This is a note to let you know that I've just added the patch titled
kfence: allow use of a deferrable timer
to the 5.15-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
kfence-allow-use-of-a-deferrable-timer.patch
and it can be found in the queue-5.15 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 9990d9eb1f985367e346dfa3f65d5142375491a9
Author: Marco Elver <elver@xxxxxxxxxx>
Date: Tue Mar 22 14:48:25 2022 -0700
kfence: allow use of a deferrable timer
[ Upstream commit 737b6a10ac19e41877aa1911bf6b361a72a88ad9 ]
Allow the use of a deferrable timer, which does not force CPU wake-ups
when the system is idle. A consequence is that the sample interval
becomes very unpredictable, to the point that it is not guaranteed that
the KFENCE KUnit test still passes.
Nevertheless, on power-constrained systems this may be preferable, so
let's give the user the option should they accept the above trade-off.
Link: https://lkml.kernel.org/r/20220308141415.3168078-1-elver@xxxxxxxxxx
Signed-off-by: Marco Elver <elver@xxxxxxxxxx>
Reviewed-by: Alexander Potapenko <glider@xxxxxxxxxx>
Cc: Dmitry Vyukov <dvyukov@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Stable-dep-of: e64f81946adf ("kfence: skip __GFP_THISNODE allocations on NUMA systems")
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/Documentation/dev-tools/kfence.rst b/Documentation/dev-tools/kfence.rst
index 48244d32780f6..b6671d907836a 100644
--- a/Documentation/dev-tools/kfence.rst
+++ b/Documentation/dev-tools/kfence.rst
@@ -41,6 +41,18 @@ guarded by KFENCE. The default is configurable via the Kconfig option
``CONFIG_KFENCE_SAMPLE_INTERVAL``. Setting ``kfence.sample_interval=0``
disables KFENCE.
+The sample interval controls a timer that sets up KFENCE allocations. By
+default, to keep the real sample interval predictable, the normal timer also
+causes CPU wake-ups when the system is completely idle. This may be undesirable
+on power-constrained systems. The boot parameter ``kfence.deferrable=1``
+instead switches to a "deferrable" timer which does not force CPU wake-ups on
+idle systems, at the risk of unpredictable sample intervals. The default is
+configurable via the Kconfig option ``CONFIG_KFENCE_DEFERRABLE``.
+
+.. warning::
+ The KUnit test suite is very likely to fail when using a deferrable timer
+ since it currently causes very unpredictable sample intervals.
+
The KFENCE memory pool is of fixed size, and if the pool is exhausted, no
further KFENCE allocations occur. With ``CONFIG_KFENCE_NUM_OBJECTS`` (default
255), the number of available guarded objects can be controlled. Each object
diff --git a/lib/Kconfig.kfence b/lib/Kconfig.kfence
index 912f252a41fc6..459dda9ef619b 100644
--- a/lib/Kconfig.kfence
+++ b/lib/Kconfig.kfence
@@ -45,6 +45,18 @@ config KFENCE_NUM_OBJECTS
pages are required; with one containing the object and two adjacent
ones used as guard pages.
+config KFENCE_DEFERRABLE
+ bool "Use a deferrable timer to trigger allocations"
+ help
+ Use a deferrable timer to trigger allocations. This avoids forcing
+ CPU wake-ups if the system is idle, at the risk of a less predictable
+ sample interval.
+
+ Warning: The KUnit test suite fails with this option enabled - due to
+ the unpredictability of the sample interval!
+
+ Say N if you are unsure.
+
config KFENCE_STATIC_KEYS
bool "Use static keys to set up allocations" if EXPERT
depends on JUMP_LABEL
diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index 3eab72fb3d8c9..1a2dc187a72f9 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -89,6 +89,10 @@ module_param_cb(sample_interval, &sample_interval_param_ops, &kfence_sample_inte
static unsigned long kfence_skip_covered_thresh __read_mostly = 75;
module_param_named(skip_covered_thresh, kfence_skip_covered_thresh, ulong, 0644);
+/* If true, use a deferrable timer. */
+static bool kfence_deferrable __read_mostly = IS_ENABLED(CONFIG_KFENCE_DEFERRABLE);
+module_param_named(deferrable, kfence_deferrable, bool, 0444);
+
/* The pool of pages used for guard pages and objects. */
char *__kfence_pool __ro_after_init;
EXPORT_SYMBOL(__kfence_pool); /* Export for test modules. */
@@ -695,6 +699,8 @@ late_initcall(kfence_debugfs_init);
/* === Allocation Gate Timer ================================================ */
+static struct delayed_work kfence_timer;
+
#ifdef CONFIG_KFENCE_STATIC_KEYS
/* Wait queue to wake up allocation-gate timer task. */
static DECLARE_WAIT_QUEUE_HEAD(allocation_wait);
@@ -717,7 +723,6 @@ static DEFINE_IRQ_WORK(wake_up_kfence_timer_work, wake_up_kfence_timer);
* avoids IPIs, at the cost of not immediately capturing allocations if the
* instructions remain cached.
*/
-static struct delayed_work kfence_timer;
static void toggle_allocation_gate(struct work_struct *work)
{
if (!READ_ONCE(kfence_enabled))
@@ -745,7 +750,6 @@ static void toggle_allocation_gate(struct work_struct *work)
queue_delayed_work(system_unbound_wq, &kfence_timer,
msecs_to_jiffies(kfence_sample_interval));
}
-static DECLARE_DELAYED_WORK(kfence_timer, toggle_allocation_gate);
/* === Public interface ===================================================== */
@@ -774,8 +778,15 @@ void __init kfence_init(void)
if (!IS_ENABLED(CONFIG_KFENCE_STATIC_KEYS))
static_branch_enable(&kfence_allocation_key);
+
+ if (kfence_deferrable)
+ INIT_DEFERRABLE_WORK(&kfence_timer, toggle_allocation_gate);
+ else
+ INIT_DELAYED_WORK(&kfence_timer, toggle_allocation_gate);
+
WRITE_ONCE(kfence_enabled, true);
queue_delayed_work(system_unbound_wq, &kfence_timer, 0);
+
pr_info("initialized - using %lu bytes for %d objects at 0x%p-0x%p\n", KFENCE_POOL_SIZE,
CONFIG_KFENCE_NUM_OBJECTS, (void *)__kfence_pool,
(void *)(__kfence_pool + KFENCE_POOL_SIZE));
