From fe4d073fcb5b399b8ed415be8a1a9ae93d52b19b Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Thu, 2 Apr 2015 14:40:58 +0300 Subject: Revert "libceph: use memalloc flags for net IO" commit 6d7fdb0ab351b33d4c12d53fe44be030b90fc9d4 upstream. This reverts commit 89baaa570ab0b476db09408d209578cfed700e9f. Dirty page throttling should be sufficient for us in the general case so there is no need to use __GFP_MEMALLOC - it would be needed only in the swap-over-rbd case, which we currently don't support. (It would probably take approximately the commit that is being reverted to add that support, but we would also need the "swap" option to distinguish from the general case and make sure swap ceph_client-s aren't shared with anything else.) See ceph-devel threads [1] and [2] for the details of why enabling pfmemalloc reserves for all cases is a bad thing. On top of potential system lockups related to drained emergency reserves, this turned out to cause ceph lockups in case peers are on the same host and communicating via loopback due to sk_filter() dropping pfmemalloc skbs on the receiving side because the receiving loopback socket is not tagged with SOCK_MEMALLOC. [1] "SOCK_MEMALLOC vs loopback" http://www.spinics.net/lists/ceph-devel/msg22998.html [2] "[PATCH] libceph: don't set memalloc flags in loopback case" http://www.spinics.net/lists/ceph-devel/msg23392.html Conflicts: net/ceph/messenger.c [ context: tcp_nodelay option ] Cc: Mike Christie Cc: Mel Gorman Cc: Sage Weil Signed-off-by: Ilya Dryomov Acked-by: Mike Christie Acked-by: Mel Gorman Signed-off-by: Greg Kroah-Hartman --- net/ceph/messenger.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 33a2f201e460..74d30ec7b234 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -484,7 +484,7 @@ static int ceph_tcp_connect(struct ceph_connection *con) IPPROTO_TCP, &sock); if (ret) return ret; - sock->sk->sk_allocation = GFP_NOFS | __GFP_MEMALLOC; + sock->sk->sk_allocation = GFP_NOFS; #ifdef CONFIG_LOCKDEP lockdep_set_class(&sock->sk->sk_lock, &socket_class); @@ -510,8 +510,6 @@ static int ceph_tcp_connect(struct ceph_connection *con) return ret; } - sk_set_memalloc(sock->sk); - con->sock = sock; return 0; } @@ -2798,11 +2796,8 @@ static void con_work(struct work_struct *work) { struct ceph_connection *con = container_of(work, struct ceph_connection, work.work); - unsigned long pflags = current->flags; bool fault; - current->flags |= PF_MEMALLOC; - mutex_lock(&con->mutex); while (true) { int ret; @@ -2856,8 +2851,6 @@ static void con_work(struct work_struct *work) con_fault_finish(con); con->ops->put(con); - - tsk_restore_flags(current, pflags, PF_MEMALLOC); } /* -- cgit v1.2.3