hotplug memory remove: generic __remove_pages() support

Generic helper function to remove section mappings and sysfs entries for the
section of the memory we are removing.  offline_pages() correctly adjusted
zone and marked the pages reserved.

TODO: Yasunori Goto is working on patches to free up allocations from bootmem.

Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com>
Acked-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 102 insertions, 4 deletions

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 8fee7a45736b..aca9c65f8d08 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -8,6 +8,7 @@
 struct page;
 struct zone;
 struct pglist_data;
+struct mem_section;
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 /*
@@ -64,9 +65,11 @@ extern int offline_pages(unsigned long, 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);
+extern int __remove_pages(struct zone *zone, unsigned long start_pfn,
+        unsigned long nr_pages);
 
 /*
- * Walk thorugh all memory which is registered as resource.
+ * Walk through all memory which is registered as resource.
  * arg is (start_pfn, nr_pages, private_arg_pointer)
  */
 extern int walk_memory_resource(unsigned long start_pfn,
@@ -176,5 +179,6 @@ extern int arch_add_memory(int nid, u64 start, u64 size);
 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);
 
 #endif /* __LINUX_MEMORY_HOTPLUG_H */
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 0fb330271271..d5094929766d 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -101,6 +101,25 @@ static int __add_section(struct zone *zone, unsigned long phys_start_pfn)
         return register_new_memory(__pfn_to_section(phys_start_pfn));
 }
 
+static int __remove_section(struct zone *zone, struct mem_section *ms)
+{
+        unsigned long flags;
+        struct pglist_data *pgdat = zone->zone_pgdat;
+        int ret = -EINVAL;
+
+        if (!valid_section(ms))
+                return ret;
+
+        ret = unregister_memory_section(ms);
+        if (ret)
+                return ret;
+
+        pgdat_resize_lock(pgdat, &flags);
+        sparse_remove_one_section(zone, ms);
+        pgdat_resize_unlock(pgdat, &flags);
+        return 0;
+}
+
 /*
  * Reasonably generic function for adding memory.  It is
  * expected that archs that support memory hotplug will
@@ -134,6 +153,42 @@ int __add_pages(struct zone *zone, unsigned long phys_start_pfn,
 }
 EXPORT_SYMBOL_GPL(__add_pages);
 
+/**
+ * __remove_pages() - remove sections of pages from a zone
+ * @zone: zone from which pages need to be removed
+ * @phys_start_pfn: starting pageframe (must be aligned to start of a section)
+ * @nr_pages: number of pages to remove (must be multiple of section size)
+ *
+ * Generic helper function to remove section mappings and sysfs entries
+ * for the section of the memory we are removing. Caller needs to make
+ * sure that pages are marked reserved and zones are adjust properly by
+ * calling offline_pages().
+ */
+int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
+                 unsigned long nr_pages)
+{
+        unsigned long i, ret = 0;
+        int sections_to_remove;
+
+        /*
+         * We can only remove entire sections
+         */
+        BUG_ON(phys_start_pfn & ~PAGE_SECTION_MASK);
+        BUG_ON(nr_pages % PAGES_PER_SECTION);
+
+        release_mem_region(phys_start_pfn << PAGE_SHIFT, nr_pages * PAGE_SIZE);
+
+        sections_to_remove = nr_pages / PAGES_PER_SECTION;
+        for (i = 0; i < sections_to_remove; i++) {
+                unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION;
+                ret = __remove_section(zone, __pfn_to_section(pfn));
+                if (ret)
+                        break;
+        }
+        return ret;
+}
+EXPORT_SYMBOL_GPL(__remove_pages);
+
 static void grow_zone_span(struct zone *zone,
                 unsigned long start_pfn, unsigned long end_pfn)
 {
diff --git a/mm/sparse.c b/mm/sparse.c
index 7e9191381f86..186a85bf7912 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -208,12 +208,13 @@ static unsigned long sparse_encode_mem_map(struct page *mem_map, unsigned long p
 }
 
 /*
- * We need this if we ever free the mem_maps.  While not implemented yet,
- * this function is included for parity with its sibling.
+ * Decode mem_map from the coded memmap
  */
-static __attribute((unused))
+static
 struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum)
 {
+        /* mask off the extra low bits of information */
+        coded_mem_map &= SECTION_MAP_MASK;
         return ((struct page *)coded_mem_map) + section_nr_to_pfn(pnum);
 }
 
@@ -404,6 +405,28 @@ static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
 }
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
+static void free_section_usemap(struct page *memmap, unsigned long *usemap)
+{
+        if (!usemap)
+                return;
+
+        /*
+         * Check to see if allocation came from hot-plug-add
+         */
+        if (PageSlab(virt_to_page(usemap))) {
+                kfree(usemap);
+                if (memmap)
+                        __kfree_section_memmap(memmap, PAGES_PER_SECTION);
+                return;
+        }
+
+        /*
+         * TODO: Allocations came from bootmem - how do I free up ?
+         */
+        printk(KERN_WARNING "Not freeing up allocations from bootmem "
+                        "- leaking memory\n");
+}
+
 /*
  * returns the number of sections whose mem_maps were properly
  * set.  If this is <=0, then that means that the passed-in
@@ -456,4 +479,20 @@ out:
         }
         return ret;
 }
+
+void sparse_remove_one_section(struct zone *zone, struct mem_section *ms)
+{
+        struct page *memmap = NULL;
+        unsigned long *usemap = NULL;
+
+        if (ms->section_mem_map) {
+                usemap = ms->pageblock_flags;
+                memmap = sparse_decode_mem_map(ms->section_mem_map,
+                                                __section_nr(ms));
+                ms->section_mem_map = 0;
+                ms->pageblock_flags = NULL;
+        }
+
+        free_section_usemap(memmap, usemap);
+}
 #endif