zram/zcomp: use GFP_NOIO to allocate streams

We can end up allocating a new compression stream with GFP_KERNEL from
within the IO path, which may result is nested (recursive) IO
operations.  That can introduce problems if the IO path in question is a
reclaimer, holding some locks that will deadlock nested IOs.

Allocate streams and working memory using GFP_NOIO flag, forbidding
recursive IO and FS operations.

An example:

  inconsistent {IN-RECLAIM_FS-W} -> {RECLAIM_FS-ON-W} usage.
  git/20158 [HC0[0]:SC0[0]:HE1:SE1] takes:
   (jbd2_handle){+.+.?.}, at:  start_this_handle+0x4ca/0x555
  {IN-RECLAIM_FS-W} state was registered at:
     __lock_acquire+0x8da/0x117b
     lock_acquire+0x10c/0x1a7
     start_this_handle+0x52d/0x555
     jbd2__journal_start+0xb4/0x237
     __ext4_journal_start_sb+0x108/0x17e
     ext4_dirty_inode+0x32/0x61
     __mark_inode_dirty+0x16b/0x60c
     iput+0x11e/0x274
     __dentry_kill+0x148/0x1b8
     shrink_dentry_list+0x274/0x44a
     prune_dcache_sb+0x4a/0x55
     super_cache_scan+0xfc/0x176
     shrink_slab.part.14.constprop.25+0x2a2/0x4d3
     shrink_zone+0x74/0x140
     kswapd+0x6b7/0x930
     kthread+0x107/0x10f
     ret_from_fork+0x3f/0x70
  irq event stamp: 138297
  hardirqs last  enabled at (138297):  debug_check_no_locks_freed+0x113/0x12f
  hardirqs last disabled at (138296):  debug_check_no_locks_freed+0x33/0x12f
  softirqs last  enabled at (137818):  __do_softirq+0x2d3/0x3e9
  softirqs last disabled at (137813):  irq_exit+0x41/0x95

               other info that might help us debug this:
   Possible unsafe locking scenario:
         CPU0
         ----
    lock(jbd2_handle);
    <Interrupt>
      lock(jbd2_handle);

                *** DEADLOCK ***
  5 locks held by git/20158:
   #0:  (sb_writers#7){.+.+.+}, at: [<ffffffff81155411>] mnt_want_write+0x24/0x4b
   #1:  (&type->i_mutex_dir_key#2/1){+.+.+.}, at: [<ffffffff81145087>] lock_rename+0xd9/0xe3
   #2:  (&sb->s_type->i_mutex_key#11){+.+.+.}, at: [<ffffffff8114f8e2>] lock_two_nondirectories+0x3f/0x6b
   #3:  (&sb->s_type->i_mutex_key#11/4){+.+.+.}, at: [<ffffffff8114f909>] lock_two_nondirectories+0x66/0x6b
   #4:  (jbd2_handle){+.+.?.}, at: [<ffffffff811e31db>] start_this_handle+0x4ca/0x555

               stack backtrace:
  CPU: 2 PID: 20158 Comm: git Not tainted 4.1.0-rc7-next-20150615-dbg-00016-g8bdf555-dirty #211
  Call Trace:
    dump_stack+0x4c/0x6e
    mark_lock+0x384/0x56d
    mark_held_locks+0x5f/0x76
    lockdep_trace_alloc+0xb2/0xb5
    kmem_cache_alloc_trace+0x32/0x1e2
    zcomp_strm_alloc+0x25/0x73 [zram]
    zcomp_strm_multi_find+0xe7/0x173 [zram]
    zcomp_strm_find+0xc/0xe [zram]
    zram_bvec_rw+0x2ca/0x7e0 [zram]
    zram_make_request+0x1fa/0x301 [zram]
    generic_make_request+0x9c/0xdb
    submit_bio+0xf7/0x120
    ext4_io_submit+0x2e/0x43
    ext4_bio_write_page+0x1b7/0x300
    mpage_submit_page+0x60/0x77
    mpage_map_and_submit_buffers+0x10f/0x21d
    ext4_writepages+0xc8c/0xe1b
    do_writepages+0x23/0x2c
    __filemap_fdatawrite_range+0x84/0x8b
    filemap_flush+0x1c/0x1e
    ext4_alloc_da_blocks+0xb8/0x117
    ext4_rename+0x132/0x6dc
    ? mark_held_locks+0x5f/0x76
    ext4_rename2+0x29/0x2b
    vfs_rename+0x540/0x636
    SyS_renameat2+0x359/0x44d
    SyS_rename+0x1e/0x20
    entry_SYSCALL_64_fastpath+0x12/0x6f

[minchan@kernel.org: add stable mark]
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: Kyeongdon Kim <kyeongdon.kim@lge.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c
index 5cb13ca3a3acac2aa16a104e9731770066ff03de..c53617752b93cc3976f764e19cc436b5cb66cdcf 100644 (file)
--- a/drivers/block/zram/zcomp.c
+++ b/drivers/block/zram/zcomp.c
@@ -76,7 +76,7 @@ static void zcomp_strm_free(struct zcomp *comp, struct zcomp_strm *zstrm)
  */
 static struct zcomp_strm *zcomp_strm_alloc(struct zcomp *comp)
 {
-       struct zcomp_strm *zstrm = kmalloc(sizeof(*zstrm), GFP_KERNEL);
+       struct zcomp_strm *zstrm = kmalloc(sizeof(*zstrm), GFP_NOIO);
        if (!zstrm)
                return NULL;
 
@@ -85,7 +85,7 @@ static struct zcomp_strm *zcomp_strm_alloc(struct zcomp *comp)
         * 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);
+       zstrm->buffer = (void *)__get_free_pages(GFP_NOIO | __GFP_ZERO, 1);
        if (!zstrm->private || !zstrm->buffer) {
                zcomp_strm_free(comp, zstrm);
                zstrm = NULL;

diff --git a/drivers/block/zram/zcomp_lz4.c b/drivers/block/zram/zcomp_lz4.c
index f2afb7e988c3776fa557e9fa4a4945e9d55f0b29..ee44b51130a45c49bc4325fb3c9ea62eeec774c5 100644 (file)
--- a/drivers/block/zram/zcomp_lz4.c
+++ b/drivers/block/zram/zcomp_lz4.c
@@ -15,7 +15,7 @@
 
 static void *zcomp_lz4_create(void)
 {
-       return kzalloc(LZ4_MEM_COMPRESS, GFP_KERNEL);
+       return kzalloc(LZ4_MEM_COMPRESS, GFP_NOIO);
 }
 
 static void zcomp_lz4_destroy(void *private)

diff --git a/drivers/block/zram/zcomp_lzo.c b/drivers/block/zram/zcomp_lzo.c
index da1bc47d588e94c9843966c3bb9295515187d79d..683ce049e07040e80626247e31508baa96bcafde 100644 (file)
--- a/drivers/block/zram/zcomp_lzo.c
+++ b/drivers/block/zram/zcomp_lzo.c
@@ -15,7 +15,7 @@
 
 static void *lzo_create(void)
 {
-       return kzalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL);
+       return kzalloc(LZO1X_MEM_COMPRESS, GFP_NOIO);
 }
 
 static void lzo_destroy(void *private)