mm, memory_hotplug: do not assume ZONE_NORMAL is default kernel zone

Heiko Carstens has noticed that he can generate overlapping zones for
ZONE_DMA and ZONE_NORMAL:

  DMA      [mem 0x0000000000000000-0x000000007fffffff]
  Normal   [mem 0x0000000080000000-0x000000017fffffff]

  $ cat /sys/devices/system/memory/block_size_bytes
  10000000
  $ cat /sys/devices/system/memory/memory5/valid_zones
  DMA
  $ echo 0 > /sys/devices/system/memory/memory5/online
  $ cat /sys/devices/system/memory/memory5/valid_zones
  Normal
  $ echo 1 > /sys/devices/system/memory/memory5/online
  Normal

  $ cat /proc/zoneinfo
  Node 0, zone      DMA
  spanned  524288        <-----
  present  458752
  managed  455078
  start_pfn:           0 <-----

  Node 0, zone   Normal
  spanned  720896
  present  589824
  managed  571648
  start_pfn:           327680 <-----

The reason is that we assume that the default zone for kernel onlining
is ZONE_NORMAL.  This was a simplification introduced by the memory
hotplug rework and it is easily fixable by checking the range overlap in
the zone order and considering the first matching zone as the default
one.  If there is no such zone then assume ZONE_NORMAL as we have been
doing so far.

Fixes: "mm, memory_hotplug: do not associate hotadded memory to zones until online"
Link: http://lkml.kernel.org/r/20170601083746.4924-3-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Reported-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Tested-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Reza Arbab <arbab@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index b86fda30ce62bc3ac1bda245baac7198a28743d7..c7c4e0325cdb6e42d97f510749c715eacf1cb247 100644 (file)
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -419,7 +419,7 @@ static ssize_t show_valid_zones(struct device *dev,
 
        nid = pfn_to_nid(start_pfn);
        if (allow_online_pfn_range(nid, start_pfn, nr_pages, MMOP_ONLINE_KERNEL)) {
-               strcat(buf, NODE_DATA(nid)->node_zones[ZONE_NORMAL].name);
+               strcat(buf, default_zone_for_pfn(nid, start_pfn, nr_pages)->name);
                append = true;
        }
 

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 8a07a49fd8dc2280fc228ec6b0091c7e8df848e4..4d65a2fcac150c9f376e45082549af5e33692c40 100644 (file)
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -311,4 +311,6 @@ extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
                                          unsigned long pnum);
 extern bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages,
                int online_type);
+extern struct zone *default_zone_for_pfn(int nid, unsigned long pfn,
+               unsigned long nr_pages);
 #endif /* __LINUX_MEMORY_HOTPLUG_H */

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 1a20e44635d34875befa796196778040069d73a3..4263fa6f2ab410ef07638ad8f9b99fd273bd49a3 100644 (file)
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1028,7 +1028,7 @@ bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages,
 {
        struct pglist_data *pgdat = NODE_DATA(nid);
        struct zone *movable_zone = &pgdat->node_zones[ZONE_MOVABLE];
-       struct zone *normal_zone =  &pgdat->node_zones[ZONE_NORMAL];
+       struct zone *default_zone = default_zone_for_pfn(nid, pfn, nr_pages);
 
        /*
         * TODO there shouldn't be any inherent reason to have ZONE_NORMAL
@@ -1042,7 +1042,7 @@ bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages,
                        return true;
                return movable_zone->zone_start_pfn >= pfn + nr_pages;
        } else if (online_type == MMOP_ONLINE_MOVABLE) {
-               return zone_end_pfn(normal_zone) <= pfn;
+               return zone_end_pfn(default_zone) <= pfn;
        }
 
        /* MMOP_ONLINE_KEEP will always succeed and inherits the current zone */
@@ -1102,6 +1102,27 @@ void move_pfn_range_to_zone(struct zone *zone,
        set_zone_contiguous(zone);
 }
 
+/*
+ * Returns a default kernel memory zone for the given pfn range.
+ * If no kernel zone covers this pfn range it will automatically go
+ * to the ZONE_NORMAL.
+ */
+struct zone *default_zone_for_pfn(int nid, unsigned long start_pfn,
+               unsigned long nr_pages)
+{
+       struct pglist_data *pgdat = NODE_DATA(nid);
+       int zid;
+
+       for (zid = 0; zid <= ZONE_NORMAL; zid++) {
+               struct zone *zone = &pgdat->node_zones[zid];
+
+               if (zone_intersects(zone, start_pfn, nr_pages))
+                       return zone;
+       }
+
+       return &pgdat->node_zones[ZONE_NORMAL];
+}
+
 /*
  * Associates the given pfn range with the given node and the zone appropriate
  * for the given online type.
@@ -1110,7 +1131,7 @@ static struct zone * __meminit move_pfn_range(int online_type, int nid,
                unsigned long start_pfn, unsigned long nr_pages)
 {
        struct pglist_data *pgdat = NODE_DATA(nid);
-       struct zone *zone = &pgdat->node_zones[ZONE_NORMAL];
+       struct zone *zone = default_zone_for_pfn(nid, start_pfn, nr_pages);
 
        if (online_type == MMOP_ONLINE_KEEP) {
                struct zone *movable_zone = &pgdat->node_zones[ZONE_MOVABLE];