2012-01-09 15:51:56 -07:00
|
|
|
/*
|
|
|
|
* zsmalloc memory allocator
|
|
|
|
*
|
|
|
|
* Copyright (C) 2011 Nitin Gupta
|
2014-01-30 16:45:55 -07:00
|
|
|
* Copyright (C) 2012, 2013 Minchan Kim
|
2012-01-09 15:51:56 -07:00
|
|
|
*
|
|
|
|
* This code is released using a dual license strategy: BSD/GPL
|
|
|
|
* You can choose the license that better fits your requirements.
|
|
|
|
*
|
|
|
|
* Released under the terms of 3-clause BSD License
|
|
|
|
* Released under the terms of GNU General Public License Version 2.0
|
|
|
|
*/
|
|
|
|
|
2012-06-09 18:41:14 -06:00
|
|
|
/*
|
2013-12-10 19:04:37 -07:00
|
|
|
* This allocator is designed for use with zram. Thus, the allocator is
|
|
|
|
* supposed to work well under low memory conditions. In particular, it
|
|
|
|
* never attempts higher order page allocation which is very likely to
|
|
|
|
* fail under memory pressure. On the other hand, if we just use single
|
|
|
|
* (0-order) pages, it would suffer from very high fragmentation --
|
|
|
|
* any object of size PAGE_SIZE/2 or larger would occupy an entire page.
|
|
|
|
* This was one of the major issues with its predecessor (xvmalloc).
|
2012-06-09 18:41:14 -06:00
|
|
|
*
|
|
|
|
* To overcome these issues, zsmalloc allocates a bunch of 0-order pages
|
|
|
|
* and links them together using various 'struct page' fields. These linked
|
|
|
|
* pages act as a single higher-order page i.e. an object can span 0-order
|
|
|
|
* page boundaries. The code refers to these linked pages as a single entity
|
|
|
|
* called zspage.
|
|
|
|
*
|
2013-12-10 19:04:37 -07:00
|
|
|
* For simplicity, zsmalloc can only allocate objects of size up to PAGE_SIZE
|
|
|
|
* since this satisfies the requirements of all its current users (in the
|
|
|
|
* worst case, page is incompressible and is thus stored "as-is" i.e. in
|
|
|
|
* uncompressed form). For allocation requests larger than this size, failure
|
|
|
|
* is returned (see zs_malloc).
|
|
|
|
*
|
|
|
|
* Additionally, zs_malloc() does not return a dereferenceable pointer.
|
|
|
|
* Instead, it returns an opaque handle (unsigned long) which encodes actual
|
|
|
|
* location of the allocated object. The reason for this indirection is that
|
|
|
|
* zsmalloc does not keep zspages permanently mapped since that would cause
|
|
|
|
* issues on 32-bit systems where the VA region for kernel space mappings
|
|
|
|
* is very small. So, before using the allocating memory, the object has to
|
|
|
|
* be mapped using zs_map_object() to get a usable pointer and subsequently
|
|
|
|
* unmapped using zs_unmap_object().
|
|
|
|
*
|
2012-06-09 18:41:14 -06:00
|
|
|
* Following is how we use various fields and flags of underlying
|
|
|
|
* struct page(s) to form a zspage.
|
|
|
|
*
|
|
|
|
* Usage of struct page fields:
|
|
|
|
* page->first_page: points to the first component (0-order) page
|
|
|
|
* page->index (union with page->freelist): offset of the first object
|
|
|
|
* starting in this page. For the first page, this is
|
|
|
|
* always 0, so we use this field (aka freelist) to point
|
|
|
|
* to the first free object in zspage.
|
|
|
|
* page->lru: links together all component pages (except the first page)
|
|
|
|
* of a zspage
|
|
|
|
*
|
|
|
|
* For _first_ page only:
|
|
|
|
*
|
|
|
|
* page->private (union with page->first_page): refers to the
|
|
|
|
* component page after the first page
|
|
|
|
* page->freelist: points to the first free object in zspage.
|
|
|
|
* Free objects are linked together using in-place
|
|
|
|
* metadata.
|
|
|
|
* page->objects: maximum number of objects we can store in this
|
|
|
|
* zspage (class->zspage_order * PAGE_SIZE / class->size)
|
|
|
|
* page->lru: links together first pages of various zspages.
|
|
|
|
* Basically forming list of zspages in a fullness group.
|
|
|
|
* page->mapping: class index and fullness group of the zspage
|
|
|
|
*
|
|
|
|
* Usage of struct page flags:
|
|
|
|
* PG_private: identifies the first component page
|
|
|
|
* PG_private2: identifies the last component page
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
2012-01-09 15:51:56 -07:00
|
|
|
#ifdef CONFIG_ZSMALLOC_DEBUG
|
|
|
|
#define DEBUG
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/bitops.h>
|
|
|
|
#include <linux/errno.h>
|
|
|
|
#include <linux/highmem.h>
|
|
|
|
#include <linux/string.h>
|
|
|
|
#include <linux/slab.h>
|
|
|
|
#include <asm/tlbflush.h>
|
|
|
|
#include <asm/pgtable.h>
|
|
|
|
#include <linux/cpumask.h>
|
|
|
|
#include <linux/cpu.h>
|
2012-02-13 07:47:49 -07:00
|
|
|
#include <linux/vmalloc.h>
|
2012-07-18 10:55:55 -06:00
|
|
|
#include <linux/hardirq.h>
|
2012-08-08 00:12:17 -06:00
|
|
|
#include <linux/spinlock.h>
|
|
|
|
#include <linux/types.h>
|
2014-01-30 16:45:50 -07:00
|
|
|
#include <linux/zsmalloc.h>
|
2012-08-08 00:12:17 -06:00
|
|
|
|
|
|
|
/*
|
|
|
|
* This must be power of 2 and greater than of equal to sizeof(link_free).
|
|
|
|
* These two conditions ensure that any 'struct link_free' itself doesn't
|
|
|
|
* span more than 1 page which avoids complex case of mapping 2 pages simply
|
|
|
|
* to restore link_free pointer values.
|
|
|
|
*/
|
|
|
|
#define ZS_ALIGN 8
|
|
|
|
|
|
|
|
/*
|
|
|
|
* A single 'zspage' is composed of up to 2^N discontiguous 0-order (single)
|
|
|
|
* pages. ZS_MAX_ZSPAGE_ORDER defines upper limit on N.
|
|
|
|
*/
|
|
|
|
#define ZS_MAX_ZSPAGE_ORDER 2
|
|
|
|
#define ZS_MAX_PAGES_PER_ZSPAGE (_AC(1, UL) << ZS_MAX_ZSPAGE_ORDER)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Object location (<PFN>, <obj_idx>) is encoded as
|
2013-12-10 19:04:37 -07:00
|
|
|
* as single (unsigned long) handle value.
|
2012-08-08 00:12:17 -06:00
|
|
|
*
|
|
|
|
* Note that object index <obj_idx> is relative to system
|
|
|
|
* page <PFN> it is stored in, so for each sub-page belonging
|
|
|
|
* to a zspage, obj_idx starts with 0.
|
|
|
|
*
|
|
|
|
* This is made more complicated by various memory models and PAE.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef MAX_PHYSMEM_BITS
|
|
|
|
#ifdef CONFIG_HIGHMEM64G
|
|
|
|
#define MAX_PHYSMEM_BITS 36
|
|
|
|
#else /* !CONFIG_HIGHMEM64G */
|
|
|
|
/*
|
|
|
|
* If this definition of MAX_PHYSMEM_BITS is used, OBJ_INDEX_BITS will just
|
|
|
|
* be PAGE_SHIFT
|
|
|
|
*/
|
|
|
|
#define MAX_PHYSMEM_BITS BITS_PER_LONG
|
|
|
|
#endif
|
|
|
|
#endif
|
|
|
|
#define _PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT)
|
|
|
|
#define OBJ_INDEX_BITS (BITS_PER_LONG - _PFN_BITS)
|
|
|
|
#define OBJ_INDEX_MASK ((_AC(1, UL) << OBJ_INDEX_BITS) - 1)
|
|
|
|
|
|
|
|
#define MAX(a, b) ((a) >= (b) ? (a) : (b))
|
|
|
|
/* ZS_MIN_ALLOC_SIZE must be multiple of ZS_ALIGN */
|
|
|
|
#define ZS_MIN_ALLOC_SIZE \
|
|
|
|
MAX(32, (ZS_MAX_PAGES_PER_ZSPAGE << PAGE_SHIFT >> OBJ_INDEX_BITS))
|
|
|
|
#define ZS_MAX_ALLOC_SIZE PAGE_SIZE
|
|
|
|
|
|
|
|
/*
|
|
|
|
* On systems with 4K page size, this gives 254 size classes! There is a
|
|
|
|
* trader-off here:
|
|
|
|
* - Large number of size classes is potentially wasteful as free page are
|
|
|
|
* spread across these classes
|
|
|
|
* - Small number of size classes causes large internal fragmentation
|
|
|
|
* - Probably its better to use specific size classes (empirically
|
|
|
|
* determined). NOTE: all those class sizes must be set as multiple of
|
|
|
|
* ZS_ALIGN to make sure link_free itself never has to span 2 pages.
|
|
|
|
*
|
|
|
|
* ZS_MIN_ALLOC_SIZE and ZS_SIZE_CLASS_DELTA must be multiple of ZS_ALIGN
|
|
|
|
* (reason above)
|
|
|
|
*/
|
2013-01-25 10:46:18 -07:00
|
|
|
#define ZS_SIZE_CLASS_DELTA (PAGE_SIZE >> 8)
|
2012-08-08 00:12:17 -06:00
|
|
|
#define ZS_SIZE_CLASSES ((ZS_MAX_ALLOC_SIZE - ZS_MIN_ALLOC_SIZE) / \
|
|
|
|
ZS_SIZE_CLASS_DELTA + 1)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We do not maintain any list for completely empty or full pages
|
|
|
|
*/
|
|
|
|
enum fullness_group {
|
|
|
|
ZS_ALMOST_FULL,
|
|
|
|
ZS_ALMOST_EMPTY,
|
|
|
|
_ZS_NR_FULLNESS_GROUPS,
|
|
|
|
|
|
|
|
ZS_EMPTY,
|
|
|
|
ZS_FULL
|
|
|
|
};
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We assign a page to ZS_ALMOST_EMPTY fullness group when:
|
|
|
|
* n <= N / f, where
|
|
|
|
* n = number of allocated objects
|
|
|
|
* N = total number of objects zspage can store
|
|
|
|
* f = 1/fullness_threshold_frac
|
|
|
|
*
|
|
|
|
* Similarly, we assign zspage to:
|
|
|
|
* ZS_ALMOST_FULL when n > N / f
|
|
|
|
* ZS_EMPTY when n == 0
|
|
|
|
* ZS_FULL when n == N
|
|
|
|
*
|
|
|
|
* (see: fix_fullness_group())
|
|
|
|
*/
|
|
|
|
static const int fullness_threshold_frac = 4;
|
|
|
|
|
|
|
|
struct size_class {
|
|
|
|
/*
|
|
|
|
* Size of objects stored in this class. Must be multiple
|
|
|
|
* of ZS_ALIGN.
|
|
|
|
*/
|
|
|
|
int size;
|
|
|
|
unsigned int index;
|
|
|
|
|
|
|
|
/* Number of PAGE_SIZE sized pages to combine to form a 'zspage' */
|
|
|
|
int pages_per_zspage;
|
|
|
|
|
|
|
|
spinlock_t lock;
|
|
|
|
|
|
|
|
/* stats */
|
|
|
|
u64 pages_allocated;
|
|
|
|
|
|
|
|
struct page *fullness_list[_ZS_NR_FULLNESS_GROUPS];
|
|
|
|
};
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Placed within free objects to form a singly linked list.
|
|
|
|
* For every zspage, first_page->freelist gives head of this list.
|
|
|
|
*
|
|
|
|
* This must be power of 2 and less than or equal to ZS_ALIGN
|
|
|
|
*/
|
|
|
|
struct link_free {
|
|
|
|
/* Handle of next free chunk (encodes <PFN, obj_idx>) */
|
|
|
|
void *next;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct zs_pool {
|
|
|
|
struct size_class size_class[ZS_SIZE_CLASSES];
|
|
|
|
|
|
|
|
gfp_t flags; /* allocation flags used when growing pool */
|
|
|
|
};
|
2012-01-09 15:51:56 -07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* A zspage's class index and fullness group
|
|
|
|
* are encoded in its (first)page->mapping
|
|
|
|
*/
|
|
|
|
#define CLASS_IDX_BITS 28
|
|
|
|
#define FULLNESS_BITS 4
|
|
|
|
#define CLASS_IDX_MASK ((1 << CLASS_IDX_BITS) - 1)
|
|
|
|
#define FULLNESS_MASK ((1 << FULLNESS_BITS) - 1)
|
|
|
|
|
2012-07-18 10:55:56 -06:00
|
|
|
struct mapping_area {
|
2013-12-10 19:04:36 -07:00
|
|
|
#ifdef CONFIG_PGTABLE_MAPPING
|
2012-07-18 10:55:56 -06:00
|
|
|
struct vm_struct *vm; /* vm area for mapping object that span pages */
|
|
|
|
#else
|
|
|
|
char *vm_buf; /* copy buffer for objects that span pages */
|
|
|
|
#endif
|
|
|
|
char *vm_addr; /* address of kmap_atomic()'ed pages */
|
|
|
|
enum zs_mapmode vm_mm; /* mapping mode */
|
|
|
|
};
|
|
|
|
|
|
|
|
|
2012-01-09 15:51:56 -07:00
|
|
|
/* per-cpu VM mapping areas for zspage accesses that cross page boundaries */
|
|
|
|
static DEFINE_PER_CPU(struct mapping_area, zs_map_area);
|
|
|
|
|
|
|
|
static int is_first_page(struct page *page)
|
|
|
|
{
|
2012-04-25 00:23:09 -06:00
|
|
|
return PagePrivate(page);
|
2012-01-09 15:51:56 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
static int is_last_page(struct page *page)
|
|
|
|
{
|
2012-04-25 00:23:09 -06:00
|
|
|
return PagePrivate2(page);
|
2012-01-09 15:51:56 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
static void get_zspage_mapping(struct page *page, unsigned int *class_idx,
|
|
|
|
enum fullness_group *fullness)
|
|
|
|
{
|
|
|
|
unsigned long m;
|
|
|
|
BUG_ON(!is_first_page(page));
|
|
|
|
|
|
|
|
m = (unsigned long)page->mapping;
|
|
|
|
*fullness = m & FULLNESS_MASK;
|
|
|
|
*class_idx = (m >> FULLNESS_BITS) & CLASS_IDX_MASK;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void set_zspage_mapping(struct page *page, unsigned int class_idx,
|
|
|
|
enum fullness_group fullness)
|
|
|
|
{
|
|
|
|
unsigned long m;
|
|
|
|
BUG_ON(!is_first_page(page));
|
|
|
|
|
|
|
|
m = ((class_idx & CLASS_IDX_MASK) << FULLNESS_BITS) |
|
|
|
|
(fullness & FULLNESS_MASK);
|
|
|
|
page->mapping = (struct address_space *)m;
|
|
|
|
}
|
|
|
|
|
2013-12-10 19:04:37 -07:00
|
|
|
/*
|
|
|
|
* zsmalloc divides the pool into various size classes where each
|
|
|
|
* class maintains a list of zspages where each zspage is divided
|
|
|
|
* into equal sized chunks. Each allocation falls into one of these
|
|
|
|
* classes depending on its size. This function returns index of the
|
|
|
|
* size class which has chunk size big enough to hold the give size.
|
|
|
|
*/
|
2012-01-09 15:51:56 -07:00
|
|
|
static int get_size_class_index(int size)
|
|
|
|
{
|
|
|
|
int idx = 0;
|
|
|
|
|
|
|
|
if (likely(size > ZS_MIN_ALLOC_SIZE))
|
|
|
|
idx = DIV_ROUND_UP(size - ZS_MIN_ALLOC_SIZE,
|
|
|
|
ZS_SIZE_CLASS_DELTA);
|
|
|
|
|
|
|
|
return idx;
|
|
|
|
}
|
|
|
|
|
2013-12-10 19:04:37 -07:00
|
|
|
/*
|
|
|
|
* For each size class, zspages are divided into different groups
|
|
|
|
* depending on how "full" they are. This was done so that we could
|
|
|
|
* easily find empty or nearly empty zspages when we try to shrink
|
|
|
|
* the pool (not yet implemented). This function returns fullness
|
|
|
|
* status of the given page.
|
|
|
|
*/
|
2012-01-09 15:51:56 -07:00
|
|
|
static enum fullness_group get_fullness_group(struct page *page)
|
|
|
|
{
|
|
|
|
int inuse, max_objects;
|
|
|
|
enum fullness_group fg;
|
|
|
|
BUG_ON(!is_first_page(page));
|
|
|
|
|
|
|
|
inuse = page->inuse;
|
|
|
|
max_objects = page->objects;
|
|
|
|
|
|
|
|
if (inuse == 0)
|
|
|
|
fg = ZS_EMPTY;
|
|
|
|
else if (inuse == max_objects)
|
|
|
|
fg = ZS_FULL;
|
|
|
|
else if (inuse <= max_objects / fullness_threshold_frac)
|
|
|
|
fg = ZS_ALMOST_EMPTY;
|
|
|
|
else
|
|
|
|
fg = ZS_ALMOST_FULL;
|
|
|
|
|
|
|
|
return fg;
|
|
|
|
}
|
|
|
|
|
2013-12-10 19:04:37 -07:00
|
|
|
/*
|
|
|
|
* Each size class maintains various freelists and zspages are assigned
|
|
|
|
* to one of these freelists based on the number of live objects they
|
|
|
|
* have. This functions inserts the given zspage into the freelist
|
|
|
|
* identified by <class, fullness_group>.
|
|
|
|
*/
|
2012-01-09 15:51:56 -07:00
|
|
|
static void insert_zspage(struct page *page, struct size_class *class,
|
|
|
|
enum fullness_group fullness)
|
|
|
|
{
|
|
|
|
struct page **head;
|
|
|
|
|
|
|
|
BUG_ON(!is_first_page(page));
|
|
|
|
|
|
|
|
if (fullness >= _ZS_NR_FULLNESS_GROUPS)
|
|
|
|
return;
|
|
|
|
|
|
|
|
head = &class->fullness_list[fullness];
|
|
|
|
if (*head)
|
|
|
|
list_add_tail(&page->lru, &(*head)->lru);
|
|
|
|
|
|
|
|
*head = page;
|
|
|
|
}
|
|
|
|
|
2013-12-10 19:04:37 -07:00
|
|
|
/*
|
|
|
|
* This function removes the given zspage from the freelist identified
|
|
|
|
* by <class, fullness_group>.
|
|
|
|
*/
|
2012-01-09 15:51:56 -07:00
|
|
|
static void remove_zspage(struct page *page, struct size_class *class,
|
|
|
|
enum fullness_group fullness)
|
|
|
|
{
|
|
|
|
struct page **head;
|
|
|
|
|
|
|
|
BUG_ON(!is_first_page(page));
|
|
|
|
|
|
|
|
if (fullness >= _ZS_NR_FULLNESS_GROUPS)
|
|
|
|
return;
|
|
|
|
|
|
|
|
head = &class->fullness_list[fullness];
|
|
|
|
BUG_ON(!*head);
|
|
|
|
if (list_empty(&(*head)->lru))
|
|
|
|
*head = NULL;
|
|
|
|
else if (*head == page)
|
|
|
|
*head = (struct page *)list_entry((*head)->lru.next,
|
|
|
|
struct page, lru);
|
|
|
|
|
|
|
|
list_del_init(&page->lru);
|
|
|
|
}
|
|
|
|
|
2013-12-10 19:04:37 -07:00
|
|
|
/*
|
|
|
|
* Each size class maintains zspages in different fullness groups depending
|
|
|
|
* on the number of live objects they contain. When allocating or freeing
|
|
|
|
* objects, the fullness status of the page can change, say, from ALMOST_FULL
|
|
|
|
* to ALMOST_EMPTY when freeing an object. This function checks if such
|
|
|
|
* a status change has occurred for the given page and accordingly moves the
|
|
|
|
* page from the freelist of the old fullness group to that of the new
|
|
|
|
* fullness group.
|
|
|
|
*/
|
2012-01-09 15:51:56 -07:00
|
|
|
static enum fullness_group fix_fullness_group(struct zs_pool *pool,
|
|
|
|
struct page *page)
|
|
|
|
{
|
|
|
|
int class_idx;
|
|
|
|
struct size_class *class;
|
|
|
|
enum fullness_group currfg, newfg;
|
|
|
|
|
|
|
|
BUG_ON(!is_first_page(page));
|
|
|
|
|
|
|
|
get_zspage_mapping(page, &class_idx, &currfg);
|
|
|
|
newfg = get_fullness_group(page);
|
|
|
|
if (newfg == currfg)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
class = &pool->size_class[class_idx];
|
|
|
|
remove_zspage(page, class, currfg);
|
|
|
|
insert_zspage(page, class, newfg);
|
|
|
|
set_zspage_mapping(page, class_idx, newfg);
|
|
|
|
|
|
|
|
out:
|
|
|
|
return newfg;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We have to decide on how many pages to link together
|
|
|
|
* to form a zspage for each size class. This is important
|
|
|
|
* to reduce wastage due to unusable space left at end of
|
|
|
|
* each zspage which is given as:
|
|
|
|
* wastage = Zp - Zp % size_class
|
|
|
|
* where Zp = zspage size = k * PAGE_SIZE where k = 1, 2, ...
|
|
|
|
*
|
|
|
|
* For example, for size class of 3/8 * PAGE_SIZE, we should
|
|
|
|
* link together 3 PAGE_SIZE sized pages to form a zspage
|
|
|
|
* since then we can perfectly fit in 8 such objects.
|
|
|
|
*/
|
2012-05-03 00:40:39 -06:00
|
|
|
static int get_pages_per_zspage(int class_size)
|
2012-01-09 15:51:56 -07:00
|
|
|
{
|
|
|
|
int i, max_usedpc = 0;
|
|
|
|
/* zspage order which gives maximum used size per KB */
|
|
|
|
int max_usedpc_order = 1;
|
|
|
|
|
2012-03-05 10:33:21 -07:00
|
|
|
for (i = 1; i <= ZS_MAX_PAGES_PER_ZSPAGE; i++) {
|
2012-01-09 15:51:56 -07:00
|
|
|
int zspage_size;
|
|
|
|
int waste, usedpc;
|
|
|
|
|
|
|
|
zspage_size = i * PAGE_SIZE;
|
|
|
|
waste = zspage_size % class_size;
|
|
|
|
usedpc = (zspage_size - waste) * 100 / zspage_size;
|
|
|
|
|
|
|
|
if (usedpc > max_usedpc) {
|
|
|
|
max_usedpc = usedpc;
|
|
|
|
max_usedpc_order = i;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return max_usedpc_order;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* A single 'zspage' is composed of many system pages which are
|
|
|
|
* linked together using fields in struct page. This function finds
|
|
|
|
* the first/head page, given any component page of a zspage.
|
|
|
|
*/
|
|
|
|
static struct page *get_first_page(struct page *page)
|
|
|
|
{
|
|
|
|
if (is_first_page(page))
|
|
|
|
return page;
|
|
|
|
else
|
|
|
|
return page->first_page;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct page *get_next_page(struct page *page)
|
|
|
|
{
|
|
|
|
struct page *next;
|
|
|
|
|
|
|
|
if (is_last_page(page))
|
|
|
|
next = NULL;
|
|
|
|
else if (is_first_page(page))
|
2013-07-12 01:08:13 -06:00
|
|
|
next = (struct page *)page_private(page);
|
2012-01-09 15:51:56 -07:00
|
|
|
else
|
|
|
|
next = list_entry(page->lru.next, struct page, lru);
|
|
|
|
|
|
|
|
return next;
|
|
|
|
}
|
|
|
|
|
2013-11-22 10:30:41 -07:00
|
|
|
/*
|
|
|
|
* Encode <page, obj_idx> as a single handle value.
|
|
|
|
* On hardware platforms with physical memory starting at 0x0 the pfn
|
|
|
|
* could be 0 so we ensure that the handle will never be 0 by adjusting the
|
|
|
|
* encoded obj_idx value before encoding.
|
|
|
|
*/
|
2012-01-09 15:51:56 -07:00
|
|
|
static void *obj_location_to_handle(struct page *page, unsigned long obj_idx)
|
|
|
|
{
|
|
|
|
unsigned long handle;
|
|
|
|
|
|
|
|
if (!page) {
|
|
|
|
BUG_ON(obj_idx);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
handle = page_to_pfn(page) << OBJ_INDEX_BITS;
|
2013-11-22 10:30:41 -07:00
|
|
|
handle |= ((obj_idx + 1) & OBJ_INDEX_MASK);
|
2012-01-09 15:51:56 -07:00
|
|
|
|
|
|
|
return (void *)handle;
|
|
|
|
}
|
|
|
|
|
2013-11-22 10:30:41 -07:00
|
|
|
/*
|
|
|
|
* Decode <page, obj_idx> pair from the given object handle. We adjust the
|
|
|
|
* decoded obj_idx back to its original value since it was adjusted in
|
|
|
|
* obj_location_to_handle().
|
|
|
|
*/
|
2012-06-08 00:39:25 -06:00
|
|
|
static void obj_handle_to_location(unsigned long handle, struct page **page,
|
2012-01-09 15:51:56 -07:00
|
|
|
unsigned long *obj_idx)
|
|
|
|
{
|
2012-06-08 00:39:25 -06:00
|
|
|
*page = pfn_to_page(handle >> OBJ_INDEX_BITS);
|
2013-11-22 10:30:41 -07:00
|
|
|
*obj_idx = (handle & OBJ_INDEX_MASK) - 1;
|
2012-01-09 15:51:56 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
static unsigned long obj_idx_to_offset(struct page *page,
|
|
|
|
unsigned long obj_idx, int class_size)
|
|
|
|
{
|
|
|
|
unsigned long off = 0;
|
|
|
|
|
|
|
|
if (!is_first_page(page))
|
|
|
|
off = page->index;
|
|
|
|
|
|
|
|
return off + obj_idx * class_size;
|
|
|
|
}
|
|
|
|
|
2012-04-02 08:13:56 -06:00
|
|
|
static void reset_page(struct page *page)
|
|
|
|
{
|
|
|
|
clear_bit(PG_private, &page->flags);
|
|
|
|
clear_bit(PG_private_2, &page->flags);
|
|
|
|
set_page_private(page, 0);
|
|
|
|
page->mapping = NULL;
|
|
|
|
page->freelist = NULL;
|
2013-02-22 17:34:59 -07:00
|
|
|
page_mapcount_reset(page);
|
2012-04-02 08:13:56 -06:00
|
|
|
}
|
|
|
|
|
2012-01-09 15:51:56 -07:00
|
|
|
static void free_zspage(struct page *first_page)
|
|
|
|
{
|
2012-04-02 08:13:56 -06:00
|
|
|
struct page *nextp, *tmp, *head_extra;
|
2012-01-09 15:51:56 -07:00
|
|
|
|
|
|
|
BUG_ON(!is_first_page(first_page));
|
|
|
|
BUG_ON(first_page->inuse);
|
|
|
|
|
2012-04-02 08:13:56 -06:00
|
|
|
head_extra = (struct page *)page_private(first_page);
|
2012-01-09 15:51:56 -07:00
|
|
|
|
2012-04-02 08:13:56 -06:00
|
|
|
reset_page(first_page);
|
2012-01-09 15:51:56 -07:00
|
|
|
__free_page(first_page);
|
|
|
|
|
|
|
|
/* zspage with only 1 system page */
|
2012-04-02 08:13:56 -06:00
|
|
|
if (!head_extra)
|
2012-01-09 15:51:56 -07:00
|
|
|
return;
|
|
|
|
|
2012-04-02 08:13:56 -06:00
|
|
|
list_for_each_entry_safe(nextp, tmp, &head_extra->lru, lru) {
|
2012-01-09 15:51:56 -07:00
|
|
|
list_del(&nextp->lru);
|
2012-04-02 08:13:56 -06:00
|
|
|
reset_page(nextp);
|
2012-01-09 15:51:56 -07:00
|
|
|
__free_page(nextp);
|
|
|
|
}
|
2012-04-02 08:13:56 -06:00
|
|
|
reset_page(head_extra);
|
|
|
|
__free_page(head_extra);
|
2012-01-09 15:51:56 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Initialize a newly allocated zspage */
|
|
|
|
static void init_zspage(struct page *first_page, struct size_class *class)
|
|
|
|
{
|
|
|
|
unsigned long off = 0;
|
|
|
|
struct page *page = first_page;
|
|
|
|
|
|
|
|
BUG_ON(!is_first_page(first_page));
|
|
|
|
while (page) {
|
|
|
|
struct page *next_page;
|
|
|
|
struct link_free *link;
|
|
|
|
unsigned int i, objs_on_page;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* page->index stores offset of first object starting
|
|
|
|
* in the page. For the first page, this is always 0,
|
|
|
|
* so we use first_page->index (aka ->freelist) to store
|
|
|
|
* head of corresponding zspage's freelist.
|
|
|
|
*/
|
|
|
|
if (page != first_page)
|
|
|
|
page->index = off;
|
|
|
|
|
|
|
|
link = (struct link_free *)kmap_atomic(page) +
|
|
|
|
off / sizeof(*link);
|
|
|
|
objs_on_page = (PAGE_SIZE - off) / class->size;
|
|
|
|
|
|
|
|
for (i = 1; i <= objs_on_page; i++) {
|
|
|
|
off += class->size;
|
|
|
|
if (off < PAGE_SIZE) {
|
|
|
|
link->next = obj_location_to_handle(page, i);
|
|
|
|
link += class->size / sizeof(*link);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We now come to the last (full or partial) object on this
|
|
|
|
* page, which must point to the first object on the next
|
|
|
|
* page (if present)
|
|
|
|
*/
|
|
|
|
next_page = get_next_page(page);
|
|
|
|
link->next = obj_location_to_handle(next_page, 0);
|
|
|
|
kunmap_atomic(link);
|
|
|
|
page = next_page;
|
|
|
|
off = (off + class->size) % PAGE_SIZE;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Allocate a zspage for the given size class
|
|
|
|
*/
|
|
|
|
static struct page *alloc_zspage(struct size_class *class, gfp_t flags)
|
|
|
|
{
|
|
|
|
int i, error;
|
2012-06-13 15:03:42 -06:00
|
|
|
struct page *first_page = NULL, *uninitialized_var(prev_page);
|
2012-01-09 15:51:56 -07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Allocate individual pages and link them together as:
|
|
|
|
* 1. first page->private = first sub-page
|
|
|
|
* 2. all sub-pages are linked together using page->lru
|
|
|
|
* 3. each sub-page is linked to the first page using page->first_page
|
|
|
|
*
|
|
|
|
* For each size class, First/Head pages are linked together using
|
|
|
|
* page->lru. Also, we set PG_private to identify the first page
|
|
|
|
* (i.e. no other sub-page has this flag set) and PG_private_2 to
|
|
|
|
* identify the last page.
|
|
|
|
*/
|
|
|
|
error = -ENOMEM;
|
2012-05-03 00:40:39 -06:00
|
|
|
for (i = 0; i < class->pages_per_zspage; i++) {
|
2012-06-13 15:03:42 -06:00
|
|
|
struct page *page;
|
2012-01-09 15:51:56 -07:00
|
|
|
|
|
|
|
page = alloc_page(flags);
|
|
|
|
if (!page)
|
|
|
|
goto cleanup;
|
|
|
|
|
|
|
|
INIT_LIST_HEAD(&page->lru);
|
|
|
|
if (i == 0) { /* first page */
|
2012-04-25 00:23:09 -06:00
|
|
|
SetPagePrivate(page);
|
2012-01-09 15:51:56 -07:00
|
|
|
set_page_private(page, 0);
|
|
|
|
first_page = page;
|
|
|
|
first_page->inuse = 0;
|
|
|
|
}
|
|
|
|
if (i == 1)
|
2013-07-12 01:08:13 -06:00
|
|
|
set_page_private(first_page, (unsigned long)page);
|
2012-01-09 15:51:56 -07:00
|
|
|
if (i >= 1)
|
|
|
|
page->first_page = first_page;
|
|
|
|
if (i >= 2)
|
|
|
|
list_add(&page->lru, &prev_page->lru);
|
2012-05-03 00:40:39 -06:00
|
|
|
if (i == class->pages_per_zspage - 1) /* last page */
|
2012-04-25 00:23:09 -06:00
|
|
|
SetPagePrivate2(page);
|
2012-01-09 15:51:56 -07:00
|
|
|
prev_page = page;
|
|
|
|
}
|
|
|
|
|
|
|
|
init_zspage(first_page, class);
|
|
|
|
|
|
|
|
first_page->freelist = obj_location_to_handle(first_page, 0);
|
|
|
|
/* Maximum number of objects we can store in this zspage */
|
2012-05-03 00:40:39 -06:00
|
|
|
first_page->objects = class->pages_per_zspage * PAGE_SIZE / class->size;
|
2012-01-09 15:51:56 -07:00
|
|
|
|
|
|
|
error = 0; /* Success */
|
|
|
|
|
|
|
|
cleanup:
|
|
|
|
if (unlikely(error) && first_page) {
|
|
|
|
free_zspage(first_page);
|
|
|
|
first_page = NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
return first_page;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct page *find_get_zspage(struct size_class *class)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
struct page *page;
|
|
|
|
|
|
|
|
for (i = 0; i < _ZS_NR_FULLNESS_GROUPS; i++) {
|
|
|
|
page = class->fullness_list[i];
|
|
|
|
if (page)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
return page;
|
|
|
|
}
|
|
|
|
|
2013-12-10 19:04:36 -07:00
|
|
|
#ifdef CONFIG_PGTABLE_MAPPING
|
2012-07-18 10:55:56 -06:00
|
|
|
static inline int __zs_cpu_up(struct mapping_area *area)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* Make sure we don't leak memory if a cpu UP notification
|
|
|
|
* and zs_init() race and both call zs_cpu_up() on the same cpu
|
|
|
|
*/
|
|
|
|
if (area->vm)
|
|
|
|
return 0;
|
|
|
|
area->vm = alloc_vm_area(PAGE_SIZE * 2, NULL);
|
|
|
|
if (!area->vm)
|
|
|
|
return -ENOMEM;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void __zs_cpu_down(struct mapping_area *area)
|
|
|
|
{
|
|
|
|
if (area->vm)
|
|
|
|
free_vm_area(area->vm);
|
|
|
|
area->vm = NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void *__zs_map_object(struct mapping_area *area,
|
|
|
|
struct page *pages[2], int off, int size)
|
|
|
|
{
|
|
|
|
BUG_ON(map_vm_area(area->vm, PAGE_KERNEL, &pages));
|
|
|
|
area->vm_addr = area->vm->addr;
|
|
|
|
return area->vm_addr + off;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void __zs_unmap_object(struct mapping_area *area,
|
|
|
|
struct page *pages[2], int off, int size)
|
|
|
|
{
|
|
|
|
unsigned long addr = (unsigned long)area->vm_addr;
|
|
|
|
|
2013-03-26 18:43:14 -06:00
|
|
|
unmap_kernel_range(addr, PAGE_SIZE * 2);
|
2012-07-18 10:55:56 -06:00
|
|
|
}
|
|
|
|
|
2013-12-10 19:04:36 -07:00
|
|
|
#else /* CONFIG_PGTABLE_MAPPING */
|
2012-07-18 10:55:56 -06:00
|
|
|
|
|
|
|
static inline int __zs_cpu_up(struct mapping_area *area)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* Make sure we don't leak memory if a cpu UP notification
|
|
|
|
* and zs_init() race and both call zs_cpu_up() on the same cpu
|
|
|
|
*/
|
|
|
|
if (area->vm_buf)
|
|
|
|
return 0;
|
|
|
|
area->vm_buf = (char *)__get_free_page(GFP_KERNEL);
|
|
|
|
if (!area->vm_buf)
|
|
|
|
return -ENOMEM;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void __zs_cpu_down(struct mapping_area *area)
|
|
|
|
{
|
|
|
|
if (area->vm_buf)
|
|
|
|
free_page((unsigned long)area->vm_buf);
|
|
|
|
area->vm_buf = NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void *__zs_map_object(struct mapping_area *area,
|
|
|
|
struct page *pages[2], int off, int size)
|
2012-07-02 15:15:49 -06:00
|
|
|
{
|
|
|
|
int sizes[2];
|
|
|
|
void *addr;
|
2012-07-18 10:55:56 -06:00
|
|
|
char *buf = area->vm_buf;
|
2012-07-02 15:15:49 -06:00
|
|
|
|
2012-07-18 10:55:56 -06:00
|
|
|
/* disable page faults to match kmap_atomic() return conditions */
|
|
|
|
pagefault_disable();
|
|
|
|
|
|
|
|
/* no read fastpath */
|
|
|
|
if (area->vm_mm == ZS_MM_WO)
|
|
|
|
goto out;
|
2012-07-02 15:15:49 -06:00
|
|
|
|
|
|
|
sizes[0] = PAGE_SIZE - off;
|
|
|
|
sizes[1] = size - sizes[0];
|
|
|
|
|
|
|
|
/* copy object to per-cpu buffer */
|
|
|
|
addr = kmap_atomic(pages[0]);
|
|
|
|
memcpy(buf, addr + off, sizes[0]);
|
|
|
|
kunmap_atomic(addr);
|
|
|
|
addr = kmap_atomic(pages[1]);
|
|
|
|
memcpy(buf + sizes[0], addr, sizes[1]);
|
|
|
|
kunmap_atomic(addr);
|
2012-07-18 10:55:56 -06:00
|
|
|
out:
|
|
|
|
return area->vm_buf;
|
2012-07-02 15:15:49 -06:00
|
|
|
}
|
|
|
|
|
2012-07-18 10:55:56 -06:00
|
|
|
static void __zs_unmap_object(struct mapping_area *area,
|
|
|
|
struct page *pages[2], int off, int size)
|
2012-07-02 15:15:49 -06:00
|
|
|
{
|
|
|
|
int sizes[2];
|
|
|
|
void *addr;
|
2012-07-18 10:55:56 -06:00
|
|
|
char *buf = area->vm_buf;
|
2012-07-02 15:15:49 -06:00
|
|
|
|
2012-07-18 10:55:56 -06:00
|
|
|
/* no write fastpath */
|
|
|
|
if (area->vm_mm == ZS_MM_RO)
|
|
|
|
goto out;
|
2012-07-02 15:15:49 -06:00
|
|
|
|
|
|
|
sizes[0] = PAGE_SIZE - off;
|
|
|
|
sizes[1] = size - sizes[0];
|
|
|
|
|
|
|
|
/* copy per-cpu buffer to object */
|
|
|
|
addr = kmap_atomic(pages[0]);
|
|
|
|
memcpy(addr + off, buf, sizes[0]);
|
|
|
|
kunmap_atomic(addr);
|
|
|
|
addr = kmap_atomic(pages[1]);
|
|
|
|
memcpy(addr, buf + sizes[0], sizes[1]);
|
|
|
|
kunmap_atomic(addr);
|
2012-07-18 10:55:56 -06:00
|
|
|
|
|
|
|
out:
|
|
|
|
/* enable page faults to match kunmap_atomic() return conditions */
|
|
|
|
pagefault_enable();
|
2012-07-02 15:15:49 -06:00
|
|
|
}
|
2012-01-09 15:51:56 -07:00
|
|
|
|
2013-12-10 19:04:36 -07:00
|
|
|
#endif /* CONFIG_PGTABLE_MAPPING */
|
2012-07-18 10:55:56 -06:00
|
|
|
|
2012-01-09 15:51:56 -07:00
|
|
|
static int zs_cpu_notifier(struct notifier_block *nb, unsigned long action,
|
|
|
|
void *pcpu)
|
|
|
|
{
|
2012-07-18 10:55:56 -06:00
|
|
|
int ret, cpu = (long)pcpu;
|
2012-01-09 15:51:56 -07:00
|
|
|
struct mapping_area *area;
|
|
|
|
|
|
|
|
switch (action) {
|
|
|
|
case CPU_UP_PREPARE:
|
|
|
|
area = &per_cpu(zs_map_area, cpu);
|
2012-07-18 10:55:56 -06:00
|
|
|
ret = __zs_cpu_up(area);
|
|
|
|
if (ret)
|
|
|
|
return notifier_from_errno(ret);
|
2012-01-09 15:51:56 -07:00
|
|
|
break;
|
|
|
|
case CPU_DEAD:
|
|
|
|
case CPU_UP_CANCELED:
|
|
|
|
area = &per_cpu(zs_map_area, cpu);
|
2012-07-18 10:55:56 -06:00
|
|
|
__zs_cpu_down(area);
|
2012-01-09 15:51:56 -07:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
return NOTIFY_OK;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct notifier_block zs_cpu_nb = {
|
|
|
|
.notifier_call = zs_cpu_notifier
|
|
|
|
};
|
|
|
|
|
|
|
|
static void zs_exit(void)
|
|
|
|
{
|
|
|
|
int cpu;
|
|
|
|
|
2014-03-10 14:39:59 -06:00
|
|
|
cpu_notifier_register_begin();
|
|
|
|
|
2012-01-09 15:51:56 -07:00
|
|
|
for_each_online_cpu(cpu)
|
|
|
|
zs_cpu_notifier(NULL, CPU_DEAD, (void *)(long)cpu);
|
2014-03-10 14:39:59 -06:00
|
|
|
__unregister_cpu_notifier(&zs_cpu_nb);
|
|
|
|
|
|
|
|
cpu_notifier_register_done();
|
2012-01-09 15:51:56 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
static int zs_init(void)
|
|
|
|
{
|
|
|
|
int cpu, ret;
|
|
|
|
|
2014-03-10 14:39:59 -06:00
|
|
|
cpu_notifier_register_begin();
|
|
|
|
|
|
|
|
__register_cpu_notifier(&zs_cpu_nb);
|
2012-01-09 15:51:56 -07:00
|
|
|
for_each_online_cpu(cpu) {
|
|
|
|
ret = zs_cpu_notifier(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
|
2014-03-10 14:39:59 -06:00
|
|
|
if (notifier_to_errno(ret)) {
|
|
|
|
cpu_notifier_register_done();
|
2012-01-09 15:51:56 -07:00
|
|
|
goto fail;
|
2014-03-10 14:39:59 -06:00
|
|
|
}
|
2012-01-09 15:51:56 -07:00
|
|
|
}
|
2014-03-10 14:39:59 -06:00
|
|
|
|
|
|
|
cpu_notifier_register_done();
|
|
|
|
|
2012-01-09 15:51:56 -07:00
|
|
|
return 0;
|
|
|
|
fail:
|
|
|
|
zs_exit();
|
|
|
|
return notifier_to_errno(ret);
|
|
|
|
}
|
|
|
|
|
2013-01-04 13:14:00 -07:00
|
|
|
/**
|
|
|
|
* zs_create_pool - Creates an allocation pool to work from.
|
2013-01-30 08:36:52 -07:00
|
|
|
* @flags: allocation flags used to allocate pool metadata
|
2013-01-04 13:14:00 -07:00
|
|
|
*
|
|
|
|
* This function must be called before anything when using
|
|
|
|
* the zsmalloc allocator.
|
|
|
|
*
|
|
|
|
* On success, a pointer to the newly created pool is returned,
|
|
|
|
* otherwise NULL.
|
|
|
|
*/
|
2013-01-30 08:36:52 -07:00
|
|
|
struct zs_pool *zs_create_pool(gfp_t flags)
|
2012-01-09 15:51:56 -07:00
|
|
|
{
|
2012-06-19 19:31:11 -06:00
|
|
|
int i, ovhd_size;
|
2012-01-09 15:51:56 -07:00
|
|
|
struct zs_pool *pool;
|
|
|
|
|
|
|
|
ovhd_size = roundup(sizeof(*pool), PAGE_SIZE);
|
|
|
|
pool = kzalloc(ovhd_size, GFP_KERNEL);
|
|
|
|
if (!pool)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
for (i = 0; i < ZS_SIZE_CLASSES; i++) {
|
|
|
|
int size;
|
|
|
|
struct size_class *class;
|
|
|
|
|
|
|
|
size = ZS_MIN_ALLOC_SIZE + i * ZS_SIZE_CLASS_DELTA;
|
|
|
|
if (size > ZS_MAX_ALLOC_SIZE)
|
|
|
|
size = ZS_MAX_ALLOC_SIZE;
|
|
|
|
|
|
|
|
class = &pool->size_class[i];
|
|
|
|
class->size = size;
|
|
|
|
class->index = i;
|
|
|
|
spin_lock_init(&class->lock);
|
2012-05-03 00:40:39 -06:00
|
|
|
class->pages_per_zspage = get_pages_per_zspage(size);
|
2012-01-09 15:51:56 -07:00
|
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
pool->flags = flags;
|
|
|
|
|
|
|
|
return pool;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(zs_create_pool);
|
|
|
|
|
|
|
|
void zs_destroy_pool(struct zs_pool *pool)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for (i = 0; i < ZS_SIZE_CLASSES; i++) {
|
|
|
|
int fg;
|
|
|
|
struct size_class *class = &pool->size_class[i];
|
|
|
|
|
|
|
|
for (fg = 0; fg < _ZS_NR_FULLNESS_GROUPS; fg++) {
|
|
|
|
if (class->fullness_list[fg]) {
|
2013-05-15 14:56:49 -06:00
|
|
|
pr_info("Freeing non-empty class with size %db, fullness group %d\n",
|
2012-01-09 15:51:56 -07:00
|
|
|
class->size, fg);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
kfree(pool);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(zs_destroy_pool);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* zs_malloc - Allocate block of given size from pool.
|
|
|
|
* @pool: pool to allocate from
|
|
|
|
* @size: size of block to allocate
|
|
|
|
*
|
2012-05-03 00:40:40 -06:00
|
|
|
* On success, handle to the allocated object is returned,
|
2012-06-08 00:39:25 -06:00
|
|
|
* otherwise 0.
|
2012-01-09 15:51:56 -07:00
|
|
|
* Allocation requests with size > ZS_MAX_ALLOC_SIZE will fail.
|
|
|
|
*/
|
2012-06-08 00:39:25 -06:00
|
|
|
unsigned long zs_malloc(struct zs_pool *pool, size_t size)
|
2012-01-09 15:51:56 -07:00
|
|
|
{
|
2012-06-08 00:39:25 -06:00
|
|
|
unsigned long obj;
|
2012-01-09 15:51:56 -07:00
|
|
|
struct link_free *link;
|
|
|
|
int class_idx;
|
|
|
|
struct size_class *class;
|
|
|
|
|
|
|
|
struct page *first_page, *m_page;
|
|
|
|
unsigned long m_objidx, m_offset;
|
|
|
|
|
|
|
|
if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE))
|
2012-06-08 00:39:25 -06:00
|
|
|
return 0;
|
2012-01-09 15:51:56 -07:00
|
|
|
|
|
|
|
class_idx = get_size_class_index(size);
|
|
|
|
class = &pool->size_class[class_idx];
|
|
|
|
BUG_ON(class_idx != class->index);
|
|
|
|
|
|
|
|
spin_lock(&class->lock);
|
|
|
|
first_page = find_get_zspage(class);
|
|
|
|
|
|
|
|
if (!first_page) {
|
|
|
|
spin_unlock(&class->lock);
|
|
|
|
first_page = alloc_zspage(class, pool->flags);
|
|
|
|
if (unlikely(!first_page))
|
2012-06-08 00:39:25 -06:00
|
|
|
return 0;
|
2012-01-09 15:51:56 -07:00
|
|
|
|
|
|
|
set_zspage_mapping(first_page, class->index, ZS_EMPTY);
|
|
|
|
spin_lock(&class->lock);
|
2012-05-03 00:40:39 -06:00
|
|
|
class->pages_allocated += class->pages_per_zspage;
|
2012-01-09 15:51:56 -07:00
|
|
|
}
|
|
|
|
|
2012-06-08 00:39:25 -06:00
|
|
|
obj = (unsigned long)first_page->freelist;
|
2012-01-09 15:51:56 -07:00
|
|
|
obj_handle_to_location(obj, &m_page, &m_objidx);
|
|
|
|
m_offset = obj_idx_to_offset(m_page, m_objidx, class->size);
|
|
|
|
|
|
|
|
link = (struct link_free *)kmap_atomic(m_page) +
|
|
|
|
m_offset / sizeof(*link);
|
|
|
|
first_page->freelist = link->next;
|
|
|
|
memset(link, POISON_INUSE, sizeof(*link));
|
|
|
|
kunmap_atomic(link);
|
|
|
|
|
|
|
|
first_page->inuse++;
|
|
|
|
/* Now move the zspage to another fullness group, if required */
|
|
|
|
fix_fullness_group(pool, first_page);
|
|
|
|
spin_unlock(&class->lock);
|
|
|
|
|
|
|
|
return obj;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(zs_malloc);
|
|
|
|
|
2012-06-08 00:39:25 -06:00
|
|
|
void zs_free(struct zs_pool *pool, unsigned long obj)
|
2012-01-09 15:51:56 -07:00
|
|
|
{
|
|
|
|
struct link_free *link;
|
|
|
|
struct page *first_page, *f_page;
|
|
|
|
unsigned long f_objidx, f_offset;
|
|
|
|
|
|
|
|
int class_idx;
|
|
|
|
struct size_class *class;
|
|
|
|
enum fullness_group fullness;
|
|
|
|
|
|
|
|
if (unlikely(!obj))
|
|
|
|
return;
|
|
|
|
|
|
|
|
obj_handle_to_location(obj, &f_page, &f_objidx);
|
|
|
|
first_page = get_first_page(f_page);
|
|
|
|
|
|
|
|
get_zspage_mapping(first_page, &class_idx, &fullness);
|
|
|
|
class = &pool->size_class[class_idx];
|
|
|
|
f_offset = obj_idx_to_offset(f_page, f_objidx, class->size);
|
|
|
|
|
|
|
|
spin_lock(&class->lock);
|
|
|
|
|
|
|
|
/* Insert this object in containing zspage's freelist */
|
|
|
|
link = (struct link_free *)((unsigned char *)kmap_atomic(f_page)
|
|
|
|
+ f_offset);
|
|
|
|
link->next = first_page->freelist;
|
|
|
|
kunmap_atomic(link);
|
2012-06-08 00:39:25 -06:00
|
|
|
first_page->freelist = (void *)obj;
|
2012-01-09 15:51:56 -07:00
|
|
|
|
|
|
|
first_page->inuse--;
|
|
|
|
fullness = fix_fullness_group(pool, first_page);
|
|
|
|
|
|
|
|
if (fullness == ZS_EMPTY)
|
2012-05-03 00:40:39 -06:00
|
|
|
class->pages_allocated -= class->pages_per_zspage;
|
2012-01-09 15:51:56 -07:00
|
|
|
|
|
|
|
spin_unlock(&class->lock);
|
|
|
|
|
|
|
|
if (fullness == ZS_EMPTY)
|
|
|
|
free_zspage(first_page);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(zs_free);
|
|
|
|
|
2012-05-03 00:40:40 -06:00
|
|
|
/**
|
|
|
|
* zs_map_object - get address of allocated object from handle.
|
|
|
|
* @pool: pool from which the object was allocated
|
|
|
|
* @handle: handle returned from zs_malloc
|
|
|
|
*
|
|
|
|
* Before using an object allocated from zs_malloc, it must be mapped using
|
|
|
|
* this function. When done with the object, it must be unmapped using
|
2012-07-02 15:15:51 -06:00
|
|
|
* zs_unmap_object.
|
|
|
|
*
|
|
|
|
* Only one object can be mapped per cpu at a time. There is no protection
|
|
|
|
* against nested mappings.
|
|
|
|
*
|
|
|
|
* This function returns with preemption and page faults disabled.
|
2013-05-20 13:18:14 -06:00
|
|
|
*/
|
2012-07-02 15:15:52 -06:00
|
|
|
void *zs_map_object(struct zs_pool *pool, unsigned long handle,
|
|
|
|
enum zs_mapmode mm)
|
2012-01-09 15:51:56 -07:00
|
|
|
{
|
|
|
|
struct page *page;
|
|
|
|
unsigned long obj_idx, off;
|
|
|
|
|
|
|
|
unsigned int class_idx;
|
|
|
|
enum fullness_group fg;
|
|
|
|
struct size_class *class;
|
|
|
|
struct mapping_area *area;
|
2012-07-18 10:55:56 -06:00
|
|
|
struct page *pages[2];
|
2012-01-09 15:51:56 -07:00
|
|
|
|
|
|
|
BUG_ON(!handle);
|
|
|
|
|
2012-07-18 10:55:55 -06:00
|
|
|
/*
|
|
|
|
* Because we use per-cpu mapping areas shared among the
|
|
|
|
* pools/users, we can't allow mapping in interrupt context
|
|
|
|
* because it can corrupt another users mappings.
|
|
|
|
*/
|
|
|
|
BUG_ON(in_interrupt());
|
|
|
|
|
2012-01-09 15:51:56 -07:00
|
|
|
obj_handle_to_location(handle, &page, &obj_idx);
|
|
|
|
get_zspage_mapping(get_first_page(page), &class_idx, &fg);
|
|
|
|
class = &pool->size_class[class_idx];
|
|
|
|
off = obj_idx_to_offset(page, obj_idx, class->size);
|
|
|
|
|
|
|
|
area = &get_cpu_var(zs_map_area);
|
2012-07-18 10:55:56 -06:00
|
|
|
area->vm_mm = mm;
|
2012-01-09 15:51:56 -07:00
|
|
|
if (off + class->size <= PAGE_SIZE) {
|
|
|
|
/* this object is contained entirely within a page */
|
|
|
|
area->vm_addr = kmap_atomic(page);
|
2012-07-02 15:15:49 -06:00
|
|
|
return area->vm_addr + off;
|
2012-01-09 15:51:56 -07:00
|
|
|
}
|
|
|
|
|
2012-07-18 10:55:56 -06:00
|
|
|
/* this object spans two pages */
|
|
|
|
pages[0] = page;
|
|
|
|
pages[1] = get_next_page(page);
|
|
|
|
BUG_ON(!pages[1]);
|
2012-07-02 15:15:52 -06:00
|
|
|
|
2012-07-18 10:55:56 -06:00
|
|
|
return __zs_map_object(area, pages, off, class->size);
|
2012-01-09 15:51:56 -07:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(zs_map_object);
|
|
|
|
|
2012-06-08 00:39:25 -06:00
|
|
|
void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
|
2012-01-09 15:51:56 -07:00
|
|
|
{
|
|
|
|
struct page *page;
|
|
|
|
unsigned long obj_idx, off;
|
|
|
|
|
|
|
|
unsigned int class_idx;
|
|
|
|
enum fullness_group fg;
|
|
|
|
struct size_class *class;
|
|
|
|
struct mapping_area *area;
|
|
|
|
|
|
|
|
BUG_ON(!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];
|
|
|
|
off = obj_idx_to_offset(page, obj_idx, class->size);
|
|
|
|
|
2012-07-18 10:55:56 -06:00
|
|
|
area = &__get_cpu_var(zs_map_area);
|
|
|
|
if (off + class->size <= PAGE_SIZE)
|
|
|
|
kunmap_atomic(area->vm_addr);
|
|
|
|
else {
|
|
|
|
struct page *pages[2];
|
|
|
|
|
|
|
|
pages[0] = page;
|
|
|
|
pages[1] = get_next_page(page);
|
|
|
|
BUG_ON(!pages[1]);
|
2012-07-02 15:15:52 -06:00
|
|
|
|
2012-07-18 10:55:56 -06:00
|
|
|
__zs_unmap_object(area, pages, off, class->size);
|
|
|
|
}
|
2012-01-09 15:51:56 -07:00
|
|
|
put_cpu_var(zs_map_area);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(zs_unmap_object);
|
|
|
|
|
|
|
|
u64 zs_get_total_size_bytes(struct zs_pool *pool)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
u64 npages = 0;
|
|
|
|
|
|
|
|
for (i = 0; i < ZS_SIZE_CLASSES; i++)
|
|
|
|
npages += pool->size_class[i].pages_allocated;
|
|
|
|
|
|
|
|
return npages << PAGE_SHIFT;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(zs_get_total_size_bytes);
|
2012-06-19 19:31:11 -06:00
|
|
|
|
|
|
|
module_init(zs_init);
|
|
|
|
module_exit(zs_exit);
|
|
|
|
|
|
|
|
MODULE_LICENSE("Dual BSD/GPL");
|
|
|
|
MODULE_AUTHOR("Nitin Gupta <ngupta@vflare.org>");
|