diff --git a/arch/arm64/configs/meson64_defconfig b/arch/arm64/configs/meson64_defconfig index 76885f849cdd..6d46e6a8421b 100644 --- a/arch/arm64/configs/meson64_defconfig +++ b/arch/arm64/configs/meson64_defconfig @@ -290,6 +290,7 @@ CONFIG_MTD_CFI_INTELEXT=y CONFIG_MTD_NAND=y CONFIG_PROC_DEVICETREE=y CONFIG_ZRAM=y +CONFIG_ZRAM_LZ4_COMPRESS=y CONFIG_BLK_DEV_LOOP=y CONFIG_VIRTIO_BLK=y CONFIG_UID_STAT=y diff --git a/drivers/block/zram/Kconfig b/drivers/block/zram/Kconfig index 3450be850399..6489c0fd0ea6 100644 --- a/drivers/block/zram/Kconfig +++ b/drivers/block/zram/Kconfig @@ -15,6 +15,16 @@ config ZRAM See zram.txt for more information. +config ZRAM_LZ4_COMPRESS + bool "Enable LZ4 algorithm support" + depends on ZRAM + select LZ4_COMPRESS + select LZ4_DECOMPRESS + default n + help + This option enables LZ4 compression algorithm support. Compression + algorithm can be changed using `comp_algorithm' device attribute. + config ZRAM_DEBUG bool "Compressed RAM block device debug support" depends on ZRAM diff --git a/drivers/block/zram/Makefile b/drivers/block/zram/Makefile index cb0f9ced6a93..be0763ff57a2 100644 --- a/drivers/block/zram/Makefile +++ b/drivers/block/zram/Makefile @@ -1,3 +1,5 @@ -zram-y := zram_drv.o +zram-y := zcomp_lzo.o zcomp.o zram_drv.o + +zram-$(CONFIG_ZRAM_LZ4_COMPRESS) += zcomp_lz4.o obj-$(CONFIG_ZRAM) += zram.o diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c new file mode 100644 index 000000000000..f54d72c56177 --- /dev/null +++ b/drivers/block/zram/zcomp.c @@ -0,0 +1,355 @@ +/* + * Copyright (C) 2014 Sergey Senozhatsky. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include +#include +#include +#include +#include +#include + +#include "zcomp.h" +#include "zcomp_lzo.h" +#ifdef CONFIG_ZRAM_LZ4_COMPRESS +#include "zcomp_lz4.h" +#endif + +/* + * single zcomp_strm backend + */ +struct zcomp_strm_single { + struct mutex strm_lock; + struct zcomp_strm *zstrm; +}; + +/* + * multi zcomp_strm backend + */ +struct zcomp_strm_multi { + /* protect strm list */ + spinlock_t strm_lock; + /* max possible number of zstrm streams */ + int max_strm; + /* number of available zstrm streams */ + int avail_strm; + /* list of available strms */ + struct list_head idle_strm; + wait_queue_head_t strm_wait; +}; + +static struct zcomp_backend *backends[] = { + &zcomp_lzo, +#ifdef CONFIG_ZRAM_LZ4_COMPRESS + &zcomp_lz4, +#endif + NULL +}; + +static struct zcomp_backend *find_backend(const char *compress) +{ + int i = 0; + while (backends[i]) { + if (sysfs_streq(compress, backends[i]->name)) + break; + i++; + } + return backends[i]; +} + +static void zcomp_strm_free(struct zcomp *comp, struct zcomp_strm *zstrm) +{ + if (zstrm->private) + comp->backend->destroy(zstrm->private); + free_pages((unsigned long)zstrm->buffer, 1); + kfree(zstrm); +} + +/* + * allocate new zcomp_strm structure with ->private initialized by + * backend, return NULL on error + */ +static struct zcomp_strm *zcomp_strm_alloc(struct zcomp *comp) +{ + struct zcomp_strm *zstrm = kmalloc(sizeof(*zstrm), GFP_KERNEL); + if (!zstrm) + return NULL; + + zstrm->private = comp->backend->create(); + /* + * allocate 2 pages. 1 for compressed data, plus 1 extra for the + * case when compressed size is larger than the original one + */ + zstrm->buffer = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1); + if (!zstrm->private || !zstrm->buffer) { + zcomp_strm_free(comp, zstrm); + zstrm = NULL; + } + return zstrm; +} + +/* + * get idle zcomp_strm or wait until other process release + * (zcomp_strm_release()) one for us + */ +static struct zcomp_strm *zcomp_strm_multi_find(struct zcomp *comp) +{ + struct zcomp_strm_multi *zs = comp->stream; + struct zcomp_strm *zstrm; + + while (1) { + spin_lock(&zs->strm_lock); + if (!list_empty(&zs->idle_strm)) { + zstrm = list_entry(zs->idle_strm.next, + struct zcomp_strm, list); + list_del(&zstrm->list); + spin_unlock(&zs->strm_lock); + return zstrm; + } + /* zstrm streams limit reached, wait for idle stream */ + if (zs->avail_strm >= zs->max_strm) { + spin_unlock(&zs->strm_lock); + wait_event(zs->strm_wait, !list_empty(&zs->idle_strm)); + continue; + } + /* allocate new zstrm stream */ + zs->avail_strm++; + spin_unlock(&zs->strm_lock); + + zstrm = zcomp_strm_alloc(comp); + if (!zstrm) { + spin_lock(&zs->strm_lock); + zs->avail_strm--; + spin_unlock(&zs->strm_lock); + wait_event(zs->strm_wait, !list_empty(&zs->idle_strm)); + continue; + } + break; + } + return zstrm; +} + +/* add stream back to idle list and wake up waiter or free the stream */ +static void zcomp_strm_multi_release(struct zcomp *comp, + struct zcomp_strm *zstrm) +{ + struct zcomp_strm_multi *zs = comp->stream; + + spin_lock(&zs->strm_lock); + if (zs->avail_strm <= zs->max_strm) { + list_add(&zstrm->list, &zs->idle_strm); + spin_unlock(&zs->strm_lock); + wake_up(&zs->strm_wait); + return; + } + + zs->avail_strm--; + spin_unlock(&zs->strm_lock); + zcomp_strm_free(comp, zstrm); +} + +/* change max_strm limit */ +static bool zcomp_strm_multi_set_max_streams(struct zcomp *comp, int num_strm) +{ + struct zcomp_strm_multi *zs = comp->stream; + struct zcomp_strm *zstrm; + + spin_lock(&zs->strm_lock); + zs->max_strm = num_strm; + /* + * if user has lowered the limit and there are idle streams, + * immediately free as much streams (and memory) as we can. + */ + while (zs->avail_strm > num_strm && !list_empty(&zs->idle_strm)) { + zstrm = list_entry(zs->idle_strm.next, + struct zcomp_strm, list); + list_del(&zstrm->list); + zcomp_strm_free(comp, zstrm); + zs->avail_strm--; + } + spin_unlock(&zs->strm_lock); + return true; +} + +static void zcomp_strm_multi_destroy(struct zcomp *comp) +{ + struct zcomp_strm_multi *zs = comp->stream; + struct zcomp_strm *zstrm; + + while (!list_empty(&zs->idle_strm)) { + zstrm = list_entry(zs->idle_strm.next, + struct zcomp_strm, list); + list_del(&zstrm->list); + zcomp_strm_free(comp, zstrm); + } + kfree(zs); +} + +static int zcomp_strm_multi_create(struct zcomp *comp, int max_strm) +{ + struct zcomp_strm *zstrm; + struct zcomp_strm_multi *zs; + + comp->destroy = zcomp_strm_multi_destroy; + comp->strm_find = zcomp_strm_multi_find; + comp->strm_release = zcomp_strm_multi_release; + comp->set_max_streams = zcomp_strm_multi_set_max_streams; + zs = kmalloc(sizeof(struct zcomp_strm_multi), GFP_KERNEL); + if (!zs) + return -ENOMEM; + + comp->stream = zs; + spin_lock_init(&zs->strm_lock); + INIT_LIST_HEAD(&zs->idle_strm); + init_waitqueue_head(&zs->strm_wait); + zs->max_strm = max_strm; + zs->avail_strm = 1; + + zstrm = zcomp_strm_alloc(comp); + if (!zstrm) { + kfree(zs); + return -ENOMEM; + } + list_add(&zstrm->list, &zs->idle_strm); + return 0; +} + +static struct zcomp_strm *zcomp_strm_single_find(struct zcomp *comp) +{ + struct zcomp_strm_single *zs = comp->stream; + mutex_lock(&zs->strm_lock); + return zs->zstrm; +} + +static void zcomp_strm_single_release(struct zcomp *comp, + struct zcomp_strm *zstrm) +{ + struct zcomp_strm_single *zs = comp->stream; + mutex_unlock(&zs->strm_lock); +} + +static bool zcomp_strm_single_set_max_streams(struct zcomp *comp, int num_strm) +{ + /* zcomp_strm_single support only max_comp_streams == 1 */ + return false; +} + +static void zcomp_strm_single_destroy(struct zcomp *comp) +{ + struct zcomp_strm_single *zs = comp->stream; + zcomp_strm_free(comp, zs->zstrm); + kfree(zs); +} + +static int zcomp_strm_single_create(struct zcomp *comp) +{ + struct zcomp_strm_single *zs; + + comp->destroy = zcomp_strm_single_destroy; + comp->strm_find = zcomp_strm_single_find; + comp->strm_release = zcomp_strm_single_release; + comp->set_max_streams = zcomp_strm_single_set_max_streams; + zs = kmalloc(sizeof(struct zcomp_strm_single), GFP_KERNEL); + if (!zs) + return -ENOMEM; + + comp->stream = zs; + mutex_init(&zs->strm_lock); + zs->zstrm = zcomp_strm_alloc(comp); + if (!zs->zstrm) { + kfree(zs); + return -ENOMEM; + } + return 0; +} + +/* show available compressors */ +ssize_t zcomp_available_show(const char *comp, char *buf) +{ + ssize_t sz = 0; + int i = 0; + + while (backends[i]) { + if (sysfs_streq(comp, backends[i]->name)) + sz += scnprintf(buf + sz, PAGE_SIZE - sz - 2, + "[%s] ", backends[i]->name); + else + sz += scnprintf(buf + sz, PAGE_SIZE - sz - 2, + "%s ", backends[i]->name); + i++; + } + sz += scnprintf(buf + sz, PAGE_SIZE - sz, "\n"); + return sz; +} + +bool zcomp_set_max_streams(struct zcomp *comp, int num_strm) +{ + return comp->set_max_streams(comp, num_strm); +} + +struct zcomp_strm *zcomp_strm_find(struct zcomp *comp) +{ + return comp->strm_find(comp); +} + +void zcomp_strm_release(struct zcomp *comp, struct zcomp_strm *zstrm) +{ + comp->strm_release(comp, zstrm); +} + +int zcomp_compress(struct zcomp *comp, struct zcomp_strm *zstrm, + const unsigned char *src, size_t *dst_len) +{ + return comp->backend->compress(src, zstrm->buffer, dst_len, + zstrm->private); +} + +int zcomp_decompress(struct zcomp *comp, const unsigned char *src, + size_t src_len, unsigned char *dst) +{ + return comp->backend->decompress(src, src_len, dst); +} + +void zcomp_destroy(struct zcomp *comp) +{ + comp->destroy(comp); + kfree(comp); +} + +/* + * search available compressors for requested algorithm. + * allocate new zcomp and initialize it. return compressing + * backend pointer or ERR_PTR if things went bad. ERR_PTR(-EINVAL) + * if requested algorithm is not supported, ERR_PTR(-ENOMEM) in + * case of allocation error. + */ +struct zcomp *zcomp_create(const char *compress, int max_strm) +{ + struct zcomp *comp; + struct zcomp_backend *backend; + + backend = find_backend(compress); + pr_info("%s, comress:%s\n", __func__, compress); + if (!backend) + return ERR_PTR(-EINVAL); + + comp = kzalloc(sizeof(struct zcomp), GFP_KERNEL); + if (!comp) + return ERR_PTR(-ENOMEM); + + comp->backend = backend; + if (max_strm > 1) + zcomp_strm_multi_create(comp, max_strm); + else + zcomp_strm_single_create(comp); + if (!comp->stream) { + kfree(comp); + return ERR_PTR(-ENOMEM); + } + return comp; +} diff --git a/drivers/block/zram/zcomp.h b/drivers/block/zram/zcomp.h new file mode 100644 index 000000000000..b5df8954aca3 --- /dev/null +++ b/drivers/block/zram/zcomp.h @@ -0,0 +1,68 @@ +/* + * Copyright (C) 2014 Sergey Senozhatsky. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _ZCOMP_H_ +#define _ZCOMP_H_ + +#include + +struct zcomp_strm { + /* compression/decompression buffer */ + void *buffer; + /* + * The private data of the compression stream, only compression + * stream backend can touch this (e.g. compression algorithm + * working memory) + */ + void *private; + /* used in multi stream backend, protected by backend strm_lock */ + struct list_head list; +}; + +/* static compression backend */ +struct zcomp_backend { + int (*compress)(const unsigned char *src, unsigned char *dst, + size_t *dst_len, void *private); + + int (*decompress)(const unsigned char *src, size_t src_len, + unsigned char *dst); + + void * (*create)(void); + void (*destroy)(void *private); + + const char *name; +}; + +/* dynamic per-device compression frontend */ +struct zcomp { + void *stream; + struct zcomp_backend *backend; + + struct zcomp_strm * (*strm_find)(struct zcomp *comp); + void (*strm_release)(struct zcomp *comp, struct zcomp_strm *zstrm); + bool (*set_max_streams)(struct zcomp *comp, int num_strm); + void (*destroy)(struct zcomp *comp); +}; + +ssize_t zcomp_available_show(const char *comp, char *buf); + +struct zcomp *zcomp_create(const char *comp, int max_strm); +void zcomp_destroy(struct zcomp *comp); + +struct zcomp_strm *zcomp_strm_find(struct zcomp *comp); +void zcomp_strm_release(struct zcomp *comp, struct zcomp_strm *zstrm); + +int zcomp_compress(struct zcomp *comp, struct zcomp_strm *zstrm, + const unsigned char *src, size_t *dst_len); + +int zcomp_decompress(struct zcomp *comp, const unsigned char *src, + size_t src_len, unsigned char *dst); + +bool zcomp_set_max_streams(struct zcomp *comp, int num_strm); +#endif /* _ZCOMP_H_ */ diff --git a/drivers/block/zram/zcomp_lz4.c b/drivers/block/zram/zcomp_lz4.c new file mode 100644 index 000000000000..f2afb7e988c3 --- /dev/null +++ b/drivers/block/zram/zcomp_lz4.c @@ -0,0 +1,47 @@ +/* + * Copyright (C) 2014 Sergey Senozhatsky. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include +#include +#include + +#include "zcomp_lz4.h" + +static void *zcomp_lz4_create(void) +{ + return kzalloc(LZ4_MEM_COMPRESS, GFP_KERNEL); +} + +static void zcomp_lz4_destroy(void *private) +{ + kfree(private); +} + +static int zcomp_lz4_compress(const unsigned char *src, unsigned char *dst, + size_t *dst_len, void *private) +{ + /* return : Success if return 0 */ + return lz4_compress(src, PAGE_SIZE, dst, dst_len, private); +} + +static int zcomp_lz4_decompress(const unsigned char *src, size_t src_len, + unsigned char *dst) +{ + size_t dst_len = PAGE_SIZE; + /* return : Success if return 0 */ + return lz4_decompress_unknownoutputsize(src, src_len, dst, &dst_len); +} + +struct zcomp_backend zcomp_lz4 = { + .compress = zcomp_lz4_compress, + .decompress = zcomp_lz4_decompress, + .create = zcomp_lz4_create, + .destroy = zcomp_lz4_destroy, + .name = "lz4", +}; diff --git a/drivers/block/zram/zcomp_lz4.h b/drivers/block/zram/zcomp_lz4.h new file mode 100644 index 000000000000..60613fb29dd8 --- /dev/null +++ b/drivers/block/zram/zcomp_lz4.h @@ -0,0 +1,17 @@ +/* + * Copyright (C) 2014 Sergey Senozhatsky. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _ZCOMP_LZ4_H_ +#define _ZCOMP_LZ4_H_ + +#include "zcomp.h" + +extern struct zcomp_backend zcomp_lz4; + +#endif /* _ZCOMP_LZ4_H_ */ diff --git a/drivers/block/zram/zcomp_lzo.c b/drivers/block/zram/zcomp_lzo.c new file mode 100644 index 000000000000..da1bc47d588e --- /dev/null +++ b/drivers/block/zram/zcomp_lzo.c @@ -0,0 +1,47 @@ +/* + * Copyright (C) 2014 Sergey Senozhatsky. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include +#include +#include + +#include "zcomp_lzo.h" + +static void *lzo_create(void) +{ + return kzalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL); +} + +static void lzo_destroy(void *private) +{ + kfree(private); +} + +static int lzo_compress(const unsigned char *src, unsigned char *dst, + size_t *dst_len, void *private) +{ + int ret = lzo1x_1_compress(src, PAGE_SIZE, dst, dst_len, private); + return ret == LZO_E_OK ? 0 : ret; +} + +static int lzo_decompress(const unsigned char *src, size_t src_len, + unsigned char *dst) +{ + size_t dst_len = PAGE_SIZE; + int ret = lzo1x_decompress_safe(src, src_len, dst, &dst_len); + return ret == LZO_E_OK ? 0 : ret; +} + +struct zcomp_backend zcomp_lzo = { + .compress = lzo_compress, + .decompress = lzo_decompress, + .create = lzo_create, + .destroy = lzo_destroy, + .name = "lzo", +}; diff --git a/drivers/block/zram/zcomp_lzo.h b/drivers/block/zram/zcomp_lzo.h new file mode 100644 index 000000000000..128c5807fa14 --- /dev/null +++ b/drivers/block/zram/zcomp_lzo.h @@ -0,0 +1,17 @@ +/* + * Copyright (C) 2014 Sergey Senozhatsky. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _ZCOMP_LZO_H_ +#define _ZCOMP_LZO_H_ + +#include "zcomp.h" + +extern struct zcomp_backend zcomp_lzo; + +#endif /* _ZCOMP_LZO_H_ */ diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 413d56e36ce6..be284199827f 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -29,21 +29,36 @@ #include #include #include -#include #include #include +#include #include "zram_drv.h" /* Globals */ static int zram_major; static struct zram *zram_devices; -void *compress_addr = NULL; -void *user_addr = NULL; -void *meta_addr = NULL; +static const char *default_compressor = "lz4"; + /* Module params (documentation at end) */ static unsigned int num_devices = 1; +#define ZRAM_ATTR_RO(name) \ +static ssize_t zram_attr_##name##_show(struct device *d, \ + struct device_attribute *attr, char *b) \ +{ \ + struct zram *zram = dev_to_zram(d); \ + return scnprintf(b, PAGE_SIZE, "%llu\n", \ + (u64)atomic64_read(&zram->stats.name)); \ +} \ +static struct device_attribute dev_attr_##name = \ + __ATTR(name, S_IRUGO, zram_attr_##name##_show, NULL); + +static inline int init_done(struct zram *zram) +{ + return zram->meta != NULL; +} + static inline struct zram *dev_to_zram(struct device *dev) { return (struct zram *)dev_to_disk(dev)->private_data; @@ -54,59 +69,20 @@ static ssize_t disksize_show(struct device *dev, { struct zram *zram = dev_to_zram(dev); - return sprintf(buf, "%llu\n", zram->disksize); + return scnprintf(buf, PAGE_SIZE, "%llu\n", zram->disksize); } static ssize_t initstate_show(struct device *dev, struct device_attribute *attr, char *buf) { + u32 val; struct zram *zram = dev_to_zram(dev); - return sprintf(buf, "%u\n", zram->init_done); -} + down_read(&zram->init_lock); + val = init_done(zram); + up_read(&zram->init_lock); -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", atomic_read(&zram->stats.pages_zero)); + return scnprintf(buf, PAGE_SIZE, "%u\n", val); } static ssize_t orig_data_size_show(struct device *dev, @@ -114,17 +90,8 @@ static ssize_t orig_data_size_show(struct device *dev, { struct zram *zram = dev_to_zram(dev); - return sprintf(buf, "%llu\n", - (u64)(atomic_read(&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)); + return scnprintf(buf, PAGE_SIZE, "%llu\n", + (u64)(atomic64_read(&zram->stats.pages_stored)) << PAGE_SHIFT); } static ssize_t mem_used_total_show(struct device *dev, @@ -132,33 +99,184 @@ static ssize_t mem_used_total_show(struct device *dev, { 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); + if (init_done(zram)) { + struct zram_meta *meta = zram->meta; + val = zs_get_total_pages(meta->mem_pool); + } up_read(&zram->init_lock); - return sprintf(buf, "%llu\n", val); + return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT); +} + +static ssize_t max_comp_streams_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int val; + struct zram *zram = dev_to_zram(dev); + + down_read(&zram->init_lock); + val = zram->max_comp_streams; + up_read(&zram->init_lock); + + return scnprintf(buf, PAGE_SIZE, "%d\n", val); +} + +static ssize_t mem_limit_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + u64 val; + struct zram *zram = dev_to_zram(dev); + + down_read(&zram->init_lock); + val = zram->limit_pages; + up_read(&zram->init_lock); + + return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT); +} + +static ssize_t mem_limit_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + u64 limit; + char *tmp; + struct zram *zram = dev_to_zram(dev); + + limit = memparse(buf, &tmp); + if (buf == tmp) /* no chars parsed, invalid input */ + return -EINVAL; + + down_write(&zram->init_lock); + zram->limit_pages = PAGE_ALIGN(limit) >> PAGE_SHIFT; + up_write(&zram->init_lock); + + return len; +} + +static ssize_t mem_used_max_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + u64 val = 0; + struct zram *zram = dev_to_zram(dev); + + down_read(&zram->init_lock); + if (init_done(zram)) + val = atomic_long_read(&zram->stats.max_used_pages); + up_read(&zram->init_lock); + + return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT); +} + +static ssize_t mem_used_max_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + int err; + unsigned long val; + struct zram *zram = dev_to_zram(dev); + + err = kstrtoul(buf, 10, &val); + if (err || val != 0) + return -EINVAL; + + down_read(&zram->init_lock); + if (init_done(zram)) { + struct zram_meta *meta = zram->meta; + atomic_long_set(&zram->stats.max_used_pages, + zs_get_total_pages(meta->mem_pool)); + } + up_read(&zram->init_lock); + + return len; +} + +static ssize_t max_comp_streams_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + int num; + struct zram *zram = dev_to_zram(dev); + int ret; + + ret = kstrtoint(buf, 0, &num); + if (ret < 0) + return ret; + if (num < 1) + return -EINVAL; + + down_write(&zram->init_lock); + if (init_done(zram)) { + if (!zcomp_set_max_streams(zram->comp, num)) { + pr_info("Cannot change max compression streams\n"); + ret = -EINVAL; + goto out; + } + } + + zram->max_comp_streams = num; + ret = len; +out: + up_write(&zram->init_lock); + return ret; +} + +static ssize_t comp_algorithm_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + size_t sz; + struct zram *zram = dev_to_zram(dev); + + down_read(&zram->init_lock); + sz = zcomp_available_show(zram->compressor, buf); + up_read(&zram->init_lock); + + return sz; +} + +static ssize_t comp_algorithm_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + struct zram *zram = dev_to_zram(dev); + down_write(&zram->init_lock); + if (init_done(zram)) { + up_write(&zram->init_lock); + pr_info("Can't change algorithm for initialized device\n"); + return -EBUSY; + } + strlcpy(zram->compressor, buf, sizeof(zram->compressor)); + up_write(&zram->init_lock); + return len; } /* flag operations needs meta->tb_lock */ static int zram_test_flag(struct zram_meta *meta, u32 index, enum zram_pageflags flag) { - return meta->table[index].flags & BIT(flag); + return meta->table[index].value & BIT(flag); } static void zram_set_flag(struct zram_meta *meta, u32 index, enum zram_pageflags flag) { - meta->table[index].flags |= BIT(flag); + meta->table[index].value |= BIT(flag); } static void zram_clear_flag(struct zram_meta *meta, u32 index, enum zram_pageflags flag) { - meta->table[index].flags &= ~BIT(flag); + meta->table[index].value &= ~BIT(flag); +} + +static size_t zram_get_obj_size(struct zram_meta *meta, u32 index) +{ + return meta->table[index].value & (BIT(ZRAM_FLAG_SHIFT) - 1); +} + +static void zram_set_obj_size(struct zram_meta *meta, + u32 index, size_t size) +{ + unsigned long flags = meta->table[index].value >> ZRAM_FLAG_SHIFT; + + meta->table[index].value = (flags << ZRAM_FLAG_SHIFT) | size; } static inline int is_partial_io(struct bio_vec *bvec) @@ -194,8 +312,6 @@ static inline int valid_io_request(struct zram *zram, struct bio *bio) 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); } @@ -207,22 +323,11 @@ static struct zram_meta *zram_meta_alloc(u64 disksize) 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; + goto free_meta; } meta->mem_pool = zs_create_pool(GFP_NOIO | __GFP_HIGHMEM); @@ -231,16 +336,10 @@ static struct zram_meta *zram_meta_alloc(u64 disksize) goto free_table; } - rwlock_init(&meta->tb_lock); - mutex_init(&meta->buffer_lock); 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; @@ -285,12 +384,16 @@ static void handle_zero_page(struct bio_vec *bvec) flush_dcache_page(page); } -/* NOTE: caller should hold meta->tb_lock with write-side */ + +/* + * To protect concurrent access to the same index entry, + * caller should hold this table index entry's bit_spinlock to + * indicate this index entry is accessing. + */ 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)) { /* @@ -299,41 +402,35 @@ static void zram_free_page(struct zram *zram, size_t index) */ if (zram_test_flag(meta, index, ZRAM_ZERO)) { zram_clear_flag(meta, index, ZRAM_ZERO); - atomic_dec(&zram->stats.pages_zero); + atomic64_dec(&zram->stats.zero_pages); } return; } - if (unlikely(size > max_zpage_size)) - atomic_dec(&zram->stats.bad_compress); - zs_free(meta->mem_pool, handle); - if (size <= PAGE_SIZE / 2) - atomic_dec(&zram->stats.good_compress); - - atomic64_sub(meta->table[index].size, &zram->stats.compr_size); - atomic_dec(&zram->stats.pages_stored); + atomic64_sub(zram_get_obj_size(meta, index), + &zram->stats.compr_data_size); + atomic64_dec(&zram->stats.pages_stored); meta->table[index].handle = 0; - meta->table[index].size = 0; + zram_set_obj_size(meta, index, 0); } static int zram_decompress_page(struct zram *zram, char *mem, u32 index) { - int ret = LZO_E_OK; - size_t clen = PAGE_SIZE; + int ret = 0; unsigned char *cmem; struct zram_meta *meta = zram->meta; unsigned long handle; - u16 size; + size_t size; - read_lock(&meta->tb_lock); + bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value); handle = meta->table[index].handle; - size = meta->table[index].size; + size = zram_get_obj_size(meta, index); if (!handle || zram_test_flag(meta, index, ZRAM_ZERO)) { - read_unlock(&meta->tb_lock); + bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); clear_page(mem); return 0; } @@ -342,14 +439,13 @@ static int zram_decompress_page(struct zram *zram, char *mem, u32 index) if (size == PAGE_SIZE) copy_page(mem, cmem); else - ret = lzo1x_decompress_safe(cmem, size, mem, &clen); + ret = zcomp_decompress(zram->comp, cmem, size, mem); zs_unmap_object(meta->mem_pool, handle); - read_unlock(&meta->tb_lock); + bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); /* Should NEVER happen. Return bio error if it does. */ - if (unlikely(ret != LZO_E_OK)) { + if (unlikely(ret)) { pr_err("Decompression failed! err=%d, page=%u\n", ret, index); - atomic64_inc(&zram->stats.failed_reads); return ret; } @@ -365,14 +461,14 @@ static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, struct zram_meta *meta = zram->meta; page = bvec->bv_page; - read_lock(&meta->tb_lock); + bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value); if (unlikely(!meta->table[index].handle) || zram_test_flag(meta, index, ZRAM_ZERO)) { - read_unlock(&meta->tb_lock); + bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); handle_zero_page(bvec); return 0; } - read_unlock(&meta->tb_lock); + bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); if (is_partial_io(bvec)) /* Use a temporary buffer to decompress the page */ @@ -390,7 +486,7 @@ static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, ret = zram_decompress_page(zram, uncmem, index); /* Should NEVER happen. Return bio error if it does. */ - if (unlikely(ret != LZO_E_OK)) + if (unlikely(ret)) goto out_cleanup; if (is_partial_io(bvec)) @@ -406,6 +502,21 @@ out_cleanup: return ret; } +static inline void update_used_max(struct zram *zram, + const unsigned long pages) +{ + int old_max, cur_max; + + old_max = atomic_long_read(&zram->stats.max_used_pages); + + do { + cur_max = old_max; + if (pages > cur_max) + old_max = atomic_long_cmpxchg( + &zram->stats.max_used_pages, cur_max, pages); + } while (old_max != cur_max); +} + static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index, int offset) { @@ -415,11 +526,11 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index, struct page *page; unsigned char *user_mem, *cmem, *src, *uncmem = NULL; struct zram_meta *meta = zram->meta; + struct zcomp_strm *zstrm; bool locked = false; + unsigned long alloced_pages; 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 @@ -435,7 +546,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index, goto out; } - mutex_lock(&meta->buffer_lock); + zstrm = zcomp_strm_find(zram->comp); locked = true; user_mem = kmap_atomic(page); @@ -452,33 +563,30 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index, if (user_mem) kunmap_atomic(user_mem); /* Free memory associated with this sector now. */ - write_lock(&zram->meta->tb_lock); + bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value); zram_free_page(zram, index); zram_set_flag(meta, index, ZRAM_ZERO); - write_unlock(&zram->meta->tb_lock); + bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); - atomic_inc(&zram->stats.pages_zero); + atomic64_inc(&zram->stats.zero_pages); ret = 0; goto out; } - ret = lzo1x_1_compress(uncmem, PAGE_SIZE, src, &clen, - meta->compress_workmem); + ret = zcomp_compress(zram->comp, zstrm, uncmem, &clen); if (!is_partial_io(bvec)) { kunmap_atomic(user_mem); user_mem = NULL; uncmem = NULL; } - if (unlikely(ret != LZO_E_OK)) { + if (unlikely(ret)) { pr_err("Compression failed! err=%d\n", ret); goto out; } - + src = zstrm->buffer; if (unlikely(clen > max_zpage_size)) { - atomic_inc(&zram->stats.bad_compress); clen = PAGE_SIZE; - src = NULL; if (is_partial_io(bvec)) src = uncmem; } @@ -490,6 +598,16 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index, ret = -ENOMEM; goto out; } + + alloced_pages = zs_get_total_pages(meta->mem_pool); + if (zram->limit_pages && alloced_pages > zram->limit_pages) { + zs_free(meta->mem_pool, handle); + ret = -ENOMEM; + goto out; + } + + update_used_max(zram, alloced_pages); + cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_WO); if ((clen == PAGE_SIZE) && !is_partial_io(bvec)) { @@ -500,63 +618,110 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index, memcpy(cmem, src, clen); } + zcomp_strm_release(zram->comp, zstrm); + locked = false; zs_unmap_object(meta->mem_pool, handle); /* * Free memory associated with this sector * before overwriting unused sectors. */ - write_lock(&zram->meta->tb_lock); + bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value); zram_free_page(zram, index); meta->table[index].handle = handle; - meta->table[index].size = clen; - write_unlock(&zram->meta->tb_lock); + zram_set_obj_size(meta, index, clen); + bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); /* Update stats */ - atomic64_add(clen, &zram->stats.compr_size); - atomic_inc(&zram->stats.pages_stored); - if (clen <= PAGE_SIZE / 2) - atomic_inc(&zram->stats.good_compress); - + atomic64_add(clen, &zram->stats.compr_data_size); + atomic64_inc(&zram->stats.pages_stored); out: if (locked) - mutex_unlock(&meta->buffer_lock); + zcomp_strm_release(zram->comp, zstrm); 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 offset, struct bio *bio) { int ret; + int rw = bio_data_dir(bio); - if (rw == READ) + if (rw == READ) { + atomic64_inc(&zram->stats.num_reads); ret = zram_bvec_read(zram, bvec, index, offset, bio); - else + } else { + atomic64_inc(&zram->stats.num_writes); ret = zram_bvec_write(zram, bvec, index, offset); + } + + if (unlikely(ret)) { + if (rw == READ) + atomic64_inc(&zram->stats.failed_reads); + else + atomic64_inc(&zram->stats.failed_writes); + } return ret; } +/* + * zram_bio_discard - handler on discard request + * @index: physical block index in PAGE_SIZE units + * @offset: byte offset within physical block + */ +static void zram_bio_discard(struct zram *zram, u32 index, + int offset, struct bio *bio) +{ + size_t n = bio->bi_iter.bi_size; + struct zram_meta *meta = zram->meta; + + /* + * zram manages data in physical block size units. Because logical block + * size isn't identical with physical block size on some arch, we + * could get a discard request pointing to a specific offset within a + * certain physical block. Although we can handle this request by + * reading that physiclal block and decompressing and partially zeroing + * and re-compressing and then re-storing it, this isn't reasonable + * because our intent with a discard request is to save memory. So + * skipping this logical block is appropriate here. + */ + if (offset) { + if (n <= (PAGE_SIZE - offset)) + return; + + n -= (PAGE_SIZE - offset); + index++; + } + + while (n >= PAGE_SIZE) { + bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value); + zram_free_page(zram, index); + bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); + atomic64_inc(&zram->stats.notify_free); + index++; + n -= PAGE_SIZE; + } +} + static void zram_reset_device(struct zram *zram, bool reset_capacity) { size_t index; struct zram_meta *meta; down_write(&zram->init_lock); - if (!zram->init_done) { + + zram->limit_pages = 0; + + if (!init_done(zram)) { 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; @@ -566,6 +731,9 @@ static void zram_reset_device(struct zram *zram, bool reset_capacity) zs_free(meta->mem_pool, handle); } + zcomp_destroy(zram->comp); + zram->max_comp_streams = 1; + zram_meta_free(zram->meta); zram->meta = NULL; /* Reset stats */ @@ -574,40 +742,26 @@ static void zram_reset_device(struct zram *zram, bool reset_capacity) zram->disksize = 0; if (reset_capacity) 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"); + /* + * Revalidate disk out of the init_lock to avoid lockdep splat. + * It's okay because disk's capacity is protected by init_lock + * so that revalidate_disk always sees up-to-date capacity. + */ + if (reset_capacity) + revalidate_disk(zram->disk); } static ssize_t disksize_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { u64 disksize; + struct zcomp *comp; struct zram_meta *meta; struct zram *zram = dev_to_zram(dev); + int err; disksize = memparse(buf, NULL); if (!disksize) @@ -617,20 +771,43 @@ static ssize_t disksize_store(struct device *dev, meta = zram_meta_alloc(disksize); if (!meta) return -ENOMEM; - 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; + + comp = zcomp_create(zram->compressor, zram->max_comp_streams); + if (IS_ERR(comp)) { + pr_info("Cannot initialise %s compressing backend\n", + zram->compressor); + err = PTR_ERR(comp); + goto out_free_meta; } + down_write(&zram->init_lock); + if (init_done(zram)) { + pr_info("Cannot change disksize for initialized device\n"); + err = -EBUSY; + goto out_destroy_comp; + } + + zram->meta = meta; + zram->comp = comp; zram->disksize = disksize; set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT); - zram_init_device(zram, meta); up_write(&zram->init_lock); + /* + * Revalidate disk out of the init_lock to avoid lockdep splat. + * It's okay because disk's capacity is protected by init_lock + * so that revalidate_disk always sees up-to-date capacity. + */ + revalidate_disk(zram->disk); + return len; + +out_destroy_comp: + up_write(&zram->init_lock); + zcomp_destroy(comp); +out_free_meta: + zram_meta_free(meta); + return err; } static ssize_t reset_store(struct device *dev, @@ -674,26 +851,23 @@ out: return ret; } -static void __zram_make_request(struct zram *zram, struct bio *bio, int rw) +static void __zram_make_request(struct zram *zram, struct bio *bio) { int offset; u32 index; struct bio_vec bvec; struct bvec_iter iter; - switch (rw) { - case READ: - atomic64_inc(&zram->stats.num_reads); - break; - case WRITE: - atomic64_inc(&zram->stats.num_writes); - break; - } - index = bio->bi_iter.bi_sector >> SECTORS_PER_PAGE_SHIFT; offset = (bio->bi_iter.bi_sector & (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT; + if (unlikely(bio->bi_rw & REQ_DISCARD)) { + zram_bio_discard(zram, index, offset, bio); + bio_endio(bio, 0); + return; + } + bio_for_each_segment(bvec, bio, iter) { int max_transfer_size = PAGE_SIZE - offset; @@ -708,16 +882,15 @@ static void __zram_make_request(struct zram *zram, struct bio *bio, int rw) bv.bv_len = max_transfer_size; bv.bv_offset = bvec.bv_offset; - if (zram_bvec_rw(zram, &bv, index, offset, bio, rw) < 0) + if (zram_bvec_rw(zram, &bv, index, offset, bio) < 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) + if (zram_bvec_rw(zram, &bv, index + 1, 0, bio) < 0) goto out; } else - if (zram_bvec_rw(zram, &bvec, index, offset, bio, rw) - < 0) + if (zram_bvec_rw(zram, &bvec, index, offset, bio) < 0) goto out; update_position(&index, &offset, &bvec); @@ -739,7 +912,7 @@ 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)) + if (unlikely(!init_done(zram))) goto error; if (!valid_io_request(zram, bio)) { @@ -747,7 +920,7 @@ static void zram_make_request(struct request_queue *queue, struct bio *bio) goto error; } - __zram_make_request(zram, bio, bio_data_dir(bio)); + __zram_make_request(zram, bio); up_read(&zram->init_lock); return; @@ -766,55 +939,13 @@ static void zram_slot_free_notify(struct block_device *bdev, zram = bdev->bd_disk->private_data; meta = zram->meta; - write_lock(&meta->tb_lock); + bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value); zram_free_page(zram, index); - write_unlock(&meta->tb_lock); + bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); atomic64_inc(&zram->stats.notify_free); } -struct prev_use { - unsigned long cmpr_len; - struct page *page; -}; -static int zram_ioctl(struct block_device *bdev, - fmode_t f_mode, - unsigned nuse, unsigned long page_addr) -{ - int ret = 0; - size_t clen; - unsigned char *src = NULL, *uncmem = NULL, *user_mem = NULL; - void *compress_workmem = NULL; - struct prev_use *prev_use; - - switch (f_mode) { - case 80: - prev_use = (struct prev_use *)page_addr; - if (!compress_addr || !user_addr || !meta_addr) { - prev_use->cmpr_len = 0; - return -ENOMEM; - } - uncmem = kmap_atomic(prev_use->page); - user_mem = user_addr; - memcpy(user_mem, uncmem, PAGE_SIZE); - src = meta_addr; - compress_workmem = compress_addr; - - ret = lzo1x_1_compress(user_mem, PAGE_SIZE, src, &clen, - compress_workmem); - - kunmap_atomic(uncmem); - - prev_use->cmpr_len = (unsigned long)clen; - break; - - default: - break; - } - - return ret; -} static const struct block_device_operations zram_devops = { - .ioctl = zram_ioctl, .swap_slot_free_notify = zram_slot_free_notify, .owner = THIS_MODULE }; @@ -823,14 +954,25 @@ 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 DEVICE_ATTR(mem_limit, S_IRUGO | S_IWUSR, mem_limit_show, + mem_limit_store); +static DEVICE_ATTR(mem_used_max, S_IRUGO | S_IWUSR, mem_used_max_show, + mem_used_max_store); +static DEVICE_ATTR(max_comp_streams, S_IRUGO | S_IWUSR, + max_comp_streams_show, max_comp_streams_store); +static DEVICE_ATTR(comp_algorithm, S_IRUGO | S_IWUSR, + comp_algorithm_show, comp_algorithm_store); + +ZRAM_ATTR_RO(num_reads); +ZRAM_ATTR_RO(num_writes); +ZRAM_ATTR_RO(failed_reads); +ZRAM_ATTR_RO(failed_writes); +ZRAM_ATTR_RO(invalid_io); +ZRAM_ATTR_RO(notify_free); +ZRAM_ATTR_RO(zero_pages); +ZRAM_ATTR_RO(compr_data_size); static struct attribute *zram_disk_attrs[] = { &dev_attr_disksize.attr, @@ -838,12 +980,18 @@ static struct attribute *zram_disk_attrs[] = { &dev_attr_reset.attr, &dev_attr_num_reads.attr, &dev_attr_num_writes.attr, + &dev_attr_failed_reads.attr, + &dev_attr_failed_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, + &dev_attr_mem_limit.attr, + &dev_attr_mem_used_max.attr, + &dev_attr_max_comp_streams.attr, + &dev_attr_comp_algorithm.attr, NULL, }; @@ -884,7 +1032,9 @@ static int create_device(struct zram *zram, int device_id) /* Actual capacity set using syfs (/sys/block/zram/disksize */ set_capacity(zram->disk, 0); - + /* zram devices sort of resembles non-rotational disks */ + queue_flag_set_unlocked(QUEUE_FLAG_NONROT, zram->disk->queue); + queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, zram->disk->queue); /* * To ensure that we always get PAGE_SIZE aligned * and n*PAGE_SIZED sized I/O requests. @@ -894,6 +1044,21 @@ static int create_device(struct zram *zram, int device_id) ZRAM_LOGICAL_BLOCK_SIZE); blk_queue_io_min(zram->disk->queue, PAGE_SIZE); blk_queue_io_opt(zram->disk->queue, PAGE_SIZE); + zram->disk->queue->limits.discard_granularity = PAGE_SIZE; + zram->disk->queue->limits.max_discard_sectors = UINT_MAX; + /* + * zram_bio_discard() will clear all logical blocks if logical block + * size is identical with physical block size(PAGE_SIZE). But if it is + * different, we will skip discarding some parts of logical blocks in + * the part of the request range which isn't aligned to physical block + * size. So we can't ensure that all discarded logical blocks are + * zeroed. + */ + if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE) + zram->disk->queue->limits.discard_zeroes_data = 1; + else + zram->disk->queue->limits.discard_zeroes_data = 0; + queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, zram->disk->queue); add_disk(zram->disk); @@ -903,8 +1068,9 @@ static int create_device(struct zram *zram, int device_id) pr_warn("Error creating sysfs group"); goto out_free_disk; } - - zram->init_done = 0; + strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor)); + zram->meta = NULL; + zram->max_comp_streams = 1; return 0; out_free_disk: @@ -937,21 +1103,6 @@ static int __init zram_init(void) ret = -EINVAL; goto out; } - compress_addr = kzalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL); - if (!compress_addr) { - ret = -ENOMEM; - goto out; - } - user_addr = kzalloc(PAGE_SIZE, GFP_KERNEL); - if (!user_addr) { - ret = -ENOMEM; - goto out; - } - meta_addr = kzalloc(PAGE_SIZE << 1, GFP_KERNEL); - if (!meta_addr) { - ret = -ENOMEM; - goto out; - } zram_major = register_blkdev(0, "zram"); if (zram_major <= 0) { @@ -1006,9 +1157,6 @@ static void __exit zram_exit(void) unregister_blkdev(zram_major, "zram"); kfree(zram_devices); - kfree(meta_addr); - kfree(compress_addr); - kfree(user_addr); pr_debug("Cleanup done!\n"); } diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index ad8aa35bae00..c6ee271317f5 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -16,9 +16,10 @@ #define _ZRAM_DRV_H_ #include -#include #include +#include "zcomp.h" + /* * Some arbitrary value. This is just to catch * invalid value for num_devices module parameter. @@ -42,7 +43,6 @@ static const size_t max_zpage_size = PAGE_SIZE / 4 * 3; /*-- 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 @@ -50,10 +50,24 @@ static const size_t max_zpage_size = PAGE_SIZE / 4 * 3; #define ZRAM_SECTOR_PER_LOGICAL_BLOCK \ (1 << (ZRAM_LOGICAL_BLOCK_SHIFT - SECTOR_SHIFT)) -/* Flags for zram pages (table[page_no].flags) */ + +/* + * The lower ZRAM_FLAG_SHIFT bits of table.value is for + * object size (excluding header), the higher bits is for + * zram_pageflags. + * + * zram is mainly used for memory efficiency so we want to keep memory + * footprint small so we can squeeze size and flags into a field. + * The lower ZRAM_FLAG_SHIFT bits is for object size (excluding header), + * the higher bits is for zram_pageflags. + */ +#define ZRAM_FLAG_SHIFT 24 + +/* Flags for zram pages (table[page_no].value) */ enum zram_pageflags { /* Page consists entirely of zeros */ - ZRAM_ZERO, + ZRAM_ZERO = ZRAM_FLAG_SHIFT + 1, + ZRAM_ACCESS, /* page in now accessed */ __NR_ZRAM_PAGEFLAGS, }; @@ -61,41 +75,35 @@ enum zram_pageflags { /*-- Data structures */ /* Allocated for each disk page */ -struct table { +struct zram_table_entry { unsigned long handle; - u16 size; /* object size (excluding header) */ - u8 count; /* object ref count (not yet used) */ - u8 flags; -} __aligned(4); + unsigned long value; +}; struct zram_stats { - atomic64_t compr_size; /* compressed size of pages stored */ + atomic64_t compr_data_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_reads; /* can happen when memory is too low */ 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 */ - atomic_t pages_zero; /* no. of zero filled pages */ - atomic_t pages_stored; /* no. of pages currently stored */ - atomic_t good_compress; /* % of pages with compression ratio<=50% */ - atomic_t bad_compress; /* % of pages with compression ratio>=75% */ + atomic64_t zero_pages; /* no. of zero filled pages */ + atomic64_t pages_stored; /* no. of pages currently stored */ + atomic_long_t max_used_pages; /* no. of maximum pages stored */ }; struct zram_meta { - rwlock_t tb_lock; /* protect table */ - void *compress_workmem; - void *compress_buffer; - struct table *table; + struct zram_table_entry *table; struct zs_pool *mem_pool; - struct mutex buffer_lock; /* protect compress buffers */ }; struct zram { struct zram_meta *meta; struct request_queue *queue; struct gendisk *disk; - int init_done; + struct zcomp *comp; + /* Prevent concurrent execution of device init, reset and R/W request */ struct rw_semaphore init_lock; /* @@ -103,7 +111,13 @@ struct zram { * we can store in a disk. */ u64 disksize; /* bytes */ - + int max_comp_streams; struct zram_stats stats; + /* + * the number of pages zram can consume for storing compressed data + */ + unsigned long limit_pages; + + char compressor[10]; }; #endif diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 6b1d2ddfb0e2..1355b3c1e205 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -127,21 +127,33 @@ enum { #endif /* #else #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) */ #ifdef CONFIG_HOTPLUG_CPU extern int register_cpu_notifier(struct notifier_block *nb); +extern int __register_cpu_notifier(struct notifier_block *nb); extern void unregister_cpu_notifier(struct notifier_block *nb); +extern void __unregister_cpu_notifier(struct notifier_block *nb); #else #ifndef MODULE extern int register_cpu_notifier(struct notifier_block *nb); +extern int __register_cpu_notifier(struct notifier_block *nb); #else static inline int register_cpu_notifier(struct notifier_block *nb) { return 0; } + +static inline int __register_cpu_notifier(struct notifier_block *nb) +{ + return 0; +} #endif static inline void unregister_cpu_notifier(struct notifier_block *nb) { } + +static inline void __unregister_cpu_notifier(struct notifier_block *nb) +{ +} #endif int cpu_up(unsigned int cpu); @@ -149,6 +161,9 @@ void notify_cpu_starting(unsigned int cpu); extern void cpu_maps_update_begin(void); extern void cpu_maps_update_done(void); +#define cpu_notifier_register_begin cpu_maps_update_begin +#define cpu_notifier_register_done cpu_maps_update_done + #else /* CONFIG_SMP */ #define cpu_notifier(fn, pri) do { (void)(fn); } while (0) diff --git a/include/linux/zpool.h b/include/linux/zpool.h new file mode 100644 index 000000000000..75e59be2a135 --- /dev/null +++ b/include/linux/zpool.h @@ -0,0 +1,106 @@ +/* + * zpool memory storage api + * + * Copyright (C) 2014 Dan Streetman + * + * This is a common frontend for the zbud and zsmalloc memory + * storage pool implementations. Typically, this is used to + * store compressed memory. + */ + +#ifndef _ZPOOL_H_ +#define _ZPOOL_H_ + +struct zpool; + +struct zpool_ops { + int (*evict)(struct zpool *pool, unsigned long handle); +}; + +/* + * Control how a handle is mapped. It will be ignored if the + * implementation does not support it. Its use is optional. + * Note that this does not refer to memory protection, it + * refers to how the memory will be copied in/out if copying + * is necessary during mapping; read-write is the safest as + * it copies the existing memory in on map, and copies the + * changed memory back out on unmap. Write-only does not copy + * in the memory and should only be used for initialization. + * If in doubt, use ZPOOL_MM_DEFAULT which is read-write. + */ +enum zpool_mapmode { + ZPOOL_MM_RW, /* normal read-write mapping */ + ZPOOL_MM_RO, /* read-only (no copy-out at unmap time) */ + ZPOOL_MM_WO, /* write-only (no copy-in at map time) */ + + ZPOOL_MM_DEFAULT = ZPOOL_MM_RW +}; + +struct zpool *zpool_create_pool(char *type, gfp_t gfp, struct zpool_ops *ops); + +char *zpool_get_type(struct zpool *pool); + +void zpool_destroy_pool(struct zpool *pool); + +int zpool_malloc(struct zpool *pool, size_t size, gfp_t gfp, + unsigned long *handle); + +void zpool_free(struct zpool *pool, unsigned long handle); + +int zpool_shrink(struct zpool *pool, unsigned int pages, + unsigned int *reclaimed); + +void *zpool_map_handle(struct zpool *pool, unsigned long handle, + enum zpool_mapmode mm); + +void zpool_unmap_handle(struct zpool *pool, unsigned long handle); + +u64 zpool_get_total_size(struct zpool *pool); + + +/** + * struct zpool_driver - driver implementation for zpool + * @type: name of the driver. + * @list: entry in the list of zpool drivers. + * @create: create a new pool. + * @destroy: destroy a pool. + * @malloc: allocate mem from a pool. + * @free: free mem from a pool. + * @shrink: shrink the pool. + * @map: map a handle. + * @unmap: unmap a handle. + * @total_size: get total size of a pool. + * + * This is created by a zpool implementation and registered + * with zpool. + */ +struct zpool_driver { + char *type; + struct module *owner; + atomic_t refcount; + struct list_head list; + + void * (*create)(gfp_t gfp, struct zpool_ops *ops); + void (*destroy)(void *pool); + + int (*malloc)(void *pool, size_t size, gfp_t gfp, + unsigned long *handle); + void (*free)(void *pool, unsigned long handle); + + int (*shrink)(void *pool, unsigned int pages, + unsigned int *reclaimed); + + void * (*map)(void *pool, unsigned long handle, + enum zpool_mapmode mm); + void (*unmap)(void *pool, unsigned long handle); + + u64 (*total_size)(void *pool); +}; + +void zpool_register_driver(struct zpool_driver *driver); + +int zpool_unregister_driver(struct zpool_driver *driver); + +int zpool_evict(void *pool, unsigned long handle); + +#endif diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h index e44d634e7fb7..05c214760977 100644 --- a/include/linux/zsmalloc.h +++ b/include/linux/zsmalloc.h @@ -46,6 +46,6 @@ 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); +unsigned long zs_get_total_pages(struct zs_pool *pool); #endif diff --git a/kernel/cpu.c b/kernel/cpu.c index 436a93bae9e0..65bc94880d0c 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -34,11 +34,13 @@ void cpu_maps_update_begin(void) { mutex_lock(&cpu_add_remove_lock); } +EXPORT_SYMBOL(cpu_notifier_register_begin); void cpu_maps_update_done(void) { mutex_unlock(&cpu_add_remove_lock); } +EXPORT_SYMBOL(cpu_notifier_register_done); static RAW_NOTIFIER_HEAD(cpu_chain); @@ -166,6 +168,11 @@ int __ref register_cpu_notifier(struct notifier_block *nb) return ret; } +int __ref __register_cpu_notifier(struct notifier_block *nb) +{ + return raw_notifier_chain_register(&cpu_chain, nb); +} + static int __cpu_notify(unsigned long val, void *v, int nr_to_call, int *nr_calls) { @@ -189,6 +196,7 @@ static void cpu_notify_nofail(unsigned long val, void *v) BUG_ON(cpu_notify(val, v)); } EXPORT_SYMBOL(register_cpu_notifier); +EXPORT_SYMBOL(__register_cpu_notifier); void __ref unregister_cpu_notifier(struct notifier_block *nb) { @@ -198,6 +206,12 @@ void __ref unregister_cpu_notifier(struct notifier_block *nb) } EXPORT_SYMBOL(unregister_cpu_notifier); +void __ref __unregister_cpu_notifier(struct notifier_block *nb) +{ + raw_notifier_chain_unregister(&cpu_chain, nb); +} +EXPORT_SYMBOL(__unregister_cpu_notifier); + /** * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU * @cpu: a CPU id diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c index 7a85967060a5..f0f5c5c3de12 100644 --- a/lib/lz4/lz4_decompress.c +++ b/lib/lz4/lz4_decompress.c @@ -139,6 +139,9 @@ static int lz4_uncompress(const char *source, char *dest, int osize) /* Error: request to write beyond destination buffer */ if (cpy > oend) goto _output_error; + if ((ref + COPYLENGTH) > oend || + (op + COPYLENGTH) > oend) + goto _output_error; LZ4_SECURECOPY(ref, op, (oend - COPYLENGTH)); while (op < cpy) *op++ = *ref++; diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index c03ca5e9fe15..d6cce6b507ef 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -92,6 +92,7 @@ #include #include #include +#include /* * This must be power of 2 and greater than of equal to sizeof(link_free). @@ -198,9 +199,6 @@ struct size_class { spinlock_t lock; - /* stats */ - u64 pages_allocated; - struct page *fullness_list[_ZS_NR_FULLNESS_GROUPS]; }; @@ -219,6 +217,7 @@ struct zs_pool { struct size_class size_class[ZS_SIZE_CLASSES]; gfp_t flags; /* allocation flags used when growing pool */ + atomic_long_t pages_allocated; }; /* @@ -240,6 +239,82 @@ struct mapping_area { enum zs_mapmode vm_mm; /* mapping mode */ }; +/* zpool driver */ + +#ifdef CONFIG_ZPOOL + +static void *zs_zpool_create(gfp_t gfp, struct zpool_ops *zpool_ops) +{ + return zs_create_pool(gfp); +} + +static void zs_zpool_destroy(void *pool) +{ + zs_destroy_pool(pool); +} + +static int zs_zpool_malloc(void *pool, size_t size, gfp_t gfp, + unsigned long *handle) +{ + *handle = zs_malloc(pool, size); + return *handle ? 0 : -1; +} +static void zs_zpool_free(void *pool, unsigned long handle) +{ + zs_free(pool, handle); +} + +static int zs_zpool_shrink(void *pool, unsigned int pages, + unsigned int *reclaimed) +{ + return -EINVAL; +} + +static void *zs_zpool_map(void *pool, unsigned long handle, + enum zpool_mapmode mm) +{ + enum zs_mapmode zs_mm; + + switch (mm) { + case ZPOOL_MM_RO: + zs_mm = ZS_MM_RO; + break; + case ZPOOL_MM_WO: + zs_mm = ZS_MM_WO; + break; + case ZPOOL_MM_RW: /* fallthru */ + default: + zs_mm = ZS_MM_RW; + break; + } + + return zs_map_object(pool, handle, zs_mm); +} +static void zs_zpool_unmap(void *pool, unsigned long handle) +{ + zs_unmap_object(pool, handle); +} + +static u64 zs_zpool_total_size(void *pool) +{ + return zs_get_total_pages(pool) << PAGE_SHIFT; +} + +static struct zpool_driver zs_zpool_driver = { + .type = "zsmalloc", + .owner = THIS_MODULE, + .create = zs_zpool_create, + .destroy = zs_zpool_destroy, + .malloc = zs_zpool_malloc, + .free = zs_zpool_free, + .shrink = zs_zpool_shrink, + .map = zs_zpool_map, + .unmap = zs_zpool_unmap, + .total_size = zs_zpool_total_size, +}; + +MODULE_ALIAS("zpool-zsmalloc"); +#endif /* CONFIG_ZPOOL */ /* per-cpu VM mapping areas for zspage accesses that cross page boundaries */ static DEFINE_PER_CPU(struct mapping_area, zs_map_area); @@ -553,7 +628,7 @@ static void init_zspage(struct page *first_page, struct size_class *class) while (page) { struct page *next_page; struct link_free *link; - unsigned int i, objs_on_page; + unsigned int i = 1; /* * page->index stores offset of first object starting @@ -566,14 +641,10 @@ static void init_zspage(struct page *first_page, struct size_class *class) 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); - } + while ((off += class->size) < PAGE_SIZE) { + link->next = obj_location_to_handle(page, i++); + link += class->size / sizeof(*link); } /* @@ -585,7 +656,7 @@ static void init_zspage(struct page *first_page, struct size_class *class) link->next = obj_location_to_handle(next_page, 0); kunmap_atomic(link); page = next_page; - off = (off + class->size) % PAGE_SIZE; + off %= PAGE_SIZE; } } @@ -690,7 +761,7 @@ static inline void __zs_cpu_down(struct mapping_area *area) 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)); + BUG_ON(map_vm_area(area->vm, PAGE_KERNEL, pages)); area->vm_addr = area->vm->addr; return area->vm_addr + off; } @@ -814,21 +885,40 @@ static void zs_exit(void) { int cpu; +#ifdef CONFIG_ZPOOL + zpool_unregister_driver(&zs_zpool_driver); +#endif + + cpu_notifier_register_begin(); + for_each_online_cpu(cpu) zs_cpu_notifier(NULL, CPU_DEAD, (void *)(long)cpu); - unregister_cpu_notifier(&zs_cpu_nb); + __unregister_cpu_notifier(&zs_cpu_nb); + + cpu_notifier_register_done(); } static int zs_init(void) { int cpu, ret; - register_cpu_notifier(&zs_cpu_nb); + cpu_notifier_register_begin(); + + __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)) + if (notifier_to_errno(ret)) { + cpu_notifier_register_done(); goto fail; + } } + + cpu_notifier_register_done(); + +#ifdef CONFIG_ZPOOL + zpool_register_driver(&zs_zpool_driver); +#endif + return 0; fail: zs_exit(); @@ -932,8 +1022,9 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size) return 0; set_zspage_mapping(first_page, class->index, ZS_EMPTY); + atomic_long_add(class->pages_per_zspage, + &pool->pages_allocated); spin_lock(&class->lock); - class->pages_allocated += class->pages_per_zspage; } obj = (unsigned long)first_page->freelist; @@ -986,14 +1077,13 @@ void zs_free(struct zs_pool *pool, unsigned long 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) + if (fullness == ZS_EMPTY) { + atomic_long_sub(class->pages_per_zspage, + &pool->pages_allocated); free_zspage(first_page); + } } EXPORT_SYMBOL_GPL(zs_free); @@ -1071,7 +1161,7 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle) class = &pool->size_class[class_idx]; off = obj_idx_to_offset(page, obj_idx, class->size); - area = &__get_cpu_var(zs_map_area); + area = this_cpu_ptr(&zs_map_area); if (off + class->size <= PAGE_SIZE) kunmap_atomic(area->vm_addr); else { @@ -1087,17 +1177,11 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle) } EXPORT_SYMBOL_GPL(zs_unmap_object); -u64 zs_get_total_size_bytes(struct zs_pool *pool) +unsigned long zs_get_total_pages(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; + return atomic_long_read(&pool->pages_allocated); } -EXPORT_SYMBOL_GPL(zs_get_total_size_bytes); +EXPORT_SYMBOL_GPL(zs_get_total_pages); module_init(zs_init); module_exit(zs_exit);