| 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: <c8eebc438e057e4bc2ce00256664b7bb0561b323.1607036601.git.reinette.chatre@intel.com>
Date: Thu, 3 Dec 2020 15:25:49 -0800
From: Reinette Chatre <reinette.chatre@...el.com>
To: tglx@...utronix.de, fenghua.yu@...el.com, bp@...en8.de,
tony.luck@...el.com
Cc: kuo-lang.tseng@...el.com, shakeelb@...gle.com,
valentin.schneider@....com, mingo@...hat.com, babu.moger@....com,
james.morse@....com, hpa@...or.com, x86@...nel.org,
linux-kernel@...r.kernel.org,
Reinette Chatre <reinette.chatre@...el.com>,
stable@...r.kernel.org
Subject: [PATCH 2/3] x86/resctrl: Update PQR_ASSOC MSR synchronously when moving task to resource group
From: Fenghua Yu <fenghua.yu@...el.com>
Currently when moving a task to a resource group the PQR_ASSOC MSR
is updated with the new closid and rmid in an added task callback.
If the task is running the work is run as soon as possible. If the
task is not running the work is executed later in the kernel exit path
when the kernel returns to the task again.
Updating the PQR_ASSOC MSR as soon as possible on the CPU a moved task
is running is the right thing to do. Queueing work for a task that is
not running is unnecessary (the PQR_ASSOC MSR is already updated when the
task is scheduled in) and causing system resource waste with the way in
which it is implemented: Work to update the PQR_ASSOC register is queued
every time the user writes a task id to the "tasks" file, even if the task
already belongs to the resource group. This could result in multiple pending
work items associated with a single task even if they are all identical and
even though only a single update with most recent values is needed.
Specifically, even if a task is moved between different resource groups
while it is sleeping then it is only the last move that is relevant but
yet a work item is queued during each move.
This unnecessary queueing of work items could result in significant system
resource waste, especially on tasks sleeping for a long time. For example,
as demonstrated by Shakeel Butt in [1] writing the same task id to the
"tasks" file can quickly consume significant memory. The same problem
(wasted system resources) occurs when moving a task between different
resource groups.
As pointed out by Valentin Schneider in [2] there is an additional issue with
the way in which the queueing of work is done in that the task_struct update
is currently done after the work is queued, resulting in a race with the
register update possibly done before the data needed by the update is available.
To solve these issues, the PQR_ASSOC MSR is updated in a synchronous way
right after the new closid and rmid are ready during the task movement,
only if the task is running. If a moved task is not running nothing is
done since the PQR_ASSOC MSR will be updated next time the task is scheduled.
This is the same way used to update the register when tasks are moved as
part of resource group removal.
[1] https://lore.kernel.org/lkml/CALvZod7E9zzHwenzf7objzGKsdBmVwTgEJ0nPgs0LUFU3SN5Pw@mail.gmail.com/
[2] https://lore.kernel.org/lkml/20201123022433.17905-1-valentin.schneider@arm.com
Fixes: e02737d5b826 ("x86/intel_rdt: Add tasks files")
Reported-by: Shakeel Butt <shakeelb@...gle.com>
Reported-by: Valentin Schneider <valentin.schneider@....com>
Signed-off-by: Fenghua Yu <fenghua.yu@...el.com>
Signed-off-by: Reinette Chatre <reinette.chatre@...el.com>
Reviewed-by: Tony Luck <tony.luck@...el.com>
Cc: stable@...r.kernel.org
---
arch/x86/kernel/cpu/resctrl/rdtgroup.c | 123 ++++++++++---------------
1 file changed, 50 insertions(+), 73 deletions(-)
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 68db7d2dec8f..9d62f1fadcc3 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -525,6 +525,16 @@ static void rdtgroup_remove(struct rdtgroup *rdtgrp)
kfree(rdtgrp);
}
+static void _update_task_closid_rmid(void *task)
+{
+ /*
+ * If the task is still current on this CPU, update PQR_ASSOC MSR.
+ * Otherwise, the MSR is updated when the task is scheduled in.
+ */
+ if (task == current)
+ resctrl_sched_in();
+}
+
#ifdef CONFIG_SMP
/* Get the CPU if the task is on it. */
static bool task_on_cpu(struct task_struct *t, int *cpu)
@@ -552,94 +562,61 @@ static void set_task_cpumask(struct task_struct *t, struct cpumask *mask)
if (mask && task_on_cpu(t, &cpu))
cpumask_set_cpu(cpu, mask);
}
-#else
-static inline void
-set_task_cpumask(struct task_struct *t, struct cpumask *mask) { }
-#endif
-
-struct task_move_callback {
- struct callback_head work;
- struct rdtgroup *rdtgrp;
-};
-static void move_myself(struct callback_head *head)
+static void update_task_closid_rmid(struct task_struct *t)
{
- struct task_move_callback *callback;
- struct rdtgroup *rdtgrp;
-
- callback = container_of(head, struct task_move_callback, work);
- rdtgrp = callback->rdtgrp;
-
- /*
- * If resource group was deleted before this task work callback
- * was invoked, then assign the task to root group and free the
- * resource group.
- */
- if (atomic_dec_and_test(&rdtgrp->waitcount) &&
- (rdtgrp->flags & RDT_DELETED)) {
- current->closid = 0;
- current->rmid = 0;
- rdtgroup_remove(rdtgrp);
- }
+ int cpu;
- if (unlikely(current->flags & PF_EXITING))
- goto out;
+ if (task_on_cpu(t, &cpu))
+ smp_call_function_single(cpu, _update_task_closid_rmid, t, 1);
+}
- preempt_disable();
- /* update PQR_ASSOC MSR to make resource group go into effect */
- resctrl_sched_in();
- preempt_enable();
+#else
+static inline void
+set_task_cpumask(struct task_struct *t, struct cpumask *mask) { }
-out:
- kfree(callback);
+static void update_task_closid_rmid(struct task_struct *t)
+{
+ _update_task_closid_rmid(t);
}
+#endif
static int __rdtgroup_move_task(struct task_struct *tsk,
struct rdtgroup *rdtgrp)
{
- struct task_move_callback *callback;
- int ret;
-
- callback = kzalloc(sizeof(*callback), GFP_KERNEL);
- if (!callback)
- return -ENOMEM;
- callback->work.func = move_myself;
- callback->rdtgrp = rdtgrp;
-
/*
- * Take a refcount, so rdtgrp cannot be freed before the
- * callback has been invoked.
+ * Set the task's closid/rmid before the PQR_ASSOC MSR can be
+ * updated by them.
+ *
+ * For ctrl_mon groups, move both closid and rmid.
+ * For monitor groups, can move the tasks only from
+ * their parent CTRL group.
*/
- atomic_inc(&rdtgrp->waitcount);
- ret = task_work_add(tsk, &callback->work, TWA_RESUME);
- if (ret) {
- /*
- * Task is exiting. Drop the refcount and free the callback.
- * No need to check the refcount as the group cannot be
- * deleted before the write function unlocks rdtgroup_mutex.
- */
- 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;
+
+ if (rdtgrp->type == RDTCTRL_GROUP) {
+ tsk->closid = rdtgrp->closid;
+ tsk->rmid = rdtgrp->mon.rmid;
+ } else if (rdtgrp->type == RDTMON_GROUP) {
+ if (rdtgrp->mon.parent->closid == tsk->closid) {
tsk->rmid = rdtgrp->mon.rmid;
- } else if (rdtgrp->type == RDTMON_GROUP) {
- if (rdtgrp->mon.parent->closid == tsk->closid) {
- tsk->rmid = rdtgrp->mon.rmid;
- } else {
- rdt_last_cmd_puts("Can't move task to different control group\n");
- ret = -EINVAL;
- }
+ } else {
+ rdt_last_cmd_puts("Can't move task to different control group\n");
+ return -EINVAL;
}
+ } else {
+ rdt_last_cmd_puts("Invalid resource group type\n");
+ return -EINVAL;
}
- return ret;
+
+ /*
+ * By now, the task's closid and rmid are set. If the task is current
+ * on a CPU, the PQR_ASSOC MSR needs to be updated to make the resource
+ * group go into effect. If the task is not current, the MSR will be
+ * updated when the task is scheduled in.
+ */
+ update_task_closid_rmid(tsk);
+
+ return 0;
}
static bool is_closid_match(struct task_struct *t, struct rdtgroup *r)
--
2.26.2
Powered by blists - more mailing lists