On 08/25/2014 02:48 PM, NeilBrown wrote: > On Fri, 22 Aug 2014 18:49:31 -0400 Trond Myklebust > <trond.myklebust@xxxxxxxxxxxxxxx> wrote: > >> Junxiao Bi reports seeing the following deadlock: >> >> @ crash> bt 1539 >> @ PID: 1539 TASK: ffff88178f64a040 CPU: 1 COMMAND: "rpciod/1" >> @ #0 [ffff88178f64d2c0] schedule at ffffffff8145833a >> @ #1 [ffff88178f64d348] io_schedule at ffffffff8145842c >> @ #2 [ffff88178f64d368] sync_page at ffffffff810d8161 >> @ #3 [ffff88178f64d378] __wait_on_bit at ffffffff8145895b >> @ #4 [ffff88178f64d3b8] wait_on_page_bit at ffffffff810d82fe >> @ #5 [ffff88178f64d418] wait_on_page_writeback at ffffffff810e2a1a >> @ #6 [ffff88178f64d438] shrink_page_list at ffffffff810e34e1 >> @ #7 [ffff88178f64d588] shrink_list at ffffffff810e3dbe >> @ #8 [ffff88178f64d6f8] shrink_zone at ffffffff810e425e >> @ #9 [ffff88178f64d7b8] do_try_to_free_pages at ffffffff810e4978 >> @ #10 [ffff88178f64d828] try_to_free_pages at ffffffff810e4c31 >> @ #11 [ffff88178f64d8c8] __alloc_pages_nodemask at ffffffff810de370 > > This stack trace (from 2.6.32) cannot happen in mainline, though it took me a > while to remember/discover exactly why. > > try_to_free_pages() creates a 'struct scan_control' with ->target_mem_cgroup > set to NULL. > shrink_page_list() checks ->target_mem_cgroup using global_reclaim() and if > it is NULL, wait_on_page_writeback is *not* called. > > So we can only hit this deadlock if mem-cgroup limits are imposed on a > process which is using NFS - which is quite possible but probably not common. > > The fact that a dead-lock can happen only when memcg limits are imposed seems > very fragile. People aren't going to test that case much so there could well > be other deadlock possibilities lurking. > > Mel: might there be some other way we could get out of this deadlock? > Could the wait_on_page_writeback() in shrink_page_list() be made a timed-out > wait or something? Any other wait out of this deadlock other than setting > PF_MEMALLOC_NOIO everywhere? Not only the wait_on_page_writeback() cause the deadlock but also the next pageout()-> (mapping->a_ops->writepage), Trond's second patch fix this. So fix the wait_on_page_writeback is not enough to fix deadlock. Thanks, Junxiao. > > Thanks, > NeilBrown > > > >> @ #12 [ffff88178f64d978] kmem_getpages at ffffffff8110e18b >> @ #13 [ffff88178f64d9a8] fallback_alloc at ffffffff8110e35e >> @ #14 [ffff88178f64da08] ____cache_alloc_node at ffffffff8110e51f >> @ #15 [ffff88178f64da48] __kmalloc at ffffffff8110efba >> @ #16 [ffff88178f64da98] xs_setup_xprt at ffffffffa00a563f [sunrpc] >> @ #17 [ffff88178f64dad8] xs_setup_tcp at ffffffffa00a7648 [sunrpc] >> @ #18 [ffff88178f64daf8] xprt_create_transport at ffffffffa00a478f [sunrpc] >> @ #19 [ffff88178f64db18] rpc_create at ffffffffa00a2d7a [sunrpc] >> @ #20 [ffff88178f64dbf8] rpcb_create at ffffffffa00b026b [sunrpc] >> @ #21 [ffff88178f64dc98] rpcb_getport_async at ffffffffa00b0c94 [sunrpc] >> @ #22 [ffff88178f64ddf8] call_bind at ffffffffa00a11f8 [sunrpc] >> @ #23 [ffff88178f64de18] __rpc_execute at ffffffffa00a88ef [sunrpc] >> @ #24 [ffff88178f64de58] rpc_async_schedule at ffffffffa00a9187 [sunrpc] >> @ #25 [ffff88178f64de78] worker_thread at ffffffff81072ed2 >> @ #26 [ffff88178f64dee8] kthread at ffffffff81076df3 >> @ #27 [ffff88178f64df48] kernel_thread at ffffffff81012e2a >> @ crash> >> >> Junxiao notes that the problem is not limited to the rpcbind client. In >> fact we can trigger the exact same problem when trying to reconnect to >> the server, and we find ourselves calling sock_alloc(). >> >> The following solution should work for all kernels that support the >> PF_MEMALLOC_NOIO flag (i.e. Linux 3.9 and newer). >> >> Link: http://lkml.kernel.org/r/53F6F772.6020708@xxxxxxxxxx >> Reported-by: Junxiao Bi <junxiao.bi@xxxxxxxxxx> >> Cc: stable@xxxxxxxxxxxxxxx # 3.9+ >> Signed-off-by: Trond Myklebust <trond.myklebust@xxxxxxxxxxxxxxx> >> --- >> net/sunrpc/sched.c | 5 +++-- >> net/sunrpc/xprtsock.c | 15 ++++++++------- >> 2 files changed, 11 insertions(+), 9 deletions(-) >> >> diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c >> index 9358c79fd589..ab3aff71ff93 100644 >> --- a/net/sunrpc/sched.c >> +++ b/net/sunrpc/sched.c >> @@ -19,6 +19,7 @@ >> #include <linux/spinlock.h> >> #include <linux/mutex.h> >> #include <linux/freezer.h> >> +#include <linux/sched.h> >> >> #include <linux/sunrpc/clnt.h> >> >> @@ -821,9 +822,9 @@ void rpc_execute(struct rpc_task *task) >> >> static void rpc_async_schedule(struct work_struct *work) >> { >> - current->flags |= PF_FSTRANS; >> + current->flags |= PF_FSTRANS | PF_MEMALLOC_NOIO; >> __rpc_execute(container_of(work, struct rpc_task, u.tk_work)); >> - current->flags &= ~PF_FSTRANS; >> + current->flags &= ~(PF_FSTRANS | PF_MEMALLOC_NOIO); >> } >> >> /** >> diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c >> index 43cd89eacfab..1d6d4d84b299 100644 >> --- a/net/sunrpc/xprtsock.c >> +++ b/net/sunrpc/xprtsock.c >> @@ -38,6 +38,7 @@ >> #include <linux/sunrpc/svcsock.h> >> #include <linux/sunrpc/xprtsock.h> >> #include <linux/file.h> >> +#include <linux/sched.h> >> #ifdef CONFIG_SUNRPC_BACKCHANNEL >> #include <linux/sunrpc/bc_xprt.h> >> #endif >> @@ -1927,7 +1928,7 @@ static int xs_local_setup_socket(struct sock_xprt *transport) >> struct socket *sock; >> int status = -EIO; >> >> - current->flags |= PF_FSTRANS; >> + current->flags |= PF_FSTRANS | PF_MEMALLOC_NOIO; >> >> clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); >> status = __sock_create(xprt->xprt_net, AF_LOCAL, >> @@ -1968,7 +1969,7 @@ static int xs_local_setup_socket(struct sock_xprt *transport) >> out: >> xprt_clear_connecting(xprt); >> xprt_wake_pending_tasks(xprt, status); >> - current->flags &= ~PF_FSTRANS; >> + current->flags &= ~(PF_FSTRANS | PF_MEMALLOC_NOIO); >> return status; >> } >> >> @@ -2071,7 +2072,7 @@ static void xs_udp_setup_socket(struct work_struct *work) >> struct socket *sock = transport->sock; >> int status = -EIO; >> >> - current->flags |= PF_FSTRANS; >> + current->flags |= PF_FSTRANS | PF_MEMALLOC_NOIO; >> >> /* Start by resetting any existing state */ >> xs_reset_transport(transport); >> @@ -2092,7 +2093,7 @@ static void xs_udp_setup_socket(struct work_struct *work) >> out: >> xprt_clear_connecting(xprt); >> xprt_wake_pending_tasks(xprt, status); >> - current->flags &= ~PF_FSTRANS; >> + current->flags &= ~(PF_FSTRANS | PF_MEMALLOC_NOIO); >> } >> >> /* >> @@ -2229,7 +2230,7 @@ static void xs_tcp_setup_socket(struct work_struct *work) >> struct rpc_xprt *xprt = &transport->xprt; >> int status = -EIO; >> >> - current->flags |= PF_FSTRANS; >> + current->flags |= PF_FSTRANS | PF_MEMALLOC_NOIO; >> >> if (!sock) { >> clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); >> @@ -2276,7 +2277,7 @@ static void xs_tcp_setup_socket(struct work_struct *work) >> case -EINPROGRESS: >> case -EALREADY: >> xprt_clear_connecting(xprt); >> - current->flags &= ~PF_FSTRANS; >> + current->flags &= ~(PF_FSTRANS | PF_MEMALLOC_NOIO); >> return; >> case -EINVAL: >> /* Happens, for instance, if the user specified a link >> @@ -2294,7 +2295,7 @@ out_eagain: >> out: >> xprt_clear_connecting(xprt); >> xprt_wake_pending_tasks(xprt, status); >> - current->flags &= ~PF_FSTRANS; >> + current->flags &= ~(PF_FSTRANS | PF_MEMALLOC_NOIO); >> } >> >> /** > -- To unsubscribe from this list: send the line "unsubscribe linux-nfs" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
