The patch titled
cpuset: fix the problem that cpuset_mem_spread_node() returns an offline node
has been added to the -mm tree. Its filename is
cpuset-fix-the-problem-that-cpuset_mem_spread_node-returns-an-offline-node.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: fix the problem that cpuset_mem_spread_node() returns an offline node
From: Miao Xie <miaox@xxxxxxxxxxxxxx>
cpuset_mem_spread_node() returns an offline node, and causes an oops.
This patch fixes it by initializing task->mems_allowed to
node_states[N_HIGH_MEMORY], and updating task->mems_allowed when doing
memory hotplug.
Signed-off-by: Miao Xie <miaox@xxxxxxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Lee Schermerhorn <lee.schermerhorn@xxxxxx>
Cc: Nick Piggin <npiggin@xxxxxxx>
Cc: Paul Menage <menage@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
init/main.c | 2 +-
kernel/cpuset.c | 30 ++++++++++++++++++++++--------
kernel/kthread.c | 2 +-
3 files changed, 24 insertions(+), 10 deletions(-)
diff -puN init/main.c~cpuset-fix-the-problem-that-cpuset_mem_spread_node-returns-an-offline-node init/main.c
--- a/init/main.c~cpuset-fix-the-problem-that-cpuset_mem_spread_node-returns-an-offline-node
+++ a/init/main.c
@@ -865,7 +865,7 @@ static int __init kernel_init(void * unu
/*
* init can allocate pages on any node
*/
- set_mems_allowed(node_possible_map);
+ set_mems_allowed(node_states[N_HIGH_MEMORY]);
/*
* init can run on any cpu.
*/
diff -puN kernel/cpuset.c~cpuset-fix-the-problem-that-cpuset_mem_spread_node-returns-an-offline-node kernel/cpuset.c
--- a/kernel/cpuset.c~cpuset-fix-the-problem-that-cpuset_mem_spread_node-returns-an-offline-node
+++ a/kernel/cpuset.c
@@ -920,9 +920,6 @@ static int update_cpumask(struct cpuset
* call to guarantee_online_mems(), as we know no one is changing
* our task's cpuset.
*
- * Hold callback_mutex around the two modifications of our tasks
- * mems_allowed to synchronize with cpuset_mems_allowed().
- *
* While the mm_struct we are migrating is typically from some
* other task, the task_struct mems_allowed that we are hacking
* is for our current task, which must allocate new pages for that
@@ -936,9 +933,23 @@ static void cpuset_migrate_mm(struct mm_
tsk->mems_allowed = *to;
+ /*
+ * After current->mems_allowed is set to a new value, current will
+ * allocate new pages for the migrating memory region. So we must
+ * ensure that update of current->mems_allowed have been completed
+ * by this moment.
+ */
+ smp_wmb();
do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);
guarantee_online_mems(task_cs(tsk),&tsk->mems_allowed);
+
+ /*
+ * After doing migrate pages, current will allocate new pages for
+ * itself not the other tasks. So we must ensure that update of
+ * current->mems_allowed have been completed by this moment.
+ */
+ smp_wmb();
}
/*
@@ -1391,11 +1402,10 @@ static void cpuset_attach(struct cgroup_
if (cs == &top_cpuset) {
cpumask_copy(cpus_attach, cpu_possible_mask);
- to = node_possible_map;
} else {
guarantee_online_cpus(cs, cpus_attach);
- guarantee_online_mems(cs, &to);
}
+ guarantee_online_mems(cs, &to);
/* do per-task migration stuff possibly for each in the threadgroup */
cpuset_attach_task(tsk, &to, cs);
@@ -2090,15 +2100,19 @@ static int cpuset_track_online_cpus(stru
static int cpuset_track_online_nodes(struct notifier_block *self,
unsigned long action, void *arg)
{
+ nodemask_t oldmems;
+
cgroup_lock();
switch (action) {
case MEM_ONLINE:
- case MEM_OFFLINE:
+ oldmems = top_cpuset.mems_allowed;
mutex_lock(&callback_mutex);
top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
mutex_unlock(&callback_mutex);
- if (action == MEM_OFFLINE)
- scan_for_empty_cpusets(&top_cpuset);
+ update_tasks_nodemask(&top_cpuset, &oldmems, NULL);
+ break;
+ case MEM_OFFLINE:
+ scan_for_empty_cpusets(&top_cpuset);
break;
default:
break;
diff -puN kernel/kthread.c~cpuset-fix-the-problem-that-cpuset_mem_spread_node-returns-an-offline-node kernel/kthread.c
--- a/kernel/kthread.c~cpuset-fix-the-problem-that-cpuset_mem_spread_node-returns-an-offline-node
+++ a/kernel/kthread.c
@@ -219,7 +219,7 @@ int kthreadd(void *unused)
set_task_comm(tsk, "kthreadd");
ignore_signals(tsk);
set_cpus_allowed_ptr(tsk, cpu_all_mask);
- set_mems_allowed(node_possible_map);
+ set_mems_allowed(node_states[N_HIGH_MEMORY]);
current->flags |= PF_NOFREEZE | PF_FREEZER_NOSIG;
_
Patches currently in -mm which might be from miaox@xxxxxxxxxxxxxx are
cpuset-fix-the-problem-that-cpuset_mem_spread_node-returns-an-offline-node.patch
nodemask-fix-the-declaration-of-nodemask_alloc.patch
cpuset-alloc-nodemask_t-at-heap-not-stack.patch
cpusetmm-use-rwlock-to-protect-task-mempolicy-and-mems_allowed.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
