Linux Virtualization - Jul 2012 - [PATCH] xen: populate correct number of pages when across mem boundary

When populate pages across a mem boundary at bootup, the page count
populated isn't correct. This is due to mem populated to non-mem
region and ignored.

Pfn range is also wrongly aligned when mem boundary isn't page aligned.

Also need consider the rare case when xen_do_chunk fail(populate).

For a dom0 booted with dom_mem=3368952K(0xcd9ff000-4k) dmesg diff is:
 [    0.000000] Freeing 9e-100 pfn range: 98 pages freed
 [    0.000000] 1-1 mapping on 9e->100
 [    0.000000] 1-1 mapping on cd9ff->100000
 [    0.000000] Released 98 pages of unused memory
 [    0.000000] Set 206435 page(s) to 1-1 mapping
-[    0.000000] Populating cd9fe-cda00 pfn range: 1 pages added
+[    0.000000] Populating cd9fe-cd9ff pfn range: 1 pages added
+[    0.000000] Populating 100000-100061 pfn range: 97 pages added
 [    0.000000] BIOS-provided physical RAM map:
 [    0.000000] Xen: 0000000000000000 - 000000000009e000 (usable)
 [    0.000000] Xen: 00000000000a0000 - 0000000000100000 (reserved)
 [    0.000000] Xen: 0000000000100000 - 00000000cd9ff000 (usable)
 [    0.000000] Xen: 00000000cd9ffc00 - 00000000cda53c00 (ACPI NVS)
...
 [    0.000000] Xen: 0000000100000000 - 0000000100061000 (usable)
 [    0.000000] Xen: 0000000100061000 - 000000012c000000 (unusable)
...
 [    0.000000] MEMBLOCK configuration:
...
-[    0.000000]  reserved[0x4]       [0x000000cd9ff000-0x000000cd9ffbff], 0xc00
bytes
-[    0.000000]  reserved[0x5]       [0x00000100000000-0x00000100060fff],
0x61000 bytes

Related xen memory layout:
(XEN) Xen-e820 RAM map:
(XEN)  0000000000000000 - 000000000009ec00 (usable)
(XEN)  00000000000f0000 - 0000000000100000 (reserved)
(XEN)  0000000000100000 - 00000000cd9ffc00 (usable)

Signed-off-by: Zhenzhong Duan <zhenzhong.duan at oracle.com>
---
 arch/x86/xen/setup.c |   24 +++++++++++-------------
 1 files changed, 11 insertions(+), 13 deletions(-)

diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index a4790bf..bd78773 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -157,50 +157,48 @@ static unsigned long __init xen_populate_chunk(
 	unsigned long dest_pfn;
 
 	for (i = 0, entry = list; i < map_size; i++, entry++) {
-		unsigned long credits = credits_left;
 		unsigned long s_pfn;
 		unsigned long e_pfn;
 		unsigned long pfns;
 		long capacity;
 
-		if (credits <= 0)
+		if (credits_left <= 0)
 			break;
 
 		if (entry->type != E820_RAM)
 			continue;
 
-		e_pfn = PFN_UP(entry->addr + entry->size);
+		e_pfn = PFN_DOWN(entry->addr + entry->size);
 
 		/* We only care about E820 after the xen_start_info->nr_pages */
 		if (e_pfn <= max_pfn)
 			continue;
 
-		s_pfn = PFN_DOWN(entry->addr);
+		s_pfn = PFN_UP(entry->addr);
 		/* If the E820 falls within the nr_pages, we want to start
 		 * at the nr_pages PFN.
 		 * If that would mean going past the E820 entry, skip it
 		 */
+again:
 		if (s_pfn <= max_pfn) {
 			capacity = e_pfn - max_pfn;
 			dest_pfn = max_pfn;
 		} else {
-			/* last_pfn MUST be within E820_RAM regions */
-			if (*last_pfn && e_pfn >= *last_pfn)
-				s_pfn = *last_pfn;
 			capacity = e_pfn - s_pfn;
 			dest_pfn = s_pfn;
 		}
-		/* If we had filled this E820_RAM entry, go to the next one. */
-		if (capacity <= 0)
-			continue;
 
-		if (credits > capacity)
-			credits = capacity;
+		if (credits_left < capacity)
+			capacity = credits_left;
 
-		pfns = xen_do_chunk(dest_pfn, dest_pfn + credits, false);
+		pfns = xen_do_chunk(dest_pfn, dest_pfn + capacity, false);
 		done += pfns;
 		credits_left -= pfns;
 		*last_pfn = (dest_pfn + pfns);
+		if (credits_left > 0 && *last_pfn < e_pfn) {
+			s_pfn = *last_pfn;
+			goto again;
+		}
 	}
 	return done;
 }
-- 
1.7.3

On 04/07/12 07:49, zhenzhong.duan wrote:
> When populate pages across a mem boundary at bootup, the page count
> populated isn't correct. This is due to mem populated to non-mem
> region and ignored.
> 
> Pfn range is also wrongly aligned when mem boundary isn't page aligned.
> 
> Also need consider the rare case when xen_do_chunk fail(populate).
> 
> For a dom0 booted with dom_mem=3368952K(0xcd9ff000-4k) dmesg diff is:
>  [    0.000000] Freeing 9e-100 pfn range: 98 pages freed
>  [    0.000000] 1-1 mapping on 9e->100
>  [    0.000000] 1-1 mapping on cd9ff->100000
>  [    0.000000] Released 98 pages of unused memory
>  [    0.000000] Set 206435 page(s) to 1-1 mapping
> -[    0.000000] Populating cd9fe-cda00 pfn range: 1 pages added
> +[    0.000000] Populating cd9fe-cd9ff pfn range: 1 pages added
> +[    0.000000] Populating 100000-100061 pfn range: 97 pages added
>  [    0.000000] BIOS-provided physical RAM map:
>  [    0.000000] Xen: 0000000000000000 - 000000000009e000 (usable)
>  [    0.000000] Xen: 00000000000a0000 - 0000000000100000 (reserved)
>  [    0.000000] Xen: 0000000000100000 - 00000000cd9ff000 (usable)
>  [    0.000000] Xen: 00000000cd9ffc00 - 00000000cda53c00 (ACPI NVS)
> ...
>  [    0.000000] Xen: 0000000100000000 - 0000000100061000 (usable)
>  [    0.000000] Xen: 0000000100061000 - 000000012c000000 (unusable)
> ...
>  [    0.000000] MEMBLOCK configuration:
> ...
> -[    0.000000]  reserved[0x4]       [0x000000cd9ff000-0x000000cd9ffbff],
0xc00 bytes
> -[    0.000000]  reserved[0x5]       [0x00000100000000-0x00000100060fff],
0x61000 bytes
> 
> Related xen memory layout:
> (XEN) Xen-e820 RAM map:
> (XEN)  0000000000000000 - 000000000009ec00 (usable)
> (XEN)  00000000000f0000 - 0000000000100000 (reserved)
> (XEN)  0000000000100000 - 00000000cd9ffc00 (usable)
> 
> Signed-off-by: Zhenzhong Duan <zhenzhong.duan at oracle.com>
> ---
>  arch/x86/xen/setup.c |   24 +++++++++++-------------
>  1 files changed, 11 insertions(+), 13 deletions(-)
> 
> diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
> index a4790bf..bd78773 100644
> --- a/arch/x86/xen/setup.c
> +++ b/arch/x86/xen/setup.c
> @@ -157,50 +157,48 @@ static unsigned long __init xen_populate_chunk(
>  	unsigned long dest_pfn;
>  
>  	for (i = 0, entry = list; i < map_size; i++, entry++) {
> -		unsigned long credits = credits_left;
>  		unsigned long s_pfn;
>  		unsigned long e_pfn;
>  		unsigned long pfns;
>  		long capacity;
>  
> -		if (credits <= 0)
> +		if (credits_left <= 0)
>  			break;
>  
>  		if (entry->type != E820_RAM)
>  			continue;
>  
> -		e_pfn = PFN_UP(entry->addr + entry->size);
> +		e_pfn = PFN_DOWN(entry->addr + entry->size);
Ok.
>  
>  		/* We only care about E820 after the xen_start_info->nr_pages */
>  		if (e_pfn <= max_pfn)
>  			continue;
>  
> -		s_pfn = PFN_DOWN(entry->addr);
> +		s_pfn = PFN_UP(entry->addr);
Ok.
>  		/* If the E820 falls within the nr_pages, we want to start
>  		 * at the nr_pages PFN.
>  		 * If that would mean going past the E820 entry, skip it
>  		 */
> +again:
>  		if (s_pfn <= max_pfn) {
>  			capacity = e_pfn - max_pfn;
>  			dest_pfn = max_pfn;
>  		} else {
> -			/* last_pfn MUST be within E820_RAM regions */
> -			if (*last_pfn && e_pfn >= *last_pfn)
> -				s_pfn = *last_pfn;
>  			capacity = e_pfn - s_pfn;
>  			dest_pfn = s_pfn;
>  		}
> -		/* If we had filled this E820_RAM entry, go to the next one. */
> -		if (capacity <= 0)
> -			continue;
>  
> -		if (credits > capacity)
> -			credits = capacity;
> +		if (credits_left < capacity)
> +			capacity = credits_left;
>  
> -		pfns = xen_do_chunk(dest_pfn, dest_pfn + credits, false);
> +		pfns = xen_do_chunk(dest_pfn, dest_pfn + capacity, false);
>  		done += pfns;
>  		credits_left -= pfns;
>  		*last_pfn = (dest_pfn + pfns);
> +		if (credits_left > 0 && *last_pfn < e_pfn) {
> +			s_pfn = *last_pfn;
> +			goto again;
> +		}
This looks like it will loop forever if xen_do_chunk() repeatedly fails
because Xen is out of pages.  I think if xen_do_chunk() cannot get a
page from Xen the repopulation process should stop -- aborting this
chunk and any others.  This will allow the guest to continue to boot
just with less memory than expected.

David

? 2012-07-12 22:55, David Vrabel ??:
> On 04/07/12 07:49, zhenzhong.duan wrote:
>> When populate pages across a mem boundary at bootup, the page count
>> populated isn't correct. This is due to mem populated to non-mem
>> region and ignored.
>>
>> Pfn range is also wrongly aligned when mem boundary isn't page
aligned.
>>
>> Also need consider the rare case when xen_do_chunk fail(populate).
>>
>> For a dom0 booted with dom_mem=3368952K(0xcd9ff000-4k) dmesg diff is:
>>   [    0.000000] Freeing 9e-100 pfn range: 98 pages freed
>>   [    0.000000] 1-1 mapping on 9e->100
>>   [    0.000000] 1-1 mapping on cd9ff->100000
>>   [    0.000000] Released 98 pages of unused memory
>>   [    0.000000] Set 206435 page(s) to 1-1 mapping
>> -[    0.000000] Populating cd9fe-cda00 pfn range: 1 pages added
>> +[    0.000000] Populating cd9fe-cd9ff pfn range: 1 pages added
>> +[    0.000000] Populating 100000-100061 pfn range: 97 pages added
>>   [    0.000000] BIOS-provided physical RAM map:
>>   [    0.000000] Xen: 0000000000000000 - 000000000009e000 (usable)
>>   [    0.000000] Xen: 00000000000a0000 - 0000000000100000 (reserved)
>>   [    0.000000] Xen: 0000000000100000 - 00000000cd9ff000 (usable)
>>   [    0.000000] Xen: 00000000cd9ffc00 - 00000000cda53c00 (ACPI NVS)
>> ...
>>   [    0.000000] Xen: 0000000100000000 - 0000000100061000 (usable)
>>   [    0.000000] Xen: 0000000100061000 - 000000012c000000 (unusable)
>> ...
>>   [    0.000000] MEMBLOCK configuration:
>> ...
>> -[    0.000000]  reserved[0x4]      
[0x000000cd9ff000-0x000000cd9ffbff], 0xc00 bytes
>> -[    0.000000]  reserved[0x5]      
[0x00000100000000-0x00000100060fff], 0x61000 bytes
>>
>> Related xen memory layout:
>> (XEN) Xen-e820 RAM map:
>> (XEN)  0000000000000000 - 000000000009ec00 (usable)
>> (XEN)  00000000000f0000 - 0000000000100000 (reserved)
>> (XEN)  0000000000100000 - 00000000cd9ffc00 (usable)
>>
>> Signed-off-by: Zhenzhong Duan<zhenzhong.duan at oracle.com>
>> ---
>>   arch/x86/xen/setup.c |   24 +++++++++++-------------
>>   1 files changed, 11 insertions(+), 13 deletions(-)
>>
>> diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
>> index a4790bf..bd78773 100644
>> --- a/arch/x86/xen/setup.c
>> +++ b/arch/x86/xen/setup.c
>> @@ -157,50 +157,48 @@ static unsigned long __init xen_populate_chunk(
>>   	unsigned long dest_pfn;
>>
>>   	for (i = 0, entry = list; i<  map_size; i++, entry++) {
>> -		unsigned long credits = credits_left;
>>   		unsigned long s_pfn;
>>   		unsigned long e_pfn;
>>   		unsigned long pfns;
>>   		long capacity;
>>
>> -		if (credits<= 0)
>> +		if (credits_left<= 0)
>>   			break;
>>
>>   		if (entry->type != E820_RAM)
>>   			continue;
>>
>> -		e_pfn = PFN_UP(entry->addr + entry->size);
>> +		e_pfn = PFN_DOWN(entry->addr + entry->size);
> Ok.
>
>>
>>   		/* We only care about E820 after the xen_start_info->nr_pages */
>>   		if (e_pfn<= max_pfn)
>>   			continue;
>>
>> -		s_pfn = PFN_DOWN(entry->addr);
>> +		s_pfn = PFN_UP(entry->addr);
> Ok.
>
>>   		/* If the E820 falls within the nr_pages, we want to start
>>   		 * at the nr_pages PFN.
>>   		 * If that would mean going past the E820 entry, skip it
>>   		 */
>> +again:
>>   		if (s_pfn<= max_pfn) {
>>   			capacity = e_pfn - max_pfn;
>>   			dest_pfn = max_pfn;
>>   		} else {
>> -			/* last_pfn MUST be within E820_RAM regions */
>> -			if (*last_pfn&&  e_pfn>= *last_pfn)
>> -				s_pfn = *last_pfn;
>>   			capacity = e_pfn - s_pfn;
>>   			dest_pfn = s_pfn;
>>   		}
>> -		/* If we had filled this E820_RAM entry, go to the next one. */
>> -		if (capacity<= 0)
>> -			continue;
>>
>> -		if (credits>  capacity)
>> -			credits = capacity;
>> +		if (credits_left<  capacity)
>> +			capacity = credits_left;
>>
>> -		pfns = xen_do_chunk(dest_pfn, dest_pfn + credits, false);
>> +		pfns = xen_do_chunk(dest_pfn, dest_pfn + capacity, false);
>>   		done += pfns;
>>   		credits_left -= pfns;
>>   		*last_pfn = (dest_pfn + pfns);
>> +		if (credits_left>  0&&  *last_pfn<  e_pfn) {
>> +			s_pfn = *last_pfn;
>> +			goto again;
>> +		}
> This looks like it will loop forever if xen_do_chunk() repeatedly fails
> because Xen is out of pages.  I think if xen_do_chunk() cannot get a
> page from Xen the repopulation process should stop -- aborting this
> chunk and any others.  This will allow the guest to continue to boot
> just with less memory than expected.
>
> David
Ok, I'll update the patch, loop forever isn't a good idea.
Originally, I considered the case there is dynamic memory control 
functionality in the system.
thanks for comment.

When populate pages across a mem boundary at bootup, the page count
populated isn't correct. This is due to mem populated to non-mem
region and ignored.

Pfn range is also wrongly aligned when mem boundary isn't page aligned.

-v2: If xen_do_chunk fail(populate), abort this chunk and any others.
Suggested by David, thanks.

For a dom0 booted with dom_mem=3368952K(0xcd9ff000-4k) dmesg diff is:
  [    0.000000] Freeing 9e-100 pfn range: 98 pages freed
  [    0.000000] 1-1 mapping on 9e->100
  [    0.000000] 1-1 mapping on cd9ff->100000
  [    0.000000] Released 98 pages of unused memory
  [    0.000000] Set 206435 page(s) to 1-1 mapping
-[    0.000000] Populating cd9fe-cda00 pfn range: 1 pages added
+[    0.000000] Populating cd9fe-cd9ff pfn range: 1 pages added
+[    0.000000] Populating 100000-100061 pfn range: 97 pages added
  [    0.000000] BIOS-provided physical RAM map:
  [    0.000000] Xen: 0000000000000000 - 000000000009e000 (usable)
  [    0.000000] Xen: 00000000000a0000 - 0000000000100000 (reserved)
  [    0.000000] Xen: 0000000000100000 - 00000000cd9ff000 (usable)
  [    0.000000] Xen: 00000000cd9ffc00 - 00000000cda53c00 (ACPI NVS)
...
  [    0.000000] Xen: 0000000100000000 - 0000000100061000 (usable)
  [    0.000000] Xen: 0000000100061000 - 000000012c000000 (unusable)
...
  [    0.000000] MEMBLOCK configuration:
...
-[    0.000000]  reserved[0x4]       [0x000000cd9ff000-0x000000cd9ffbff], 0xc00
bytes
-[    0.000000]  reserved[0x5]       [0x00000100000000-0x00000100060fff],
0x61000 bytes

Related xen memory layout:
(XEN) Xen-e820 RAM map:
(XEN)  0000000000000000 - 000000000009ec00 (usable)
(XEN)  00000000000f0000 - 0000000000100000 (reserved)
(XEN)  0000000000100000 - 00000000cd9ffc00 (usable)

Signed-off-by: Zhenzhong Duan<zhenzhong.duan at oracle.com>
---
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index a4790bf..ead8557 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -157,25 +157,24 @@ static unsigned long __init xen_populate_chunk(
  	unsigned long dest_pfn;

  	for (i = 0, entry = list; i<  map_size; i++, entry++) {
-		unsigned long credits = credits_left;
  		unsigned long s_pfn;
  		unsigned long e_pfn;
  		unsigned long pfns;
  		long capacity;

-		if (credits<= 0)
+		if (credits_left<= 0)
  			break;

  		if (entry->type != E820_RAM)
  			continue;

-		e_pfn = PFN_UP(entry->addr + entry->size);
+		e_pfn = PFN_DOWN(entry->addr + entry->size);

  		/* We only care about E820 after the xen_start_info->nr_pages */
  		if (e_pfn<= max_pfn)
  			continue;

-		s_pfn = PFN_DOWN(entry->addr);
+		s_pfn = PFN_UP(entry->addr);
  		/* If the E820 falls within the nr_pages, we want to start
  		 * at the nr_pages PFN.
  		 * If that would mean going past the E820 entry, skip it
@@ -184,23 +183,19 @@ static unsigned long __init xen_populate_chunk(
  			capacity = e_pfn - max_pfn;
  			dest_pfn = max_pfn;
  		} else {
-			/* last_pfn MUST be within E820_RAM regions */
-			if (*last_pfn&&  e_pfn>= *last_pfn)
-				s_pfn = *last_pfn;
  			capacity = e_pfn - s_pfn;
  			dest_pfn = s_pfn;
  		}
-		/* If we had filled this E820_RAM entry, go to the next one. */
-		if (capacity<= 0)
-			continue;

-		if (credits>  capacity)
-			credits = capacity;
+		if (credits_left<  capacity)
+			capacity = credits_left;

-		pfns = xen_do_chunk(dest_pfn, dest_pfn + credits, false);
+		pfns = xen_do_chunk(dest_pfn, dest_pfn + capacity, false);
  		done += pfns;
-		credits_left -= pfns;
  		*last_pfn = (dest_pfn + pfns);
+		if (pfns<  capacity)
+			break;
+		credits_left -= pfns;
  	}
  	return done;
  }
-- 
1.7.3