diff options
authorMarco Elver <>2021-05-04 18:40:21 -0700
committerLinus Torvalds <>2021-05-05 11:27:27 -0700
commit407f1d8c1b5f3ec66a6a3eb835d3b81c76440f4e (patch)
parent94868a1e127bbe0e03a4467f27196cd668cbc344 (diff)
kfence: await for allocation using wait_event
Patch series "kfence: optimize timer scheduling", v2. We have observed that mostly-idle systems with KFENCE enabled wake up otherwise idle CPUs, preventing such to enter a lower power state. Debugging revealed that KFENCE spends too much active time in toggle_allocation_gate(). While the first version of KFENCE was using all the right bits to be scheduling optimal, and thus power efficient, by simply using wait_event() + wake_up(), that code was unfortunately removed. As KFENCE was exposed to various different configs and tests, the scheduling optimal code slowly disappeared. First because of hung task warnings, and finally because of deadlocks when an allocation is made by timer code with debug objects enabled. Clearly, the "fixes" were not too friendly for devices that want to be power efficient. Therefore, let's try a little harder to fix the hung task and deadlock problems that we have with wait_event() + wake_up(), while remaining as scheduling friendly and power efficient as possible. Crucially, we need to defer the wake_up() to an irq_work, avoiding any potential for deadlock. The result with this series is that on the devices where we observed a power regression, power usage returns back to baseline levels. This patch (of 3): On mostly-idle systems, we have observed that toggle_allocation_gate() is a cause of frequent wake-ups, preventing an otherwise idle CPU to go into a lower power state. A late change in KFENCE's development, due to a potential deadlock [1], required changing the scheduling-friendly wait_event_timeout() and wake_up() to an open-coded wait-loop using schedule_timeout(). [1] To avoid unnecessary wake-ups, switch to using wait_event_timeout(). Unfortunately, we still cannot use a version with direct wake_up() in __kfence_alloc() due to the same potential for deadlock as in [1]. Instead, add a level of indirection via an irq_work that is scheduled if we determine that the kfence_timer requires a wake_up(). Link: Link: Fixes: 0ce20dd84089 ("mm: add Kernel Electric-Fence infrastructure") Signed-off-by: Marco Elver <> Cc: Alexander Potapenko <> Cc: Dmitry Vyukov <> Cc: Jann Horn <> Cc: Mark Rutland <> Cc: Hillf Danton <> Signed-off-by: Andrew Morton <> Signed-off-by: Linus Torvalds <>
2 files changed, 30 insertions, 16 deletions
diff --git a/lib/Kconfig.kfence b/lib/Kconfig.kfence
index 78f50ccb3b45..e641add33947 100644
--- a/lib/Kconfig.kfence
+++ b/lib/Kconfig.kfence
@@ -7,6 +7,7 @@ menuconfig KFENCE
bool "KFENCE: low-overhead sampling-based memory safety error detector"
depends on HAVE_ARCH_KFENCE && (SLAB || SLUB)
+ select IRQ_WORK
KFENCE is a low-overhead sampling-based detector of heap out-of-bounds
access, use-after-free, and invalid-free errors. KFENCE is designed
diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index 768dbd58170d..235d726f88bc 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -10,6 +10,7 @@
#include <linux/atomic.h>
#include <linux/bug.h>
#include <linux/debugfs.h>
+#include <linux/irq_work.h>
#include <linux/kcsan-checks.h>
#include <linux/kfence.h>
#include <linux/kmemleak.h>
@@ -587,6 +588,17 @@ late_initcall(kfence_debugfs_init);
/* === Allocation Gate Timer ================================================ */
+/* Wait queue to wake up allocation-gate timer task. */
+static DECLARE_WAIT_QUEUE_HEAD(allocation_wait);
+static void wake_up_kfence_timer(struct irq_work *work)
+ wake_up(&allocation_wait);
+static DEFINE_IRQ_WORK(wake_up_kfence_timer_work, wake_up_kfence_timer);
* Set up delayed work, which will enable and disable the static key. We need to
* use a work queue (rather than a simple timer), since enabling and disabling a
@@ -604,25 +616,13 @@ static void toggle_allocation_gate(struct work_struct *work)
if (!READ_ONCE(kfence_enabled))
- /* Enable static key, and await allocation to happen. */
atomic_set(&kfence_allocation_gate, 0);
+ /* Enable static key, and await allocation to happen. */
- /*
- * Await an allocation. Timeout after 1 second, in case the kernel stops
- * doing allocations, to avoid stalling this worker task for too long.
- */
- {
- unsigned long end_wait = jiffies + HZ;
- do {
- set_current_state(TASK_UNINTERRUPTIBLE);
- if (atomic_read(&kfence_allocation_gate) != 0)
- break;
- schedule_timeout(1);
- } while (time_before(jiffies, end_wait));
- __set_current_state(TASK_RUNNING);
- }
+ wait_event_timeout(allocation_wait, atomic_read(&kfence_allocation_gate), HZ);
/* Disable static key and reset timer. */
@@ -729,6 +729,19 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags)
if (atomic_read(&kfence_allocation_gate) || atomic_inc_return(&kfence_allocation_gate) > 1)
return NULL;
+ /*
+ * waitqueue_active() is fully ordered after the update of
+ * kfence_allocation_gate per atomic_inc_return().
+ */
+ if (waitqueue_active(&allocation_wait)) {
+ /*
+ * Calling wake_up() here may deadlock when allocations happen
+ * from within timer code. Use an irq_work to defer it.
+ */
+ irq_work_queue(&wake_up_kfence_timer_work);
+ }
if (!READ_ONCE(kfence_enabled))
return NULL;