zram: promote zram from staging

Zram has lived in staging for a LONG LONG time and have been
fixed/improved by many contributors so code is clean and stable now.  Of
course, there are lots of product using zram in real practice.

The major TV companys have used zram as swap since two years ago and
recently our production team released android smart phone with zram
which is used as swap, too and recently Android Kitkat start to use zram
for small memory smart phone.  And there was a report Google released
their ChromeOS with zram, too and cyanogenmod have been used zram long
time ago.  And I heard some disto have used zram block device for tmpfs.
In addition, I saw many report from many other peoples.  For example,
Lubuntu start to use it.

The benefit of zram is very clear.  With my experience, one of the
benefit was to remove jitter of video application with backgroud memory
pressure.  It would be effect of efficient memory usage by compression
but more issue is whether swap is there or not in the system.  Recent
mobile platforms have used JAVA so there are many anonymous pages.  But
embedded system normally are reluctant to use eMMC or SDCard as swap
because there is wear-leveling and latency issues so if we do not use
swap, it means we can't reclaim anoymous pages and at last, we could
encounter OOM kill.  :(

Although we have real storage as swap, it was a problem, too.  Because
it sometime ends up making system very unresponsible caused by slow swap
storage performance.

Quote from Luigi on Google
 "Since Chrome OS was mentioned: the main reason why we don't use swap
  to a disk (rotating or SSD) is because it doesn't degrade gracefully
  and leads to a bad interactive experience.  Generally we prefer to
  manage RAM at a higher level, by transparently killing and restarting
  processes.  But we noticed that zram is fast enough to be competitive
  with the latter, and it lets us make more efficient use of the
  available RAM.  " and he announced.
http://www.spinics.net/lists/linux-mm/msg57717.html

Other uses case is to use zram for block device.  Zram is block device
so anyone can format the block device and mount on it so some guys on
the internet start zram as /var/tmp.
http://forums.gentoo.org/viewtopic-t-838198-start-0.html

Let's promote zram and enhance/maintain it instead of removing.

Signed-off-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Nitin Gupta <ngupta@vflare.org>
Acked-by: Pekka Enberg <penberg@kernel.org>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Seth Jennings <sjenning@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 124 insertions, 0 deletions

diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
new file mode 100644
index 000000000000..d8f6596513c3
--- /dev/null
+++ b/drivers/block/zram/zram_drv.h
@@ -0,0 +1,124 @@
+/*
+ * Compressed RAM block device
+ *
+ * Copyright (C) 2008, 2009, 2010  Nitin Gupta
+ *
+ * This code is released using a dual license strategy: BSD/GPL
+ * You can choose the licence that better fits your requirements.
+ *
+ * Released under the terms of 3-clause BSD License
+ * Released under the terms of GNU General Public License Version 2.0
+ *
+ * Project home: http://compcache.googlecode.com
+ */
+
+#ifndef _ZRAM_DRV_H_
+#define _ZRAM_DRV_H_
+
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+#include <linux/zsmalloc.h>
+
+/*
+ * Some arbitrary value. This is just to catch
+ * invalid value for num_devices module parameter.
+ */
+static const unsigned max_num_devices = 32;
+
+/*-- Configurable parameters */
+
+/*
+ * Pages that compress to size greater than this are stored
+ * uncompressed in memory.
+ */
+static const size_t max_zpage_size = PAGE_SIZE / 4 * 3;
+
+/*
+ * NOTE: max_zpage_size must be less than or equal to:
+ *   ZS_MAX_ALLOC_SIZE. Otherwise, zs_malloc() would
+ * always return failure.
+ */
+
+/*-- End of configurable params */
+
+#define SECTOR_SHIFT		9
+#define SECTOR_SIZE		(1 << SECTOR_SHIFT)
+#define SECTORS_PER_PAGE_SHIFT	(PAGE_SHIFT - SECTOR_SHIFT)
+#define SECTORS_PER_PAGE	(1 << SECTORS_PER_PAGE_SHIFT)
+#define ZRAM_LOGICAL_BLOCK_SHIFT 12
+#define ZRAM_LOGICAL_BLOCK_SIZE	(1 << ZRAM_LOGICAL_BLOCK_SHIFT)
+#define ZRAM_SECTOR_PER_LOGICAL_BLOCK	\
+	(1 << (ZRAM_LOGICAL_BLOCK_SHIFT - SECTOR_SHIFT))
+
+/* Flags for zram pages (table[page_no].flags) */
+enum zram_pageflags {
+	/* Page consists entirely of zeros */
+	ZRAM_ZERO,
+
+	__NR_ZRAM_PAGEFLAGS,
+};
+
+/*-- Data structures */
+
+/* Allocated for each disk page */
+struct table {
+	unsigned long handle;
+	u16 size;	/* object size (excluding header) */
+	u8 count;	/* object ref count (not yet used) */
+	u8 flags;
+} __aligned(4);
+
+/*
+ * All 64bit fields should only be manipulated by 64bit atomic accessors.
+ * All modifications to 32bit counter should be protected by zram->lock.
+ */
+struct zram_stats {
+	atomic64_t compr_size;	/* compressed size of pages stored */
+	atomic64_t num_reads;	/* failed + successful */
+	atomic64_t num_writes;	/* --do-- */
+	atomic64_t failed_reads;	/* should NEVER! happen */
+	atomic64_t failed_writes;	/* can happen when memory is too low */
+	atomic64_t invalid_io;	/* non-page-aligned I/O requests */
+	atomic64_t notify_free;	/* no. of swap slot free notifications */
+	u32 pages_zero;		/* no. of zero filled pages */
+	u32 pages_stored;	/* no. of pages currently stored */
+	u32 good_compress;	/* % of pages with compression ratio<=50% */
+	u32 bad_compress;	/* % of pages with compression ratio>=75% */
+};
+
+struct zram_meta {
+	void *compress_workmem;
+	void *compress_buffer;
+	struct table *table;
+	struct zs_pool *mem_pool;
+};
+
+struct zram_slot_free {
+	unsigned long index;
+	struct zram_slot_free *next;
+};
+
+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;
+	/* Prevent concurrent execution of device init, reset and R/W request */
+	struct rw_semaphore init_lock;
+	/*
+	 * This is the limit on amount of *uncompressed* worth of data
+	 * we can store in a disk.
+	 */
+	u64 disksize;	/* bytes */
+	spinlock_t slot_free_lock;
+
+	struct zram_stats stats;
+};
+#endif