On 2012-12-6 9:26, Tang Chen wrote:
> On 12/05/2012 11:43 PM, Jiang Liu wrote:
>> If we make "movablecore_map" take precedence over "movablecore/kernelcore",
>> the logic could be simplified. I think it's not so attractive to support
>> both "movablecore_map" and "movablecore/kernelcore" at the same time.
>
> Hi Liu,
>
> Thanks for you advice. :)
>
> Memory hotplug needs different support on different hardware. We are
> trying to figure out a way to satisfy as many users as we can.
> Since it is a little difficult, it may take sometime. :)
>
> But I still think we need a boot option to support it. Just a metter of
> how to make it easier to use. :)
>
> Thanks. :)
>
>>
>> On 11/23/2012 06:44 PM, Tang Chen wrote:
>>> If kernelcore or movablecore is specified at the same time
>>> with movablecore_map, movablecore_map will have higher
>>> priority to be satisfied.
>>> This patch will make find_zone_movable_pfns_for_nodes()
>>> calculate zone_movable_pfn[] with the limit from
>>> zone_movable_limit[].
>>>
>>> Signed-off-by: Tang Chen<tangchen@xxxxxxxxxxxxxx>
>>> Reviewed-by: Wen Congyang<wency@xxxxxxxxxxxxxx>
>>> Reviewed-by: Lai Jiangshan<laijs@xxxxxxxxxxxxxx>
>>> Tested-by: Lin Feng<linfeng@xxxxxxxxxxxxxx>
>>> ---
>>> mm/page_alloc.c | 35 +++++++++++++++++++++++++++++++----
>>> 1 files changed, 31 insertions(+), 4 deletions(-)
>>>
>>> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
>>> index f23d76a..05bafbb 100644
>>> --- a/mm/page_alloc.c
>>> +++ b/mm/page_alloc.c
>>> @@ -4800,12 +4800,25 @@ static void __init find_zone_movable_pfns_for_nodes(void)
>>> required_kernelcore = max(required_kernelcore, corepages);
>>> }
>>>
>>> - /* If kernelcore was not specified, there is no ZONE_MOVABLE */
>>> - if (!required_kernelcore)
>>> + /*
>>> + * No matter kernelcore/movablecore was limited or not, movable_zone
>>> + * should always be set to a usable zone index.
>>> + */
>>> + find_usable_zone_for_movable();
>>> +
>>> + /*
>>> + * If neither kernelcore/movablecore nor movablecore_map is specified,
>>> + * there is no ZONE_MOVABLE. But if movablecore_map is specified, the
>>> + * start pfn of ZONE_MOVABLE has been stored in zone_movable_limit[].
>>> + */
>>> + if (!required_kernelcore) {
>>> + if (movablecore_map.nr_map)
>>> + memcpy(zone_movable_pfn, zone_movable_limit,
>>> + sizeof(zone_movable_pfn));
>>> goto out;
>>> + }
>>>
>>> /* usable_startpfn is the lowest possible pfn ZONE_MOVABLE can be at */
>>> - find_usable_zone_for_movable();
>>> usable_startpfn = arch_zone_lowest_possible_pfn[movable_zone];
>>>
>>> restart:
>>> @@ -4833,10 +4846,24 @@ restart:
>>> for_each_mem_pfn_range(i, nid,&start_pfn,&end_pfn, NULL) {
>>> unsigned long size_pages;
>>>
>>> + /*
>>> + * Find more memory for kernelcore in
>>> + * [zone_movable_pfn[nid], zone_movable_limit[nid]).
>>> + */
>>> start_pfn = max(start_pfn, zone_movable_pfn[nid]);
>>> if (start_pfn>= end_pfn)
>>> continue;
>>>
>>> + if (zone_movable_limit[nid]) {
>>> + end_pfn = min(end_pfn, zone_movable_limit[nid]);
>>> + /* No range left for kernelcore in this node */
>>> + if (start_pfn>= end_pfn) {
>>> + zone_movable_pfn[nid] =
>>> + zone_movable_limit[nid];
>>> + break;
>>> + }
>>> + }
Hi Tang,
I just to remove the above logic, so the implementation will be greatly
simplified. Please refer to the attachment.
Regards!
Gerry
>>> +
>>> /* Account for what is only usable for kernelcore */
>>> if (start_pfn< usable_startpfn) {
>>> unsigned long kernel_pages;
>>> @@ -4896,12 +4923,12 @@ restart:
>>> if (usable_nodes&& required_kernelcore> usable_nodes)
>>> goto restart;
>>>
>>> +out:
>>> /* Align start of ZONE_MOVABLE on all nids to MAX_ORDER_NR_PAGES */
>>> for (nid = 0; nid< MAX_NUMNODES; nid++)
>>> zone_movable_pfn[nid] =
>>> roundup(zone_movable_pfn[nid], MAX_ORDER_NR_PAGES);
>>>
>>> -out:
>>> /* restore the node_state */
>>> node_states[N_HIGH_MEMORY] = saved_node_state;
>>> }
>>>
>>
>>
>
>
> .
>
>From 120759daa8410e1bf61d19210ddeb52ef32d002a Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@xxxxxxxxxx>
Date: Wed, 5 Dec 2012 23:58:42 +0800
Subject: [PATCH 3/6] page_alloc: Introduce zone_movable_limit[] to keep
movable limit for nodes
This patch introduces a new array zone_movable_limit[] to store the
ZONE_MOVABLE limit from movablecore_map boot option for all nodes.
The function sanitize_zone_movable_limit() will find out to which
node the ranges in movable_map.map[] belongs, and calculates the
low boundary of ZONE_MOVABLE for each node.
Signed-off-by: Tang Chen <tangchen@xxxxxxxxxxxxxx>
Reviewed-by: Wen Congyang <wency@xxxxxxxxxxxxxx>
Reviewed-by: Lai Jiangshan <laijs@xxxxxxxxxxxxxx>
Tested-by: Lin Feng <linfeng@xxxxxxxxxxxxxx>
page_alloc: Make movablecore_map has higher priority
If kernelcore or movablecore is specified at the same time
with movablecore_map, movablecore_map will have higher
priority to be satisfied.
This patch will make find_zone_movable_pfns_for_nodes()
calculate zone_movable_pfn[] with the limit from
zone_movable_limit[].
Signed-off-by: Tang Chen <tangchen@xxxxxxxxxxxxxx>
Reviewed-by: Wen Congyang <wency@xxxxxxxxxxxxxx>
Reviewed-by: Lai Jiangshan <laijs@xxxxxxxxxxxxxx>
Tested-by: Lin Feng <linfeng@xxxxxxxxxxxxxx>
---
mm/page_alloc.c | 66 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 65 insertions(+), 1 deletion(-)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e35ee27..41c3b51 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4338,6 +4338,60 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid,
return __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn);
}
+/**
+ * Try to figure out zone_movable_pfn[] from movablecore_map.
+ */
+static int __init find_zone_movable_from_movablecore_map(void)
+{
+ int map_pos = 0, i, nid;
+ unsigned long start_pfn, end_pfn;
+
+ if (!movablecore_map.nr_map)
+ return 0;
+
+ /* Iterate all ranges from minimum to maximum */
+ for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
+ /*
+ * If we have found lowest pfn of ZONE_MOVABLE of the node
+ * specified by user, just go on to check next range.
+ */
+ if (zone_movable_pfn[nid])
+ continue;
+
+#ifdef CONFIG_HIGHMEM
+ /* Skip lowmem if ZONE_MOVABLE is highmem */
+ if (zone_movable_is_highmem() &&
+ start_pfn < arch_zone_lowest_possible_pfn[ZONE_HIGHMEM])
+ start_pfn = arch_zone_lowest_possible_pfn[ZONE_HIGHMEM];
+ if (start_pfn > end_pfn)
+ continue;
+#endif
+
+ while (map_pos < movablecore_map.nr_map) {
+ if (end_pfn < movablecore_map.map[map_pos].start)
+ break;
+
+ if (start_pfn > movablecore_map.map[map_pos].end) {
+ map_pos++;
+ continue;
+ }
+
+ /*
+ * The start_pfn of ZONE_MOVABLE is either the minimum
+ * pfn specified by movablecore_map, or 0, which means
+ * the node has no ZONE_MOVABLE.
+ */
+ start_pfn = max(start_pfn,
+ movablecore_map.map[map_pos].start);
+ zone_movable_pfn[nid] = roundup(zone_movable_pfn[nid],
+ MAX_ORDER_NR_PAGES);
+ break;
+ }
+ }
+
+ return 1;
+}
+
#else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
static inline unsigned long __meminit zone_spanned_pages_in_node(int nid,
unsigned long zone_type,
@@ -4356,6 +4410,11 @@ static inline unsigned long __meminit zone_absent_pages_in_node(int nid,
return zholes_size[zone_type];
}
+static int __init find_zone_movable_from_movablecore_map(void)
+{
+ return 0;
+}
+
#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
static void __meminit calculate_node_totalpages(struct pglist_data *pgdat,
@@ -4739,6 +4798,12 @@ static void __init find_zone_movable_pfns_for_nodes(void)
unsigned long totalpages = early_calculate_totalpages();
int usable_nodes = nodes_weight(node_states[N_HIGH_MEMORY]);
+ find_usable_zone_for_movable();
+
+ /* movablecore_map takes precedence over movablecore/kernelcore */
+ if (find_zone_movable_from_movablecore_map())
+ return;
+
/*
* If movablecore was specified, calculate what size of
* kernelcore that corresponds so that memory usable for
@@ -4766,7 +4831,6 @@ static void __init find_zone_movable_pfns_for_nodes(void)
goto out;
/* usable_startpfn is the lowest possible pfn ZONE_MOVABLE can be at */
- find_usable_zone_for_movable();
usable_startpfn = arch_zone_lowest_possible_pfn[movable_zone];
restart:
--
1.7.9.5