summaryrefslogtreecommitdiffstats
path: root/mm/memory_hotplug.c
diff options
context:
space:
mode:
authorMichal Hocko <mhocko@suse.com>2017-09-06 16:19:40 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2017-09-06 17:27:25 -0700
commitc6f03e2903c9ecd8fd709a5b3fa8cf0a8ae0b3da (patch)
tree24ef4fabcf71dc247298b8b1bb464325ad7dd778 /mm/memory_hotplug.c
parente5e68930263377c6d4f6da0ff06f36b55d83a83f (diff)
downloadlinux-c6f03e2903c9ecd8fd709a5b3fa8cf0a8ae0b3da.tar.bz2
mm, memory_hotplug: remove zone restrictions
Historically we have enforced that any kernel zone (e.g ZONE_NORMAL) has to precede the Movable zone in the physical memory range. The purpose of the movable zone is, however, not bound to any physical memory restriction. It merely defines a class of migrateable and reclaimable memory. There are users (e.g. CMA) who might want to reserve specific physical memory ranges for their own purpose. Moreover our pfn walkers have to be prepared for zones overlapping in the physical range already because we do support interleaving NUMA nodes and therefore zones can interleave as well. This means we can allow each memory block to be associated with a different zone. Loosen the current onlining semantic and allow explicit onlining type on any memblock. That means that online_{kernel,movable} will be allowed regardless of the physical address of the memblock as long as it is offline of course. This might result in moveble zone overlapping with other kernel zones. Default onlining then becomes a bit tricky but still sensible. echo online > memoryXY/state will online the given block to 1) the default zone if the given range is outside of any zone 2) the enclosing zone if such a zone doesn't interleave with any other zone 3) the default zone if more zones interleave for this range where default zone is movable zone only if movable_node is enabled otherwise it is a kernel zone. Here is an example of the semantic with (movable_node is not present but it work in an analogous way). We start with following memblocks, all of them offline: memory34/valid_zones:Normal Movable memory35/valid_zones:Normal Movable memory36/valid_zones:Normal Movable memory37/valid_zones:Normal Movable memory38/valid_zones:Normal Movable memory39/valid_zones:Normal Movable memory40/valid_zones:Normal Movable memory41/valid_zones:Normal Movable Now, we online block 34 in default mode and block 37 as movable root@test1:/sys/devices/system/node/node1# echo online > memory34/state root@test1:/sys/devices/system/node/node1# echo online_movable > memory37/state memory34/valid_zones:Normal memory35/valid_zones:Normal Movable memory36/valid_zones:Normal Movable memory37/valid_zones:Movable memory38/valid_zones:Normal Movable memory39/valid_zones:Normal Movable memory40/valid_zones:Normal Movable memory41/valid_zones:Normal Movable As we can see all other blocks can still be onlined both into Normal and Movable zones and the Normal is default because the Movable zone spans only block37 now. root@test1:/sys/devices/system/node/node1# echo online_movable > memory41/state memory34/valid_zones:Normal memory35/valid_zones:Normal Movable memory36/valid_zones:Normal Movable memory37/valid_zones:Movable memory38/valid_zones:Movable Normal memory39/valid_zones:Movable Normal memory40/valid_zones:Movable Normal memory41/valid_zones:Movable Now the default zone for blocks 37-41 has changed because movable zone spans that range. root@test1:/sys/devices/system/node/node1# echo online_kernel > memory39/state memory34/valid_zones:Normal memory35/valid_zones:Normal Movable memory36/valid_zones:Normal Movable memory37/valid_zones:Movable memory38/valid_zones:Normal Movable memory39/valid_zones:Normal memory40/valid_zones:Movable Normal memory41/valid_zones:Movable Note that the block 39 now belongs to the zone Normal and so block38 falls into Normal by default as well. For completness root@test1:/sys/devices/system/node/node1# for i in memory[34]? do echo online > $i/state 2>/dev/null done memory34/valid_zones:Normal memory35/valid_zones:Normal memory36/valid_zones:Normal memory37/valid_zones:Movable memory38/valid_zones:Normal memory39/valid_zones:Normal memory40/valid_zones:Movable memory41/valid_zones:Movable Implementation wise the change is quite straightforward. We can get rid of allow_online_pfn_range altogether. online_pages allows only offline nodes already. The original default_zone_for_pfn will become default_kernel_zone_for_pfn. New default_zone_for_pfn implements the above semantic. zone_for_pfn_range is slightly reorganized to implement kernel and movable online type explicitly and MMOP_ONLINE_KEEP becomes a catch all default behavior. Link: http://lkml.kernel.org/r/20170714121233.16861-3-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Reza Arbab <arbab@linux.vnet.ibm.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Yasuaki Ishimatsu <yasu.isimatu@gmail.com> Cc: Xishi Qiu <qiuxishi@huawei.com> Cc: Kani Toshimitsu <toshi.kani@hpe.com> Cc: <slaoub@gmail.com> Cc: Daniel Kiper <daniel.kiper@oracle.com> Cc: Igor Mammedov <imammedo@redhat.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Wei Yang <richard.weiyang@gmail.com> Cc: <linux-api@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/memory_hotplug.c')
-rw-r--r--mm/memory_hotplug.c74
1 files changed, 23 insertions, 51 deletions
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index e342624622a1..3e69984346da 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -831,7 +831,7 @@ void __ref move_pfn_range_to_zone(struct zone *zone,
* If no kernel zone covers this pfn range it will automatically go
* to the ZONE_NORMAL.
*/
-static struct zone *default_zone_for_pfn(int nid, unsigned long start_pfn,
+static struct zone *default_kernel_zone_for_pfn(int nid, unsigned long start_pfn,
unsigned long nr_pages)
{
struct pglist_data *pgdat = NODE_DATA(nid);
@@ -847,65 +847,40 @@ static struct zone *default_zone_for_pfn(int nid, unsigned long start_pfn,
return &pgdat->node_zones[ZONE_NORMAL];
}
-bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages, int online_type)
+static inline struct zone *default_zone_for_pfn(int nid, unsigned long start_pfn,
+ unsigned long nr_pages)
{
- struct pglist_data *pgdat = NODE_DATA(nid);
- struct zone *movable_zone = &pgdat->node_zones[ZONE_MOVABLE];
- struct zone *default_zone = default_zone_for_pfn(nid, pfn, nr_pages);
+ struct zone *kernel_zone = default_kernel_zone_for_pfn(nid, start_pfn,
+ nr_pages);
+ struct zone *movable_zone = &NODE_DATA(nid)->node_zones[ZONE_MOVABLE];
+ bool in_kernel = zone_intersects(kernel_zone, start_pfn, nr_pages);
+ bool in_movable = zone_intersects(movable_zone, start_pfn, nr_pages);
/*
- * TODO there shouldn't be any inherent reason to have ZONE_NORMAL
- * physically before ZONE_MOVABLE. All we need is they do not
- * overlap. Historically we didn't allow ZONE_NORMAL after ZONE_MOVABLE
- * though so let's stick with it for simplicity for now.
- * TODO make sure we do not overlap with ZONE_DEVICE
+ * We inherit the existing zone in a simple case where zones do not
+ * overlap in the given range
*/
- if (online_type == MMOP_ONLINE_KERNEL) {
- if (zone_is_empty(movable_zone))
- return true;
- return movable_zone->zone_start_pfn >= pfn + nr_pages;
- } else if (online_type == MMOP_ONLINE_MOVABLE) {
- return zone_end_pfn(default_zone) <= pfn;
- }
-
- /* MMOP_ONLINE_KEEP will always succeed and inherits the current zone */
- return online_type == MMOP_ONLINE_KEEP;
-}
-
-static inline bool movable_pfn_range(int nid, struct zone *default_zone,
- unsigned long start_pfn, unsigned long nr_pages)
-{
- if (!allow_online_pfn_range(nid, start_pfn, nr_pages,
- MMOP_ONLINE_KERNEL))
- return true;
-
- if (!movable_node_is_enabled())
- return false;
+ if (in_kernel ^ in_movable)
+ return (in_kernel) ? kernel_zone : movable_zone;
- return !zone_intersects(default_zone, start_pfn, nr_pages);
+ /*
+ * If the range doesn't belong to any zone or two zones overlap in the
+ * given range then we use movable zone only if movable_node is
+ * enabled because we always online to a kernel zone by default.
+ */
+ return movable_node_enabled ? movable_zone : kernel_zone;
}
struct zone * zone_for_pfn_range(int online_type, int nid, unsigned start_pfn,
unsigned long nr_pages)
{
- struct pglist_data *pgdat = NODE_DATA(nid);
- struct zone *zone = default_zone_for_pfn(nid, start_pfn, nr_pages);
+ if (online_type == MMOP_ONLINE_KERNEL)
+ return default_kernel_zone_for_pfn(nid, start_pfn, nr_pages);
- if (online_type == MMOP_ONLINE_KEEP) {
- struct zone *movable_zone = &pgdat->node_zones[ZONE_MOVABLE];
- /*
- * MMOP_ONLINE_KEEP defaults to MMOP_ONLINE_KERNEL but use
- * movable zone if that is not possible (e.g. we are within
- * or past the existing movable zone). movable_node overrides
- * this default and defaults to movable zone
- */
- if (movable_pfn_range(nid, zone, start_pfn, nr_pages))
- zone = movable_zone;
- } else if (online_type == MMOP_ONLINE_MOVABLE) {
- zone = &pgdat->node_zones[ZONE_MOVABLE];
- }
+ if (online_type == MMOP_ONLINE_MOVABLE)
+ return &NODE_DATA(nid)->node_zones[ZONE_MOVABLE];
- return zone;
+ return default_zone_for_pfn(nid, start_pfn, nr_pages);
}
/*
@@ -934,9 +909,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ
struct memory_notify arg;
nid = pfn_to_nid(pfn);
- if (!allow_online_pfn_range(nid, pfn, nr_pages, online_type))
- return -EINVAL;
-
/* associate pfn range with the zone */
zone = move_pfn_range(online_type, nid, pfn, nr_pages);