s390/mm: fix zone calculation in arch_add_memory()

Standby (hotplug) memory should be added to ZONE_MOVABLE on s390. After
commit 199071f1 "s390/mm: make arch_add_memory() NUMA aware",
arch_add_memory() used memblock_end_of_DRAM() to find out the end of
ZONE_NORMAL and the beginning of ZONE_MOVABLE. However, commit 7f36e3e5
"memory-hotplug: add hot-added memory ranges to memblock before allocate
node_data for a node." moved the call of memblock_add_node() before
the call of arch_add_memory() in add_memory_resource(), and thus changed
the return value of memblock_end_of_DRAM() when called in
arch_add_memory(). As a result, arch_add_memory() will think that all
memory blocks should be added to ZONE_NORMAL.

Fix this by changing the logic in arch_add_memory() so that it will
manually iterate over all zones of a given node to find out which zone
a memory block should be added to.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index f56a39b..b3e9d18 100644 (file)
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -151,36 +151,40 @@ void __init free_initrd_mem(unsigned long start, unsigned long end)
 #ifdef CONFIG_MEMORY_HOTPLUG
 int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
 {
-       unsigned long normal_end_pfn = PFN_DOWN(memblock_end_of_DRAM());
-       unsigned long dma_end_pfn = PFN_DOWN(MAX_DMA_ADDRESS);
+       unsigned long zone_start_pfn, zone_end_pfn, nr_pages;
        unsigned long start_pfn = PFN_DOWN(start);
        unsigned long size_pages = PFN_DOWN(size);
-       unsigned long nr_pages;
-       int rc, zone_enum;
+       pg_data_t *pgdat = NODE_DATA(nid);
+       struct zone *zone;
+       int rc, i;
 
        rc = vmem_add_mapping(start, size);
        if (rc)
                return rc;
 
-       while (size_pages > 0) {
-               if (start_pfn < dma_end_pfn) {
-                       nr_pages = (start_pfn + size_pages > dma_end_pfn) ?
-                                  dma_end_pfn - start_pfn : size_pages;
-                       zone_enum = ZONE_DMA;
-               } else if (start_pfn < normal_end_pfn) {
-                       nr_pages = (start_pfn + size_pages > normal_end_pfn) ?
-                                  normal_end_pfn - start_pfn : size_pages;
-                       zone_enum = ZONE_NORMAL;
+       for (i = 0; i < MAX_NR_ZONES; i++) {
+               zone = pgdat->node_zones + i;
+               if (zone_idx(zone) != ZONE_MOVABLE) {
+                       /* Add range within existing zone limits, if possible */
+                       zone_start_pfn = zone->zone_start_pfn;
+                       zone_end_pfn = zone->zone_start_pfn +
+                                      zone->spanned_pages;
                } else {
-                       nr_pages = size_pages;
-                       zone_enum = ZONE_MOVABLE;
+                       /* Add remaining range to ZONE_MOVABLE */
+                       zone_start_pfn = start_pfn;
+                       zone_end_pfn = start_pfn + size_pages;
                }
-               rc = __add_pages(nid, NODE_DATA(nid)->node_zones + zone_enum,
-                                start_pfn, size_pages);
+               if (start_pfn < zone_start_pfn || start_pfn >= zone_end_pfn)
+                       continue;
+               nr_pages = (start_pfn + size_pages > zone_end_pfn) ?
+                          zone_end_pfn - start_pfn : size_pages;
+               rc = __add_pages(nid, zone, start_pfn, nr_pages);
                if (rc)
                        break;
                start_pfn += nr_pages;
                size_pages -= nr_pages;
+               if (!size_pages)
+                       break;
        }
        if (rc)
                vmem_remove_mapping(start, size);