From: Alexander Potapenko <glider@google.com>
To: syzbot@lists.linux.dev
Subject: [PATCH v7] kcov: fix data corruption and race conditions on PREEMPT_RT by moving saved remote state to task_struct (v7)
Date: Mon, 20 Jul 2026 12:41:26 +0000 [thread overview]
Message-ID: <20260720124126.1977559-1-glider@google.com> (raw)
syzbot is reporting KCOV state corruption on PREEMPT_RT kernels, for the temporary storage used for saving/restoring remote KCOV state is currently allocated as the per-CPU area.
On PREEMPT_RT kernels, softirq handlers run as preemptible task threads (e.g., ksoftirqd). If a softirq context preempts a task running a remote KCOV session, it safely saves the task's state into the per-CPU area.
However, if that softirq thread is subsequently preempted by a higher-priority softirq thread on the same CPU, the second softirq will overwrite the same per-CPU area, permanently destroying the original task's KCOV state.
Fix this data corruption by moving the temporary storage from the per-CPU area to the per-thread area. Since each softirq thread now owns its own task context, nested softirq preemption no longer causes data overwrites.
Note that while the temporary storage is now on a per-thread basis, the per-CPU kcov_percpu_data.lock must be retained, for we need to ensure that kcov_remote_start() and kcov_remote_stop() operate atomically without racing against asynchronous interrupts that manipulate the current task's KCOV state.
Fixes: 5ff3b30ab57d ("kcov: collect coverage from interrupts")
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
---
include/linux/sched.h | 8 ++++
kernel/kcov.c | 90 ++++++++++++++++++++++---------------------
lib/Kconfig.debug | 5 ++-
3 files changed, 58 insertions(+), 45 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 373bcc0598d1..7a53c15cecb5 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1543,6 +1543,14 @@ struct task_struct {
/* Collect coverage from softirq context: */
unsigned int kcov_softirq;
+
+ /* Temporary storage for preempting remote coverage collection: */
+ unsigned int kcov_saved_mode;
+ unsigned int kcov_saved_size;
+ void *kcov_saved_area;
+ struct kcov *kcov_saved_kcov;
+ int kcov_saved_sequence;
+
#endif
#ifdef CONFIG_MEMCG_V1
diff --git a/kernel/kcov.c b/kernel/kcov.c
index 1df373fb562b..a7514303eff3 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -86,17 +86,12 @@ struct kcov_remote {
static DEFINE_SPINLOCK(kcov_remote_lock);
static DEFINE_HASHTABLE(kcov_remote_map, 4);
-static struct list_head kcov_remote_areas = LIST_HEAD_INIT(kcov_remote_areas);
+static struct list_head kcov_remote_areas[2] = {
+ LIST_HEAD_INIT(kcov_remote_areas[0]), LIST_HEAD_INIT(kcov_remote_areas[1])
+};
struct kcov_percpu_data {
- void *irq_area;
local_lock_t lock;
-
- unsigned int saved_mode;
- unsigned int saved_size;
- void *saved_area;
- struct kcov *saved_kcov;
- int saved_sequence;
};
static DEFINE_PER_CPU(struct kcov_percpu_data, kcov_percpu_data) = {
@@ -132,12 +127,13 @@ static struct kcov_remote *kcov_remote_add(struct kcov *kcov, u64 handle)
}
/* Must be called with kcov_remote_lock locked. */
-static struct kcov_remote_area *kcov_remote_area_get(unsigned int size)
+static struct kcov_remote_area *kcov_remote_area_get(unsigned int size, bool irq)
{
struct kcov_remote_area *area;
struct list_head *pos;
+ struct list_head *list = &kcov_remote_areas[irq];
- list_for_each(pos, &kcov_remote_areas) {
+ list_for_each(pos, list) {
area = list_entry(pos, struct kcov_remote_area, list);
if (area->size == size) {
list_del(&area->list);
@@ -149,11 +145,11 @@ static struct kcov_remote_area *kcov_remote_area_get(unsigned int size)
/* Must be called with kcov_remote_lock locked. */
static void kcov_remote_area_put(struct kcov_remote_area *area,
- unsigned int size)
+ unsigned int size, bool irq)
{
INIT_LIST_HEAD(&area->list);
area->size = size;
- list_add(&area->list, &kcov_remote_areas);
+ list_add(&area->list, &kcov_remote_areas[irq]);
/*
* KMSAN doesn't instrument this file, so it may not know area->list
* is initialized. Unpoison it explicitly to avoid reports in
@@ -390,6 +386,12 @@ void kcov_task_init(struct task_struct *t)
kcov_task_reset(t);
t->kcov_remote = NULL;
t->kcov_handle = current->kcov_handle;
+ t->kcov_softirq = 0;
+ t->kcov_saved_mode = 0;
+ t->kcov_saved_size = 0;
+ t->kcov_saved_area = NULL;
+ t->kcov_saved_kcov = NULL;
+ t->kcov_saved_sequence = 0;
}
static void kcov_reset(struct kcov *kcov)
@@ -836,17 +838,16 @@ static inline bool kcov_mode_enabled(unsigned int mode)
static void kcov_remote_softirq_start(struct task_struct *t)
__must_hold(&kcov_percpu_data.lock)
{
- struct kcov_percpu_data *data = this_cpu_ptr(&kcov_percpu_data);
unsigned int mode;
mode = READ_ONCE(t->kcov_mode);
barrier();
if (kcov_mode_enabled(mode)) {
- data->saved_mode = mode;
- data->saved_size = t->kcov_size;
- data->saved_area = t->kcov_area;
- data->saved_sequence = t->kcov_sequence;
- data->saved_kcov = t->kcov;
+ t->kcov_saved_mode = mode;
+ t->kcov_saved_size = t->kcov_size;
+ t->kcov_saved_area = t->kcov_area;
+ t->kcov_saved_sequence = t->kcov_sequence;
+ t->kcov_saved_kcov = t->kcov;
kcov_stop(t);
}
}
@@ -854,17 +855,15 @@ static void kcov_remote_softirq_start(struct task_struct *t)
static void kcov_remote_softirq_stop(struct task_struct *t)
__must_hold(&kcov_percpu_data.lock)
{
- struct kcov_percpu_data *data = this_cpu_ptr(&kcov_percpu_data);
-
- if (data->saved_kcov) {
- kcov_start(t, data->saved_kcov, data->saved_size,
- data->saved_area, data->saved_mode,
- data->saved_sequence);
- data->saved_mode = 0;
- data->saved_size = 0;
- data->saved_area = NULL;
- data->saved_sequence = 0;
- data->saved_kcov = NULL;
+ if (t->kcov_saved_kcov) {
+ kcov_start(t, t->kcov_saved_kcov, t->kcov_saved_size,
+ t->kcov_saved_area, t->kcov_saved_mode,
+ t->kcov_saved_sequence);
+ t->kcov_saved_mode = 0;
+ t->kcov_saved_size = 0;
+ t->kcov_saved_area = NULL;
+ t->kcov_saved_sequence = 0;
+ t->kcov_saved_kcov = NULL;
}
}
@@ -927,17 +926,17 @@ void kcov_remote_start(u64 handle)
sequence = kcov->sequence;
if (in_task()) {
size = kcov->remote_size;
- area = kcov_remote_area_get(size);
+ area = kcov_remote_area_get(size, false);
} else {
size = CONFIG_KCOV_IRQ_AREA_SIZE;
- area = this_cpu_ptr(&kcov_percpu_data)->irq_area;
+ area = kcov_remote_area_get(size, true);
}
spin_unlock(&kcov_remote_lock);
- /* Can only happen when in_task(). */
+ /* Allocate new buffer if we can sleep. */
if (!area) {
local_unlock_irqrestore(&kcov_percpu_data.lock, flags);
- area = vmalloc(size * sizeof(unsigned long));
+ area = in_task() ? vmalloc(size * sizeof(unsigned long)) : NULL;
if (!area) {
kcov_put(kcov);
return;
@@ -1079,11 +1078,9 @@ void kcov_remote_stop(void)
kcov_move_area(kcov->mode, kcov->area, kcov->size, area);
spin_unlock(&kcov->lock);
- if (in_task()) {
- spin_lock(&kcov_remote_lock);
- kcov_remote_area_put(area, size);
- spin_unlock(&kcov_remote_lock);
- }
+ spin_lock(&kcov_remote_lock);
+ kcov_remote_area_put(area, size, !in_task());
+ spin_unlock(&kcov_remote_lock);
local_unlock_irqrestore(&kcov_percpu_data.lock, flags);
@@ -1129,14 +1126,21 @@ static void __init selftest(void)
static int __init kcov_init(void)
{
- int cpu;
+ int cpu = num_possible_cpus();
+
+#ifdef CONFIG_PREEMPT_RT
+ /* Allocate some extra buffers in order to prepare for softirq preemption. */
+ cpu = cpu >= 4 ? cpu * 2 : cpu + 4;
+#endif
+ while (cpu--) {
+ void *area = vmalloc(CONFIG_KCOV_IRQ_AREA_SIZE * sizeof(unsigned long));
+ unsigned long flags;
- for_each_possible_cpu(cpu) {
- void *area = vmalloc_node(CONFIG_KCOV_IRQ_AREA_SIZE *
- sizeof(unsigned long), cpu_to_node(cpu));
if (!area)
return -ENOMEM;
- per_cpu_ptr(&kcov_percpu_data, cpu)->irq_area = area;
+ spin_lock_irqsave(&kcov_remote_lock, flags);
+ kcov_remote_area_put(area, CONFIG_KCOV_IRQ_AREA_SIZE, true);
+ spin_unlock_irqrestore(&kcov_remote_lock, flags);
}
/*
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 1244dcac2294..12786379bf1d 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2247,10 +2247,11 @@ config KCOV_INSTRUMENT_ALL
config KCOV_IRQ_AREA_SIZE
hex "Size of interrupt coverage collection area in words"
depends on KCOV
+ range 0x80 0x1000000
default 0x40000
help
- KCOV uses preallocated per-cpu areas to collect coverage from
- soft interrupts. This specifies the size of those areas in the
+ KCOV uses preallocated areas to collect coverage from soft
+ interrupts. This specifies the size of those areas in the
number of unsigned long words.
config KCOV_SELFTEST
--
2.55.0.229.g6434b31f56-goog
next reply other threads:[~2026-07-20 12:41 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-07-20 12:41 Alexander Potapenko [this message]
2026-07-21 14:51 ` [syzbot ci] Re: kcov: fix data corruption and race conditions on PREEMPT_RT by moving saved remote state to task_struct (v7) syzbot ci
2026-07-21 14:51 ` syzbot ci
-- strict thread matches above, loose matches on Subject: below --
2026-07-20 15:01 [PATCH v7] " Alexander Potapenko
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260720124126.1977559-1-glider@google.com \
--to=glider@google.com \
--cc=syzbot@lists.linux.dev \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.