These changes are the raw update to linux-4.4.6-rt14. Kernel sources

[kvmfornfv.git] / kernel / mm / memory_hotplug.c

diff --git a/kernel/mm/memory_hotplug.c b/kernel/mm/memory_hotplug.c
index 9e88f74..a042a9d 100644 (file)
--- a/kernel/mm/memory_hotplug.c
+++ b/kernel/mm/memory_hotplug.c
@@ -339,8 +339,8 @@ static int __ref ensure_zone_is_initialized(struct zone *zone,
                        unsigned long start_pfn, unsigned long num_pages)
 {
        if (!zone_is_initialized(zone))
-               return init_currently_empty_zone(zone, start_pfn, num_pages,
-                                                MEMMAP_HOTPLUG);
+               return init_currently_empty_zone(zone, start_pfn, num_pages);
+
        return 0;
 }
 
@@ -446,7 +446,7 @@ static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn)
        int nr_pages = PAGES_PER_SECTION;
        int nid = pgdat->node_id;
        int zone_type;
-       unsigned long flags;
+       unsigned long flags, pfn;
        int ret;
 
        zone_type = zone - pgdat->node_zones;
@@ -461,6 +461,14 @@ static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn)
        pgdat_resize_unlock(zone->zone_pgdat, &flags);
        memmap_init_zone(nr_pages, nid, zone_type,
                         phys_start_pfn, MEMMAP_HOTPLUG);
+
+       /* online_page_range is called later and expects pages reserved */
+       for (pfn = phys_start_pfn; pfn < phys_start_pfn + nr_pages; pfn++) {
+               if (!pfn_valid(pfn))
+                       continue;
+
+               SetPageReserved(pfn_to_page(pfn));
+       }
        return 0;
 }
 
@@ -513,6 +521,7 @@ int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn,
                        break;
                err = 0;
        }
+       vmemmap_populate_print_last();
 
        return err;
 }
@@ -769,7 +778,10 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
 
        start = phys_start_pfn << PAGE_SHIFT;
        size = nr_pages * PAGE_SIZE;
-       ret = release_mem_region_adjustable(&iomem_resource, start, size);
+
+       /* in the ZONE_DEVICE case device driver owns the memory region */
+       if (!is_dev_zone(zone))
+               ret = release_mem_region_adjustable(&iomem_resource, start, size);
        if (ret) {
                resource_size_t endres = start + size - 1;
 
@@ -1206,8 +1218,13 @@ static int should_add_memory_movable(int nid, u64 start, u64 size)
        return 0;
 }
 
-int zone_for_memory(int nid, u64 start, u64 size, int zone_default)
+int zone_for_memory(int nid, u64 start, u64 size, int zone_default,
+               bool for_device)
 {
+#ifdef CONFIG_ZONE_DEVICE
+       if (for_device)
+               return ZONE_DEVICE;
+#endif
        if (should_add_memory_movable(nid, start, size))
                return ZONE_MOVABLE;
 
@@ -1215,23 +1232,21 @@ int zone_for_memory(int nid, u64 start, u64 size, int zone_default)
 }
 
 /* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
-int __ref add_memory(int nid, u64 start, u64 size)
+int __ref add_memory_resource(int nid, struct resource *res)
 {
+       u64 start, size;
        pg_data_t *pgdat = NULL;
        bool new_pgdat;
        bool new_node;
-       struct resource *res;
        int ret;
 
+       start = res->start;
+       size = resource_size(res);
+
        ret = check_hotplug_memory_range(start, size);
        if (ret)
                return ret;
 
-       res = register_memory_resource(start, size);
-       ret = -EEXIST;
-       if (!res)
-               return ret;
-
        {       /* Stupid hack to suppress address-never-null warning */
                void *p = NODE_DATA(nid);
                new_pgdat = !p;
@@ -1239,6 +1254,14 @@ int __ref add_memory(int nid, u64 start, u64 size)
 
        mem_hotplug_begin();
 
+       /*
+        * Add new range to memblock so that when hotadd_new_pgdat() is called
+        * to allocate new pgdat, get_pfn_range_for_nid() will be able to find
+        * this new range and calculate total pages correctly.  The range will
+        * be removed at hot-remove time.
+        */
+       memblock_add_node(start, size, nid);
+
        new_node = !node_online(nid);
        if (new_node) {
                pgdat = hotadd_new_pgdat(nid, start);
@@ -1248,7 +1271,7 @@ int __ref add_memory(int nid, u64 start, u64 size)
        }
 
        /* call arch's memory hotadd */
-       ret = arch_add_memory(nid, start, size);
+       ret = arch_add_memory(nid, start, size, false);
 
        if (ret < 0)
                goto error;
@@ -1275,12 +1298,28 @@ error:
        /* rollback pgdat allocation and others */
        if (new_pgdat)
                rollback_node_hotadd(nid, pgdat);
-       release_memory_resource(res);
+       memblock_remove(start, size);
 
 out:
        mem_hotplug_done();
        return ret;
 }
+EXPORT_SYMBOL_GPL(add_memory_resource);
+
+int __ref add_memory(int nid, u64 start, u64 size)
+{
+       struct resource *res;
+       int ret;
+
+       res = register_memory_resource(start, size);
+       if (!res)
+               return -EEXIST;
+
+       ret = add_memory_resource(nid, res);
+       if (ret < 0)
+               release_memory_resource(res);
+       return ret;
+}
 EXPORT_SYMBOL_GPL(add_memory);
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
@@ -1336,23 +1375,30 @@ int is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages)
  */
 int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
 {
-       unsigned long pfn;
+       unsigned long pfn, sec_end_pfn;
        struct zone *zone = NULL;
        struct page *page;
        int i;
-       for (pfn = start_pfn;
+       for (pfn = start_pfn, sec_end_pfn = SECTION_ALIGN_UP(start_pfn);
             pfn < end_pfn;
-            pfn += MAX_ORDER_NR_PAGES) {
-               i = 0;
-               /* This is just a CONFIG_HOLES_IN_ZONE check.*/
-               while ((i < MAX_ORDER_NR_PAGES) && !pfn_valid_within(pfn + i))
-                       i++;
-               if (i == MAX_ORDER_NR_PAGES)
+            pfn = sec_end_pfn + 1, sec_end_pfn += PAGES_PER_SECTION) {
+               /* Make sure the memory section is present first */
+               if (!present_section_nr(pfn_to_section_nr(pfn)))
                        continue;
-               page = pfn_to_page(pfn + i);
-               if (zone && page_zone(page) != zone)
-                       return 0;
-               zone = page_zone(page);
+               for (; pfn < sec_end_pfn && pfn < end_pfn;
+                    pfn += MAX_ORDER_NR_PAGES) {
+                       i = 0;
+                       /* This is just a CONFIG_HOLES_IN_ZONE check.*/
+                       while ((i < MAX_ORDER_NR_PAGES) &&
+                               !pfn_valid_within(pfn + i))
+                               i++;
+                       if (i == MAX_ORDER_NR_PAGES)
+                               continue;
+                       page = pfn_to_page(pfn + i);
+                       if (zone && page_zone(page) != zone)
+                               return 0;
+                       zone = page_zone(page);
+               }
        }
        return 1;
 }
@@ -2004,6 +2050,8 @@ void __ref remove_memory(int nid, u64 start, u64 size)
 
        /* remove memmap entry */
        firmware_map_remove(start, start + size, "System RAM");
+       memblock_free(start, size);
+       memblock_remove(start, size);
 
        arch_remove_memory(start, size);