zsmalloc: merge size_class to reduce fragmentation

[linux-2.6-block.git] / mm / zsmalloc.c

diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 839a48c3ca27b2bf008496c89867f7210aeb6610..b3b57ef85830beb4f97e5369234214547a86c673 100644 (file)
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -214,7 +214,7 @@ struct link_free {
 };
 
 struct zs_pool {
-       struct size_class size_class[ZS_SIZE_CLASSES];
+       struct size_class *size_class[ZS_SIZE_CLASSES];
 
        gfp_t flags;    /* allocation flags used when growing pool */
        atomic_long_t pages_allocated;
@@ -468,7 +468,7 @@ static enum fullness_group fix_fullness_group(struct zs_pool *pool,
        if (newfg == currfg)
                goto out;
 
-       class = &pool->size_class[class_idx];
+       class = pool->size_class[class_idx];
        remove_zspage(page, class, currfg);
        insert_zspage(page, class, newfg);
        set_zspage_mapping(page, class_idx, newfg);
@@ -925,6 +925,23 @@ fail:
        return notifier_to_errno(ret);
 }
 
+static unsigned int get_maxobj_per_zspage(int size, int pages_per_zspage)
+{
+       return pages_per_zspage * PAGE_SIZE / size;
+}
+
+static bool can_merge(struct size_class *prev, int size, int pages_per_zspage)
+{
+       if (prev->pages_per_zspage != pages_per_zspage)
+               return false;
+
+       if (get_maxobj_per_zspage(prev->size, prev->pages_per_zspage)
+               != get_maxobj_per_zspage(size, pages_per_zspage))
+               return false;
+
+       return true;
+}
+
 /**
  * zs_create_pool - Creates an allocation pool to work from.
  * @flags: allocation flags used to allocate pool metadata
@@ -945,25 +962,56 @@ struct zs_pool *zs_create_pool(gfp_t flags)
        if (!pool)
                return NULL;
 
-       for (i = 0; i < ZS_SIZE_CLASSES; i++) {
+       /*
+        * Iterate reversly, because, size of size_class that we want to use
+        * for merging should be larger or equal to current size.
+        */
+       for (i = ZS_SIZE_CLASSES - 1; i >= 0; i--) {
                int size;
+               int pages_per_zspage;
                struct size_class *class;
+               struct size_class *prev_class;
 
                size = ZS_MIN_ALLOC_SIZE + i * ZS_SIZE_CLASS_DELTA;
                if (size > ZS_MAX_ALLOC_SIZE)
                        size = ZS_MAX_ALLOC_SIZE;
+               pages_per_zspage = get_pages_per_zspage(size);
+
+               /*
+                * size_class is used for normal zsmalloc operation such
+                * as alloc/free for that size. Although it is natural that we
+                * have one size_class for each size, there is a chance that we
+                * can get more memory utilization if we use one size_class for
+                * many different sizes whose size_class have same
+                * characteristics. So, we makes size_class point to
+                * previous size_class if possible.
+                */
+               if (i < ZS_SIZE_CLASSES - 1) {
+                       prev_class = pool->size_class[i + 1];
+                       if (can_merge(prev_class, size, pages_per_zspage)) {
+                               pool->size_class[i] = prev_class;
+                               continue;
+                       }
+               }
+
+               class = kzalloc(sizeof(struct size_class), GFP_KERNEL);
+               if (!class)
+                       goto err;
 
-               class = &pool->size_class[i];
                class->size = size;
                class->index = i;
+               class->pages_per_zspage = pages_per_zspage;
                spin_lock_init(&class->lock);
-               class->pages_per_zspage = get_pages_per_zspage(size);
-
+               pool->size_class[i] = class;
        }
 
        pool->flags = flags;
 
        return pool;
+
+err:
+       zs_destroy_pool(pool);
+       return NULL;
 }
 EXPORT_SYMBOL_GPL(zs_create_pool);
 
@@ -973,7 +1021,13 @@ void zs_destroy_pool(struct zs_pool *pool)
 
        for (i = 0; i < ZS_SIZE_CLASSES; i++) {
                int fg;
-               struct size_class *class = &pool->size_class[i];
+               struct size_class *class = pool->size_class[i];
+
+               if (!class)
+                       continue;
+
+               if (class->index != i)
+                       continue;
 
                for (fg = 0; fg < _ZS_NR_FULLNESS_GROUPS; fg++) {
                        if (class->fullness_list[fg]) {
@@ -981,6 +1035,7 @@ void zs_destroy_pool(struct zs_pool *pool)
                                        class->size, fg);
                        }
                }
+               kfree(class);
        }
        kfree(pool);
 }
@@ -999,7 +1054,6 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size)
 {
        unsigned long obj;
        struct link_free *link;
-       int class_idx;
        struct size_class *class;
 
        struct page *first_page, *m_page;
@@ -1008,9 +1062,7 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size)
        if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE))
                return 0;
 
-       class_idx = get_size_class_index(size);
-       class = &pool->size_class[class_idx];
-       BUG_ON(class_idx != class->index);
+       class = pool->size_class[get_size_class_index(size)];
 
        spin_lock(&class->lock);
        first_page = find_get_zspage(class);
@@ -1063,7 +1115,7 @@ void zs_free(struct zs_pool *pool, unsigned long obj)
        first_page = get_first_page(f_page);
 
        get_zspage_mapping(first_page, &class_idx, &fullness);
-       class = &pool->size_class[class_idx];
+       class = pool->size_class[class_idx];
        f_offset = obj_idx_to_offset(f_page, f_objidx, class->size);
 
        spin_lock(&class->lock);
@@ -1124,7 +1176,7 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle,
 
        obj_handle_to_location(handle, &page, &obj_idx);
        get_zspage_mapping(get_first_page(page), &class_idx, &fg);
-       class = &pool->size_class[class_idx];
+       class = pool->size_class[class_idx];
        off = obj_idx_to_offset(page, obj_idx, class->size);
 
        area = &get_cpu_var(zs_map_area);
@@ -1158,7 +1210,7 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
 
        obj_handle_to_location(handle, &page, &obj_idx);
        get_zspage_mapping(get_first_page(page), &class_idx, &fg);
-       class = &pool->size_class[class_idx];
+       class = pool->size_class[class_idx];
        off = obj_idx_to_offset(page, obj_idx, class->size);
 
        area = this_cpu_ptr(&zs_map_area);