diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2014-01-31 02:44:44 (GMT) |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-01-31 02:44:44 (GMT) |
commit | aa2e7100e38880db7907cb2b7ec6267b2b243771 (patch) | |
tree | 67f9d2479365398c07833d3fc4f794861f7da5b1 /drivers | |
parent | 2def2ef2ae5f3990aabdbe8a755911902707d268 (diff) | |
parent | 7c094fd698de2f333fa39b6da213f880d40b9bfe (diff) | |
download | linux-aa2e7100e38880db7907cb2b7ec6267b2b243771.tar.xz |
Merge branch 'akpm' (patches from Andrew Morton)
Merge misc fixes from Andrew Morton:
"A few hotfixes and various leftovers which were awaiting other merges.
Mainly movement of zram into mm/"
* emailed patches fron Andrew Morton <akpm@linux-foundation.org>: (25 commits)
memcg: fix mutex not unlocked on memcg_create_kmem_cache fail path
Documentation/filesystems/vfs.txt: update file_operations documentation
mm, oom: base root bonus on current usage
mm: don't lose the SOFT_DIRTY flag on mprotect
mm/slub.c: fix page->_count corruption (again)
mm/mempolicy.c: fix mempolicy printing in numa_maps
zram: remove zram->lock in read path and change it with mutex
zram: remove workqueue for freeing removed pending slot
zram: introduce zram->tb_lock
zram: use atomic operation for stat
zram: remove unnecessary free
zram: delay pending free request in read path
zram: fix race between reset and flushing pending work
zsmalloc: add maintainers
zram: add zram maintainers
zsmalloc: add copyright
zram: add copyright
zram: remove old private project comment
zram: promote zram from staging
zsmalloc: move it under mm
...
Diffstat (limited to 'drivers')
-rw-r--r-- | drivers/block/Kconfig | 2 | ||||
-rw-r--r-- | drivers/block/Makefile | 1 | ||||
-rw-r--r-- | drivers/block/zram/Kconfig (renamed from drivers/staging/zram/Kconfig) | 1 | ||||
-rw-r--r-- | drivers/block/zram/Makefile (renamed from drivers/staging/zram/Makefile) | 0 | ||||
-rw-r--r-- | drivers/block/zram/zram_drv.c (renamed from drivers/staging/zram/zram_drv.c) | 128 | ||||
-rw-r--r-- | drivers/block/zram/zram_drv.h (renamed from drivers/staging/zram/zram_drv.h) | 32 | ||||
-rw-r--r-- | drivers/net/phy/mdio_bus.c | 1 | ||||
-rw-r--r-- | drivers/staging/Kconfig | 4 | ||||
-rw-r--r-- | drivers/staging/Makefile | 2 | ||||
-rw-r--r-- | drivers/staging/zram/zram.txt | 77 | ||||
-rw-r--r-- | drivers/staging/zsmalloc/Kconfig | 24 | ||||
-rw-r--r-- | drivers/staging/zsmalloc/Makefile | 3 | ||||
-rw-r--r-- | drivers/staging/zsmalloc/zsmalloc-main.c | 1106 | ||||
-rw-r--r-- | drivers/staging/zsmalloc/zsmalloc.h | 50 | ||||
-rw-r--r-- | drivers/video/backlight/lcd.c | 2 |
15 files changed, 59 insertions, 1374 deletions
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index 9ffa90c..014a1cf 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -108,6 +108,8 @@ source "drivers/block/paride/Kconfig" source "drivers/block/mtip32xx/Kconfig" +source "drivers/block/zram/Kconfig" + config BLK_CPQ_DA tristate "Compaq SMART2 support" depends on PCI && VIRT_TO_BUS && 0 diff --git a/drivers/block/Makefile b/drivers/block/Makefile index 816d979..02b688d 100644 --- a/drivers/block/Makefile +++ b/drivers/block/Makefile @@ -42,6 +42,7 @@ obj-$(CONFIG_BLK_DEV_PCIESSD_MTIP32XX) += mtip32xx/ obj-$(CONFIG_BLK_DEV_RSXX) += rsxx/ obj-$(CONFIG_BLK_DEV_NULL_BLK) += null_blk.o +obj-$(CONFIG_ZRAM) += zram/ nvme-y := nvme-core.o nvme-scsi.o skd-y := skd_main.o diff --git a/drivers/staging/zram/Kconfig b/drivers/block/zram/Kconfig index 983314c..3450be8 100644 --- a/drivers/staging/zram/Kconfig +++ b/drivers/block/zram/Kconfig @@ -14,7 +14,6 @@ config ZRAM 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" diff --git a/drivers/staging/zram/Makefile b/drivers/block/zram/Makefile index cb0f9ce..cb0f9ce 100644 --- a/drivers/staging/zram/Makefile +++ b/drivers/block/zram/Makefile diff --git a/drivers/staging/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 108f273..011e55d 100644 --- a/drivers/staging/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -2,6 +2,7 @@ * Compressed RAM block device * * Copyright (C) 2008, 2009, 2010 Nitin Gupta + * 2012, 2013 Minchan Kim * * This code is released using a dual license strategy: BSD/GPL * You can choose the licence that better fits your requirements. @@ -9,7 +10,6 @@ * 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" @@ -104,7 +104,7 @@ static ssize_t zero_pages_show(struct device *dev, { struct zram *zram = dev_to_zram(dev); - return sprintf(buf, "%u\n", zram->stats.pages_zero); + return sprintf(buf, "%u\n", atomic_read(&zram->stats.pages_zero)); } static ssize_t orig_data_size_show(struct device *dev, @@ -113,7 +113,7 @@ static ssize_t orig_data_size_show(struct device *dev, struct zram *zram = dev_to_zram(dev); return sprintf(buf, "%llu\n", - (u64)(zram->stats.pages_stored) << PAGE_SHIFT); + (u64)(atomic_read(&zram->stats.pages_stored)) << PAGE_SHIFT); } static ssize_t compr_data_size_show(struct device *dev, @@ -140,6 +140,7 @@ static ssize_t mem_used_total_show(struct device *dev, return sprintf(buf, "%llu\n", val); } +/* flag operations needs meta->tb_lock */ static int zram_test_flag(struct zram_meta *meta, u32 index, enum zram_pageflags flag) { @@ -228,6 +229,8 @@ 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: @@ -280,6 +283,7 @@ static void handle_zero_page(struct bio_vec *bvec) flush_dcache_page(page); } +/* NOTE: caller should hold meta->tb_lock with write-side */ static void zram_free_page(struct zram *zram, size_t index) { struct zram_meta *meta = zram->meta; @@ -293,21 +297,21 @@ 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); - zram->stats.pages_zero--; + atomic_dec(&zram->stats.pages_zero); } return; } if (unlikely(size > max_zpage_size)) - zram->stats.bad_compress--; + atomic_dec(&zram->stats.bad_compress); zs_free(meta->mem_pool, handle); if (size <= PAGE_SIZE / 2) - zram->stats.good_compress--; + atomic_dec(&zram->stats.good_compress); atomic64_sub(meta->table[index].size, &zram->stats.compr_size); - zram->stats.pages_stored--; + atomic_dec(&zram->stats.pages_stored); meta->table[index].handle = 0; meta->table[index].size = 0; @@ -319,20 +323,26 @@ static int zram_decompress_page(struct zram *zram, char *mem, u32 index) size_t clen = PAGE_SIZE; unsigned char *cmem; struct zram_meta *meta = zram->meta; - unsigned long handle = meta->table[index].handle; + unsigned long handle; + u16 size; + + read_lock(&meta->tb_lock); + handle = meta->table[index].handle; + size = meta->table[index].size; if (!handle || zram_test_flag(meta, index, ZRAM_ZERO)) { + read_unlock(&meta->tb_lock); clear_page(mem); return 0; } cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_RO); - if (meta->table[index].size == PAGE_SIZE) + if (size == PAGE_SIZE) copy_page(mem, cmem); else - ret = lzo1x_decompress_safe(cmem, meta->table[index].size, - mem, &clen); + ret = lzo1x_decompress_safe(cmem, size, mem, &clen); zs_unmap_object(meta->mem_pool, handle); + read_unlock(&meta->tb_lock); /* Should NEVER happen. Return bio error if it does. */ if (unlikely(ret != LZO_E_OK)) { @@ -353,11 +363,14 @@ 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); if (unlikely(!meta->table[index].handle) || zram_test_flag(meta, index, ZRAM_ZERO)) { + read_unlock(&meta->tb_lock); handle_zero_page(bvec); return 0; } + read_unlock(&meta->tb_lock); if (is_partial_io(bvec)) /* Use a temporary buffer to decompress the page */ @@ -400,6 +413,7 @@ 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; + bool locked = false; page = bvec->bv_page; src = meta->compress_buffer; @@ -419,6 +433,8 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index, goto out; } + mutex_lock(&meta->buffer_lock); + locked = true; user_mem = kmap_atomic(page); if (is_partial_io(bvec)) { @@ -433,25 +449,18 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index, if (page_zero_filled(uncmem)) { kunmap_atomic(user_mem); /* Free memory associated with this sector now. */ + write_lock(&zram->meta->tb_lock); zram_free_page(zram, index); - - zram->stats.pages_zero++; zram_set_flag(meta, index, ZRAM_ZERO); + write_unlock(&zram->meta->tb_lock); + + atomic_inc(&zram->stats.pages_zero); ret = 0; goto out; } - /* - * zram_slot_free_notify could miss free so that let's - * double check. - */ - if (unlikely(meta->table[index].handle || - zram_test_flag(meta, index, ZRAM_ZERO))) - zram_free_page(zram, index); - ret = lzo1x_1_compress(uncmem, PAGE_SIZE, src, &clen, meta->compress_workmem); - if (!is_partial_io(bvec)) { kunmap_atomic(user_mem); user_mem = NULL; @@ -464,7 +473,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index, } if (unlikely(clen > max_zpage_size)) { - zram->stats.bad_compress++; + atomic_inc(&zram->stats.bad_compress); clen = PAGE_SIZE; src = NULL; if (is_partial_io(bvec)) @@ -494,18 +503,22 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index, * Free memory associated with this sector * before overwriting unused sectors. */ + write_lock(&zram->meta->tb_lock); zram_free_page(zram, index); meta->table[index].handle = handle; meta->table[index].size = clen; + write_unlock(&zram->meta->tb_lock); /* Update stats */ atomic64_add(clen, &zram->stats.compr_size); - zram->stats.pages_stored++; + atomic_inc(&zram->stats.pages_stored); if (clen <= PAGE_SIZE / 2) - zram->stats.good_compress++; + atomic_inc(&zram->stats.good_compress); out: + if (locked) + mutex_unlock(&meta->buffer_lock); if (is_partial_io(bvec)) kfree(uncmem); @@ -514,36 +527,15 @@ out: return ret; } -static void handle_pending_slot_free(struct zram *zram) -{ - struct zram_slot_free *free_rq; - - spin_lock(&zram->slot_free_lock); - while (zram->slot_free_rq) { - free_rq = zram->slot_free_rq; - zram->slot_free_rq = free_rq->next; - zram_free_page(zram, free_rq->index); - kfree(free_rq); - } - spin_unlock(&zram->slot_free_lock); -} - 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); - handle_pending_slot_free(zram); + if (rw == READ) ret = zram_bvec_read(zram, bvec, index, offset, bio); - up_read(&zram->lock); - } else { - down_write(&zram->lock); - handle_pending_slot_free(zram); + else ret = zram_bvec_write(zram, bvec, index, offset); - up_write(&zram->lock); - } return ret; } @@ -553,8 +545,6 @@ static void zram_reset_device(struct zram *zram, bool reset_capacity) size_t index; struct zram_meta *meta; - flush_work(&zram->free_work); - down_write(&zram->init_lock); if (!zram->init_done) { up_write(&zram->init_lock); @@ -762,40 +752,19 @@ error: bio_io_error(bio); } -static void zram_slot_free(struct work_struct *work) -{ - struct zram *zram; - - zram = container_of(work, struct zram, free_work); - down_write(&zram->lock); - handle_pending_slot_free(zram); - up_write(&zram->lock); -} - -static void add_slot_free(struct zram *zram, struct zram_slot_free *free_rq) -{ - spin_lock(&zram->slot_free_lock); - free_rq->next = zram->slot_free_rq; - zram->slot_free_rq = free_rq; - spin_unlock(&zram->slot_free_lock); -} - static void zram_slot_free_notify(struct block_device *bdev, unsigned long index) { struct zram *zram; - struct zram_slot_free *free_rq; + struct zram_meta *meta; zram = bdev->bd_disk->private_data; - atomic64_inc(&zram->stats.notify_free); - - free_rq = kmalloc(sizeof(struct zram_slot_free), GFP_ATOMIC); - if (!free_rq) - return; + meta = zram->meta; - free_rq->index = index; - add_slot_free(zram, free_rq); - schedule_work(&zram->free_work); + write_lock(&meta->tb_lock); + zram_free_page(zram, index); + write_unlock(&meta->tb_lock); + atomic64_inc(&zram->stats.notify_free); } static const struct block_device_operations zram_devops = { @@ -839,13 +808,8 @@ static int create_device(struct zram *zram, int device_id) { int ret = -ENOMEM; - init_rwsem(&zram->lock); init_rwsem(&zram->init_lock); - INIT_WORK(&zram->free_work, zram_slot_free); - spin_lock_init(&zram->slot_free_lock); - zram->slot_free_rq = NULL; - zram->queue = blk_alloc_queue(GFP_KERNEL); if (!zram->queue) { pr_err("Error allocating disk queue for device %d\n", diff --git a/drivers/staging/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 97a3acf..ad8aa35 100644 --- a/drivers/staging/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -2,6 +2,7 @@ * Compressed RAM block device * * Copyright (C) 2008, 2009, 2010 Nitin Gupta + * 2012, 2013 Minchan Kim * * This code is released using a dual license strategy: BSD/GPL * You can choose the licence that better fits your requirements. @@ -9,7 +10,6 @@ * 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_ @@ -17,8 +17,7 @@ #include <linux/spinlock.h> #include <linux/mutex.h> - -#include "../zsmalloc/zsmalloc.h" +#include <linux/zsmalloc.h> /* * Some arbitrary value. This is just to catch @@ -69,10 +68,6 @@ struct table { 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 */ @@ -81,33 +76,23 @@ struct zram_stats { 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% */ + 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% */ }; struct zram_meta { + rwlock_t tb_lock; /* protect table */ void *compress_workmem; void *compress_buffer; struct table *table; struct zs_pool *mem_pool; -}; - -struct zram_slot_free { - unsigned long index; - struct zram_slot_free *next; + struct mutex buffer_lock; /* protect compress buffers */ }; struct zram { struct zram_meta *meta; - struct rw_semaphore lock; /* protect compression buffers, table, - * 32bit stat counters against concurrent - * notifications, reads and writes */ - - struct work_struct free_work; /* handle pending free request */ - struct zram_slot_free *slot_free_rq; /* list head of free request */ - struct request_queue *queue; struct gendisk *disk; int init_done; @@ -118,7 +103,6 @@ struct zram { * we can store in a disk. */ u64 disksize; /* bytes */ - spinlock_t slot_free_lock; struct zram_stats stats; }; diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 930694d..71e4900 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -150,6 +150,7 @@ int mdiobus_register(struct mii_bus *bus) err = device_register(&bus->dev); if (err) { pr_err("mii_bus %s failed to register\n", bus->id); + put_device(&bus->dev); return -EINVAL; } diff --git a/drivers/staging/Kconfig b/drivers/staging/Kconfig index 4bb6b11..040a515 100644 --- a/drivers/staging/Kconfig +++ b/drivers/staging/Kconfig @@ -76,10 +76,6 @@ 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 9f07e5e..dea056b 100644 --- a/drivers/staging/Makefile +++ b/drivers/staging/Makefile @@ -32,8 +32,6 @@ 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/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/zsmalloc/Kconfig b/drivers/staging/zsmalloc/Kconfig deleted file mode 100644 index 9d1f2a2..0000000 --- a/drivers/staging/zsmalloc/Kconfig +++ /dev/null @@ -1,24 +0,0 @@ -config ZSMALLOC - bool "Memory allocator for compressed pages" - depends on MMU - 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. - -config PGTABLE_MAPPING - bool "Use page table mapping to access object in zsmalloc" - depends on ZSMALLOC - help - By default, zsmalloc uses a copy-based object mapping method to - access allocations that span two pages. However, if a particular - architecture (ex, ARM) performs VM mapping faster than copying, - then you should select this. This causes zsmalloc to use page table - mapping rather than copying for object mapping. - - You can check speed with zsmalloc benchmark[1]. - [1] https://github.com/spartacus06/zsmalloc 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 7660c87..0000000 --- a/drivers/staging/zsmalloc/zsmalloc-main.c +++ /dev/null @@ -1,1106 +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 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. - * - * For simplicity, zsmalloc can only allocate objects of size up to PAGE_SIZE - * since this satisfies the requirements of all its current users (in the - * worst case, page is incompressible and is thus stored "as-is" i.e. in - * uncompressed form). For allocation requests larger than this size, failure - * is returned (see zs_malloc). - * - * Additionally, zs_malloc() does not return a dereferenceable pointer. - * Instead, it returns an opaque handle (unsigned long) which encodes actual - * location of the allocated object. The reason for this indirection is that - * zsmalloc does not keep zspages permanently mapped since that would cause - * issues on 32-bit systems where the VA region for kernel space mappings - * is very small. So, before using the allocating memory, the object has to - * be mapped using zs_map_object() to get a usable pointer and subsequently - * unmapped using zs_unmap_object(). - * - * 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/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 (unsigned long) 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) - -struct mapping_area { -#ifdef CONFIG_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; -} - -/* - * zsmalloc divides the pool into various size classes where each - * class maintains a list of zspages where each zspage is divided - * into equal sized chunks. Each allocation falls into one of these - * classes depending on its size. This function returns index of the - * size class which has chunk size big enough to hold the give size. - */ -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; -} - -/* - * For each size class, zspages are divided into different groups - * depending on how "full" they are. This was done so that we could - * easily find empty or nearly empty zspages when we try to shrink - * the pool (not yet implemented). This function returns fullness - * status of the given page. - */ -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; -} - -/* - * Each size class maintains various freelists and zspages are assigned - * to one of these freelists based on the number of live objects they - * have. This functions inserts the given zspage into the freelist - * identified by <class, fullness_group>. - */ -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; -} - -/* - * This function removes the given zspage from the freelist identified - * by <class, fullness_group>. - */ -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); -} - -/* - * Each size class maintains zspages in different fullness groups depending - * on the number of live objects they contain. When allocating or freeing - * objects, the fullness status of the page can change, say, from ALMOST_FULL - * to ALMOST_EMPTY when freeing an object. This function checks if such - * a status change has occurred for the given page and accordingly moves the - * page from the freelist of the old fullness group to that of the new - * fullness group. - */ -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(page); - else - next = list_entry(page->lru.next, struct page, lru); - - return next; -} - -/* - * Encode <page, obj_idx> as a single handle value. - * On hardware platforms with physical memory starting at 0x0 the pfn - * could be 0 so we ensure that the handle will never be 0 by adjusting the - * encoded obj_idx value before encoding. - */ -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 + 1) & OBJ_INDEX_MASK); - - return (void *)handle; -} - -/* - * Decode <page, obj_idx> pair from the given object handle. We adjust the - * decoded obj_idx back to its original value since it was adjusted in - * obj_location_to_handle(). - */ -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) - 1; -} - -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) - set_page_private(first_page, (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 CONFIG_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 /* CONFIG_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 /* CONFIG_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 c2eb174..0000000 --- a/drivers/staging/zsmalloc/zsmalloc.h +++ /dev/null @@ -1,50 +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. - * They also have no effect when PGTABLE_MAPPING is selected. - */ -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) */ - /* - * NOTE: ZS_MM_WO should only be used for initializing new - * (uninitialized) allocations. Partial writes to already - * initialized allocations should use ZS_MM_RW to preserve the - * existing data. - */ -}; - -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/drivers/video/backlight/lcd.c b/drivers/video/backlight/lcd.c index 93cf15e..7de847d 100644 --- a/drivers/video/backlight/lcd.c +++ b/drivers/video/backlight/lcd.c @@ -228,7 +228,7 @@ struct lcd_device *lcd_device_register(const char *name, struct device *parent, rc = device_register(&new_ld->dev); if (rc) { - kfree(new_ld); + put_device(&new_ld->dev); return ERR_PTR(rc); } |