diff mbox

[RFC,v3,04/35] mm: Initialize node memory regions during boot

Message ID 20130830131504.4947.86008.stgit@srivatsabhat.in.ibm.com (mailing list archive)
State RFC, archived
Headers show

Commit Message

Srivatsa S. Bhat Aug. 30, 2013, 1:15 p.m. UTC 
Initialize the node's memory-regions structures with the information about
the region-boundaries, at boot time.

Based-on-patch-by: Ankita Garg <gargankita@gmail.com>
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
---

 include/linux/mm.h |    4 ++++
 mm/page_alloc.c    |   28 ++++++++++++++++++++++++++++
 2 files changed, 32 insertions(+)


--
To unsubscribe from this list: send the line "unsubscribe linux-pm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Comments

Yasuaki Ishimatsu Sept. 2, 2013, 6:20 a.m. UTC | #1 
(2013/08/30 22:15), Srivatsa S. Bhat wrote:
> Initialize the node's memory-regions structures with the information about
> the region-boundaries, at boot time.
>
> Based-on-patch-by: Ankita Garg <gargankita@gmail.com>
> Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
> ---
>
>   include/linux/mm.h |    4 ++++
>   mm/page_alloc.c    |   28 ++++++++++++++++++++++++++++
>   2 files changed, 32 insertions(+)
>
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index f022460..18fdec4 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -627,6 +627,10 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
>   #define LAST_NID_MASK		((1UL << LAST_NID_WIDTH) - 1)
>   #define ZONEID_MASK		((1UL << ZONEID_SHIFT) - 1)
>
> +/* Hard-code memory region size to be 512 MB for now. */
> +#define MEM_REGION_SHIFT	(29 - PAGE_SHIFT)
> +#define MEM_REGION_SIZE		(1UL << MEM_REGION_SHIFT)
> +
>   static inline enum zone_type page_zonenum(const struct page *page)
>   {
>   	return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK;
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index b86d7e3..bb2d5d4 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -4809,6 +4809,33 @@ static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat)
>   #endif /* CONFIG_FLAT_NODE_MEM_MAP */
>   }
>
> +static void __meminit init_node_memory_regions(struct pglist_data *pgdat)
> +{
> +	int nid = pgdat->node_id;
> +	unsigned long start_pfn = pgdat->node_start_pfn;
> +	unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages;
> +	struct node_mem_region *region;
> +	unsigned long i, absent;
> +	int idx;
> +
> +	for (i = start_pfn, idx = 0; i < end_pfn;
> +				i += region->spanned_pages, idx++) {
> +

> +		region = &pgdat->node_regions[idx];

It seems that overflow easily occurs.
node_regions[] has 256 entries and MEM_REGION_SIZE is 512MiB. So if
the pgdat has more than 128 GiB, overflow will occur. Am I wrong?

Thanks,
Yasuaki Ishimatsu

> +		region->pgdat = pgdat;
> +		region->start_pfn = i;
> +		region->spanned_pages = min(MEM_REGION_SIZE, end_pfn - i);
> +		region->end_pfn = region->start_pfn + region->spanned_pages;
> +
> +		absent = __absent_pages_in_range(nid, region->start_pfn,
> +						 region->end_pfn);
> +
> +		region->present_pages = region->spanned_pages - absent;
> +	}
> +
> +	pgdat->nr_node_regions = idx;
> +}
> +
>   void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
>   		unsigned long node_start_pfn, unsigned long *zholes_size)
>   {
> @@ -4837,6 +4864,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
>
>   	free_area_init_core(pgdat, start_pfn, end_pfn,
>   			    zones_size, zholes_size);
> +	init_node_memory_regions(pgdat);
>   }
>
>   #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
>


--
To unsubscribe from this list: send the line "unsubscribe linux-pm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Srivatsa S. Bhat Sept. 2, 2013, 5:43 p.m. UTC | #2 
On 09/02/2013 11:50 AM, Yasuaki Ishimatsu wrote:
> (2013/08/30 22:15), Srivatsa S. Bhat wrote:
>> Initialize the node's memory-regions structures with the information
>> about
>> the region-boundaries, at boot time.
>>
>> Based-on-patch-by: Ankita Garg <gargankita@gmail.com>
>> Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
>> ---
>>
>>   include/linux/mm.h |    4 ++++
>>   mm/page_alloc.c    |   28 ++++++++++++++++++++++++++++
>>   2 files changed, 32 insertions(+)
>>
>> diff --git a/include/linux/mm.h b/include/linux/mm.h
>> index f022460..18fdec4 100644
>> --- a/include/linux/mm.h
>> +++ b/include/linux/mm.h
>> @@ -627,6 +627,10 @@ static inline pte_t maybe_mkwrite(pte_t pte,
>> struct vm_area_struct *vma)
>>   #define LAST_NID_MASK        ((1UL << LAST_NID_WIDTH) - 1)
>>   #define ZONEID_MASK        ((1UL << ZONEID_SHIFT) - 1)
>>
>> +/* Hard-code memory region size to be 512 MB for now. */
>> +#define MEM_REGION_SHIFT    (29 - PAGE_SHIFT)
>> +#define MEM_REGION_SIZE        (1UL << MEM_REGION_SHIFT)
>> +
>>   static inline enum zone_type page_zonenum(const struct page *page)
>>   {
>>       return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK;
>> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
>> index b86d7e3..bb2d5d4 100644
>> --- a/mm/page_alloc.c
>> +++ b/mm/page_alloc.c
>> @@ -4809,6 +4809,33 @@ static void __init_refok
>> alloc_node_mem_map(struct pglist_data *pgdat)
>>   #endif /* CONFIG_FLAT_NODE_MEM_MAP */
>>   }
>>
>> +static void __meminit init_node_memory_regions(struct pglist_data
>> *pgdat)
>> +{
>> +    int nid = pgdat->node_id;
>> +    unsigned long start_pfn = pgdat->node_start_pfn;
>> +    unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages;
>> +    struct node_mem_region *region;
>> +    unsigned long i, absent;
>> +    int idx;
>> +
>> +    for (i = start_pfn, idx = 0; i < end_pfn;
>> +                i += region->spanned_pages, idx++) {
>> +
> 
>> +        region = &pgdat->node_regions[idx];
> 
> It seems that overflow easily occurs.
> node_regions[] has 256 entries and MEM_REGION_SIZE is 512MiB. So if
> the pgdat has more than 128 GiB, overflow will occur. Am I wrong?
>

No, you are right. It should be made dynamic to accommodate larger
memory. I just used that value as a placeholder, since my focus was to
demonstrate what algorithms and designs could be developed on top of
this infrastructure, to help shape memory allocations. But certainly
this needs to be modified to be flexible enough to work with any memory
size. Thank you for your review!

Regards,
Srivatsa S. Bhat
 
> 
>> +        region->pgdat = pgdat;
>> +        region->start_pfn = i;
>> +        region->spanned_pages = min(MEM_REGION_SIZE, end_pfn - i);
>> +        region->end_pfn = region->start_pfn + region->spanned_pages;
>> +
>> +        absent = __absent_pages_in_range(nid, region->start_pfn,
>> +                         region->end_pfn);
>> +
>> +        region->present_pages = region->spanned_pages - absent;
>> +    }
>> +
>> +    pgdat->nr_node_regions = idx;
>> +}
>> +
>>   void __paginginit free_area_init_node(int nid, unsigned long
>> *zones_size,
>>           unsigned long node_start_pfn, unsigned long *zholes_size)
>>   {
>> @@ -4837,6 +4864,7 @@ void __paginginit free_area_init_node(int nid,
>> unsigned long *zones_size,
>>
>>       free_area_init_core(pgdat, start_pfn, end_pfn,
>>                   zones_size, zholes_size);
>> +    init_node_memory_regions(pgdat);
>>   }
>>
>>   #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
>>
> 
> 

--
To unsubscribe from this list: send the line "unsubscribe linux-pm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Yasuaki Ishimatsu Sept. 3, 2013, 4:53 a.m. UTC | #3 
(2013/09/03 2:43), Srivatsa S. Bhat wrote:
> On 09/02/2013 11:50 AM, Yasuaki Ishimatsu wrote:
>> (2013/08/30 22:15), Srivatsa S. Bhat wrote:
>>> Initialize the node's memory-regions structures with the information
>>> about
>>> the region-boundaries, at boot time.
>>>
>>> Based-on-patch-by: Ankita Garg <gargankita@gmail.com>
>>> Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
>>> ---
>>>
>>>    include/linux/mm.h |    4 ++++
>>>    mm/page_alloc.c    |   28 ++++++++++++++++++++++++++++
>>>    2 files changed, 32 insertions(+)
>>>
>>> diff --git a/include/linux/mm.h b/include/linux/mm.h
>>> index f022460..18fdec4 100644
>>> --- a/include/linux/mm.h
>>> +++ b/include/linux/mm.h
>>> @@ -627,6 +627,10 @@ static inline pte_t maybe_mkwrite(pte_t pte,
>>> struct vm_area_struct *vma)
>>>    #define LAST_NID_MASK        ((1UL << LAST_NID_WIDTH) - 1)
>>>    #define ZONEID_MASK        ((1UL << ZONEID_SHIFT) - 1)
>>>
>>> +/* Hard-code memory region size to be 512 MB for now. */
>>> +#define MEM_REGION_SHIFT    (29 - PAGE_SHIFT)
>>> +#define MEM_REGION_SIZE        (1UL << MEM_REGION_SHIFT)
>>> +
>>>    static inline enum zone_type page_zonenum(const struct page *page)
>>>    {
>>>        return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK;
>>> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
>>> index b86d7e3..bb2d5d4 100644
>>> --- a/mm/page_alloc.c
>>> +++ b/mm/page_alloc.c
>>> @@ -4809,6 +4809,33 @@ static void __init_refok
>>> alloc_node_mem_map(struct pglist_data *pgdat)
>>>    #endif /* CONFIG_FLAT_NODE_MEM_MAP */
>>>    }
>>>
>>> +static void __meminit init_node_memory_regions(struct pglist_data
>>> *pgdat)
>>> +{
>>> +    int nid = pgdat->node_id;
>>> +    unsigned long start_pfn = pgdat->node_start_pfn;
>>> +    unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages;
>>> +    struct node_mem_region *region;
>>> +    unsigned long i, absent;
>>> +    int idx;
>>> +
>>> +    for (i = start_pfn, idx = 0; i < end_pfn;
>>> +                i += region->spanned_pages, idx++) {
>>> +
>>
>>> +        region = &pgdat->node_regions[idx];
>>
>> It seems that overflow easily occurs.
>> node_regions[] has 256 entries and MEM_REGION_SIZE is 512MiB. So if
>> the pgdat has more than 128 GiB, overflow will occur. Am I wrong?
>>
>
> No, you are right. It should be made dynamic to accommodate larger
> memory. I just used that value as a placeholder, since my focus was to
> demonstrate what algorithms and designs could be developed on top of
> this infrastructure, to help shape memory allocations. But certainly
> this needs to be modified to be flexible enough to work with any memory
> size. Thank you for your review!

Thank you for your explanation. I understood it.

Thanks,
Yasuaki Ishimatsu

>
> Regards,
> Srivatsa S. Bhat
>
>>
>>> +        region->pgdat = pgdat;
>>> +        region->start_pfn = i;
>>> +        region->spanned_pages = min(MEM_REGION_SIZE, end_pfn - i);
>>> +        region->end_pfn = region->start_pfn + region->spanned_pages;
>>> +
>>> +        absent = __absent_pages_in_range(nid, region->start_pfn,
>>> +                         region->end_pfn);
>>> +
>>> +        region->present_pages = region->spanned_pages - absent;
>>> +    }
>>> +
>>> +    pgdat->nr_node_regions = idx;
>>> +}
>>> +
>>>    void __paginginit free_area_init_node(int nid, unsigned long
>>> *zones_size,
>>>            unsigned long node_start_pfn, unsigned long *zholes_size)
>>>    {
>>> @@ -4837,6 +4864,7 @@ void __paginginit free_area_init_node(int nid,
>>> unsigned long *zones_size,
>>>
>>>        free_area_init_core(pgdat, start_pfn, end_pfn,
>>>                    zones_size, zholes_size);
>>> +    init_node_memory_regions(pgdat);
>>>    }
>>>
>>>    #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
>>>
>>
>>
>


--
To unsubscribe from this list: send the line "unsubscribe linux-pm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/include/linux/mm.h b/include/linux/mm.h
index f022460..18fdec4 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -627,6 +627,10 @@  static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 #define LAST_NID_MASK		((1UL << LAST_NID_WIDTH) - 1)
 #define ZONEID_MASK		((1UL << ZONEID_SHIFT) - 1)
 
+/* Hard-code memory region size to be 512 MB for now. */
+#define MEM_REGION_SHIFT	(29 - PAGE_SHIFT)
+#define MEM_REGION_SIZE		(1UL << MEM_REGION_SHIFT)
+
 static inline enum zone_type page_zonenum(const struct page *page)
 {
 	return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b86d7e3..bb2d5d4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4809,6 +4809,33 @@  static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat)
 #endif /* CONFIG_FLAT_NODE_MEM_MAP */
 }
 
+static void __meminit init_node_memory_regions(struct pglist_data *pgdat)
+{
+	int nid = pgdat->node_id;
+	unsigned long start_pfn = pgdat->node_start_pfn;
+	unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages;
+	struct node_mem_region *region;
+	unsigned long i, absent;
+	int idx;
+
+	for (i = start_pfn, idx = 0; i < end_pfn;
+				i += region->spanned_pages, idx++) {
+
+		region = &pgdat->node_regions[idx];
+		region->pgdat = pgdat;
+		region->start_pfn = i;
+		region->spanned_pages = min(MEM_REGION_SIZE, end_pfn - i);
+		region->end_pfn = region->start_pfn + region->spanned_pages;
+
+		absent = __absent_pages_in_range(nid, region->start_pfn,
+						 region->end_pfn);
+
+		region->present_pages = region->spanned_pages - absent;
+	}
+
+	pgdat->nr_node_regions = idx;
+}
+
 void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 		unsigned long node_start_pfn, unsigned long *zholes_size)
 {
@@ -4837,6 +4864,7 @@  void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 
 	free_area_init_core(pgdat, start_pfn, end_pfn,
 			    zones_size, zholes_size);
+	init_node_memory_regions(pgdat);
 }
 
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP