From 06f4e94898918bcad00cdd4d349313a439d6911e Mon Sep 17 00:00:00 2001 From: Zefan Li Date: Tue, 9 Aug 2016 11:25:01 +0800 Subject: [PATCH 1/2] cpuset: make sure new tasks conform to the current config of the cpuset A new task inherits cpus_allowed and mems_allowed masks from its parent, but if someone changes cpuset's config by writing to cpuset.cpus/cpuset.mems before this new task is inserted into the cgroup's task list, the new task won't be updated accordingly. Signed-off-by: Zefan Li Signed-off-by: Tejun Heo Cc: stable@vger.kernel.org --- kernel/cpuset.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/kernel/cpuset.c b/kernel/cpuset.c index c7fd2778ed50..c27e53326bef 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2069,6 +2069,20 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css) mutex_unlock(&cpuset_mutex); } +/* + * Make sure the new task conform to the current state of its parent, + * which could have been changed by cpuset just after it inherits the + * state from the parent and before it sits on the cgroup's task list. + */ +void cpuset_fork(struct task_struct *task) +{ + if (task_css_is_root(task, cpuset_cgrp_id)) + return; + + set_cpus_allowed_ptr(task, ¤t->cpus_allowed); + task->mems_allowed = current->mems_allowed; +} + struct cgroup_subsys cpuset_cgrp_subsys = { .css_alloc = cpuset_css_alloc, .css_online = cpuset_css_online, @@ -2079,6 +2093,7 @@ struct cgroup_subsys cpuset_cgrp_subsys = { .attach = cpuset_attach, .post_attach = cpuset_post_attach, .bind = cpuset_bind, + .fork = cpuset_fork, .legacy_cftypes = files, .early_init = true, }; From 568ac888215c7fb2fabe8ea739b00ec3c1f5d440 Mon Sep 17 00:00:00 2001 From: Balbir Singh Date: Wed, 10 Aug 2016 15:43:06 -0400 Subject: [PATCH 2/2] cgroup: reduce read locked section of cgroup_threadgroup_rwsem during fork 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 Acked-by: Zefan Li Cc: Oleg Nesterov Cc: Andrew Morton Cc: stable@vger.kernel.org # v4.2+ Signed-off-by: Tejun Heo --- kernel/fork.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/fork.c b/kernel/fork.c index 52e725d4a866..aaf782327bf3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1404,7 +1404,6 @@ 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); @@ -1556,6 +1555,7 @@ 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 @@ -1656,6 +1656,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, bad_fork_cancel_cgroup: cgroup_cancel_fork(p); bad_fork_free_pid: + threadgroup_change_end(current); if (pid != &init_struct_pid) free_pid(pid); bad_fork_cleanup_thread: @@ -1688,7 +1689,6 @@ 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);