libceph: force GFP_NOIO for socket allocations
authorIlya Dryomov <idryomov@gmail.com>
Tue, 21 Mar 2017 12:44:28 +0000 (13:44 +0100)
committerIlya Dryomov <idryomov@gmail.com>
Thu, 23 Mar 2017 11:03:36 +0000 (12:03 +0100)
sock_alloc_inode() allocates socket+inode and socket_wq with
GFP_KERNEL, which is not allowed on the writeback path:

    Workqueue: ceph-msgr con_work [libceph]
    ffff8810871cb018 0000000000000046 0000000000000000 ffff881085d40000
    0000000000012b00 ffff881025cad428 ffff8810871cbfd8 0000000000012b00
    ffff880102fc1000 ffff881085d40000 ffff8810871cb038 ffff8810871cb148
    Call Trace:
    [<ffffffff816dd629>] schedule+0x29/0x70
    [<ffffffff816e066d>] schedule_timeout+0x1bd/0x200
    [<ffffffff81093ffc>] ? ttwu_do_wakeup+0x2c/0x120
    [<ffffffff81094266>] ? ttwu_do_activate.constprop.135+0x66/0x70
    [<ffffffff816deb5f>] wait_for_completion+0xbf/0x180
    [<ffffffff81097cd0>] ? try_to_wake_up+0x390/0x390
    [<ffffffff81086335>] flush_work+0x165/0x250
    [<ffffffff81082940>] ? worker_detach_from_pool+0xd0/0xd0
    [<ffffffffa03b65b1>] xlog_cil_force_lsn+0x81/0x200 [xfs]
    [<ffffffff816d6b42>] ? __slab_free+0xee/0x234
    [<ffffffffa03b4b1d>] _xfs_log_force_lsn+0x4d/0x2c0 [xfs]
    [<ffffffff811adc1e>] ? lookup_page_cgroup_used+0xe/0x30
    [<ffffffffa039a723>] ? xfs_reclaim_inode+0xa3/0x330 [xfs]
    [<ffffffffa03b4dcf>] xfs_log_force_lsn+0x3f/0xf0 [xfs]
    [<ffffffffa039a723>] ? xfs_reclaim_inode+0xa3/0x330 [xfs]
    [<ffffffffa03a62c6>] xfs_iunpin_wait+0xc6/0x1a0 [xfs]
    [<ffffffff810aa250>] ? wake_atomic_t_function+0x40/0x40
    [<ffffffffa039a723>] xfs_reclaim_inode+0xa3/0x330 [xfs]
    [<ffffffffa039ac07>] xfs_reclaim_inodes_ag+0x257/0x3d0 [xfs]
    [<ffffffffa039bb13>] xfs_reclaim_inodes_nr+0x33/0x40 [xfs]
    [<ffffffffa03ab745>] xfs_fs_free_cached_objects+0x15/0x20 [xfs]
    [<ffffffff811c0c18>] super_cache_scan+0x178/0x180
    [<ffffffff8115912e>] shrink_slab_node+0x14e/0x340
    [<ffffffff811afc3b>] ? mem_cgroup_iter+0x16b/0x450
    [<ffffffff8115af70>] shrink_slab+0x100/0x140
    [<ffffffff8115e425>] do_try_to_free_pages+0x335/0x490
    [<ffffffff8115e7f9>] try_to_free_pages+0xb9/0x1f0
    [<ffffffff816d56e4>] ? __alloc_pages_direct_compact+0x69/0x1be
    [<ffffffff81150cba>] __alloc_pages_nodemask+0x69a/0xb40
    [<ffffffff8119743e>] alloc_pages_current+0x9e/0x110
    [<ffffffff811a0ac5>] new_slab+0x2c5/0x390
    [<ffffffff816d71c4>] __slab_alloc+0x33b/0x459
    [<ffffffff815b906d>] ? sock_alloc_inode+0x2d/0xd0
    [<ffffffff8164bda1>] ? inet_sendmsg+0x71/0xc0
    [<ffffffff815b906d>] ? sock_alloc_inode+0x2d/0xd0
    [<ffffffff811a21f2>] kmem_cache_alloc+0x1a2/0x1b0
    [<ffffffff815b906d>] sock_alloc_inode+0x2d/0xd0
    [<ffffffff811d8566>] alloc_inode+0x26/0xa0
    [<ffffffff811da04a>] new_inode_pseudo+0x1a/0x70
    [<ffffffff815b933e>] sock_alloc+0x1e/0x80
    [<ffffffff815ba855>] __sock_create+0x95/0x220
    [<ffffffff815baa04>] sock_create_kern+0x24/0x30
    [<ffffffffa04794d9>] con_work+0xef9/0x2050 [libceph]
    [<ffffffffa04aa9ec>] ? rbd_img_request_submit+0x4c/0x60 [rbd]
    [<ffffffff81084c19>] process_one_work+0x159/0x4f0
    [<ffffffff8108561b>] worker_thread+0x11b/0x530
    [<ffffffff81085500>] ? create_worker+0x1d0/0x1d0
    [<ffffffff8108b6f9>] kthread+0xc9/0xe0
    [<ffffffff8108b630>] ? flush_kthread_worker+0x90/0x90
    [<ffffffff816e1b98>] ret_from_fork+0x58/0x90
    [<ffffffff8108b630>] ? flush_kthread_worker+0x90/0x90

Use memalloc_noio_{save,restore}() to temporarily force GFP_NOIO here.

Cc: stable@vger.kernel.org # 3.10+, needs backporting
Link: http://tracker.ceph.com/issues/19309
Reported-by: Sergey Jerusalimov <wintchester@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Jeff Layton <jlayton@redhat.com>
net/ceph/messenger.c

index 38dcf1e..f76bb33 100644 (file)
@@ -7,6 +7,7 @@
 #include <linux/kthread.h>
 #include <linux/net.h>
 #include <linux/nsproxy.h>
+#include <linux/sched/mm.h>
 #include <linux/slab.h>
 #include <linux/socket.h>
 #include <linux/string.h>
@@ -469,11 +470,16 @@ static int ceph_tcp_connect(struct ceph_connection *con)
 {
        struct sockaddr_storage *paddr = &con->peer_addr.in_addr;
        struct socket *sock;
+       unsigned int noio_flag;
        int ret;
 
        BUG_ON(con->sock);
+
+       /* sock_create_kern() allocates with GFP_KERNEL */
+       noio_flag = memalloc_noio_save();
        ret = sock_create_kern(read_pnet(&con->msgr->net), paddr->ss_family,
                               SOCK_STREAM, IPPROTO_TCP, &sock);
+       memalloc_noio_restore(noio_flag);
        if (ret)
                return ret;
        sock->sk->sk_allocation = GFP_NOFS;