[PATCH] pgdat allocation for new node add (specify node id)

Change the name of old add_memory() to arch_add_memory.  And use node id to
get pgdat for the node at NODE_DATA().

Note: Powerpc's old add_memory() is defined as __devinit. However,
      add_memory() is usually called only after bootup.
      I suppose it may be redundant. But, I'm not well known about powerpc.
      So, I keep it. (But, __meminit is better at least.)

Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Dave Hansen <haveblue@us.ibm.com>
Cc: "Brown, Len" <len.brown@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

9 files changed, 78 insertions, 39 deletions

diff --git a/arch/i386/mm/init.c b/arch/i386/mm/init.c
index bf19513f0cea..468592531793 100644
--- a/arch/i386/mm/init.c
+++ b/arch/i386/mm/init.c
@@ -654,7 +654,7 @@ void __init mem_init(void)
  */
 #ifdef CONFIG_MEMORY_HOTPLUG
 #ifndef CONFIG_NEED_MULTIPLE_NODES
-int add_memory(u64 start, u64 size)
+int arch_add_memory(int nid, u64 start, u64 size)
 {
         struct pglist_data *pgdata = &contig_page_data;
         struct zone *zone = pgdata->node_zones + MAX_NR_ZONES-1;
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 11f08001f8c2..38306e98f04b 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -652,7 +652,7 @@ void online_page(struct page *page)
         num_physpages++;
 }
 
-int add_memory(u64 start, u64 size)
+int arch_add_memory(int nid, u64 start, u64 size)
 {
         pg_data_t *pgdat;
         struct zone *zone;
@@ -660,7 +660,7 @@ int add_memory(u64 start, u64 size)
         unsigned long nr_pages = size >> PAGE_SHIFT;
         int ret;
 
-        pgdat = NODE_DATA(0);
+        pgdat = NODE_DATA(nid);
 
         zone = pgdat->node_zones + ZONE_NORMAL;
         ret = __add_pages(zone, start_pfn, nr_pages);
@@ -671,7 +671,6 @@ int add_memory(u64 start, u64 size)
 
         return ret;
 }
-EXPORT_SYMBOL_GPL(add_memory);
 
 int remove_memory(u64 start, u64 size)
 {
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 69f3b9a20beb..089d939a0b3e 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -114,15 +114,20 @@ void online_page(struct page *page)
         num_physpages++;
 }
 
-int __devinit add_memory(u64 start, u64 size)
+#ifdef CONFIG_NUMA
+int memory_add_physaddr_to_nid(u64 start)
+{
+        return hot_add_scn_to_nid(start);
+}
+#endif
+
+int __devinit arch_add_memory(int nid, u64 start, u64 size)
 {
         struct pglist_data *pgdata;
         struct zone *zone;
-        int nid;
         unsigned long start_pfn = start >> PAGE_SHIFT;
         unsigned long nr_pages = size >> PAGE_SHIFT;
 
-        nid = hot_add_scn_to_nid(start);
         pgdata = NODE_DATA(nid);
 
         start = (unsigned long)__va(start);
diff --git a/arch/x86_64/mm/init.c b/arch/x86_64/mm/init.c
index 02add1d1dfa8..51fbf3eddf13 100644
--- a/arch/x86_64/mm/init.c
+++ b/arch/x86_64/mm/init.c
@@ -506,8 +506,6 @@ void __init clear_kernel_mapping(unsigned long address, unsigned long size)
 /*
  * Memory hotplug specific functions
  */
-#if defined(CONFIG_ACPI_HOTPLUG_MEMORY) || defined(CONFIG_ACPI_HOTPLUG_MEMORY_MODULE)
-
 void online_page(struct page *page)
 {
         ClearPageReserved(page);
@@ -517,31 +515,17 @@ void online_page(struct page *page)
         num_physpages++;
 }
 
-#ifndef CONFIG_MEMORY_HOTPLUG
+#ifdef CONFIG_MEMORY_HOTPLUG
 /*
- * Memory Hotadd without sparsemem. The mem_maps have been allocated in advance,
- * just online the pages.
+ * XXX: memory_add_physaddr_to_nid() is to find node id from physical address
+ *      via probe interface of sysfs. If acpi notifies hot-add event, then it
+ *      can tell node id by searching dsdt. But, probe interface doesn't have
+ *      node id. So, return 0 as node id at this time.
  */
-int __add_pages(struct zone *z, unsigned long start_pfn, unsigned long nr_pages)
+#ifdef CONFIG_NUMA
+int memory_add_physaddr_to_nid(u64 start)
 {
-        int err = -EIO;
-        unsigned long pfn;
-        unsigned long total = 0, mem = 0;
-        for (pfn = start_pfn; pfn < start_pfn + nr_pages; pfn++) {
-                if (pfn_valid(pfn)) {
-                        online_page(pfn_to_page(pfn));
-                        err = 0;
-                        mem++;
-                }
-                total++;
-        }
-        if (!err) {
-                z->spanned_pages += total;
-                z->present_pages += mem;
-                z->zone_pgdat->node_spanned_pages += total;
-                z->zone_pgdat->node_present_pages += mem;
-        }
-        return err;
+        return 0;
 }
 #endif
 
@@ -549,9 +533,9 @@ int __add_pages(struct zone *z, unsigned long start_pfn, unsigned long nr_pages)
  * Memory is added always to NORMAL zone. This means you will never get
  * additional DMA/DMA32 memory.
  */
-int add_memory(u64 start, u64 size)
+int arch_add_memory(int nid, u64 start, u64 size)
 {
-        struct pglist_data *pgdat = NODE_DATA(0);
+        struct pglist_data *pgdat = NODE_DATA(nid);
         struct zone *zone = pgdat->node_zones + MAX_NR_ZONES-2;
         unsigned long start_pfn = start >> PAGE_SHIFT;
         unsigned long nr_pages = size >> PAGE_SHIFT;
@@ -568,7 +552,7 @@ error:
         printk("%s: Problem encountered in __add_pages!\n", __func__);
         return ret;
 }
-EXPORT_SYMBOL_GPL(add_memory);
+EXPORT_SYMBOL_GPL(arch_add_memory);
 
 int remove_memory(u64 start, u64 size)
 {
@@ -576,7 +560,33 @@ int remove_memory(u64 start, u64 size)
 }
 EXPORT_SYMBOL_GPL(remove_memory);
 
-#endif
+#else /* CONFIG_MEMORY_HOTPLUG */
+/*
+ * Memory Hotadd without sparsemem. The mem_maps have been allocated in advance,
+ * just online the pages.
+ */
+int __add_pages(struct zone *z, unsigned long start_pfn, unsigned long nr_pages)
+{
+        int err = -EIO;
+        unsigned long pfn;
+        unsigned long total = 0, mem = 0;
+        for (pfn = start_pfn; pfn < start_pfn + nr_pages; pfn++) {
+                if (pfn_valid(pfn)) {
+                        online_page(pfn_to_page(pfn));
+                        err = 0;
+                        mem++;
+                }
+                total++;
+        }
+        if (!err) {
+                z->spanned_pages += total;
+                z->present_pages += mem;
+                z->zone_pgdat->node_spanned_pages += total;
+                z->zone_pgdat->node_present_pages += mem;
+        }
+        return err;
+}
+#endif /* CONFIG_MEMORY_HOTPLUG */
 
 static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel, kcore_modules,
                          kcore_vsyscall;
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 94b8d820c512..610d2cc02cf8 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -328,7 +328,7 @@ config ACPI_CONTAINER
 config ACPI_HOTPLUG_MEMORY
         tristate "Memory Hotplug"
         depends on ACPI
-        depends on MEMORY_HOTPLUG || X86_64
+        depends on MEMORY_HOTPLUG
         default n
         help
           This driver adds supports for ACPI Memory Hotplug.  This driver
diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c
index 5652569b3762..0424326eae15 100644
--- a/drivers/acpi/acpi_memhotplug.c
+++ b/drivers/acpi/acpi_memhotplug.c
@@ -215,6 +215,7 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device)
 {
         int result, num_enabled = 0;
         struct acpi_memory_info *info;
+        int node = 0;
 
         ACPI_FUNCTION_TRACE("acpi_memory_enable_device");
 
@@ -245,7 +246,7 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device)
                         continue;
                 }
 
-                result = add_memory(info->start_addr, info->length);
+                result = add_memory(node, info->start_addr, info->length);
                 if (result)
                         continue;
                 info->enabled = 1;
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index dd547af4681a..c6b7d9c4b651 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -306,11 +306,13 @@ static ssize_t
 memory_probe_store(struct class *class, const char *buf, size_t count)
 {
         u64 phys_addr;
+        int nid;
         int ret;
 
         phys_addr = simple_strtoull(buf, NULL, 0);
 
-        ret = add_memory(phys_addr, PAGES_PER_SECTION << PAGE_SHIFT);
+        nid = memory_add_physaddr_to_nid(phys_addr);
+        ret = add_memory(nid, phys_addr, PAGES_PER_SECTION << PAGE_SHIFT);
 
         if (ret)
                 count = ret;
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 911206386171..29c1472efad0 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -63,6 +63,16 @@ extern int online_pages(unsigned long, unsigned long);
 /* reasonably generic interface to expand the physical pages in a zone  */
 extern int __add_pages(struct zone *zone, unsigned long start_pfn,
         unsigned long nr_pages);
+
+#ifdef CONFIG_NUMA
+extern int memory_add_physaddr_to_nid(u64 start);
+#else
+static inline int memory_add_physaddr_to_nid(u64 start)
+{
+        return 0;
+}
+#endif
+
 #else /* ! CONFIG_MEMORY_HOTPLUG */
 /*
  * Stub functions for when hotplug is off
@@ -99,7 +109,8 @@ static inline int __remove_pages(struct zone *zone, unsigned long start_pfn,
         return -ENOSYS;
 }
 
-extern int add_memory(u64 start, u64 size);
+extern int add_memory(int nid, u64 start, u64 size);
+extern int arch_add_memory(int nid, u64 start, u64 size);
 extern int remove_memory(u64 start, u64 size);
 
 #endif /* __LINUX_MEMORY_HOTPLUG_H */
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 841a077d5aeb..6cdeabe9f6d4 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -163,3 +163,14 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
         vm_total_pages = nr_free_pagecache_pages();
         return 0;
 }
+
+int add_memory(int nid, u64 start, u64 size)
+{
+        int ret;
+
+        /* call arch's memory hotadd */
+        ret = arch_add_memory(nid, start, size);
+
+        return ret;
+}
+EXPORT_SYMBOL_GPL(add_memory);