cgroup: reduce read locked section of cgroup_threadgroup_rwsem during fork

commit 568ac888215c7fb2fabe8ea739b00ec3c1f5d440 upstream.

cgroup_threadgroup_rwsem is acquired in read mode during process exit
and fork.  It is also grabbed in write mode during
__cgroups_proc_write().  I've recently run into a scenario with lots
of memory pressure and OOM and I am beginning to see

systemd

 __switch_to+0x1f8/0x350
 __schedule+0x30c/0x990
 schedule+0x48/0xc0
 percpu_down_write+0x114/0x170
 __cgroup_procs_write.isra.12+0xb8/0x3c0
 cgroup_file_write+0x74/0x1a0
 kernfs_fop_write+0x188/0x200
 __vfs_write+0x6c/0xe0
 vfs_write+0xc0/0x230
 SyS_write+0x6c/0x110
 system_call+0x38/0xb4

This thread is waiting on the reader of cgroup_threadgroup_rwsem to
exit.  The reader itself is under memory pressure and has gone into
reclaim after fork. There are times the reader also ends up waiting on
oom_lock as well.

 __switch_to+0x1f8/0x350
 __schedule+0x30c/0x990
 schedule+0x48/0xc0
 jbd2_log_wait_commit+0xd4/0x180
 ext4_evict_inode+0x88/0x5c0
 evict+0xf8/0x2a0
 dispose_list+0x50/0x80
 prune_icache_sb+0x6c/0x90
 super_cache_scan+0x190/0x210
 shrink_slab.part.15+0x22c/0x4c0
 shrink_zone+0x288/0x3c0
 do_try_to_free_pages+0x1dc/0x590
 try_to_free_pages+0xdc/0x260
 __alloc_pages_nodemask+0x72c/0xc90
 alloc_pages_current+0xb4/0x1a0
 page_table_alloc+0xc0/0x170
 __pte_alloc+0x58/0x1f0
 copy_page_range+0x4ec/0x950
 copy_process.isra.5+0x15a0/0x1870
 _do_fork+0xa8/0x4b0
 ppc_clone+0x8/0xc

In the meanwhile, all processes exiting/forking are blocked almost
stalling the system.

This patch moves the threadgroup_change_begin from before
cgroup_fork() to just before cgroup_canfork().  There is no nee to
worry about threadgroup changes till the task is actually added to the
threadgroup.  This avoids having to call reclaim with
cgroup_threadgroup_rwsem held.

tj: Subject and description edits.

Signed-off-by: Balbir Singh <bsingharora@gmail.com>
Acked-by: Zefan Li <lizefan@huawei.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/kernel/fork.c b/kernel/fork.c
index 1155eac616878b5494ae94f2f1d0294812ddda72..c485cb156772848a4f4325caa3067f6029cd5fa5 100644 (file)
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1369,7 +1369,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
        p->real_start_time = ktime_get_boot_ns();
        p->io_context = NULL;
        p->audit_context = NULL;
-       threadgroup_change_begin(current);
        cgroup_fork(p);
 #ifdef CONFIG_NUMA
        p->mempolicy = mpol_dup(p->mempolicy);
@@ -1521,6 +1520,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
        INIT_LIST_HEAD(&p->thread_group);
        p->task_works = NULL;
 
+       threadgroup_change_begin(current);
        /*
         * Ensure that the cgroup subsystem policies allow the new process to be
         * forked. It should be noted the the new process's css_set can be changed
@@ -1621,6 +1621,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 bad_fork_cancel_cgroup:
        cgroup_cancel_fork(p, cgrp_ss_priv);
 bad_fork_free_pid:
+       threadgroup_change_end(current);
        if (pid != &init_struct_pid)
                free_pid(pid);
 bad_fork_cleanup_io:
@@ -1651,7 +1652,6 @@ bad_fork_cleanup_policy:
        mpol_put(p->mempolicy);
 bad_fork_cleanup_threadgroup_lock:
 #endif
-       threadgroup_change_end(current);
        delayacct_tsk_free(p);
 bad_fork_cleanup_count:
        atomic_dec(&p->cred->user->processes);