Revision b1dd693e5b9348bd68a80e679e03cf9c0973b01b authored by Daisuke Nishimura on 24 November 2010, 20:57:06 UTC, committed by Linus Torvalds on 24 November 2010, 21:50:44 UTC
__mem_cgroup_try_charge() can be called under down_write(&mmap_sem)(e.g.
mlock does it). This means it can cause deadlock if it races with move charge:

Ex.1)
                move charge             |        try charge
  --------------------------------------+------------------------------
    mem_cgroup_can_attach()             |  down_write(&mmap_sem)
      mc.moving_task = current          |    ..
      mem_cgroup_precharge_mc()         |  __mem_cgroup_try_charge()
        mem_cgroup_count_precharge()    |    prepare_to_wait()
          down_read(&mmap_sem)          |    if (mc.moving_task)
          -> cannot aquire the lock     |    -> true
                                        |      schedule()

Ex.2)
                move charge             |        try charge
  --------------------------------------+------------------------------
    mem_cgroup_can_attach()             |
      mc.moving_task = current          |
      mem_cgroup_precharge_mc()         |
        mem_cgroup_count_precharge()    |
          down_read(&mmap_sem)          |
          ..                            |
          up_read(&mmap_sem)            |
                                        |  down_write(&mmap_sem)
    mem_cgroup_move_task()              |    ..
      mem_cgroup_move_charge()          |  __mem_cgroup_try_charge()
        down_read(&mmap_sem)            |    prepare_to_wait()
        -> cannot aquire the lock       |    if (mc.moving_task)
                                        |    -> true
                                        |      schedule()

To avoid this deadlock, we do all the move charge works (both can_attach() and
attach()) under one mmap_sem section.
And after this patch, we set/clear mc.moving_task outside mc.lock, because we
use the lock only to check mc.from/to.

Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 11e7946
History
File Mode Size
auth_gss
xprtrdma
Kconfig -rw-r--r-- 1004 bytes
Makefile -rw-r--r-- 541 bytes
addr.c -rw-r--r-- 8.7 KB
auth.c -rw-r--r-- 15.4 KB
auth_generic.c -rw-r--r-- 4.5 KB
auth_null.c -rw-r--r-- 2.5 KB
auth_unix.c -rw-r--r-- 5.5 KB
backchannel_rqst.c -rw-r--r-- 8.8 KB
bc_svc.c -rw-r--r-- 2.0 KB
cache.c -rw-r--r-- 42.3 KB
clnt.c -rw-r--r-- 44.2 KB
netns.h -rw-r--r-- 353 bytes
rpc_pipe.c -rw-r--r-- 24.7 KB
rpcb_clnt.c -rw-r--r-- 26.5 KB
sched.c -rw-r--r-- 24.0 KB
socklib.c -rw-r--r-- 4.5 KB
stats.c -rw-r--r-- 6.8 KB
sunrpc.h -rw-r--r-- 1.7 KB
sunrpc_syms.c -rw-r--r-- 2.2 KB
svc.c -rw-r--r-- 30.7 KB
svc_xprt.c -rw-r--r-- 33.1 KB
svcauth.c -rw-r--r-- 3.8 KB
svcauth_unix.c -rw-r--r-- 22.1 KB
svcsock.c -rw-r--r-- 40.0 KB
sysctl.c -rw-r--r-- 3.5 KB
timer.c -rw-r--r-- 2.9 KB
xdr.c -rw-r--r-- 28.2 KB
xprt.c -rw-r--r-- 31.0 KB
xprtsock.c -rw-r--r-- 65.4 KB

back to top