memory hotplug: register section/node id to free

This patch set is to free pages which is allocated by bootmem for
memory-hotremove.  Some structures of memory management are allocated by
bootmem.  ex) memmap, etc.

To remove memory physically, some of them must be freed according to
circumstance.  This patch set makes basis to free those pages, and free
memmaps.

Basic my idea is using remain members of struct page to remember information
of users of bootmem (section number or node id).  When the section is
removing, kernel can confirm it.  By this information, some issues can be
solved.

  1) When the memmap of removing section is allocated on other
     section by bootmem, it should/can be free.
  2) When the memmap of removing section is allocated on the
     same section, it shouldn't be freed. Because the section has to be
     logical memory offlined already and all pages must be isolated against
     page allocater. If it is freed, page allocator may use it which will
     be removed physically soon.
  3) When removing section has other section's memmap,
     kernel will be able to show easily which section should be removed
     before it for user. (Not implemented yet)
  4) When the above case 2), the page isolation will be able to check and skip
     memmap's page when logical memory offline (offline_pages()).
     Current page isolation code fails in this case because this page is
     just reserved page and it can't distinguish this pages can be
     removed or not. But, it will be able to do by this patch.
     (Not implemented yet.)
  5) The node information like pgdat has similar issues. But, this
     will be able to be solved too by this.
     (Not implemented yet, but, remembering node id in the pages.)

Fortunately, current bootmem allocator just keeps PageReserved flags,
and doesn't use any other members of page struct. The users of
bootmem doesn't use them too.

This patch:

This is to register information which is node or section's id.  Kernel can
distinguish which node/section uses the pages allcated by bootmem.  This is
basis for hot-remove sections or nodes.

Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Badari Pulavarty <pbadari@us.ibm.com>
Cc: Yinghai Lu <yhlu.kernel@gmail.com>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

5 files changed, 128 insertions, 3 deletions

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index aca9c65f8d08..73e358612eaf 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -11,6 +11,15 @@ struct pglist_data;
 struct mem_section;
 
 #ifdef CONFIG_MEMORY_HOTPLUG
+
+/*
+ * Magic number for free bootmem.
+ * The normal smallest mapcount is -1. Here is smaller value than it.
+ */
+#define SECTION_INFO            0xfffffffe
+#define MIX_INFO                0xfffffffd
+#define NODE_INFO               0xfffffffc
+
 /*
  * pgdat resizing functions
  */
@@ -145,6 +154,18 @@ static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
 #endif /* CONFIG_NUMA */
 #endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */
 
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
+{
+}
+static inline void put_page_bootmem(struct page *page)
+{
+}
+#else
+extern void register_page_bootmem_info_node(struct pglist_data *pgdat);
+extern void put_page_bootmem(struct page *page);
+#endif
+
 #else /* ! CONFIG_MEMORY_HOTPLUG */
 /*
  * Stub functions for when hotplug is off
@@ -172,6 +193,10 @@ static inline int mhp_notimplemented(const char *func)
         return -ENOSYS;
 }
 
+static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
+{
+}
+
 #endif /* ! CONFIG_MEMORY_HOTPLUG */
 
 extern int add_memory(int nid, u64 start, u64 size);
@@ -180,5 +205,7 @@ extern int remove_memory(u64 start, u64 size);
 extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
                                                                 int nr_pages);
 extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms);
+extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
+                                          unsigned long pnum);
 
 #endif /* __LINUX_MEMORY_HOTPLUG_H */
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index c3828497f41d..aad98003176f 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -896,6 +896,7 @@ static inline struct mem_section *__nr_to_section(unsigned long nr)
         return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK];
 }
 extern int __section_nr(struct mem_section* ms);
+extern unsigned long usemap_size(void);
 
 /*
  * We use the lower bits of the mem_map pointer to store
diff --git a/mm/bootmem.c b/mm/bootmem.c
index b6791646143e..369624d2789c 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -461,6 +461,7 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 
 unsigned long __init free_all_bootmem_node(pg_data_t *pgdat)
 {
+        register_page_bootmem_info_node(pgdat);
         return free_all_bootmem_core(pgdat);
 }
 
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index c8b3ca79de2d..cba36ef0d506 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -58,8 +58,105 @@ static void release_memory_resource(struct resource *res)
         return;
 }
 
-
 #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
+#ifndef CONFIG_SPARSEMEM_VMEMMAP
+static void get_page_bootmem(unsigned long info,  struct page *page, int magic)
+{
+        atomic_set(&page->_mapcount, magic);
+        SetPagePrivate(page);
+        set_page_private(page, info);
+        atomic_inc(&page->_count);
+}
+
+void put_page_bootmem(struct page *page)
+{
+        int magic;
+
+        magic = atomic_read(&page->_mapcount);
+        BUG_ON(magic >= -1);
+
+        if (atomic_dec_return(&page->_count) == 1) {
+                ClearPagePrivate(page);
+                set_page_private(page, 0);
+                reset_page_mapcount(page);
+                __free_pages_bootmem(page, 0);
+        }
+
+}
+
+void register_page_bootmem_info_section(unsigned long start_pfn)
+{
+        unsigned long *usemap, mapsize, section_nr, i;
+        struct mem_section *ms;
+        struct page *page, *memmap;
+
+        if (!pfn_valid(start_pfn))
+                return;
+
+        section_nr = pfn_to_section_nr(start_pfn);
+        ms = __nr_to_section(section_nr);
+
+        /* Get section's memmap address */
+        memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
+
+        /*
+         * Get page for the memmap's phys address
+         * XXX: need more consideration for sparse_vmemmap...
+         */
+        page = virt_to_page(memmap);
+        mapsize = sizeof(struct page) * PAGES_PER_SECTION;
+        mapsize = PAGE_ALIGN(mapsize) >> PAGE_SHIFT;
+
+        /* remember memmap's page */
+        for (i = 0; i < mapsize; i++, page++)
+                get_page_bootmem(section_nr, page, SECTION_INFO);
+
+        usemap = __nr_to_section(section_nr)->pageblock_flags;
+        page = virt_to_page(usemap);
+
+        mapsize = PAGE_ALIGN(usemap_size()) >> PAGE_SHIFT;
+
+        for (i = 0; i < mapsize; i++, page++)
+                get_page_bootmem(section_nr, page, MIX_INFO);
+
+}
+
+void register_page_bootmem_info_node(struct pglist_data *pgdat)
+{
+        unsigned long i, pfn, end_pfn, nr_pages;
+        int node = pgdat->node_id;
+        struct page *page;
+        struct zone *zone;
+
+        nr_pages = PAGE_ALIGN(sizeof(struct pglist_data)) >> PAGE_SHIFT;
+        page = virt_to_page(pgdat);
+
+        for (i = 0; i < nr_pages; i++, page++)
+                get_page_bootmem(node, page, NODE_INFO);
+
+        zone = &pgdat->node_zones[0];
+        for (; zone < pgdat->node_zones + MAX_NR_ZONES - 1; zone++) {
+                if (zone->wait_table) {
+                        nr_pages = zone->wait_table_hash_nr_entries
+                                * sizeof(wait_queue_head_t);
+                        nr_pages = PAGE_ALIGN(nr_pages) >> PAGE_SHIFT;
+                        page = virt_to_page(zone->wait_table);
+
+                        for (i = 0; i < nr_pages; i++, page++)
+                                get_page_bootmem(node, page, NODE_INFO);
+                }
+        }
+
+        pfn = pgdat->node_start_pfn;
+        end_pfn = pfn + pgdat->node_spanned_pages;
+
+        /* register_section info */
+        for (; pfn < end_pfn; pfn += PAGES_PER_SECTION)
+                register_page_bootmem_info_section(pfn);
+
+}
+#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
+
 static int __add_zone(struct zone *zone, unsigned long phys_start_pfn)
 {
         struct pglist_data *pgdat = zone->zone_pgdat;
diff --git a/mm/sparse.c b/mm/sparse.c
index 186a85bf7912..8903c484389a 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -210,7 +210,6 @@ static unsigned long sparse_encode_mem_map(struct page *mem_map, unsigned long p
 /*
  * Decode mem_map from the coded memmap
  */
-static
 struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum)
 {
         /* mask off the extra low bits of information */
@@ -233,7 +232,7 @@ static int __meminit sparse_init_one_section(struct mem_section *ms,
         return 1;
 }
 
-static unsigned long usemap_size(void)
+unsigned long usemap_size(void)
 {
         unsigned long size_bytes;
         size_bytes = roundup(SECTION_BLOCKFLAGS_BITS, 8) / 8;