The patch titled
cgroups: allow subsystems to cancel a fork
has been added to the -mm tree. Its filename is
cgroups-allow-subsystems-to-cancel-a-fork.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: cgroups: allow subsystems to cancel a fork
From: Frederic Weisbecker <fweisbec@xxxxxxxxx>
Let the subsystem's fork callback return an error value so that they can
cancel a fork. This is going to be used by the task counter subsystem to
implement the limit.
Suggested-by: Oleg Nesterov <oleg@xxxxxxxxxx>
Signed-off-by: Frederic Weisbecker <fweisbec@xxxxxxxxx>
Cc: Paul Menage <paul@xxxxxxxxxxxxxx>
Cc: Li Zefan <lizf@xxxxxxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Aditya Kali <adityakali@xxxxxxxxxx>
Cc: Oleg Nesterov <oleg@xxxxxxxxxx>
Cc: Kay Sievers <kay.sievers@xxxxxxxx>
Cc: Tim Hockin <thockin@xxxxxxxxxx>
Cc: Tejun Heo <tj@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/cgroup.h | 14 +++++++++-----
kernel/cgroup.c | 23 +++++++++++++++++++----
kernel/cgroup_freezer.c | 6 ++++--
kernel/exit.c | 2 +-
kernel/fork.c | 7 +++++--
5 files changed, 38 insertions(+), 14 deletions(-)
diff -puN include/linux/cgroup.h~cgroups-allow-subsystems-to-cancel-a-fork include/linux/cgroup.h
--- a/include/linux/cgroup.h~cgroups-allow-subsystems-to-cancel-a-fork
+++ a/include/linux/cgroup.h
@@ -32,9 +32,11 @@ extern int cgroup_lock_is_held(void);
extern bool cgroup_lock_live_group(struct cgroup *cgrp);
extern void cgroup_unlock(void);
extern void cgroup_fork(struct task_struct *p);
-extern void cgroup_fork_callbacks(struct task_struct *p);
+extern int cgroup_fork_callbacks(struct task_struct *p,
+ struct cgroup_subsys **failed_ss);
extern void cgroup_post_fork(struct task_struct *p);
-extern void cgroup_exit(struct task_struct *p, int run_callbacks);
+extern void cgroup_exit(struct task_struct *p, int run_callbacks,
+ struct cgroup_subsys *failed_ss);
extern int cgroupstats_build(struct cgroupstats *stats,
struct dentry *dentry);
extern int cgroup_load_subsys(struct cgroup_subsys *ss);
@@ -477,7 +479,7 @@ struct cgroup_subsys {
void (*attach_task)(struct cgroup *cgrp, struct cgroup *old_cgrp, struct task_struct *tsk);
void (*attach)(struct cgroup_subsys *ss, struct cgroup *cgrp,
struct cgroup *old_cgrp, struct task_struct *tsk);
- void (*fork)(struct cgroup_subsys *ss, struct task_struct *task);
+ int (*fork)(struct cgroup_subsys *ss, struct task_struct *task);
void (*exit)(struct cgroup_subsys *ss, struct cgroup *cgrp,
struct cgroup *old_cgrp, struct task_struct *task);
int (*populate)(struct cgroup_subsys *ss,
@@ -634,9 +636,11 @@ struct cgroup_subsys_state *cgroup_css_f
static inline int cgroup_init_early(void) { return 0; }
static inline int cgroup_init(void) { return 0; }
static inline void cgroup_fork(struct task_struct *p) {}
-static inline void cgroup_fork_callbacks(struct task_struct *p) {}
+static inline int cgroup_fork_callbacks(struct task_struct *p,
+ struct cgroup_subsys **failed_ss) {}
static inline void cgroup_post_fork(struct task_struct *p) {}
-static inline void cgroup_exit(struct task_struct *p, int callbacks) {}
+static inline void cgroup_exit(struct task_struct *p, int callbacks,
+ struct cgroup_subsys **failed_ss) {}
static inline void cgroup_lock(void) {}
static inline void cgroup_unlock(void) {}
diff -puN kernel/cgroup.c~cgroups-allow-subsystems-to-cancel-a-fork kernel/cgroup.c
--- a/kernel/cgroup.c~cgroups-allow-subsystems-to-cancel-a-fork
+++ a/kernel/cgroup.c
@@ -4538,8 +4538,11 @@ void cgroup_fork(struct task_struct *chi
* tasklist. No need to take any locks since no-one can
* be operating on this task.
*/
-void cgroup_fork_callbacks(struct task_struct *child)
+int cgroup_fork_callbacks(struct task_struct *child,
+ struct cgroup_subsys **failed_ss)
{
+ int err;
+
if (need_forkexit_callback) {
int i;
/*
@@ -4549,10 +4552,17 @@ void cgroup_fork_callbacks(struct task_s
*/
for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
struct cgroup_subsys *ss = subsys[i];
- if (ss->fork)
- ss->fork(ss, child);
+ if (ss->fork) {
+ err = ss->fork(ss, child);
+ if (err) {
+ *failed_ss = ss;
+ return err;
+ }
+ }
}
}
+
+ return 0;
}
/**
@@ -4610,7 +4620,8 @@ void cgroup_post_fork(struct task_struct
* which wards off any cgroup_attach_task() attempts, or task is a failed
* fork, never visible to cgroup_attach_task.
*/
-void cgroup_exit(struct task_struct *tsk, int run_callbacks)
+void cgroup_exit(struct task_struct *tsk, int run_callbacks,
+ struct cgroup_subsys *failed_ss)
{
struct css_set *cg;
int i;
@@ -4639,6 +4650,10 @@ void cgroup_exit(struct task_struct *tsk
*/
for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
struct cgroup_subsys *ss = subsys[i];
+
+ if (ss == failed_ss)
+ break;
+
if (ss->exit) {
struct cgroup *old_cgrp =
rcu_dereference_raw(cg->subsys[i])->cgroup;
diff -puN kernel/cgroup_freezer.c~cgroups-allow-subsystems-to-cancel-a-fork kernel/cgroup_freezer.c
--- a/kernel/cgroup_freezer.c~cgroups-allow-subsystems-to-cancel-a-fork
+++ a/kernel/cgroup_freezer.c
@@ -180,7 +180,7 @@ static int freezer_can_attach_task(struc
return cgroup_freezing(tsk) ? -EBUSY : 0;
}
-static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task)
+static int freezer_fork(struct cgroup_subsys *ss, struct task_struct *task)
{
struct freezer *freezer;
@@ -200,7 +200,7 @@ static void freezer_fork(struct cgroup_s
* following check.
*/
if (!freezer->css.cgroup->parent)
- return;
+ return 0;
spin_lock_irq(&freezer->lock);
BUG_ON(freezer->state == CGROUP_FROZEN);
@@ -209,6 +209,8 @@ static void freezer_fork(struct cgroup_s
if (freezer->state == CGROUP_FREEZING)
freeze_task(task, true);
spin_unlock_irq(&freezer->lock);
+
+ return 0;
}
/*
diff -puN kernel/exit.c~cgroups-allow-subsystems-to-cancel-a-fork kernel/exit.c
--- a/kernel/exit.c~cgroups-allow-subsystems-to-cancel-a-fork
+++ a/kernel/exit.c
@@ -997,7 +997,7 @@ NORET_TYPE void do_exit(long code)
*/
perf_event_exit_task(tsk);
- cgroup_exit(tsk, 1);
+ cgroup_exit(tsk, 1, NULL);
if (group_dead)
disassociate_ctty(1);
diff -puN kernel/fork.c~cgroups-allow-subsystems-to-cancel-a-fork kernel/fork.c
--- a/kernel/fork.c~cgroups-allow-subsystems-to-cancel-a-fork
+++ a/kernel/fork.c
@@ -1083,6 +1083,7 @@ static struct task_struct *copy_process(
int retval;
struct task_struct *p;
int cgroup_callbacks_done = 0;
+ struct cgroup_subsys *cgroup_failed_ss = NULL;
if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
return ERR_PTR(-EINVAL);
@@ -1341,8 +1342,10 @@ static struct task_struct *copy_process(
/* Now that the task is set up, run cgroup callbacks if
* necessary. We need to run them before the task is visible
* on the tasklist. */
- cgroup_fork_callbacks(p);
+ retval = cgroup_fork_callbacks(p, &cgroup_failed_ss);
cgroup_callbacks_done = 1;
+ if (retval)
+ goto bad_fork_free_pid;
/* Need tasklist lock for parent etc handling! */
write_lock_irq(&tasklist_lock);
@@ -1443,7 +1446,7 @@ bad_fork_cleanup_cgroup:
#endif
if (clone_flags & CLONE_THREAD)
threadgroup_fork_read_unlock(current);
- cgroup_exit(p, cgroup_callbacks_done);
+ cgroup_exit(p, cgroup_callbacks_done, cgroup_failed_ss);
delayacct_tsk_free(p);
module_put(task_thread_info(p)->exec_domain->module);
bad_fork_cleanup_count:
_
Patches currently in -mm which might be from fweisbec@xxxxxxxxx are
linux-next.patch
tracex86-add-tracepoint-to-x86-timer-interrupt-handler.patch
tracex86-add-x86-irq-vector-entry-exit-tracepoints.patch
cgroups-more-safe-tasklist-locking-in-cgroup_attach_proc.patch
cgroups-fix-ordering-of-calls-in-cgroup_attach_proc.patch
cgroups-add-res_counter_write_u64-api.patch
cgroups-new-resource-counter-inheritance-api.patch
cgroups-add-previous-cgroup-in-can_attach_task-attach_task-callbacks.patch
cgroups-new-cancel_attach_task-subsystem-callback.patch
cgroups-new-cancel_attach_task-subsystem-callback-fix.patch
cgroups-ability-to-stop-res-charge-propagation-on-bounded-ancestor.patch
cgroups-add-res-counter-common-ancestor-searching.patch
cgroups-add-res-counter-common-ancestor-searching-fix.patch
res_counter-allow-charge-failure-pointer-to-be-null.patch
cgroups-pull-up-res-counter-charge-failure-interpretation-to-caller.patch
cgroups-add-a-task-counter-subsystem.patch
cgroups-add-documentation-for-task-counter-subsystem.patch
cgroups-allow-subsystems-to-cancel-a-fork.patch
cgroups-convert-task-counter-to-use-the-subsys-fork-callback.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
