* [PATCH 1/4] drivers: staging: drop zram and zsmalloc
2013-08-18 8:40 [PATCH 0/4] mm: merge zram into zswap Bob Liu
@ 2013-08-18 8:40 ` Bob Liu
2013-08-18 8:40 ` [PATCH 2/4] mm: promote zsmalloc to mm/ Bob Liu
` (3 subsequent siblings)
4 siblings, 0 replies; 11+ messages in thread
From: Bob Liu @ 2013-08-18 8:40 UTC (permalink / raw)
To: linux-mm
Cc: linux-kernel, eternaleye, minchan, mgorman, gregkh, akpm, axboe,
sjenning, ngupta, semenzato, penberg, sonnyrao, smbarber,
konrad.wilk, riel, kmpark, Bob Liu
Zswap will be used to replace zram.
Signed-off-by: Bob Liu <bob.liu@oracle.com>
---
drivers/staging/Kconfig | 4 -
drivers/staging/Makefile | 2 -
drivers/staging/zram/Kconfig | 25 -
drivers/staging/zram/Makefile | 3 -
drivers/staging/zram/zram.txt | 77 ---
drivers/staging/zram/zram_drv.c | 925 --------------------------
drivers/staging/zram/zram_drv.h | 115 ----
drivers/staging/zsmalloc/Kconfig | 10 -
drivers/staging/zsmalloc/Makefile | 3 -
drivers/staging/zsmalloc/zsmalloc-main.c | 1063 ------------------------------
drivers/staging/zsmalloc/zsmalloc.h | 43 --
11 files changed, 2270 deletions(-)
delete mode 100644 drivers/staging/zram/Kconfig
delete mode 100644 drivers/staging/zram/Makefile
delete mode 100644 drivers/staging/zram/zram.txt
delete mode 100644 drivers/staging/zram/zram_drv.c
delete mode 100644 drivers/staging/zram/zram_drv.h
delete mode 100644 drivers/staging/zsmalloc/Kconfig
delete mode 100644 drivers/staging/zsmalloc/Makefile
delete mode 100644 drivers/staging/zsmalloc/zsmalloc-main.c
delete mode 100644 drivers/staging/zsmalloc/zsmalloc.h
diff --git a/drivers/staging/Kconfig b/drivers/staging/Kconfig
index 57d8b34..d5355f4 100644
--- a/drivers/staging/Kconfig
+++ b/drivers/staging/Kconfig
@@ -74,10 +74,6 @@ source "drivers/staging/sep/Kconfig"
source "drivers/staging/iio/Kconfig"
-source "drivers/staging/zsmalloc/Kconfig"
-
-source "drivers/staging/zram/Kconfig"
-
source "drivers/staging/wlags49_h2/Kconfig"
source "drivers/staging/wlags49_h25/Kconfig"
diff --git a/drivers/staging/Makefile b/drivers/staging/Makefile
index 429321f..17a828f 100644
--- a/drivers/staging/Makefile
+++ b/drivers/staging/Makefile
@@ -31,8 +31,6 @@ obj-$(CONFIG_VT6656) += vt6656/
obj-$(CONFIG_VME_BUS) += vme/
obj-$(CONFIG_DX_SEP) += sep/
obj-$(CONFIG_IIO) += iio/
-obj-$(CONFIG_ZRAM) += zram/
-obj-$(CONFIG_ZSMALLOC) += zsmalloc/
obj-$(CONFIG_WLAGS49_H2) += wlags49_h2/
obj-$(CONFIG_WLAGS49_H25) += wlags49_h25/
obj-$(CONFIG_FB_SM7XX) += sm7xxfb/
diff --git a/drivers/staging/zram/Kconfig b/drivers/staging/zram/Kconfig
deleted file mode 100644
index 983314c..0000000
--- a/drivers/staging/zram/Kconfig
+++ /dev/null
@@ -1,25 +0,0 @@
-config ZRAM
- tristate "Compressed RAM block device support"
- depends on BLOCK && SYSFS && ZSMALLOC
- select LZO_COMPRESS
- select LZO_DECOMPRESS
- default n
- help
- Creates virtual block devices called /dev/zramX (X = 0, 1, ...).
- Pages written to these disks are compressed and stored in memory
- itself. These disks allow very fast I/O and compression provides
- good amounts of memory savings.
-
- It has several use cases, for example: /tmp storage, use as swap
- disks and maybe many more.
-
- See zram.txt for more information.
- Project home: <https://compcache.googlecode.com/>
-
-config ZRAM_DEBUG
- bool "Compressed RAM block device debug support"
- depends on ZRAM
- default n
- help
- This option adds additional debugging code to the compressed
- RAM block device driver.
diff --git a/drivers/staging/zram/Makefile b/drivers/staging/zram/Makefile
deleted file mode 100644
index cb0f9ce..0000000
--- a/drivers/staging/zram/Makefile
+++ /dev/null
@@ -1,3 +0,0 @@
-zram-y := zram_drv.o
-
-obj-$(CONFIG_ZRAM) += zram.o
diff --git a/drivers/staging/zram/zram.txt b/drivers/staging/zram/zram.txt
deleted file mode 100644
index 765d790..0000000
--- a/drivers/staging/zram/zram.txt
+++ /dev/null
@@ -1,77 +0,0 @@
-zram: Compressed RAM based block devices
-----------------------------------------
-
-Project home: http://compcache.googlecode.com/
-
-* Introduction
-
-The zram module creates RAM based block devices named /dev/zram<id>
-(<id> = 0, 1, ...). Pages written to these disks are compressed and stored
-in memory itself. These disks allow very fast I/O and compression provides
-good amounts of memory savings. Some of the usecases include /tmp storage,
-use as swap disks, various caches under /var and maybe many more :)
-
-Statistics for individual zram devices are exported through sysfs nodes at
-/sys/block/zram<id>/
-
-* Usage
-
-Following shows a typical sequence of steps for using zram.
-
-1) Load Module:
- modprobe zram num_devices=4
- This creates 4 devices: /dev/zram{0,1,2,3}
- (num_devices parameter is optional. Default: 1)
-
-2) Set Disksize
- Set disk size by writing the value to sysfs node 'disksize'.
- The value can be either in bytes or you can use mem suffixes.
- Examples:
- # Initialize /dev/zram0 with 50MB disksize
- echo $((50*1024*1024)) > /sys/block/zram0/disksize
-
- # Using mem suffixes
- echo 256K > /sys/block/zram0/disksize
- echo 512M > /sys/block/zram0/disksize
- echo 1G > /sys/block/zram0/disksize
-
-3) Activate:
- mkswap /dev/zram0
- swapon /dev/zram0
-
- mkfs.ext4 /dev/zram1
- mount /dev/zram1 /tmp
-
-4) Stats:
- Per-device statistics are exported as various nodes under
- /sys/block/zram<id>/
- disksize
- num_reads
- num_writes
- invalid_io
- notify_free
- discard
- zero_pages
- orig_data_size
- compr_data_size
- mem_used_total
-
-5) Deactivate:
- swapoff /dev/zram0
- umount /dev/zram1
-
-6) Reset:
- Write any positive value to 'reset' sysfs node
- echo 1 > /sys/block/zram0/reset
- echo 1 > /sys/block/zram1/reset
-
- This frees all the memory allocated for the given device and
- resets the disksize to zero. You must set the disksize again
- before reusing the device.
-
-Please report any problems at:
- - Mailing list: linux-mm-cc at laptop dot org
- - Issue tracker: http://code.google.com/p/compcache/issues/list
-
-Nitin Gupta
-ngupta@vflare.org
diff --git a/drivers/staging/zram/zram_drv.c b/drivers/staging/zram/zram_drv.c
deleted file mode 100644
index e77fb6e..0000000
--- a/drivers/staging/zram/zram_drv.c
+++ /dev/null
@@ -1,925 +0,0 @@
-/*
- * Compressed RAM block device
- *
- * Copyright (C) 2008, 2009, 2010 Nitin Gupta
- *
- * This code is released using a dual license strategy: BSD/GPL
- * You can choose the licence 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
- *
- * Project home: http://compcache.googlecode.com
- */
-
-#define KMSG_COMPONENT "zram"
-#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
-
-#ifdef CONFIG_ZRAM_DEBUG
-#define DEBUG
-#endif
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/bio.h>
-#include <linux/bitops.h>
-#include <linux/blkdev.h>
-#include <linux/buffer_head.h>
-#include <linux/device.h>
-#include <linux/genhd.h>
-#include <linux/highmem.h>
-#include <linux/slab.h>
-#include <linux/lzo.h>
-#include <linux/string.h>
-#include <linux/vmalloc.h>
-
-#include "zram_drv.h"
-
-/* Globals */
-static int zram_major;
-static struct zram *zram_devices;
-
-/* Module params (documentation at end) */
-static unsigned int num_devices = 1;
-
-static inline struct zram *dev_to_zram(struct device *dev)
-{
- return (struct zram *)dev_to_disk(dev)->private_data;
-}
-
-static ssize_t disksize_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%llu\n", zram->disksize);
-}
-
-static ssize_t initstate_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%u\n", zram->init_done);
-}
-
-static ssize_t num_reads_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%llu\n",
- (u64)atomic64_read(&zram->stats.num_reads));
-}
-
-static ssize_t num_writes_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%llu\n",
- (u64)atomic64_read(&zram->stats.num_writes));
-}
-
-static ssize_t invalid_io_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%llu\n",
- (u64)atomic64_read(&zram->stats.invalid_io));
-}
-
-static ssize_t notify_free_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%llu\n",
- (u64)atomic64_read(&zram->stats.notify_free));
-}
-
-static ssize_t zero_pages_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%u\n", zram->stats.pages_zero);
-}
-
-static ssize_t orig_data_size_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%llu\n",
- (u64)(zram->stats.pages_stored) << PAGE_SHIFT);
-}
-
-static ssize_t compr_data_size_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%llu\n",
- (u64)atomic64_read(&zram->stats.compr_size));
-}
-
-static ssize_t mem_used_total_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- u64 val = 0;
- struct zram *zram = dev_to_zram(dev);
- struct zram_meta *meta = zram->meta;
-
- down_read(&zram->init_lock);
- if (zram->init_done)
- val = zs_get_total_size_bytes(meta->mem_pool);
- up_read(&zram->init_lock);
-
- return sprintf(buf, "%llu\n", val);
-}
-
-static int zram_test_flag(struct zram_meta *meta, u32 index,
- enum zram_pageflags flag)
-{
- return meta->table[index].flags & BIT(flag);
-}
-
-static void zram_set_flag(struct zram_meta *meta, u32 index,
- enum zram_pageflags flag)
-{
- meta->table[index].flags |= BIT(flag);
-}
-
-static void zram_clear_flag(struct zram_meta *meta, u32 index,
- enum zram_pageflags flag)
-{
- meta->table[index].flags &= ~BIT(flag);
-}
-
-static inline int is_partial_io(struct bio_vec *bvec)
-{
- return bvec->bv_len != PAGE_SIZE;
-}
-
-/*
- * Check if request is within bounds and aligned on zram logical blocks.
- */
-static inline int valid_io_request(struct zram *zram, struct bio *bio)
-{
- u64 start, end, bound;
-
- /* unaligned request */
- if (unlikely(bio->bi_sector & (ZRAM_SECTOR_PER_LOGICAL_BLOCK - 1)))
- return 0;
- if (unlikely(bio->bi_size & (ZRAM_LOGICAL_BLOCK_SIZE - 1)))
- return 0;
-
- start = bio->bi_sector;
- end = start + (bio->bi_size >> SECTOR_SHIFT);
- bound = zram->disksize >> SECTOR_SHIFT;
- /* out of range range */
- if (unlikely(start >= bound || end > bound || start > end))
- return 0;
-
- /* I/O request is valid */
- return 1;
-}
-
-static void zram_meta_free(struct zram_meta *meta)
-{
- zs_destroy_pool(meta->mem_pool);
- kfree(meta->compress_workmem);
- free_pages((unsigned long)meta->compress_buffer, 1);
- vfree(meta->table);
- kfree(meta);
-}
-
-static struct zram_meta *zram_meta_alloc(u64 disksize)
-{
- size_t num_pages;
- struct zram_meta *meta = kmalloc(sizeof(*meta), GFP_KERNEL);
- if (!meta)
- goto out;
-
- meta->compress_workmem = kzalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL);
- if (!meta->compress_workmem)
- goto free_meta;
-
- meta->compress_buffer =
- (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1);
- if (!meta->compress_buffer) {
- pr_err("Error allocating compressor buffer space\n");
- goto free_workmem;
- }
-
- num_pages = disksize >> PAGE_SHIFT;
- meta->table = vzalloc(num_pages * sizeof(*meta->table));
- if (!meta->table) {
- pr_err("Error allocating zram address table\n");
- goto free_buffer;
- }
-
- meta->mem_pool = zs_create_pool(GFP_NOIO | __GFP_HIGHMEM);
- if (!meta->mem_pool) {
- pr_err("Error creating memory pool\n");
- goto free_table;
- }
-
- return meta;
-
-free_table:
- vfree(meta->table);
-free_buffer:
- free_pages((unsigned long)meta->compress_buffer, 1);
-free_workmem:
- kfree(meta->compress_workmem);
-free_meta:
- kfree(meta);
- meta = NULL;
-out:
- return meta;
-}
-
-static void update_position(u32 *index, int *offset, struct bio_vec *bvec)
-{
- if (*offset + bvec->bv_len >= PAGE_SIZE)
- (*index)++;
- *offset = (*offset + bvec->bv_len) % PAGE_SIZE;
-}
-
-static int page_zero_filled(void *ptr)
-{
- unsigned int pos;
- unsigned long *page;
-
- page = (unsigned long *)ptr;
-
- for (pos = 0; pos != PAGE_SIZE / sizeof(*page); pos++) {
- if (page[pos])
- return 0;
- }
-
- return 1;
-}
-
-static void handle_zero_page(struct bio_vec *bvec)
-{
- struct page *page = bvec->bv_page;
- void *user_mem;
-
- user_mem = kmap_atomic(page);
- if (is_partial_io(bvec))
- memset(user_mem + bvec->bv_offset, 0, bvec->bv_len);
- else
- clear_page(user_mem);
- kunmap_atomic(user_mem);
-
- flush_dcache_page(page);
-}
-
-static void zram_free_page(struct zram *zram, size_t index)
-{
- struct zram_meta *meta = zram->meta;
- unsigned long handle = meta->table[index].handle;
- u16 size = meta->table[index].size;
-
- if (unlikely(!handle)) {
- /*
- * No memory is allocated for zero filled pages.
- * Simply clear zero page flag.
- */
- if (zram_test_flag(meta, index, ZRAM_ZERO)) {
- zram_clear_flag(meta, index, ZRAM_ZERO);
- zram->stats.pages_zero--;
- }
- return;
- }
-
- if (unlikely(size > max_zpage_size))
- zram->stats.bad_compress--;
-
- zs_free(meta->mem_pool, handle);
-
- if (size <= PAGE_SIZE / 2)
- zram->stats.good_compress--;
-
- atomic64_sub(meta->table[index].size, &zram->stats.compr_size);
- zram->stats.pages_stored--;
-
- meta->table[index].handle = 0;
- meta->table[index].size = 0;
-}
-
-static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
-{
- int ret = LZO_E_OK;
- size_t clen = PAGE_SIZE;
- unsigned char *cmem;
- struct zram_meta *meta = zram->meta;
- unsigned long handle = meta->table[index].handle;
-
- if (!handle || zram_test_flag(meta, index, ZRAM_ZERO)) {
- clear_page(mem);
- return 0;
- }
-
- cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_RO);
- if (meta->table[index].size == PAGE_SIZE)
- copy_page(mem, cmem);
- else
- ret = lzo1x_decompress_safe(cmem, meta->table[index].size,
- mem, &clen);
- zs_unmap_object(meta->mem_pool, handle);
-
- /* Should NEVER happen. Return bio error if it does. */
- if (unlikely(ret != LZO_E_OK)) {
- pr_err("Decompression failed! err=%d, page=%u\n", ret, index);
- atomic64_inc(&zram->stats.failed_reads);
- return ret;
- }
-
- return 0;
-}
-
-static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
- u32 index, int offset, struct bio *bio)
-{
- int ret;
- struct page *page;
- unsigned char *user_mem, *uncmem = NULL;
- struct zram_meta *meta = zram->meta;
- page = bvec->bv_page;
-
- if (unlikely(!meta->table[index].handle) ||
- zram_test_flag(meta, index, ZRAM_ZERO)) {
- handle_zero_page(bvec);
- return 0;
- }
-
- if (is_partial_io(bvec))
- /* Use a temporary buffer to decompress the page */
- uncmem = kmalloc(PAGE_SIZE, GFP_NOIO);
-
- user_mem = kmap_atomic(page);
- if (!is_partial_io(bvec))
- uncmem = user_mem;
-
- if (!uncmem) {
- pr_info("Unable to allocate temp memory\n");
- ret = -ENOMEM;
- goto out_cleanup;
- }
-
- ret = zram_decompress_page(zram, uncmem, index);
- /* Should NEVER happen. Return bio error if it does. */
- if (unlikely(ret != LZO_E_OK))
- goto out_cleanup;
-
- if (is_partial_io(bvec))
- memcpy(user_mem + bvec->bv_offset, uncmem + offset,
- bvec->bv_len);
-
- flush_dcache_page(page);
- ret = 0;
-out_cleanup:
- kunmap_atomic(user_mem);
- if (is_partial_io(bvec))
- kfree(uncmem);
- return ret;
-}
-
-static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
- int offset)
-{
- int ret = 0;
- size_t clen;
- unsigned long handle;
- struct page *page;
- unsigned char *user_mem, *cmem, *src, *uncmem = NULL;
- struct zram_meta *meta = zram->meta;
-
- page = bvec->bv_page;
- src = meta->compress_buffer;
-
- if (is_partial_io(bvec)) {
- /*
- * This is a partial IO. We need to read the full page
- * before to write the changes.
- */
- uncmem = kmalloc(PAGE_SIZE, GFP_NOIO);
- if (!uncmem) {
- ret = -ENOMEM;
- goto out;
- }
- ret = zram_decompress_page(zram, uncmem, index);
- if (ret)
- goto out;
- }
-
- /*
- * System overwrites unused sectors. Free memory associated
- * with this sector now.
- */
- if (meta->table[index].handle ||
- zram_test_flag(meta, index, ZRAM_ZERO))
- zram_free_page(zram, index);
-
- user_mem = kmap_atomic(page);
-
- if (is_partial_io(bvec)) {
- memcpy(uncmem + offset, user_mem + bvec->bv_offset,
- bvec->bv_len);
- kunmap_atomic(user_mem);
- user_mem = NULL;
- } else {
- uncmem = user_mem;
- }
-
- if (page_zero_filled(uncmem)) {
- kunmap_atomic(user_mem);
- zram->stats.pages_zero++;
- zram_set_flag(meta, index, ZRAM_ZERO);
- ret = 0;
- goto out;
- }
-
- ret = lzo1x_1_compress(uncmem, PAGE_SIZE, src, &clen,
- meta->compress_workmem);
-
- if (!is_partial_io(bvec)) {
- kunmap_atomic(user_mem);
- user_mem = NULL;
- uncmem = NULL;
- }
-
- if (unlikely(ret != LZO_E_OK)) {
- pr_err("Compression failed! err=%d\n", ret);
- goto out;
- }
-
- if (unlikely(clen > max_zpage_size)) {
- zram->stats.bad_compress++;
- clen = PAGE_SIZE;
- src = NULL;
- if (is_partial_io(bvec))
- src = uncmem;
- }
-
- handle = zs_malloc(meta->mem_pool, clen);
- if (!handle) {
- pr_info("Error allocating memory for compressed page: %u, size=%zu\n",
- index, clen);
- ret = -ENOMEM;
- goto out;
- }
- cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_WO);
-
- if ((clen == PAGE_SIZE) && !is_partial_io(bvec)) {
- src = kmap_atomic(page);
- copy_page(cmem, src);
- kunmap_atomic(src);
- } else {
- memcpy(cmem, src, clen);
- }
-
- zs_unmap_object(meta->mem_pool, handle);
-
- meta->table[index].handle = handle;
- meta->table[index].size = clen;
-
- /* Update stats */
- atomic64_add(clen, &zram->stats.compr_size);
- zram->stats.pages_stored++;
- if (clen <= PAGE_SIZE / 2)
- zram->stats.good_compress++;
-
-out:
- if (is_partial_io(bvec))
- kfree(uncmem);
-
- if (ret)
- atomic64_inc(&zram->stats.failed_writes);
- return ret;
-}
-
-static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
- int offset, struct bio *bio, int rw)
-{
- int ret;
-
- if (rw == READ) {
- down_read(&zram->lock);
- ret = zram_bvec_read(zram, bvec, index, offset, bio);
- up_read(&zram->lock);
- } else {
- down_write(&zram->lock);
- ret = zram_bvec_write(zram, bvec, index, offset);
- up_write(&zram->lock);
- }
-
- return ret;
-}
-
-static void zram_reset_device(struct zram *zram)
-{
- size_t index;
- struct zram_meta *meta;
-
- down_write(&zram->init_lock);
- if (!zram->init_done) {
- up_write(&zram->init_lock);
- return;
- }
-
- meta = zram->meta;
- zram->init_done = 0;
-
- /* Free all pages that are still in this zram device */
- for (index = 0; index < zram->disksize >> PAGE_SHIFT; index++) {
- unsigned long handle = meta->table[index].handle;
- if (!handle)
- continue;
-
- zs_free(meta->mem_pool, handle);
- }
-
- zram_meta_free(zram->meta);
- zram->meta = NULL;
- /* Reset stats */
- memset(&zram->stats, 0, sizeof(zram->stats));
-
- zram->disksize = 0;
- set_capacity(zram->disk, 0);
- up_write(&zram->init_lock);
-}
-
-static void zram_init_device(struct zram *zram, struct zram_meta *meta)
-{
- if (zram->disksize > 2 * (totalram_pages << PAGE_SHIFT)) {
- pr_info(
- "There is little point creating a zram of greater than "
- "twice the size of memory since we expect a 2:1 compression "
- "ratio. Note that zram uses about 0.1%% of the size of "
- "the disk when not in use so a huge zram is "
- "wasteful.\n"
- "\tMemory Size: %lu kB\n"
- "\tSize you selected: %llu kB\n"
- "Continuing anyway ...\n",
- (totalram_pages << PAGE_SHIFT) >> 10, zram->disksize >> 10
- );
- }
-
- /* zram devices sort of resembles non-rotational disks */
- queue_flag_set_unlocked(QUEUE_FLAG_NONROT, zram->disk->queue);
-
- zram->meta = meta;
- zram->init_done = 1;
-
- pr_debug("Initialization done!\n");
-}
-
-static ssize_t disksize_store(struct device *dev,
- struct device_attribute *attr, const char *buf, size_t len)
-{
- u64 disksize;
- struct zram_meta *meta;
- struct zram *zram = dev_to_zram(dev);
-
- disksize = memparse(buf, NULL);
- if (!disksize)
- return -EINVAL;
-
- disksize = PAGE_ALIGN(disksize);
- meta = zram_meta_alloc(disksize);
- down_write(&zram->init_lock);
- if (zram->init_done) {
- up_write(&zram->init_lock);
- zram_meta_free(meta);
- pr_info("Cannot change disksize for initialized device\n");
- return -EBUSY;
- }
-
- zram->disksize = disksize;
- set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT);
- zram_init_device(zram, meta);
- up_write(&zram->init_lock);
-
- return len;
-}
-
-static ssize_t reset_store(struct device *dev,
- struct device_attribute *attr, const char *buf, size_t len)
-{
- int ret;
- unsigned short do_reset;
- struct zram *zram;
- struct block_device *bdev;
-
- zram = dev_to_zram(dev);
- bdev = bdget_disk(zram->disk, 0);
-
- /* Do not reset an active device! */
- if (bdev->bd_holders)
- return -EBUSY;
-
- ret = kstrtou16(buf, 10, &do_reset);
- if (ret)
- return ret;
-
- if (!do_reset)
- return -EINVAL;
-
- /* Make sure all pending I/O is finished */
- if (bdev)
- fsync_bdev(bdev);
-
- zram_reset_device(zram);
- return len;
-}
-
-static void __zram_make_request(struct zram *zram, struct bio *bio, int rw)
-{
- int i, offset;
- u32 index;
- struct bio_vec *bvec;
-
- switch (rw) {
- case READ:
- atomic64_inc(&zram->stats.num_reads);
- break;
- case WRITE:
- atomic64_inc(&zram->stats.num_writes);
- break;
- }
-
- index = bio->bi_sector >> SECTORS_PER_PAGE_SHIFT;
- offset = (bio->bi_sector & (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT;
-
- bio_for_each_segment(bvec, bio, i) {
- int max_transfer_size = PAGE_SIZE - offset;
-
- if (bvec->bv_len > max_transfer_size) {
- /*
- * zram_bvec_rw() can only make operation on a single
- * zram page. Split the bio vector.
- */
- struct bio_vec bv;
-
- bv.bv_page = bvec->bv_page;
- bv.bv_len = max_transfer_size;
- bv.bv_offset = bvec->bv_offset;
-
- if (zram_bvec_rw(zram, &bv, index, offset, bio, rw) < 0)
- goto out;
-
- bv.bv_len = bvec->bv_len - max_transfer_size;
- bv.bv_offset += max_transfer_size;
- if (zram_bvec_rw(zram, &bv, index+1, 0, bio, rw) < 0)
- goto out;
- } else
- if (zram_bvec_rw(zram, bvec, index, offset, bio, rw)
- < 0)
- goto out;
-
- update_position(&index, &offset, bvec);
- }
-
- set_bit(BIO_UPTODATE, &bio->bi_flags);
- bio_endio(bio, 0);
- return;
-
-out:
- bio_io_error(bio);
-}
-
-/*
- * Handler function for all zram I/O requests.
- */
-static void zram_make_request(struct request_queue *queue, struct bio *bio)
-{
- struct zram *zram = queue->queuedata;
-
- down_read(&zram->init_lock);
- if (unlikely(!zram->init_done))
- goto error;
-
- if (!valid_io_request(zram, bio)) {
- atomic64_inc(&zram->stats.invalid_io);
- goto error;
- }
-
- __zram_make_request(zram, bio, bio_data_dir(bio));
- up_read(&zram->init_lock);
-
- return;
-
-error:
- up_read(&zram->init_lock);
- bio_io_error(bio);
-}
-
-static void zram_slot_free_notify(struct block_device *bdev,
- unsigned long index)
-{
- struct zram *zram;
-
- zram = bdev->bd_disk->private_data;
- down_write(&zram->lock);
- zram_free_page(zram, index);
- up_write(&zram->lock);
- atomic64_inc(&zram->stats.notify_free);
-}
-
-static const struct block_device_operations zram_devops = {
- .swap_slot_free_notify = zram_slot_free_notify,
- .owner = THIS_MODULE
-};
-
-static DEVICE_ATTR(disksize, S_IRUGO | S_IWUSR,
- disksize_show, disksize_store);
-static DEVICE_ATTR(initstate, S_IRUGO, initstate_show, NULL);
-static DEVICE_ATTR(reset, S_IWUSR, NULL, reset_store);
-static DEVICE_ATTR(num_reads, S_IRUGO, num_reads_show, NULL);
-static DEVICE_ATTR(num_writes, S_IRUGO, num_writes_show, NULL);
-static DEVICE_ATTR(invalid_io, S_IRUGO, invalid_io_show, NULL);
-static DEVICE_ATTR(notify_free, S_IRUGO, notify_free_show, NULL);
-static DEVICE_ATTR(zero_pages, S_IRUGO, zero_pages_show, NULL);
-static DEVICE_ATTR(orig_data_size, S_IRUGO, orig_data_size_show, NULL);
-static DEVICE_ATTR(compr_data_size, S_IRUGO, compr_data_size_show, NULL);
-static DEVICE_ATTR(mem_used_total, S_IRUGO, mem_used_total_show, NULL);
-
-static struct attribute *zram_disk_attrs[] = {
- &dev_attr_disksize.attr,
- &dev_attr_initstate.attr,
- &dev_attr_reset.attr,
- &dev_attr_num_reads.attr,
- &dev_attr_num_writes.attr,
- &dev_attr_invalid_io.attr,
- &dev_attr_notify_free.attr,
- &dev_attr_zero_pages.attr,
- &dev_attr_orig_data_size.attr,
- &dev_attr_compr_data_size.attr,
- &dev_attr_mem_used_total.attr,
- NULL,
-};
-
-static struct attribute_group zram_disk_attr_group = {
- .attrs = zram_disk_attrs,
-};
-
-static int create_device(struct zram *zram, int device_id)
-{
- int ret = -ENOMEM;
-
- init_rwsem(&zram->lock);
- init_rwsem(&zram->init_lock);
-
- zram->queue = blk_alloc_queue(GFP_KERNEL);
- if (!zram->queue) {
- pr_err("Error allocating disk queue for device %d\n",
- device_id);
- goto out;
- }
-
- blk_queue_make_request(zram->queue, zram_make_request);
- zram->queue->queuedata = zram;
-
- /* gendisk structure */
- zram->disk = alloc_disk(1);
- if (!zram->disk) {
- pr_warn("Error allocating disk structure for device %d\n",
- device_id);
- goto out_free_queue;
- }
-
- zram->disk->major = zram_major;
- zram->disk->first_minor = device_id;
- zram->disk->fops = &zram_devops;
- zram->disk->queue = zram->queue;
- zram->disk->private_data = zram;
- snprintf(zram->disk->disk_name, 16, "zram%d", device_id);
-
- /* Actual capacity set using syfs (/sys/block/zram<id>/disksize */
- set_capacity(zram->disk, 0);
-
- /*
- * To ensure that we always get PAGE_SIZE aligned
- * and n*PAGE_SIZED sized I/O requests.
- */
- blk_queue_physical_block_size(zram->disk->queue, PAGE_SIZE);
- blk_queue_logical_block_size(zram->disk->queue,
- ZRAM_LOGICAL_BLOCK_SIZE);
- blk_queue_io_min(zram->disk->queue, PAGE_SIZE);
- blk_queue_io_opt(zram->disk->queue, PAGE_SIZE);
-
- add_disk(zram->disk);
-
- ret = sysfs_create_group(&disk_to_dev(zram->disk)->kobj,
- &zram_disk_attr_group);
- if (ret < 0) {
- pr_warn("Error creating sysfs group");
- goto out_free_disk;
- }
-
- zram->init_done = 0;
- return 0;
-
-out_free_disk:
- del_gendisk(zram->disk);
- put_disk(zram->disk);
-out_free_queue:
- blk_cleanup_queue(zram->queue);
-out:
- return ret;
-}
-
-static void destroy_device(struct zram *zram)
-{
- sysfs_remove_group(&disk_to_dev(zram->disk)->kobj,
- &zram_disk_attr_group);
-
- if (zram->disk) {
- del_gendisk(zram->disk);
- put_disk(zram->disk);
- }
-
- if (zram->queue)
- blk_cleanup_queue(zram->queue);
-}
-
-static int __init zram_init(void)
-{
- int ret, dev_id;
-
- if (num_devices > max_num_devices) {
- pr_warn("Invalid value for num_devices: %u\n",
- num_devices);
- ret = -EINVAL;
- goto out;
- }
-
- zram_major = register_blkdev(0, "zram");
- if (zram_major <= 0) {
- pr_warn("Unable to get major number\n");
- ret = -EBUSY;
- goto out;
- }
-
- /* Allocate the device array and initialize each one */
- zram_devices = kzalloc(num_devices * sizeof(struct zram), GFP_KERNEL);
- if (!zram_devices) {
- ret = -ENOMEM;
- goto unregister;
- }
-
- for (dev_id = 0; dev_id < num_devices; dev_id++) {
- ret = create_device(&zram_devices[dev_id], dev_id);
- if (ret)
- goto free_devices;
- }
-
- pr_info("Created %u device(s) ...\n", num_devices);
-
- return 0;
-
-free_devices:
- while (dev_id)
- destroy_device(&zram_devices[--dev_id]);
- kfree(zram_devices);
-unregister:
- unregister_blkdev(zram_major, "zram");
-out:
- return ret;
-}
-
-static void __exit zram_exit(void)
-{
- int i;
- struct zram *zram;
-
- for (i = 0; i < num_devices; i++) {
- zram = &zram_devices[i];
-
- get_disk(zram->disk);
- destroy_device(zram);
- zram_reset_device(zram);
- put_disk(zram->disk);
- }
-
- unregister_blkdev(zram_major, "zram");
-
- kfree(zram_devices);
- pr_debug("Cleanup done!\n");
-}
-
-module_init(zram_init);
-module_exit(zram_exit);
-
-module_param(num_devices, uint, 0);
-MODULE_PARM_DESC(num_devices, "Number of zram devices");
-
-MODULE_LICENSE("Dual BSD/GPL");
-MODULE_AUTHOR("Nitin Gupta <ngupta@vflare.org>");
-MODULE_DESCRIPTION("Compressed RAM Block Device");
diff --git a/drivers/staging/zram/zram_drv.h b/drivers/staging/zram/zram_drv.h
deleted file mode 100644
index 9e57bfb..0000000
--- a/drivers/staging/zram/zram_drv.h
+++ /dev/null
@@ -1,115 +0,0 @@
-/*
- * Compressed RAM block device
- *
- * Copyright (C) 2008, 2009, 2010 Nitin Gupta
- *
- * This code is released using a dual license strategy: BSD/GPL
- * You can choose the licence 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
- *
- * Project home: http://compcache.googlecode.com
- */
-
-#ifndef _ZRAM_DRV_H_
-#define _ZRAM_DRV_H_
-
-#include <linux/spinlock.h>
-#include <linux/mutex.h>
-
-#include "../zsmalloc/zsmalloc.h"
-
-/*
- * Some arbitrary value. This is just to catch
- * invalid value for num_devices module parameter.
- */
-static const unsigned max_num_devices = 32;
-
-/*-- Configurable parameters */
-
-/*
- * Pages that compress to size greater than this are stored
- * uncompressed in memory.
- */
-static const size_t max_zpage_size = PAGE_SIZE / 4 * 3;
-
-/*
- * NOTE: max_zpage_size must be less than or equal to:
- * ZS_MAX_ALLOC_SIZE. Otherwise, zs_malloc() would
- * always return failure.
- */
-
-/*-- End of configurable params */
-
-#define SECTOR_SHIFT 9
-#define SECTOR_SIZE (1 << SECTOR_SHIFT)
-#define SECTORS_PER_PAGE_SHIFT (PAGE_SHIFT - SECTOR_SHIFT)
-#define SECTORS_PER_PAGE (1 << SECTORS_PER_PAGE_SHIFT)
-#define ZRAM_LOGICAL_BLOCK_SHIFT 12
-#define ZRAM_LOGICAL_BLOCK_SIZE (1 << ZRAM_LOGICAL_BLOCK_SHIFT)
-#define ZRAM_SECTOR_PER_LOGICAL_BLOCK \
- (1 << (ZRAM_LOGICAL_BLOCK_SHIFT - SECTOR_SHIFT))
-
-/* Flags for zram pages (table[page_no].flags) */
-enum zram_pageflags {
- /* Page consists entirely of zeros */
- ZRAM_ZERO,
-
- __NR_ZRAM_PAGEFLAGS,
-};
-
-/*-- Data structures */
-
-/* Allocated for each disk page */
-struct table {
- unsigned long handle;
- u16 size; /* object size (excluding header) */
- u8 count; /* object ref count (not yet used) */
- u8 flags;
-} __aligned(4);
-
-/*
- * All 64bit fields should only be manipulated by 64bit atomic accessors.
- * All modifications to 32bit counter should be protected by zram->lock.
- */
-struct zram_stats {
- atomic64_t compr_size; /* compressed size of pages stored */
- atomic64_t num_reads; /* failed + successful */
- atomic64_t num_writes; /* --do-- */
- atomic64_t failed_reads; /* should NEVER! happen */
- atomic64_t failed_writes; /* can happen when memory is too low */
- atomic64_t invalid_io; /* non-page-aligned I/O requests */
- atomic64_t notify_free; /* no. of swap slot free notifications */
- u32 pages_zero; /* no. of zero filled pages */
- u32 pages_stored; /* no. of pages currently stored */
- u32 good_compress; /* % of pages with compression ratio<=50% */
- u32 bad_compress; /* % of pages with compression ratio>=75% */
-};
-
-struct zram_meta {
- void *compress_workmem;
- void *compress_buffer;
- struct table *table;
- struct zs_pool *mem_pool;
-};
-
-struct zram {
- struct zram_meta *meta;
- struct rw_semaphore lock; /* protect compression buffers, table,
- * 32bit stat counters against concurrent
- * notifications, reads and writes */
- struct request_queue *queue;
- struct gendisk *disk;
- int init_done;
- /* Prevent concurrent execution of device init, reset and R/W request */
- struct rw_semaphore init_lock;
- /*
- * This is the limit on amount of *uncompressed* worth of data
- * we can store in a disk.
- */
- u64 disksize; /* bytes */
-
- struct zram_stats stats;
-};
-#endif
diff --git a/drivers/staging/zsmalloc/Kconfig b/drivers/staging/zsmalloc/Kconfig
deleted file mode 100644
index 7fab032..0000000
--- a/drivers/staging/zsmalloc/Kconfig
+++ /dev/null
@@ -1,10 +0,0 @@
-config ZSMALLOC
- bool "Memory allocator for compressed pages"
- default n
- help
- zsmalloc is a slab-based memory allocator designed to store
- compressed RAM pages. zsmalloc uses virtual memory mapping
- in order to reduce fragmentation. However, this results in a
- non-standard allocator interface where a handle, not a pointer, is
- returned by an alloc(). This handle must be mapped in order to
- access the allocated space.
diff --git a/drivers/staging/zsmalloc/Makefile b/drivers/staging/zsmalloc/Makefile
deleted file mode 100644
index b134848..0000000
--- a/drivers/staging/zsmalloc/Makefile
+++ /dev/null
@@ -1,3 +0,0 @@
-zsmalloc-y := zsmalloc-main.o
-
-obj-$(CONFIG_ZSMALLOC) += zsmalloc.o
diff --git a/drivers/staging/zsmalloc/zsmalloc-main.c b/drivers/staging/zsmalloc/zsmalloc-main.c
deleted file mode 100644
index 4bb275b..0000000
--- a/drivers/staging/zsmalloc/zsmalloc-main.c
+++ /dev/null
@@ -1,1063 +0,0 @@
-/*
- * zsmalloc memory allocator
- *
- * Copyright (C) 2011 Nitin Gupta
- *
- * 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
- */
-
-
-/*
- * This allocator is designed for use with zcache and 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).
- *
- * 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.
- *
- * 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
- *
- */
-
-#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/init.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>
-#include <linux/vmalloc.h>
-#include <linux/hardirq.h>
-#include <linux/spinlock.h>
-#include <linux/types.h>
-
-#include "zsmalloc.h"
-
-/*
- * 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
- * as single (void *) handle value.
- *
- * 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)
- */
-#define ZS_SIZE_CLASS_DELTA (PAGE_SIZE >> 8)
-#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 */
-};
-
-/*
- * 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)
-
-/*
- * By default, zsmalloc uses a copy-based object mapping method to access
- * allocations that span two pages. However, if a particular architecture
- * performs VM mapping faster than copying, then it should be added here
- * so that USE_PGTABLE_MAPPING is defined. This causes zsmalloc to use
- * page table mapping rather than copying for object mapping.
- */
-#if defined(CONFIG_ARM) && !defined(MODULE)
-#define USE_PGTABLE_MAPPING
-#endif
-
-struct mapping_area {
-#ifdef USE_PGTABLE_MAPPING
- 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 */
-};
-
-
-/* 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)
-{
- return PagePrivate(page);
-}
-
-static int is_last_page(struct page *page)
-{
- return PagePrivate2(page);
-}
-
-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;
-}
-
-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;
-}
-
-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;
-}
-
-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;
-}
-
-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);
-}
-
-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.
- */
-static int get_pages_per_zspage(int class_size)
-{
- int i, max_usedpc = 0;
- /* zspage order which gives maximum used size per KB */
- int max_usedpc_order = 1;
-
- for (i = 1; i <= ZS_MAX_PAGES_PER_ZSPAGE; i++) {
- 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))
- next = (struct page *)page->private;
- else
- next = list_entry(page->lru.next, struct page, lru);
-
- return next;
-}
-
-/* Encode <page, obj_idx> as a single handle value */
-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;
- handle |= (obj_idx & OBJ_INDEX_MASK);
-
- return (void *)handle;
-}
-
-/* Decode <page, obj_idx> pair from the given object handle */
-static void obj_handle_to_location(unsigned long handle, struct page **page,
- unsigned long *obj_idx)
-{
- *page = pfn_to_page(handle >> OBJ_INDEX_BITS);
- *obj_idx = handle & OBJ_INDEX_MASK;
-}
-
-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;
-}
-
-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;
- page_mapcount_reset(page);
-}
-
-static void free_zspage(struct page *first_page)
-{
- struct page *nextp, *tmp, *head_extra;
-
- BUG_ON(!is_first_page(first_page));
- BUG_ON(first_page->inuse);
-
- head_extra = (struct page *)page_private(first_page);
-
- reset_page(first_page);
- __free_page(first_page);
-
- /* zspage with only 1 system page */
- if (!head_extra)
- return;
-
- list_for_each_entry_safe(nextp, tmp, &head_extra->lru, lru) {
- list_del(&nextp->lru);
- reset_page(nextp);
- __free_page(nextp);
- }
- reset_page(head_extra);
- __free_page(head_extra);
-}
-
-/* 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;
- struct page *first_page = NULL, *uninitialized_var(prev_page);
-
- /*
- * 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;
- for (i = 0; i < class->pages_per_zspage; i++) {
- struct page *page;
-
- page = alloc_page(flags);
- if (!page)
- goto cleanup;
-
- INIT_LIST_HEAD(&page->lru);
- if (i == 0) { /* first page */
- SetPagePrivate(page);
- set_page_private(page, 0);
- first_page = page;
- first_page->inuse = 0;
- }
- if (i == 1)
- first_page->private = (unsigned long)page;
- if (i >= 1)
- page->first_page = first_page;
- if (i >= 2)
- list_add(&page->lru, &prev_page->lru);
- if (i == class->pages_per_zspage - 1) /* last page */
- SetPagePrivate2(page);
- 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 */
- first_page->objects = class->pages_per_zspage * PAGE_SIZE / class->size;
-
- 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;
-}
-
-#ifdef USE_PGTABLE_MAPPING
-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;
-
- unmap_kernel_range(addr, PAGE_SIZE * 2);
-}
-
-#else /* USE_PGTABLE_MAPPING */
-
-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)
-{
- int sizes[2];
- void *addr;
- char *buf = area->vm_buf;
-
- /* disable page faults to match kmap_atomic() return conditions */
- pagefault_disable();
-
- /* no read fastpath */
- if (area->vm_mm == ZS_MM_WO)
- goto out;
-
- 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);
-out:
- return area->vm_buf;
-}
-
-static void __zs_unmap_object(struct mapping_area *area,
- struct page *pages[2], int off, int size)
-{
- int sizes[2];
- void *addr;
- char *buf = area->vm_buf;
-
- /* no write fastpath */
- if (area->vm_mm == ZS_MM_RO)
- goto out;
-
- 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);
-
-out:
- /* enable page faults to match kunmap_atomic() return conditions */
- pagefault_enable();
-}
-
-#endif /* USE_PGTABLE_MAPPING */
-
-static int zs_cpu_notifier(struct notifier_block *nb, unsigned long action,
- void *pcpu)
-{
- int ret, cpu = (long)pcpu;
- struct mapping_area *area;
-
- switch (action) {
- case CPU_UP_PREPARE:
- area = &per_cpu(zs_map_area, cpu);
- ret = __zs_cpu_up(area);
- if (ret)
- return notifier_from_errno(ret);
- break;
- case CPU_DEAD:
- case CPU_UP_CANCELED:
- area = &per_cpu(zs_map_area, cpu);
- __zs_cpu_down(area);
- break;
- }
-
- return NOTIFY_OK;
-}
-
-static struct notifier_block zs_cpu_nb = {
- .notifier_call = zs_cpu_notifier
-};
-
-static void zs_exit(void)
-{
- int cpu;
-
- for_each_online_cpu(cpu)
- zs_cpu_notifier(NULL, CPU_DEAD, (void *)(long)cpu);
- unregister_cpu_notifier(&zs_cpu_nb);
-}
-
-static int zs_init(void)
-{
- int cpu, ret;
-
- register_cpu_notifier(&zs_cpu_nb);
- for_each_online_cpu(cpu) {
- ret = zs_cpu_notifier(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
- if (notifier_to_errno(ret))
- goto fail;
- }
- return 0;
-fail:
- zs_exit();
- return notifier_to_errno(ret);
-}
-
-/**
- * zs_create_pool - Creates an allocation pool to work from.
- * @flags: allocation flags used to allocate pool metadata
- *
- * 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.
- */
-struct zs_pool *zs_create_pool(gfp_t flags)
-{
- int i, ovhd_size;
- 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);
- class->pages_per_zspage = get_pages_per_zspage(size);
-
- }
-
- 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]) {
- pr_info("Freeing non-empty class with size %db, fullness group %d\n",
- 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
- *
- * On success, handle to the allocated object is returned,
- * otherwise 0.
- * Allocation requests with size > ZS_MAX_ALLOC_SIZE will fail.
- */
-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;
- unsigned long m_objidx, m_offset;
-
- 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);
-
- 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))
- return 0;
-
- set_zspage_mapping(first_page, class->index, ZS_EMPTY);
- spin_lock(&class->lock);
- class->pages_allocated += class->pages_per_zspage;
- }
-
- obj = (unsigned long)first_page->freelist;
- 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);
-
-void zs_free(struct zs_pool *pool, unsigned long obj)
-{
- 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);
- first_page->freelist = (void *)obj;
-
- first_page->inuse--;
- fullness = fix_fullness_group(pool, first_page);
-
- if (fullness == ZS_EMPTY)
- class->pages_allocated -= class->pages_per_zspage;
-
- spin_unlock(&class->lock);
-
- if (fullness == ZS_EMPTY)
- free_zspage(first_page);
-}
-EXPORT_SYMBOL_GPL(zs_free);
-
-/**
- * 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
- * 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.
- */
-void *zs_map_object(struct zs_pool *pool, unsigned long handle,
- enum zs_mapmode mm)
-{
- struct page *page;
- unsigned long obj_idx, off;
-
- unsigned int class_idx;
- enum fullness_group fg;
- struct size_class *class;
- struct mapping_area *area;
- struct page *pages[2];
-
- BUG_ON(!handle);
-
- /*
- * 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());
-
- 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);
- area->vm_mm = mm;
- if (off + class->size <= PAGE_SIZE) {
- /* this object is contained entirely within a page */
- area->vm_addr = kmap_atomic(page);
- return area->vm_addr + off;
- }
-
- /* this object spans two pages */
- pages[0] = page;
- pages[1] = get_next_page(page);
- BUG_ON(!pages[1]);
-
- return __zs_map_object(area, pages, off, class->size);
-}
-EXPORT_SYMBOL_GPL(zs_map_object);
-
-void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
-{
- 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);
-
- 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]);
-
- __zs_unmap_object(area, pages, off, class->size);
- }
- 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);
-
-module_init(zs_init);
-module_exit(zs_exit);
-
-MODULE_LICENSE("Dual BSD/GPL");
-MODULE_AUTHOR("Nitin Gupta <ngupta@vflare.org>");
diff --git a/drivers/staging/zsmalloc/zsmalloc.h b/drivers/staging/zsmalloc/zsmalloc.h
deleted file mode 100644
index fbe6bec..0000000
--- a/drivers/staging/zsmalloc/zsmalloc.h
+++ /dev/null
@@ -1,43 +0,0 @@
-/*
- * zsmalloc memory allocator
- *
- * Copyright (C) 2011 Nitin Gupta
- *
- * 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
- */
-
-#ifndef _ZS_MALLOC_H_
-#define _ZS_MALLOC_H_
-
-#include <linux/types.h>
-
-/*
- * zsmalloc mapping modes
- *
- * NOTE: These only make a difference when a mapped object spans pages
- */
-enum zs_mapmode {
- ZS_MM_RW, /* normal read-write mapping */
- ZS_MM_RO, /* read-only (no copy-out at unmap time) */
- ZS_MM_WO /* write-only (no copy-in at map time) */
-};
-
-struct zs_pool;
-
-struct zs_pool *zs_create_pool(gfp_t flags);
-void zs_destroy_pool(struct zs_pool *pool);
-
-unsigned long zs_malloc(struct zs_pool *pool, size_t size);
-void zs_free(struct zs_pool *pool, unsigned long obj);
-
-void *zs_map_object(struct zs_pool *pool, unsigned long handle,
- enum zs_mapmode mm);
-void zs_unmap_object(struct zs_pool *pool, unsigned long handle);
-
-u64 zs_get_total_size_bytes(struct zs_pool *pool);
-
-#endif
--
1.7.10.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH 2/4] mm: promote zsmalloc to mm/
2013-08-18 8:40 [PATCH 0/4] mm: merge zram into zswap Bob Liu
2013-08-18 8:40 ` [PATCH 1/4] drivers: staging: drop zram and zsmalloc Bob Liu
@ 2013-08-18 8:40 ` Bob Liu
2013-08-18 8:40 ` [PATCH 3/4] mm: zswap: add supporting for zsmalloc Bob Liu
` (2 subsequent siblings)
4 siblings, 0 replies; 11+ messages in thread
From: Bob Liu @ 2013-08-18 8:40 UTC (permalink / raw)
To: linux-mm
Cc: linux-kernel, eternaleye, minchan, mgorman, gregkh, akpm, axboe,
sjenning, ngupta, semenzato, penberg, sonnyrao, smbarber,
konrad.wilk, riel, kmpark, Bob Liu
zsmalloc is a new slab-based memory allocator for storing
compressed pages. It is designed for low fragmentation and
high allocation success rate on large object, but <= PAGE_SIZE
allocations.
zsmalloc differs from the kernel slab allocator in two primary
ways to achieve these design goals.
zsmalloc never requires high order page allocations to back
slabs, or "size classes" in zsmalloc terms. Instead it allows
multiple single-order pages to be stitched together into a
"zspage" which backs the slab. This allows for higher allocation
success rate under memory pressure.
Also, zsmalloc allows objects to span page boundaries within the
zspage. This allows for lower fragmentation than could be had
with the kernel slab allocator for objects between PAGE_SIZE/2
and PAGE_SIZE. With the kernel slab allocator, if a page compresses
to 60% of it original size, the memory savings gained through
compression is lost in fragmentation because another object of
the same size can't be stored in the leftover space.
This ability to span pages results in zsmalloc allocations not being
directly addressable by the user. The user is given an
non-dereferencable handle in response to an allocation request.
That handle must be mapped, using zs_map_object(), which returns
a pointer to the mapped region that can be used. The mapping is
necessary since the object data may reside in two different
noncontigious pages.
Signed-off-by: Bob Liu <bob.liu@oracle.com>
---
include/linux/zsmalloc.h | 43 ++
mm/Kconfig | 35 +-
mm/Makefile | 1 +
mm/zsmalloc.c | 1063 ++++++++++++++++++++++++++++++++++++++++++++++
4 files changed, 1131 insertions(+), 11 deletions(-)
create mode 100644 include/linux/zsmalloc.h
create mode 100644 mm/zsmalloc.c
diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h
new file mode 100644
index 0000000..fbe6bec
--- /dev/null
+++ b/include/linux/zsmalloc.h
@@ -0,0 +1,43 @@
+/*
+ * zsmalloc memory allocator
+ *
+ * Copyright (C) 2011 Nitin Gupta
+ *
+ * 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
+ */
+
+#ifndef _ZS_MALLOC_H_
+#define _ZS_MALLOC_H_
+
+#include <linux/types.h>
+
+/*
+ * zsmalloc mapping modes
+ *
+ * NOTE: These only make a difference when a mapped object spans pages
+ */
+enum zs_mapmode {
+ ZS_MM_RW, /* normal read-write mapping */
+ ZS_MM_RO, /* read-only (no copy-out at unmap time) */
+ ZS_MM_WO /* write-only (no copy-in at map time) */
+};
+
+struct zs_pool;
+
+struct zs_pool *zs_create_pool(gfp_t flags);
+void zs_destroy_pool(struct zs_pool *pool);
+
+unsigned long zs_malloc(struct zs_pool *pool, size_t size);
+void zs_free(struct zs_pool *pool, unsigned long obj);
+
+void *zs_map_object(struct zs_pool *pool, unsigned long handle,
+ enum zs_mapmode mm);
+void zs_unmap_object(struct zs_pool *pool, unsigned long handle);
+
+u64 zs_get_total_size_bytes(struct zs_pool *pool);
+
+#endif
diff --git a/mm/Kconfig b/mm/Kconfig
index 8028dcc..48d1786 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -478,21 +478,10 @@ config FRONTSWAP
If unsure, say Y to enable frontswap.
-config ZBUD
- tristate
- default n
- help
- A special purpose allocator for storing compressed pages.
- It is designed to store up to two compressed pages per physical
- page. While this design limits storage density, it has simple and
- deterministic reclaim properties that make it preferable to a higher
- density approach when reclaim will be used.
-
config ZSWAP
bool "Compressed cache for swap pages (EXPERIMENTAL)"
depends on FRONTSWAP && CRYPTO=y
select CRYPTO_LZO
- select ZBUD
default n
help
A lightweight compressed cache for swap pages. It takes
@@ -508,6 +497,30 @@ config ZSWAP
they have not be fully explored on the large set of potential
configurations and workloads that exist.
+choice
+ prompt "Select memory allocator for compressed pages"
+ depends on ZSWAP
+ default ZBUD
+
+ config ZBUD
+ bool "zbud"
+ help
+ A special purpose allocator for storing compressed pages.
+ It is designed to store up to two compressed pages per physical
+ page. While this design limits storage density, it has simple and
+ deterministic reclaim properties that make it preferable to a higher
+ density approach when reclaim will be used.
+
+ config ZSMALLOC
+ bool "zsmalloc"
+ help
+ zsmalloc is a slab-based memory allocator designed to store
+ compressed RAM pages. zsmalloc uses virtual memory mapping
+ in order to reduce fragmentation and has high compression density.
+ However, this results in a unpredictable performance characteristics
+ when reclaiming a single page.
+endchoice
+
config MEM_SOFT_DIRTY
bool "Track memory changes"
depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY
diff --git a/mm/Makefile b/mm/Makefile
index f008033..7d11958 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -60,3 +60,4 @@ obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o
obj-$(CONFIG_CLEANCACHE) += cleancache.o
obj-$(CONFIG_MEMORY_ISOLATION) += page_isolation.o
obj-$(CONFIG_ZBUD) += zbud.o
+obj-$(CONFIG_ZSMALLOC) += zsmalloc.o
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
new file mode 100644
index 0000000..4bb275b
--- /dev/null
+++ b/mm/zsmalloc.c
@@ -0,0 +1,1063 @@
+/*
+ * zsmalloc memory allocator
+ *
+ * Copyright (C) 2011 Nitin Gupta
+ *
+ * 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
+ */
+
+
+/*
+ * This allocator is designed for use with zcache and 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).
+ *
+ * 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.
+ *
+ * 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
+ *
+ */
+
+#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/init.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>
+#include <linux/vmalloc.h>
+#include <linux/hardirq.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+#include "zsmalloc.h"
+
+/*
+ * 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
+ * as single (void *) handle value.
+ *
+ * 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)
+ */
+#define ZS_SIZE_CLASS_DELTA (PAGE_SIZE >> 8)
+#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 */
+};
+
+/*
+ * 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)
+
+/*
+ * By default, zsmalloc uses a copy-based object mapping method to access
+ * allocations that span two pages. However, if a particular architecture
+ * performs VM mapping faster than copying, then it should be added here
+ * so that USE_PGTABLE_MAPPING is defined. This causes zsmalloc to use
+ * page table mapping rather than copying for object mapping.
+ */
+#if defined(CONFIG_ARM) && !defined(MODULE)
+#define USE_PGTABLE_MAPPING
+#endif
+
+struct mapping_area {
+#ifdef USE_PGTABLE_MAPPING
+ 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 */
+};
+
+
+/* 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)
+{
+ return PagePrivate(page);
+}
+
+static int is_last_page(struct page *page)
+{
+ return PagePrivate2(page);
+}
+
+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;
+}
+
+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;
+}
+
+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;
+}
+
+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;
+}
+
+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);
+}
+
+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.
+ */
+static int get_pages_per_zspage(int class_size)
+{
+ int i, max_usedpc = 0;
+ /* zspage order which gives maximum used size per KB */
+ int max_usedpc_order = 1;
+
+ for (i = 1; i <= ZS_MAX_PAGES_PER_ZSPAGE; i++) {
+ 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))
+ next = (struct page *)page->private;
+ else
+ next = list_entry(page->lru.next, struct page, lru);
+
+ return next;
+}
+
+/* Encode <page, obj_idx> as a single handle value */
+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;
+ handle |= (obj_idx & OBJ_INDEX_MASK);
+
+ return (void *)handle;
+}
+
+/* Decode <page, obj_idx> pair from the given object handle */
+static void obj_handle_to_location(unsigned long handle, struct page **page,
+ unsigned long *obj_idx)
+{
+ *page = pfn_to_page(handle >> OBJ_INDEX_BITS);
+ *obj_idx = handle & OBJ_INDEX_MASK;
+}
+
+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;
+}
+
+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;
+ page_mapcount_reset(page);
+}
+
+static void free_zspage(struct page *first_page)
+{
+ struct page *nextp, *tmp, *head_extra;
+
+ BUG_ON(!is_first_page(first_page));
+ BUG_ON(first_page->inuse);
+
+ head_extra = (struct page *)page_private(first_page);
+
+ reset_page(first_page);
+ __free_page(first_page);
+
+ /* zspage with only 1 system page */
+ if (!head_extra)
+ return;
+
+ list_for_each_entry_safe(nextp, tmp, &head_extra->lru, lru) {
+ list_del(&nextp->lru);
+ reset_page(nextp);
+ __free_page(nextp);
+ }
+ reset_page(head_extra);
+ __free_page(head_extra);
+}
+
+/* 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;
+ struct page *first_page = NULL, *uninitialized_var(prev_page);
+
+ /*
+ * 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;
+ for (i = 0; i < class->pages_per_zspage; i++) {
+ struct page *page;
+
+ page = alloc_page(flags);
+ if (!page)
+ goto cleanup;
+
+ INIT_LIST_HEAD(&page->lru);
+ if (i == 0) { /* first page */
+ SetPagePrivate(page);
+ set_page_private(page, 0);
+ first_page = page;
+ first_page->inuse = 0;
+ }
+ if (i == 1)
+ first_page->private = (unsigned long)page;
+ if (i >= 1)
+ page->first_page = first_page;
+ if (i >= 2)
+ list_add(&page->lru, &prev_page->lru);
+ if (i == class->pages_per_zspage - 1) /* last page */
+ SetPagePrivate2(page);
+ 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 */
+ first_page->objects = class->pages_per_zspage * PAGE_SIZE / class->size;
+
+ 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;
+}
+
+#ifdef USE_PGTABLE_MAPPING
+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;
+
+ unmap_kernel_range(addr, PAGE_SIZE * 2);
+}
+
+#else /* USE_PGTABLE_MAPPING */
+
+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)
+{
+ int sizes[2];
+ void *addr;
+ char *buf = area->vm_buf;
+
+ /* disable page faults to match kmap_atomic() return conditions */
+ pagefault_disable();
+
+ /* no read fastpath */
+ if (area->vm_mm == ZS_MM_WO)
+ goto out;
+
+ 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);
+out:
+ return area->vm_buf;
+}
+
+static void __zs_unmap_object(struct mapping_area *area,
+ struct page *pages[2], int off, int size)
+{
+ int sizes[2];
+ void *addr;
+ char *buf = area->vm_buf;
+
+ /* no write fastpath */
+ if (area->vm_mm == ZS_MM_RO)
+ goto out;
+
+ 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);
+
+out:
+ /* enable page faults to match kunmap_atomic() return conditions */
+ pagefault_enable();
+}
+
+#endif /* USE_PGTABLE_MAPPING */
+
+static int zs_cpu_notifier(struct notifier_block *nb, unsigned long action,
+ void *pcpu)
+{
+ int ret, cpu = (long)pcpu;
+ struct mapping_area *area;
+
+ switch (action) {
+ case CPU_UP_PREPARE:
+ area = &per_cpu(zs_map_area, cpu);
+ ret = __zs_cpu_up(area);
+ if (ret)
+ return notifier_from_errno(ret);
+ break;
+ case CPU_DEAD:
+ case CPU_UP_CANCELED:
+ area = &per_cpu(zs_map_area, cpu);
+ __zs_cpu_down(area);
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block zs_cpu_nb = {
+ .notifier_call = zs_cpu_notifier
+};
+
+static void zs_exit(void)
+{
+ int cpu;
+
+ for_each_online_cpu(cpu)
+ zs_cpu_notifier(NULL, CPU_DEAD, (void *)(long)cpu);
+ unregister_cpu_notifier(&zs_cpu_nb);
+}
+
+static int zs_init(void)
+{
+ int cpu, ret;
+
+ register_cpu_notifier(&zs_cpu_nb);
+ for_each_online_cpu(cpu) {
+ ret = zs_cpu_notifier(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
+ if (notifier_to_errno(ret))
+ goto fail;
+ }
+ return 0;
+fail:
+ zs_exit();
+ return notifier_to_errno(ret);
+}
+
+/**
+ * zs_create_pool - Creates an allocation pool to work from.
+ * @flags: allocation flags used to allocate pool metadata
+ *
+ * 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.
+ */
+struct zs_pool *zs_create_pool(gfp_t flags)
+{
+ int i, ovhd_size;
+ 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);
+ class->pages_per_zspage = get_pages_per_zspage(size);
+
+ }
+
+ 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]) {
+ pr_info("Freeing non-empty class with size %db, fullness group %d\n",
+ 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
+ *
+ * On success, handle to the allocated object is returned,
+ * otherwise 0.
+ * Allocation requests with size > ZS_MAX_ALLOC_SIZE will fail.
+ */
+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;
+ unsigned long m_objidx, m_offset;
+
+ 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);
+
+ 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))
+ return 0;
+
+ set_zspage_mapping(first_page, class->index, ZS_EMPTY);
+ spin_lock(&class->lock);
+ class->pages_allocated += class->pages_per_zspage;
+ }
+
+ obj = (unsigned long)first_page->freelist;
+ 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);
+
+void zs_free(struct zs_pool *pool, unsigned long obj)
+{
+ 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);
+ first_page->freelist = (void *)obj;
+
+ first_page->inuse--;
+ fullness = fix_fullness_group(pool, first_page);
+
+ if (fullness == ZS_EMPTY)
+ class->pages_allocated -= class->pages_per_zspage;
+
+ spin_unlock(&class->lock);
+
+ if (fullness == ZS_EMPTY)
+ free_zspage(first_page);
+}
+EXPORT_SYMBOL_GPL(zs_free);
+
+/**
+ * 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
+ * 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.
+ */
+void *zs_map_object(struct zs_pool *pool, unsigned long handle,
+ enum zs_mapmode mm)
+{
+ struct page *page;
+ unsigned long obj_idx, off;
+
+ unsigned int class_idx;
+ enum fullness_group fg;
+ struct size_class *class;
+ struct mapping_area *area;
+ struct page *pages[2];
+
+ BUG_ON(!handle);
+
+ /*
+ * 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());
+
+ 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);
+ area->vm_mm = mm;
+ if (off + class->size <= PAGE_SIZE) {
+ /* this object is contained entirely within a page */
+ area->vm_addr = kmap_atomic(page);
+ return area->vm_addr + off;
+ }
+
+ /* this object spans two pages */
+ pages[0] = page;
+ pages[1] = get_next_page(page);
+ BUG_ON(!pages[1]);
+
+ return __zs_map_object(area, pages, off, class->size);
+}
+EXPORT_SYMBOL_GPL(zs_map_object);
+
+void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
+{
+ 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);
+
+ 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]);
+
+ __zs_unmap_object(area, pages, off, class->size);
+ }
+ 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);
+
+module_init(zs_init);
+module_exit(zs_exit);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Nitin Gupta <ngupta@vflare.org>");
--
1.7.10.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH 3/4] mm: zswap: add supporting for zsmalloc
2013-08-18 8:40 [PATCH 0/4] mm: merge zram into zswap Bob Liu
2013-08-18 8:40 ` [PATCH 1/4] drivers: staging: drop zram and zsmalloc Bob Liu
2013-08-18 8:40 ` [PATCH 2/4] mm: promote zsmalloc to mm/ Bob Liu
@ 2013-08-18 8:40 ` Bob Liu
2013-08-19 16:59 ` Seth Jennings
2013-08-18 8:40 ` [PATCH 4/4] mm: zswap: create a pseudo device /dev/zram0 Bob Liu
2013-08-19 4:10 ` [PATCH 0/4] mm: merge zram into zswap Minchan Kim
4 siblings, 1 reply; 11+ messages in thread
From: Bob Liu @ 2013-08-18 8:40 UTC (permalink / raw)
To: linux-mm
Cc: linux-kernel, eternaleye, minchan, mgorman, gregkh, akpm, axboe,
sjenning, ngupta, semenzato, penberg, sonnyrao, smbarber,
konrad.wilk, riel, kmpark, Bob Liu
Make zswap can use zsmalloc as its allocater.
But note that zsmalloc don't reclaim any zswap pool pages mandatory, if zswap
pool gets full, frontswap_store will be refused unless frontswap_get happened
and freed some space.
The reason of don't implement reclaiming zsmalloc pages from zswap pool is there
is no requiremnet currently.
If we want to do mandatory reclaim, we have to write those pages to real backend
swap devices. But most of current users of zsmalloc are from embeded world,
there is even no real backend swap device.
This action is also the same as privous zram!
For several area, zsmalloc has unpredictable performance characteristics when
reclaiming a single page, then CONFIG_ZBUD are suggested.
Signed-off-by: Bob Liu <bob.liu@oracle.com>
---
include/linux/zsmalloc.h | 1 +
mm/Kconfig | 4 +++
mm/zsmalloc.c | 9 ++++--
mm/zswap.c | 73 +++++++++++++++++++++++++++++++++++++++++++---
4 files changed, 81 insertions(+), 6 deletions(-)
diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h
index fbe6bec..72fc126 100644
--- a/include/linux/zsmalloc.h
+++ b/include/linux/zsmalloc.h
@@ -39,5 +39,6 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle,
void zs_unmap_object(struct zs_pool *pool, unsigned long handle);
u64 zs_get_total_size_bytes(struct zs_pool *pool);
+u64 zs_get_pool_size(struct zs_pool *pool);
#endif
diff --git a/mm/Kconfig b/mm/Kconfig
index 48d1786..d80a575 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -519,6 +519,10 @@ choice
in order to reduce fragmentation and has high compression density.
However, this results in a unpredictable performance characteristics
when reclaiming a single page.
+
+ Note: By using zsmalloc, no supporting for mandatory reclaiming from
+ compressed memory pool. If the pool gets full, frontswap_store will
+ be refused unless frontswap_get happened and freed some space.
endchoice
config MEM_SOFT_DIRTY
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 4bb275b..9df8d25 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -78,8 +78,7 @@
#include <linux/hardirq.h>
#include <linux/spinlock.h>
#include <linux/types.h>
-
-#include "zsmalloc.h"
+#include <linux/zsmalloc.h>
/*
* This must be power of 2 and greater than of equal to sizeof(link_free).
@@ -1056,6 +1055,12 @@ u64 zs_get_total_size_bytes(struct zs_pool *pool)
}
EXPORT_SYMBOL_GPL(zs_get_total_size_bytes);
+u64 zs_get_pool_size(struct zs_pool *pool)
+{
+ return zs_get_total_size_bytes(pool) >> PAGE_SHIFT;
+}
+EXPORT_SYMBOL_GPL(zs_get_pool_size);
+
module_init(zs_init);
module_exit(zs_exit);
diff --git a/mm/zswap.c b/mm/zswap.c
index deda2b6..8e8dc99 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -34,8 +34,11 @@
#include <linux/swap.h>
#include <linux/crypto.h>
#include <linux/mempool.h>
+#ifdef CONFIG_ZBUD
#include <linux/zbud.h>
-
+#else
+#include <linux/zsmalloc.h>
+#endif
#include <linux/mm_types.h>
#include <linux/page-flags.h>
#include <linux/swapops.h>
@@ -189,7 +192,11 @@ struct zswap_header {
struct zswap_tree {
struct rb_root rbroot;
spinlock_t lock;
+#ifdef CONFIG_ZBUD
struct zbud_pool *pool;
+#else
+ struct zs_pool *pool;
+#endif
};
static struct zswap_tree *zswap_trees[MAX_SWAPFILES];
@@ -374,12 +381,21 @@ static bool zswap_is_full(void)
*/
static void zswap_free_entry(struct zswap_tree *tree, struct zswap_entry *entry)
{
+#ifdef CONFIG_ZBUD
zbud_free(tree->pool, entry->handle);
+#else
+ zs_free(tree->pool, entry->handle);
+#endif
zswap_entry_cache_free(entry);
atomic_dec(&zswap_stored_pages);
+#ifdef CONFIG_ZBUD
zswap_pool_pages = zbud_get_pool_size(tree->pool);
+#else
+ zswap_pool_pages = zs_get_pool_size(tree->pool);
+#endif
}
+#ifdef CONFIG_ZBUD
/*********************************
* writeback code
**********************************/
@@ -595,6 +611,7 @@ fail:
spin_unlock(&tree->lock);
return ret;
}
+#endif
/*********************************
* frontswap hooks
@@ -620,11 +637,22 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
/* reclaim space if needed */
if (zswap_is_full()) {
zswap_pool_limit_hit++;
+#ifdef CONFIG_ZBUD
if (zbud_reclaim_page(tree->pool, 8)) {
zswap_reject_reclaim_fail++;
ret = -ENOMEM;
goto reject;
}
+#else
+ /*
+ * zsmalloc has unpredictable performance
+ * characteristics when reclaiming, so don't support
+ * mandatory reclaiming from zsmalloc
+ */
+ zswap_reject_reclaim_fail++;
+ ret = -ENOMEM;
+ goto reject;
+#endif
}
/* allocate entry */
@@ -647,8 +675,9 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
/* store */
len = dlen + sizeof(struct zswap_header);
+#ifdef CONFIG_ZBUD
ret = zbud_alloc(tree->pool, len, __GFP_NORETRY | __GFP_NOWARN,
- &handle);
+ &handle);
if (ret == -ENOSPC) {
zswap_reject_compress_poor++;
goto freepage;
@@ -658,10 +687,23 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
goto freepage;
}
zhdr = zbud_map(tree->pool, handle);
+#else
+ handle = zs_malloc(tree->pool, len);
+ if (!handle) {
+ ret = -ENOMEM;
+ zswap_reject_alloc_fail++;
+ goto freepage;
+ }
+ zhdr = zs_map_object(tree->pool, handle, ZS_MM_WO);
+#endif
zhdr->swpentry = swp_entry(type, offset);
buf = (u8 *)(zhdr + 1);
memcpy(buf, dst, dlen);
+#ifdef CONFIG_ZBUD
zbud_unmap(tree->pool, handle);
+#else
+ zs_unmap_object(tree->pool, handle);
+#endif
put_cpu_var(zswap_dstmem);
/* populate entry */
@@ -687,8 +729,11 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
/* update stats */
atomic_inc(&zswap_stored_pages);
+#ifdef CONFIG_ZBUD
zswap_pool_pages = zbud_get_pool_size(tree->pool);
-
+#else
+ zswap_pool_pages = zs_get_pool_size(tree->pool);
+#endif
return 0;
freepage:
@@ -724,13 +769,22 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset,
/* decompress */
dlen = PAGE_SIZE;
+#ifdef CONFIG_ZBUD
src = (u8 *)zbud_map(tree->pool, entry->handle) +
- sizeof(struct zswap_header);
+ sizeof(struct zswap_header);
+#else
+ src = zs_map_object(tree->pool, entry->handle, ZS_MM_RO);
+ src += sizeof(struct zswap_header);
+#endif
dst = kmap_atomic(page);
ret = zswap_comp_op(ZSWAP_COMPOP_DECOMPRESS, src, entry->length,
dst, &dlen);
kunmap_atomic(dst);
+#ifdef CONFIG_ZBUD
zbud_unmap(tree->pool, entry->handle);
+#else
+ zs_unmap_object(tree->pool, entry->handle);
+#endif
BUG_ON(ret);
spin_lock(&tree->lock);
@@ -810,7 +864,11 @@ static void zswap_frontswap_invalidate_area(unsigned type)
while ((node = rb_first(&tree->rbroot))) {
entry = rb_entry(node, struct zswap_entry, rbnode);
rb_erase(&entry->rbnode, &tree->rbroot);
+#ifdef CONFIG_ZBUD
zbud_free(tree->pool, entry->handle);
+#else
+ zs_free(tree->pool, entry->handle);
+#endif
zswap_entry_cache_free(entry);
atomic_dec(&zswap_stored_pages);
}
@@ -818,9 +876,11 @@ static void zswap_frontswap_invalidate_area(unsigned type)
spin_unlock(&tree->lock);
}
+#ifdef CONFIG_ZBUD
static struct zbud_ops zswap_zbud_ops = {
.evict = zswap_writeback_entry
};
+#endif
static void zswap_frontswap_init(unsigned type)
{
@@ -829,7 +889,12 @@ static void zswap_frontswap_init(unsigned type)
tree = kzalloc(sizeof(struct zswap_tree), GFP_KERNEL);
if (!tree)
goto err;
+
+#ifdef CONFIG_ZBUD
tree->pool = zbud_create_pool(GFP_KERNEL, &zswap_zbud_ops);
+#else
+ tree->pool = zs_create_pool(GFP_NOWAIT);
+#endif
if (!tree->pool)
goto freetree;
tree->rbroot = RB_ROOT;
--
1.7.10.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 11+ messages in thread