1 files changed, 187 insertions, 87 deletions

diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 933442f40321..45d7c8fc73bd 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -27,8 +27,17 @@
 #include <asm/atomic.h>
 #include <asm/uaccess.h>
 
+static DEFINE_MUTEX(mem_sysfs_mutex);
+
 #define MEMORY_CLASS_NAME       "memory"
 
+static int sections_per_block;
+
+static inline int base_memory_block_id(int section_nr)
+{
+        return section_nr / sections_per_block;
+}
+
 static struct sysdev_class memory_sysdev_class = {
         .name = MEMORY_CLASS_NAME,
 };
@@ -38,7 +47,8 @@ static const char *memory_uevent_name(struct kset *kset, struct kobject *kobj)
         return MEMORY_CLASS_NAME;
 }
 
-static int memory_uevent(struct kset *kset, struct kobject *obj, struct kobj_uevent_env *env)
+static int memory_uevent(struct kset *kset, struct kobject *obj,
+                        struct kobj_uevent_env *env)
 {
         int retval = 0;
 
@@ -82,39 +92,72 @@ EXPORT_SYMBOL(unregister_memory_isolate_notifier);
  * register_memory - Setup a sysfs device for a memory block
  */
 static
-int register_memory(struct memory_block *memory, struct mem_section *section)
+int register_memory(struct memory_block *memory)
 {
         int error;
 
         memory->sysdev.cls = &memory_sysdev_class;
-        memory->sysdev.id = __section_nr(section);
+        memory->sysdev.id = memory->start_section_nr / sections_per_block;
 
         error = sysdev_register(&memory->sysdev);
         return error;
 }
 
 static void
-unregister_memory(struct memory_block *memory, struct mem_section *section)
+unregister_memory(struct memory_block *memory)
 {
         BUG_ON(memory->sysdev.cls != &memory_sysdev_class);
-        BUG_ON(memory->sysdev.id != __section_nr(section));
 
         /* drop the ref. we got in remove_memory_block() */
         kobject_put(&memory->sysdev.kobj);
         sysdev_unregister(&memory->sysdev);
 }
 
+unsigned long __weak memory_block_size_bytes(void)
+{
+        return MIN_MEMORY_BLOCK_SIZE;
+}
+
+static unsigned long get_memory_block_size(void)
+{
+        unsigned long block_sz;
+
+        block_sz = memory_block_size_bytes();
+
+        /* Validate blk_sz is a power of 2 and not less than section size */
+        if ((block_sz & (block_sz - 1)) || (block_sz < MIN_MEMORY_BLOCK_SIZE)) {
+                WARN_ON(1);
+                block_sz = MIN_MEMORY_BLOCK_SIZE;
+        }
+
+        return block_sz;
+}
+
 /*
  * use this as the physical section index that this memsection
  * uses.
  */
 
-static ssize_t show_mem_phys_index(struct sys_device *dev,
+static ssize_t show_mem_start_phys_index(struct sys_device *dev,
+                        struct sysdev_attribute *attr, char *buf)
+{
+        struct memory_block *mem =
+                container_of(dev, struct memory_block, sysdev);
+        unsigned long phys_index;
+
+        phys_index = mem->start_section_nr / sections_per_block;
+        return sprintf(buf, "%08lx\n", phys_index);
+}
+
+static ssize_t show_mem_end_phys_index(struct sys_device *dev,
                         struct sysdev_attribute *attr, char *buf)
 {
         struct memory_block *mem =
                 container_of(dev, struct memory_block, sysdev);
-        return sprintf(buf, "%08lx\n", mem->phys_index);
+        unsigned long phys_index;
+
+        phys_index = mem->end_section_nr / sections_per_block;
+        return sprintf(buf, "%08lx\n", phys_index);
 }
 
 /*
@@ -123,13 +166,16 @@ static ssize_t show_mem_phys_index(struct sys_device *dev,
 static ssize_t show_mem_removable(struct sys_device *dev,
                         struct sysdev_attribute *attr, char *buf)
 {
-        unsigned long start_pfn;
-        int ret;
+        unsigned long i, pfn;
+        int ret = 1;
         struct memory_block *mem =
                 container_of(dev, struct memory_block, sysdev);
 
-        start_pfn = section_nr_to_pfn(mem->phys_index);
-        ret = is_mem_section_removable(start_pfn, PAGES_PER_SECTION);
+        for (i = 0; i < sections_per_block; i++) {
+                pfn = section_nr_to_pfn(mem->start_section_nr + i);
+                ret &= is_mem_section_removable(pfn, PAGES_PER_SECTION);
+        }
+
         return sprintf(buf, "%d\n", ret);
 }
 
@@ -182,17 +228,15 @@ int memory_isolate_notify(unsigned long val, void *v)
  * OK to have direct references to sparsemem variables in here.
  */
 static int
-memory_block_action(struct memory_block *mem, unsigned long action)
+memory_block_action(unsigned long phys_index, unsigned long action)
 {
         int i;
-        unsigned long psection;
         unsigned long start_pfn, start_paddr;
+        unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
         struct page *first_page;
         int ret;
-        int old_state = mem->state;
 
-        psection = mem->phys_index;
-        first_page = pfn_to_page(psection << PFN_SECTION_SHIFT);
+        first_page = pfn_to_page(phys_index << PFN_SECTION_SHIFT);
 
         /*
          * The probe routines leave the pages reserved, just
@@ -200,13 +244,13 @@ memory_block_action(struct memory_block *mem, unsigned long action)
          * that way.
          */
         if (action == MEM_ONLINE) {
-                for (i = 0; i < PAGES_PER_SECTION; i++) {
+                for (i = 0; i < nr_pages; i++) {
                         if (PageReserved(first_page+i))
                                 continue;
 
                         printk(KERN_WARNING "section number %ld page number %d "
-                                "not reserved, was it already online? \n",
-                                psection, i);
+                                "not reserved, was it already online?\n",
+                                phys_index, i);
                         return -EBUSY;
                 }
         }
@@ -214,21 +258,16 @@ memory_block_action(struct memory_block *mem, unsigned long action)
         switch (action) {
                 case MEM_ONLINE:
                         start_pfn = page_to_pfn(first_page);
-                        ret = online_pages(start_pfn, PAGES_PER_SECTION);
+                        ret = online_pages(start_pfn, nr_pages);
                         break;
                 case MEM_OFFLINE:
-                        mem->state = MEM_GOING_OFFLINE;
                         start_paddr = page_to_pfn(first_page) << PAGE_SHIFT;
                         ret = remove_memory(start_paddr,
-                                            PAGES_PER_SECTION << PAGE_SHIFT);
-                        if (ret) {
-                                mem->state = old_state;
-                                break;
-                        }
+                                            nr_pages << PAGE_SHIFT);
                         break;
                 default:
-                        WARN(1, KERN_WARNING "%s(%p, %ld) unknown action: %ld\n",
-                                        __func__, mem, action, action);
+                        WARN(1, KERN_WARNING "%s(%ld, %ld) unknown action: "
+                             "%ld\n", __func__, phys_index, action, action);
                         ret = -EINVAL;
         }
 
@@ -239,6 +278,7 @@ static int memory_block_change_state(struct memory_block *mem,
                 unsigned long to_state, unsigned long from_state_req)
 {
         int ret = 0;
+
         mutex_lock(&mem->state_mutex);
 
         if (mem->state != from_state_req) {
@@ -246,8 +286,14 @@ static int memory_block_change_state(struct memory_block *mem,
                 goto out;
         }
 
-        ret = memory_block_action(mem, to_state);
-        if (!ret)
+        if (to_state == MEM_OFFLINE)
+                mem->state = MEM_GOING_OFFLINE;
+
+        ret = memory_block_action(mem->start_section_nr, to_state);
+
+        if (ret)
+                mem->state = from_state_req;
+        else
                 mem->state = to_state;
 
 out:
@@ -260,20 +306,15 @@ store_mem_state(struct sys_device *dev,
                 struct sysdev_attribute *attr, const char *buf, size_t count)
 {
         struct memory_block *mem;
-        unsigned int phys_section_nr;
         int ret = -EINVAL;
 
         mem = container_of(dev, struct memory_block, sysdev);
-        phys_section_nr = mem->phys_index;
-
-        if (!present_section_nr(phys_section_nr))
-                goto out;
 
         if (!strncmp(buf, "online", min((int)count, 6)))
                 ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE);
         else if(!strncmp(buf, "offline", min((int)count, 7)))
                 ret = memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE);
-out:
+
         if (ret)
                 return ret;
         return count;
@@ -296,7 +337,8 @@ static ssize_t show_phys_device(struct sys_device *dev,
         return sprintf(buf, "%d\n", mem->phys_device);
 }
 
-static SYSDEV_ATTR(phys_index, 0444, show_mem_phys_index, NULL);
+static SYSDEV_ATTR(phys_index, 0444, show_mem_start_phys_index, NULL);
+static SYSDEV_ATTR(end_phys_index, 0444, show_mem_end_phys_index, NULL);
 static SYSDEV_ATTR(state, 0644, show_mem_state, store_mem_state);
 static SYSDEV_ATTR(phys_device, 0444, show_phys_device, NULL);
 static SYSDEV_ATTR(removable, 0444, show_mem_removable, NULL);
@@ -313,7 +355,7 @@ static ssize_t
 print_block_size(struct sysdev_class *class, struct sysdev_class_attribute *attr,
                  char *buf)
 {
-        return sprintf(buf, "%lx\n", (unsigned long)PAGES_PER_SECTION * PAGE_SIZE);
+        return sprintf(buf, "%lx\n", get_memory_block_size());
 }
 
 static SYSDEV_CLASS_ATTR(block_size_bytes, 0444, print_block_size, NULL);
@@ -337,17 +379,23 @@ memory_probe_store(struct class *class, struct class_attribute *attr,
 {
         u64 phys_addr;
         int nid;
-        int ret;
+        int i, ret;
 
         phys_addr = simple_strtoull(buf, NULL, 0);
 
-        nid = memory_add_physaddr_to_nid(phys_addr);
-        ret = add_memory(nid, phys_addr, PAGES_PER_SECTION << PAGE_SHIFT);
+        for (i = 0; i < sections_per_block; i++) {
+                nid = memory_add_physaddr_to_nid(phys_addr);
+                ret = add_memory(nid, phys_addr,
+                                 PAGES_PER_SECTION << PAGE_SHIFT);
+                if (ret)
+                        goto out;
 
-        if (ret)
-                count = ret;
+                phys_addr += MIN_MEMORY_BLOCK_SIZE;
+        }
 
-        return count;
+        ret = count;
+out:
+        return ret;
 }
 static CLASS_ATTR(probe, S_IWUSR, NULL, memory_probe_store);
 
@@ -435,68 +483,107 @@ int __weak arch_get_memory_phys_device(unsigned long start_pfn)
         return 0;
 }
 
-static int add_memory_block(int nid, struct mem_section *section,
-                        unsigned long state, enum mem_add_context context)
+struct memory_block *find_memory_block_hinted(struct mem_section *section,
+                                              struct memory_block *hint)
 {
-        struct memory_block *mem = kzalloc(sizeof(*mem), GFP_KERNEL);
+        struct kobject *kobj;
+        struct sys_device *sysdev;
+        struct memory_block *mem;
+        char name[sizeof(MEMORY_CLASS_NAME) + 9 + 1];
+        int block_id = base_memory_block_id(__section_nr(section));
+
+        kobj = hint ? &hint->sysdev.kobj : NULL;
+
+        /*
+         * This only works because we know that section == sysdev->id
+         * slightly redundant with sysdev_register()
+         */
+        sprintf(&name[0], "%s%d", MEMORY_CLASS_NAME, block_id);
+
+        kobj = kset_find_obj_hinted(&memory_sysdev_class.kset, name, kobj);
+        if (!kobj)
+                return NULL;
+
+        sysdev = container_of(kobj, struct sys_device, kobj);
+        mem = container_of(sysdev, struct memory_block, sysdev);
+
+        return mem;
+}
+
+/*
+ * For now, we have a linear search to go find the appropriate
+ * memory_block corresponding to a particular phys_index. If
+ * this gets to be a real problem, we can always use a radix
+ * tree or something here.
+ *
+ * This could be made generic for all sysdev classes.
+ */
+struct memory_block *find_memory_block(struct mem_section *section)
+{
+        return find_memory_block_hinted(section, NULL);
+}
+
+static int init_memory_block(struct memory_block **memory,
+                             struct mem_section *section, unsigned long state)
+{
+        struct memory_block *mem;
         unsigned long start_pfn;
+        int scn_nr;
         int ret = 0;
 
+        mem = kzalloc(sizeof(*mem), GFP_KERNEL);
         if (!mem)
                 return -ENOMEM;
 
-        mem->phys_index = __section_nr(section);
+        scn_nr = __section_nr(section);
+        mem->start_section_nr =
+                        base_memory_block_id(scn_nr) * sections_per_block;
+        mem->end_section_nr = mem->start_section_nr + sections_per_block - 1;
         mem->state = state;
+        mem->section_count++;
         mutex_init(&mem->state_mutex);
-        start_pfn = section_nr_to_pfn(mem->phys_index);
+        start_pfn = section_nr_to_pfn(mem->start_section_nr);
         mem->phys_device = arch_get_memory_phys_device(start_pfn);
 
-        ret = register_memory(mem, section);
+        ret = register_memory(mem);
         if (!ret)
                 ret = mem_create_simple_file(mem, phys_index);
         if (!ret)
+                ret = mem_create_simple_file(mem, end_phys_index);
+        if (!ret)
                 ret = mem_create_simple_file(mem, state);
         if (!ret)
                 ret = mem_create_simple_file(mem, phys_device);
         if (!ret)
                 ret = mem_create_simple_file(mem, removable);
-        if (!ret) {
-                if (context == HOTPLUG)
-                        ret = register_mem_sect_under_node(mem, nid);
-        }
 
+        *memory = mem;
         return ret;
 }
 
-/*
- * For now, we have a linear search to go find the appropriate
- * memory_block corresponding to a particular phys_index. If
- * this gets to be a real problem, we can always use a radix
- * tree or something here.
- *
- * This could be made generic for all sysdev classes.
- */
-struct memory_block *find_memory_block(struct mem_section *section)
+static int add_memory_section(int nid, struct mem_section *section,
+                        unsigned long state, enum mem_add_context context)
 {
-        struct kobject *kobj;
-        struct sys_device *sysdev;
         struct memory_block *mem;
-        char name[sizeof(MEMORY_CLASS_NAME) + 9 + 1];
+        int ret = 0;
 
-        /*
-         * This only works because we know that section == sysdev->id
-         * slightly redundant with sysdev_register()
-         */
-        sprintf(&name[0], "%s%d", MEMORY_CLASS_NAME, __section_nr(section));
+        mutex_lock(&mem_sysfs_mutex);
 
-        kobj = kset_find_obj(&memory_sysdev_class.kset, name);
-        if (!kobj)
-                return NULL;
+        mem = find_memory_block(section);
+        if (mem) {
+                mem->section_count++;
+                kobject_put(&mem->sysdev.kobj);
+        } else
+                ret = init_memory_block(&mem, section, state);
 
-        sysdev = container_of(kobj, struct sys_device, kobj);
-        mem = container_of(sysdev, struct memory_block, sysdev);
+        if (!ret) {
+                if (context == HOTPLUG &&
+                    mem->section_count == sections_per_block)
+                        ret = register_mem_sect_under_node(mem, nid);
+        }
 
-        return mem;
+        mutex_unlock(&mem_sysfs_mutex);
+        return ret;
 }
 
 int remove_memory_block(unsigned long node_id, struct mem_section *section,
@@ -504,14 +591,23 @@ int remove_memory_block(unsigned long node_id, struct mem_section *section,
 {
         struct memory_block *mem;
 
+        mutex_lock(&mem_sysfs_mutex);
         mem = find_memory_block(section);
-        unregister_mem_sect_under_nodes(mem);
-        mem_remove_simple_file(mem, phys_index);
-        mem_remove_simple_file(mem, state);
-        mem_remove_simple_file(mem, phys_device);
-        mem_remove_simple_file(mem, removable);
-        unregister_memory(mem, section);
-
+        unregister_mem_sect_under_nodes(mem, __section_nr(section));
+
+        mem->section_count--;
+        if (mem->section_count == 0) {
+                mem_remove_simple_file(mem, phys_index);
+                mem_remove_simple_file(mem, end_phys_index);
+                mem_remove_simple_file(mem, state);
+                mem_remove_simple_file(mem, phys_device);
+                mem_remove_simple_file(mem, removable);
+                unregister_memory(mem);
+                kfree(mem);
+        } else
+                kobject_put(&mem->sysdev.kobj);
+
+        mutex_unlock(&mem_sysfs_mutex);
         return 0;
 }
 
@@ -521,7 +617,7 @@ int remove_memory_block(unsigned long node_id, struct mem_section *section,
  */
 int register_new_memory(int nid, struct mem_section *section)
 {
-        return add_memory_block(nid, section, MEM_OFFLINE, HOTPLUG);
+        return add_memory_section(nid, section, MEM_OFFLINE, HOTPLUG);
 }
 
 int unregister_memory_section(struct mem_section *section)
@@ -540,12 +636,16 @@ int __init memory_dev_init(void)
         unsigned int i;
         int ret;
         int err;
+        unsigned long block_sz;
 
         memory_sysdev_class.kset.uevent_ops = &memory_uevent_ops;
         ret = sysdev_class_register(&memory_sysdev_class);
         if (ret)
                 goto out;
 
+        block_sz = get_memory_block_size();
+        sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE;
+
         /*
          * Create entries for memory sections that were found
          * during boot and have been initialized
@@ -553,8 +653,8 @@ int __init memory_dev_init(void)
         for (i = 0; i < NR_MEM_SECTIONS; i++) {
                 if (!present_section_nr(i))
                         continue;
-                err = add_memory_block(0, __nr_to_section(i), MEM_ONLINE,
-                                       BOOT);
+                err = add_memory_section(0, __nr_to_section(i), MEM_ONLINE,
+                                         BOOT);
                 if (!ret)
                         ret = err;
         }