linux-stable.git/drivers/block/zram, branch v4.0

zram: use proper type to update max_used_pages

2015-02-28T17:57:51+00:00

max_used_pages is defined as atomic_long_t so we need to use unsigned
long to keep temporary value for it rather than int which is smaller
than unsigned long in a 64 bit system.

Signed-off-by: Joonsoo Kim 
Cc: Minchan Kim 
Cc: Jerome Marchand 
Cc: Nitin Gupta 
Cc: Sergey Senozhatsky 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm/zpool: add name argument to create zpool

2015-02-13T02:54:12+00:00

Currently the underlay of zpool: zsmalloc/zbud, do not know who creates
them.  There is not a method to let zsmalloc/zbud find which caller they
belong to.

Now we want to add statistics collection in zsmalloc.  We need to name the
debugfs dir for each pool created.  The way suggested by Minchan Kim is to
use a name passed by caller(such as zram) to create the zsmalloc pool.

    /sys/kernel/debug/zsmalloc/zram0

This patch adds an argument `name' to zs_create_pool() and other related
functions.

Signed-off-by: Ganesh Mahendran 
Acked-by: Minchan Kim 
Cc: Seth Jennings 
Cc: Nitin Gupta 
Cc: Dan Streetman 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

zram: remove request_queue from struct zram

2015-02-13T02:54:12+00:00

`struct zram' contains both `struct gendisk' and `struct request_queue'.
the latter can be deleted, because zram->disk carries ->queue pointer, and
->queue carries zram pointer:

create_device()
	zram->queue->queuedata = zram
	zram->disk->queue = zram->queue
	zram->disk->private_data = zram

so zram->queue is not needed, we can access all necessary data anyway.

Signed-off-by: Sergey Senozhatsky 
Cc: Minchan Kim 
Cc: Jerome Marchand 
Cc: Nitin Gupta 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

zram: remove init_lock in zram_make_request

2015-02-13T02:54:12+00:00

Admin could reset zram during I/O operation going on so we have used
zram->init_lock as read-side lock in I/O path to prevent sudden zram
meta freeing.

However, the init_lock is really troublesome.  We can't do call
zram_meta_alloc under init_lock due to lockdep splat because
zram_rw_page is one of the function under reclaim path and hold it as
read_lock while other places in process context hold it as write_lock.
So, we have used allocation out of the lock to avoid lockdep warn but
it's not good for readability and fainally, I met another lockdep splat
between init_lock and cpu_hotplug from kmem_cache_destroy during working
zsmalloc compaction.  :(

Yes, the ideal is to remove horrible init_lock of zram in rw path.  This
patch removes it in rw path and instead, add atomic refcount for meta
lifetime management and completion to free meta in process context.
It's important to free meta in process context because some of resource
destruction needs mutex lock, which could be held if we releases the
resource in reclaim context so it's deadlock, again.

As a bonus, we could remove init_done check in rw path because
zram_meta_get will do a role for it, instead.

Signed-off-by: Sergey Senozhatsky 
Signed-off-by: Minchan Kim 
Cc: Nitin Gupta 
Cc: Jerome Marchand 
Cc: Ganesh Mahendran 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

zram: check bd_openers instead of bd_holders

2015-02-13T02:54:11+00:00

bd_holders is increased only when user open the device file as FMODE_EXCL
so if something opens zram0 as !FMODE_EXCL and request I/O while another
user reset zram0, we can see following warning.

  zram0: detected capacity change from 0 to 64424509440
  Buffer I/O error on dev zram0, logical block 180823, lost async page write
  Buffer I/O error on dev zram0, logical block 180824, lost async page write
  Buffer I/O error on dev zram0, logical block 180825, lost async page write
  Buffer I/O error on dev zram0, logical block 180826, lost async page write
  Buffer I/O error on dev zram0, logical block 180827, lost async page write
  Buffer I/O error on dev zram0, logical block 180828, lost async page write
  Buffer I/O error on dev zram0, logical block 180829, lost async page write
  Buffer I/O error on dev zram0, logical block 180830, lost async page write
  Buffer I/O error on dev zram0, logical block 180831, lost async page write
  Buffer I/O error on dev zram0, logical block 180832, lost async page write
  ------------[ cut here ]------------
  WARNING: CPU: 11 PID: 1996 at fs/block_dev.c:57 __blkdev_put+0x1d7/0x210()
  Modules linked in:
  CPU: 11 PID: 1996 Comm: dd Not tainted 3.19.0-rc6-next-20150202+ #1125
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
  Call Trace:
    dump_stack+0x45/0x57
    warn_slowpath_common+0x8a/0xc0
    warn_slowpath_null+0x1a/0x20
    __blkdev_put+0x1d7/0x210
    blkdev_put+0x50/0x130
    blkdev_close+0x25/0x30
    __fput+0xdf/0x1e0
    ____fput+0xe/0x10
    task_work_run+0xa7/0xe0
    do_notify_resume+0x49/0x60
    int_signal+0x12/0x17
  ---[ end trace 274fbbc5664827d2 ]---

The warning comes from bdev_write_node in blkdev_put path.

   static void bdev_write_inode(struct inode *inode)
   {
        spin_lock(&inode->i_lock);
        while (inode->i_state & I_DIRTY) {
                spin_unlock(&inode->i_lock);
                WARN_ON_ONCE(write_inode_now(inode, true)); <========= here.
                spin_lock(&inode->i_lock);
        }
        spin_unlock(&inode->i_lock);
   }

The reason is dd process encounters I/O fails due to sudden block device
disappear so in filemap_check_errors in __writeback_single_inode returns
-EIO.

If we check bd_openers instead of bd_holders, we could address the
problem.  When I see the brd, it already have used it rather than
bd_holders so although I'm not a expert of block layer, it seems to be
better.

I can make following warning with below simple script.  In addition, I
added msleep(2000) below set_capacity(zram->disk, 0) after applying your
patch to make window huge(Kudos to Ganesh!)

script:

   echo $((60<<30)) > /sys/block/zram0/disksize
   setsid dd if=/dev/zero of=/dev/zram0 &
   sleep 1
   setsid echo 1 > /sys/block/zram0/reset

Signed-off-by: Minchan Kim 
Acked-by: Sergey Senozhatsky 
Cc: Nitin Gupta 
Cc: Jerome Marchand 
Cc: Ganesh Mahendran 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

zram: rework reset and destroy path

2015-02-13T02:54:11+00:00

We need to return set_capacity(disk, 0) from reset_store() back to
zram_reset_device(), a catch by Ganesh Mahendran.  Potentially, we can
race set_capacity() calls from init and reset paths.

The problem is that zram_reset_device() is also getting called from
zram_exit(), which performs operations in misleading reversed order -- we
first create_device() and then init it, while zram_exit() perform
destroy_device() first and then does zram_reset_device().  This is done to
remove sysfs group before we reset device, so we can continue with device
reset/destruction not being raced by sysfs attr write (f.e.  disksize).

Apart from that, destroy_device() releases zram->disk (but we still have
->disk pointer), so we cannot acces zram->disk in later
zram_reset_device() call, which may cause additional errors in the future.

So, this patch rework and cleanup destroy path.

1) remove several unneeded goto labels in zram_init()

2) factor out zram_init() error path and zram_exit() into
   destroy_devices() function, which takes the number of devices to
   destroy as its argument.

3) remove sysfs group in destroy_devices() first, so we can reorder
   operations -- reset device (as expected) goes before disk destroy and
   queue cleanup.  So we can always access ->disk in zram_reset_device().

4) and, finally, return set_capacity() back under ->init_lock.

[akpm@linux-foundation.org: tweak comment]
Signed-off-by: Sergey Senozhatsky 
Reported-by: Ganesh Mahendran 
Cc: Minchan Kim 
Cc: Jerome Marchand 
Cc: Nitin Gupta 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

zram: fix umount-reset_store-mount race condition

2015-02-13T02:54:11+00:00

Ganesh Mahendran was the first one who proposed to use bdev->bd_mutex to
avoid ->bd_holders race condition:

        CPU0                            CPU1
umount /* zram->init_done is true */
reset_store()
bdev->bd_holders == 0                   mount
...                                     zram_make_request()
zram_reset_device()

However, his solution required some considerable amount of code movement,
which we can avoid.

Apart from using bdev->bd_mutex in reset_store(), this patch also
simplifies zram_reset_device().

zram_reset_device() has a bool parameter reset_capacity which tells it
whether disk capacity and itself disk should be reset.  There are two
zram_reset_device() callers:

-- zram_exit() passes reset_capacity=false
-- reset_store() passes reset_capacity=true

So we can move reset_capacity-sensitive work out of zram_reset_device()
and perform it unconditionally in reset_store().  This also lets us drop
reset_capacity parameter from zram_reset_device() and pass zram pointer
only.

Signed-off-by: Sergey Senozhatsky 
Reported-by: Ganesh Mahendran 
Cc: Minchan Kim 
Cc: Vlastimil Babka 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

zram: free meta table in zram_meta_free

2015-02-13T02:54:11+00:00

zram_meta_alloc() and zram_meta_free() are a pair.  In
zram_meta_alloc(), meta table is allocated.  So it it better to free it
in zram_meta_free().

Signed-off-by: Ganesh Mahendran 
Acked-by: Minchan Kim 
Acked-by: Sergey Senozhatsky 
Cc: Nitin Gupta 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

zram: clean up zram_meta_alloc()

2015-02-13T02:54:11+00:00

A trivial cleanup of zram_meta_alloc() error handling.

Signed-off-by: Sergey Senozhatsky 
Acked-by: Minchan Kim 
Cc: Nitin Gupta 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

zram: use DEVICE_ATTR_[RW|RO|WO] to define zram sys device attribute

2014-12-13T20:42:50+00:00

In current zram, we use DEVICE_ATTR() to define sys device attributes.
SO, we need to set (S_IRUGO | S_IWUSR) permission and other arguments
manually.  Linux already provids the macro DEVICE_ATTR_[RW|RO|WO] to
define sys device attribute.  It is simple and readable.

This patch uses kernel defined macro DEVICE_ATTR_[RW|RO|WO] to define
zram device attribute.

Signed-off-by: Ganesh Mahendran 
Acked-by: Jerome Marchand 
Cc: Minchan Kim 
Cc: Nitin Gupta 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds