The patch titled
cpuset: avoid changing cpuset's mems when errno returned
has been added to the -mm tree. Its filename is
cpuset-avoid-changing-cpusets-mems-when-errno-returned.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: cpuset: avoid changing cpuset's mems when errno returned
From: Li Zefan <lizf@xxxxxxxxxxxxxx>
When writing to cpuset.mems, cpuset has to update its mems_allowed before
calling update_tasks_nodemask(), but this function might return -ENOMEM.
To avoid this rare case, we allocate the memory before changing
mems_allowed, and then pass to update_tasks_nodemask(). Similar to what
update_cpumask() does.
Signed-off-by: Li Zefan <lizf@xxxxxxxxxxxxxx>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Cc: Paul Menage <menage@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
kernel/cpuset.c | 25 ++++++++++++++++---------
1 file changed, 16 insertions(+), 9 deletions(-)
diff -puN kernel/cpuset.c~cpuset-avoid-changing-cpusets-mems-when-errno-returned kernel/cpuset.c
--- a/kernel/cpuset.c~cpuset-avoid-changing-cpusets-mems-when-errno-returned
+++ a/kernel/cpuset.c
@@ -1057,13 +1057,15 @@ 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 cgroup_mutex held
- * Return 0 if successful, -errno if not.
+ * No return value. It's guaranteed that cgroup_scan_tasks() always returns 0
+ * if @heap != NULL.
*/
-static int update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem)
+static void update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem,
+ struct ptr_heap *heap)
{
- int retval;
struct cgroup_scanner scan;
cpuset_being_rebound = cs; /* causes mpol_dup() rebind */
@@ -1071,7 +1073,7 @@ static int update_tasks_nodemask(struct
scan.cg = cs->css.cgroup;
scan.test_task = NULL;
scan.process_task = cpuset_change_nodemask;
- scan.heap = NULL;
+ scan.heap = heap;
scan.data = (nodemask_t *)oldmem;
/*
@@ -1084,12 +1086,10 @@ static int update_tasks_nodemask(struct
* It's ok if we rebind the same mm twice; mpol_rebind_mm()
* is idempotent. Also migrate pages in each mm to new nodes.
*/
- retval = cgroup_scan_tasks(&scan);
+ cgroup_scan_tasks(&scan);
/* We're done rebinding vmas to this cpuset's new mems_allowed. */
cpuset_being_rebound = NULL;
-
- return retval;
}
/*
@@ -1110,6 +1110,7 @@ static int update_nodemask(struct cpuset
{
nodemask_t oldmem;
int retval;
+ struct ptr_heap heap;
/*
* top_cpuset.mems_allowed tracks node_stats[N_HIGH_MEMORY];
@@ -1144,12 +1145,18 @@ static int update_nodemask(struct cpuset
if (retval < 0)
goto done;
+ retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL);
+ if (retval < 0)
+ goto done;
+
mutex_lock(&callback_mutex);
cs->mems_allowed = trialcs->mems_allowed;
cs->mems_generation = cpuset_mems_generation++;
mutex_unlock(&callback_mutex);
- retval = update_tasks_nodemask(cs, &oldmem);
+ update_tasks_nodemask(cs, &oldmem, &heap);
+
+ heap_free(&heap);
done:
return retval;
}
@@ -2002,7 +2009,7 @@ static void scan_for_empty_cpusets(struc
remove_tasks_in_empty_cpuset(cp);
else {
update_tasks_cpumask(cp, NULL);
- update_tasks_nodemask(cp, &oldmems);
+ update_tasks_nodemask(cp, &oldmems, NULL);
}
}
}
_
Patches currently in -mm which might be from lizf@xxxxxxxxxxxxxx are
linux-next.patch
vfs-add-missing-unlock-in-sget.patch
relax-ns_can_attach-checks-to-allow-attaching-to-grandchild-cgroups.patch
cgroup-css-id-support.patch
cgroup-fix-frequent-ebusy-at-rmdir.patch
cgroups-more-documentation-for-remount-and-release_agent.patch
memcg-use-css-id.patch
memcg-hierarchical-stat.patch
memcg-fix-shrinking-memory-to-return-ebusy-by-fixing-retry-algorithm.patch
memcg-fix-oom-killer-under-memcg.patch
memcg-fix-oom-killer-under-memcg-fix2.patch
memcg-fix-oom-killer-under-memcg-fix.patch
memcg-show-memcg-information-during-oom.patch
memcg-show-memcg-information-during-oom-fix2.patch
memcg-show-memcg-information-during-oom-fix.patch
memcg-show-memcg-information-during-oom-fix-fix.patch
memcg-show-memcg-information-during-oom-fix-fix-checkpatch-fixes.patch
use-css-id-in-swap_cgroup-for-saving-memory-v4.patch
cpuset-fix-possible-races-in-cpu-memory-hotplug.patch
cgroups-add-data-field-to-struct-cgroup_scanner.patch
cpuset-rewrite-update_tasks_nodemask.patch
cpuset-avoid-changing-cpusets-mems-when-errno-returned.patch
cpuset-remove-struct-cpuset_hotplug_scanner.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
