Mon Feb 22 09:44:09 2010 -0600
> @@ -19,8 +19,10 @@
>  
>  #include <xen/libelf/libelf.h>
>  
> -#define SUPERPAGE_PFN_SHIFT  9
> -#define SUPERPAGE_NR_PFNS    (1UL << SUPERPAGE_PFN_SHIFT)
> +#define SUPERPAGE_2MB_SHIFT   9
> +#define SUPERPAGE_2MB_NR_PFNS (1UL << SUPERPAGE_2MB_SHIFT)
> +#define SUPERPAGE_1GB_SHIFT   18
> +#define SUPERPAGE_1GB_NR_PFNS (1UL << SUPERPAGE_1GB_SHIFT)
>  
>  #define SPECIALPAGE_BUFIOREQ 0
>  #define SPECIALPAGE_XENSTORE 1
> @@ -117,6 +119,8 @@
>      uint64_t v_start, v_end;
>      int rc;
>      xen_capabilities_info_t caps;
> +    unsigned long stat_normal_pages = 0, stat_2mb_pages = 0, 
> +        stat_1gb_pages = 0;
>      int pod_mode = 0;
>      
>  
> @@ -166,35 +170,43 @@
>  
>      /*
>       * Allocate memory for HVM guest, skipping VGA hole 0xA0000-0xC0000.
> -     * We allocate pages in batches of no more than 8MB to ensure that
> -     * we can be preempted and hence dom0 remains responsive.
> +     *
> +     * We attempt to allocate 1GB pages if possible. It falls back on 2MB
> +     * pages if 1GB allocation fails. 4KB pages will be used eventually if
> +     * both fail.
> +     * 
> +     * Under 2MB mode, we allocate pages in batches of no more than 8MB to 
> +     * ensure that we can be preempted and hence dom0 remains responsive.
>       */
>      rc = xc_domain_memory_populate_physmap(
>          xc_handle, dom, 0xa0, 0, 0, &page_array[0x00]);
>      cur_pages = 0xc0;
> +    stat_normal_pages = 0xc0;
>      while ( (rc == 0) && (nr_pages > cur_pages) )
>      {
>          /* Clip count to maximum 8MB extent. */

ITYM 1GB here. 

>          unsigned long count = nr_pages - cur_pages;
> -        if ( count > 2048 )
> -            count = 2048;
> +        unsigned long max_pages = SUPERPAGE_1GB_NR_PFNS;
>  
> -        /* Clip partial superpage extents to superpage boundaries. */
> -        if ( ((cur_pages & (SUPERPAGE_NR_PFNS-1)) != 0) &&
> -             (count > (-cur_pages & (SUPERPAGE_NR_PFNS-1))) )
> -            count = -cur_pages & (SUPERPAGE_NR_PFNS-1); /* clip s.p. tail */
> -        else if ( ((count & (SUPERPAGE_NR_PFNS-1)) != 0) &&
> -                  (count > SUPERPAGE_NR_PFNS) )
> -            count &= ~(SUPERPAGE_NR_PFNS - 1); /* clip non-s.p. tail */
> +        if ( count > max_pages )
> +            count = max_pages;
> +        
> +        /* Take care the corner cases of super page tails */
> +        if ( ((cur_pages & (SUPERPAGE_1GB_NR_PFNS-1)) != 0) &&
> +             (count > (-cur_pages & (SUPERPAGE_1GB_NR_PFNS-1))) )
> +            count = -cur_pages & (SUPERPAGE_1GB_NR_PFNS-1);
> +        else if ( ((count & (SUPERPAGE_1GB_NR_PFNS-1)) != 0) &&
> +                  (count > SUPERPAGE_1GB_NR_PFNS) )
> +            count &= ~(SUPERPAGE_1GB_NR_PFNS - 1);

This logic is overkill since you allocate at most one 1GB page in each
pass.  In fact, given that you test for <1GB immediately below, I think
you can just drop this 'tails' chunk entirely.

>  
> -        /* Attempt to allocate superpage extents. */
> -        if ( ((count | cur_pages) & (SUPERPAGE_NR_PFNS - 1)) == 0 )
> +        /* Attemp to allocate 1GB super page */
> +        if ( ((count | cur_pages) & (SUPERPAGE_1GB_NR_PFNS - 1)) == 0 )
>          {
>              long done;
> -            xen_pfn_t sp_extents[count >> SUPERPAGE_PFN_SHIFT];
> +            xen_pfn_t sp_extents[count >> SUPERPAGE_1GB_SHIFT];
>              struct xen_memory_reservation sp_req = {
> -                .nr_extents   = count >> SUPERPAGE_PFN_SHIFT,
> -                .extent_order = SUPERPAGE_PFN_SHIFT,
> +                .nr_extents   = count >> SUPERPAGE_1GB_SHIFT,
> +                .extent_order = SUPERPAGE_1GB_SHIFT,
>                  .domid        = dom
>              };
>  
> @@ -203,11 +215,12 @@
>  
>              set_xen_guest_handle(sp_req.extent_start, sp_extents);
>              for ( i = 0; i < sp_req.nr_extents; i++ )
> -                sp_extents[i] = 
> page_array[cur_pages+(i<<SUPERPAGE_PFN_SHIFT)];
> +                sp_extents[i] = 
> page_array[cur_pages+(i<<SUPERPAGE_1GB_SHIFT)];
>              done = xc_memory_op(xc_handle, XENMEM_populate_physmap, &sp_req);
>              if ( done > 0 )
>              {
> -                done <<= SUPERPAGE_PFN_SHIFT;
> +                stat_1gb_pages += done;
> +                done <<= SUPERPAGE_1GB_SHIFT;
>                  if ( pod_mode && target_pages > cur_pages )
>                  {
>                      int d = target_pages - cur_pages;
> @@ -218,12 +231,60 @@
>              }
>          }
>  
> +        if ( count != 0 )
> +        {
> +            max_pages = 2048;

Call this (SUPERPAGE_2MB_NR_PFNS * 4)?


Cheers,

Tim.

-- 
Tim Deegan <Tim.Deegan@xxxxxxxxxx>
Principal Software Engineer, XenServer Engineering
Citrix Systems UK Ltd.  (Company #02937203, SL9 0BG)

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel