[PATCH] memory hotplug: sysfs and add/remove functions

This adds generic memory add/remove and supporting functions for memory
hotplug into a new file as well as a memory hotplug kernel config option.

Individual architecture patches will follow.

For now, disable memory hotplug when swsusp is enabled.  There's a lot of
churn there right now.  We'll fix it up properly once it calms down.

Signed-off-by: Matt Tolentino <matthew.e.tolentino@intel.com>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

4 files changed, 189 insertions, 3 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index f35a550ba4b9..1a4473fcb2ca 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -112,6 +112,14 @@ config SPARSEMEM_EXTREME
         def_bool y
         depends on SPARSEMEM && !SPARSEMEM_STATIC
 
+# eventually, we can have this option just 'select SPARSEMEM'
+config MEMORY_HOTPLUG
+        bool "Allow for memory hot-add"
+        depends on SPARSEMEM && HOTPLUG && !SOFTWARE_SUSPEND
+
+comment "Memory hotplug is currently incompatible with Software Suspend"
+        depends on SPARSEMEM && HOTPLUG && SOFTWARE_SUSPEND
+
 # Heavily threaded applications may benefit from splitting the mm-wide
 # page_table_lock, so that faults on different parts of the user address
 # space can be handled with less contention: split it at this NR_CPUS.
diff --git a/mm/Makefile b/mm/Makefile
index 4cd69e3ce421..2fa6d2ca9f28 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -18,5 +18,5 @@ obj-$(CONFIG_NUMA) 	+= mempolicy.o
 obj-$(CONFIG_SPARSEMEM) += sparse.o
 obj-$(CONFIG_SHMEM) += shmem.o
 obj-$(CONFIG_TINY_SHMEM) += tiny-shmem.o
-
+obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 obj-$(CONFIG_FS_XIP) += filemap_xip.o
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
new file mode 100644
index 000000000000..855e0fc928b3
--- /dev/null
+++ b/mm/memory_hotplug.c
@@ -0,0 +1,178 @@
+/*
+ *  linux/mm/memory_hotplug.c
+ *
+ *  Copyright (C)
+ */
+
+#include <linux/config.h>
+#include <linux/stddef.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/interrupt.h>
+#include <linux/pagemap.h>
+#include <linux/bootmem.h>
+#include <linux/compiler.h>
+#include <linux/module.h>
+#include <linux/pagevec.h>
+#include <linux/slab.h>
+#include <linux/sysctl.h>
+#include <linux/cpu.h>
+#include <linux/memory.h>
+#include <linux/memory_hotplug.h>
+#include <linux/highmem.h>
+#include <linux/vmalloc.h>
+
+#include <asm/tlbflush.h>
+
+static struct page *__kmalloc_section_memmap(unsigned long nr_pages)
+{
+        struct page *page, *ret;
+        unsigned long memmap_size = sizeof(struct page) * nr_pages;
+
+        page = alloc_pages(GFP_KERNEL, get_order(memmap_size));
+        if (page)
+                goto got_map_page;
+
+        ret = vmalloc(memmap_size);
+        if (ret)
+                goto got_map_ptr;
+
+        return NULL;
+got_map_page:
+        ret = (struct page *)pfn_to_kaddr(page_to_pfn(page));
+got_map_ptr:
+        memset(ret, 0, memmap_size);
+
+        return ret;
+}
+
+extern void zonetable_add(struct zone *zone, int nid, int zid, unsigned long pfn,
+                          unsigned long size);
+static void __add_zone(struct zone *zone, unsigned long phys_start_pfn)
+{
+        struct pglist_data *pgdat = zone->zone_pgdat;
+        int nr_pages = PAGES_PER_SECTION;
+        int nid = pgdat->node_id;
+        int zone_type;
+
+        zone_type = zone - pgdat->node_zones;
+        memmap_init_zone(nr_pages, nid, zone_type, phys_start_pfn);
+        zonetable_add(zone, nid, zone_type, phys_start_pfn, nr_pages);
+}
+
+extern int sparse_add_one_section(struct zone *, unsigned long,
+                                  struct page *mem_map);
+static int __add_section(struct zone *zone, unsigned long phys_start_pfn)
+{
+        struct pglist_data *pgdat = zone->zone_pgdat;
+        int nr_pages = PAGES_PER_SECTION;
+        struct page *memmap;
+        int ret;
+
+        /*
+         * This can potentially allocate memory, and does its own
+         * internal locking.
+         */
+        sparse_index_init(pfn_to_section_nr(phys_start_pfn), pgdat->node_id);
+
+        pgdat_resize_lock(pgdat, &flags);
+        memmap = __kmalloc_section_memmap(nr_pages);
+        ret = sparse_add_one_section(zone, phys_start_pfn, memmap);
+        pgdat_resize_unlock(pgdat, &flags);
+
+        if (ret <= 0) {
+                /* the mem_map didn't get used */
+                if (memmap >= (struct page *)VMALLOC_START &&
+                    memmap < (struct page *)VMALLOC_END)
+                        vfree(memmap);
+                else
+                        free_pages((unsigned long)memmap,
+                                   get_order(sizeof(struct page) * nr_pages));
+        }
+
+        if (ret < 0)
+                return ret;
+
+        __add_zone(zone, phys_start_pfn);
+        return register_new_memory(__pfn_to_section(phys_start_pfn));
+}
+
+/*
+ * Reasonably generic function for adding memory.  It is
+ * expected that archs that support memory hotplug will
+ * call this function after deciding the zone to which to
+ * add the new pages.
+ */
+int __add_pages(struct zone *zone, unsigned long phys_start_pfn,
+                 unsigned long nr_pages)
+{
+        unsigned long i;
+        int err = 0;
+
+        for (i = 0; i < nr_pages; i += PAGES_PER_SECTION) {
+                err = __add_section(zone, phys_start_pfn + i);
+
+                if (err)
+                        break;
+        }
+
+        return err;
+}
+
+static void grow_zone_span(struct zone *zone,
+                unsigned long start_pfn, unsigned long end_pfn)
+{
+        unsigned long old_zone_end_pfn;
+
+        zone_span_writelock(zone);
+
+        old_zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
+        if (start_pfn < zone->zone_start_pfn)
+                zone->zone_start_pfn = start_pfn;
+
+        if (end_pfn > old_zone_end_pfn)
+                zone->spanned_pages = end_pfn - zone->zone_start_pfn;
+
+        zone_span_writeunlock(zone);
+}
+
+static void grow_pgdat_span(struct pglist_data *pgdat,
+                unsigned long start_pfn, unsigned long end_pfn)
+{
+        unsigned long old_pgdat_end_pfn =
+                pgdat->node_start_pfn + pgdat->node_spanned_pages;
+
+        if (start_pfn < pgdat->node_start_pfn)
+                pgdat->node_start_pfn = start_pfn;
+
+        if (end_pfn > old_pgdat_end_pfn)
+                pgdat->node_spanned_pages = end_pfn - pgdat->node_spanned_pages;
+}
+
+int online_pages(unsigned long pfn, unsigned long nr_pages)
+{
+        unsigned long i;
+        unsigned long flags;
+        unsigned long onlined_pages = 0;
+        struct zone *zone;
+
+        /*
+         * This doesn't need a lock to do pfn_to_page().
+         * The section can't be removed here because of the
+         * memory_block->state_sem.
+         */
+        zone = page_zone(pfn_to_page(pfn));
+        pgdat_resize_lock(zone->zone_pgdat, &flags);
+        grow_zone_span(zone, pfn, pfn + nr_pages);
+        grow_pgdat_span(zone->zone_pgdat, pfn, pfn + nr_pages);
+        pgdat_resize_unlock(zone->zone_pgdat, &flags);
+
+        for (i = 0; i < nr_pages; i++) {
+                struct page *page = pfn_to_page(pfn + i);
+                online_page(page);
+                onlined_pages++;
+        }
+        zone->present_pages += onlined_pages;
+
+        return 0;
+}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 817635f2ab62..183abf39b445 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1686,7 +1686,7 @@ static void __init calculate_zone_totalpages(struct pglist_data *pgdat,
  * up by free_all_bootmem() once the early boot process is
  * done. Non-atomic initialization, single-pass.
  */
-void __init memmap_init_zone(unsigned long size, int nid, unsigned long zone,
+void __devinit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
                 unsigned long start_pfn)
 {
         struct page *page;
@@ -2407,7 +2407,7 @@ static void setup_per_zone_lowmem_reserve(void)
  *      that the pages_{min,low,high} values for each zone are set correctly 
  *      with respect to min_free_kbytes.
  */
-static void setup_per_zone_pages_min(void)
+void setup_per_zone_pages_min(void)
 {
         unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
         unsigned long lowmem_pages = 0;