| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <51713864.2030204@huawei.com>
Date: Fri, 19 Apr 2013 20:28:20 +0800
From: Li Zefan <lizefan@...wei.com>
To: Tejun Heo <tj@...nel.org>
CC: LKML <linux-kernel@...r.kernel.org>,
Cgroups <cgroups@...r.kernel.org>,
Containers <containers@...ts.linux-foundation.org>,
Glauber Costa <glommer@...allels.com>
Subject: [PATCH 07/10] cpuset: record old_mems_allowed in struct cpuset
When we update a cpuset's mems_allowed and thus update tasks'
mems_allowed, it's required to pass the old mems_allowed and new
mems_allowed to cpuset_migrate_mm().
Currently we save old mems_allowed in a temp local variable before
changing cpuset->mems_allowed. This patch changes it by saving
old mems_allowed in cpuset->old_mems_allowed.
This currently won't change any behavior, but it will later allow
us to keep tasks in empty cpusets.
Signed-off-by: Li Zefan <lizefan@...wei.com>
---
kernel/cpuset.c | 62 +++++++++++++++++++++++++++++++++------------------------
1 file changed, 36 insertions(+), 26 deletions(-)
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 63a5343..c4f9ebd 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -87,6 +87,18 @@ struct cpuset {
cpumask_var_t cpus_allowed; /* CPUs allowed to tasks in cpuset */
nodemask_t mems_allowed; /* Memory Nodes allowed to tasks */
+ /*
+ * This is old Memory Nodes tasks took on.
+ *
+ * - top_cpuset.old_mems_allowed is initialized to mems_allowed.
+ * - A new cpuset's old_mems_allowed is initialized when some
+ * task is moved into it.
+ * - old_mems_allowed is used in cpuset_migrate_mm() when we change
+ * cpuset.mems_allowed and have tasks' nodemask updated, and
+ * then old_mems_allowed is updated to mems_allowed.
+ */
+ nodemask_t old_mems_allowed;
+
struct fmeter fmeter; /* memory_pressure filter */
/*
@@ -975,16 +987,12 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
static void cpuset_change_nodemask(struct task_struct *p,
struct cgroup_scanner *scan)
{
+ struct cpuset *cs = cgroup_cs(scan->cg);
struct mm_struct *mm;
- struct cpuset *cs;
int migrate;
- const nodemask_t *oldmem = scan->data;
- static nodemask_t newmems; /* protected by cpuset_mutex */
-
- cs = cgroup_cs(scan->cg);
- guarantee_online_mems(cs, &newmems);
+ nodemask_t *newmems = scan->data;
- cpuset_change_task_nodemask(p, &newmems);
+ cpuset_change_task_nodemask(p, newmems);
mm = get_task_mm(p);
if (!mm)
@@ -994,7 +1002,7 @@ static void cpuset_change_nodemask(struct task_struct *p,
mpol_rebind_mm(mm, &cs->mems_allowed);
if (migrate)
- cpuset_migrate_mm(mm, oldmem, &cs->mems_allowed);
+ cpuset_migrate_mm(mm, &cs->old_mems_allowed, newmems);
mmput(mm);
}
@@ -1003,25 +1011,26 @@ static void *cpuset_being_rebound;
/**
* update_tasks_nodemask - Update the nodemasks of tasks in the cpuset.
* @cs: the cpuset in which each task's mems_allowed mask needs to be changed
- * @oldmem: old mems_allowed of cpuset cs
* @heap: if NULL, defer allocating heap memory to cgroup_scan_tasks()
*
* Called with cpuset_mutex held
* No return value. It's guaranteed that cgroup_scan_tasks() always returns 0
* if @heap != NULL.
*/
-static void update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem,
- struct ptr_heap *heap)
+static void update_tasks_nodemask(struct cpuset *cs, struct ptr_heap *heap)
{
+ static nodemask_t newmems; /* protected by cpuset_mutex */
struct cgroup_scanner scan;
cpuset_being_rebound = cs; /* causes mpol_dup() rebind */
+ guarantee_online_mems(cs, &newmems);
+
scan.cg = cs->css.cgroup;
scan.test_task = NULL;
scan.process_task = cpuset_change_nodemask;
scan.heap = heap;
- scan.data = (nodemask_t *)oldmem;
+ scan.data = &newmems;
/*
* The mpol_rebind_mm() call takes mmap_sem, which we couldn't
@@ -1035,6 +1044,12 @@ static void update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem,
*/
cgroup_scan_tasks(&scan);
+ /*
+ * All the tasks' nodemasks have been updated, update
+ * cs->old_mems_allowed.
+ */
+ cs->old_mems_allowed = newmems;
+
/* We're done rebinding vmas to this cpuset's new mems_allowed. */
cpuset_being_rebound = NULL;
}
@@ -1055,13 +1070,9 @@ static void update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem,
static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
const char *buf)
{
- NODEMASK_ALLOC(nodemask_t, oldmem, GFP_KERNEL);
int retval;
struct ptr_heap heap;
- if (!oldmem)
- return -ENOMEM;
-
/*
* top_cpuset.mems_allowed tracks node_stats[N_MEMORY];
* it's read-only
@@ -1090,8 +1101,8 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
goto done;
}
}
- *oldmem = cs->mems_allowed;
- if (nodes_equal(*oldmem, trialcs->mems_allowed)) {
+
+ if (nodes_equal(cs->mems_allowed, trialcs->mems_allowed)) {
retval = 0; /* Too easy - nothing to do */
goto done;
}
@@ -1107,11 +1118,10 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
cs->mems_allowed = trialcs->mems_allowed;
mutex_unlock(&callback_mutex);
- update_tasks_nodemask(cs, oldmem, &heap);
+ update_tasks_nodemask(cs, &heap);
heap_free(&heap);
done:
- NODEMASK_FREE(oldmem);
return retval;
}
@@ -1424,7 +1434,6 @@ static void cpuset_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
* Change mm, possibly for multiple threads in a threadgroup. This is
* expensive and may sleep.
*/
- cpuset_attach_nodemask_to = cs->mems_allowed;
mm = get_task_mm(leader);
if (mm) {
mpol_rebind_mm(mm, &cpuset_attach_nodemask_to);
@@ -1434,6 +1443,8 @@ static void cpuset_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
mmput(mm);
}
+ cs->old_mems_allowed = cpuset_attach_nodemask_to;
+
cs->attach_in_progress--;
/*
@@ -2000,7 +2011,7 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs)
static void cpuset_propagate_hotplug_workfn(struct work_struct *work)
{
static cpumask_t off_cpus;
- static nodemask_t off_mems, tmp_mems;
+ static nodemask_t off_mems;
struct cpuset *cs = container_of(work, struct cpuset, hotplug_work);
bool is_empty;
@@ -2021,13 +2032,12 @@ static void cpuset_propagate_hotplug_workfn(struct work_struct *work)
/* remove offline mems from @cs */
if (!nodes_empty(off_mems)) {
- tmp_mems = cs->mems_allowed;
mutex_lock(&callback_mutex);
nodes_andnot(cs->mems_allowed, cs->mems_allowed, off_mems);
mutex_unlock(&callback_mutex);
if (!nodes_empty(cs->mems_allowed))
- update_tasks_nodemask(cs, &tmp_mems, NULL);
+ update_tasks_nodemask(cs, NULL);
}
is_empty = cpumask_empty(cs->cpus_allowed) ||
@@ -2119,11 +2129,10 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
/* synchronize mems_allowed to N_MEMORY */
if (mems_updated) {
- tmp_mems = top_cpuset.mems_allowed;
mutex_lock(&callback_mutex);
top_cpuset.mems_allowed = new_mems;
mutex_unlock(&callback_mutex);
- update_tasks_nodemask(&top_cpuset, &tmp_mems, NULL);
+ update_tasks_nodemask(&top_cpuset, NULL);
}
/* if cpus or mems went down, we need to propagate to descendants */
@@ -2196,6 +2205,7 @@ void __init cpuset_init_smp(void)
{
cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);
top_cpuset.mems_allowed = node_states[N_MEMORY];
+ top_cpuset.old_mems_allowed = top_cpuset.mems_allowed;
hotplug_memory_notifier(cpuset_track_online_nodes, 10);
--
1.8.0.2
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists