From: Oleg Nesterov oleg@redhat.com
[ Upstream commit 51bee5abeab2058ea5813c5615d6197a23dbf041 ]
The only user of cgroup_subsys->free() callback is pids_cgrp_subsys which needs pids_free() to uncharge the pid.
However, ->free() is called from __put_task_struct()->cgroup_free() and this is too late. Even the trivial program which does
for (;;) { int pid = fork(); assert(pid >= 0); if (pid) wait(NULL); else exit(0); }
can run out of limits because release_task()->call_rcu(delayed_put_task_struct) implies an RCU gp after the task/pid goes away and before the final put().
Test-case:
mkdir -p /tmp/CG mount -t cgroup2 none /tmp/CG echo '+pids' > /tmp/CG/cgroup.subtree_control
mkdir /tmp/CG/PID echo 2 > /tmp/CG/PID/pids.max
perl -e 'while ($p = fork) { wait; } $p // die "fork failed: $!\n"' & echo $! > /tmp/CG/PID/cgroup.procs
Without this patch the forking process fails soon after migration.
Rename cgroup_subsys->free() to cgroup_subsys->release() and move the callsite into the new helper, cgroup_release(), called by release_task() which actually frees the pid(s).
Reported-by: Herton R. Krzesinski hkrzesin@redhat.com Reported-by: Jan Stancek jstancek@redhat.com Signed-off-by: Oleg Nesterov oleg@redhat.com Signed-off-by: Tejun Heo tj@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/cgroup-defs.h | 2 +- include/linux/cgroup.h | 2 ++ kernel/cgroup/cgroup.c | 15 +++++++++------ kernel/cgroup/pids.c | 4 ++-- kernel/exit.c | 1 + 5 files changed, 15 insertions(+), 9 deletions(-)
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 22254c1fe1c5..6002275937f5 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -597,7 +597,7 @@ struct cgroup_subsys { void (*cancel_fork)(struct task_struct *task); void (*fork)(struct task_struct *task); void (*exit)(struct task_struct *task); - void (*free)(struct task_struct *task); + void (*release)(struct task_struct *task); void (*bind)(struct cgroup_subsys_state *root_css);
bool early_init:1; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 32c553556bbd..ca51b2c15bcc 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -119,6 +119,7 @@ extern int cgroup_can_fork(struct task_struct *p); extern void cgroup_cancel_fork(struct task_struct *p); extern void cgroup_post_fork(struct task_struct *p); void cgroup_exit(struct task_struct *p); +void cgroup_release(struct task_struct *p); void cgroup_free(struct task_struct *p);
int cgroup_init_early(void); @@ -699,6 +700,7 @@ static inline int cgroup_can_fork(struct task_struct *p) { return 0; } static inline void cgroup_cancel_fork(struct task_struct *p) {} static inline void cgroup_post_fork(struct task_struct *p) {} static inline void cgroup_exit(struct task_struct *p) {} +static inline void cgroup_release(struct task_struct *p) {} static inline void cgroup_free(struct task_struct *p) {}
static inline int cgroup_init_early(void) { return 0; } diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index e710ac7fbbbf..63dae7e0ccae 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -195,7 +195,7 @@ static u64 css_serial_nr_next = 1; */ static u16 have_fork_callback __read_mostly; static u16 have_exit_callback __read_mostly; -static u16 have_free_callback __read_mostly; +static u16 have_release_callback __read_mostly; static u16 have_canfork_callback __read_mostly;
/* cgroup namespace for init task */ @@ -5240,7 +5240,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early)
have_fork_callback |= (bool)ss->fork << ss->id; have_exit_callback |= (bool)ss->exit << ss->id; - have_free_callback |= (bool)ss->free << ss->id; + have_release_callback |= (bool)ss->release << ss->id; have_canfork_callback |= (bool)ss->can_fork << ss->id;
/* At system boot, before all subsystems have been @@ -5676,16 +5676,19 @@ void cgroup_exit(struct task_struct *tsk) } while_each_subsys_mask(); }
-void cgroup_free(struct task_struct *task) +void cgroup_release(struct task_struct *task) { - struct css_set *cset = task_css_set(task); struct cgroup_subsys *ss; int ssid;
- do_each_subsys_mask(ss, ssid, have_free_callback) { - ss->free(task); + do_each_subsys_mask(ss, ssid, have_release_callback) { + ss->release(task); } while_each_subsys_mask(); +}
+void cgroup_free(struct task_struct *task) +{ + struct css_set *cset = task_css_set(task); put_css_set(cset); }
diff --git a/kernel/cgroup/pids.c b/kernel/cgroup/pids.c index 9829c67ebc0a..c9960baaa14f 100644 --- a/kernel/cgroup/pids.c +++ b/kernel/cgroup/pids.c @@ -247,7 +247,7 @@ static void pids_cancel_fork(struct task_struct *task) pids_uncharge(pids, 1); }
-static void pids_free(struct task_struct *task) +static void pids_release(struct task_struct *task) { struct pids_cgroup *pids = css_pids(task_css(task, pids_cgrp_id));
@@ -342,7 +342,7 @@ struct cgroup_subsys pids_cgrp_subsys = { .cancel_attach = pids_cancel_attach, .can_fork = pids_can_fork, .cancel_fork = pids_cancel_fork, - .free = pids_free, + .release = pids_release, .legacy_cftypes = pids_files, .dfl_cftypes = pids_files, .threaded = true, diff --git a/kernel/exit.c b/kernel/exit.c index d607e23fd0c3..5c0964dc805a 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -219,6 +219,7 @@ void release_task(struct task_struct *p) }
write_unlock_irq(&tasklist_lock); + cgroup_release(p); release_thread(p); call_rcu(&p->rcu, delayed_put_task_struct);