Upon moving a task to a new control / monitor group, said task's
{closid, rmid} fields are updated *after* triggering the move_myself()
task_work callback. If the triggering thread gets preempted, or if the
targeted task was already on its way to return to userspace, then
move_myself() might be executed before the relevant task's {closid, rmid}
fields have been updated.
Update the task_struct's {closid, rmid} tuple *before* invoking
task_work_add(). Highlight the required ordering with a pair of comments.
Fixes: e02737d5b826 ("x86/intel_rdt: Add tasks files")
Reviewed-by: James Morse <[email protected]>
Signed-off-by: Valentin Schneider <[email protected]>
---
arch/x86/kernel/cpu/resctrl/rdtgroup.c | 34 ++++++++++++++++----------
1 file changed, 21 insertions(+), 13 deletions(-)
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index b6b5b95df833..f62d81104fd0 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -524,6 +524,8 @@ static void move_myself(struct callback_head *head)
* If resource group was deleted before this task work callback
* was invoked, then assign the task to root group and free the
* resource group.
+ *
+ * See pairing atomic_inc() in __rdtgroup_move_task()
*/
if (atomic_dec_and_test(&rdtgrp->waitcount) &&
(rdtgrp->flags & RDT_DELETED)) {
@@ -553,14 +555,32 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
callback = kzalloc(sizeof(*callback), GFP_KERNEL);
if (!callback)
return -ENOMEM;
- callback->work.func = move_myself;
+
+ init_task_work(&callback->work, move_myself);
callback->rdtgrp = rdtgrp;
+ /*
+ * For ctrl_mon groups move both closid and rmid.
+ * For monitor groups, can move the tasks only from
+ * their parent CTRL group.
+ */
+ if (rdtgrp->type == RDTCTRL_GROUP)
+ tsk->closid = rdtgrp->closid;
+ tsk->rmid = rdtgrp->mon.rmid;
+
/*
* Take a refcount, so rdtgrp cannot be freed before the
* callback has been invoked.
+ *
+ * Also ensures above {closid, rmid} writes are observed by
+ * move_myself(), as it can run immediately after task_work_add().
+ * Otherwise old values may be loaded, and the move will only actually
+ * happen at the next context switch.
+ *
+ * Pairs with atomic_dec() in move_myself().
*/
atomic_inc(&rdtgrp->waitcount);
+
ret = task_work_add(tsk, &callback->work, TWA_RESUME);
if (ret) {
/*
@@ -571,18 +591,6 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
atomic_dec(&rdtgrp->waitcount);
kfree(callback);
rdt_last_cmd_puts("Task exited\n");
- } else {
- /*
- * For ctrl_mon groups move both closid and rmid.
- * For monitor groups, can move the tasks only from
- * their parent CTRL group.
- */
- if (rdtgrp->type == RDTCTRL_GROUP) {
- tsk->closid = rdtgrp->closid;
- tsk->rmid = rdtgrp->mon.rmid;
- } else if (rdtgrp->type == RDTMON_GROUP) {
- tsk->rmid = rdtgrp->mon.rmid;
- }
}
return ret;
}
--
2.27.0
