On Thu, Mar 6, 2025 at 7:51 AM Dmitry Torokhov dmitry.torokhov@gmail.com wrote:
If userspace reads "uevent" device attribute at the same time as another threads unbinds the device from its driver, change to dev->driver from a valid pointer to NULL may result in crash. Fix this by using READ_ONCE() when fetching the pointer, and take bus' drivers klist lock to make sure driver instance will not disappear while we access it.
Use WRITE_ONCE() when setting the driver pointer to ensure there is no tearing.
Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov dmitry.torokhov@gmail.com
v2: addressed Rafael's feedback by introducing device_set_driver() helper that does WRITE_ONCE() to prevent tearing.
So the code changes look OK to me now, but I would introduce device_set_driver() in a separate preliminary patch, to start with as a simple assignment.
Then, in the fix patch proper, I'd replace the assignment in device_set_driver() with WRITE_ONCE().
That would allow the fix itself to be distinguished from the tangentially related changes depended on by it.
I added Cc: stable however I do not think we need to worry too much about backporting it to [very] old kernels: the race window is very small, and in real life we do not unbind devices that often.
I believe there are more questionable places where we read dev->driver pointer, those need to be adjusted separately.
drivers/base/base.h | 18 ++++++++++++++++++ drivers/base/bus.c | 2 +- drivers/base/core.c | 34 +++++++++++++++++++++++++++++++--- drivers/base/dd.c | 7 +++---- 4 files changed, 53 insertions(+), 8 deletions(-)
diff --git a/drivers/base/base.h b/drivers/base/base.h index 8cf04a557bdb..ed2d7ccc7354 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -73,6 +73,7 @@ static inline void subsys_put(struct subsys_private *sp) kset_put(&sp->subsys); }
+struct subsys_private *bus_to_subsys(const struct bus_type *bus); struct subsys_private *class_to_subsys(const struct class *class);
struct driver_private { @@ -179,6 +180,23 @@ int driver_add_groups(const struct device_driver *drv, const struct attribute_gr void driver_remove_groups(const struct device_driver *drv, const struct attribute_group **groups); void device_driver_detach(struct device *dev);
+static inline void device_set_driver(struct device *dev, const struct device_driver *drv) +{
/*
* Majority (all?) read accesses to dev->driver happens either
* while holding device lock or in bus/driver code that is only
* invoked when the device is bound to a driver and there is no
* concern of the pointer being changed while it is being read.
* However when reading device's uevent file we read driver pointer
* without taking device lock (so we do not block there for
* arbitrary amount of time). We use WRITE_ONCE() here to prevent
* tearing so that READ_ONCE() can safely be used in uevent code.
*/
// FIXME - this cast should not be needed "soon"
WRITE_ONCE(dev->driver, (struct device_driver *)drv);
+}
int devres_release_all(struct device *dev); void device_block_probing(void); void device_unblock_probing(void); diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 6b9e65a42cd2..c8c7e0804024 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -57,7 +57,7 @@ static int __must_check bus_rescan_devices_helper(struct device *dev,
- NULL. A call to subsys_put() must be done when finished with the pointer in
- order for it to be properly freed.
*/ -static struct subsys_private *bus_to_subsys(const struct bus_type *bus) +struct subsys_private *bus_to_subsys(const struct bus_type *bus) { struct subsys_private *sp = NULL; struct kobject *kobj; diff --git a/drivers/base/core.c b/drivers/base/core.c index 9f4d4868e3b4..27fe69d06765 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2623,6 +2623,34 @@ static const char *dev_uevent_name(const struct kobject *kobj) return NULL; }
+/*
- Try filling "DRIVER=<name>" uevent variable for a device. Because this
- function may race with binding and unbinding device from a driver we need to
- be careful. Binding is generally safe, at worst we miss the fact that device
- is already bound to a driver (but the driver information that is delivered
- through uevents is best-effort, it may become obsolete as soon as it is
- generated anyways). Unbinding is more risky as driver transitioning to NULL,
- so READ_ONCE() should be used to make sure we are dealing with the same
- pointer, and to ensure that driver structure is not going to disappear from
- under us we take bus' drivers klist lock. The assumption that only registered
- driver can be bound to a device, and to unregister a driver bus code will
- take the same lock.
- */
+static void dev_driver_uevent(const struct device *dev, struct kobj_uevent_env *env) +{
struct subsys_private *sp = bus_to_subsys(dev->bus);
if (sp) {
scoped_guard(spinlock, &sp->klist_drivers.k_lock) {
struct device_driver *drv = READ_ONCE(dev->driver);
if (drv)
add_uevent_var(env, "DRIVER=%s", drv->name);
}
subsys_put(sp);
}
+}
static int dev_uevent(const struct kobject *kobj, struct kobj_uevent_env *env) { const struct device *dev = kobj_to_dev(kobj); @@ -2654,8 +2682,8 @@ static int dev_uevent(const struct kobject *kobj, struct kobj_uevent_env *env) if (dev->type && dev->type->name) add_uevent_var(env, "DEVTYPE=%s", dev->type->name);
if (dev->driver)
add_uevent_var(env, "DRIVER=%s", dev->driver->name);
/* Add "DRIVER=%s" variable if the device is bound to a driver */
dev_driver_uevent(dev, env); /* Add common DT information about the device */ of_device_uevent(dev, env);
@@ -3696,7 +3724,7 @@ int device_add(struct device *dev) device_pm_remove(dev); dpm_sysfs_remove(dev); DPMError:
dev->driver = NULL;
BusError: device_remove_attrs(dev);device_set_driver(dev, NULL); bus_remove_device(dev);
diff --git a/drivers/base/dd.c b/drivers/base/dd.c index f0e4b4aba885..b526e0e0f52d 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -550,7 +550,7 @@ static void device_unbind_cleanup(struct device *dev) arch_teardown_dma_ops(dev); kfree(dev->dma_range_map); dev->dma_range_map = NULL;
dev->driver = NULL;
device_set_driver(dev, NULL); dev_set_drvdata(dev, NULL); if (dev->pm_domain && dev->pm_domain->dismiss) dev->pm_domain->dismiss(dev);
@@ -629,8 +629,7 @@ static int really_probe(struct device *dev, const struct device_driver *drv) }
re_probe:
// FIXME - this cast should not be needed "soon"
dev->driver = (struct device_driver *)drv;
device_set_driver(dev, drv); /* If using pinctrl, bind pins now before probing */ ret = pinctrl_bind_pins(dev);
@@ -1014,7 +1013,7 @@ static int __device_attach(struct device *dev, bool allow_async) if (ret == 0) ret = 1; else {
dev->driver = NULL;
device_set_driver(dev, NULL); ret = 0; } } else {
-- 2.49.0.rc0.332.g42c0ae87b1-goog